slowdown of zfs (tx->tx)

Wed Jan 16 07:38:03 UTC 2013

* Artem Belevich <art at freebsd.org> [2013-01-15 16:16 -0800]:
> On Tue, Jan 15, 2013 at 2:45 PM, Nicolas Rachinsky
> <fbsd-mas-0 at ml.turing-complete.org> wrote:
> >  147     0 100098 kernel           zio_write_issue_ mi_switch+0x176 sleepq_wait+0x42 _cv_wait+0x129 space_map_load_wait+0x20 metaslab_activate+0x73 metaslab_alloc+0x7b2 zio_dva_allocate+0x9a zio_execute+0xc3 taskqueue_run_locked+0x85 taskqueue_thread_loop+0x4e fork_exit+0x11f fork_trampoline+0xe
> 
> It appears that lots of threads are stuck in
> metaslab_activate->space_map_load_wait path. This sounds like CR#
> 6876962 in Solaris: "degraded write performance with threads held up
> by space_map_load_wait(). This bug is fixed in patch 147440-05, -06 or
> -07, which is current and contains the fix." Alas, I could not find
> specifics on how the issue got fixed and whether the same fix is
> present in illumos and FreeBSD.
> 
> You may want to update your system to very recent FreeBSD as quite a
> few fixes were recently imported from illumos. Hopefully it will deal
> with the issue. I'm out of ideas otherwise. Sorry.

Do you mean -CURRENT or -STABLE with very recent? Or just 9.1?

Thank you for your efforts!

Nicolas
-- 
http://www.rachinsky.de/nicolas