Bug 73051
Summary: | Hung Tasks related to ext4 IO | ||
---|---|---|---|
Product: | File System | Reporter: | Nik Martin (nik.martin) |
Component: | ext4 | Assignee: | fs_ext4 (fs_ext4) |
Status: | NEEDINFO --- | ||
Severity: | high | CC: | jack |
Priority: | P1 | ||
Hardware: | x86-64 | ||
OS: | Linux | ||
Kernel Version: | 3.13.6 | Subsystem: | |
Regression: | No | Bisected commit-id: | |
Attachments: | attachment-19080-0.html |
Description
Nik Martin
2014-03-27 20:26:48 UTC
Any update on this? Can I provide more information? This has become a persistent issue, and at some point I am going to lose data. Looking into the traces, this doesn't seem to be ext4 problem at the first sight. We are waiting in filemap_fdatawait_range() for IO on the page to finish. It seems that never happens which would be a bug somewhere in the block layer, device mapper, etc. Seeing that you mention bcache, would it be possible to try whether the hangs happen without it? Created attachment 131671 [details] attachment-19080-0.html I can try that, and see if I can replicate the issue. I'm not exactly sure how to disable bcache, it's not the most well documented system. On Apr 7, 2014 8:25 AM, <bugzilla-daemon@bugzilla.kernel.org> wrote: > https://bugzilla.kernel.org/show_bug.cgi?id=73051 > > Jan Kara <jack@suse.cz> changed: > > What |Removed |Added > > ---------------------------------------------------------------------------- > Status|NEW |NEEDINFO > CC| |jack@suse.cz > > --- Comment #2 from Jan Kara <jack@suse.cz> --- > Looking into the traces, this doesn't seem to be ext4 problem at the first > sight. We are waiting in filemap_fdatawait_range() for IO on the page to > finish. It seems that never happens which would be a bug somewhere in the > block > layer, device mapper, etc. Seeing that you mention bcache, would it be > possible > to try whether the hangs happen without it? > > -- > You are receiving this mail because: > You reported the bug. > |