From 761dd3640e4e11741c342fcf5fc869e09901cdb1 Mon Sep 17 00:00:00 2001 From: David Porter Date: Wed, 11 Jan 2023 16:05:25 -0800 Subject: [PATCH] deps: Bump to cAdvisor v0.47.1 Signed-off-by: David Porter --- .../github.com/mindprince/gonvml/LICENSE | 206 - go.mod | 7 +- go.sum | 22 +- staging/src/k8s.io/cloud-provider/go.mod | 2 +- staging/src/k8s.io/cloud-provider/go.sum | 11 +- staging/src/k8s.io/component-base/go.mod | 3 +- staging/src/k8s.io/component-base/go.sum | 12 +- staging/src/k8s.io/kubectl/go.mod | 2 +- staging/src/k8s.io/kubectl/go.sum | 12 +- .../google/cadvisor/accelerators/nvidia.go | 276 - .../cadvisor/container/common/helpers.go | 2 +- .../google/cadvisor/container/factory.go | 2 - .../google/cadvisor/info/v1/machine.go | 3 + .../google/cadvisor/machine/info.go | 6 + .../google/cadvisor/manager/container.go | 15 +- .../google/cadvisor/manager/manager.go | 15 - .../google/cadvisor/metrics/prometheus.go | 54 +- .../mindprince/gonvml/.travis.gofmt.sh | 7 - .../github.com/mindprince/gonvml/.travis.yml | 9 - vendor/github.com/mindprince/gonvml/LICENSE | 202 - vendor/github.com/mindprince/gonvml/Makefile | 23 - .../github.com/mindprince/gonvml/NVML_NOTICE | 32 - vendor/github.com/mindprince/gonvml/README.md | 19 - .../github.com/mindprince/gonvml/bindings.go | 524 -- .../mindprince/gonvml/bindings_nocgo.go | 115 - vendor/github.com/mindprince/gonvml/nvml.h | 5605 ----------------- vendor/github.com/moby/term/tc.go | 1 + vendor/github.com/moby/term/term.go | 26 +- vendor/github.com/moby/term/termios.go | 1 + vendor/github.com/moby/term/termios_bsd.go | 1 + vendor/github.com/moby/term/termios_nonbsd.go | 3 +- .../moby/term/windows/ansi_reader.go | 2 +- .../moby/term/windows/ansi_writer.go | 1 + .../github.com/moby/term/windows/console.go | 1 + vendor/github.com/moby/term/winsize.go | 1 + .../runtime-spec/specs-go/config.go | 107 +- vendor/modules.txt | 12 +- 37 files changed, 144 insertions(+), 7198 deletions(-) delete mode 100644 LICENSES/vendor/github.com/mindprince/gonvml/LICENSE delete mode 100644 vendor/github.com/google/cadvisor/accelerators/nvidia.go delete mode 100644 vendor/github.com/mindprince/gonvml/.travis.gofmt.sh delete mode 100644 vendor/github.com/mindprince/gonvml/.travis.yml delete mode 100644 vendor/github.com/mindprince/gonvml/LICENSE delete mode 100644 vendor/github.com/mindprince/gonvml/Makefile delete mode 100644 vendor/github.com/mindprince/gonvml/NVML_NOTICE delete mode 100644 vendor/github.com/mindprince/gonvml/README.md delete mode 100644 vendor/github.com/mindprince/gonvml/bindings.go delete mode 100644 vendor/github.com/mindprince/gonvml/bindings_nocgo.go delete mode 100644 vendor/github.com/mindprince/gonvml/nvml.h diff --git a/LICENSES/vendor/github.com/mindprince/gonvml/LICENSE b/LICENSES/vendor/github.com/mindprince/gonvml/LICENSE deleted file mode 100644 index 3b69d65f781..00000000000 --- a/LICENSES/vendor/github.com/mindprince/gonvml/LICENSE +++ /dev/null @@ -1,206 +0,0 @@ -= vendor/github.com/mindprince/gonvml licensed under: = - - - Apache License - Version 2.0, January 2004 - http://www.apache.org/licenses/ - - TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION - - 1. Definitions. - - "License" shall mean the terms and conditions for use, reproduction, - and distribution as defined by Sections 1 through 9 of this document. - - "Licensor" shall mean the copyright owner or entity authorized by - the copyright owner that is granting the License. - - "Legal Entity" shall mean the union of the acting entity and all - other entities that control, are controlled by, or are under common - control with that entity. For the purposes of this definition, - "control" means (i) the power, direct or indirect, to cause the - direction or management of such entity, whether by contract or - otherwise, or (ii) ownership of fifty percent (50%) or more of the - outstanding shares, or (iii) beneficial ownership of such entity. - - "You" (or "Your") shall mean an individual or Legal Entity - exercising permissions granted by this License. - - "Source" form shall mean the preferred form for making modifications, - including but not limited to software source code, documentation - source, and configuration files. - - "Object" form shall mean any form resulting from mechanical - transformation or translation of a Source form, including but - not limited to compiled object code, generated documentation, - and conversions to other media types. - - "Work" shall mean the work of authorship, whether in Source or - Object form, made available under the License, as indicated by a - copyright notice that is included in or attached to the work - (an example is provided in the Appendix below). - - "Derivative Works" shall mean any work, whether in Source or Object - form, that is based on (or derived from) the Work and for which the - editorial revisions, annotations, elaborations, or other modifications - represent, as a whole, an original work of authorship. For the purposes - of this License, Derivative Works shall not include works that remain - separable from, or merely link (or bind by name) to the interfaces of, - the Work and Derivative Works thereof. - - "Contribution" shall mean any work of authorship, including - the original version of the Work and any modifications or additions - to that Work or Derivative Works thereof, that is intentionally - submitted to Licensor for inclusion in the Work by the copyright owner - or by an individual or Legal Entity authorized to submit on behalf of - the copyright owner. For the purposes of this definition, "submitted" - means any form of electronic, verbal, or written communication sent - to the Licensor or its representatives, including but not limited to - communication on electronic mailing lists, source code control systems, - and issue tracking systems that are managed by, or on behalf of, the - Licensor for the purpose of discussing and improving the Work, but - excluding communication that is conspicuously marked or otherwise - designated in writing by the copyright owner as "Not a Contribution." - - "Contributor" shall mean Licensor and any individual or Legal Entity - on behalf of whom a Contribution has been received by Licensor and - subsequently incorporated within the Work. - - 2. Grant of Copyright License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - copyright license to reproduce, prepare Derivative Works of, - publicly display, publicly perform, sublicense, and distribute the - Work and such Derivative Works in Source or Object form. - - 3. Grant of Patent License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - (except as stated in this section) patent license to make, have made, - use, offer to sell, sell, import, and otherwise transfer the Work, - where such license applies only to those patent claims licensable - by such Contributor that are necessarily infringed by their - Contribution(s) alone or by combination of their Contribution(s) - with the Work to which such Contribution(s) was submitted. If You - institute patent litigation against any entity (including a - cross-claim or counterclaim in a lawsuit) alleging that the Work - or a Contribution incorporated within the Work constitutes direct - or contributory patent infringement, then any patent licenses - granted to You under this License for that Work shall terminate - as of the date such litigation is filed. - - 4. Redistribution. You may reproduce and distribute copies of the - Work or Derivative Works thereof in any medium, with or without - modifications, and in Source or Object form, provided that You - meet the following conditions: - - (a) You must give any other recipients of the Work or - Derivative Works a copy of this License; and - - (b) You must cause any modified files to carry prominent notices - stating that You changed the files; and - - (c) You must retain, in the Source form of any Derivative Works - that You distribute, all copyright, patent, trademark, and - attribution notices from the Source form of the Work, - excluding those notices that do not pertain to any part of - the Derivative Works; and - - (d) If the Work includes a "NOTICE" text file as part of its - distribution, then any Derivative Works that You distribute must - include a readable copy of the attribution notices contained - within such NOTICE file, excluding those notices that do not - pertain to any part of the Derivative Works, in at least one - of the following places: within a NOTICE text file distributed - as part of the Derivative Works; within the Source form or - documentation, if provided along with the Derivative Works; or, - within a display generated by the Derivative Works, if and - wherever such third-party notices normally appear. The contents - of the NOTICE file are for informational purposes only and - do not modify the License. You may add Your own attribution - notices within Derivative Works that You distribute, alongside - or as an addendum to the NOTICE text from the Work, provided - that such additional attribution notices cannot be construed - as modifying the License. - - You may add Your own copyright statement to Your modifications and - may provide additional or different license terms and conditions - for use, reproduction, or distribution of Your modifications, or - for any such Derivative Works as a whole, provided Your use, - reproduction, and distribution of the Work otherwise complies with - the conditions stated in this License. - - 5. Submission of Contributions. Unless You explicitly state otherwise, - any Contribution intentionally submitted for inclusion in the Work - by You to the Licensor shall be under the terms and conditions of - this License, without any additional terms or conditions. - Notwithstanding the above, nothing herein shall supersede or modify - the terms of any separate license agreement you may have executed - with Licensor regarding such Contributions. - - 6. Trademarks. This License does not grant permission to use the trade - names, trademarks, service marks, or product names of the Licensor, - except as required for reasonable and customary use in describing the - origin of the Work and reproducing the content of the NOTICE file. - - 7. Disclaimer of Warranty. Unless required by applicable law or - agreed to in writing, Licensor provides the Work (and each - Contributor provides its Contributions) on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or - implied, including, without limitation, any warranties or conditions - of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A - PARTICULAR PURPOSE. You are solely responsible for determining the - appropriateness of using or redistributing the Work and assume any - risks associated with Your exercise of permissions under this License. - - 8. Limitation of Liability. In no event and under no legal theory, - whether in tort (including negligence), contract, or otherwise, - unless required by applicable law (such as deliberate and grossly - negligent acts) or agreed to in writing, shall any Contributor be - liable to You for damages, including any direct, indirect, special, - incidental, or consequential damages of any character arising as a - result of this License or out of the use or inability to use the - Work (including but not limited to damages for loss of goodwill, - work stoppage, computer failure or malfunction, or any and all - other commercial damages or losses), even if such Contributor - has been advised of the possibility of such damages. - - 9. Accepting Warranty or Additional Liability. While redistributing - the Work or Derivative Works thereof, You may choose to offer, - and charge a fee for, acceptance of support, warranty, indemnity, - or other liability obligations and/or rights consistent with this - License. However, in accepting such obligations, You may act only - on Your own behalf and on Your sole responsibility, not on behalf - of any other Contributor, and only if You agree to indemnify, - defend, and hold each Contributor harmless for any liability - incurred by, or claims asserted against, such Contributor by reason - of your accepting any such warranty or additional liability. - - END OF TERMS AND CONDITIONS - - APPENDIX: How to apply the Apache License to your work. - - To apply the Apache License to your work, attach the following - boilerplate notice, with the fields enclosed by brackets "[]" - replaced with your own identifying information. (Don't include - the brackets!) The text should be enclosed in the appropriate - comment syntax for the file format. We also recommend that a - file or class name and description of purpose be included on the - same "printed page" as the copyright notice for easier - identification within third-party archives. - - Copyright [yyyy] [name of copyright owner] - - Licensed under the Apache License, Version 2.0 (the "License"); - you may not use this file except in compliance with the License. - You may obtain a copy of the License at - - http://www.apache.org/licenses/LICENSE-2.0 - - Unless required by applicable law or agreed to in writing, software - distributed under the License is distributed on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - See the License for the specific language governing permissions and - limitations under the License. - -= vendor/github.com/mindprince/gonvml/LICENSE 3b83ef96387f14655fc854ddc3c6bd57 diff --git a/go.mod b/go.mod index 122ad0f2568..29f0f189f3b 100644 --- a/go.mod +++ b/go.mod @@ -39,7 +39,7 @@ require ( github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da github.com/golang/mock v1.6.0 github.com/golang/protobuf v1.5.2 - github.com/google/cadvisor v0.46.0 + github.com/google/cadvisor v0.47.1 github.com/google/gnostic v0.5.7-v3refs github.com/google/go-cmp v0.5.9 github.com/google/gofuzz v1.1.0 @@ -192,20 +192,19 @@ require ( github.com/liggitt/tabwriter v0.0.0-20181228230101-89fcab3d43de // indirect github.com/mailru/easyjson v0.7.7 // indirect github.com/matttproud/golang_protobuf_extensions v1.0.2 // indirect - github.com/mindprince/gonvml v0.0.0-20190828220739-9ebdce4bb989 // indirect github.com/mistifyio/go-zfs v2.1.2-0.20190413222219-f784269be439+incompatible // indirect github.com/mitchellh/go-wordwrap v1.0.0 // indirect github.com/mitchellh/mapstructure v1.4.1 // indirect github.com/moby/spdystream v0.2.0 // indirect github.com/moby/sys/mountinfo v0.6.2 // indirect - github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae // indirect + github.com/moby/term v0.0.0-20221205130635-1aeaba878587 // indirect github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect github.com/modern-go/reflect2 v1.0.2 // indirect github.com/mohae/deepcopy v0.0.0-20170603005431-491d3605edfb // indirect github.com/monochromegane/go-gitignore v0.0.0-20200626010858-205db1a8cc00 // indirect github.com/mxk/go-flowrate v0.0.0-20140419014527-cca7078d478f // indirect github.com/opencontainers/go-digest v1.0.0 // indirect - github.com/opencontainers/runtime-spec v1.0.3-0.20210326190908-1c3f411f0417 // indirect + github.com/opencontainers/runtime-spec v1.0.3-0.20220909204839-494a5a6aca78 // indirect github.com/peterbourgon/diskv v2.0.1+incompatible // indirect github.com/pquerna/cachecontrol v0.1.0 // indirect github.com/prometheus/procfs v0.8.0 // indirect diff --git a/go.sum b/go.sum index 14a9feadbe8..1b427ec4180 100644 --- a/go.sum +++ b/go.sum @@ -196,8 +196,9 @@ github.com/cpuguy83/go-md2man/v2 v2.0.0/go.mod h1:maD7wRr/U5Z6m/iR4s+kqSMx2CaBsr github.com/cpuguy83/go-md2man/v2 v2.0.2 h1:p1EgwI/C7NhT0JmVkwCD2ZBK8j4aeHQX2pMHHBfMQ6w= github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o= github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E= -github.com/creack/pty v1.1.11 h1:07n33Z8lZxZ2qwegKbObQohDhXDQxiMMz1NOUGYlesw= github.com/creack/pty v1.1.11/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E= +github.com/creack/pty v1.1.18 h1:n56/Zwd5o6whRC5PMGretI4IdRLlmBXYNjScPaBgsbY= +github.com/creack/pty v1.1.18/go.mod h1:MOBLtS5ELjhRRrroQr9kyvTxUAFNvYEK993ew/Vr4O4= github.com/cyphar/filepath-securejoin v0.2.3 h1:YX6ebbZCZP7VkM3scTTokDgBL2TY741X51MTk3ycuNI= github.com/cyphar/filepath-securejoin v0.2.3/go.mod h1:aPGpWjXOXUn2NCNjFvBE6aRxGGx79pTxQpKOJNYHHl4= github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= @@ -210,8 +211,8 @@ github.com/dgryski/go-sip13 v0.0.0-20181026042036-e10d5fee7954/go.mod h1:vAd38F8 github.com/dnaeon/go-vcr v1.2.0 h1:zHCHvJYTMh1N7xnV7zf1m1GPBF9Ad0Jk/whtQ1663qI= github.com/docker/distribution v2.8.1+incompatible h1:Q50tZOPR6T/hjNsyc9g8/syEs6bk8XXApsHjKukMl68= github.com/docker/distribution v2.8.1+incompatible/go.mod h1:J2gT2udsDAN96Uj4KfcMRqY0/ypR+oyYUYmja8H+y+w= -github.com/docker/docker v20.10.18+incompatible h1:SN84VYXTBNGn92T/QwIRPlum9zfemfitN7pbsp26WSc= -github.com/docker/docker v20.10.18+incompatible/go.mod h1:eEKB0N0r5NX/I1kEveEz05bcu8tLC/8azJZsviup8Sk= +github.com/docker/docker v20.10.21+incompatible h1:UTLdBmHk3bEY+w8qeO5KttOhy6OmXWsl/FEet9Uswog= +github.com/docker/docker v20.10.21+incompatible/go.mod h1:eEKB0N0r5NX/I1kEveEz05bcu8tLC/8azJZsviup8Sk= github.com/docker/go-connections v0.4.0 h1:El9xVISelRB7BuFusrZozjnkIM5YnzCViNKohAFqRJQ= github.com/docker/go-connections v0.4.0/go.mod h1:Gbd7IOopHjR8Iph03tsViu4nIes5XhDvyHbTtUxmeec= github.com/docker/go-units v0.4.0/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk= @@ -352,8 +353,8 @@ github.com/google/btree v0.0.0-20180813153112-4030bb1f1f0c/go.mod h1:lNA+9X1NB3Z github.com/google/btree v1.0.0/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ= github.com/google/btree v1.0.1 h1:gK4Kx5IaGY9CD5sPJ36FHiBJ6ZXl0kilRiiCj+jdYp4= github.com/google/btree v1.0.1/go.mod h1:xXMiIv4Fb/0kKde4SpL7qlzvu5cMJDRkFDxJfI9uaxA= -github.com/google/cadvisor v0.46.0 h1:ryTIniqhN8/wR8UA1RuYSXHvsAtdpk/01XwTZtYHekY= -github.com/google/cadvisor v0.46.0/go.mod h1:YnCDnR8amaS0HoMEjheOI0TMPzFKCBLc30mciLEjwGI= +github.com/google/cadvisor v0.47.1 h1:YyKnRy/3myRNGOvF1bNF9FFnpjY7Gky5yKi/ZlN+BSo= +github.com/google/cadvisor v0.47.1/go.mod h1:iJdTjcjyKHjLCf7OSTzwP5GxdfrkPusw2x5bwGvuLUw= github.com/google/cel-go v0.12.6 h1:kjeKudqV0OygrAqA9fX6J55S8gj+Jre2tckIm5RoG4M= github.com/google/cel-go v0.12.6/go.mod h1:Jk7ljRzLBhkmiAwBoUxB1sZSCVBAzkqPF25olK/iRDw= github.com/google/gnostic v0.5.7-v3refs h1:FhTMOKj2VhjpouxvWJAV1TL304uMlb9zcDqkl6cEI54= @@ -504,8 +505,6 @@ github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5 github.com/matttproud/golang_protobuf_extensions v1.0.2 h1:hAHbPm5IJGijwng3PWk09JkG9WeqChjprR5s9bBZ+OM= github.com/matttproud/golang_protobuf_extensions v1.0.2/go.mod h1:BSXmuO+STAnVfrANrmjBb36TMTDstsz7MSK+HVaYKv4= github.com/miekg/dns v1.0.14/go.mod h1:W1PPwlIAgtquWBMBEV9nkV9Cazfe8ScdGz/Lj7v3Nrg= -github.com/mindprince/gonvml v0.0.0-20190828220739-9ebdce4bb989 h1:PS1dLCGtD8bb9RPKJrc8bS7qHL6JnW1CZvwzH9dPoUs= -github.com/mindprince/gonvml v0.0.0-20190828220739-9ebdce4bb989/go.mod h1:2eu9pRWp8mo84xCg6KswZ+USQHjwgRhNp06sozOdsTY= github.com/mistifyio/go-zfs v2.1.2-0.20190413222219-f784269be439+incompatible h1:aKW/4cBs+yK6gpqU3K/oIwk9Q/XICqd3zOX/UFuvqmk= github.com/mistifyio/go-zfs v2.1.2-0.20190413222219-f784269be439+incompatible/go.mod h1:8AuVvqP/mXw1px98n46wfvcGfQ4ci2FwoAjKYxuo3Z4= github.com/mitchellh/cli v1.0.0/go.mod h1:hNIlj7HEI86fIcpObd7a0FcrxTWetlwJDGcceTlRvqc= @@ -527,8 +526,8 @@ github.com/moby/spdystream v0.2.0/go.mod h1:f7i0iNDQJ059oMTcWxx8MA/zKFIuD/lY+0Gq github.com/moby/sys/mountinfo v0.5.0/go.mod h1:3bMD3Rg+zkqx8MRYPi7Pyb0Ie97QEBmdxbhnCLlSvSU= github.com/moby/sys/mountinfo v0.6.2 h1:BzJjoreD5BMFNmD9Rus6gdd1pLuecOFPt8wC+Vygl78= github.com/moby/sys/mountinfo v0.6.2/go.mod h1:IJb6JQeOklcdMU9F5xQ8ZALD+CUr5VlGpwtX+VE0rpI= -github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae h1:O4SWKdcHVCvYqyDV+9CJA1fcDN2L11Bule0iFy3YlAI= -github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae/go.mod h1:E2VnQOmVuvZB6UYnnDB0qG5Nq/1tD9acaOpo6xmt0Kw= +github.com/moby/term v0.0.0-20221205130635-1aeaba878587 h1:HfkjXDfhgVaN5rmueG8cL8KKeFNecRCXFhaJ2qZ5SKA= +github.com/moby/term v0.0.0-20221205130635-1aeaba878587/go.mod h1:8FzsFHVUBGZdbDsJw/ot+X+d5HLUbvklYLJ9uGfcI3Y= github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q= github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg= github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q= @@ -562,8 +561,9 @@ github.com/opencontainers/runc v1.1.4 h1:nRCz/8sKg6K6jgYAFLDlXzPeITBZJyX28DBVhWD github.com/opencontainers/runc v1.1.4/go.mod h1:1J5XiS+vdZ3wCyZybsuxXZWGrgSr8fFJHLXuG2PsnNg= github.com/opencontainers/runtime-spec v1.0.2/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0= github.com/opencontainers/runtime-spec v1.0.3-0.20200929063507-e6143ca7d51d/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0= -github.com/opencontainers/runtime-spec v1.0.3-0.20210326190908-1c3f411f0417 h1:3snG66yBm59tKhhSPQrQ/0bCrv1LQbKt40LnUPiUxdc= github.com/opencontainers/runtime-spec v1.0.3-0.20210326190908-1c3f411f0417/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0= +github.com/opencontainers/runtime-spec v1.0.3-0.20220909204839-494a5a6aca78 h1:R5M2qXZiK/mWPMT4VldCOiSL9HIAMuxQZWdG0CSM5+4= +github.com/opencontainers/runtime-spec v1.0.3-0.20220909204839-494a5a6aca78/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0= github.com/opencontainers/selinux v1.10.0 h1:rAiKF8hTcgLI3w0DHm6i0ylVVcOrlgR1kK99DRLDhyU= github.com/opencontainers/selinux v1.10.0/go.mod h1:2i0OySw99QjzBBQByd1Gr9gSjvuho1lHsJxIJ3gGbJI= github.com/opentracing/opentracing-go v1.1.0/go.mod h1:UkNAQd3GIcIGf0SeVgPpRdFStlNbqXla1AfSYxPUl2o= @@ -587,7 +587,6 @@ github.com/prometheus/client_golang v1.7.1/go.mod h1:PY5Wy2awLA44sXw4AOSfFBetzPP github.com/prometheus/client_golang v1.11.0/go.mod h1:Z6t4BnS23TR94PD6BsDNk8yVqroYurpAkEiz0P2BEV0= github.com/prometheus/client_golang v1.11.1/go.mod h1:Z6t4BnS23TR94PD6BsDNk8yVqroYurpAkEiz0P2BEV0= github.com/prometheus/client_golang v1.12.1/go.mod h1:3Z9XVyYiZYEO+YQWt3RD2R3jrbd179Rt297l4aS6nDY= -github.com/prometheus/client_golang v1.13.0/go.mod h1:vTeo+zgvILHsnnj/39Ou/1fPN5nJFOEMgftOUOmlvYQ= github.com/prometheus/client_golang v1.14.0 h1:nJdhIvne2eSX/XRAFV9PcvFFRbrjbcTUj0VP62TMhnw= github.com/prometheus/client_golang v1.14.0/go.mod h1:8vpkKitgIVNcqrRBWh1C4TIUQgYNtG/XQE4E/Zae36Y= github.com/prometheus/client_model v0.0.0-20180712105110-5c3871d89910/go.mod h1:MbSGuTsp3dbXC40dX6PRTWyKYBIrTGTE9sqQNg2J8bo= @@ -1206,7 +1205,6 @@ google.golang.org/grpc v1.40.0/go.mod h1:ogyxbiOoUXAkP+4+xa6PZSE9DZgIHtSpzjDTB9K google.golang.org/grpc v1.41.0/go.mod h1:U3l9uK9J0sini8mHphKoXyaqDA/8VyGnDee1zzIUK6k= google.golang.org/grpc v1.42.0/go.mod h1:k+4IHHFw41K8+bbowsex27ge2rCb65oeWqe4jJ590SU= google.golang.org/grpc v1.46.0/go.mod h1:vN9eftEi1UMyUsIF80+uQXhHjbXYbm0uXoFCACuMGWk= -google.golang.org/grpc v1.49.0/go.mod h1:ZgQEeidpAuNRZ8iRrlBKXZQP1ghovWIVhdJRyCDK+GI= google.golang.org/grpc v1.51.0 h1:E1eGv1FTqoLIdnBCZufiSHgKjlqG6fKFf6pPWtMTh8U= google.golang.org/grpc v1.51.0/go.mod h1:wgNDFcnuBGmxLKI/qn4T+m5BtEBYXJPvibbUPsAIPww= google.golang.org/grpc/cmd/protoc-gen-go-grpc v1.1.0/go.mod h1:6Kw0yEErY5E/yWrBtf03jp27GLLJujG4z/JK95pnjjw= diff --git a/staging/src/k8s.io/cloud-provider/go.mod b/staging/src/k8s.io/cloud-provider/go.mod index d6a6fffb4b6..544324f2aa5 100644 --- a/staging/src/k8s.io/cloud-provider/go.mod +++ b/staging/src/k8s.io/cloud-provider/go.mod @@ -55,7 +55,7 @@ require ( github.com/json-iterator/go v1.1.12 // indirect github.com/mailru/easyjson v0.7.7 // indirect github.com/matttproud/golang_protobuf_extensions v1.0.2 // indirect - github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae // indirect + github.com/moby/term v0.0.0-20221205130635-1aeaba878587 // indirect github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect github.com/modern-go/reflect2 v1.0.2 // indirect github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect diff --git a/staging/src/k8s.io/cloud-provider/go.sum b/staging/src/k8s.io/cloud-provider/go.sum index 139b2dde8be..80dd183bb98 100644 --- a/staging/src/k8s.io/cloud-provider/go.sum +++ b/staging/src/k8s.io/cloud-provider/go.sum @@ -81,8 +81,7 @@ github.com/coreos/go-systemd/v22 v22.3.2 h1:D9/bQk5vlXQFZ6Kwuu6zaiXJ9oTPe68++AzA github.com/coreos/go-systemd/v22 v22.3.2/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc= github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o= github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E= -github.com/creack/pty v1.1.11 h1:07n33Z8lZxZ2qwegKbObQohDhXDQxiMMz1NOUGYlesw= -github.com/creack/pty v1.1.11/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E= +github.com/creack/pty v1.1.18 h1:n56/Zwd5o6whRC5PMGretI4IdRLlmBXYNjScPaBgsbY= github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c= github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= @@ -250,8 +249,8 @@ github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJ github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0= github.com/matttproud/golang_protobuf_extensions v1.0.2 h1:hAHbPm5IJGijwng3PWk09JkG9WeqChjprR5s9bBZ+OM= github.com/matttproud/golang_protobuf_extensions v1.0.2/go.mod h1:BSXmuO+STAnVfrANrmjBb36TMTDstsz7MSK+HVaYKv4= -github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae h1:O4SWKdcHVCvYqyDV+9CJA1fcDN2L11Bule0iFy3YlAI= -github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae/go.mod h1:E2VnQOmVuvZB6UYnnDB0qG5Nq/1tD9acaOpo6xmt0Kw= +github.com/moby/term v0.0.0-20221205130635-1aeaba878587 h1:HfkjXDfhgVaN5rmueG8cL8KKeFNecRCXFhaJ2qZ5SKA= +github.com/moby/term v0.0.0-20221205130635-1aeaba878587/go.mod h1:8FzsFHVUBGZdbDsJw/ot+X+d5HLUbvklYLJ9uGfcI3Y= github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q= github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg= github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q= @@ -309,7 +308,6 @@ github.com/soheilhy/cmux v0.1.5 h1:jjzc5WVemNEDTLwv9tlmemhC73tI08BNOIGwBOo10Js= github.com/spaolacci/murmur3 v0.0.0-20180118202830-f09979ecbc72/go.mod h1:JwIasOWyU6f++ZhiEuf87xNszmSA2myDM2Kzu9HwQUA= github.com/spf13/cobra v1.6.0 h1:42a0n6jwCot1pUmomAp4T7DeMD+20LFv4Q54pxLf2LI= github.com/spf13/cobra v1.6.0/go.mod h1:IOw/AERYS7UzyrGinqmz6HLUo219MORXGxhbaJUqzrY= -github.com/spf13/pflag v1.0.3/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4= github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA= github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg= github.com/stoewer/go-strcase v1.2.0 h1:Z2iHWqGXH00XYgqDmNgQbIBxf3wrNq0F3feEy0ainaU= @@ -554,7 +552,6 @@ golang.org/x/tools v0.0.0-20190506145303-2d16b83fe98c/go.mod h1:RgjU9mgBXZiqYHBn golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q= golang.org/x/tools v0.0.0-20190606124116-d0a3d012864b/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc= golang.org/x/tools v0.0.0-20190621195816-6e04913cbbac/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc= -golang.org/x/tools v0.0.0-20190624222133-a101b041ded4/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc= golang.org/x/tools v0.0.0-20190628153133-6cdbf07be9d0/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc= golang.org/x/tools v0.0.0-20190816200558-6889da9d5479/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= golang.org/x/tools v0.0.0-20190911174233-4f2ddba30aff/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= @@ -713,8 +710,6 @@ gopkg.in/yaml.v3 v3.0.0-20200615113413-eeeca48fe776/go.mod h1:K4uyk7z7BCEPqu6E+C gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= -gotest.tools/v3 v3.0.2/go.mod h1:3SzNCllyD9/Y+b5r9JIKQ474KzkZyqLqEfYqMsX94Bk= -gotest.tools/v3 v3.0.3 h1:4AuOwCGf4lLR9u3YOe2awrHygurzhO/HeQ6laiA6Sx0= honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4= honnef.co/go/tools v0.0.0-20190106161140-3f1c8253044a/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4= honnef.co/go/tools v0.0.0-20190418001031-e561f6794a2a/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4= diff --git a/staging/src/k8s.io/component-base/go.mod b/staging/src/k8s.io/component-base/go.mod index 831cabca312..3099f09e9eb 100644 --- a/staging/src/k8s.io/component-base/go.mod +++ b/staging/src/k8s.io/component-base/go.mod @@ -9,7 +9,7 @@ require ( github.com/go-logr/logr v1.2.3 github.com/go-logr/zapr v1.2.3 github.com/google/go-cmp v0.5.9 - github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae + github.com/moby/term v0.0.0-20221205130635-1aeaba878587 github.com/prometheus/client_golang v1.14.0 github.com/prometheus/client_model v0.3.0 github.com/prometheus/common v0.37.0 @@ -75,7 +75,6 @@ require ( gopkg.in/inf.v0 v0.9.1 // indirect gopkg.in/yaml.v2 v2.4.0 // indirect gopkg.in/yaml.v3 v3.0.1 // indirect - gotest.tools/v3 v3.0.3 // indirect k8s.io/api v0.0.0 // indirect k8s.io/kube-openapi v0.0.0-20230109183929-3758b55a6596 // indirect sigs.k8s.io/structured-merge-diff/v4 v4.2.3 // indirect diff --git a/staging/src/k8s.io/component-base/go.sum b/staging/src/k8s.io/component-base/go.sum index 558ec1f4b63..e3d7cf370dd 100644 --- a/staging/src/k8s.io/component-base/go.sum +++ b/staging/src/k8s.io/component-base/go.sum @@ -71,8 +71,7 @@ github.com/cncf/xds/go v0.0.0-20211001041855-01bcc9b48dfe/go.mod h1:eXthEFrGJvWH github.com/cncf/xds/go v0.0.0-20211011173535-cb28da3451f1/go.mod h1:eXthEFrGJvWHgFFCl3hGmgk+/aYT6PnTQLykKQRLhEs= github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o= github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E= -github.com/creack/pty v1.1.11 h1:07n33Z8lZxZ2qwegKbObQohDhXDQxiMMz1NOUGYlesw= -github.com/creack/pty v1.1.11/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E= +github.com/creack/pty v1.1.18 h1:n56/Zwd5o6whRC5PMGretI4IdRLlmBXYNjScPaBgsbY= github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c= github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= @@ -221,8 +220,8 @@ github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJ github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0= github.com/matttproud/golang_protobuf_extensions v1.0.2 h1:hAHbPm5IJGijwng3PWk09JkG9WeqChjprR5s9bBZ+OM= github.com/matttproud/golang_protobuf_extensions v1.0.2/go.mod h1:BSXmuO+STAnVfrANrmjBb36TMTDstsz7MSK+HVaYKv4= -github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae h1:O4SWKdcHVCvYqyDV+9CJA1fcDN2L11Bule0iFy3YlAI= -github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae/go.mod h1:E2VnQOmVuvZB6UYnnDB0qG5Nq/1tD9acaOpo6xmt0Kw= +github.com/moby/term v0.0.0-20221205130635-1aeaba878587 h1:HfkjXDfhgVaN5rmueG8cL8KKeFNecRCXFhaJ2qZ5SKA= +github.com/moby/term v0.0.0-20221205130635-1aeaba878587/go.mod h1:8FzsFHVUBGZdbDsJw/ot+X+d5HLUbvklYLJ9uGfcI3Y= github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q= github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg= github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q= @@ -277,7 +276,6 @@ github.com/sirupsen/logrus v1.6.0/go.mod h1:7uNnSEd1DgxDLC74fIahvMZmmYsHGZGEOFrf github.com/spaolacci/murmur3 v0.0.0-20180118202830-f09979ecbc72/go.mod h1:JwIasOWyU6f++ZhiEuf87xNszmSA2myDM2Kzu9HwQUA= github.com/spf13/cobra v1.6.0 h1:42a0n6jwCot1pUmomAp4T7DeMD+20LFv4Q54pxLf2LI= github.com/spf13/cobra v1.6.0/go.mod h1:IOw/AERYS7UzyrGinqmz6HLUo219MORXGxhbaJUqzrY= -github.com/spf13/pflag v1.0.3/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4= github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA= github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg= github.com/stoewer/go-strcase v1.2.0/go.mod h1:IBiWB2sKIp3wVVQ3Y035++gc+knqhUQag1KpM8ahLw8= @@ -495,7 +493,6 @@ golang.org/x/tools v0.0.0-20190506145303-2d16b83fe98c/go.mod h1:RgjU9mgBXZiqYHBn golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q= golang.org/x/tools v0.0.0-20190606124116-d0a3d012864b/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc= golang.org/x/tools v0.0.0-20190621195816-6e04913cbbac/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc= -golang.org/x/tools v0.0.0-20190624222133-a101b041ded4/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc= golang.org/x/tools v0.0.0-20190628153133-6cdbf07be9d0/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc= golang.org/x/tools v0.0.0-20190816200558-6889da9d5479/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= golang.org/x/tools v0.0.0-20190911174233-4f2ddba30aff/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= @@ -648,9 +645,6 @@ gopkg.in/yaml.v3 v3.0.0-20200615113413-eeeca48fe776/go.mod h1:K4uyk7z7BCEPqu6E+C gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= -gotest.tools/v3 v3.0.2/go.mod h1:3SzNCllyD9/Y+b5r9JIKQ474KzkZyqLqEfYqMsX94Bk= -gotest.tools/v3 v3.0.3 h1:4AuOwCGf4lLR9u3YOe2awrHygurzhO/HeQ6laiA6Sx0= -gotest.tools/v3 v3.0.3/go.mod h1:Z7Lb0S5l+klDB31fvDQX8ss/FlKDxtlFlw3Oa8Ymbl8= honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4= honnef.co/go/tools v0.0.0-20190106161140-3f1c8253044a/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4= honnef.co/go/tools v0.0.0-20190418001031-e561f6794a2a/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4= diff --git a/staging/src/k8s.io/kubectl/go.mod b/staging/src/k8s.io/kubectl/go.mod index 2d4d1185113..088e1345ffc 100644 --- a/staging/src/k8s.io/kubectl/go.mod +++ b/staging/src/k8s.io/kubectl/go.mod @@ -20,7 +20,7 @@ require ( github.com/liggitt/tabwriter v0.0.0-20181228230101-89fcab3d43de github.com/lithammer/dedent v1.1.0 github.com/mitchellh/go-wordwrap v1.0.0 - github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae + github.com/moby/term v0.0.0-20221205130635-1aeaba878587 github.com/onsi/ginkgo/v2 v2.7.0 github.com/onsi/gomega v1.24.2 github.com/pkg/errors v0.9.1 diff --git a/staging/src/k8s.io/kubectl/go.sum b/staging/src/k8s.io/kubectl/go.sum index 4b03dd3445e..80167433414 100644 --- a/staging/src/k8s.io/kubectl/go.sum +++ b/staging/src/k8s.io/kubectl/go.sum @@ -48,8 +48,7 @@ github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDk github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc= github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o= github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E= -github.com/creack/pty v1.1.11 h1:07n33Z8lZxZ2qwegKbObQohDhXDQxiMMz1NOUGYlesw= -github.com/creack/pty v1.1.11/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E= +github.com/creack/pty v1.1.18 h1:n56/Zwd5o6whRC5PMGretI4IdRLlmBXYNjScPaBgsbY= github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c= github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= @@ -194,8 +193,8 @@ github.com/mitchellh/go-wordwrap v1.0.0 h1:6GlHJ/LTGMrIJbwgdqdl2eEH8o+Exx/0m8ir9 github.com/mitchellh/go-wordwrap v1.0.0/go.mod h1:ZXFpozHsX6DPmq2I0TCekCxypsnAUbP2oI0UX1GXzOo= github.com/moby/spdystream v0.2.0 h1:cjW1zVyyoiM0T7b6UoySUFqzXMoqRckQtXwGPiBhOM8= github.com/moby/spdystream v0.2.0/go.mod h1:f7i0iNDQJ059oMTcWxx8MA/zKFIuD/lY+0GqbN2Wy8c= -github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae h1:O4SWKdcHVCvYqyDV+9CJA1fcDN2L11Bule0iFy3YlAI= -github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae/go.mod h1:E2VnQOmVuvZB6UYnnDB0qG5Nq/1tD9acaOpo6xmt0Kw= +github.com/moby/term v0.0.0-20221205130635-1aeaba878587 h1:HfkjXDfhgVaN5rmueG8cL8KKeFNecRCXFhaJ2qZ5SKA= +github.com/moby/term v0.0.0-20221205130635-1aeaba878587/go.mod h1:8FzsFHVUBGZdbDsJw/ot+X+d5HLUbvklYLJ9uGfcI3Y= github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q= github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg= github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q= @@ -215,7 +214,6 @@ github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8 github.com/opencontainers/go-digest v1.0.0/go.mod h1:0JzlMkj0TRzQZfJkVvzbP0HBR3IKzErnv2BNG4W4MAM= github.com/peterbourgon/diskv v2.0.1+incompatible h1:UBdAOUP5p4RWqPBg048CAvpKN+vxiaj6gdUUzhl4XmI= github.com/peterbourgon/diskv v2.0.1+incompatible/go.mod h1:uqqh8zWWbv1HBMNONnaR/tNboyR3/BZd58JJSHlUSCU= -github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0= github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4= github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0= github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= @@ -227,7 +225,6 @@ github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQD github.com/sergi/go-diff v1.1.0 h1:we8PVUC3FE2uYfodKH/nBHMSetSfHDR6scGdBi+erh0= github.com/spf13/cobra v1.6.0 h1:42a0n6jwCot1pUmomAp4T7DeMD+20LFv4Q54pxLf2LI= github.com/spf13/cobra v1.6.0/go.mod h1:IOw/AERYS7UzyrGinqmz6HLUo219MORXGxhbaJUqzrY= -github.com/spf13/pflag v1.0.3/go.mod h1:DYY7MBk1bdzusC3SYhjObp+wFpr4gzcvqqNjLnInEg4= github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA= github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg= github.com/stoewer/go-strcase v1.2.0/go.mod h1:IBiWB2sKIp3wVVQ3Y035++gc+knqhUQag1KpM8ahLw8= @@ -396,7 +393,6 @@ golang.org/x/tools v0.0.0-20190506145303-2d16b83fe98c/go.mod h1:RgjU9mgBXZiqYHBn golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q= golang.org/x/tools v0.0.0-20190606124116-d0a3d012864b/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc= golang.org/x/tools v0.0.0-20190621195816-6e04913cbbac/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc= -golang.org/x/tools v0.0.0-20190624222133-a101b041ded4/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc= golang.org/x/tools v0.0.0-20190628153133-6cdbf07be9d0/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc= golang.org/x/tools