Hello.
Hesse, Christian wrote:
On Thursday 17 November 2005 18:22, Vladimir V. Saveliev wrote:
Hello
Hesse, Christian wrote:
Vladimir V. Saveliev wrote:
Please try whether the attached patch improves anything. It simplifies
fsync by avoid commiting of transactions which do not modify file being
fsync-ed.
The patch applied to 2.6.14-mm2 with warnings, but that can be ignored.
Hi everybody,
I'm suffering the same problem, sync and fsync are horribly slow. I've
written a small test program:
http://www.earthworm.de/tmp/reiser4-fsync.c
with 2.6.13:
sync() = 0 <0.000198>
fsync(3) = 0 <0.003353>
with 2.6.14 (with and without patch):
sync() = 0 <2.092873>
fsync(3) = 0 <0.132579>
I tried your test on a box with reiser4 root fs:
2.6.13:
strace -T -e sync,fsync ./eworm xx
fsync(3) = 0 <0.158808>
2.6.14-mm2 +
ftp://ftp.namesys.com/pub/reiser4-for-2.6/2.6.14-mm2/reiser4-for-2.6.14-mm2
-1.patch.gz
strace -T -e sync,fsync ./eworm xx
fsync(3) = 0 <0.005373>
Would you please try whether 2.6.14-mm2 with fresh reiser4 update fsyncs
better?
No change, still bad performance: up to 2 seconds in sync(), up to 0.2 seconds
in fsync().
Unfortunately we are not able to reproduce this slowdown. Would you
please provide more info?:
Is this 2.6.14-mm2 bad sync/fsync performance reproducible on fresh
created reiser4 too?
Are these values stable reproducible? If you run this test several time
-- do you have the same results?
Would you please send df -T output and 2.6.14-mm2 config file?
Did you try this test on ext2? If no -- would you please try it on ext2
for the same kernels and send us the results?
Thanks,
Lena
