xfs
[Top] [All Lists]

Re: [PATCH] Tweak tracing allocation sizes

To: Andi Kleen <andi@xxxxxxxxxxxxxx>
Subject: Re: [PATCH] Tweak tracing allocation sizes
From: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Date: Tue, 2 Sep 2008 17:55:16 -0400
Cc: lachlan@xxxxxxx, xfs-dev <xfs-dev@xxxxxxx>, xfs-oss <xfs@xxxxxxxxxxx>
In-reply-to: <87fxojvy5v.fsf@xxxxxxxxxxxxxxxxx>
References: <48BCD3BE.5040107@xxxxxxx> <20080902055604.GD15962@disturbed> <48BCD93E.9040407@xxxxxxx> <87fxojvy5v.fsf@xxxxxxxxxxxxxxxxx>
User-agent: Mutt/1.5.18 (2008-05-17)
On Tue, Sep 02, 2008 at 08:50:52AM +0200, Andi Kleen wrote:
> > alternative - maybe a very large global trace buffer that is allocated at 
> > mount
> > time and shared by all inodes?
> 
> You could use vmalloc(). While that is also not fast it will at least
> not stall.

In fact kmem_alloc first tries vmalloc, and then falls back to slab
when it fails.  See fs/xfs/linux-2.6/kmem.c:kmem_alloc().

Yes, it's all a big mess..

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