v0.0.0-20190816200558-6889da9d5479/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= golang.org/x/tools v0.0.0-20190911174233-4f2ddba30aff/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo= @@ -528,8 +524,6 @@ gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C gopkg.in/yaml.v3 v3.0.0-20200615113413-eeeca48fe776/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= -gotest.tools/v3 v3.0.2/go.mod h1:3SzNCllyD9/Y+b5r9JIKQ474KzkZyqLqEfYqMsX94Bk= -gotest.tools/v3 v3.0.3 h1:4AuOwCGf4lLR9u3YOe2awrHygurzhO/HeQ6laiA6Sx0= honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4= honnef.co/go/tools v0.0.0-20190106161140-3f1c8253044a/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4= honnef.co/go/tools v0.0.0-20190418001031-e561f6794a2a/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4= diff --git a/vendor/github.com/google/cadvisor/accelerators/nvidia.go b/vendor/github.com/google/cadvisor/accelerators/nvidia.go deleted file mode 100644 index 226b78dd46e..00000000000 --- a/vendor/github.com/google/cadvisor/accelerators/nvidia.go +++ /dev/null @@ -1,276 +0,0 @@ -// Copyright 2017 Google Inc. All Rights Reserved. -// -// Licensed under the Apache License, Version 2.0 (the "License"); -// you may not use this file except in compliance with the License. -// You may obtain a copy of the License at -// -// http://www.apache.org/licenses/LICENSE-2.0 -// -// Unless required by applicable law or agreed to in writing, software -// distributed under the License is distributed on an "AS IS" BASIS, -// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -// See the License for the specific language governing permissions and -// limitations under the License. - -package accelerators - -import ( - "bufio" - "fmt" - "io/ioutil" - "os" - "path/filepath" - "strconv" - "strings" - "sync" - "time" - - "github.com/google/cadvisor/container" - info "github.com/google/cadvisor/info/v1" - "github.com/google/cadvisor/stats" - - "github.com/mindprince/gonvml" - "k8s.io/klog/v2" -) - -type nvidiaManager struct { - sync.Mutex - - // true if there are NVIDIA devices present on the node - devicesPresent bool - - // true if the NVML library (libnvidia-ml.so.1) was loaded successfully - nvmlInitialized bool - - // nvidiaDevices is a map from device minor number to a handle that can be used to get metrics about the device - nvidiaDevices map[int]gonvml.Device -} - -var sysFsPCIDevicesPath = "/sys/bus/pci/devices/" - -const nvidiaVendorID = "0x10de" - -func NewNvidiaManager(includedMetrics container.MetricSet) stats.Manager { - if !includedMetrics.Has(container.AcceleratorUsageMetrics) { - klog.V(2).Info("NVIDIA GPU metrics disabled") - return &stats.NoopManager{} - } - - manager := &nvidiaManager{} - err := manager.setup() - if err != nil { - klog.V(2).Infof("NVIDIA setup failed: %s", err) - } - return manager -} - -// setup initializes NVML if NVIDIA devices are present on the node. -func (nm *nvidiaManager) setup() error { - if !detectDevices(nvidiaVendorID) { - return fmt.Errorf("no NVIDIA devices found") - } - - nm.devicesPresent = true - - return initializeNVML(nm) -} - -// detectDevices returns true if a device with given pci id is present on the node. -func detectDevices(vendorID string) bool { - devices, err := ioutil.ReadDir(sysFsPCIDevicesPath) - if err != nil { - klog.Warningf("Error reading %q: %v", sysFsPCIDevicesPath, err) - return false - } - - for _, device := range devices { - vendorPath := filepath.Join(sysFsPCIDevicesPath, device.Name(), "vendor") - content, err := ioutil.ReadFile(vendorPath) - if err != nil { - klog.V(4).Infof("Error while reading %q: %v", vendorPath, err) - continue - } - if strings.EqualFold(strings.TrimSpace(string(content)), vendorID) { - klog.V(3).Infof("Found device with vendorID %q", vendorID) - return true - } - } - return false -} - -// initializeNVML initializes the NVML library and sets up the nvmlDevices map. -// This is defined as a variable to help in testing. -var initializeNVML = func(nm *nvidiaManager) error { - if err := gonvml.Initialize(); err != nil { - // This is under a logging level because otherwise we may cause - // log spam if the drivers/nvml is not installed on the system. - return fmt.Errorf("Could not initialize NVML: %v", err) - } - nm.nvmlInitialized = true - numDevices, err := gonvml.DeviceCount() - if err != nil { - return fmt.Errorf("GPU metrics would not be available. Failed to get the number of NVIDIA devices: %v", err) - } - if numDevices == 0 { - return nil - } - klog.V(1).Infof("NVML initialized. Number of NVIDIA devices: %v", numDevices) - nm.nvidiaDevices = make(map[int]gonvml.Device, numDevices) - for i := 0; i < int(numDevices); i++ { - device, err := gonvml.DeviceHandleByIndex(uint(i)) - if err != nil { - return fmt.Errorf("Failed to get NVIDIA device handle %d: %v", i, err) - } - minorNumber, err := device.MinorNumber() - if err != nil { - return fmt.Errorf("Failed to get NVIDIA device minor number: %v", err) - } - nm.nvidiaDevices[int(minorNumber)] = device - } - return nil -} - -// Destroy shuts down NVML. -func (nm *nvidiaManager) Destroy() { - if nm.nvmlInitialized { - err := gonvml.Shutdown() - if err != nil { - klog.Warningf("nvml library shutdown failed: %s", err) - } - } -} - -// GetCollector returns a collector that can fetch NVIDIA gpu metrics for NVIDIA devices -// present in the devices.list file in the given devicesCgroupPath. -func (nm *nvidiaManager) GetCollector(devicesCgroupPath string) (stats.Collector, error) { - nc := &nvidiaCollector{} - - if !nm.devicesPresent { - return &stats.NoopCollector{}, nil - } - // Makes sure that we don't call initializeNVML() concurrently and - // that we only call initializeNVML() when it's not initialized. - nm.Lock() - if !nm.nvmlInitialized { - err := initializeNVML(nm) - if err != nil { - nm.Unlock() - return &stats.NoopCollector{}, err - } - } - nm.Unlock() - if len(nm.nvidiaDevices) == 0 { - return &stats.NoopCollector{}, nil - } - nvidiaMinorNumbers, err := parseDevicesCgroup(devicesCgroupPath) - if err != nil { - return &stats.NoopCollector{}, err - } - - for _, minor := range nvidiaMinorNumbers { - device, ok := nm.nvidiaDevices[minor] - if !ok { - return &stats.NoopCollector{}, fmt.Errorf("NVIDIA device minor number %d not found in cached devices", minor) - } - nc.devices = append(nc.devices, device) - } - return nc, nil -} - -// parseDevicesCgroup parses the devices cgroup devices.list file for the container -// and returns a list of minor numbers corresponding to NVIDIA GPU devices that the -// container is allowed to access. In cases where the container has access to all -// devices or all NVIDIA devices but the devices are not enumerated separately in -// the devices.list file, we return an empty list. -// This is defined as a variable to help in testing. -var parseDevicesCgroup = func(devicesCgroupPath string) ([]int, error) { - // Always return a non-nil slice - nvidiaMinorNumbers := []int{} - - devicesList := filepath.Join(devicesCgroupPath, "devices.list") - f, err := os.Open(devicesList) - if err != nil { - return nvidiaMinorNumbers, fmt.Errorf("error while opening devices cgroup file %q: %v", devicesList, err) - } - defer f.Close() - - s := bufio.NewScanner(f) - - // See https://www.kernel.org/doc/Documentation/cgroup-v1/devices.txt for the file format - for s.Scan() { - text := s.Text() - - fields := strings.Fields(text) - if len(fields) != 3 { - return nvidiaMinorNumbers, fmt.Errorf("invalid devices cgroup entry %q: must contain three whitespace-separated fields", text) - } - - // Split the second field to find out major:minor numbers - majorMinor := strings.Split(fields[1], ":") - if len(majorMinor) != 2 { - return nvidiaMinorNumbers, fmt.Errorf("invalid devices cgroup entry %q: second field should have one colon", text) - } - - // NVIDIA graphics devices are character devices with major number 195. - // https://github.com/torvalds/linux/blob/v4.13/Documentation/admin-guide/devices.txt#L2583 - if fields[0] == "c" && majorMinor[0] == "195" { - minorNumber, err := strconv.Atoi(majorMinor[1]) - if err != nil { - return nvidiaMinorNumbers, fmt.Errorf("invalid devices cgroup entry %q: minor number is not integer", text) - } - // We don't want devices like nvidiactl (195:255) and nvidia-modeset (195:254) - if minorNumber < 128 { - nvidiaMinorNumbers = append(nvidiaMinorNumbers, minorNumber) - } - // We are ignoring the "195:*" case - // where the container has access to all NVIDIA devices on the machine. - } - // We are ignoring the "*:*" case - // where the container has access to all devices on the machine. - } - return nvidiaMinorNumbers, nil -} - -type nvidiaCollector struct { - // Exposed for testing - devices []gonvml.Device - - stats.NoopDestroy -} - -func NewNvidiaCollector(devices []gonvml.Device) stats.Collector { - return &nvidiaCollector{devices: devices} -} - -// UpdateStats updates the stats for NVIDIA GPUs (if any) attached to the container. -func (nc *nvidiaCollector) UpdateStats(stats *info.ContainerStats) error { - for _, device := range nc.devices { - model, err := device.Name() - if err != nil { - return fmt.Errorf("error while getting gpu name: %v", err) - } - uuid, err := device.UUID() - if err != nil { - return fmt.Errorf("error while getting gpu uuid: %v", err) - } - memoryTotal, memoryUsed, err := device.MemoryInfo() - if err != nil { - return fmt.Errorf("error while getting gpu memory info: %v", err) - } - //TODO: Use housekeepingInterval - utilizationGPU, err := device.AverageGPUUtilization(10 * time.Second) - if err != nil { - return fmt.Errorf("error while getting gpu utilization: %v", err) - } - - stats.Accelerators = append(stats.Accelerators, info.AcceleratorStats{ - Make: "nvidia", - Model: model, - ID: uuid, - MemoryTotal: memoryTotal, - MemoryUsed: memoryUsed, - DutyCycle: uint64(utilizationGPU), - }) - } - return nil -} diff --git a/vendor/github.com/google/cadvisor/container/common/helpers.go b/vendor/github.com/google/cadvisor/container/common/helpers.go index e028f279cfc..7248f3b0b84 100644 --- a/vendor/github.com/google/cadvisor/container/common/helpers.go +++ b/vendor/github.com/google/cadvisor/container/common/helpers.go @@ -172,7 +172,7 @@ func getSpecInternal(cgroupPaths map[string]string, machineInfoFactory info.Mach if cgroup2UnifiedMode { if utils.FileExists(path.Join(memoryRoot, "memory.max")) { spec.HasMemory = true - spec.Memory.Reservation = readUInt64(memoryRoot, "memory.high") + spec.Memory.Reservation = readUInt64(memoryRoot, "memory.min") spec.Memory.Limit = readUInt64(memoryRoot, "memory.max") spec.Memory.SwapLimit = readUInt64(memoryRoot, "memory.swap.max") } diff --git a/vendor/github.com/google/cadvisor/container/factory.go b/vendor/github.com/google/cadvisor/container/factory.go index 8f32f8c6af7..226a6fa6e5d 100644 --- a/vendor/github.com/google/cadvisor/container/factory.go +++ b/vendor/github.com/google/cadvisor/container/factory.go @@ -57,7 +57,6 @@ const ( NetworkTcpUsageMetrics MetricKind = "tcp" NetworkAdvancedTcpUsageMetrics MetricKind = "advtcp" NetworkUdpUsageMetrics MetricKind = "udp" - AcceleratorUsageMetrics MetricKind = "accelerator" AppMetrics MetricKind = "app" ProcessMetrics MetricKind = "process" HugetlbUsageMetrics MetricKind = "hugetlb" @@ -78,7 +77,6 @@ var AllMetrics = MetricSet{ MemoryNumaMetrics: struct{}{}, CpuLoadMetrics: struct{}{}, DiskIOMetrics: struct{}{}, - AcceleratorUsageMetrics: struct{}{}, DiskUsageMetrics: struct{}{}, NetworkUsageMetrics: struct{}{}, NetworkTcpUsageMetrics: struct{}{}, diff --git a/vendor/github.com/google/cadvisor/info/v1/machine.go b/vendor/github.com/google/cadvisor/info/v1/machine.go index 95d8b9ac4c9..47a43604053 100644 --- a/vendor/github.com/google/cadvisor/info/v1/machine.go +++ b/vendor/github.com/google/cadvisor/info/v1/machine.go @@ -197,6 +197,9 @@ type MachineInfo struct { // The amount of memory (in bytes) in this machine MemoryCapacity uint64 `json:"memory_capacity"` + // The amount of swap (in bytes) in this machine + SwapCapacity uint64 `json:"swap_capacity"` + // Memory capacity and number of DIMMs by memory type MemoryByType map[string]*MemoryInfo `json:"memory_by_type"` diff --git a/vendor/github.com/google/cadvisor/machine/info.go b/vendor/github.com/google/cadvisor/machine/info.go index 0550a5fa299..a7a3d3e0cdb 100644 --- a/vendor/github.com/google/cadvisor/machine/info.go +++ b/vendor/github.com/google/cadvisor/machine/info.go @@ -79,6 +79,11 @@ func Info(sysFs sysfs.SysFs, fsInfo fs.FsInfo, inHostNamespace bool) (*info.Mach return nil, err } + swapCapacity, err := GetMachineSwapCapacity() + if err != nil { + return nil, err + } + nvmInfo, err := nvm.GetInfo() if err != nil { return nil, err @@ -128,6 +133,7 @@ func Info(sysFs sysfs.SysFs, fsInfo fs.FsInfo, inHostNamespace bool) (*info.Mach CpuFrequency: clockSpeed, MemoryCapacity: memoryCapacity, MemoryByType: memoryByType, + SwapCapacity: swapCapacity, NVMInfo: nvmInfo, HugePages: hugePagesInfo, DiskMap: diskMap, diff --git a/vendor/github.com/google/cadvisor/manager/container.go b/vendor/github.com/google/cadvisor/manager/container.go index a5f2040a6fa..861e230cfc4 100644 --- a/vendor/github.com/google/cadvisor/manager/container.go +++ b/vendor/github.com/google/cadvisor/manager/container.go @@ -40,6 +40,7 @@ import ( "github.com/google/cadvisor/utils/cpuload" "github.com/docker/go-units" + "k8s.io/klog/v2" "k8s.io/utils/clock" ) @@ -96,9 +97,6 @@ type containerData struct { // Runs custom metric collectors. collectorManager collector.CollectorManager - // nvidiaCollector updates stats for Nvidia GPUs attached to the container. - nvidiaCollector stats.Collector - // perfCollector updates stats for perf_event cgroup controller. perfCollector stats.Collector @@ -448,7 +446,6 @@ func newContainerData(containerName string, memoryCache *memory.InMemoryCache, h onDemandChan: make(chan chan struct{}, 100), clock: clock, perfCollector: &stats.NoopCollector{}, - nvidiaCollector: &stats.NoopCollector{}, resctrlCollector: &stats.NoopCollector{}, } cont.info.ContainerReference = ref @@ -688,12 +685,6 @@ func (cd *containerData) updateStats() error { } } - var nvidiaStatsErr error - if cd.nvidiaCollector != nil { - // This updates the Accelerators field of the stats struct - nvidiaStatsErr = cd.nvidiaCollector.UpdateStats(stats) - } - perfStatsErr := cd.perfCollector.UpdateStats(stats) resctrlStatsErr := cd.resctrlCollector.UpdateStats(stats) @@ -718,10 +709,6 @@ func (cd *containerData) updateStats() error { if statsErr != nil { return statsErr } - if nvidiaStatsErr != nil { - klog.Errorf("error occurred while collecting nvidia stats for container %s: %s", cInfo.Name, err) - return nvidiaStatsErr - } if perfStatsErr != nil { klog.Errorf("error occurred while collecting perf stats for container %s: %s", cInfo.Name, err) return perfStatsErr diff --git a/vendor/github.com/google/cadvisor/manager/manager.go b/vendor/github.com/google/cadvisor/manager/manager.go index 980e0a3863a..8c4396d65dc 100644 --- a/vendor/github.com/google/cadvisor/manager/manager.go +++ b/vendor/github.com/google/cadvisor/manager/manager.go @@ -27,7 +27,6 @@ import ( "sync/atomic" "time" - "github.com/google/cadvisor/accelerators" "github.com/google/cadvisor/cache/memory" "github.com/google/cadvisor/collector" "github.com/google/cadvisor/container" @@ -199,7 +198,6 @@ func New(memoryCache *memory.InMemoryCache, sysfs sysfs.SysFs, houskeepingConfig containerWatchers: []watcher.ContainerWatcher{}, eventsChannel: eventsChannel, collectorHTTPClient: collectorHTTPClient, - nvidiaManager: accelerators.NewNvidiaManager(includedMetricsSet), rawContainerCgroupPathPrefixWhiteList: rawContainerCgroupPathPrefixWhiteList, containerEnvMetadataWhiteList: containerEnvMetadataWhiteList, } @@ -259,7 +257,6 @@ type manager struct { containerWatchers []watcher.ContainerWatcher eventsChannel chan watcher.ContainerEvent collectorHTTPClient *http.Client - nvidiaManager stats.Manager perfManager stats.Manager resctrlManager resctrl.Manager // List of raw container cgroup path prefix whitelist. @@ -327,7 +324,6 @@ func (m *manager) Start() error { } func (m *manager) Stop() error { - defer m.nvidiaManager.Destroy() defer m.destroyCollectors() // Stop and wait on all quit channels. for i, c := range m.quitChannels { @@ -934,17 +930,6 @@ func (m *manager) createContainerLocked(containerName string, watchSource watche return err } - if !cgroups.IsCgroup2UnifiedMode() { - devicesCgroupPath, err := handler.GetCgroupPath("devices") - if err != nil { - klog.Warningf("Error getting devices cgroup path: %v", err) - } else { - cont.nvidiaCollector, err = m.nvidiaManager.GetCollector(devicesCgroupPath) - if err != nil { - klog.V(4).Infof("GPU metrics may be unavailable/incomplete for container %s: %s", cont.info.Name, err) - } - } - } if m.includedMetrics.Has(container.PerfMetrics) { perfCgroupPath, err := handler.GetCgroupPath("perf_event") if err != nil { diff --git a/vendor/github.com/google/cadvisor/metrics/prometheus.go b/vendor/github.com/google/cadvisor/metrics/prometheus.go index 04c8d27e8f7..75fc2905fde 100644 --- a/vendor/github.com/google/cadvisor/metrics/prometheus.go +++ b/vendor/github.com/google/cadvisor/metrics/prometheus.go @@ -25,6 +25,7 @@ import ( v2 "github.com/google/cadvisor/info/v2" "github.com/prometheus/client_golang/prometheus" + "k8s.io/klog/v2" "k8s.io/utils/clock" ) @@ -492,59 +493,6 @@ func NewPrometheusCollector(i infoProvider, f ContainerLabelsFunc, includedMetri }, }...) } - if includedMetrics.Has(container.AcceleratorUsageMetrics) { - c.containerMetrics = append(c.containerMetrics, []containerMetric{ - { - name: "container_accelerator_memory_total_bytes", - help: "Total accelerator memory.", - valueType: prometheus.GaugeValue, - extraLabels: []string{"make", "model", "acc_id"}, - getValues: func(s *info.ContainerStats) metricValues { - values := make(metricValues, 0, len(s.Accelerators)) - for _, value := range s.Accelerators { - values = append(values, metricValue{ - value: float64(value.MemoryTotal), - labels: []string{value.Make, value.Model, value.ID}, - timestamp: s.Timestamp, - }) - } - return values - }, - }, { - name: "container_accelerator_memory_used_bytes", - help: "Total accelerator memory allocated.", - valueType: prometheus.GaugeValue, - extraLabels: []string{"make", "model", "acc_id"}, - getValues: func(s *info.ContainerStats) metricValues { - values := make(metricValues, 0, len(s.Accelerators)) - for _, value := range s.Accelerators { - values = append(values, metricValue{ - value: float64(value.MemoryUsed), - labels: []string{value.Make, value.Model, value.ID}, - timestamp: s.Timestamp, - }) - } - return values - }, - }, { - name: "container_accelerator_duty_cycle", - help: "Percent of time over the past sample period during which the accelerator was actively processing.", - valueType: prometheus.GaugeValue, - extraLabels: []string{"make", "model", "acc_id"}, - getValues: func(s *info.ContainerStats) metricValues { - values := make(metricValues, 0, len(s.Accelerators)) - for _, value := range s.Accelerators { - values = append(values, metricValue{ - value: float64(value.DutyCycle), - labels: []string{value.Make, value.Model, value.ID}, - timestamp: s.Timestamp, - }) - } - return values - }, - }, - }...) - } if includedMetrics.Has(container.DiskUsageMetrics) { c.containerMetrics = append(c.containerMetrics, []containerMetric{ { diff --git a/vendor/github.com/mindprince/gonvml/.travis.gofmt.sh b/vendor/github.com/mindprince/gonvml/.travis.gofmt.sh deleted file mode 100644 index 646934bb404..00000000000 --- a/vendor/github.com/mindprince/gonvml/.travis.gofmt.sh +++ /dev/null @@ -1,7 +0,0 @@ -#!/bin/bash - -if [ -n "$(gofmt -s -l .)" ]; then - echo "Go code is not properly formatted:" - gofmt -s -d -e . - exit 1 -fi diff --git a/vendor/github.com/mindprince/gonvml/.travis.yml b/vendor/github.com/mindprince/gonvml/.travis.yml deleted file mode 100644 index d45dc3c918c..00000000000 --- a/vendor/github.com/mindprince/gonvml/.travis.yml +++ /dev/null @@ -1,9 +0,0 @@ -language: go - -go: - - "1.8" - - "1.9" - - "1.10" - -script: - - make presubmit diff --git a/vendor/github.com/mindprince/gonvml/LICENSE b/vendor/github.com/mindprince/gonvml/LICENSE deleted file mode 100644 index d6456956733..00000000000 --- a/vendor/github.com/mindprince/gonvml/LICENSE +++ /dev/null @@ -1,202 +0,0 @@ - - Apache License - Version 2.0, January 2004 - http://www.apache.org/licenses/ - - TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION - - 1. Definitions. - - "License" shall mean the terms and conditions for use, reproduction, - and distribution as defined by Sections 1 through 9 of this document. - - "Licensor" shall mean the copyright owner or entity authorized by - the copyright owner that is granting the License. - - "Legal Entity" shall mean the union of the acting entity and all - other entities that control, are controlled by, or are under common - control with that entity. For the purposes of this definition, - "control" means (i) the power, direct or indirect, to cause the - direction or management of such entity, whether by contract or - otherwise, or (ii) ownership of fifty percent (50%) or more of the - outstanding shares, or (iii) beneficial ownership of such entity. - - "You" (or "Your") shall mean an individual or Legal Entity - exercising permissions granted by this License. - - "Source" form shall mean the preferred form for making modifications, - including but not limited to software source code, documentation - source, and configuration files. - - "Object" form shall mean any form resulting from mechanical - transformation or translation of a Source form, including but - not limited to compiled object code, generated documentation, - and conversions to other media types. - - "Work" shall mean the work of authorship, whether in Source or - Object form, made available under the License, as indicated by a - copyright notice that is included in or attached to the work - (an example is provided in the Appendix below). - - "Derivative Works" shall mean any work, whether in Source or Object - form, that is based on (or derived from) the Work and for which the - editorial revisions, annotations, elaborations, or other modifications - represent, as a whole, an original work of authorship. For the purposes - of this License, Derivative Works shall not include works that remain - separable from, or merely link (or bind by name) to the interfaces of, - the Work and Derivative Works thereof. - - "Contribution" shall mean any work of authorship, including - the original version of the Work and any modifications or additions - to that Work or Derivative Works thereof, that is intentionally - submitted to Licensor for inclusion in the Work by the copyright owner - or by an individual or Legal Entity authorized to submit on behalf of - the copyright owner. For the purposes of this definition, "submitted" - means any form of electronic, verbal, or written communication sent - to the Licensor or its representatives, including but not limited to - communication on electronic mailing lists, source code control systems, - and issue tracking systems that are managed by, or on behalf of, the - Licensor for the purpose of discussing and improving the Work, but - excluding communication that is conspicuously marked or otherwise - designated in writing by the copyright owner as "Not a Contribution." - - "Contributor" shall mean Licensor and any individual or Legal Entity - on behalf of whom a Contribution has been received by Licensor and - subsequently incorporated within the Work. - - 2. Grant of Copyright License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - copyright license to reproduce, prepare Derivative Works of, - publicly display, publicly perform, sublicense, and distribute the - Work and such Derivative Works in Source or Object form. - - 3. Grant of Patent License. Subject to the terms and conditions of - this License, each Contributor hereby grants to You a perpetual, - worldwide, non-exclusive, no-charge, royalty-free, irrevocable - (except as stated in this section) patent license to make, have made, - use, offer to sell, sell, import, and otherwise transfer the Work, - where such license applies only to those patent claims licensable - by such Contributor that are necessarily infringed by their - Contribution(s) alone or by combination of their Contribution(s) - with the Work to which such Contribution(s) was submitted. If You - institute patent litigation against any entity (including a - cross-claim or counterclaim in a lawsuit) alleging that the Work - or a Contribution incorporated within the Work constitutes direct - or contributory patent infringement, then any patent licenses - granted to You under this License for that Work shall terminate - as of the date such litigation is filed. - - 4. Redistribution. You may reproduce and distribute copies of the - Work or Derivative Works thereof in any medium, with or without - modifications, and in Source or Object form, provided that You - meet the following conditions: - - (a) You must give any other recipients of the Work or - Derivative Works a copy of this License; and - - (b) You must cause any modified files to carry prominent notices - stating that You changed the files; and - - (c) You must retain, in the Source form of any Derivative Works - that You distribute, all copyright, patent, trademark, and - attribution notices from the Source form of the Work, - excluding those notices that do not pertain to any part of - the Derivative Works; and - - (d) If the Work includes a "NOTICE" text file as part of its - distribution, then any Derivative Works that You distribute must - include a readable copy of the attribution notices contained - within such NOTICE file, excluding those notices that do not - pertain to any part of the Derivative Works, in at least one - of the following places: within a NOTICE text file distributed - as part of the Derivative Works; within the Source form or - documentation, if provided along with the Derivative Works; or, - within a display generated by the Derivative Works, if and - wherever such third-party notices normally appear. The contents - of the NOTICE file are for informational purposes only and - do not modify the License. You may add Your own attribution - notices within Derivative Works that You distribute, alongside - or as an addendum to the NOTICE text from the Work, provided - that such additional attribution notices cannot be construed - as modifying the License. - - You may add Your own copyright statement to Your modifications and - may provide additional or different license terms and conditions - for use, reproduction, or distribution of Your modifications, or - for any such Derivative Works as a whole, provided Your use, - reproduction, and distribution of the Work otherwise complies with - the conditions stated in this License. - - 5. Submission of Contributions. Unless You explicitly state otherwise, - any Contribution intentionally submitted for inclusion in the Work - by You to the Licensor shall be under the terms and conditions of - this License, without any additional terms or conditions. - Notwithstanding the above, nothing herein shall supersede or modify - the terms of any separate license agreement you may have executed - with Licensor regarding such Contributions. - - 6. Trademarks. This License does not grant permission to use the trade - names, trademarks, service marks, or product names of the Licensor, - except as required for reasonable and customary use in describing the - origin of the Work and reproducing the content of the NOTICE file. - - 7. Disclaimer of Warranty. Unless required by applicable law or - agreed to in writing, Licensor provides the Work (and each - Contributor provides its Contributions) on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or - implied, including, without limitation, any warranties or conditions - of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A - PARTICULAR PURPOSE. You are solely responsible for determining the - appropriateness of using or redistributing the Work and assume any - risks associated with Your exercise of permissions under this License. - - 8. Limitation of Liability. In no event and under no legal theory, - whether in tort (including negligence), contract, or otherwise, - unless required by applicable law (such as deliberate and grossly - negligent acts) or agreed to in writing, shall any Contributor be - liable to You for damages, including any direct, indirect, special, - incidental, or consequential damages of any character arising as a - result of this License or out of the use or inability to use the - Work (including but not limited to damages for loss of goodwill, - work stoppage, computer failure or malfunction, or any and all - other commercial damages or losses), even if such Contributor - has been advised of the possibility of such damages. - - 9. Accepting Warranty or Additional Liability. While redistributing - the Work or Derivative Works thereof, You may choose to offer, - and charge a fee for, acceptance of support, warranty, indemnity, - or other liability obligations and/or rights consistent with this - License. However, in accepting such obligations, You may act only - on Your own behalf and on Your sole responsibility, not on behalf - of any other Contributor, and only if You agree to indemnify, - defend, and hold each Contributor harmless for any liability - incurred by, or claims asserted against, such Contributor by reason - of your accepting any such warranty or additional liability. - - END OF TERMS AND CONDITIONS - - APPENDIX: How to apply the Apache License to your work. - - To apply the Apache License to your work, attach the following - boilerplate notice, with the fields enclosed by brackets "[]" - replaced with your own identifying information. (Don't include - the brackets!) The text should be enclosed in the appropriate - comment syntax for the file format. We also recommend that a - file or class name and description of purpose be included on the - same "printed page" as the copyright notice for easier - identification within third-party archives. - - Copyright [yyyy] [name of copyright owner] - - Licensed under the Apache License, Version 2.0 (the "License"); - you may not use this file except in compliance with the License. - You may obtain a copy of the License at - - http://www.apache.org/licenses/LICENSE-2.0 - - Unless required by applicable law or agreed to in writing, software - distributed under the License is distributed on an "AS IS" BASIS, - WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - See the License for the specific language governing permissions and - limitations under the License. diff --git a/vendor/github.com/mindprince/gonvml/Makefile b/vendor/github.com/mindprince/gonvml/Makefile deleted file mode 100644 index 65314b34b4a..00000000000 --- a/vendor/github.com/mindprince/gonvml/Makefile +++ /dev/null @@ -1,23 +0,0 @@ -# Copyright 2017 Google Inc. -# -# Licensed under the Apache License, Version 2.0 (the "License"); -# you may not use this file except in compliance with the License. -# You may obtain a copy of the License at -# -# http://www.apache.org/licenses/LICENSE-2.0 -# -# Unless required by applicable law or agreed to in writing, software -# distributed under the License is distributed on an "AS IS" BASIS, -# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -# See the License for the specific language governing permissions and -# limitations under the License. - -PKG=github.com/mindprince/gonvml - -.PHONY: build -build: - docker run -v $(shell pwd):/go/src/$(PKG) --workdir=/go/src/$(PKG) golang:1.8 go build cmd/example/example.go - -.PHONY: presubmit -presubmit: - ./.travis.gofmt.sh diff --git a/vendor/github.com/mindprince/gonvml/NVML_NOTICE b/vendor/github.com/mindprince/gonvml/NVML_NOTICE deleted file mode 100644 index 3fc131329d8..00000000000 --- a/vendor/github.com/mindprince/gonvml/NVML_NOTICE +++ /dev/null @@ -1,32 +0,0 @@ -Copyright 1993-2016 NVIDIA Corporation. All rights reserved. - -NOTICE TO USER: - -This source code is subject to NVIDIA ownership rights under U.S. and -international Copyright laws. Users and possessors of this source code -are hereby granted a nonexclusive, royalty-free license to use this code -in individual and commercial software. - -NVIDIA MAKES NO REPRESENTATION ABOUT THE SUITABILITY OF THIS SOURCE -CODE FOR ANY PURPOSE. IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR -IMPLIED WARRANTY OF ANY KIND. NVIDIA DISCLAIMS ALL WARRANTIES WITH -REGARD TO THIS SOURCE CODE, INCLUDING ALL IMPLIED WARRANTIES OF -MERCHANTABILITY, NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE. -IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL, -OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS -OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE -OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE -OR PERFORMANCE OF THIS SOURCE CODE. - -U.S. Government End Users. This source code is a "commercial item" as -that term is defined at 48 C.F.R. 2.101 (OCT 1995), consisting of -"commercial computer software" and "commercial computer software -documentation" as such terms are used in 48 C.F.R. 12.212 (SEPT 1995) -and is provided to the U.S. Government only as a commercial end item. -Consistent with 48 C.F.R.12.212 and 48 C.F.R. 227.7202-1 through -227.7202-4 (JUNE 1995), all U.S. Government End Users acquire the -source code with only those rights set forth herein. - -Any use of this source code in individual and commercial software must -include, in the user documentation and internal comments to the code, -the above Disclaimer and U.S. Government End Users Notice. diff --git a/vendor/github.com/mindprince/gonvml/README.md b/vendor/github.com/mindprince/gonvml/README.md deleted file mode 100644 index 91bbf574078..00000000000 --- a/vendor/github.com/mindprince/gonvml/README.md +++ /dev/null @@ -1,19 +0,0 @@ -Go Bindings for NVML --------------------- - -[NVML or NVIDIA Management -Library](https://developer.nvidia.com/nvidia-management-library-nvml) is a -C-based API that can be used for monitoring NVIDIA GPU devices. It's closed -source but can be downloaded as part of the [GPU Deployment -Kit](https://developer.nvidia.com/gpu-deployment-kit). - -The [NVML API -Reference](http://docs.nvidia.com/deploy/nvml-api/nvml-api-reference.html) -describe various methods that are available as part of NVML. - -The `nvml.h` file is included in this repository so that we don't depend on -the presence of NVML in the build environment. - -The `bindings.go` file is the cgo bridge which calls the NVML functions. The -cgo preamble in `bindings.go` uses `dlopen` to dynamically load NVML and makes -its functions available. diff --git a/vendor/github.com/mindprince/gonvml/bindings.go b/vendor/github.com/mindprince/gonvml/bindings.go deleted file mode 100644 index abefe83eabf..00000000000 --- a/vendor/github.com/mindprince/gonvml/bindings.go +++ /dev/null @@ -1,524 +0,0 @@ -/* -Copyright 2017 Google Inc. - -Licensed under the Apache License, Version 2.0 (the "License"); -you may not use this file except in compliance with the License. -You may obtain a copy of the License at - - http://www.apache.org/licenses/LICENSE-2.0 - -Unless required by applicable law or agreed to in writing, software -distributed under the License is distributed on an "AS IS" BASIS, -WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. -See the License for the specific language governing permissions and -limitations under the License. -*/ - -package gonvml - -// #cgo LDFLAGS: -ldl -/* -#include -#include -#include - -#include "nvml.h" - -// nvmlHandle is the handle for dynamically loaded libnvidia-ml.so -void *nvmlHandle; - -nvmlReturn_t (*nvmlInitFunc)(void); - -nvmlReturn_t (*nvmlShutdownFunc)(void); - -const char* (*nvmlErrorStringFunc)(nvmlReturn_t result); -const char* nvmlErrorString(nvmlReturn_t result) { - if (nvmlErrorStringFunc == NULL) { - return "nvmlErrorString Function Not Found"; - } - return nvmlErrorStringFunc(result); -} - -nvmlReturn_t (*nvmlSystemGetDriverVersionFunc)(char *version, unsigned int length); -nvmlReturn_t nvmlSystemGetDriverVersion(char *version, unsigned int length) { - if (nvmlSystemGetDriverVersionFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - return nvmlSystemGetDriverVersionFunc(version, length); -} - -nvmlReturn_t (*nvmlDeviceGetCountFunc)(unsigned int *deviceCount); -nvmlReturn_t nvmlDeviceGetCount(unsigned int *deviceCount) { - if (nvmlDeviceGetCountFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - return nvmlDeviceGetCountFunc(deviceCount); -} - -nvmlReturn_t (*nvmlDeviceGetHandleByIndexFunc)(unsigned int index, nvmlDevice_t *device); -nvmlReturn_t nvmlDeviceGetHandleByIndex(unsigned int index, nvmlDevice_t *device) { - if (nvmlDeviceGetHandleByIndexFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - return nvmlDeviceGetHandleByIndexFunc(index, device); -} - -nvmlReturn_t (*nvmlDeviceGetMinorNumberFunc)(nvmlDevice_t