Description of problem: ======================= "-bash: fork: Cannot allocate memory error" is seen constantly on the nodes on execution of any command. This issue is seen with the latest glusterfs 3.7.0beta2 build. Not sure if this is a glusterfs problem as this issue was not seen on the earlier build on the same hardware. I have collected the sosreports after rebooting from the console as no commands can be executed through the CLI until a reboot. Version-Release number of selected component (if applicable): ============================================================= glusterfs 3.7.0beta2 How reproducible: ================= Intermittent. Steps to Reproduce: =================== 1.Created some EC and tiered volumes with USS, quota and bitrot enabled. 2.Scheduled some snapshots Actual results: ============== After a while we get "-bash: fork: Cannot allocate memory" on execution of any command. Expected results: Additional info:
I also faced this issue immediately after installing glusterfs 3.7.0beta2 build.
I have seen this behavior with bitrot and more than 3 bricks on the same node. Maybe that's something we can avoid for now as it is a known problem with bitrot. Thanks.
This is related to bz #1207134. Patch is under review.
Just to be fully sure: did the problematic node have more than three (3) bricks (for a given volume).
Yes, the nodes where I faced the issue had more than 3 bricks per volume
This bug is getting closed because GlusteFS-3.7 has reached its end-of-life. Note: This bug is being closed using a script. No verification has been performed to check if it still exists on newer releases of GlusterFS. If this bug still exists in newer GlusterFS releases, please reopen this bug against the newer release.