https://bugzilla.kernel.org/show_bug.cgi?id=107301 --- Comment #2 from Mehdi Abaakouk <sileht@xxxxxxxxxx> --- Yes ceph heavy uses xattr I don't have a 'step by step to reproduce' list. But I have the issue ~4-5 times per day on a ceph cluster since the first incident. On November 5, 2015 6:02:57 PM GMT+01:00, bugzilla-daemon@xxxxxxxxxxxxxxxxxxx wrote: >https://bugzilla.kernel.org/show_bug.cgi?id=107301 > >Jan Kara <jack@xxxxxxx> changed: > > What |Removed |Added >---------------------------------------------------------------------------- > Status|NEW |NEEDINFO > >--- Comment #1 from Jan Kara <jack@xxxxxxx> --- >Hum, from the stack traces in the log it seems mb_cache_entry_alloc() >is racing >with other operations on the LRU and restarting all the time. Another >possibility is that there are lots of entries in the LRU and it takes a >long >time to scan (if I remember right ceph is a heavy user of xattrs). > >The first problem would be easily fixed by adding cond_resched() at >appropriate >place, the second problem would require more intrusive changes in how >LRU is >handled. > >Can you reproduce the issue? > >-- >You are receiving this mail because: >You reported the bug. -- You are receiving this mail because: You are watching the assignee of the bug. -- To unsubscribe from this list: send the line "unsubscribe linux-ext4" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
