From 4e87973a9b3bb406314ffe26b2a78ea2496f2b89 Mon Sep 17 00:00:00 2001 From: Yu-Ju Hong Date: Tue, 10 Jan 2017 13:07:21 -0800 Subject: [PATCH] Bump container-linux and gci timeout for docker health check The command `docker ps` can take longer time to respond under heavy load or when encountering some known issues. In these cases, the containers are running fine, so aggressive health check could cause serious disruption. Bump the timeout to 60s to be consistent with the debian-based containerVM. --- cluster/gce/container-linux/health-monitor.sh | 2 +- cluster/gce/gci/health-monitor.sh | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/cluster/gce/container-linux/health-monitor.sh b/cluster/gce/container-linux/health-monitor.sh index 4d50e4ee8dd..c26ce288c38 100644 --- a/cluster/gce/container-linux/health-monitor.sh +++ b/cluster/gce/container-linux/health-monitor.sh @@ -26,7 +26,7 @@ set -o pipefail # automatically restart the process. function docker_monitoring { while [ 1 ]; do - if ! timeout 10 docker ps > /dev/null; then + if ! timeout 60 docker ps > /dev/null; then echo "Docker daemon failed!" pkill docker # Wait for a while, as we don't want to kill it again before it is really up. diff --git a/cluster/gce/gci/health-monitor.sh b/cluster/gce/gci/health-monitor.sh index 4d50e4ee8dd..c26ce288c38 100644 --- a/cluster/gce/gci/health-monitor.sh +++ b/cluster/gce/gci/health-monitor.sh @@ -26,7 +26,7 @@ set -o pipefail # automatically restart the process. function docker_monitoring { while [ 1 ]; do - if ! timeout 10 docker ps > /dev/null; then + if ! timeout 60 docker ps > /dev/null; then echo "Docker daemon failed!" pkill docker # Wait for a while, as we don't want to kill it again before it is really up.