Increase size of ARP cache

We already had this increased above the defaults, but even larger values
seem to be recommended.

See https://blog.openai.com/scaling-kubernetes-to-2500-nodes/

"It’s common to tune this setting in HPC clusters, and is particularly
relevant in Kubernetes clusters since every pod has its own IP address
which consumes space in the ARP cache."

Signed-off-by: Justin Cormack <justin.cormack@docker.com>
This commit is contained in:
Justin Cormack 2018-01-19 11:02:17 +00:00
parent 059bdfbdad
commit d4b23a76de

View File

@ -7,9 +7,9 @@ net.ipv4.ping_group_range=999 59999
vm.max_map_count = 262144
vm.overcommit_memory = 1
net.core.somaxconn = 1024
net.ipv4.neigh.default.gc_thresh1 = 30000
net.ipv4.neigh.default.gc_thresh2 = 32000
net.ipv4.neigh.default.gc_thresh3 = 32768
net.ipv4.neigh.default.gc_thresh1 = 80000
net.ipv4.neigh.default.gc_thresh2 = 90000
net.ipv4.neigh.default.gc_thresh3 = 100000
fs.aio-max-nr = 1048576
fs.inotify.max_user_watches = 524288
fs.file-max = 524288