mir/criu
2
0
Fork 0
mirror of https://github.com/checkpoint-restore/criu synced 2025-08-30 22:05:36 +00:00
Code Issues Releases Wiki Activity

docker-test: handle race condition error

Browse Source 
There is a race condition in docker/containerd that causes docker to
occasionally fail when starting a container from a checkpoint immediately
after the checkpoint has been created.

This problem is unrelated to criu and has been reported in
https://github.com/moby/moby/issues/42900

Signed-off-by: Radostin Stoyanov <rstoyanov@fedoraproject.org>
This commit is contained in:
Radostin Stoyanov
2022-08-11 09:51:34 +01:00
committed by Andrei Vagin
parent 49319cd579
commit 2642b657da
1 changed files with 25 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
scripts/ci/docker-test.sh
View File

@@ -75,17 +75,37 @@ checkpoint_container () {
docker wait cr
}
restore_container () {
CHECKPOINT_NAME=$1
docker start --checkpoint "$CHECKPOINT_NAME" cr 2>&1 | tee log || {
print_logs () {
cat "$(grep log 'log file:' | sed 's/log file:\s*//')" || true
docker logs cr || true
cat $CRIU_LOG || true
dmesg
docker ps
exit 1
}
}
declare -i max_restore_container_tries=3
current_iteration=
restore_container () {
CHECKPOINT_NAME=$1
docker start --checkpoint "$CHECKPOINT_NAME" cr 2>&1 | tee log || {
# FIXME: There is a race condition in docker/containerd that causes
# docker to occasionally fail when starting a container from a
# checkpoint immediately after the checkpoint has been created.
# https://github.com/moby/moby/issues/42900
if [ "$current_iteration" -gt "$max_restore_container_tries" ]; then
print_logs
fi
grep -Eq '^Error response from daemon: failed to upload checkpoint to containerd: commit failed: content sha256:.*: already exists$' log && {
((current_iteration+=1))
echo "Retry container restore: $current_iteration"
sleep 1;
restore_container "$CHECKPOINT_NAME"
} ||
print_logs
} && current_iteration=0
}
# Scenario: Create multiple containers and checkpoint and restore them once