device, unsigned int *minorNumber); -nvmlReturn_t nvmlDeviceGetMinorNumber(nvmlDevice_t device, unsigned int *minorNumber) { - if (nvmlDeviceGetMinorNumberFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - return nvmlDeviceGetMinorNumberFunc(device, minorNumber); -} - -nvmlReturn_t (*nvmlDeviceGetUUIDFunc)(nvmlDevice_t device, char *uuid, unsigned int length); -nvmlReturn_t nvmlDeviceGetUUID(nvmlDevice_t device, char *uuid, unsigned int length) { - if (nvmlDeviceGetUUIDFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - return nvmlDeviceGetUUIDFunc(device, uuid, length); -} - -nvmlReturn_t (*nvmlDeviceGetNameFunc)(nvmlDevice_t device, char *name, unsigned int length); -nvmlReturn_t nvmlDeviceGetName(nvmlDevice_t device, char *name, unsigned int length) { - if (nvmlDeviceGetNameFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - return nvmlDeviceGetNameFunc(device, name, length); -} - -nvmlReturn_t (*nvmlDeviceGetMemoryInfoFunc)(nvmlDevice_t device, nvmlMemory_t *memory); -nvmlReturn_t nvmlDeviceGetMemoryInfo(nvmlDevice_t device, nvmlMemory_t *memory) { - if (nvmlDeviceGetMemoryInfoFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - return nvmlDeviceGetMemoryInfoFunc(device, memory); -} - -nvmlReturn_t (*nvmlDeviceGetUtilizationRatesFunc)(nvmlDevice_t device, nvmlUtilization_t *utilization); -nvmlReturn_t nvmlDeviceGetUtilizationRates(nvmlDevice_t device, nvmlUtilization_t *utilization) { - if (nvmlDeviceGetUtilizationRatesFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - return nvmlDeviceGetUtilizationRatesFunc(device, utilization); -} - -nvmlReturn_t (*nvmlDeviceGetPowerUsageFunc)(nvmlDevice_t device, unsigned int *power); -nvmlReturn_t nvmlDeviceGetPowerUsage(nvmlDevice_t device, unsigned int *power) { - if (nvmlDeviceGetPowerUsageFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - return nvmlDeviceGetPowerUsageFunc(device, power); -} - -nvmlReturn_t (*nvmlDeviceGetTemperatureFunc)(nvmlDevice_t device, nvmlTemperatureSensors_t sensorType, unsigned int *temp); -nvmlReturn_t nvmlDeviceGetTemperature(nvmlDevice_t device, nvmlTemperatureSensors_t sensorType, unsigned int *temp) { - if (nvmlDeviceGetTemperatureFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - return nvmlDeviceGetTemperatureFunc(device, sensorType, temp); -} - -nvmlReturn_t (*nvmlDeviceGetFanSpeedFunc)(nvmlDevice_t device, unsigned int *speed); -nvmlReturn_t nvmlDeviceGetFanSpeed(nvmlDevice_t device, unsigned int *speed) { - if (nvmlDeviceGetFanSpeedFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - return nvmlDeviceGetFanSpeedFunc(device, speed); -} - -nvmlReturn_t (*nvmlDeviceGetEncoderUtilizationFunc)(nvmlDevice_t device, unsigned int* utilization, unsigned int* samplingPeriodUs); -nvmlReturn_t nvmlDeviceGetEncoderUtilization(nvmlDevice_t device, unsigned int* utilization, unsigned int* samplingPeriodUs) { - if (nvmlDeviceGetEncoderUtilizationFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - return nvmlDeviceGetEncoderUtilizationFunc(device, utilization, samplingPeriodUs); -} - -nvmlReturn_t (*nvmlDeviceGetDecoderUtilizationFunc)(nvmlDevice_t device, unsigned int* utilization, unsigned int* samplingPeriodUs); -nvmlReturn_t nvmlDeviceGetDecoderUtilization(nvmlDevice_t device, unsigned int* utilization, unsigned int* samplingPeriodUs) { - if (nvmlDeviceGetDecoderUtilizationFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - return nvmlDeviceGetDecoderUtilizationFunc(device, utilization, samplingPeriodUs); -} - -nvmlReturn_t (*nvmlDeviceGetSamplesFunc)(nvmlDevice_t device, nvmlSamplingType_t type, unsigned long long lastSeenTimeStamp, nvmlValueType_t *sampleValType, unsigned int *sampleCount, nvmlSample_t *samples); - -// Loads the "libnvidia-ml.so.1" shared library. -// Loads all symbols needed and initializes NVML. -// Call this before calling any other methods. -nvmlReturn_t nvmlInit_dl(void) { - nvmlHandle = dlopen("libnvidia-ml.so.1", RTLD_LAZY); - if (nvmlHandle == NULL) { - return NVML_ERROR_LIBRARY_NOT_FOUND; - } - nvmlInitFunc = dlsym(nvmlHandle, "nvmlInit_v2"); - if (nvmlInitFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlShutdownFunc = dlsym(nvmlHandle, "nvmlShutdown"); - if (nvmlShutdownFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlErrorStringFunc = dlsym(nvmlHandle, "nvmlErrorString"); - if (nvmlErrorStringFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlSystemGetDriverVersionFunc = dlsym(nvmlHandle, "nvmlSystemGetDriverVersion"); - if (nvmlSystemGetDriverVersionFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlDeviceGetCountFunc = dlsym(nvmlHandle, "nvmlDeviceGetCount_v2"); - if (nvmlDeviceGetCountFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlDeviceGetHandleByIndexFunc = dlsym(nvmlHandle, "nvmlDeviceGetHandleByIndex_v2"); - if (nvmlDeviceGetHandleByIndexFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlDeviceGetMinorNumberFunc = dlsym(nvmlHandle, "nvmlDeviceGetMinorNumber"); - if (nvmlDeviceGetMinorNumberFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlDeviceGetUUIDFunc = dlsym(nvmlHandle, "nvmlDeviceGetUUID"); - if (nvmlDeviceGetUUIDFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlDeviceGetNameFunc = dlsym(nvmlHandle, "nvmlDeviceGetName"); - if (nvmlDeviceGetNameFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlDeviceGetMemoryInfoFunc = dlsym(nvmlHandle, "nvmlDeviceGetMemoryInfo"); - if (nvmlDeviceGetMemoryInfoFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlDeviceGetUtilizationRatesFunc = dlsym(nvmlHandle, "nvmlDeviceGetUtilizationRates"); - if (nvmlDeviceGetUtilizationRatesFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlDeviceGetPowerUsageFunc = dlsym(nvmlHandle, "nvmlDeviceGetPowerUsage"); - if (nvmlDeviceGetPowerUsageFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlDeviceGetTemperatureFunc = dlsym(nvmlHandle, "nvmlDeviceGetTemperature"); - if (nvmlDeviceGetTemperatureFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlDeviceGetFanSpeedFunc = dlsym(nvmlHandle, "nvmlDeviceGetFanSpeed"); - if (nvmlDeviceGetFanSpeedFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlDeviceGetSamplesFunc = dlsym(nvmlHandle, "nvmlDeviceGetSamples"); - if (nvmlDeviceGetSamplesFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlDeviceGetEncoderUtilizationFunc = dlsym(nvmlHandle, "nvmlDeviceGetEncoderUtilization"); - if (nvmlDeviceGetEncoderUtilizationFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlDeviceGetDecoderUtilizationFunc = dlsym(nvmlHandle, "nvmlDeviceGetDecoderUtilization"); - if (nvmlDeviceGetDecoderUtilizationFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlReturn_t result = nvmlInitFunc(); - if (result != NVML_SUCCESS) { - dlclose(nvmlHandle); - nvmlHandle = NULL; - return result; - } - return NVML_SUCCESS; -} - -// Shuts down NVML and decrements the reference count on the dynamically loaded -// "libnvidia-ml.so.1" library. -// Call this once NVML is no longer being used. -nvmlReturn_t nvmlShutdown_dl(void) { - if (nvmlHandle == NULL) { - return NVML_SUCCESS; - } - if (nvmlShutdownFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - nvmlReturn_t r = nvmlShutdownFunc(); - if (r != NVML_SUCCESS) { - return r; - } - return (dlclose(nvmlHandle) ? NVML_ERROR_UNKNOWN : NVML_SUCCESS); -} - -// This function is here because the API provided by NVML is not very user -// friendly. This function can be used to get average utilization.gpu or -// power.draw. -// -// `device`: The identifier of the target device. -// `type`: Type of sampling event. Only NVML_TOTAL_POWER_SAMPLES and NVML_GPU_UTILIZATION_SAMPLES are supported. -// `lastSeenTimeStamp`: Return average using samples with timestamp greather than this timestamp. Unix epoch in micro seconds. -// `averageUsage`: Reference in which average is returned. -// -// In my experiments, I found that NVML_GPU_UTILIZATION_SAMPLES buffer stores -// 100 samples that are uniformly spread with ~6 samples per second. So the -// buffer stores last ~16s of data. -// NVML_TOTAL_POWER_SAMPLES buffer stores 120 samples, but in different runs I -// noticed them to be non-uniformly separated. Sometimes 120 samples only -// consisted of 10s of data and sometimes they were spread over 60s. -// -nvmlReturn_t nvmlDeviceGetAverageUsage(nvmlDevice_t device, nvmlSamplingType_t type, unsigned long long lastSeenTimeStamp, unsigned int* averageUsage) { - if (nvmlHandle == NULL) { - return NVML_ERROR_LIBRARY_NOT_FOUND; - } - if (nvmlDeviceGetSamplesFunc == NULL) { - return NVML_ERROR_FUNCTION_NOT_FOUND; - } - - // We don't really use this because both the metrics we support - // averagePowerUsage and averageGPUUtilization are unsigned int. - nvmlValueType_t sampleValType; - - // This will be set to the number of samples that can be queried. We would - // need to allocate an array of this size to store the samples. - unsigned int sampleCount; - - // Invoking this method with `samples` set to NULL sets the sampleCount. - nvmlReturn_t r = nvmlDeviceGetSamplesFunc(device, type, lastSeenTimeStamp, &sampleValType, &sampleCount, NULL); - if (r != NVML_SUCCESS) { - return r; - } - - // Allocate memory to store sampleCount samples. - // In my experiments, the sampleCount at this stage was always 120 for - // NVML_TOTAL_POWER_SAMPLES and 100 for NVML_GPU_UTILIZATION_SAMPLES - nvmlSample_t* samples = (nvmlSample_t*) malloc(sampleCount * sizeof(nvmlSample_t)); - - r = nvmlDeviceGetSamplesFunc(device, type, lastSeenTimeStamp, &sampleValType, &sampleCount, samples); - if (r != NVML_SUCCESS) { - free(samples); - return r; - } - - int i = 0; - unsigned int sum = 0; - for (; i < sampleCount; i++) { - sum += samples[i].sampleValue.uiVal; - } - *averageUsage = sum/sampleCount; - - free(samples); - return r; -} -*/ -import "C" - -import ( - "errors" - "fmt" - "time" -) - -const ( - szDriver = C.NVML_SYSTEM_DRIVER_VERSION_BUFFER_SIZE - szName = C.NVML_DEVICE_NAME_BUFFER_SIZE - szUUID = C.NVML_DEVICE_UUID_BUFFER_SIZE -) - -var errLibraryNotLoaded = errors.New("could not load NVML library") - -// Initialize initializes NVML. -// Call this before calling any other methods. -func Initialize() error { - return errorString(C.nvmlInit_dl()) -} - -// Shutdown shuts down NVML. -// Call this once NVML is no longer being used. -func Shutdown() error { - return errorString(C.nvmlShutdown_dl()) -} - -// errorString takes a nvmlReturn_t and converts it into a golang error. -// It uses a nvml method to convert to a user friendly error message. -func errorString(ret C.nvmlReturn_t) error { - if ret == C.NVML_SUCCESS { - return nil - } - // We need to special case this because if nvml library is not found - // nvmlErrorString() method will not work. - if ret == C.NVML_ERROR_LIBRARY_NOT_FOUND || C.nvmlHandle == nil { - return errLibraryNotLoaded - } - err := C.GoString(C.nvmlErrorString(ret)) - return fmt.Errorf("nvml: %v", err) -} - -// SystemDriverVersion returns the the driver version on the system. -func SystemDriverVersion() (string, error) { - if C.nvmlHandle == nil { - return "", errLibraryNotLoaded - } - var driver [szDriver]C.char - r := C.nvmlSystemGetDriverVersion(&driver[0], szDriver) - return C.GoString(&driver[0]), errorString(r) -} - -// DeviceCount returns the number of nvidia devices on the system. -func DeviceCount() (uint, error) { - if C.nvmlHandle == nil { - return 0, errLibraryNotLoaded - } - var n C.uint - r := C.nvmlDeviceGetCount(&n) - return uint(n), errorString(r) -} - -// Device is the handle for the device. -// This handle is obtained by calling DeviceHandleByIndex(). -type Device struct { - dev C.nvmlDevice_t -} - -// DeviceHandleByIndex returns the device handle for a particular index. -// The indices range from 0 to DeviceCount()-1. The order in which NVML -// enumerates devices has no guarantees of consistency between reboots. -func DeviceHandleByIndex(idx uint) (Device, error) { - if C.nvmlHandle == nil { - return Device{}, errLibraryNotLoaded - } - var dev C.nvmlDevice_t - r := C.nvmlDeviceGetHandleByIndex(C.uint(idx), &dev) - return Device{dev}, errorString(r) -} - -// MinorNumber returns the minor number for the device. -// The minor number for the device is such that the Nvidia device node -// file for each GPU will have the form /dev/nvidia[minor number]. -func (d Device) MinorNumber() (uint, error) { - if C.nvmlHandle == nil { - return 0, errLibraryNotLoaded - } - var n C.uint - r := C.nvmlDeviceGetMinorNumber(d.dev, &n) - return uint(n), errorString(r) -} - -// UUID returns the globally unique immutable UUID associated with this device. -func (d Device) UUID() (string, error) { - if C.nvmlHandle == nil { - return "", errLibraryNotLoaded - } - var uuid [szUUID]C.char - r := C.nvmlDeviceGetUUID(d.dev, &uuid[0], szUUID) - return C.GoString(&uuid[0]), errorString(r) -} - -// Name returns the product name of the device. -func (d Device) Name() (string, error) { - if C.nvmlHandle == nil { - return "", errLibraryNotLoaded - } - var name [szName]C.char - r := C.nvmlDeviceGetName(d.dev, &name[0], szName) - return C.GoString(&name[0]), errorString(r) -} - -// MemoryInfo returns the total and used memory (in bytes) of the device. -func (d Device) MemoryInfo() (uint64, uint64, error) { - if C.nvmlHandle == nil { - return 0, 0, errLibraryNotLoaded - } - var memory C.nvmlMemory_t - r := C.nvmlDeviceGetMemoryInfo(d.dev, &memory) - return uint64(memory.total), uint64(memory.used), errorString(r) -} - -// UtilizationRates returns the percent of time over the past sample period during which: -// utilization.gpu: one or more kernels were executing on the GPU. -// utilization.memory: global (device) memory was being read or written. -func (d Device) UtilizationRates() (uint, uint, error) { - if C.nvmlHandle == nil { - return 0, 0, errLibraryNotLoaded - } - var utilization C.nvmlUtilization_t - r := C.nvmlDeviceGetUtilizationRates(d.dev, &utilization) - return uint(utilization.gpu), uint(utilization.memory), errorString(r) -} - -// PowerUsage returns the power usage for this GPU and its associated circuitry -// in milliwatts. The reading is accurate to within +/- 5% of current power draw. -func (d Device) PowerUsage() (uint, error) { - if C.nvmlHandle == nil { - return 0, errLibraryNotLoaded - } - var n C.uint - r := C.nvmlDeviceGetPowerUsage(d.dev, &n) - return uint(n), errorString(r) -} - -// AveragePowerUsage returns the power usage for this GPU and its associated circuitry -// in milliwatts averaged over the samples collected in the last `since` duration. -func (d Device) AveragePowerUsage(since time.Duration) (uint, error) { - if C.nvmlHandle == nil { - return 0, errLibraryNotLoaded - } - lastTs := C.ulonglong(time.Now().Add(-1*since).UnixNano() / 1000) - var n C.uint - r := C.nvmlDeviceGetAverageUsage(d.dev, C.NVML_TOTAL_POWER_SAMPLES, lastTs, &n) - return uint(n), errorString(r) -} - -// AverageGPUUtilization returns the utilization.gpu metric (percent of time -// one of more kernels were executing on the GPU) averaged over the samples -// collected in the last `since` duration. -func (d Device) AverageGPUUtilization(since time.Duration) (uint, error) { - if C.nvmlHandle == nil { - return 0, errLibraryNotLoaded - } - lastTs := C.ulonglong(time.Now().Add(-1*since).UnixNano() / 1000) - var n C.uint - r := C.nvmlDeviceGetAverageUsage(d.dev, C.NVML_GPU_UTILIZATION_SAMPLES, lastTs, &n) - return uint(n), errorString(r) -} - -// Temperature returns the temperature for this GPU in Celsius. -func (d Device) Temperature() (uint, error) { - if C.nvmlHandle == nil { - return 0, errLibraryNotLoaded - } - var n C.uint - r := C.nvmlDeviceGetTemperature(d.dev, C.NVML_TEMPERATURE_GPU, &n) - return uint(n), errorString(r) -} - -// FanSpeed returns the temperature for this GPU in the percentage of its full -// speed, with 100 being the maximum. -func (d Device) FanSpeed() (uint, error) { - if C.nvmlHandle == nil { - return 0, errLibraryNotLoaded - } - var n C.uint - r := C.nvmlDeviceGetFanSpeed(d.dev, &n) - return uint(n), errorString(r) -} - -// EncoderUtilization returns the percent of time over the last sample period during which the GPU video encoder was being used. -// The sampling period is variable and is returned in the second return argument in microseconds. -func (d Device) EncoderUtilization() (uint, uint, error) { - if C.nvmlHandle == nil { - return 0, 0, errLibraryNotLoaded - } - var n C.uint - var sp C.uint - r := C.nvmlDeviceGetEncoderUtilization(d.dev, &n, &sp) - return uint(n), uint(sp), errorString(r) -} - -// DecoderUtilization returns the percent of time over the last sample period during which the GPU video decoder was being used. -// The sampling period is variable and is returned in the second return argument in microseconds. -func (d Device) DecoderUtilization() (uint, uint, error) { - if C.nvmlHandle == nil { - return 0, 0, errLibraryNotLoaded - } - var n C.uint - var sp C.uint - r := C.nvmlDeviceGetDecoderUtilization(d.dev, &n, &sp) - return uint(n), uint(sp), errorString(r) -} diff --git a/vendor/github.com/mindprince/gonvml/bindings_nocgo.go b/vendor/github.com/mindprince/gonvml/bindings_nocgo.go deleted file mode 100644 index ddbec565077..00000000000 --- a/vendor/github.com/mindprince/gonvml/bindings_nocgo.go +++ /dev/null @@ -1,115 +0,0 @@ -// +build !cgo - -package gonvml - -import ( - "errors" - "time" -) - -var errNoCgo = errors.New("this binary is built without CGO, NVML is disabled") - -// Initialize initializes NVML. -// Call this before calling any other methods. -func Initialize() error { - return errNoCgo -} - -// Shutdown shuts down NVML. -// Call this once NVML is no longer being used. -func Shutdown() error { - return errNoCgo -} - -// SystemDriverVersion returns the the driver version on the system. -func SystemDriverVersion() (string, error) { - return "", errNoCgo -} - -// DeviceCount returns the number of nvidia devices on the system. -func DeviceCount() (uint, error) { - return 0, errNoCgo -} - -// Device is the handle for the device. -// This handle is obtained by calling DeviceHandleByIndex(). -type Device struct { -} - -// DeviceHandleByIndex returns the device handle for a particular index. -// The indices range from 0 to DeviceCount()-1. The order in which NVML -// enumerates devices has no guarantees of consistency between reboots. -func DeviceHandleByIndex(idx uint) (Device, error) { - return Device{}, errNoCgo -} - -// MinorNumber returns the minor number for the device. -// The minor number for the device is such that the Nvidia device node -// file for each GPU will have the form /dev/nvidia[minor number]. -func (d Device) MinorNumber() (uint, error) { - return 0, errNoCgo -} - -// UUID returns the globally unique immutable UUID associated with this device. -func (d Device) UUID() (string, error) { - return "", errNoCgo -} - -// Name returns the product name of the device. -func (d Device) Name() (string, error) { - return "", errNoCgo -} - -// MemoryInfo returns the total and used memory (in bytes) of the device. -func (d Device) MemoryInfo() (uint64, uint64, error) { - return 0, 0, errNoCgo -} - -// UtilizationRates returns the percent of time over the past sample period during which: -// utilization.gpu: one or more kernels were executing on the GPU. -// utilizatoin.memory: global (device) memory was being read or written. -func (d Device) UtilizationRates() (uint, uint, error) { - return 0, 0, errNoCgo -} - -// PowerUsage returns the power usage for this GPU and its associated circuitry -// in milliwatts. The reading is accurate to within +/- 5% of current power draw. -func (d Device) PowerUsage() (uint, error) { - return 0, errNoCgo -} - -// AveragePowerUsage returns the power usage for this GPU and its associated circuitry -// in milliwatts averaged over the samples collected in the last `since` duration. -func (d Device) AveragePowerUsage(since time.Duration) (uint, error) { - return 0, errNoCgo -} - -// AverageGPUUtilization returns the utilization.gpu metric (percent of time -// one of more kernels were executing on the GPU) averaged over the samples -// collected in the last `since` duration. -func (d Device) AverageGPUUtilization(since time.Duration) (uint, error) { - return 0, errNoCgo -} - -// Temperature returns the temperature for this GPU in Celsius. -func (d Device) Temperature() (uint, error) { - return 0, errNoCgo -} - -// FanSpeed returns the temperature for this GPU in the percentage of its full -// speed, with 100 being the maximum. -func (d Device) FanSpeed() (uint, error) { - return 0, errNoCgo -} - -// EncoderUtilization returns the percent of time over the last sample period during which the GPU video encoder was being used. -// The sampling period is variable and is returned in the second return argument in microseconds. -func (d Device) EncoderUtilization() (uint, uint, error) { - return 0, 0, errNoCgo -} - -// DecoderUtilization returns the percent of time over the last sample period during which the GPU video decoder was being used. -// The sampling period is variable and is returned in the second return argument in microseconds. -func (d Device) DecoderUtilization() (uint, uint, error) { - return 0, 0, errNoCgo -} diff --git a/vendor/github.com/mindprince/gonvml/nvml.h b/vendor/github.com/mindprince/gonvml/nvml.h deleted file mode 100644 index 6febac22b60..00000000000 --- a/vendor/github.com/mindprince/gonvml/nvml.h +++ /dev/null @@ -1,5605 +0,0 @@ -/* - * Copyright 1993-2016 NVIDIA Corporation. All rights reserved. - * - * NOTICE TO USER: - * - * This source code is subject to NVIDIA ownership rights under U.S. and - * international Copyright laws. Users and possessors of this source code - * are hereby granted a nonexclusive, royalty-free license to use this code - * in individual and commercial software. - * - * NVIDIA MAKES NO REPRESENTATION ABOUT THE SUITABILITY OF THIS SOURCE - * CODE FOR ANY PURPOSE. IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR - * IMPLIED WARRANTY OF ANY KIND. NVIDIA DISCLAIMS ALL WARRANTIES WITH - * REGARD TO THIS SOURCE CODE, INCLUDING ALL IMPLIED WARRANTIES OF - * MERCHANTABILITY, NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE. - * IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL, - * OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS - * OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE - * OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE - * OR PERFORMANCE OF THIS SOURCE CODE. - * - * U.S. Government End Users. This source code is a "commercial item" as - * that term is defined at 48 C.F.R. 2.101 (OCT 1995), consisting of - * "commercial computer software" and "commercial computer software - * documentation" as such terms are used in 48 C.F.R. 12.212 (SEPT 1995) - * and is provided to the U.S. Government only as a commercial end item. - * Consistent with 48 C.F.R.12.212 and 48 C.F.R. 227.7202-1 through - * 227.7202-4 (JUNE 1995), all U.S. Government End Users acquire the - * source code with only those rights set forth herein. - * - * Any use of this source code in individual and commercial software must - * include, in the user documentation and internal comments to the code, - * the above Disclaimer and U.S. Government End Users Notice. - */ - -/* -NVML API Reference - -The NVIDIA Management Library (NVML) is a C-based programmatic interface for monitoring and -managing various states within NVIDIA Tesla &tm; GPUs. It is intended to be a platform for building -3rd party applications, and is also the underlying library for the NVIDIA-supported nvidia-smi -tool. NVML is thread-safe so it is safe to make simultaneous NVML calls from multiple threads. - -API Documentation - -Supported platforms: -- Windows: Windows Server 2008 R2 64bit, Windows Server 2012 R2 64bit, Windows 7 64bit, Windows 8 64bit, Windows 10 64bit -- Linux: 32-bit and 64-bit -- Hypervisors: Windows Server 2008R2/2012 Hyper-V 64bit, Citrix XenServer 6.2 SP1+, VMware ESX 5.1/5.5 - -Supported products: -- Full Support - - All Tesla products, starting with the Fermi architecture - - All Quadro products, starting with the Fermi architecture - - All GRID products, starting with the Kepler architecture - - Selected GeForce Titan products -- Limited Support - - All Geforce products, starting with the Fermi architecture - -The NVML library can be found at \%ProgramW6432\%\\"NVIDIA Corporation"\\NVSMI\\ on Windows. It is -not be added to the system path by default. To dynamically link to NVML, add this path to the PATH -environmental variable. To dynamically load NVML, call LoadLibrary with this path. - -On Linux the NVML library will be found on the standard library path. For 64 bit Linux, both the 32 bit -and 64 bit NVML libraries will be installed. - -Online documentation for this library is available at http://docs.nvidia.com/deploy/nvml-api/index.html -*/ - -#ifndef __nvml_nvml_h__ -#define __nvml_nvml_h__ - -#ifdef __cplusplus -extern "C" { -#endif - -/* - * On Windows, set up methods for DLL export - * define NVML_STATIC_IMPORT when using nvml_loader library - */ -#if defined _WINDOWS - #if !defined NVML_STATIC_IMPORT - #if defined NVML_LIB_EXPORT - #define DECLDIR __declspec(dllexport) - #else - #define DECLDIR __declspec(dllimport) - #endif - #else - #define DECLDIR - #endif -#else - #define DECLDIR -#endif - -/** - * NVML API versioning support - */ -#define NVML_API_VERSION 8 -#define NVML_API_VERSION_STR "8" -#define nvmlInit nvmlInit_v2 -#define nvmlDeviceGetPciInfo nvmlDeviceGetPciInfo_v2 -#define nvmlDeviceGetCount nvmlDeviceGetCount_v2 -#define nvmlDeviceGetHandleByIndex nvmlDeviceGetHandleByIndex_v2 -#define nvmlDeviceGetHandleByPciBusId nvmlDeviceGetHandleByPciBusId_v2 - -/***************************************************************************************************/ -/** @defgroup nvmlDeviceStructs Device Structs - * @{ - */ -/***************************************************************************************************/ - -/** - * Special constant that some fields take when they are not available. - * Used when only part of the struct is not available. - * - * Each structure explicitly states when to check for this value. - */ -#define NVML_VALUE_NOT_AVAILABLE (-1) - -typedef struct nvmlDevice_st* nvmlDevice_t; - -/** - * Buffer size guaranteed to be large enough for pci bus id - */ -#define NVML_DEVICE_PCI_BUS_ID_BUFFER_SIZE 16 - -/** - * PCI information about a GPU device. - */ -typedef struct nvmlPciInfo_st -{ - char busId[NVML_DEVICE_PCI_BUS_ID_BUFFER_SIZE]; //!< The tuple domain:bus:device.function PCI identifier (& NULL terminator) - unsigned int domain; //!< The PCI domain on which the device's bus resides, 0 to 0xffff - unsigned int bus; //!< The bus on which the device resides, 0 to 0xff - unsigned int device; //!< The device's id on the bus, 0 to 31 - unsigned int pciDeviceId; //!< The combined 16-bit device id and 16-bit vendor id - - // Added in NVML 2.285 API - unsigned int pciSubSystemId; //!< The 32-bit Sub System Device ID - - // NVIDIA reserved for internal use only - unsigned int reserved0; - unsigned int reserved1; - unsigned int reserved2; - unsigned int reserved3; -} nvmlPciInfo_t; - -/** - * Detailed ECC error counts for a device. - * - * @deprecated Different GPU families can have different memory error counters - * See \ref nvmlDeviceGetMemoryErrorCounter - */ -typedef struct nvmlEccErrorCounts_st -{ - unsigned long long l1Cache; //!< L1 cache errors - unsigned long long l2Cache; //!< L2 cache errors - unsigned long long deviceMemory; //!< Device memory errors - unsigned long long registerFile; //!< Register file errors -} nvmlEccErrorCounts_t; - -/** - * Utilization information for a device. - * Each sample period may be between 1 second and 1/6 second, depending on the product being queried. - */ -typedef struct nvmlUtilization_st -{ - unsigned int gpu; //!< Percent of time over the past sample period during which one or more kernels was executing on the GPU - unsigned int memory; //!< Percent of time over the past sample period during which global (device) memory was being read or written -} nvmlUtilization_t; - -/** - * Memory allocation information for a device. - */ -typedef struct nvmlMemory_st -{ - unsigned long long total; //!< Total installed FB memory (in bytes) - unsigned long long free; //!< Unallocated FB memory (in bytes) - unsigned long long used; //!< Allocated FB memory (in bytes). Note that the driver/GPU always sets aside a small amount of memory for bookkeeping -} nvmlMemory_t; - -/** - * BAR1 Memory allocation Information for a device - */ -typedef struct nvmlBAR1Memory_st -{ - unsigned long long bar1Total; //!< Total BAR1 Memory (in bytes) - unsigned long long bar1Free; //!< Unallocated BAR1 Memory (in bytes) - unsigned long long bar1Used; //!< Allocated Used Memory (in bytes) -}nvmlBAR1Memory_t; - -/** - * Information about running compute processes on the GPU - */ -typedef struct nvmlProcessInfo_st -{ - unsigned int pid; //!< Process ID - unsigned long long usedGpuMemory; //!< Amount of used GPU memory in bytes. - //! Under WDDM, \ref NVML_VALUE_NOT_AVAILABLE is always reported - //! because Windows KMD manages all the memory and not the NVIDIA driver -} nvmlProcessInfo_t; - -/** - * Enum to represent type of bridge chip - */ -typedef enum nvmlBridgeChipType_enum -{ - NVML_BRIDGE_CHIP_PLX = 0, - NVML_BRIDGE_CHIP_BRO4 = 1 -}nvmlBridgeChipType_t; - -/** - * Maximum number of NvLink links supported - */ -#define NVML_NVLINK_MAX_LINKS 6 - -/** - * Enum to represent the NvLink utilization counter packet units - */ -typedef enum nvmlNvLinkUtilizationCountUnits_enum -{ - NVML_NVLINK_COUNTER_UNIT_CYCLES = 0, // count by cycles - NVML_NVLINK_COUNTER_UNIT_PACKETS = 1, // count by packets - NVML_NVLINK_COUNTER_UNIT_BYTES = 2, // count by bytes - - // this must be last - NVML_NVLINK_COUNTER_UNIT_COUNT -} nvmlNvLinkUtilizationCountUnits_t; - -/** - * Enum to represent the NvLink utilization counter packet types to count - * ** this is ONLY applicable with the units as packets or bytes - * ** as specified in \a nvmlNvLinkUtilizationCountUnits_t - * ** all packet filter descriptions are target GPU centric - * ** these can be "OR'd" together - */ -typedef enum nvmlNvLinkUtilizationCountPktTypes_enum -{ - NVML_NVLINK_COUNTER_PKTFILTER_NOP = 0x1, // no operation packets - NVML_NVLINK_COUNTER_PKTFILTER_READ = 0x2, // read packets - NVML_NVLINK_COUNTER_PKTFILTER_WRITE = 0x4, // write packets - NVML_NVLINK_COUNTER_PKTFILTER_RATOM = 0x8, // reduction atomic requests - NVML_NVLINK_COUNTER_PKTFILTER_NRATOM = 0x10, // non-reduction atomic requests - NVML_NVLINK_COUNTER_PKTFILTER_FLUSH = 0x20, // flush requests - NVML_NVLINK_COUNTER_PKTFILTER_RESPDATA = 0x40, // responses with data - NVML_NVLINK_COUNTER_PKTFILTER_RESPNODATA = 0x80, // responses without data - NVML_NVLINK_COUNTER_PKTFILTER_ALL = 0xFF // all packets -} nvmlNvLinkUtilizationCountPktTypes_t; - -/** - * Struct to define the NVLINK counter controls - */ -typedef struct nvmlNvLinkUtilizationControl_st -{ - nvmlNvLinkUtilizationCountUnits_t units; - nvmlNvLinkUtilizationCountPktTypes_t pktfilter; -} nvmlNvLinkUtilizationControl_t; - -/** - * Enum to represent NvLink queryable capabilities - */ -typedef enum nvmlNvLinkCapability_enum -{ - NVML_NVLINK_CAP_P2P_SUPPORTED = 0, // P2P over NVLink is supported - NVML_NVLINK_CAP_SYSMEM_ACCESS = 1, // Access to system memory is supported - NVML_NVLINK_CAP_P2P_ATOMICS = 2, // P2P atomics are supported - NVML_NVLINK_CAP_SYSMEM_ATOMICS= 3, // System memory atomics are supported - NVML_NVLINK_CAP_SLI_BRIDGE = 4, // SLI is supported over this link - NVML_NVLINK_CAP_VALID = 5, // Link is supported on this device - // should be last - NVML_NVLINK_CAP_COUNT -} nvmlNvLinkCapability_t; - -/** - * Enum to represent NvLink queryable error counters - */ -typedef enum nvmlNvLinkErrorCounter_enum -{ - NVML_NVLINK_ERROR_DL_REPLAY = 0, // Data link transmit replay error counter - NVML_NVLINK_ERROR_DL_RECOVERY = 1, // Data link transmit recovery error counter - NVML_NVLINK_ERROR_DL_CRC_FLIT = 2, // Data link receive flow control digit CRC error counter - NVML_NVLINK_ERROR_DL_CRC_DATA = 3, // Data link receive data CRC error counter - - // this must be last - NVML_NVLINK_ERROR_COUNT -} nvmlNvLinkErrorCounter_t; - -/** - * Represents level relationships within a system between two GPUs - * The enums are spaced to allow for future relationships - */ -typedef enum nvmlGpuLevel_enum -{ - NVML_TOPOLOGY_INTERNAL = 0, // e.g. Tesla K80 - NVML_TOPOLOGY_SINGLE = 10, // all devices that only need traverse a single PCIe switch - NVML_TOPOLOGY_MULTIPLE = 20, // all devices that need not traverse a host bridge - NVML_TOPOLOGY_HOSTBRIDGE = 30, // all devices that are connected to the same host bridge - NVML_TOPOLOGY_CPU = 40, // all devices that are connected to the same CPU but possibly multiple host bridges - NVML_TOPOLOGY_SYSTEM = 50, // all devices in the system - - // there is purposefully no COUNT here because of the need for spacing above -} nvmlGpuTopologyLevel_t; - -/* P2P Capability Index Status*/ -typedef enum nvmlGpuP2PStatus_enum -{ - NVML_P2P_STATUS_OK = 0, - NVML_P2P_STATUS_CHIPSET_NOT_SUPPORED, - NVML_P2P_STATUS_GPU_NOT_SUPPORTED, - NVML_P2P_STATUS_IOH_TOPOLOGY_NOT_SUPPORTED, - NVML_P2P_STATUS_DISABLED_BY_REGKEY, - NVML_P2P_STATUS_NOT_SUPPORTED, - NVML_P2P_STATUS_UNKNOWN - -} nvmlGpuP2PStatus_t; - -/* P2P Capability Index*/ -typedef enum nvmlGpuP2PCapsIndex_enum -{ - NVML_P2P_CAPS_INDEX_READ = 0, - NVML_P2P_CAPS_INDEX_WRITE, - NVML_P2P_CAPS_INDEX_NVLINK, - NVML_P2P_CAPS_INDEX_ATOMICS, - NVML_P2P_CAPS_INDEX_PROP, - NVML_P2P_CAPS_INDEX_UNKNOWN -}nvmlGpuP2PCapsIndex_t; - -/** - * Maximum limit on Physical Bridges per Board - */ -#define NVML_MAX_PHYSICAL_BRIDGE (128) - -/** - * Information about the Bridge Chip Firmware - */ -typedef struct nvmlBridgeChipInfo_st -{ - nvmlBridgeChipType_t type; //!< Type of Bridge Chip - unsigned int fwVersion; //!< Firmware Version. 0=Version is unavailable -}nvmlBridgeChipInfo_t; - -/** - * This structure stores the complete Hierarchy of the Bridge Chip within the board. The immediate - * bridge is stored at index 0 of bridgeInfoList, parent to immediate bridge is at index 1 and so forth. - */ -typedef struct nvmlBridgeChipHierarchy_st -{ - unsigned char bridgeCount; //!< Number of Bridge Chips on the Board - nvmlBridgeChipInfo_t bridgeChipInfo[NVML_MAX_PHYSICAL_BRIDGE]; //!< Hierarchy of Bridge Chips on the board -}nvmlBridgeChipHierarchy_t; - -/** - * Represents Type of Sampling Event - */ -typedef enum nvmlSamplingType_enum -{ - NVML_TOTAL_POWER_SAMPLES = 0, //!< To represent total power drawn by GPU - NVML_GPU_UTILIZATION_SAMPLES = 1, //!< To represent percent of time during which one or more kernels was executing on the GPU - NVML_MEMORY_UTILIZATION_SAMPLES = 2, //!< To represent percent of time during which global (device) memory was being read or written - NVML_ENC_UTILIZATION_SAMPLES = 3, //!< To represent percent of time during which NVENC remains busy - NVML_DEC_UTILIZATION_SAMPLES = 4, //!< To represent percent of time during which NVDEC remains busy - NVML_PROCESSOR_CLK_SAMPLES = 5, //!< To represent processor clock samples - NVML_MEMORY_CLK_SAMPLES = 6, //!< To represent memory clock samples - - // Keep this last - NVML_SAMPLINGTYPE_COUNT -}nvmlSamplingType_t; - -/** - * Represents the queryable PCIe utilization counters - */ -typedef enum nvmlPcieUtilCounter_enum -{ - NVML_PCIE_UTIL_TX_BYTES = 0, // 1KB granularity - NVML_PCIE_UTIL_RX_BYTES = 1, // 1KB granularity - - // Keep this last - NVML_PCIE_UTIL_COUNT -} nvmlPcieUtilCounter_t; - -/** - * Represents the type for sample value returned - */ -typedef enum nvmlValueType_enum -{ - NVML_VALUE_TYPE_DOUBLE = 0, - NVML_VALUE_TYPE_UNSIGNED_INT = 1, - NVML_VALUE_TYPE_UNSIGNED_LONG = 2, - NVML_VALUE_TYPE_UNSIGNED_LONG_LONG = 3, - NVML_VALUE_TYPE_SIGNED_LONG_LONG = 4, - - // Keep this last - NVML_VALUE_TYPE_COUNT -}nvmlValueType_t; - - -/** - * Union to represent different types of Value - */ -typedef union nvmlValue_st -{ - double dVal; //!< If the value is double - unsigned int uiVal; //!< If the value is unsigned int - unsigned long ulVal; //!< If the value is unsigned long - unsigned long long ullVal; //!< If the value is unsigned long long - signed long long sllVal; //!< If the value is signed long long -}nvmlValue_t; - -/** - * Information for Sample - */ -typedef struct nvmlSample_st -{ - unsigned long long timeStamp; //!< CPU Timestamp in microseconds - nvmlValue_t sampleValue; //!< Sample Value -}nvmlSample_t; - -/** - * Represents type of perf policy for which violation times can be queried - */ -typedef enum nvmlPerfPolicyType_enum -{ - NVML_PERF_POLICY_POWER = 0, //!< How long did power violations cause the GPU to be below application clocks - NVML_PERF_POLICY_THERMAL = 1, //!< How long did thermal violations cause the GPU to be below application clocks - NVML_PERF_POLICY_SYNC_BOOST = 2, //!< How long did sync boost cause the GPU to be below application clocks - NVML_PERF_POLICY_BOARD_LIMIT = 3, //!< How long did the board limit cause the GPU to be below application clocks - NVML_PERF_POLICY_LOW_UTILIZATION = 4, //!