14 Mar
2019
14 Mar
'19
13:32
http://bugzilla.suse.com/show_bug.cgi?id=1129214
http://bugzilla.suse.com/show_bug.cgi?id=1129214#c5
--- Comment #5 from Anthony Iliopoulos
It looks like the page allocation stall from xfs_inode_alloc(). Its order is 0, so a really critical failure.
Adding both FS and MM people to Cc, who should have better clue.
Looks like rsync is exerting a lot of memory pressure, and potentially writeback at the same time cannot keep up (it seems that the md layer has pending data to be flushed). Perhaps also a stacktrace of the blocked tasks (echo w > /proc/sysrq-trigger) would give a bit more insight next time this occurs. -- You are receiving this mail because: You are on the CC list for the bug.