linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [Regression] Filesystem I/O is CPU-bound in rc7 and rc8
@ 2010-02-14  3:11 James Cloos
  2010-02-14 16:40 ` James Cloos
                   ` (3 more replies)
  0 siblings, 4 replies; 13+ messages in thread
From: James Cloos @ 2010-02-14  3:11 UTC (permalink / raw)
  To: linux-kernel; +Cc: linux-fsdevel, linux-ext4, linux-btrfs, jfs-discussion

Sometime between rc6 and rc7 all filesystem I/O started using 100% CPU,
usually on the order of 60% sys, 40% user.

I've tried this with each of ext4, jfs and btrfs filesystems.  All show
the same issue.

Using dd(1) to read from the block specials directly works as well and
as fast as it always has; only reading or writing to mounted filesystems
is affected.

Box is 32-bit x86, PentiumIII-M; drives are ide using libata.

If the btrfs fs is mounted, the slowdown is enought to trigger the
hung_task call trace (120s) on the btrfs-transac process.

But the regression is just as apparent when only jfs and ext4 are mounted.

The only filesystems I've found which avoid the regression are tmpfs and
devtmpfs.

I didn't have time to write up a report when I noticed this in rc7 but
had to boot back into rc6 for work.

Some of the commits since rc7 looked like they might have addressed this
regression, but it persists in rc8.

-JimC
-- 
James Cloos <cloos@jhcloos.com>         OpenPGP: 1024D/ED7DAEA6

^ permalink raw reply	[flat|nested] 13+ messages in thread

end of thread, other threads:[~2010-02-21  2:12 UTC | newest]

Thread overview: 13+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2010-02-14  3:11 [Regression] Filesystem I/O is CPU-bound in rc7 and rc8 James Cloos
2010-02-14 16:40 ` James Cloos
2010-02-14 23:12 ` Rafael J. Wysocki
2010-02-15 15:45 ` Chris Mason
2010-02-15 19:27   ` James Cloos
2010-02-17 20:04   ` James Cloos
2010-02-19 21:02     ` Dave Airlie
2010-02-19 21:37       ` James Cloos
2010-02-19 22:03         ` Dave Airlie
2010-02-20 15:59           ` James Cloos
2010-02-21  2:12           ` James Cloos
2010-02-19 21:22 ` Mike Fedyk
2010-02-19 21:44   ` James Cloos

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).