< How long did low utilization cause the GPU to be below application clocks - NVML_PERF_POLICY_RELIABILITY = 5, //!< How long did the board reliability limit cause the GPU to be below application clocks - - NVML_PERF_POLICY_TOTAL_APP_CLOCKS = 10, //!< Total time the GPU was held below application clocks by any limiter (0 - 5 above) - NVML_PERF_POLICY_TOTAL_BASE_CLOCKS = 11, //!< Total time the GPU was held below base clocks - - // Keep this last - NVML_PERF_POLICY_COUNT -}nvmlPerfPolicyType_t; - -/** - * Struct to hold perf policy violation status data - */ -typedef struct nvmlViolationTime_st -{ - unsigned long long referenceTime; //!< referenceTime represents CPU timestamp in microseconds - unsigned long long violationTime; //!< violationTime in Nanoseconds -}nvmlViolationTime_t; - -/** @} */ - -/***************************************************************************************************/ -/** @defgroup nvmlDeviceEnumvs Device Enums - * @{ - */ -/***************************************************************************************************/ - -/** - * Generic enable/disable enum. - */ -typedef enum nvmlEnableState_enum -{ - NVML_FEATURE_DISABLED = 0, //!< Feature disabled - NVML_FEATURE_ENABLED = 1 //!< Feature enabled -} nvmlEnableState_t; - -//! Generic flag used to specify the default behavior of some functions. See description of particular functions for details. -#define nvmlFlagDefault 0x00 -//! Generic flag used to force some behavior. See description of particular functions for details. -#define nvmlFlagForce 0x01 - -/** - * * The Brand of the GPU - * */ -typedef enum nvmlBrandType_enum -{ - NVML_BRAND_UNKNOWN = 0, - NVML_BRAND_QUADRO = 1, - NVML_BRAND_TESLA = 2, - NVML_BRAND_NVS = 3, - NVML_BRAND_GRID = 4, - NVML_BRAND_GEFORCE = 5, - - // Keep this last - NVML_BRAND_COUNT -} nvmlBrandType_t; - -/** - * Temperature thresholds. - */ -typedef enum nvmlTemperatureThresholds_enum -{ - NVML_TEMPERATURE_THRESHOLD_SHUTDOWN = 0, // Temperature at which the GPU will shut down - // for HW protection - NVML_TEMPERATURE_THRESHOLD_SLOWDOWN = 1, // Temperature at which the GPU will begin slowdown - // Keep this last - NVML_TEMPERATURE_THRESHOLD_COUNT -} nvmlTemperatureThresholds_t; - -/** - * Temperature sensors. - */ -typedef enum nvmlTemperatureSensors_enum -{ - NVML_TEMPERATURE_GPU = 0, //!< Temperature sensor for the GPU die - - // Keep this last - NVML_TEMPERATURE_COUNT -} nvmlTemperatureSensors_t; - -/** - * Compute mode. - * - * NVML_COMPUTEMODE_EXCLUSIVE_PROCESS was added in CUDA 4.0. - * Earlier CUDA versions supported a single exclusive mode, - * which is equivalent to NVML_COMPUTEMODE_EXCLUSIVE_THREAD in CUDA 4.0 and beyond. - */ -typedef enum nvmlComputeMode_enum -{ - NVML_COMPUTEMODE_DEFAULT = 0, //!< Default compute mode -- multiple contexts per device - NVML_COMPUTEMODE_EXCLUSIVE_THREAD = 1, //!< Support Removed - NVML_COMPUTEMODE_PROHIBITED = 2, //!< Compute-prohibited mode -- no contexts per device - NVML_COMPUTEMODE_EXCLUSIVE_PROCESS = 3, //!< Compute-exclusive-process mode -- only one context per device, usable from multiple threads at a time - - // Keep this last - NVML_COMPUTEMODE_COUNT -} nvmlComputeMode_t; - -/** - * ECC bit types. - * - * @deprecated See \ref nvmlMemoryErrorType_t for a more flexible type - */ -#define nvmlEccBitType_t nvmlMemoryErrorType_t - -/** - * Single bit ECC errors - * - * @deprecated Mapped to \ref NVML_MEMORY_ERROR_TYPE_CORRECTED - */ -#define NVML_SINGLE_BIT_ECC NVML_MEMORY_ERROR_TYPE_CORRECTED - -/** - * Double bit ECC errors - * - * @deprecated Mapped to \ref NVML_MEMORY_ERROR_TYPE_UNCORRECTED - */ -#define NVML_DOUBLE_BIT_ECC NVML_MEMORY_ERROR_TYPE_UNCORRECTED - -/** - * Memory error types - */ -typedef enum nvmlMemoryErrorType_enum -{ - /** - * A memory error that was corrected - * - * For ECC errors, these are single bit errors - * For Texture memory, these are errors fixed by resend - */ - NVML_MEMORY_ERROR_TYPE_CORRECTED = 0, - /** - * A memory error that was not corrected - * - * For ECC errors, these are double bit errors - * For Texture memory, these are errors where the resend fails - */ - NVML_MEMORY_ERROR_TYPE_UNCORRECTED = 1, - - - // Keep this last - NVML_MEMORY_ERROR_TYPE_COUNT //!< Count of memory error types - -} nvmlMemoryErrorType_t; - -/** - * ECC counter types. - * - * Note: Volatile counts are reset each time the driver loads. On Windows this is once per boot. On Linux this can be more frequent. - * On Linux the driver unloads when no active clients exist. If persistence mode is enabled or there is always a driver - * client active (e.g. X11), then Linux also sees per-boot behavior. If not, volatile counts are reset each time a compute app - * is run. - */ -typedef enum nvmlEccCounterType_enum -{ - NVML_VOLATILE_ECC = 0, //!< Volatile counts are reset each time the driver loads. - NVML_AGGREGATE_ECC = 1, //!< Aggregate counts persist across reboots (i.e. for the lifetime of the device) - - // Keep this last - NVML_ECC_COUNTER_TYPE_COUNT //!< Count of memory counter types -} nvmlEccCounterType_t; - -/** - * Clock types. - * - * All speeds are in Mhz. - */ -typedef enum nvmlClockType_enum -{ - NVML_CLOCK_GRAPHICS = 0, //!< Graphics clock domain - NVML_CLOCK_SM = 1, //!< SM clock domain - NVML_CLOCK_MEM = 2, //!< Memory clock domain - NVML_CLOCK_VIDEO = 3, //!< Video encoder/decoder clock domain - - // Keep this last - NVML_CLOCK_COUNT //usedGpuMemory is not supported - - - unsigned long long time; //!< Amount of time in ms during which the compute context was active. The time is reported as 0 if - //!< the process is not terminated - - unsigned long long startTime; //!< CPU Timestamp in usec representing start time for the process - - unsigned int isRunning; //!< Flag to represent if the process is running (1 for running, 0 for terminated) - - unsigned int reserved[5]; //!< Reserved for future use -} nvmlAccountingStats_t; - -/** @} */ - -/***************************************************************************************************/ -/** @defgroup nvmlVgpuConstants Vgpu Constants - * @{ - */ -/***************************************************************************************************/ - -/** - * Buffer size guaranteed to be large enough for \ref nvmlVgpuTypeGetLicense - */ -#define NVML_GRID_LICENSE_BUFFER_SIZE 128 - -#define NVML_VGPU_NAME_BUFFER_SIZE 64 - -#define NVML_MAX_VGPU_TYPES_PER_PGPU 17 - -#define NVML_MAX_VGPU_INSTANCES_PER_PGPU 24 - -#define NVML_GRID_LICENSE_FEATURE_MAX_COUNT 3 - -#define NVML_GRID_LICENSE_INFO_MAX_LENGTH 128 - -/** @} */ - -/***************************************************************************************************/ -/** @defgroup nvmlVgpuEnum Vgpu Enum - * @{ - */ -/***************************************************************************************************/ - -/*! - * Types of VM identifiers - */ -typedef enum nvmlVgpuVmIdType { - NVML_VGPU_VM_ID_DOMAIN_ID = 0, //!< VM ID represents DOMAIN ID - NVML_VGPU_VM_ID_UUID = 1, //!< VM ID represents UUID -} nvmlVgpuVmIdType_t; - -// vGPU GUEST info state. -typedef enum nvmlVgpuGuestInfoState_enum -{ - NVML_VGPU_INSTANCE_GUEST_INFO_STATE_UNINITIALIZED = 0, //= 0 and < \a unitCount - * @param unit Reference in which to return the unit handle - * - * @return - * - \ref NVML_SUCCESS if \a unit has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a index is invalid or \a unit is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlUnitGetHandleByIndex(unsigned int index, nvmlUnit_t *unit); - -/** - * Retrieves the static information associated with a unit. - * - * For S-class products. - * - * See \ref nvmlUnitInfo_t for details on available unit info. - * - * @param unit The identifier of the target unit - * @param info Reference in which to return the unit information - * - * @return - * - \ref NVML_SUCCESS if \a info has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a unit is invalid or \a info is NULL - */ -nvmlReturn_t DECLDIR nvmlUnitGetUnitInfo(nvmlUnit_t unit, nvmlUnitInfo_t *info); - -/** - * Retrieves the LED state associated with this unit. - * - * For S-class products. - * - * See \ref nvmlLedState_t for details on allowed states. - * - * @param unit The identifier of the target unit - * @param state Reference in which to return the current LED state - * - * @return - * - \ref NVML_SUCCESS if \a state has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a unit is invalid or \a state is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if this is not an S-class product - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlUnitSetLedState() - */ -nvmlReturn_t DECLDIR nvmlUnitGetLedState(nvmlUnit_t unit, nvmlLedState_t *state); - -/** - * Retrieves the PSU stats for the unit. - * - * For S-class products. - * - * See \ref nvmlPSUInfo_t for details on available PSU info. - * - * @param unit The identifier of the target unit - * @param psu Reference in which to return the PSU information - * - * @return - * - \ref NVML_SUCCESS if \a psu has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a unit is invalid or \a psu is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if this is not an S-class product - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlUnitGetPsuInfo(nvmlUnit_t unit, nvmlPSUInfo_t *psu); - -/** - * Retrieves the temperature readings for the unit, in degrees C. - * - * For S-class products. - * - * Depending on the product, readings may be available for intake (type=0), - * exhaust (type=1) and board (type=2). - * - * @param unit The identifier of the target unit - * @param type The type of reading to take - * @param temp Reference in which to return the intake temperature - * - * @return - * - \ref NVML_SUCCESS if \a temp has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a unit or \a type is invalid or \a temp is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if this is not an S-class product - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlUnitGetTemperature(nvmlUnit_t unit, unsigned int type, unsigned int *temp); - -/** - * Retrieves the fan speed readings for the unit. - * - * For S-class products. - * - * See \ref nvmlUnitFanSpeeds_t for details on available fan speed info. - * - * @param unit The identifier of the target unit - * @param fanSpeeds Reference in which to return the fan speed information - * - * @return - * - \ref NVML_SUCCESS if \a fanSpeeds has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a unit is invalid or \a fanSpeeds is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if this is not an S-class product - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlUnitGetFanSpeedInfo(nvmlUnit_t unit, nvmlUnitFanSpeeds_t *fanSpeeds); - -/** - * Retrieves the set of GPU devices that are attached to the specified unit. - * - * For S-class products. - * - * The \a deviceCount argument is expected to be set to the size of the input \a devices array. - * - * @param unit The identifier of the target unit - * @param deviceCount Reference in which to provide the \a devices array size, and - * to return the number of attached GPU devices - * @param devices Reference in which to return the references to the attached GPU devices - * - * @return - * - \ref NVML_SUCCESS if \a deviceCount and \a devices have been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a deviceCount indicates that the \a devices array is too small - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a unit is invalid, either of \a deviceCount or \a devices is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlUnitGetDevices(nvmlUnit_t unit, unsigned int *deviceCount, nvmlDevice_t *devices); - -/** - * Retrieves the IDs and firmware versions for any Host Interface Cards (HICs) in the system. - * - * For S-class products. - * - * The \a hwbcCount argument is expected to be set to the size of the input \a hwbcEntries array. - * The HIC must be connected to an S-class system for it to be reported by this function. - * - * @param hwbcCount Size of hwbcEntries array - * @param hwbcEntries Array holding information about hwbc - * - * @return - * - \ref NVML_SUCCESS if \a hwbcCount and \a hwbcEntries have been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if either \a hwbcCount or \a hwbcEntries is NULL - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a hwbcCount indicates that the \a hwbcEntries array is too small - */ -nvmlReturn_t DECLDIR nvmlSystemGetHicVersion(unsigned int *hwbcCount, nvmlHwbcEntry_t *hwbcEntries); -/** @} */ - -/***************************************************************************************************/ -/** @defgroup nvmlDeviceQueries Device Queries - * This chapter describes that queries that NVML can perform against each device. - * In each case the device is identified with an nvmlDevice_t handle. This handle is obtained by - * calling one of \ref nvmlDeviceGetHandleByIndex(), \ref nvmlDeviceGetHandleBySerial(), - * \ref nvmlDeviceGetHandleByPciBusId(). or \ref nvmlDeviceGetHandleByUUID(). - * @{ - */ -/***************************************************************************************************/ - - /** - * Retrieves the number of compute devices in the system. A compute device is a single GPU. - * - * For all products. - * - * Note: New nvmlDeviceGetCount_v2 (default in NVML 5.319) returns count of all devices in the system - * even if nvmlDeviceGetHandleByIndex_v2 returns NVML_ERROR_NO_PERMISSION for such device. - * Update your code to handle this error, or use NVML 4.304 or older nvml header file. - * For backward binary compatibility reasons _v1 version of the API is still present in the shared - * library. - * Old _v1 version of nvmlDeviceGetCount doesn't count devices that NVML has no permission to talk to. - * - * @param deviceCount Reference in which to return the number of accessible devices - * - * @return - * - \ref NVML_SUCCESS if \a deviceCount has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a deviceCount is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetCount(unsigned int *deviceCount); - -/** - * Acquire the handle for a particular device, based on its index. - * - * For all products. - * - * Valid indices are derived from the \a accessibleDevices count returned by - * \ref nvmlDeviceGetCount(). For example, if \a accessibleDevices is 2 the valid indices - * are 0 and 1, corresponding to GPU 0 and GPU 1. - * - * The order in which NVML enumerates devices has no guarantees of consistency between reboots. For that reason it - * is recommended that devices be looked up by their PCI ids or UUID. See - * \ref nvmlDeviceGetHandleByUUID() and \ref nvmlDeviceGetHandleByPciBusId(). - * - * Note: The NVML index may not correlate with other APIs, such as the CUDA device index. - * - * Starting from NVML 5, this API causes NVML to initialize the target GPU - * NVML may initialize additional GPUs if: - * - The target GPU is an SLI slave - * - * Note: New nvmlDeviceGetCount_v2 (default in NVML 5.319) returns count of all devices in the system - * even if nvmlDeviceGetHandleByIndex_v2 returns NVML_ERROR_NO_PERMISSION for such device. - * Update your code to handle this error, or use NVML 4.304 or older nvml header file. - * For backward binary compatibility reasons _v1 version of the API is still present in the shared - * library. - * Old _v1 version of nvmlDeviceGetCount doesn't count devices that NVML has no permission to talk to. - * - * This means that nvmlDeviceGetHandleByIndex_v2 and _v1 can return different devices for the same index. - * If you don't touch macros that map old (_v1) versions to _v2 versions at the top of the file you don't - * need to worry about that. - * - * @param index The index of the target GPU, >= 0 and < \a accessibleDevices - * @param device Reference in which to return the device handle - * - * @return - * - \ref NVML_SUCCESS if \a device has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a index is invalid or \a device is NULL - * - \ref NVML_ERROR_INSUFFICIENT_POWER if any attached devices have improperly attached external power cables - * - \ref NVML_ERROR_NO_PERMISSION if the user doesn't have permission to talk to this device - * - \ref NVML_ERROR_IRQ_ISSUE if NVIDIA kernel detected an interrupt issue with the attached GPUs - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetIndex - * @see nvmlDeviceGetCount - */ -nvmlReturn_t DECLDIR nvmlDeviceGetHandleByIndex(unsigned int index, nvmlDevice_t *device); - -/** - * Acquire the handle for a particular device, based on its board serial number. - * - * For Fermi &tm; or newer fully supported devices. - * - * This number corresponds to the value printed directly on the board, and to the value returned by - * \ref nvmlDeviceGetSerial(). - * - * @deprecated Since more than one GPU can exist on a single board this function is deprecated in favor - * of \ref nvmlDeviceGetHandleByUUID. - * For dual GPU boards this function will return NVML_ERROR_INVALID_ARGUMENT. - * - * Starting from NVML 5, this API causes NVML to initialize the target GPU - * NVML may initialize additional GPUs as it searches for the target GPU - * - * @param serial The board serial number of the target GPU - * @param device Reference in which to return the device handle - * - * @return - * - \ref NVML_SUCCESS if \a device has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a serial is invalid, \a device is NULL or more than one - * device has the same serial (dual GPU boards) - * - \ref NVML_ERROR_NOT_FOUND if \a serial does not match a valid device on the system - * - \ref NVML_ERROR_INSUFFICIENT_POWER if any attached devices have improperly attached external power cables - * - \ref NVML_ERROR_IRQ_ISSUE if NVIDIA kernel detected an interrupt issue with the attached GPUs - * - \ref NVML_ERROR_GPU_IS_LOST if any GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetSerial - * @see nvmlDeviceGetHandleByUUID - */ -nvmlReturn_t DECLDIR nvmlDeviceGetHandleBySerial(const char *serial, nvmlDevice_t *device); - -/** - * Acquire the handle for a particular device, based on its globally unique immutable UUID associated with each device. - * - * For all products. - * - * @param uuid The UUID of the target GPU - * @param device Reference in which to return the device handle - * - * Starting from NVML 5, this API causes NVML to initialize the target GPU - * NVML may initialize additional GPUs as it searches for the target GPU - * - * @return - * - \ref NVML_SUCCESS if \a device has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a uuid is invalid or \a device is null - * - \ref NVML_ERROR_NOT_FOUND if \a uuid does not match a valid device on the system - * - \ref NVML_ERROR_INSUFFICIENT_POWER if any attached devices have improperly attached external power cables - * - \ref NVML_ERROR_IRQ_ISSUE if NVIDIA kernel detected an interrupt issue with the attached GPUs - * - \ref NVML_ERROR_GPU_IS_LOST if any GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetUUID - */ -nvmlReturn_t DECLDIR nvmlDeviceGetHandleByUUID(const char *uuid, nvmlDevice_t *device); - -/** - * Acquire the handle for a particular device, based on its PCI bus id. - * - * For all products. - * - * This value corresponds to the nvmlPciInfo_t::busId returned by \ref nvmlDeviceGetPciInfo(). - * - * Starting from NVML 5, this API causes NVML to initialize the target GPU - * NVML may initialize additional GPUs if: - * - The target GPU is an SLI slave - * - * \note NVML 4.304 and older version of nvmlDeviceGetHandleByPciBusId"_v1" returns NVML_ERROR_NOT_FOUND - * instead of NVML_ERROR_NO_PERMISSION. - * - * @param pciBusId The PCI bus id of the target GPU - * @param device Reference in which to return the device handle - * - * @return - * - \ref NVML_SUCCESS if \a device has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a pciBusId is invalid or \a device is NULL - * - \ref NVML_ERROR_NOT_FOUND if \a pciBusId does not match a valid device on the system - * - \ref NVML_ERROR_INSUFFICIENT_POWER if the attached device has improperly attached external power cables - * - \ref NVML_ERROR_NO_PERMISSION if the user doesn't have permission to talk to this device - * - \ref NVML_ERROR_IRQ_ISSUE if NVIDIA kernel detected an interrupt issue with the attached GPUs - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetHandleByPciBusId(const char *pciBusId, nvmlDevice_t *device); - -/** - * Retrieves the name of this device. - * - * For all products. - * - * The name is an alphanumeric string that denotes a particular product, e.g. Tesla &tm; C2070. It will not - * exceed 64 characters in length (including the NULL terminator). See \ref - * nvmlConstants::NVML_DEVICE_NAME_BUFFER_SIZE. - * - * @param device The identifier of the target device - * @param name Reference in which to return the product name - * @param length The maximum allowed length of the string returned in \a name - * - * @return - * - \ref NVML_SUCCESS if \a name has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, or \a name is NULL - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a length is too small - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetName(nvmlDevice_t device, char *name, unsigned int length); - -/** - * Retrieves the brand of this device. - * - * For all products. - * - * The type is a member of \ref nvmlBrandType_t defined above. - * - * @param device The identifier of the target device - * @param type Reference in which to return the product brand type - * - * @return - * - \ref NVML_SUCCESS if \a name has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, or \a type is NULL - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetBrand(nvmlDevice_t device, nvmlBrandType_t *type); - -/** - * Retrieves the NVML index of this device. - * - * For all products. - * - * Valid indices are derived from the \a accessibleDevices count returned by - * \ref nvmlDeviceGetCount(). For example, if \a accessibleDevices is 2 the valid indices - * are 0 and 1, corresponding to GPU 0 and GPU 1. - * - * The order in which NVML enumerates devices has no guarantees of consistency between reboots. For that reason it - * is recommended that devices be looked up by their PCI ids or GPU UUID. See - * \ref nvmlDeviceGetHandleByPciBusId() and \ref nvmlDeviceGetHandleByUUID(). - * - * Note: The NVML index may not correlate with other APIs, such as the CUDA device index. - * - * @param device The identifier of the target device - * @param index Reference in which to return the NVML index of the device - * - * @return - * - \ref NVML_SUCCESS if \a index has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, or \a index is NULL - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetHandleByIndex() - * @see nvmlDeviceGetCount() - */ -nvmlReturn_t DECLDIR nvmlDeviceGetIndex(nvmlDevice_t device, unsigned int *index); - -/** - * Retrieves the globally unique board serial number associated with this device's board. - * - * For all products with an inforom. - * - * The serial number is an alphanumeric string that will not exceed 30 characters (including the NULL terminator). - * This number matches the serial number tag that is physically attached to the board. See \ref - * nvmlConstants::NVML_DEVICE_SERIAL_BUFFER_SIZE. - * - * @param device The identifier of the target device - * @param serial Reference in which to return the board/module serial number - * @param length The maximum allowed length of the string returned in \a serial - * - * @return - * - \ref NVML_SUCCESS if \a serial has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, or \a serial is NULL - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a length is too small - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetSerial(nvmlDevice_t device, char *serial, unsigned int length); - -/** - * Retrieves an array of unsigned ints (sized to cpuSetSize) of bitmasks with the ideal CPU affinity for the device - * For example, if processors 0, 1, 32, and 33 are ideal for the device and cpuSetSize == 2, - * result[0] = 0x3, result[1] = 0x3 - * - * For Kepler &tm; or newer fully supported devices. - * Supported on Linux only. - * - * @param device The identifier of the target device - * @param cpuSetSize The size of the cpuSet array that is safe to access - * @param cpuSet Array reference in which to return a bitmask of CPUs, 64 CPUs per - * unsigned long on 64-bit machines, 32 on 32-bit machines - * - * @return - * - \ref NVML_SUCCESS if \a cpuAffinity has been filled - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, cpuSetSize == 0, or cpuSet is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetCpuAffinity(nvmlDevice_t device, unsigned int cpuSetSize, unsigned long *cpuSet); - -/** - * Sets the ideal affinity for the calling thread and device using the guidelines - * given in nvmlDeviceGetCpuAffinity(). Note, this is a change as of version 8.0. - * Older versions set the affinity for a calling process and all children. - * Currently supports up to 64 processors. - * - * For Kepler &tm; or newer fully supported devices. - * Supported on Linux only. - * - * @param device The identifier of the target device - * - * @return - * - \ref NVML_SUCCESS if the calling process has been successfully bound - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceSetCpuAffinity(nvmlDevice_t device); - -/** - * Clear all affinity bindings for the calling thread. Note, this is a change as of version - * 8.0 as older versions cleared the affinity for a calling process and all children. - * - * For Kepler &tm; or newer fully supported devices. - * Supported on Linux only. - * - * @param device The identifier of the target device - * - * @return - * - \ref NVML_SUCCESS if the calling process has been successfully unbound - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceClearCpuAffinity(nvmlDevice_t device); - -/** - * Retrieve the common ancestor for two devices - * For all products. - * Supported on Linux only. - * - * @param device1 The identifier of the first device - * @param device2 The identifier of the second device - * @param pathInfo A \ref nvmlGpuTopologyLevel_t that gives the path type - * - * @return - * - \ref NVML_SUCCESS if \a pathInfo has been set - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device1, or \a device2 is invalid, or \a pathInfo is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device or OS does not support this feature - * - \ref NVML_ERROR_UNKNOWN an error has occurred in underlying topology discovery - */ -nvmlReturn_t DECLDIR nvmlDeviceGetTopologyCommonAncestor(nvmlDevice_t device1, nvmlDevice_t device2, nvmlGpuTopologyLevel_t *pathInfo); - -/** - * Retrieve the set of GPUs that are nearest to a given device at a specific interconnectivity level - * For all products. - * Supported on Linux only. - * - * @param device The identifier of the first device - * @param level The \ref nvmlGpuTopologyLevel_t level to search for other GPUs - * @param count When zero, is set to the number of matching GPUs such that \a deviceArray - * can be malloc'd. When non-zero, \a deviceArray will be filled with \a count - * number of device handles. - * @param deviceArray An array of device handles for GPUs found at \a level - * - * @return - * - \ref NVML_SUCCESS if \a deviceArray or \a count (if initially zero) has been set - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device, \a level, or \a count is invalid, or \a deviceArray is NULL with a non-zero \a count - * - \ref NVML_ERROR_NOT_SUPPORTED if the device or OS does not support this feature - * - \ref NVML_ERROR_UNKNOWN an error has occurred in underlying topology discovery - */ -nvmlReturn_t DECLDIR nvmlDeviceGetTopologyNearestGpus(nvmlDevice_t device, nvmlGpuTopologyLevel_t level, unsigned int *count, nvmlDevice_t *deviceArray); - -/** - * Retrieve the set of GPUs that have a CPU affinity with the given CPU number - * For all products. - * Supported on Linux only. - * - * @param cpuNumber The CPU number - * @param count When zero, is set to the number of matching GPUs such that \a deviceArray - * can be malloc'd. When non-zero, \a deviceArray will be filled with \a count - * number of device handles. - * @param deviceArray An array of device handles for GPUs found with affinity to \a cpuNumber - * - * @return - * - \ref NVML_SUCCESS if \a deviceArray or \a count (if initially zero) has been set - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a cpuNumber, or \a count is invalid, or \a deviceArray is NULL with a non-zero \a count - * - \ref NVML_ERROR_NOT_SUPPORTED if the device or OS does not support this feature - * - \ref NVML_ERROR_UNKNOWN an error has occurred in underlying topology discovery - */ -nvmlReturn_t DECLDIR nvmlSystemGetTopologyGpuSet(unsigned int cpuNumber, unsigned int *count, nvmlDevice_t *deviceArray); - -/** - * Retrieve the status for a given p2p capability index between a given pair of GPU - * - * @param device1 The first device - * @param device2 The second device - * @param p2pIndex p2p Capability Index being looked for between \a device1 and \a device2 - * @param p2pStatus Reference in which to return the status of the \a p2pIndex - * between \a device1 and \a device2 - * @return - * - \ref NVML_SUCCESS if \a p2pStatus has been populated - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device1 or \a device2 or \a p2pIndex is invalid or \a p2pStatus is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetP2PStatus(nvmlDevice_t device1, nvmlDevice_t device2, nvmlGpuP2PCapsIndex_t p2pIndex,nvmlGpuP2PStatus_t *p2pStatus); - -/** - * Retrieves the globally unique immutable UUID associated with this device, as a 5 part hexadecimal string, - * that augments the immutable, board serial identifier. - * - * For all products. - * - * The UUID is a globally unique identifier. It is the only available identifier for pre-Fermi-architecture products. - * It does NOT correspond to any identifier printed on the board. It will not exceed 80 characters in length - * (including the NULL terminator). See \ref nvmlConstants::NVML_DEVICE_UUID_BUFFER_SIZE. - * - * @param device The identifier of the target device - * @param uuid Reference in which to return the GPU UUID - * @param length The maximum allowed length of the string returned in \a uuid - * - * @return - * - \ref NVML_SUCCESS if \a uuid has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, or \a uuid is NULL - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a length is too small - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetUUID(nvmlDevice_t device, char *uuid, unsigned int length); - -/** - * Retrieves minor number for the device. The minor number for the device is such that the Nvidia device node file for - * each GPU will have the form /dev/nvidia[minor number]. - * - * For all products. - * Supported only for Linux - * - * @param device The identifier of the target device - * @param minorNumber Reference in which to return the minor number for the device - * @return - * - \ref NVML_SUCCESS if the minor number is successfully retrieved - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a minorNumber is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if this query is not supported by the device - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetMinorNumber(nvmlDevice_t device, unsigned int *minorNumber); - -/** - * Retrieves the the device board part number which is programmed into the board's InfoROM - * - * For all products. - * - * @param device Identifier of the target device - * @param partNumber Reference to the buffer to return - * @param length Length of the buffer reference - * - * @return - * - \ref NVML_SUCCESS if \a partNumber has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_NOT_SUPPORTED if the needed VBIOS fields have not been filled - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a serial is NULL - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetBoardPartNumber(nvmlDevice_t device, char* partNumber, unsigned int length); - -/** - * Retrieves the version information for the device's infoROM object. - * - * For all products with an inforom. - * - * Fermi and higher parts have non-volatile on-board memory for persisting device info, such as aggregate - * ECC counts. The version of the data structures in this memory may change from time to time. It will not - * exceed 16 characters in length (including the NULL terminator). - * See \ref nvmlConstants::NVML_DEVICE_INFOROM_VERSION_BUFFER_SIZE. - * - * See \ref nvmlInforomObject_t for details on the available infoROM objects. - * - * @param device The identifier of the target device - * @param object The target infoROM object - * @param version Reference in which to return the infoROM version - * @param length The maximum allowed length of the string returned in \a version - * - * @return - * - \ref NVML_SUCCESS if \a version has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a version is NULL - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a length is too small - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not have an infoROM - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetInforomImageVersion - */ -nvmlReturn_t DECLDIR nvmlDeviceGetInforomVersion(nvmlDevice_t device, nvmlInforomObject_t object, char *version, unsigned int length); - -/** - * Retrieves the global infoROM image version - * - * For all products with an inforom. - * - * Image version just like VBIOS version uniquely describes the exact version of the infoROM flashed on the board - * in contrast to infoROM object version which is only an indicator of supported features. - * Version string will not exceed 16 characters in length (including the NULL terminator). - * See \ref nvmlConstants::NVML_DEVICE_INFOROM_VERSION_BUFFER_SIZE. - * - * @param device The identifier of the target device - * @param version Reference in which to return the infoROM image version - * @param length The maximum allowed length of the string returned in \a version - * - * @return - * - \ref NVML_SUCCESS if \a version has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a version is NULL - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a length is too small - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not have an infoROM - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetInforomVersion - */ -nvmlReturn_t DECLDIR nvmlDeviceGetInforomImageVersion(nvmlDevice_t device, char *version, unsigned int length); - -/** - * Retrieves the checksum of the configuration stored in the device's infoROM. - * - * For all products with an inforom. - * - * Can be used to make sure that two GPUs have the exact same configuration. - * Current checksum takes into account configuration stored in PWR and ECC infoROM objects. - * Checksum can change between driver releases or when user changes configuration (e.g. disable/enable ECC) - * - * @param device The identifier of the target device - * @param checksum Reference in which to return the infoROM configuration checksum - * - * @return - * - \ref NVML_SUCCESS if \a checksum has been set - * - \ref NVML_ERROR_CORRUPTED_INFOROM if the device's checksum couldn't be retrieved due to infoROM corruption - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a checksum is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetInforomConfigurationChecksum(nvmlDevice_t device, unsigned int *checksum); - -/** - * Reads the infoROM from the flash and verifies the checksums. - * - * For all products with an inforom. - * - * @param device The identifier of the target device - * - * @return - * - \ref NVML_SUCCESS if infoROM is not corrupted - * - \ref NVML_ERROR_CORRUPTED_INFOROM if the device's infoROM is corrupted - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceValidateInforom(nvmlDevice_t device); - -/** - * Retrieves the display mode for the device. - * - * For all products. - * - * This method indicates whether a physical display (e.g. monitor) is currently connected to - * any of the device's connectors. - * - * See \ref nvmlEnableState_t for details on allowed modes. - * - * @param device The identifier of the target device - * @param display Reference in which to return the display mode - * - * @return - * - \ref NVML_SUCCESS if \a display has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a display is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetDisplayMode(nvmlDevice_t device, nvmlEnableState_t *display); - -/** - * Retrieves the display active state for the device. - * - * For all products. - * - * This method indicates whether a display is initialized on the device. - * For example whether X Server is attached to this device and has allocated memory for the screen. - * - * Display can be active even when no monitor is physically attached. - * - * See \ref nvmlEnableState_t for details on allowed modes. - * - * @param device The identifier of the target device - * @param isActive Reference in which to return the display active state - * - * @return - * - \ref NVML_SUCCESS if \a isActive has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a isActive is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetDisplayActive(nvmlDevice_t device, nvmlEnableState_t *isActive); - -/** - * Retrieves the persistence mode associated with this device. - * - * For all products. - * For Linux only. - * - * When driver persistence mode is enabled the driver software state is not torn down when the last - * client disconnects. By default this feature is disabled. - * - * See \ref nvmlEnableState_t for details on allowed modes. - * - * @param device The identifier of the target device - * @param mode Reference in which to return the current driver persistence mode - * - * @return - * - \ref NVML_SUCCESS if \a mode has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a mode is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceSetPersistenceMode() - */ -nvmlReturn_t DECLDIR nvmlDeviceGetPersistenceMode(nvmlDevice_t device, nvmlEnableState_t *mode); - -/** - * Retrieves the PCI attributes of this device. - * - * For all products. - * - * See \ref nvmlPciInfo_t for details on the available PCI info. - * - * @param device The identifier of the target device - * @param pci Reference in which to return the PCI info - * - * @return - * - \ref NVML_SUCCESS if \a pci has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a pci is NULL - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetPciInfo(nvmlDevice_t device, nvmlPciInfo_t *pci); - -/** - * Retrieves the maximum PCIe link generation possible with this device and system - * - * I.E. for a generation 2 PCIe device attached to a generation 1 PCIe bus the max link generation this function will - * report is generation 1. - * - * For Fermi &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param maxLinkGen Reference in which to return the max PCIe link generation - * - * @return - * - \ref NVML_SUCCESS if \a maxLinkGen has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a maxLinkGen is null - * - \ref NVML_ERROR_NOT_SUPPORTED if PCIe link information is not available - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetMaxPcieLinkGeneration(nvmlDevice_t device, unsigned int *maxLinkGen); - -/** - * Retrieves the maximum PCIe link width possible with this device and system - * - * I.E. for a device with a 16x PCIe bus width attached to a 8x PCIe system bus this function will report - * a max link width of 8. - * - * For Fermi &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param maxLinkWidth Reference in which to return the max PCIe link generation - * - * @return - * - \ref NVML_SUCCESS if \a maxLinkWidth has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a maxLinkWidth is null - * - \ref NVML_ERROR_NOT_SUPPORTED if PCIe link information is not available - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetMaxPcieLinkWidth(nvmlDevice_t device, unsigned int *maxLinkWidth); - -/** - * Retrieves the current PCIe link generation - * - * For Fermi &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param currLinkGen Reference in which to return the current PCIe link generation - * - * @return - * - \ref NVML_SUCCESS if \a currLinkGen has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a currLinkGen is null - * - \ref NVML_ERROR_NOT_SUPPORTED if PCIe link information is not available - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetCurrPcieLinkGeneration(nvmlDevice_t device, unsigned int *currLinkGen); - -/** - * Retrieves the current PCIe link width - * - * For Fermi &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param currLinkWidth Reference in which to return the current PCIe link generation - * - * @return - * - \ref NVML_SUCCESS if \a currLinkWidth has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a currLinkWidth is null - * - \ref NVML_ERROR_NOT_SUPPORTED if PCIe link information is not available - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetCurrPcieLinkWidth(nvmlDevice_t device, unsigned int *currLinkWidth); - -/** - * Retrieve PCIe utilization information. - * This function is querying a byte counter over a 20ms interval and thus is the - * PCIe throughput over that interval. - * - * For Maxwell &tm; or newer fully supported devices. - * - * This method is not supported in virtual machines running virtual GPU (vGPU). - * - * @param device The identifier of the target device - * @param counter The specific counter that should be queried \ref nvmlPcieUtilCounter_t - * @param value Reference in which to return throughput in KB/s - * - * @return - * - \ref NVML_SUCCESS if \a value has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device or \a counter is invalid, or \a value is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetPcieThroughput(nvmlDevice_t device, nvmlPcieUtilCounter_t counter, unsigned int *value); - -/** - * Retrieve the PCIe replay counter. