Date: Fri, 22 Jan 2010 07:22:11 -0600 From: "Doug Poland" <doug@polands.org> To: "Artem Belevich" <fbsdlist@src.cx> Cc: freebsd-fs@freebsd.org Subject: Re: Repeatable ZFS "kmem map too small" panic on 8.0-STABLE Message-ID: <a8b9c9e35a14c4ada1c8f2602c91db63.squirrel@email.polands.org> In-Reply-To: <ed91d4a81001212209o3cf5955fw1eb0dd78703ad905@mail.gmail.com> References: <4B58976E.1020402@polands.org> <4B58A069.8000802@egr.msu.edu> <4B58BD2D.30803@rcn.com> <ed91d4a81001211421r4f7ba7a8n1c92bfc413e5feed@mail.gmail.com> <4B58D4D3.80009@egr.msu.edu> <20100122042843.GA8858@polands.org> <ed91d4a81001212209o3cf5955fw1eb0dd78703ad905@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, January 22, 2010 00:09, Artem Belevich wrote: > On Thu, Jan 21, 2010 at 8:28 PM, Doug Poland <doug@polands.org> > wrote: >> Interesting discussion :) I added vm.kmem_size="20G" to >> /boot/loader.conf per your instructions. This time, it didn't >> panic at the same point in the test, however, it appears the >> filesystem is "hanging". >> >> On the fdisk test, I hit <CTRL> T and get: >> cmd: fsdisk 37066 [zio->io_cv)] 245.62r 0.12u 25.10s 0 >> >> My various metrics are still running, but anything that needs the >> filesystem appears "stuck". >> >> The memory usage of the item "solaris" (vmstat -m | grep solaris) >> spiked at 3334781952 (3180.30 MiB). >> >> # zpool iostat 2, a <CTRL> T shows: >> load: 0.00 cmd: zpool 934 [tx->tx_quiesce_done_cv)] 2052.45r 0.06 u 0.39s 0% 0k >> >> # vmstat -v | grep solaris to disk every second and it's hung at: >> load: 0.00 cmd: sh 38551 [zfs] 909.85r 0.00u 0.00s 0% 16k >> >> Any suggestions! >> > Next step would be to set vfs.zfs.arc_max to a value that's somewhat > below your physical memory size. Let's say - 1G or so. On my box with > 8GB of RAM I set these values: > > vfs.zfs.arc_max="6500M" > vfs.zfs.arc_min="4G" > OK, I'll give that a shot... > You didn't mention how recent is your kernel. There were quite a few > bugfixes committed to -8. Make sure your kernel is r201987 or newer. > Right now I'm running a stock 8.0-RELEASE. I had tried it on -STABLE a couple of days ago with similar results. I'll get the box back up to -STABLE again. Do you advise to upgrade the pool to v14 for this testing? -- Regards, Doug
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?a8b9c9e35a14c4ada1c8f2602c91db63.squirrel>