[Top] [All Lists]

Re: another problem with latest code drops

To: Lachlan McIlroy <lachlan@xxxxxxx>, xfs-oss <xfs@xxxxxxxxxxx>
Subject: Re: another problem with latest code drops
From: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Date: Sun, 19 Oct 2008 05:10:21 -0400
In-reply-to: <20081016072019.GH25906@disturbed>
References: <48F6A19D.9080900@xxxxxxx> <20081016060247.GF25906@disturbed> <48F6EF7F.4070008@xxxxxxx> <20081016072019.GH25906@disturbed>
User-agent: Mutt/1.5.18 (2008-05-17)
On Thu, Oct 16, 2008 at 06:20:19PM +1100, Dave Chinner wrote:
> I just ran up the same load in a UML session. I'd say it's this
> slab:
>   2482   2481  99%    0.23K    146       17       584K xfs_btree_cur
> which is showing a leak. It is slowly growing on my system
> and dropping the caches doesn't reduce it's size. At least it's
> a place to start looking - somewhere in the new btree code we
> seem to be leaking a btree cursor....

I've been running

for i in $(seq 1 8); do
        fsstress -p 64 -n 10000000 -d /mnt/data/fsstress.$i &

for about 20 hours now, and I'm only up to a few hundred xfs_btree_cur
entires, not changing much at all over time.  This is xfs-2.6 on a 4-way
PPC machine.

<Prev in Thread] Current Thread [Next in Thread>