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param value Reference in which to return the counter's value - * - * @return - * - \ref NVML_SUCCESS if \a value and \a rollover have been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, or \a value or \a rollover are NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetPcieReplayCounter(nvmlDevice_t device, unsigned int *value); - -/** - * Retrieves the current clock speeds for the device. - * - * For Fermi &tm; or newer fully supported devices. - * - * See \ref nvmlClockType_t for details on available clock information. - * - * @param device The identifier of the target device - * @param type Identify which clock domain to query - * @param clock Reference in which to return the clock speed in MHz - * - * @return - * - \ref NVML_SUCCESS if \a clock has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a clock is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device cannot report the specified clock - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetClockInfo(nvmlDevice_t device, nvmlClockType_t type, unsigned int *clock); - -/** - * Retrieves the maximum clock speeds for the device. - * - * For Fermi &tm; or newer fully supported devices. - * - * See \ref nvmlClockType_t for details on available clock information. - * - * \note On GPUs from Fermi family current P0 clocks (reported by \ref nvmlDeviceGetClockInfo) can differ from max clocks - * by few MHz. - * - * @param device The identifier of the target device - * @param type Identify which clock domain to query - * @param clock Reference in which to return the clock speed in MHz - * - * @return - * - \ref NVML_SUCCESS if \a clock has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a clock is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device cannot report the specified clock - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetMaxClockInfo(nvmlDevice_t device, nvmlClockType_t type, unsigned int *clock); - -/** - * Retrieves the current setting of a clock that applications will use unless an overspec situation occurs. - * Can be changed using \ref nvmlDeviceSetApplicationsClocks. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param clockType Identify which clock domain to query - * @param clockMHz Reference in which to return the clock in MHz - * - * @return - * - \ref NVML_SUCCESS if \a clockMHz has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a clockMHz is NULL or \a clockType is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetApplicationsClock(nvmlDevice_t device, nvmlClockType_t clockType, unsigned int *clockMHz); - -/** - * Retrieves the default applications clock that GPU boots with or - * defaults to after \ref nvmlDeviceResetApplicationsClocks call. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param clockType Identify which clock domain to query - * @param clockMHz Reference in which to return the default clock in MHz - * - * @return - * - \ref NVML_SUCCESS if \a clockMHz has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a clockMHz is NULL or \a clockType is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * \see nvmlDeviceGetApplicationsClock - */ -nvmlReturn_t DECLDIR nvmlDeviceGetDefaultApplicationsClock(nvmlDevice_t device, nvmlClockType_t clockType, unsigned int *clockMHz); - -/** - * Resets the application clock to the default value - * - * This is the applications clock that will be used after system reboot or driver reload. - * Default value is constant, but the current value an be changed using \ref nvmlDeviceSetApplicationsClocks. - * - * On Pascal and newer hardware, if clocks were previously locked with \ref nvmlDeviceSetApplicationsClocks, - * this call will unlock clocks. This returns clocks their default behavior ofautomatically boosting above - * base clocks as thermal limits allow. - * - * @see nvmlDeviceGetApplicationsClock - * @see nvmlDeviceSetApplicationsClocks - * - * For Fermi &tm; or newer non-GeForce fully supported devices and Maxwell or newer GeForce devices. - * - * @param device The identifier of the target device - * - * @return - * - \ref NVML_SUCCESS if new settings were successfully set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceResetApplicationsClocks(nvmlDevice_t device); - -/** - * Retrieves the clock speed for the clock specified by the clock type and clock ID. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param clockType Identify which clock domain to query - * @param clockId Identify which clock in the domain to query - * @param clockMHz Reference in which to return the clock in MHz - * - * @return - * - \ref NVML_SUCCESS if \a clockMHz has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a clockMHz is NULL or \a clockType is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetClock(nvmlDevice_t device, nvmlClockType_t clockType, nvmlClockId_t clockId, unsigned int *clockMHz); - -/** - * Retrieves the customer defined maximum boost clock speed specified by the given clock type. - * - * For Pascal &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param clockType Identify which clock domain to query - * @param clockMHz Reference in which to return the clock in MHz - * - * @return - * - \ref NVML_SUCCESS if \a clockMHz has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a clockMHz is NULL or \a clockType is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device or the \a clockType on this device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetMaxCustomerBoostClock(nvmlDevice_t device, nvmlClockType_t clockType, unsigned int *clockMHz); - -/** - * Retrieves the list of possible memory clocks that can be used as an argument for \ref nvmlDeviceSetApplicationsClocks. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param count Reference in which to provide the \a clocksMHz array size, and - * to return the number of elements - * @param clocksMHz Reference in which to return the clock in MHz - * - * @return - * - \ref NVML_SUCCESS if \a count and \a clocksMHz have been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a count is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a count is too small (\a count is set to the number of - * required elements) - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceSetApplicationsClocks - * @see nvmlDeviceGetSupportedGraphicsClocks - */ -nvmlReturn_t DECLDIR nvmlDeviceGetSupportedMemoryClocks(nvmlDevice_t device, unsigned int *count, unsigned int *clocksMHz); - -/** - * Retrieves the list of possible graphics clocks that can be used as an argument for \ref nvmlDeviceSetApplicationsClocks. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param memoryClockMHz Memory clock for which to return possible graphics clocks - * @param count Reference in which to provide the \a clocksMHz array size, and - * to return the number of elements - * @param clocksMHz Reference in which to return the clocks in MHz - * - * @return - * - \ref NVML_SUCCESS if \a count and \a clocksMHz have been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_NOT_FOUND if the specified \a memoryClockMHz is not a supported frequency - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a clock is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a count is too small - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceSetApplicationsClocks - * @see nvmlDeviceGetSupportedMemoryClocks - */ -nvmlReturn_t DECLDIR nvmlDeviceGetSupportedGraphicsClocks(nvmlDevice_t device, unsigned int memoryClockMHz, unsigned int *count, unsigned int *clocksMHz); - -/** - * Retrieve the current state of Auto Boosted clocks on a device and store it in \a isEnabled - * - * For Kepler &tm; or newer fully supported devices. - * - * Auto Boosted clocks are enabled by default on some hardware, allowing the GPU to run at higher clock rates - * to maximize performance as thermal limits allow. - * - * On Pascal and newer hardware, Auto Aoosted clocks are controlled through application clocks. - * Use \ref nvmlDeviceSetApplicationsClocks and \ref nvmlDeviceResetApplicationsClocks to control Auto Boost - * behavior. - * - * @param device The identifier of the target device - * @param isEnabled Where to store the current state of Auto Boosted clocks of the target device - * @param defaultIsEnabled Where to store the default Auto Boosted clocks behavior of the target device that the device will - * revert to when no applications are using the GPU - * - * @return - * - \ref NVML_SUCCESS If \a isEnabled has been been set with the Auto Boosted clocks state of \a device - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a isEnabled is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support Auto Boosted clocks - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - */ -nvmlReturn_t DECLDIR nvmlDeviceGetAutoBoostedClocksEnabled(nvmlDevice_t device, nvmlEnableState_t *isEnabled, nvmlEnableState_t *defaultIsEnabled); - -/** - * Try to set the current state of Auto Boosted clocks on a device. - * - * For Kepler &tm; or newer fully supported devices. - * - * Auto Boosted clocks are enabled by default on some hardware, allowing the GPU to run at higher clock rates - * to maximize performance as thermal limits allow. Auto Boosted clocks should be disabled if fixed clock - * rates are desired. - * - * Non-root users may use this API by default but can be restricted by root from using this API by calling - * \ref nvmlDeviceSetAPIRestriction with apiType=NVML_RESTRICTED_API_SET_AUTO_BOOSTED_CLOCKS. - * Note: Persistence Mode is required to modify current Auto Boost settings, therefore, it must be enabled. - * - * On Pascal and newer hardware, Auto Boosted clocks are controlled through application clocks. - * Use \ref nvmlDeviceSetApplicationsClocks and \ref nvmlDeviceResetApplicationsClocks to control Auto Boost - * behavior. - * - * @param device The identifier of the target device - * @param enabled What state to try to set Auto Boosted clocks of the target device to - * - * @return - * - \ref NVML_SUCCESS If the Auto Boosted clocks were successfully set to the state specified by \a enabled - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support Auto Boosted clocks - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - */ -nvmlReturn_t DECLDIR nvmlDeviceSetAutoBoostedClocksEnabled(nvmlDevice_t device, nvmlEnableState_t enabled); - -/** - * Try to set the default state of Auto Boosted clocks on a device. This is the default state that Auto Boosted clocks will - * return to when no compute running processes (e.g. CUDA application which have an active context) are running - * - * For Kepler &tm; or newer non-GeForce fully supported devices and Maxwell or newer GeForce devices. - * Requires root/admin permissions. - * - * Auto Boosted clocks are enabled by default on some hardware, allowing the GPU to run at higher clock rates - * to maximize performance as thermal limits allow. Auto Boosted clocks should be disabled if fixed clock - * rates are desired. - * - * On Pascal and newer hardware, Auto Boosted clocks are controlled through application clocks. - * Use \ref nvmlDeviceSetApplicationsClocks and \ref nvmlDeviceResetApplicationsClocks to control Auto Boost - * behavior. - * - * @param device The identifier of the target device - * @param enabled What state to try to set default Auto Boosted clocks of the target device to - * @param flags Flags that change the default behavior. Currently Unused. - * - * @return - * - \ref NVML_SUCCESS If the Auto Boosted clock's default state was successfully set to the state specified by \a enabled - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_NO_PERMISSION If the calling user does not have permission to change Auto Boosted clock's default state. - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support Auto Boosted clocks - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - */ -nvmlReturn_t DECLDIR nvmlDeviceSetDefaultAutoBoostedClocksEnabled(nvmlDevice_t device, nvmlEnableState_t enabled, unsigned int flags); - - -/** - * Retrieves the intended operating speed of the device's fan. - * - * Note: The reported speed is the intended fan speed. If the fan is physically blocked and unable to spin, the - * output will not match the actual fan speed. - * - * For all discrete products with dedicated fans. - * - * The fan speed is expressed as a percent of the maximum, i.e. full speed is 100%. - * - * @param device The identifier of the target device - * @param speed Reference in which to return the fan speed percentage - * - * @return - * - \ref NVML_SUCCESS if \a speed has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a speed is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not have a fan - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetFanSpeed(nvmlDevice_t device, unsigned int *speed); - -/** - * Retrieves the current temperature readings for the device, in degrees C. - * - * For all products. - * - * See \ref nvmlTemperatureSensors_t for details on available temperature sensors. - * - * @param device The identifier of the target device - * @param sensorType Flag that indicates which sensor reading to retrieve - * @param temp Reference in which to return the temperature reading - * - * @return - * - \ref NVML_SUCCESS if \a temp has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, \a sensorType is invalid or \a temp is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not have the specified sensor - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetTemperature(nvmlDevice_t device, nvmlTemperatureSensors_t sensorType, unsigned int *temp); - -/** - * Retrieves the temperature threshold for the GPU with the specified threshold type in degrees C. - * - * For Kepler &tm; or newer fully supported devices. - * - * See \ref nvmlTemperatureThresholds_t for details on available temperature thresholds. - * - * @param device The identifier of the target device - * @param thresholdType The type of threshold value queried - * @param temp Reference in which to return the temperature reading - * @return - * - \ref NVML_SUCCESS if \a temp has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, \a thresholdType is invalid or \a temp is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not have a temperature sensor or is unsupported - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetTemperatureThreshold(nvmlDevice_t device, nvmlTemperatureThresholds_t thresholdType, unsigned int *temp); - -/** - * Retrieves the current performance state for the device. - * - * For Fermi &tm; or newer fully supported devices. - * - * See \ref nvmlPstates_t for details on allowed performance states. - * - * @param device The identifier of the target device - * @param pState Reference in which to return the performance state reading - * - * @return - * - \ref NVML_SUCCESS if \a pState has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a pState is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetPerformanceState(nvmlDevice_t device, nvmlPstates_t *pState); - -/** - * Retrieves current clocks throttling reasons. - * - * For all fully supported products. - * - * \note More than one bit can be enabled at the same time. Multiple reasons can be affecting clocks at once. - * - * @param device The identifier of the target device - * @param clocksThrottleReasons Reference in which to return bitmask of active clocks throttle - * reasons - * - * @return - * - \ref NVML_SUCCESS if \a clocksThrottleReasons has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a clocksThrottleReasons is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlClocksThrottleReasons - * @see nvmlDeviceGetSupportedClocksThrottleReasons - */ -nvmlReturn_t DECLDIR nvmlDeviceGetCurrentClocksThrottleReasons(nvmlDevice_t device, unsigned long long *clocksThrottleReasons); - -/** - * Retrieves bitmask of supported clocks throttle reasons that can be returned by - * \ref nvmlDeviceGetCurrentClocksThrottleReasons - * - * For all fully supported products. - * - * This method is not supported in virtual machines running virtual GPU (vGPU). - * - * @param device The identifier of the target device - * @param supportedClocksThrottleReasons Reference in which to return bitmask of supported - * clocks throttle reasons - * - * @return - * - \ref NVML_SUCCESS if \a supportedClocksThrottleReasons has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a supportedClocksThrottleReasons is NULL - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlClocksThrottleReasons - * @see nvmlDeviceGetCurrentClocksThrottleReasons - */ -nvmlReturn_t DECLDIR nvmlDeviceGetSupportedClocksThrottleReasons(nvmlDevice_t device, unsigned long long *supportedClocksThrottleReasons); - -/** - * Deprecated: Use \ref nvmlDeviceGetPerformanceState. This function exposes an incorrect generalization. - * - * Retrieve the current performance state for the device. - * - * For Fermi &tm; or newer fully supported devices. - * - * See \ref nvmlPstates_t for details on allowed performance states. - * - * @param device The identifier of the target device - * @param pState Reference in which to return the performance state reading - * - * @return - * - \ref NVML_SUCCESS if \a pState has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a pState is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetPowerState(nvmlDevice_t device, nvmlPstates_t *pState); - -/** - * This API has been deprecated. - * - * Retrieves the power management mode associated with this device. - * - * For products from the Fermi family. - * - Requires \a NVML_INFOROM_POWER version 3.0 or higher. - * - * For from the Kepler or newer families. - * - Does not require \a NVML_INFOROM_POWER object. - * - * This flag indicates whether any power management algorithm is currently active on the device. An - * enabled state does not necessarily mean the device is being actively throttled -- only that - * that the driver will do so if the appropriate conditions are met. - * - * See \ref nvmlEnableState_t for details on allowed modes. - * - * @param device The identifier of the target device - * @param mode Reference in which to return the current power management mode - * - * @return - * - \ref NVML_SUCCESS if \a mode has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a mode is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetPowerManagementMode(nvmlDevice_t device, nvmlEnableState_t *mode); - -/** - * Retrieves the power management limit associated with this device. - * - * For Fermi &tm; or newer fully supported devices. - * - * The power limit defines the upper boundary for the card's power draw. If - * the card's total power draw reaches this limit the power management algorithm kicks in. - * - * This reading is only available if power management mode is supported. - * See \ref nvmlDeviceGetPowerManagementMode. - * - * @param device The identifier of the target device - * @param limit Reference in which to return the power management limit in milliwatts - * - * @return - * - \ref NVML_SUCCESS if \a limit has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a limit is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetPowerManagementLimit(nvmlDevice_t device, unsigned int *limit); - -/** - * Retrieves information about possible values of power management limits on this device. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param minLimit Reference in which to return the minimum power management limit in milliwatts - * @param maxLimit Reference in which to return the maximum power management limit in milliwatts - * - * @return - * - \ref NVML_SUCCESS if \a minLimit and \a maxLimit have been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a minLimit or \a maxLimit is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceSetPowerManagementLimit - */ -nvmlReturn_t DECLDIR nvmlDeviceGetPowerManagementLimitConstraints(nvmlDevice_t device, unsigned int *minLimit, unsigned int *maxLimit); - -/** - * Retrieves default power management limit on this device, in milliwatts. - * Default power management limit is a power management limit that the device boots with. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param defaultLimit Reference in which to return the default power management limit in milliwatts - * - * @return - * - \ref NVML_SUCCESS if \a defaultLimit has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a defaultLimit is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetPowerManagementDefaultLimit(nvmlDevice_t device, unsigned int *defaultLimit); - -/** - * Retrieves power usage for this GPU in milliwatts and its associated circuitry (e.g. memory) - * - * For Fermi &tm; or newer fully supported devices. - * - * On Fermi and Kepler GPUs the reading is accurate to within +/- 5% of current power draw. - * - * It is only available if power management mode is supported. See \ref nvmlDeviceGetPowerManagementMode. - * - * @param device The identifier of the target device - * @param power Reference in which to return the power usage information - * - * @return - * - \ref NVML_SUCCESS if \a power has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a power is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support power readings - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetPowerUsage(nvmlDevice_t device, unsigned int *power); - -/** - * Retrieves total energy consumption for this GPU in millijoules (mJ) since the driver was last reloaded - * - * For newer than Pascal &tm; fully supported devices. - * - * @param device The identifier of the target device - * @param energy Reference in which to return the energy consumption information - * - * @return - * - \ref NVML_SUCCESS if \a energy has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a energy is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support energy readings - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetTotalEnergyConsumption(nvmlDevice_t device, unsigned long long *energy); - -/** - * Get the effective power limit that the driver enforces after taking into account all limiters - * - * Note: This can be different from the \ref nvmlDeviceGetPowerManagementLimit if other limits are set elsewhere - * This includes the out of band power limit interface - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The device to communicate with - * @param limit Reference in which to return the power management limit in milliwatts - * - * @return - * - \ref NVML_SUCCESS if \a limit has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a limit is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetEnforcedPowerLimit(nvmlDevice_t device, unsigned int *limit); - -/** - * Retrieves the current GOM and pending GOM (the one that GPU will switch to after reboot). - * - * For GK110 M-class and X-class Tesla &tm; products from the Kepler family. - * Modes \ref NVML_GOM_LOW_DP and \ref NVML_GOM_ALL_ON are supported on fully supported GeForce products. - * Not supported on Quadro ® and Tesla &tm; C-class products. - * - * @param device The identifier of the target device - * @param current Reference in which to return the current GOM - * @param pending Reference in which to return the pending GOM - * - * @return - * - \ref NVML_SUCCESS if \a mode has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a current or \a pending is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlGpuOperationMode_t - * @see nvmlDeviceSetGpuOperationMode - */ -nvmlReturn_t DECLDIR nvmlDeviceGetGpuOperationMode(nvmlDevice_t device, nvmlGpuOperationMode_t *current, nvmlGpuOperationMode_t *pending); - -/** - * Retrieves the amount of used, free and total memory available on the device, in bytes. - * - * For all products. - * - * Enabling ECC reduces the amount of total available memory, due to the extra required parity bits. - * Under WDDM most device memory is allocated and managed on startup by Windows. - * - * Under Linux and Windows TCC, the reported amount of used memory is equal to the sum of memory allocated - * by all active channels on the device. - * - * See \ref nvmlMemory_t for details on available memory info. - * - * @param device The identifier of the target device - * @param memory Reference in which to return the memory information - * - * @return - * - \ref NVML_SUCCESS if \a memory has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a memory is NULL - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetMemoryInfo(nvmlDevice_t device, nvmlMemory_t *memory); - -/** - * Retrieves the current compute mode for the device. - * - * For all products. - * - * See \ref nvmlComputeMode_t for details on allowed compute modes. - * - * @param device The identifier of the target device - * @param mode Reference in which to return the current compute mode - * - * @return - * - \ref NVML_SUCCESS if \a mode has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a mode is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceSetComputeMode() - */ -nvmlReturn_t DECLDIR nvmlDeviceGetComputeMode(nvmlDevice_t device, nvmlComputeMode_t *mode); - -/** - * Retrieves the CUDA compute capability of the device. - * - * For all products. - * - * Returns the major and minor compute capability version numbers of the - * device. The major and minor versions are equivalent to the - * CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MINOR and - * CU_DEVICE_ATTRIBUTE_COMPUTE_CAPABILITY_MAJOR attributes that would be - * returned by CUDA's cuDeviceGetAttribute(). - * - * @param device The identifier of the target device - * @param major Reference in which to return the major CUDA compute capability - * @param minor Reference in which to return the minor CUDA compute capability - * - * @return - * - \ref NVML_SUCCESS if \a major and \a minor have been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a major or \a minor are NULL - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetCudaComputeCapability(nvmlDevice_t device, int *major, int *minor); - -/** - * Retrieves the current and pending ECC modes for the device. - * - * For Fermi &tm; or newer fully supported devices. - * Only applicable to devices with ECC. - * Requires \a NVML_INFOROM_ECC version 1.0 or higher. - * - * Changing ECC modes requires a reboot. The "pending" ECC mode refers to the target mode following - * the next reboot. - * - * See \ref nvmlEnableState_t for details on allowed modes. - * - * @param device The identifier of the target device - * @param current Reference in which to return the current ECC mode - * @param pending Reference in which to return the pending ECC mode - * - * @return - * - \ref NVML_SUCCESS if \a current and \a pending have been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or either \a current or \a pending is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceSetEccMode() - */ -nvmlReturn_t DECLDIR nvmlDeviceGetEccMode(nvmlDevice_t device, nvmlEnableState_t *current, nvmlEnableState_t *pending); - -/** - * Retrieves the device boardId from 0-N. - * Devices with the same boardId indicate GPUs connected to the same PLX. Use in conjunction with - * \ref nvmlDeviceGetMultiGpuBoard() to decide if they are on the same board as well. - * The boardId returned is a unique ID for the current configuration. Uniqueness and ordering across - * reboots and system configurations is not guaranteed (i.e. if a Tesla K40c returns 0x100 and - * the two GPUs on a Tesla K10 in the same system returns 0x200 it is not guaranteed they will - * always return those values but they will always be different from each other). - * - * - * For Fermi &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param boardId Reference in which to return the device's board ID - * - * @return - * - \ref NVML_SUCCESS if \a boardId has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a boardId is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetBoardId(nvmlDevice_t device, unsigned int *boardId); - -/** - * Retrieves whether the device is on a Multi-GPU Board - * Devices that are on multi-GPU boards will set \a multiGpuBool to a non-zero value. - * - * For Fermi &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param multiGpuBool Reference in which to return a zero or non-zero value - * to indicate whether the device is on a multi GPU board - * - * @return - * - \ref NVML_SUCCESS if \a multiGpuBool has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a multiGpuBool is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetMultiGpuBoard(nvmlDevice_t device, unsigned int *multiGpuBool); - -/** - * Retrieves the total ECC error counts for the device. - * - * For Fermi &tm; or newer fully supported devices. - * Only applicable to devices with ECC. - * Requires \a NVML_INFOROM_ECC version 1.0 or higher. - * Requires ECC Mode to be enabled. - * - * The total error count is the sum of errors across each of the separate memory systems, i.e. the total set of - * errors across the entire device. - * - * See \ref nvmlMemoryErrorType_t for a description of available error types.\n - * See \ref nvmlEccCounterType_t for a description of available counter types. - * - * @param device The identifier of the target device - * @param errorType Flag that specifies the type of the errors. - * @param counterType Flag that specifies the counter-type of the errors. - * @param eccCounts Reference in which to return the specified ECC errors - * - * @return - * - \ref NVML_SUCCESS if \a eccCounts has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device, \a errorType or \a counterType is invalid, or \a eccCounts is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceClearEccErrorCounts() - */ -nvmlReturn_t DECLDIR nvmlDeviceGetTotalEccErrors(nvmlDevice_t device, nvmlMemoryErrorType_t errorType, nvmlEccCounterType_t counterType, unsigned long long *eccCounts); - -/** - * Retrieves the detailed ECC error counts for the device. - * - * @deprecated This API supports only a fixed set of ECC error locations - * On different GPU architectures different locations are supported - * See \ref nvmlDeviceGetMemoryErrorCounter - * - * For Fermi &tm; or newer fully supported devices. - * Only applicable to devices with ECC. - * Requires \a NVML_INFOROM_ECC version 2.0 or higher to report aggregate location-based ECC counts. - * Requires \a NVML_INFOROM_ECC version 1.0 or higher to report all other ECC counts. - * Requires ECC Mode to be enabled. - * - * Detailed errors provide separate ECC counts for specific parts of the memory system. - * - * Reports zero for unsupported ECC error counters when a subset of ECC error counters are supported. - * - * See \ref nvmlMemoryErrorType_t for a description of available bit types.\n - * See \ref nvmlEccCounterType_t for a description of available counter types.\n - * See \ref nvmlEccErrorCounts_t for a description of provided detailed ECC counts. - * - * @param device The identifier of the target device - * @param errorType Flag that specifies the type of the errors. - * @param counterType Flag that specifies the counter-type of the errors. - * @param eccCounts Reference in which to return the specified ECC errors - * - * @return - * - \ref NVML_SUCCESS if \a eccCounts has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device, \a errorType or \a counterType is invalid, or \a eccCounts is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceClearEccErrorCounts() - */ -nvmlReturn_t DECLDIR nvmlDeviceGetDetailedEccErrors(nvmlDevice_t device, nvmlMemoryErrorType_t errorType, nvmlEccCounterType_t counterType, nvmlEccErrorCounts_t *eccCounts); - -/** - * Retrieves the requested memory error counter for the device. - * - * For Fermi &tm; or newer fully supported devices. - * Requires \a NVML_INFOROM_ECC version 2.0 or higher to report aggregate location-based memory error counts. - * Requires \a NVML_INFOROM_ECC version 1.0 or higher to report all other memory error counts. - * - * Only applicable to devices with ECC. - * - * Requires ECC Mode to be enabled. - * - * See \ref nvmlMemoryErrorType_t for a description of available memory error types.\n - * See \ref nvmlEccCounterType_t for a description of available counter types.\n - * See \ref nvmlMemoryLocation_t for a description of available counter locations.