Hi,
On 2023-07-03 11:59:38 +0900, Masahiko Sawada wrote:
> On Mon, Jul 3, 2023 at 11:55 AM Masahiko Sawada <sawada.mshk@gmail.com> wrote:
> >
> > After further investigation, the performance degradation comes from
> > calling posix_fallocate() (called via FileFallocate()) and pwritev()
> > (called via FileZero) alternatively depending on how many blocks we
> > extend by. And it happens only on the xfs filesystem.
>
> FYI, the attached simple C program proves the fact that calling
> alternatively posix_fallocate() and pwrite() causes slow performance
> on posix_fallocate():
>
> $ gcc -o test test.c
> $ time ./test test.1 1
> total 200000
> fallocate 200000
> filewrite 0
>
> real 0m1.305s
> user 0m0.050s
> sys 0m1.255s
>
> $ time ./test test.2 2
> total 200000
> fallocate 100000
> filewrite 100000
>
> real 1m29.222s
> user 0m0.139s
> sys 0m3.139s
On an xfs filesystem, with a very recent kernel:
time /tmp/msw_test /srv/dev/fio/msw 0
total 200000
fallocate 0
filewrite 200000
real 0m0.456s
user 0m0.017s
sys 0m0.439s
time /tmp/msw_test /srv/dev/fio/msw 1
total 200000
fallocate 200000
filewrite 0
real 0m0.141s
user 0m0.010s
sys 0m0.131s
time /tmp/msw_test /srv/dev/fio/msw 2
total 200000
fallocate 100000
filewrite 100000
real 0m0.297s
user 0m0.017s
sys 0m0.280s
So I don't think I can reproduce your problem on that system...
I also tried adding a fdatasync() into the loop, but that just made things
uniformly slow.
I guess I'll try to dig up whether this is a problem in older upstream
kernels, or whether it's been introduced in RHEL.
Greetings,
Andres Freund