Re: ZFS leaking vnodes (sort of)

From: Joao Barros <joao.barros_at_gmail.com>
Date: Fri, 13 Jul 2007 00:10:48 +0100
On 7/9/07, Pawel Jakub Dawidek <pjd_at_freebsd.org> wrote:
> On Sat, Jul 07, 2007 at 02:26:17PM +0100, Doug Rabson wrote:
> > I've been testing ZFS recently and I noticed some performance issues
> > while doing large-scale port builds on a ZFS mounted /usr/ports tree.
> > Eventually I realised that virtually nothing ever ended up on the vnode
> > free list. This meant that when the system reached its maximum vnode
> > limit, it had to resort to reclaiming vnodes from the various
> > filesystem's active vnode lists (via vlrureclaim). Since those lists
> > are not sorted in LRU order, this led to pessimal cache performance
> > after the system got into that state.
> >
> > I looked a bit closer at the ZFS code and poked around with DDB and I
> > think the problem was caused by a couple of extraneous calls to vhold
> > when creating a new ZFS vnode. On FreeBSD, getnewvnode returns a vnode
> > which is already held (not on the free list) so there is no need to
> > call vhold again.
>
> Whoa! Nice catch... The patch works here - I did some pretty heavy
> tests, so please commit it ASAP.
>
> I also wonder if this can help with some of those 'kmem_map too small'
> panics. I was observing that ARC cannot reclaim memory and this may be
> because all vnodes and thus associated data are beeing held.
>
> To ZFS users having problems with performance and/or stability of ZFS:
> Can you test the patch and see if it helps?
>

I've recompiled my system after Doug committed this patch 3 days ago
and I can panic my machine as soon as I don't set kern.maxvnodes to
50000 while doing a ls -R after a recursive chown on some thousands of
files and dirs:

panic: kmem_malloc(16384): kmem_map too small: 326066176 total allocated

I noticed that before this patch the system panicked very easily and
soon in the chown process. Now it completes the chown on the thousands
of files and dirs I have in it and only panics after in the ls -R
process. It's an improvement, but something else is still there...

-- 
Joao Barros
Received on Thu Jul 12 2007 - 21:39:49 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:39:14 UTC