\n - * - * @param device The identifier of the target device - * @param errorType Flag that specifies the type of error. - * @param counterType Flag that specifies the counter-type of the errors. - * @param locationType Specifies the location of the counter. - * @param count Reference in which to return the ECC counter - * - * @return - * - \ref NVML_SUCCESS if \a count has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device, \a bitTyp,e \a counterType or \a locationType is - * invalid, or \a count is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support ECC error reporting in the specified memory - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetMemoryErrorCounter(nvmlDevice_t device, nvmlMemoryErrorType_t errorType, - nvmlEccCounterType_t counterType, - nvmlMemoryLocation_t locationType, unsigned long long *count); - -/** - * Retrieves the current utilization rates for the device's major subsystems. - * - * For Fermi &tm; or newer fully supported devices. - * - * See \ref nvmlUtilization_t for details on available utilization rates. - * - * \note During driver initialization when ECC is enabled one can see high GPU and Memory Utilization readings. - * This is caused by ECC Memory Scrubbing mechanism that is performed during driver initialization. - * - * @param device The identifier of the target device - * @param utilization Reference in which to return the utilization information - * - * @return - * - \ref NVML_SUCCESS if \a utilization has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a utilization is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetUtilizationRates(nvmlDevice_t device, nvmlUtilization_t *utilization); - -/** - * Retrieves the current utilization and sampling size in microseconds for the Encoder - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param utilization Reference to an unsigned int for encoder utilization info - * @param samplingPeriodUs Reference to an unsigned int for the sampling period in US - * - * @return - * - \ref NVML_SUCCESS if \a utilization has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, \a utilization is NULL, or \a samplingPeriodUs is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetEncoderUtilization(nvmlDevice_t device, unsigned int *utilization, unsigned int *samplingPeriodUs); - -/** - * Retrieves the current capacity of the device's encoder, in macroblocks per second. - * - * For Maxwell &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param encoderQueryType Type of encoder to query - * @param encoderCapacity Reference to an unsigned int for the encoder capacity - * - * @return - * - \ref NVML_SUCCESS if \a encoderCapacity is fetched - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a encoderCapacity is NULL, or \a device or \a encoderQueryType - * are invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if device does not support the encoder specified in \a encodeQueryType - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetEncoderCapacity (nvmlDevice_t device, nvmlEncoderType_t encoderQueryType, unsigned int *encoderCapacity); - -/** - * Retrieves the current encoder statistics for a given device. - * - * For Maxwell &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param sessionCount Reference to an unsigned int for count of active encoder sessions - * @param averageFps Reference to an unsigned int for trailing average FPS of all active sessions - * @param averageLatency Reference to an unsigned int for encode latency in microseconds - * - * @return - * - \ref NVML_SUCCESS if \a sessionCount, \a averageFps and \a averageLatency is fetched - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a sessionCount, or \a device or \a averageFps, - * or \a averageLatency is NULL - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetEncoderStats (nvmlDevice_t device, unsigned int *sessionCount, - unsigned int *averageFps, unsigned int *averageLatency); - -/** - * Retrieves information about active encoder sessions on a target device. - * - * An array of active encoder sessions is returned in the caller-supplied buffer pointed at by \a sessionInfos. The - * array elememt count is passed in \a sessionCount, and \a sessionCount is used to return the number of sessions - * written to the buffer. - * - * If the supplied buffer is not large enough to accomodate the active session array, the function returns - * NVML_ERROR_INSUFFICIENT_SIZE, with the element count of nvmlEncoderSessionInfo_t array required in \a sessionCount. - * To query the number of active encoder sessions, call this function with *sessionCount = 0. The code will return - * NVML_SUCCESS with number of active encoder sessions updated in *sessionCount. - * - * For Maxwell &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param sessionCount Reference to caller supplied array size, and returns the number of sessions. - * @param sessionInfos Reference in which to return the session information - * - * @return - * - \ref NVML_SUCCESS if \a sessionInfos is fetched - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a sessionCount is too small, array element count is returned in \a sessionCount - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a sessionCount is NULL. - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetEncoderSessions(nvmlDevice_t device, unsigned int *sessionCount, nvmlEncoderSessionInfo_t *sessionInfos); - -/** - * Retrieves the current utilization and sampling size in microseconds for the Decoder - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param utilization Reference to an unsigned int for decoder utilization info - * @param samplingPeriodUs Reference to an unsigned int for the sampling period in US - * - * @return - * - \ref NVML_SUCCESS if \a utilization has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, \a utilization is NULL, or \a samplingPeriodUs is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetDecoderUtilization(nvmlDevice_t device, unsigned int *utilization, unsigned int *samplingPeriodUs); - -/** - * Retrieves the current and pending driver model for the device. - * - * For Fermi &tm; or newer fully supported devices. - * For windows only. - * - * On Windows platforms the device driver can run in either WDDM or WDM (TCC) mode. If a display is attached - * to the device it must run in WDDM mode. TCC mode is preferred if a display is not attached. - * - * See \ref nvmlDriverModel_t for details on available driver models. - * - * @param device The identifier of the target device - * @param current Reference in which to return the current driver model - * @param pending Reference in which to return the pending driver model - * - * @return - * - \ref NVML_SUCCESS if either \a current and/or \a pending have been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or both \a current and \a pending are NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the platform is not windows - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceSetDriverModel() - */ -nvmlReturn_t DECLDIR nvmlDeviceGetDriverModel(nvmlDevice_t device, nvmlDriverModel_t *current, nvmlDriverModel_t *pending); - -/** - * Get VBIOS version of the device. - * - * For all products. - * - * The VBIOS version may change from time to time. It will not exceed 32 characters in length - * (including the NULL terminator). See \ref nvmlConstants::NVML_DEVICE_VBIOS_VERSION_BUFFER_SIZE. - * - * @param device The identifier of the target device - * @param version Reference to which to return the VBIOS version - * @param length The maximum allowed length of the string returned in \a version - * - * @return - * - \ref NVML_SUCCESS if \a version has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, or \a version is NULL - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a length is too small - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetVbiosVersion(nvmlDevice_t device, char *version, unsigned int length); - -/** - * Get Bridge Chip Information for all the bridge chips on the board. - * - * For all fully supported products. - * Only applicable to multi-GPU products. - * - * @param device The identifier of the target device - * @param bridgeHierarchy Reference to the returned bridge chip Hierarchy - * - * @return - * - \ref NVML_SUCCESS if bridge chip exists - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, or \a bridgeInfo is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if bridge chip not supported on the device - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - */ -nvmlReturn_t DECLDIR nvmlDeviceGetBridgeChipInfo(nvmlDevice_t device, nvmlBridgeChipHierarchy_t *bridgeHierarchy); - -/** - * Get information about processes with a compute context on a device - * - * For Fermi &tm; or newer fully supported devices. - * - * This function returns information only about compute running processes (e.g. CUDA application which have - * active context). Any graphics applications (e.g. using OpenGL, DirectX) won't be listed by this function. - * - * To query the current number of running compute processes, call this function with *infoCount = 0. The - * return code will be NVML_ERROR_INSUFFICIENT_SIZE, or NVML_SUCCESS if none are running. For this call - * \a infos is allowed to be NULL. - * - * The usedGpuMemory field returned is all of the memory used by the application. - * - * Keep in mind that information returned by this call is dynamic and the number of elements might change in - * time. Allocate more space for \a infos table in case new compute processes are spawned. - * - * @param device The identifier of the target device - * @param infoCount Reference in which to provide the \a infos array size, and - * to return the number of returned elements - * @param infos Reference in which to return the process information - * - * @return - * - \ref NVML_SUCCESS if \a infoCount and \a infos have been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a infoCount indicates that the \a infos array is too small - * \a infoCount will contain minimal amount of space necessary for - * the call to complete - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, either of \a infoCount or \a infos is NULL - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see \ref nvmlSystemGetProcessName - */ -nvmlReturn_t DECLDIR nvmlDeviceGetComputeRunningProcesses(nvmlDevice_t device, unsigned int *infoCount, nvmlProcessInfo_t *infos); - -/** - * Get information about processes with a graphics context on a device - * - * For Kepler &tm; or newer fully supported devices. - * - * This function returns information only about graphics based processes - * (eg. applications using OpenGL, DirectX) - * - * To query the current number of running graphics processes, call this function with *infoCount = 0. The - * return code will be NVML_ERROR_INSUFFICIENT_SIZE, or NVML_SUCCESS if none are running. For this call - * \a infos is allowed to be NULL. - * - * The usedGpuMemory field returned is all of the memory used by the application. - * - * Keep in mind that information returned by this call is dynamic and the number of elements might change in - * time. Allocate more space for \a infos table in case new graphics processes are spawned. - * - * @param device The identifier of the target device - * @param infoCount Reference in which to provide the \a infos array size, and - * to return the number of returned elements - * @param infos Reference in which to return the process information - * - * @return - * - \ref NVML_SUCCESS if \a infoCount and \a infos have been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a infoCount indicates that the \a infos array is too small - * \a infoCount will contain minimal amount of space necessary for - * the call to complete - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, either of \a infoCount or \a infos is NULL - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see \ref nvmlSystemGetProcessName - */ -nvmlReturn_t DECLDIR nvmlDeviceGetGraphicsRunningProcesses(nvmlDevice_t device, unsigned int *infoCount, nvmlProcessInfo_t *infos); - -/** - * Check if the GPU devices are on the same physical board. - * - * For all fully supported products. - * - * @param device1 The first GPU device - * @param device2 The second GPU device - * @param onSameBoard Reference in which to return the status. - * Non-zero indicates that the GPUs are on the same board. - * - * @return - * - \ref NVML_SUCCESS if \a onSameBoard has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a dev1 or \a dev2 are invalid or \a onSameBoard is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if this check is not supported by the device - * - \ref NVML_ERROR_GPU_IS_LOST if the either GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceOnSameBoard(nvmlDevice_t device1, nvmlDevice_t device2, int *onSameBoard); - -/** - * Retrieves the root/admin permissions on the target API. See \a nvmlRestrictedAPI_t for the list of supported APIs. - * If an API is restricted only root users can call that API. See \a nvmlDeviceSetAPIRestriction to change current permissions. - * - * For all fully supported products. - * - * @param device The identifier of the target device - * @param apiType Target API type for this operation - * @param isRestricted Reference in which to return the current restriction - * NVML_FEATURE_ENABLED indicates that the API is root-only - * NVML_FEATURE_DISABLED indicates that the API is accessible to all users - * - * @return - * - \ref NVML_SUCCESS if \a isRestricted has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, \a apiType incorrect or \a isRestricted is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if this query is not supported by the device or the device does not support - * the feature that is being queried (E.G. Enabling/disabling Auto Boosted clocks is - * not supported by the device) - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlRestrictedAPI_t - */ -nvmlReturn_t DECLDIR nvmlDeviceGetAPIRestriction(nvmlDevice_t device, nvmlRestrictedAPI_t apiType, nvmlEnableState_t *isRestricted); - -/** - * Gets recent samples for the GPU. - * - * For Kepler &tm; or newer fully supported devices. - * - * Based on type, this method can be used to fetch the power, utilization or clock samples maintained in the buffer by - * the driver. - * - * Power, Utilization and Clock samples are returned as type "unsigned int" for the union nvmlValue_t. - * - * To get the size of samples that user needs to allocate, the method is invoked with samples set to NULL. - * The returned samplesCount will provide the number of samples that can be queried. The user needs to - * allocate the buffer with size as samplesCount * sizeof(nvmlSample_t). - * - * lastSeenTimeStamp represents CPU timestamp in microseconds. Set it to 0 to fetch all the samples maintained by the - * underlying buffer. Set lastSeenTimeStamp to one of the timeStamps retrieved from the date of the previous query - * to get more recent samples. - * - * This method fetches the number of entries which can be accommodated in the provided samples array, and the - * reference samplesCount is updated to indicate how many samples were actually retrieved. The advantage of using this - * method for samples in contrast to polling via existing methods is to get get higher frequency data at lower polling cost. - * - * @param device The identifier for the target device - * @param type Type of sampling event - * @param lastSeenTimeStamp Return only samples with timestamp greater than lastSeenTimeStamp. - * @param sampleValType Output parameter to represent the type of sample value as described in nvmlSampleVal_t - * @param sampleCount Reference to provide the number of elements which can be queried in samples array - * @param samples Reference in which samples are returned - - * @return - * - \ref NVML_SUCCESS if samples are successfully retrieved - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, \a samplesCount is NULL or - * reference to \a sampleCount is 0 for non null \a samples - * - \ref NVML_ERROR_NOT_SUPPORTED if this query is not supported by the device - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_NOT_FOUND if sample entries are not found - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetSamples(nvmlDevice_t device, nvmlSamplingType_t type, unsigned long long lastSeenTimeStamp, - nvmlValueType_t *sampleValType, unsigned int *sampleCount, nvmlSample_t *samples); - -/** - * Gets Total, Available and Used size of BAR1 memory. - * - * BAR1 is used to map the FB (device memory) so that it can be directly accessed by the CPU or by 3rd party - * devices (peer-to-peer on the PCIE bus). - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param bar1Memory Reference in which BAR1 memory - * information is returned. - * - * @return - * - \ref NVML_SUCCESS if BAR1 memory is successfully retrieved - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, \a bar1Memory is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if this query is not supported by the device - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - */ -nvmlReturn_t DECLDIR nvmlDeviceGetBAR1MemoryInfo(nvmlDevice_t device, nvmlBAR1Memory_t *bar1Memory); - - -/** - * Gets the duration of time during which the device was throttled (lower than requested clocks) due to power - * or thermal constraints. - * - * The method is important to users who are tying to understand if their GPUs throttle at any point during their applications. The - * difference in violation times at two different reference times gives the indication of GPU throttling event. - * - * Violation for thermal capping is not supported at this time. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param perfPolicyType Represents Performance policy which can trigger GPU throttling - * @param violTime Reference to which violation time related information is returned - * - * - * @return - * - \ref NVML_SUCCESS if violation time is successfully retrieved - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, \a perfPolicyType is invalid, or \a violTime is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if this query is not supported by the device - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - */ -nvmlReturn_t DECLDIR nvmlDeviceGetViolationStatus(nvmlDevice_t device, nvmlPerfPolicyType_t perfPolicyType, nvmlViolationTime_t *violTime); - -/** - * @} - */ - -/** @addtogroup nvmlAccountingStats - * @{ - */ - -/** - * Queries the state of per process accounting mode. - * - * For Kepler &tm; or newer fully supported devices. - * - * See \ref nvmlDeviceGetAccountingStats for more details. - * See \ref nvmlDeviceSetAccountingMode - * - * @param device The identifier of the target device - * @param mode Reference in which to return the current accounting mode - * - * @return - * - \ref NVML_SUCCESS if the mode has been successfully retrieved - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a mode are NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetAccountingMode(nvmlDevice_t device, nvmlEnableState_t *mode); - -/** - * Queries process's accounting stats. - * - * For Kepler &tm; or newer fully supported devices. - * - * Accounting stats capture GPU utilization and other statistics across the lifetime of a process. - * Accounting stats can be queried during life time of the process and after its termination. - * The time field in \ref nvmlAccountingStats_t is reported as 0 during the lifetime of the process and - * updated to actual running time after its termination. - * Accounting stats are kept in a circular buffer, newly created processes overwrite information about old - * processes. - * - * See \ref nvmlAccountingStats_t for description of each returned metric. - * List of processes that can be queried can be retrieved from \ref nvmlDeviceGetAccountingPids. - * - * @note Accounting Mode needs to be on. See \ref nvmlDeviceGetAccountingMode. - * @note Only compute and graphics applications stats can be queried. Monitoring applications stats can't be - * queried since they don't contribute to GPU utilization. - * @note In case of pid collision stats of only the latest process (that terminated last) will be reported - * - * @warning On Kepler devices per process statistics are accurate only if there's one process running on a GPU. - * - * @param device The identifier of the target device - * @param pid Process Id of the target process to query stats for - * @param stats Reference in which to return the process's accounting stats - * - * @return - * - \ref NVML_SUCCESS if stats have been successfully retrieved - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a stats are NULL - * - \ref NVML_ERROR_NOT_FOUND if process stats were not found - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature or accounting mode is disabled - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetAccountingBufferSize - */ -nvmlReturn_t DECLDIR nvmlDeviceGetAccountingStats(nvmlDevice_t device, unsigned int pid, nvmlAccountingStats_t *stats); - -/** - * Queries list of processes that can be queried for accounting stats. The list of processes returned - * can be in running or terminated state. - * - * For Kepler &tm; or newer fully supported devices. - * - * To just query the number of processes ready to be queried, call this function with *count = 0 and - * pids=NULL. The return code will be NVML_ERROR_INSUFFICIENT_SIZE, or NVML_SUCCESS if list is empty. - * - * For more details see \ref nvmlDeviceGetAccountingStats. - * - * @note In case of PID collision some processes might not be accessible before the circular buffer is full. - * - * @param device The identifier of the target device - * @param count Reference in which to provide the \a pids array size, and - * to return the number of elements ready to be queried - * @param pids Reference in which to return list of process ids - * - * @return - * - \ref NVML_SUCCESS if pids were successfully retrieved - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a count is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature or accounting mode is disabled - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a count is too small (\a count is set to - * expected value) - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetAccountingBufferSize - */ -nvmlReturn_t DECLDIR nvmlDeviceGetAccountingPids(nvmlDevice_t device, unsigned int *count, unsigned int *pids); - -/** - * Returns the number of processes that the circular buffer with accounting pids can hold. - * - * For Kepler &tm; or newer fully supported devices. - * - * This is the maximum number of processes that accounting information will be stored for before information - * about oldest processes will get overwritten by information about new processes. - * - * @param device The identifier of the target device - * @param bufferSize Reference in which to provide the size (in number of elements) - * of the circular buffer for accounting stats. - * - * @return - * - \ref NVML_SUCCESS if buffer size was successfully retrieved - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a bufferSize is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature or accounting mode is disabled - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetAccountingStats - * @see nvmlDeviceGetAccountingPids - */ -nvmlReturn_t DECLDIR nvmlDeviceGetAccountingBufferSize(nvmlDevice_t device, unsigned int *bufferSize); - -/** @} */ - -/** @addtogroup nvmlDeviceQueries - * @{ - */ - -/** - * Returns the list of retired pages by source, including pages that are pending retirement - * The address information provided from this API is the hardware address of the page that was retired. Note - * that this does not match the virtual address used in CUDA, but will match the address information in XID 63 - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param cause Filter page addresses by cause of retirement - * @param pageCount Reference in which to provide the \a addresses buffer size, and - * to return the number of retired pages that match \a cause - * Set to 0 to query the size without allocating an \a addresses buffer - * @param addresses Buffer to write the page addresses into - * - * @return - * - \ref NVML_SUCCESS if \a pageCount was populated and \a addresses was filled - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a pageCount indicates the buffer is not large enough to store all the - * matching page addresses. \a pageCount is set to the needed size. - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, \a pageCount is NULL, \a cause is invalid, or - * \a addresses is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetRetiredPages(nvmlDevice_t device, nvmlPageRetirementCause_t cause, - unsigned int *pageCount, unsigned long long *addresses); - -/** - * Check if any pages are pending retirement and need a reboot to fully retire. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param isPending Reference in which to return the pending status - * - * @return - * - \ref NVML_SUCCESS if \a isPending was populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a isPending is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetRetiredPagesPendingStatus(nvmlDevice_t device, nvmlEnableState_t *isPending); - -/** @} */ - -/***************************************************************************************************/ -/** @defgroup nvmlUnitCommands Unit Commands - * This chapter describes NVML operations that change the state of the unit. For S-class products. - * Each of these requires root/admin access. Non-admin users will see an NVML_ERROR_NO_PERMISSION - * error code when invoking any of these methods. - * @{ - */ -/***************************************************************************************************/ - -/** - * Set the LED state for the unit. The LED can be either green (0) or amber (1). - * - * For S-class products. - * Requires root/admin permissions. - * - * This operation takes effect immediately. - * - * - * Current S-Class products don't provide unique LEDs for each unit. As such, both front - * and back LEDs will be toggled in unison regardless of which unit is specified with this command. - * - * See \ref nvmlLedColor_t for available colors. - * - * @param unit The identifier of the target unit - * @param color The target LED color - * - * @return - * - \ref NVML_SUCCESS if the LED color has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a unit or \a color is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if this is not an S-class product - * - \ref NVML_ERROR_NO_PERMISSION if the user doesn't have permission to perform this operation - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlUnitGetLedState() - */ -nvmlReturn_t DECLDIR nvmlUnitSetLedState(nvmlUnit_t unit, nvmlLedColor_t color); - -/** @} */ - -/***************************************************************************************************/ -/** @defgroup nvmlDeviceCommands Device Commands - * This chapter describes NVML operations that change the state of the device. - * Each of these requires root/admin access. Non-admin users will see an NVML_ERROR_NO_PERMISSION - * error code when invoking any of these methods. - * @{ - */ -/***************************************************************************************************/ - -/** - * Set the persistence mode for the device. - * - * For all products. - * For Linux only. - * Requires root/admin permissions. - * - * The persistence mode determines whether the GPU driver software is torn down after the last client - * exits. - * - * This operation takes effect immediately. It is not persistent across reboots. After each reboot the - * persistence mode is reset to "Disabled". - * - * See \ref nvmlEnableState_t for available modes. - * - * @param device The identifier of the target device - * @param mode The target persistence mode - * - * @return - * - \ref NVML_SUCCESS if the persistence mode was set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a mode is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_NO_PERMISSION if the user doesn't have permission to perform this operation - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetPersistenceMode() - */ -nvmlReturn_t DECLDIR nvmlDeviceSetPersistenceMode(nvmlDevice_t device, nvmlEnableState_t mode); - -/** - * Set the compute mode for the device. - * - * For all products. - * Requires root/admin permissions. - * - * The compute mode determines whether a GPU can be used for compute operations and whether it can - * be shared across contexts. - * - * This operation takes effect immediately. Under Linux it is not persistent across reboots and - * always resets to "Default". Under windows it is persistent. - * - * Under windows compute mode may only be set to DEFAULT when running in WDDM - * - * See \ref nvmlComputeMode_t for details on available compute modes. - * - * @param device The identifier of the target device - * @param mode The target compute mode - * - * @return - * - \ref NVML_SUCCESS if the compute mode was set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a mode is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_NO_PERMISSION if the user doesn't have permission to perform this operation - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetComputeMode() - */ -nvmlReturn_t DECLDIR nvmlDeviceSetComputeMode(nvmlDevice_t device, nvmlComputeMode_t mode); - -/** - * Set the ECC mode for the device. - * - * For Kepler &tm; or newer fully supported devices. - * Only applicable to devices with ECC. - * Requires \a NVML_INFOROM_ECC version 1.0 or higher. - * Requires root/admin permissions. - * - * The ECC mode determines whether the GPU enables its ECC support. - * - * This operation takes effect after the next reboot. - * - * See \ref nvmlEnableState_t for details on available modes. - * - * @param device The identifier of the target device - * @param ecc The target ECC mode - * - * @return - * - \ref NVML_SUCCESS if the ECC mode was set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a ecc is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_NO_PERMISSION if the user doesn't have permission to perform this operation - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetEccMode() - */ -nvmlReturn_t DECLDIR nvmlDeviceSetEccMode(nvmlDevice_t device, nvmlEnableState_t ecc); - -/** - * Clear the ECC error and other memory error counts for the device. - * - * For Kepler &tm; or newer fully supported devices. - * Only applicable to devices with ECC. - * Requires \a NVML_INFOROM_ECC version 2.0 or higher to clear aggregate location-based ECC counts. - * Requires \a NVML_INFOROM_ECC version 1.0 or higher to clear all other ECC counts. - * Requires root/admin permissions. - * Requires ECC Mode to be enabled. - * - * Sets all of the specified ECC counters to 0, including both detailed and total counts. - * - * This operation takes effect immediately. - * - * See \ref nvmlMemoryErrorType_t for details on available counter types. - * - * @param device The identifier of the target device - * @param counterType Flag that indicates which type of errors should be cleared. - * - * @return - * - \ref NVML_SUCCESS if the error counts were cleared - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a counterType is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_NO_PERMISSION if the user doesn't have permission to perform this operation - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see - * - nvmlDeviceGetDetailedEccErrors() - * - nvmlDeviceGetTotalEccErrors() - */ -nvmlReturn_t DECLDIR nvmlDeviceClearEccErrorCounts(nvmlDevice_t device, nvmlEccCounterType_t counterType); - -/** - * Set the driver model for the device. - * - * For Fermi &tm; or newer fully supported devices. - * For windows only. - * Requires root/admin permissions. - * - * On Windows platforms the device driver can run in either WDDM or WDM (TCC) mode. If a display is attached - * to the device it must run in WDDM mode. - * - * It is possible to force the change to WDM (TCC) while the display is still attached with a force flag (nvmlFlagForce). - * This should only be done if the host is subsequently powered down and the display is detached from the device - * before the next reboot. - * - * This operation takes effect after the next reboot. - * - * Windows driver model may only be set to WDDM when running in DEFAULT compute mode. - * - * Change driver model to WDDM is not supported when GPU doesn't support graphics acceleration or - * will not support it after reboot. See \ref nvmlDeviceSetGpuOperationMode. - * - * See \ref nvmlDriverModel_t for details on available driver models. - * See \ref nvmlFlagDefault and \ref nvmlFlagForce - * - * @param device The identifier of the target device - * @param driverModel The target driver model - * @param flags Flags that change the default behavior - * - * @return - * - \ref NVML_SUCCESS if the driver model has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a driverModel is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the platform is not windows or the device does not support this feature - * - \ref NVML_ERROR_NO_PERMISSION if the user doesn't have permission to perform this operation - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetDriverModel() - */ -nvmlReturn_t DECLDIR nvmlDeviceSetDriverModel(nvmlDevice_t device, nvmlDriverModel_t driverModel, unsigned int flags); - -/** - * Set clocks that applications will lock to. - * - * Sets the clocks that compute and graphics applications will be running at. - * e.g. CUDA driver requests these clocks during context creation which means this property - * defines clocks at which CUDA applications will be running unless some overspec event - * occurs (e.g. over power, over thermal or external HW brake). - * - * Can be used as a setting to request constant performance. - * - * On Pascal and newer hardware, this will automatically disable automatic boosting of clocks. - * - * On K80 and newer Kepler and Maxwell GPUs, users desiring fixed performance should also call - * \ref nvmlDeviceSetAutoBoostedClocksEnabled to prevent clocks from automatically boosting - * above the clock value being set. - * - * For Kepler &tm; or newer non-GeForce fully supported devices and Maxwell or newer GeForce devices. - * Requires root/admin permissions. - * - * See \ref nvmlDeviceGetSupportedMemoryClocks and \ref nvmlDeviceGetSupportedGraphicsClocks - * for details on how to list available clocks combinations. - * - * After system reboot or driver reload applications clocks go back to their default value. - * See \ref nvmlDeviceResetApplicationsClocks. - * - * @param device The identifier of the target device - * @param memClockMHz Requested memory clock in MHz - * @param graphicsClockMHz Requested graphics clock in MHz - * - * @return - * - \ref NVML_SUCCESS if new settings were successfully set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a memClockMHz and \a graphicsClockMHz - * is not a valid clock combination - * - \ref NVML_ERROR_NO_PERMISSION if the user doesn't have permission to perform this operation - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceSetApplicationsClocks(nvmlDevice_t device, unsigned int memClockMHz, unsigned int graphicsClockMHz); - -/** - * Set new power limit of this device. - * - * For Kepler &tm; or newer fully supported devices. - * Requires root/admin permissions. - * - * See \ref nvmlDeviceGetPowerManagementLimitConstraints to check the allowed ranges of values. - * - * \note Limit is not persistent across reboots or driver unloads. - * Enable persistent mode to prevent driver from unloading when no application is using the device. - * - * @param device The identifier of the target device - * @param limit Power management limit in milliwatts to set - * - * @return - * - \ref NVML_SUCCESS if \a limit has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a defaultLimit is out of range - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceGetPowerManagementLimitConstraints - * @see nvmlDeviceGetPowerManagementDefaultLimit - */ -nvmlReturn_t DECLDIR nvmlDeviceSetPowerManagementLimit(nvmlDevice_t device, unsigned int limit); - -/** - * Sets new GOM. See \a nvmlGpuOperationMode_t for details. - * - * For GK110 M-class and X-class Tesla &tm; products from the Kepler family. - * Modes \ref NVML_GOM_LOW_DP and \ref NVML_GOM_ALL_ON are supported on fully supported GeForce products. - * Not supported on Quadro ® and Tesla &tm; C-class products. - * Requires root/admin permissions. - * - * Changing GOMs requires a reboot. - * The reboot requirement might be removed in the future. - * - * Compute only GOMs don't support graphics acceleration. Under windows switching to these GOMs when - * pending driver model is WDDM is not supported. See \ref nvmlDeviceSetDriverModel. - * - * @param device The identifier of the target device - * @param mode Target GOM - * - * @return - * - \ref NVML_SUCCESS if \a mode has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a mode incorrect - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support GOM or specific mode - * - \ref NVML_ERROR_NO_PERMISSION if the user doesn't have permission to perform this operation - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlGpuOperationMode_t - * @see nvmlDeviceGetGpuOperationMode - */ -nvmlReturn_t DECLDIR nvmlDeviceSetGpuOperationMode(nvmlDevice_t device, nvmlGpuOperationMode_t mode); - -/** - * Changes the root/admin restructions on certain APIs. See \a nvmlRestrictedAPI_t for the list of supported APIs. - * This method can be used by a root/admin user to give non-root/admin access to certain otherwise-restricted APIs. - * The new setting lasts for the lifetime of the NVIDIA driver; it is not persistent. See \a nvmlDeviceGetAPIRestriction - * to query the current restriction settings. - * - * For Kepler &tm; or newer fully supported devices. - * Requires root/admin permissions. - * - * @param device The identifier of the target device - * @param apiType Target API type for this operation - * @param isRestricted The target restriction - * - * @return - * - \ref NVML_SUCCESS if \a isRestricted has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a apiType incorrect - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support changing API restrictions or the device does not support - * the feature that api restrictions are being set for (E.G. Enabling/disabling auto - * boosted clocks is not supported by the device) - * - \ref NVML_ERROR_NO_PERMISSION if the user doesn't have permission to perform this operation - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlRestrictedAPI_t - */ -nvmlReturn_t DECLDIR nvmlDeviceSetAPIRestriction(nvmlDevice_t device, nvmlRestrictedAPI_t apiType, nvmlEnableState_t isRestricted); - -/** - * @} - */ - -/** @addtogroup nvmlAccountingStats - * @{ - */ - -/** - * Enables or disables per process accounting. - * - * For Kepler &tm; or newer fully supported devices. - * Requires root/admin permissions. - * - * @note This setting is not persistent and will default to disabled after driver unloads. - * Enable persistence mode to be sure the setting doesn't switch off to disabled. - * - * @note Enabling accounting mode has no negative impact on the GPU performance. - * - * @note Disabling accounting clears all accounting pids information. - * - * See \ref nvmlDeviceGetAccountingMode - * See \ref nvmlDeviceGetAccountingStats - * See \ref nvmlDeviceClearAccountingPids - * - * @param device The identifier of the target device - * @param mode The target accounting mode - * - * @return - * - \ref NVML_SUCCESS if the new mode has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device or \a mode are invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_NO_PERMISSION if the user doesn't have permission to perform this operation - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceSetAccountingMode(nvmlDevice_t device, nvmlEnableState_t mode); - -/** - * Clears accounting information about all processes that have already terminated. - * - * For Kepler &tm; or newer fully supported devices. - * Requires root/admin permissions. - * - * See \ref nvmlDeviceGetAccountingMode - * See \ref nvmlDeviceGetAccountingStats - * See \ref nvmlDeviceSetAccountingMode - * - * @param device The identifier of the target device - * - * @return - * - \ref NVML_SUCCESS if accounting information has been cleared - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device are invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_NO_PERMISSION if the user doesn't have permission to perform this operation - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceClearAccountingPids(nvmlDevice_t device); - -/** @} */ - -/***************************************************************************************************/ -/** @defgroup NvLink NvLink Methods - * This chapter describes methods that NVML can perform on NVLINK enabled devices. - * @{ - */ -/***************************************************************************************************/ - -/** - * Retrieves the state of the device's NvLink for the link specified - * - * For Pascal &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param link Specifies the NvLink link to be queried - * @param isActive \a nvmlEnableState_t where NVML_FEATURE_ENABLED indicates that - * the link is active and NVML_FEATURE_DISABLED indicates it - * is inactive - * - * @return - * - \ref NVML_SUCCESS if \a isActive has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device or \a link is invalid or \a isActive is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetNvLinkState(nvmlDevice_t device, unsigned int link, nvmlEnableState_t *isActive); - -/** - * Retrieves the version of the device's NvLink for the link specified - * - * For Pascal &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param link Specifies the NvLink link to be queried - * @param version Requested NvLink version - * - * @return - * - \ref NVML_SUCCESS if \a version has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device or \a link is invalid or \a version is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetNvLinkVersion(nvmlDevice_t device, unsigned int link, unsigned int *version); - -/** - * Retrieves the requested capability from the device's NvLink for the link specified - * Please refer to the \a nvmlNvLinkCapability_t structure for the specific caps that can be queried - * The return value should be treated as a boolean. - * - * For Pascal &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param link Specifies the NvLink link to be queried - * @param capability Specifies the \a nvmlNvLinkCapability_t to be queried - * @param capResult A boolean for the queried capability indicating that feature is available - * - * @return - * - \ref NVML_SUCCESS if \a capResult has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device, \a link, or \a capability is invalid or \a capResult is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetNvLinkCapability(nvmlDevice_t device, unsigned int link, - nvmlNvLinkCapability_t capability, unsigned int *capResult); - -/** - * Retrieves the PCI information for the remote node on a NvLink link - * Note: pciSubSystemId is not filled in this function and is indeterminate - * - * For Pascal &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param link Specifies the NvLink link to be queried - * @param pci \a nvmlPciInfo_t of the remote node for the specified link - * - * @return - * - \ref NVML_SUCCESS if \a pci has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device or \a link is invalid or \a pci is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetNvLinkRemotePciInfo(nvmlDevice_t device, unsigned int link, nvmlPciInfo_t *pci); - -/** - * Retrieves the specified error counter value - * Please refer to \a nvmlNvLinkErrorCounter_t for error counters that are available - * - * For Pascal &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param link Specifies the NvLink link to be queried - * @param counter Specifies the NvLink counter to be queried - * @param counterValue Returned counter value - * - * @return - * - \ref NVML_SUCCESS if \a counter has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device, \a link, or \a counter is invalid or \a counterValue is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetNvLinkErrorCounter(nvmlDevice_t device, unsigned int link, - nvmlNvLinkErrorCounter_t counter, unsigned long long *counterValue); - -/** - * Resets all error counters to zero - * Please refer to \a nvmlNvLinkErrorCounter_t for the list of error counters that are reset - * - * For Pascal &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param link Specifies the NvLink link to be queried - * - * @return - * - \ref NVML_SUCCESS if the reset is successful - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device or \a link is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceResetNvLinkErrorCounters(nvmlDevice_t device, unsigned int link); - -/** - * Set the NVLINK utilization counter control information for the specified counter, 0 or 1. - * Please refer to \a nvmlNvLinkUtilizationControl_t for the structure definition. Performs a reset - * of the counters if the reset parameter is non-zero. - * - * For Pascal &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param counter Specifies the counter that should be set (0 or 1). - * @param link Specifies the NvLink link to be queried - * @param control A reference to the \a nvmlNvLinkUtilizationControl_t to set - * @param reset Resets the counters on set if non-zero - * - * @return - * - \ref NVML_SUCCESS if the control has been set successfully - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device, \a counter, \a link, or \a control is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceSetNvLinkUtilizationControl(nvmlDevice_t device, unsigned int link, unsigned int counter, - nvmlNvLinkUtilizationControl_t *control, unsigned int reset); - -/** - * Get the NVLINK utilization counter control information for the specified counter, 0 or 1. - * Please refer to \a nvmlNvLinkUtilizationControl_t for the structure definition - * - * For Pascal &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param counter Specifies the counter that should be set (0 or 1). - * @param link Specifies the NvLink link to be queried - * @param control A reference to the \a nvmlNvLinkUtilizationControl_t to place information - * - * @return - * - \ref NVML_SUCCESS if the control has been set successfully - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device, \a counter, \a link, or \a control is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetNvLinkUtilizationControl(nvmlDevice_t device, unsigned int link, unsigned int counter, - nvmlNvLinkUtilizationControl_t *control); - - -/** - * Retrieve the NVLINK utilization counter based on the current control for a specified counter. - * In general it is good practice to use \a nvmlDeviceSetNvLinkUtilizationControl - * before reading the utilization counters as they have no default state - * - * For Pascal &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param link Specifies the NvLink link to be queried - * @param counter Specifies the counter that should be read (0 or 1). - * @param rxcounter Receive counter return value - * @param txcounter Transmit counter return value - * - * @return - * - \ref NVML_SUCCESS if \a rxcounter and \a txcounter have been successfully set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device, \a counter, or \a link is invalid or \a rxcounter or \a txcounter are NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetNvLinkUtilizationCounter(nvmlDevice_t device, unsigned int link, unsigned int counter, - unsigned long long *rxcounter, unsigned long long *txcounter); - -/** - * Freeze the NVLINK utilization counters - * Both the receive and transmit counters are operated on by this function - * - * For Pascal &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param link Specifies the NvLink link to be queried - * @param counter Specifies the counter that should be frozen (0 or 1). - * @param freeze NVML_FEATURE_ENABLED = freeze the receive and transmit counters - * NVML_FEATURE_DISABLED = unfreeze the receive and transmit counters - * - * @return - * - \ref NVML_SUCCESS if counters were successfully frozen or unfrozen - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device, \a link, \a counter, or \a freeze is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceFreezeNvLinkUtilizationCounter (nvmlDevice_t device, unsigned int link, - unsigned int counter, nvmlEnableState_t freeze); - -/** - * Reset the NVLINK utilization counters - * Both the receive and transmit counters are operated on by this function - * - * For Pascal &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param link Specifies the NvLink link to be reset - * @param counter Specifies the counter that should be reset (0 or 1) - * - * @return - * - \ref NVML_SUCCESS if counters were successfully reset - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device, \a link, or \a counter is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceResetNvLinkUtilizationCounter (nvmlDevice_t device, unsigned int link, unsigned int counter); - -/** @} */ - -/***************************************************************************************************/ -/** @defgroup nvmlEvents Event Handling Methods - * This chapter describes methods that NVML can perform against each device to register and wait for - * some event to occur. - * @{ - */ -/***************************************************************************************************/ - -/** - * Create an empty set of events. - * Event set should be freed by \ref nvmlEventSetFree - * - * For Fermi &tm; or newer fully supported devices. - * @param set Reference in which to return the event handle - * - * @return - * - \ref NVML_SUCCESS if the event has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a set is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlEventSetFree - */ -nvmlReturn_t DECLDIR nvmlEventSetCreate(nvmlEventSet_t *set); - -/** - * Starts recording of events on a specified devices and add the events to specified \ref nvmlEventSet_t - * - * For Fermi &tm; or newer fully supported devices. - * Ecc events are available only on ECC enabled devices (see \ref nvmlDeviceGetTotalEccErrors) - * Power capping events are available only on Power Management enabled devices (see \ref nvmlDeviceGetPowerManagementMode) - * - * For Linux only. - * - * \b IMPORTANT: Operations on \a set are not thread safe - * - * This call starts recording of events on specific device. - * All events that occurred before this call are not recorded. - * Checking if some event occurred can be done with \ref nvmlEventSetWait - * - * If function reports NVML_ERROR_UNKNOWN, event set is in undefined state and should be freed. - * If function reports NVML_ERROR_NOT_SUPPORTED, event set can still be used. None of the requested eventTypes - * are registered in that case. - * - * @param device The identifier of the target device - * @param eventTypes Bitmask of \ref nvmlEventType to record - * @param set Set to which add new event types - * - * @return - * - \ref NVML_SUCCESS if the event has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a eventTypes is invalid or \a set is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the platform does not support this feature or some of requested event types - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlEventType - * @see nvmlDeviceGetSupportedEventTypes - * @see nvmlEventSetWait - * @see nvmlEventSetFree - */ -nvmlReturn_t DECLDIR nvmlDeviceRegisterEvents(nvmlDevice_t device, unsigned long long eventTypes, nvmlEventSet_t set); - -/** - * Returns information about events supported on device - * - * For Fermi &tm; or newer fully supported devices. - * - * Events are not supported on Windows. So this function returns an empty mask in \a eventTypes on Windows. - * - * @param device The identifier of the target device - * @param eventTypes Reference in which to return bitmask of supported events - * - * @return - * - \ref NVML_SUCCESS if the eventTypes has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a eventType is NULL - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlEventType - * @see nvmlDeviceRegisterEvents - */ -nvmlReturn_t DECLDIR nvmlDeviceGetSupportedEventTypes(nvmlDevice_t device, unsigned long long *eventTypes); - -/** - * Waits on events and delivers events - * - * For Fermi &tm; or newer fully supported devices. - * - * If some events are ready to be delivered at the time of the call, function returns immediately. - * If there are no events ready to be delivered, function sleeps till event arrives - * but not longer than specified timeout. This function in certain conditions can return before - * specified timeout passes (e.g. when interrupt arrives) - * - * In case of xid error, the function returns the most recent xid error type seen by the system. If there are multiple - * xid errors generated before nvmlEventSetWait is invoked then the last seen xid error type is returned for all - * xid error events. - * - * @param set Reference to set of events to wait on - * @param data Reference in which to return event data - * @param timeoutms Maximum amount of wait time in milliseconds for registered event - * - * @return - * - \ref NVML_SUCCESS if the data has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a data is NULL - * - \ref NVML_ERROR_TIMEOUT if no event arrived in specified timeout or interrupt arrived - * - \ref NVML_ERROR_GPU_IS_LOST if a GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlEventType - * @see nvmlDeviceRegisterEvents - */ -nvmlReturn_t DECLDIR nvmlEventSetWait(nvmlEventSet_t set, nvmlEventData_t * data, unsigned int timeoutms); - -/** - * Releases events in the set - * - * For Fermi &tm; or newer fully supported devices. - * - * @param set Reference to events to be released - * - * @return - * - \ref NVML_SUCCESS if the event has been successfully released - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - * - * @see nvmlDeviceRegisterEvents - */ -nvmlReturn_t DECLDIR nvmlEventSetFree(nvmlEventSet_t set); - -/** @} */ - -/***************************************************************************************************/ -/** @defgroup nvmlZPI Drain states - * This chapter describes methods that NVML can perform against each device to control their drain state - * and recognition by NVML and NVIDIA kernel driver. These methods can be used with out-of-band tools to - * power on/off GPUs, enable robust reset scenarios, etc. - * @{ - */ -/***************************************************************************************************/ - -/** - * Modify the drain state of a GPU. This method forces a GPU to no longer accept new incoming requests. - * Any new NVML process will no longer see this GPU. Persistence mode for this GPU must be turned off before - * this call is made. - * Must be called as administrator. - * For Linux only. - * - * For Pascal &tm; or newer fully supported devices. - * Some Kepler devices supported. - * - * @param pciInfo The PCI address of the GPU drain state to be modified - * @param newState The drain state that should be entered, see \ref nvmlEnableState_t - * - * @return - * - \ref NVML_SUCCESS if counters were successfully reset - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a nvmlIndex or \a newState is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_NO_PERMISSION if the calling process has insufficient permissions to perform operation - * - \ref NVML_ERROR_IN_USE if the device has persistence mode turned on - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceModifyDrainState (nvmlPciInfo_t *pciInfo, nvmlEnableState_t newState); - -/** - * Query the drain state of a GPU. This method is used to check if a GPU is in a currently draining - * state. - * For Linux only. - * - * For Pascal &tm; or newer fully supported devices. - * Some Kepler devices supported. - * - * @param pciInfo The PCI address of the GPU drain state to be queried - * @param currentState The current drain state for this GPU, see \ref nvmlEnableState_t - * - * @return - * - \ref NVML_SUCCESS if counters were successfully reset - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a nvmlIndex or \a currentState is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceQueryDrainState (nvmlPciInfo_t *pciInfo, nvmlEnableState_t *currentState); - -/** - * This method will remove the specified GPU from the view of both NVML and the NVIDIA kernel driver - * as long as no other processes are attached. If other processes are attached, this call will return - * NVML_ERROR_IN_USE and the GPU will be returned to its original "draining" state. Note: the - * only situation where a process can still be attached after nvmlDeviceModifyDrainState() is called - * to initiate the draining state is if that process was using, and is still using, a GPU before the - * call was made. Also note, persistence mode counts as an attachment to the GPU thus it must be disabled - * prior to this call. - * - * For long-running NVML processes please note that this will change the enumeration of current GPUs. - * For example, if there are four GPUs present and GPU1 is removed, the new enumeration will be 0-2. - * Also, device handles after the removed GPU will not be valid and must be re-established. - * Must be run as administrator. - * For Linux only. - * - * For Pascal &tm; or newer fully supported devices. - * Some Kepler devices supported. - * - * @param pciInfo The PCI address of the GPU to be removed - * - * @return - * - \ref NVML_SUCCESS if counters were successfully reset - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a nvmlIndex is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature - * - \ref NVML_ERROR_IN_USE if the device is still in use and cannot be removed - */ -nvmlReturn_t DECLDIR nvmlDeviceRemoveGpu (nvmlPciInfo_t *pciInfo); - -/** - * Request the OS and the NVIDIA kernel driver to rediscover a portion of the PCI subsystem looking for GPUs that - * were previously removed. The portion of the PCI tree can be narrowed by specifying a domain, bus, and device. - * If all are zeroes then the entire PCI tree will be searched. Please note that for long-running NVML processes - * the enumeration will change based on how many GPUs are discovered and where they are inserted in bus order. - * - * In addition, all newly discovered GPUs will be initialized and their ECC scrubbed which may take several seconds - * per GPU. Also, all device handles are no longer guaranteed to be valid post discovery. - * - * Must be run as administrator. - * For Linux only. - * - * For Pascal &tm; or newer fully supported devices. - * Some Kepler devices supported. - * - * @param pciInfo The PCI tree to be searched. Only the domain, bus, and device - * fields are used in this call. - * - * @return - * - \ref NVML_SUCCESS if counters were successfully reset - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a pciInfo is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if the operating system does not support this feature - * - \ref NVML_ERROR_OPERATING_SYSTEM if the operating system is denying this feature - * - \ref NVML_ERROR_NO_PERMISSION if the calling process has insufficient permissions to perform operation - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceDiscoverGpus (nvmlPciInfo_t *pciInfo); - -/** @} */ - -/***************************************************************************************************/ -/** @defgroup nvmlFieldValueQueries Field Value Queries - * This chapter describes NVML operations that are associated with retrieving Field Values from NVML - * @{ - */ -/***************************************************************************************************/ - -/** - * Request values for a list of fields for a device. This API allows multiple fields to be queried at once. - * If any of the underlying fieldIds are populated by the same driver call, the results for those field IDs - * will be populated from a single call rather than making a driver call for each fieldId. - * - * @param device The device handle of the GPU to request field values for - * @param valuesCount Number of entries in values that should be retrieved - * @param values Array of \a valuesCount structures to hold field values. - * Each value's fieldId must be populated prior to this call - * - * @return - * - \ref NVML_SUCCESS if any values in \a values were populated. Note that you must - * check the nvmlReturn field of each value for each individual - * status - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a values is NULL - */ -nvmlReturn_t DECLDIR nvmlDeviceGetFieldValues(nvmlDevice_t device, int valuesCount, nvmlFieldValue_t *values); - - -/** @} */ - -/***************************************************************************************************/ -/** @defgroup nvmlGridQueries Grid Queries - * This chapter describes NVML operations that are associated with NVIDIA GRID products. - * @{ - */ -/***************************************************************************************************/ - -/** - * This method is used to get the virtualization mode corresponding to the GPU. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device Identifier of the target device - * @param pVirtualMode Reference to virtualization mode. One of NVML_GPU_VIRTUALIZATION_? - * - * @return - * - \ref NVML_SUCCESS if \a pVirtualMode is fetched - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a pVirtualMode is NULL - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetVirtualizationMode(nvmlDevice_t device, nvmlGpuVirtualizationMode_t *pVirtualMode); - -/** @} */ - -/***************************************************************************************************/ -/** @defgroup nvmlGridCommands Grid Commands - * This chapter describes NVML operations that are associated with NVIDIA GRID products. - * @{ - */ -/***************************************************************************************************/ - -/** - * This method is used to set the virtualization mode corresponding to the GPU. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device Identifier of the target device - * @param virtualMode virtualization mode. One of NVML_GPU_VIRTUALIZATION_? - * - * @return - * - \ref NVML_SUCCESS if \a pVirtualMode is set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid or \a pVirtualMode is NULL - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_NOT_SUPPORTED if setting of virtualization mode is not supported. - * - \ref NVML_ERROR_NO_PERMISSION if setting of virtualization mode is not allowed for this client. - */ -nvmlReturn_t DECLDIR nvmlDeviceSetVirtualizationMode(nvmlDevice_t device, nvmlGpuVirtualizationMode_t virtualMode); - -/** @} */ - -/***************************************************************************************************/ -/** @defgroup nvmlVgpu vGPU Management - * @{ - * - * Set of APIs supporting GRID vGPU - */ -/***************************************************************************************************/ - -/** - * Retrieve the supported vGPU types on a physical GPU (device). - * - * An array of supported vGPU types for the physical GPU indicated by \a device is returned in the caller-supplied buffer - * pointed at by \a vgpuTypeIds. The element count of nvmlVgpuTypeId_t array is passed in \a vgpuCount, and \a vgpuCount - * is used to return the number of vGPU types written to the buffer. - * - * If the supplied buffer is not large enough to accomodate the vGPU type array, the function returns - * NVML_ERROR_INSUFFICIENT_SIZE, with the element count of nvmlVgpuTypeId_t array required in \a vgpuCount. - * To query the number of vGPU types supported for the GPU, call this function with *vgpuCount = 0. - * The code will return NVML_ERROR_INSUFFICIENT_SIZE, or NVML_SUCCESS if no vGPU types are supported. - * - * @param device The identifier of the target device - * @param vgpuCount Pointer to caller-supplied array size, and returns number of vGPU types - * @param vgpuTypeIds Pointer to caller-supplied array in which to return list of vGPU types - * - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_INSUFFICIENT_SIZE \a vgpuTypeIds buffer is too small, array element count is returned in \a vgpuCount - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuCount is NULL or \a device is invalid - * - \ref NVML_ERROR_NOT_SUPPORTED if vGPU is not supported by the device - * - \ref NVML_ERROR_VGPU_ECC_NOT_SUPPORTED if ECC is enabled on the device - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetSupportedVgpus(nvmlDevice_t device, unsigned int *vgpuCount, nvmlVgpuTypeId_t *vgpuTypeIds); - -/** - * Retrieve the currently creatable vGPU types on a physical GPU (device). - * - * An array of creatable vGPU types for the physical GPU indicated by \a device is returned in the caller-supplied buffer - * pointed at by \a vgpuTypeIds. The element count of nvmlVgpuTypeId_t array is passed in \a vgpuCount, and \a vgpuCount - * is used to return the number of vGPU types written to the buffer. - * - * The creatable vGPU types for a device may differ over time, as there may be restrictions on what type of vGPU types - * can concurrently run on a device. For example, if only one vGPU type is allowed at a time on a device, then the creatable - * list will be restricted to whatever vGPU type is already running on the device. - * - * If the supplied buffer is not large enough to accomodate the vGPU type array, the function returns - * NVML_ERROR_INSUFFICIENT_SIZE, with the element count of nvmlVgpuTypeId_t array required in \a vgpuCount. - * To query the number of vGPU types createable for the GPU, call this function with *vgpuCount = 0. - * The code will return NVML_ERROR_INSUFFICIENT_SIZE, or NVML_SUCCESS if no vGPU types are creatable. - * - * @param device The identifier of the target device - * @param vgpuCount Pointer to caller-supplied array size, and returns number of vGPU types - * @param vgpuTypeIds Pointer to caller-supplied array in which to return list of vGPU types - * - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_INSUFFICIENT_SIZE \a vgpuTypeIds buffer is too small, array element count is returned in \a vgpuCount - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuCount is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if vGPU is not supported by the device - * - \ref NVML_ERROR_VGPU_ECC_NOT_SUPPORTED if ECC is enabled on the device - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetCreatableVgpus(nvmlDevice_t device, unsigned int *vgpuCount, nvmlVgpuTypeId_t *vgpuTypeIds); - -/** - * Retrieve the class of a vGPU type. It will not exceed 64 characters in length (including the NUL terminator). - * See \ref nvmlConstants::NVML_DEVICE_NAME_BUFFER_SIZE. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuTypeId Handle to vGPU type - * @param vgpuTypeClass Pointer to string array to return class in - * @param size Size of string - * - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuTypeId is invalid, or \a vgpuTypeClass is NULL - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a size is too small - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuTypeGetClass(nvmlVgpuTypeId_t vgpuTypeId, char *vgpuTypeClass, unsigned int *size); - -/** - * Retrieve the vGPU type name. - * - * The name is an alphanumeric string that denotes a particular vGPU, e.g. GRID M60-2Q. It will not - * exceed 64 characters in length (including the NUL terminator). See \ref - * nvmlConstants::NVML_DEVICE_NAME_BUFFER_SIZE. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuTypeId Handle to vGPU type - * @param vgpuTypeName Pointer to buffer to return name - * @param size Size of buffer - * - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuTypeId is invalid, or \a name is NULL - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a size is too small - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuTypeGetName(nvmlVgpuTypeId_t vgpuTypeId, char *vgpuTypeName, unsigned int *size); - -/** - * Retrieve the device ID of a vGPU type. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuTypeId Handle to vGPU type - * @param deviceID Device ID and vendor ID of the device contained in single 32 bit value - * @param subsystemID Subsytem ID and subsytem vendor ID of the device contained in single 32 bit value - * - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuTypeId is invalid, or \a deviceId or \a subsystemID are NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuTypeGetDeviceID(nvmlVgpuTypeId_t vgpuTypeId, unsigned long long *deviceID, unsigned long long *subsystemID); - -/** - * Retrieve the vGPU framebuffer size in bytes. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuTypeId Handle to vGPU type - * @param fbSize Pointer to framebuffer size in bytes - * - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuTypeId is invalid, or \a fbSize is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuTypeGetFramebufferSize(nvmlVgpuTypeId_t vgpuTypeId, unsigned long long *fbSize); - -/** - * Retrieve count of vGPU's supported display heads. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuTypeId Handle to vGPU type - * @param numDisplayHeads Pointer to number of display heads - * - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuTypeId is invalid, or \a numDisplayHeads is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuTypeGetNumDisplayHeads(nvmlVgpuTypeId_t vgpuTypeId, unsigned int *numDisplayHeads); - -/** - * Retrieve vGPU display head's maximum supported resolution. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuTypeId Handle to vGPU type - * @param displayIndex Zero-based index of display head - * @param xdim Pointer to maximum number of pixels in X dimension - * @param ydim Pointer to maximum number of pixels in Y dimension - * - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuTypeId is invalid, or \a xdim or \a ydim are NULL, or \a displayIndex - * is out of range. - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuTypeGetResolution(nvmlVgpuTypeId_t vgpuTypeId, unsigned int displayIndex, unsigned int *xdim, unsigned int *ydim); - -/** - * Retrieve license requirements for a vGPU type - * - * The license type and version required to run the specified vGPU type is returned as an alphanumeric string, in the form - * ",", for example "GRID-Virtual-PC,2.0". If a vGPU is runnable with* more than one type of license, - * the licenses are delimited by a semicolon, for example "GRID-Virtual-PC,2.0;GRID-Virtual-WS,2.0;GRID-Virtual-WS-Ext,2.0". - * - * The total length of the returned string will not exceed 128 characters, including the NUL terminator. - * See \ref nvmlVgpuConstants::NVML_GRID_LICENSE_BUFFER_SIZE. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuTypeId Handle to vGPU type - * @param vgpuTypeLicenseString Pointer to buffer to return license info - * @param size Size of \a vgpuTypeLicenseString buffer - * - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuTypeId is invalid, or \a vgpuTypeLicenseString is NULL - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a size is too small - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuTypeGetLicense(nvmlVgpuTypeId_t vgpuTypeId, char *vgpuTypeLicenseString, unsigned int size); - -/** - * Retrieve the static frame rate limit value of the vGPU type - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuTypeId Handle to vGPU type - * @param frameRateLimit Reference to return the frame rate limit value - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_NOT_SUPPORTED if frame rate limiter is turned off for the vGPU type - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, or \a frameRateLimit is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuTypeGetFrameRateLimit(nvmlVgpuTypeId_t vgpuTypeId, unsigned int *frameRateLimit); - -/** - * Retrieve the maximum number of vGPU instances creatable on a device for given vGPU type - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param vgpuTypeId Handle to vGPU type - * @param vgpuInstanceCount Pointer to get the max number of vGPU instances - * that can be created on a deicve for given vgpuTypeId - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuTypeId is invalid or is not supported on target device, - * or \a vgpuInstanceCount is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuTypeGetMaxInstances(nvmlDevice_t device, nvmlVgpuTypeId_t vgpuTypeId, unsigned int *vgpuInstanceCount); - -/** - * Retrieve the active vGPU instances on a device. - * - * An array of active vGPU instances is returned in the caller-supplied buffer pointed at by \a vgpuInstances. The - * array elememt count is passed in \a vgpuCount, and \a vgpuCount is used to return the number of vGPU instances - * written to the buffer. - * - * If the supplied buffer is not large enough to accomodate the vGPU instance array, the function returns - * NVML_ERROR_INSUFFICIENT_SIZE, with the element count of nvmlVgpuInstance_t array required in \a vgpuCount. - * To query the number of active vGPU instances, call this function with *vgpuCount = 0. The code will return - * NVML_ERROR_INSUFFICIENT_SIZE, or NVML_SUCCESS if no vGPU Types are supported. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param device The identifier of the target device - * @param vgpuCount Pointer which passes in the array size as well as get - * back the number of types - * @param vgpuInstances Pointer to array in which to return list of vGPU instances - * - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, or \a vgpuCount is NULL - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a size is too small - * - \ref NVML_ERROR_NOT_SUPPORTED if vGPU is not supported by the device - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetActiveVgpus(nvmlDevice_t device, unsigned int *vgpuCount, nvmlVgpuInstance_t *vgpuInstances); - -/** - * Retrieve the VM ID associated with a vGPU instance. - * - * The VM ID is returned as a string, not exceeding 80 characters in length (including the NUL terminator). - * See \ref nvmlConstants::NVML_DEVICE_UUID_BUFFER_SIZE. - * - * The format of the VM ID varies by platform, and is indicated by the type identifier returned in \a vmIdType. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuInstance Identifier of the target vGPU instance - * @param vmId Pointer to caller-supplied buffer to hold VM ID - * @param size Size of buffer in bytes - * @param vmIdType Pointer to hold VM ID type - * - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuInstance is invalid, or \a vmId or \a vmIdType are NULL - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a size is too small - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuInstanceGetVmID(nvmlVgpuInstance_t vgpuInstance, char *vmId, unsigned int size, nvmlVgpuVmIdType_t *vmIdType); - -/** - * Retrieve the UUID of a vGPU instance. - * - * The UUID is a globally unique identifier associated with the vGPU, and is returned as a 5-part hexadecimal string, - * not exceeding 80 characters in length (including the NULL terminator). - * See \ref nvmlConstants::NVML_DEVICE_UUID_BUFFER_SIZE. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuInstance Identifier of the target vGPU instance - * @param uuid Pointer to caller-supplied buffer to hold vGPU UUID - * @param size Size of buffer in bytes - * - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuInstance is invalid, or \a uuid is NULL - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a size is too small - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuInstanceGetUUID(nvmlVgpuInstance_t vgpuInstance, char *uuid, unsigned int size); - -/** - * Retrieve the NVIDIA driver version installed in the VM associated with a vGPU. - * - * The version is returned as an alphanumeric string in the caller-supplied buffer \a version. The length of the version - * string will not exceed 80 characters in length (including the NUL terminator). - * See \ref nvmlConstants::NVML_SYSTEM_DRIVER_VERSION_BUFFER_SIZE. - * - * nvmlVgpuInstanceGetVmDriverVersion() may be called at any time for a vGPU instance. The guest VM driver version is - * returned as "Unknown" if no NVIDIA driver is installed in the VM, or the VM has not yet booted to the point where the - * NVIDIA driver is loaded and initialized. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuInstance Identifier of the target vGPU instance - * @param version Caller-supplied buffer to return driver version string - * @param length Size of \a version buffer - * - * @return - * - \ref NVML_SUCCESS if \a version has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuInstance is invalid - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a length is too small - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuInstanceGetVmDriverVersion(nvmlVgpuInstance_t vgpuInstance, char* version, unsigned int length); - -/** - * Retrieve the framebuffer usage in bytes. - * - * Framebuffer usage is the amont of vGPU framebuffer memory that is currently in use by the VM. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuInstance The identifier of the target instance - * @param fbUsage Pointer to framebuffer usage in bytes - * - * @return - * - \ref NVML_SUCCESS successful completion - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuInstance is invalid, or \a fbUsage is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuInstanceGetFbUsage(nvmlVgpuInstance_t vgpuInstance, unsigned long long *fbUsage); - -/** - * Retrieve the current licensing state of the vGPU instance. - * - * If the vGPU is currently licensed, \a licensed is set to 1, otherwise it is set to 0. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuInstance Identifier of the target vGPU instance - * @param licensed Reference to return the licensing status - * - * @return - * - \ref NVML_SUCCESS if \a licensed has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuInstance is invalid, or \a licensed is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuInstanceGetLicenseStatus(nvmlVgpuInstance_t vgpuInstance, unsigned int *licensed); - -/** - * Retrieve the vGPU type of a vGPU instance. - * - * Returns the vGPU type ID of vgpu assigned to the vGPU instance. - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuInstance Identifier of the target vGPU instance - * @param vgpuTypeId Reference to return the vgpuTypeId - * - * @return - * - \ref NVML_SUCCESS if \a vgpuTypeId has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuInstance is invalid, or \a vgpuTypeId is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuInstanceGetType(nvmlVgpuInstance_t vgpuInstance, nvmlVgpuTypeId_t *vgpuTypeId); - -/** - * Retrieve the frame rate limit set for the vGPU instance. - * - * Returns the value of the frame rate limit set for the vGPU instance - * - * For Kepler &tm; or newer fully supported devices. - * - * @param vgpuInstance Identifier of the target vGPU instance - * @param frameRateLimit Reference to return the frame rate limit - * - * @return - * - \ref NVML_SUCCESS if \a frameRateLimit has been set - * - \ref NVML_ERROR_NOT_SUPPORTED if frame rate limiter is turned off for the vGPU type - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuInstance is invalid, or \a frameRateLimit is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuInstanceGetFrameRateLimit(nvmlVgpuInstance_t vgpuInstance, unsigned int *frameRateLimit); - -/** - * Retrieve the encoder Capacity of a vGPU instance, in macroblocks per second. - * - * For Maxwell &tm; or newer fully supported devices. - * - * @param vgpuInstance Identifier of the target vGPU instance - * @param encoderCapacity Reference to an unsigned int for the encoder capacity - * - * @return - * - \ref NVML_SUCCESS if \a encoderCapacity has been retrived - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuInstance is invalid, or \a encoderQueryType is invalid - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuInstanceGetEncoderCapacity(nvmlVgpuInstance_t vgpuInstance, unsigned int *encoderCapacity); - -/** - * Set the encoder Capacity of a vGPU instance, in macroblocks per second. - * - * For Maxwell &tm; or newer fully supported devices. - * - * @param vgpuInstance Identifier of the target vGPU instance - * @param encoderCapacity Unsigned int for the encoder capacity value - * - * @return - * - \ref NVML_SUCCESS if \a encoderCapacity has been set - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a vgpuInstance is invalid - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuInstanceSetEncoderCapacity(nvmlVgpuInstance_t vgpuInstance, unsigned int encoderCapacity); - -/** - * Retrieves current utilization for vGPUs on a physical GPU (device). - * - * For Kepler &tm; or newer fully supported devices. - * - * Reads recent utilization of GPU SM (3D/Compute), framebuffer, video encoder, and video decoder for vGPU instances running - * on a device. Utilization values are returned as an array of utilization sample structures in the caller-supplied buffer - * pointed at by \a utilizationSamples. One utilization sample structure is returned per vGPU instance, and includes the - * CPU timestamp at which the samples were recorded. Individual utilization values are returned as "unsigned int" values - * in nvmlValue_t unions. The function sets the caller-supplied \a sampleValType to NVML_VALUE_TYPE_UNSIGNED_INT to - * indicate the returned value type. - * - * To read utilization values, first determine the size of buffer required to hold the samples by invoking the function with - * \a utilizationSamples set to NULL. The function will return NVML_ERROR_INSUFFICIENT_SIZE, with the current vGPU instance - * count in \a vgpuInstanceSamplesCount, or NVML_SUCCESS if the current vGPU instance count is zero. The caller should allocate - * a buffer of size vgpuInstanceSamplesCount * sizeof(nvmlVgpuInstanceUtilizationSample_t). Invoke the function again with - * the allocated buffer passed in \a utilizationSamples, and \a vgpuInstanceSamplesCount set to the number of entries the - * buffer is sized for. - * - * On successful return, the function updates \a vgpuInstanceSampleCount with the number of vGPU utilization sample - * structures that were actually written. This may differ from a previously read value as vGPU instances are created or - * destroyed. - * - * lastSeenTimeStamp represents the CPU timestamp in microseconds at which utilization samples were last read. Set it to 0 - * to read utilization based on all the samples maintained by the driver's internal sample buffer. Set lastSeenTimeStamp - * to a timeStamp retrieved from a previous query to read utilization since the previous query. - * - * @param device The identifier for the target device - * @param lastSeenTimeStamp Return only samples with timestamp greater than lastSeenTimeStamp. - * @param sampleValType Pointer to caller-supplied buffer to hold the type of returned sample values - * @param vgpuInstanceSamplesCount Pointer to caller-supplied array size, and returns number of vGPU instances - * @param utilizationSamples Pointer to caller-supplied buffer in which vGPU utilization samples are returned - - * @return - * - \ref NVML_SUCCESS if utilization samples are successfully retrieved - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, \a vgpuInstanceSamplesCount or \a sampleValType is - * NULL, or a sample count of 0 is passed with a non-NULL \a utilizationSamples - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if supplied \a vgpuInstanceSamplesCount is too small to return samples for all - * vGPU instances currently executing on the device - * - \ref NVML_ERROR_NOT_SUPPORTED if vGPU is not supported by the device - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_NOT_FOUND if sample entries are not found - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetVgpuUtilization(nvmlDevice_t device, unsigned long long lastSeenTimeStamp, - nvmlValueType_t *sampleValType, unsigned int *vgpuInstanceSamplesCount, - nvmlVgpuInstanceUtilizationSample_t *utilizationSamples); - -/** - * Retrieves current utilization for processes running on vGPUs on a physical GPU (device). - * - * For Maxwell &tm; or newer fully supported devices. - * - * Reads recent utilization of GPU SM (3D/Compute), framebuffer, video encoder, and video decoder for processes running on - * vGPU instances active on a device. Utilization values are returned as an array of utilization sample structures in the - * caller-supplied buffer pointed at by \a utilizationSamples. One utilization sample structure is returned per process running - * on vGPU instances, that had some non-zero utilization during the last sample period. It includes the CPU timestamp at which - * the samples were recorded. Individual utilization values are returned as "unsigned int" values. - * - * To read utilization values, first determine the size of buffer required to hold the samples by invoking the function with - * \a utilizationSamples set to NULL. The function will return NVML_ERROR_INSUFFICIENT_SIZE, with the current vGPU instance - * count in \a vgpuProcessSamplesCount. The caller should allocate a buffer of size - * vgpuProcessSamplesCount * sizeof(nvmlVgpuProcessUtilizationSample_t). Invoke the function again with - * the allocated buffer passed in \a utilizationSamples, and \a vgpuProcessSamplesCount set to the number of entries the - * buffer is sized for. - * - * On successful return, the function updates \a vgpuSubProcessSampleCount with the number of vGPU sub process utilization sample - * structures that were actually written. This may differ from a previously read value depending on the number of processes that are active - * in any given sample period. - * - * lastSeenTimeStamp represents the CPU timestamp in microseconds at which utilization samples were last read. Set it to 0 - * to read utilization based on all the samples maintained by the driver's internal sample buffer. Set lastSeenTimeStamp - * to a timeStamp retrieved from a previous query to read utilization since the previous query. - * - * @param device The identifier for the target device - * @param lastSeenTimeStamp Return only samples with timestamp greater than lastSeenTimeStamp. - * @param vgpuProcessSamplesCount Pointer to caller-supplied array size, and returns number of processes running on vGPU instances - * @param utilizationSamples Pointer to caller-supplied buffer in which vGPU sub process utilization samples are returned - - * @return - * - \ref NVML_SUCCESS if utilization samples are successfully retrieved - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, \a vgpuProcessSamplesCount or a sample count of 0 is - * passed with a non-NULL \a utilizationSamples - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if supplied \a vgpuProcessSamplesCount is too small to return samples for all - * vGPU instances currently executing on the device - * - \ref NVML_ERROR_NOT_SUPPORTED if vGPU is not supported by the device - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_NOT_FOUND if sample entries are not found - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetVgpuProcessUtilization(nvmlDevice_t device, unsigned long long lastSeenTimeStamp, - unsigned int *vgpuProcessSamplesCount, - nvmlVgpuProcessUtilizationSample_t *utilizationSamples); -/** - * Retrieve the GRID licensable features. - * - * Identifies whether the system supports GRID Software Licensing. If it does, return the list of licensable feature(s) - * and their current license status. - * - * @param device Identifier of the target device - * @param pGridLicensableFeatures Pointer to structure in which GRID licensable features are returned - * - * @return - * - \ref NVML_SUCCESS if licensable features are successfully retrieved - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a pGridLicensableFeatures is NULL - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetGridLicensableFeatures(nvmlDevice_t device, nvmlGridLicensableFeatures_t *pGridLicensableFeatures); - -/** - * Retrieves the current encoder statistics of a vGPU Instance - * - * For Maxwell &tm; or newer fully supported devices. - * - * @param vgpuInstance Identifier of the target vGPU instance - * @param sessionCount Reference to an unsigned int for count of active encoder sessions - * @param averageFps Reference to an unsigned int for trailing average FPS of all active sessions - * @param averageLatency Reference to an unsigned int for encode latency in microseconds - * - * @return - * - \ref NVML_SUCCESS if \a sessionCount, \a averageFps and \a averageLatency is fetched - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a sessionCount , or \a averageFps or \a averageLatency is NULL - * or \a vgpuInstance is invalid. - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuInstanceGetEncoderStats(nvmlVgpuInstance_t vgpuInstance, unsigned int *sessionCount, - unsigned int *averageFps, unsigned int *averageLatency); - -/** - * Retrieves information about all active encoder sessions on a vGPU Instance. - * - * An array of active encoder sessions is returned in the caller-supplied buffer pointed at by \a sessionInfo. The - * array elememt count is passed in \a sessionCount, and \a sessionCount is used to return the number of sessions - * written to the buffer. - * - * If the supplied buffer is not large enough to accomodate the active session array, the function returns - * NVML_ERROR_INSUFFICIENT_SIZE, with the element count of nvmlEncoderSessionInfo_t array required in \a sessionCount. - * To query the number of active encoder sessions, call this function with *sessionCount = 0. The code will return - * NVML_SUCCESS with number of active encoder sessions updated in *sessionCount. - * - * For Maxwell &tm; or newer fully supported devices. - * - * @param vgpuInstance Identifier of the target vGPU instance - * @param sessionCount Reference to caller supplied array size, and returns - * the number of sessions. - * @param sessionInfo Reference to caller supplied array in which the list - * of session information us returned. - * - * @return - * - \ref NVML_SUCCESS if \a sessionInfo is fetched - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INSUFFICIENT_SIZE if \a sessionCount is too small, array element count is - returned in \a sessionCount - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a sessionCount is NULL or \a vgpuInstance is invalid.. - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlVgpuInstanceGetEncoderSessions(nvmlVgpuInstance_t vgpuInstance, unsigned int *sessionCount, nvmlEncoderSessionInfo_t *sessionInfo); - -/** - * Retrieves the current utilization and process ID - * - * For Maxwell &tm; or newer fully supported devices. - * - * Reads recent utilization of GPU SM (3D/Compute), framebuffer, video encoder, and video decoder for processes running. - * Utilization values are returned as an array of utilization sample structures in the caller-supplied buffer pointed at - * by \a utilization. One utilization sample structure is returned per process running, that had some non-zero utilization - * during the last sample period. It includes the CPU timestamp at which the samples were recorded. Individual utilization values - * are returned as "unsigned int" values. - * - * To read utilization values, first determine the size of buffer required to hold the samples by invoking the function with - * \a utilization set to NULL. The caller should allocate a buffer of size - * processSamplesCount * sizeof(nvmlProcessUtilizationSample_t). Invoke the function again with the allocated buffer passed - * in \a utilization, and \a processSamplesCount set to the number of entries the buffer is sized for. - * - * On successful return, the function updates \a processSamplesCount with the number of process utilization sample - * structures that were actually written. This may differ from a previously read value as instances are created or - * destroyed. - * - * lastSeenTimeStamp represents the CPU timestamp in microseconds at which utilization samples were last read. Set it to 0 - * to read utilization based on all the samples maintained by the driver's internal sample buffer. Set lastSeenTimeStamp - * to a timeStamp retrieved from a previous query to read utilization since the previous query. - * - * @param device The identifier of the target device - * @param utilization Pointer to caller-supplied buffer in which guest process utilization samples are returned - * @param processSamplesCount Pointer to caller-supplied array size, and returns number of processes running - * @param lastSeenTimeStamp Return only samples with timestamp greater than lastSeenTimeStamp. - - * @return - * - \ref NVML_SUCCESS if \a utilization has been populated - * - \ref NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized - * - \ref NVML_ERROR_INVALID_ARGUMENT if \a device is invalid, \a utilization is NULL, or \a samplingPeriodUs is NULL - * - \ref NVML_ERROR_NOT_SUPPORTED if the device does not support this feature - * - \ref NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible - * - \ref NVML_ERROR_UNKNOWN on any unexpected error - */ -nvmlReturn_t DECLDIR nvmlDeviceGetProcessUtilization(nvmlDevice_t device, nvmlProcessUtilizationSample_t *utilization, - unsigned int *processSamplesCount, unsigned long long lastSeenTimeStamp); - -/** @} */ - -/** - * NVML API versioning support - */ -#if defined(__NVML_API_VERSION_INTERNAL) -#undef nvmlDeviceGetPciInfo -#undef nvmlDeviceGetCount -#undef nvmlDeviceGetHandleByIndex -#undef nvmlDeviceGetHandleByPciBusId -#undef nvmlInit -#endif - -#ifdef __cplusplus -} -#endif - -#endif diff --git a/vendor/github.com/moby/term/tc.go b/vendor/github.com/moby/term/tc.go index 65556027a6d..8a5e09f5849 100644 --- a/vendor/github.com/moby/term/tc.go +++ b/vendor/github.com/moby/term/tc.go @@ -1,3 +1,4 @@ +//go:build !windows // +build !windows package term diff --git a/vendor/github.com/moby/term/term.go b/vendor/github.com/moby/term/term.go index 29c6acf1c7e..2dd3d090dff 100644 --- a/vendor/github.com/moby/term/term.go +++ b/vendor/github.com/moby/term/term.go @@ -1,3 +1,4 @@ +//go:build !windows // +build !windows // Package term provides structures and helper functions to work with @@ -6,18 +7,14 @@ package term import ( "errors" - "fmt" "io" "os" - "os/signal" "golang.org/x/sys/unix" ) -var ( - // ErrInvalidState is returned if the state of the terminal is invalid. - ErrInvalidState = errors.New("Invalid terminal state") -) +// ErrInvalidState is returned if the state of the terminal is invalid. +var ErrInvalidState = errors.New("Invalid terminal state") // State represents the state of the terminal. type State struct { @@ -81,7 +78,6 @@ func DisableEcho(fd uintptr, state *State) error { if err := tcset(fd, &newState); err != nil { return err } - handleInterrupt(fd, state) return nil } @@ -93,7 +89,6 @@ func SetRawTerminal(fd uintptr) (*State, error) { if err != nil { return nil, err } - handleInterrupt(fd, oldState) return oldState, err } @@ -103,18 +98,3 @@ func SetRawTerminal(fd uintptr) (*State, error) { func SetRawTerminalOutput(fd uintptr) (*State, error) { return nil, nil } - -func handleInterrupt(fd uintptr, state *State) { - sigchan := make(chan os.Signal, 1) - signal.Notify(sigchan, os.Interrupt) - go func() { - for range sigchan { - // quit cleanly and the new terminal item is on a new line - fmt.Println() - signal.Stop(sigchan) - close(sigchan) - RestoreTerminal(fd, state) - os.Exit(1) - } - }() -} diff --git a/vendor/github.com/moby/term/termios.go b/vendor/github.com/moby/term/termios.go index 0f028e2273a..99c0f7de60d 100644 --- a/vendor/github.com/moby/term/termios.go +++ b/vendor/github.com/moby/term/termios.go @@ -1,3 +1,4 @@ +//go:build !windows // +build !windows package term diff --git a/vendor/github.com/moby/term/termios_bsd.go b/vendor/github.com/moby/term/termios_bsd.go index 922dd4baab0..45f77e03c7f 100644 --- a/vendor/github.com/moby/term/termios_bsd.go +++ b/vendor/github.com/moby/term/termios_bsd.go @@ -1,3 +1,4 @@ +//go:build darwin || freebsd || openbsd || netbsd // +build darwin freebsd openbsd netbsd package term diff --git a/vendor/github.com/moby/term/termios_nonbsd.go b/vendor/github.com/moby/term/termios_nonbsd.go index 038fd61ba1e..88b7b215638 100644 --- a/vendor/github.com/moby/term/termios_nonbsd.go +++ b/vendor/github.com/moby/term/termios_nonbsd.go @@ -1,4 +1,5 @@ -//+build !darwin,!freebsd,!netbsd,!openbsd,!windows +//go:build !darwin && !freebsd && !netbsd && !openbsd && !windows +// +build !darwin,!freebsd,!netbsd,!openbsd,!windows package term diff --git a/vendor/github.com/moby/term/windows/ansi_reader.go b/vendor/github.com/moby/term/windows/ansi_reader.go index 155251521b0..f32aa537ef2 100644 --- a/vendor/github.com/moby/term/windows/ansi_reader.go +++ b/vendor/github.com/moby/term/windows/ansi_reader.go @@ -1,3 +1,4 @@ +//go:build windows // +build windows package windowsconsole @@ -190,7 +191,6 @@ func keyToString(keyEvent *winterm.KEY_EVENT_RECORD, escapeSequence []byte) stri // -S Suspends printing on the screen (does not stop the program). // -U Deletes all characters on the current line. Also called the KILL key. // -E Quits current command and creates a core - } // +Key generates ESC N Key diff --git a/vendor/github.com/moby/term/windows/ansi_writer.go b/vendor/github.com/moby/term/windows/ansi_writer.go index ccb5ef07757..4243307fd35 100644 --- a/vendor/github.com/moby/term/windows/ansi_writer.go +++ b/vendor/github.com/moby/term/windows/ansi_writer.go @@ -1,3 +1,4 @@ +//go:build windows // +build windows package windowsconsole diff --git a/vendor/github.com/moby/term/windows/console.go b/vendor/github.com/moby/term/windows/console.go index 993694ddcd9..116b74e8f58 100644 --- a/vendor/github.com/moby/term/windows/console.go +++ b/vendor/github.com/moby/term/windows/console.go @@ -1,3 +1,4 @@ +//go:build windows // +build windows package windowsconsole diff --git a/vendor/github.com/moby/term/winsize.go b/vendor/github.com/moby/term/winsize.go index 1ef98d59961..bea8d4595cf 100644 --- a/vendor/github.com/moby/term/winsize.go +++ b/vendor/github.com/moby/term/winsize.go @@ -1,3 +1,4 @@ +//go:build !windows // +build !windows package term diff --git a/vendor/github.com/opencontainers/runtime-spec/specs-go/config.go b/vendor/github.com/opencontainers/runtime-spec/specs-go/config.go index 6a7a91e5596..068edd052c1 100644 --- a/vendor/github.com/opencontainers/runtime-spec/specs-go/config.go +++ b/vendor/github.com/opencontainers/runtime-spec/specs-go/config.go @@ -12,10 +12,12 @@ type Spec struct { Root *Root `json:"root,omitempty"` // Hostname configures the container's hostname. Hostname string `json:"hostname,omitempty"` + // Domainname configures the container's domainname. + Domainname string `json:"domainname,omitempty"` // Mounts configures additional mounts (on top of Root). Mounts []Mount `json:"mounts,omitempty"` // Hooks configures callbacks for container lifecycle events. - Hooks *Hooks `json:"hooks,omitempty" platform:"linux,solaris"` + Hooks *Hooks `json:"hooks,omitempty" platform:"linux,solaris,zos"` // Annotations contains arbitrary metadata for the container. Annotations map[string]string `json:"annotations,omitempty"` @@ -27,6 +29,8 @@ type Spec struct { Windows *Windows `json:"windows,omitempty" platform:"windows"` // VM specifies configuration for virtual-machine-based containers. VM *VM `json:"vm,omitempty" platform:"vm"` + // ZOS is platform-specific configuration for z/OS based containers. + ZOS *ZOS `json:"zos,omitempty" platform:"zos"` } // Process contains information to start a specific application inside the container. @@ -49,7 +53,7 @@ type Process struct { // Capabilities are Linux capabilities that are kept for the process. Capabilities *LinuxCapabilities `json:"capabilities,omitempty" platform:"linux"` // Rlimits specifies rlimit options to apply to the process. - Rlimits []POSIXRlimit `json:"rlimits,omitempty" platform:"linux,solaris"` + Rlimits []POSIXRlimit `json:"rlimits,omitempty" platform:"linux,solaris,zos"` // NoNewPrivileges controls whether additional privileges could be gained by processes in the container. NoNewPrivileges bool `json:"noNewPrivileges,omitempty" platform:"linux"` // ApparmorProfile specifies the apparmor profile for the container. @@ -86,11 +90,11 @@ type Box struct { // User specifies specific user (and group) information for the container process. type User struct { // UID is the user id. - UID uint32 `json:"uid" platform:"linux,solaris"` + UID uint32 `json:"uid" platform:"linux,solaris,zos"` // GID is the group id. - GID uint32 `json:"gid" platform:"linux,solaris"` + GID uint32 `json:"gid" platform:"linux,solaris,zos"` // Umask is the umask for the init process. - Umask *uint32 `json:"umask,omitempty" platform:"linux,solaris"` + Umask *uint32 `json:"umask,omitempty" platform:"linux,solaris,zos"` // AdditionalGids are additional group ids set for the container's process. AdditionalGids []uint32 `json:"additionalGids,omitempty" platform:"linux,solaris"` // Username is the user name. @@ -110,11 +114,16 @@ type Mount struct { // Destination is the absolute path where the mount will be placed in the container. Destination string `json:"destination"` // Type specifies the mount kind. - Type string `json:"type,omitempty" platform:"linux,solaris"` + Type string `json:"type,omitempty" platform:"linux,solaris,zos"` // Source specifies the source path of the mount. Source string `json:"source,omitempty"` // Options are fstab style mount options. Options []string `json:"options,omitempty"` + + // UID/GID mappings used for changing file owners w/o calling chown, fs should support it. + // Every mount point could have its own mapping. + UIDMappings []LinuxIDMapping `json:"uidMappings,omitempty" platform:"linux"` + GIDMappings []LinuxIDMapping `json:"gidMappings,omitempty" platform:"linux"` } // Hook specifies a command that is run at a particular event in the lifecycle of a container @@ -178,7 +187,7 @@ type Linux struct { // MountLabel specifies the selinux context for the mounts in the container. MountLabel string `json:"mountLabel,omitempty"` // IntelRdt contains Intel Resource Director Technology (RDT) information for - // handling resource constraints (e.g., L3 cache, memory bandwidth) for the container + // handling resource constraints and monitoring metrics (e.g., L3 cache, memory bandwidth) for the container IntelRdt *LinuxIntelRdt `json:"intelRdt,omitempty"` // Personality contains configuration for the Linux personality syscall Personality *LinuxPersonality `json:"personality,omitempty"` @@ -250,8 +259,8 @@ type LinuxInterfacePriority struct { Priority uint32 `json:"priority"` } -// linuxBlockIODevice holds major:minor format supported in blkio cgroup -type linuxBlockIODevice struct { +// LinuxBlockIODevice holds major:minor format supported in blkio cgroup +type LinuxBlockIODevice struct { // Major is the device's major number. Major int64 `json:"major"` // Minor is the device's minor number. @@ -260,7 +269,7 @@ type linuxBlockIODevice struct { // LinuxWeightDevice struct holds a `major:minor weight` pair for weightDevice type LinuxWeightDevice struct { - linuxBlockIODevice + LinuxBlockIODevice // Weight is the bandwidth rate for the device. Weight *uint16 `json:"weight,omitempty"` // LeafWeight is the bandwidth rate for the device while competing with the cgroup's child cgroups, CFQ scheduler only @@ -269,7 +278,7 @@ type LinuxWeightDevice struct { // LinuxThrottleDevice struct holds a `major:minor rate_per_second` pair type LinuxThrottleDevice struct { - linuxBlockIODevice + LinuxBlockIODevice // Rate is the IO rate limit per cgroup per device Rate uint64 `json:"rate"` } @@ -310,6 +319,10 @@ type LinuxMemory struct { DisableOOMKiller *bool `json:"disableOOMKiller,omitempty"` // Enables hierarchical memory accounting UseHierarchy *bool `json:"useHierarchy,omitempty"` + // CheckBeforeUpdate enables checking if a new memory limit is lower + // than the current usage during update, and if so, rejecting the new + // limit. + CheckBeforeUpdate *bool `json:"checkBeforeUpdate,omitempty"` } // LinuxCPU for Linux cgroup 'cpu' resource management @@ -328,6 +341,8 @@ type LinuxCPU struct { Cpus string `json:"cpus,omitempty"` // List of memory nodes in the cpuset. Default is to use any available memory node. Mems string `json:"mems,omitempty"` + // cgroups are configured with minimum weight, 0: default behavior, 1: SCHED_IDLE. + Idle *int64 `json:"idle,omitempty"` } // LinuxPids for Linux cgroup 'pids' resource management (Linux 4.3) @@ -522,11 +537,21 @@ type WindowsMemoryResources struct { // WindowsCPUResources contains CPU resource management settings. type WindowsCPUResources struct { - // Number of CPUs available to the container. + // Count is the number of CPUs available to the container. It represents the + // fraction of the configured processor `count` in a container in relation + // to the processors available in the host. The fraction ultimately + // determines the portion of processor cycles that the threads in a + // container can use during each scheduling interval, as the number of + // cycles per 10,000 cycles. Count *uint64 `json:"count,omitempty"` - // CPU shares (relative weight to other containers with cpu shares). + // Shares limits the share of processor time given to the container relative + // to other workloads on the processor. The processor `shares` (`weight` at + // the platform level) is a value between 0 and 10000. Shares *uint16 `json:"shares,omitempty"` - // Specifies the portion of processor cycles that this container can use as a percentage times 100. + // Maximum determines the portion of processor cycles that the threads in a + // container can use during each scheduling interval, as the number of + // cycles per 10,000 cycles. Set processor `maximum` to a percentage times + // 100. Maximum *uint16 `json:"maximum,omitempty"` } @@ -613,6 +638,23 @@ type Arch string // LinuxSeccompFlag is a flag to pass to seccomp(2). type LinuxSeccompFlag string +const ( + // LinuxSeccompFlagLog is a seccomp flag to request all returned + // actions except SECCOMP_RET_ALLOW to be logged. An administrator may + // override this filter flag by preventing specific actions from being + // logged via the /proc/sys/kernel/seccomp/actions_logged file. (since + // Linux 4.14) + LinuxSeccompFlagLog LinuxSeccompFlag = "SECCOMP_FILTER_FLAG_LOG" + + // LinuxSeccompFlagSpecAllow can be used to disable Speculative Store + // Bypass mitigation. (since Linux 4.17) + LinuxSeccompFlagSpecAllow LinuxSeccompFlag = "SECCOMP_FILTER_FLAG_SPEC_ALLOW" + + // LinuxSeccompFlagWaitKillableRecv can be used to switch to the wait + // killable semantics. (since Linux 5.19) + LinuxSeccompFlagWaitKillableRecv LinuxSeccompFlag = "SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV" +) + // Additional architectures permitted to be used for system calls // By default only the native architecture of the kernel is permitted const ( @@ -683,8 +725,9 @@ type LinuxSyscall struct { Args []LinuxSeccompArg `json:"args,omitempty"` } -// LinuxIntelRdt has container runtime resource constraints for Intel RDT -// CAT and MBA features which introduced in Linux 4.10 and 4.12 kernel +// LinuxIntelRdt has container runtime resource constraints for Intel RDT CAT and MBA +// features and flags enabling Intel RDT CMT and MBM features. +// Intel RDT features are available in Linux 4.14 and newer kernel versions. type LinuxIntelRdt struct { // The identity for RDT Class of Service ClosID string `json:"closID,omitempty"` @@ -697,4 +740,36 @@ type LinuxIntelRdt struct { // The unit of memory bandwidth is specified in "percentages" by // default, and in "MBps" if MBA Software Controller is enabled. MemBwSchema string `json:"memBwSchema,omitempty"` + + // EnableCMT is the flag to indicate if the Intel RDT CMT is enabled. CMT (Cache Monitoring Technology) supports monitoring of + // the last-level cache (LLC) occupancy for the container. + EnableCMT bool `json:"enableCMT,omitempty"` + + // EnableMBM is the flag to indicate if the Intel RDT MBM is enabled. MBM (Memory Bandwidth Monitoring) supports monitoring of + // total and local memory bandwidth for the container. + EnableMBM bool `json:"enableMBM,omitempty"` +} + +// ZOS contains platform-specific configuration for z/OS based containers. +type ZOS struct { + // Devices are a list of device nodes that are created for the container + Devices []ZOSDevice `json:"devices,omitempty"` +} + +// ZOSDevice represents the mknod information for a z/OS special device file +type ZOSDevice struct { + // Path to the device. + Path string `json:"path"` + // Device type, block, char, etc. + Type string `json:"type"` + // Major is the device's major number. + Major int64 `json:"major"` + // Minor is the device's minor number. + Minor int64 `json:"minor"` + // FileMode permission bits for the device. + FileMode *os.FileMode `json:"fileMode,omitempty"` + // UID of the device. + UID *uint32 `json:"uid,omitempty"` + // Gid of the device. + GID *uint32 `json:"gid,omitempty"` } diff --git a/vendor/modules.txt b/vendor/modules.txt index 41b5d8e2077..5dafab628b2 100644 --- a/vendor/modules.txt +++ b/vendor/modules.txt @@ -353,9 +353,8 @@ github.com/golang/protobuf/ptypes/wrappers # github.com/google/btree v1.0.1 ## explicit; go 1.12 github.com/google/btree -# github.com/google/cadvisor v0.46.0 +# github.com/google/cadvisor v0.47.1 ## explicit; go 1.16 -github.com/google/cadvisor/accelerators github.com/google/cadvisor/cache/memory github.com/google/cadvisor/client/v2 github.com/google/cadvisor/collector @@ -526,9 +525,6 @@ github.com/mailru/easyjson/jwriter # github.com/matttproud/golang_protobuf_extensions v1.0.2 ## explicit; go 1.9 github.com/matttproud/golang_protobuf_extensions/pbutil -# github.com/mindprince/gonvml v0.0.0-20190828220739-9ebdce4bb989 -## explicit -github.com/mindprince/gonvml # github.com/mistifyio/go-zfs v2.1.2-0.20190413222219-f784269be439+incompatible ## explicit github.com/mistifyio/go-zfs @@ -548,8 +544,8 @@ github.com/moby/spdystream/spdy # github.com/moby/sys/mountinfo v0.6.2 ## explicit; go 1.16 github.com/moby/sys/mountinfo -# github.com/moby/term v0.0.0-20220808134915-39b0c02b01ae -## explicit; go 1.13 +# github.com/moby/term v0.0.0-20221205130635-1aeaba878587 +## explicit; go 1.18 github.com/moby/term github.com/moby/term/windows # github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd @@ -641,7 +637,7 @@ github.com/opencontainers/runc/libcontainer/user github.com/opencontainers/runc/libcontainer/userns github.com/opencontainers/runc/libcontainer/utils github.com/opencontainers/runc/types -# github.com/opencontainers/runtime-spec v1.0.3-0.20210326190908-1c3f411f0417 +# github.com/opencontainers/runtime-spec v1.0.3-0.20220909204839-494a5a6aca78 ## explicit github.com/opencontainers/runtime-spec/specs-go # github.com/opencontainers/selinux v1.10.0