[Top] [All Lists]

Re: 2.4.20pre5aa2

To: Andrea Arcangeli <andrea@xxxxxxx>
Subject: Re: 2.4.20pre5aa2
From: Stephen Lord <lord@xxxxxxx>
Date: 14 Sep 2002 09:39:24 -0500
Cc: Samuel Flory <sflory@xxxxxxxxxxxx>, Austin Gonyou <austin@xxxxxxxxxxxxxxx>, Christian Guggenberger <christian.guggenberger@xxxxxxxxxxxxxxxxxxxxxxxx>, Linux Kernel Mailing List <linux-kernel@xxxxxxxxxxxxxxx>, linux-xfs@xxxxxxxxxxx
In-reply-to: <20020913211844.GP11605@xxxxxxxxxxxxxxxxx>
References: <20020911201602.A13655@xxxxxxxxxxxxxxxxxxxxxxxx> <1031768655.24629.23.camel@xxxxxxxxxxxxxxxxxxxxxxxx> <20020911184111.GY17868@xxxxxxxxxxxxxxxxx> <3D81235B.6080809@xxxxxxxxxxxx> <20020913002316.GG11605@xxxxxxxxxxxxxxxxx> <1031878070.1236.29.camel@snafu> <20020913005440.GJ11605@xxxxxxxxxxxxxxxxx> <3D8149F6.9060702@xxxxxxxxxxxx> <20020913125345.GO11605@xxxxxxxxxxxxxxxxx> <3D825422.8000007@xxxxxxxxxxxx> <20020913211844.GP11605@xxxxxxxxxxxxxxxxx>
Sender: linux-xfs-bounce@xxxxxxxxxxx
On Fri, 2002-09-13 at 16:18, Andrea Arcangeli wrote:

> So, returning to xfs, it is possible dbench really generates lots of
> simultaneous vmaps because of its concurrency, so I would suggest to add
> an atomic counter increased at every vmap/vmalloc and decreased at every
> vfree and to check it after every increase storing the max value in a
> sysctl, to see what's the max concurrency you reach with the vmaps. (you
> can also export the counter via the sysctl, to verify for no memleaks
> after unmounting xfs)
> Andrea

There are no vmaps during normal operation on xfs unless you are
setting extended attributes of more than 4K in size, or you
used some more obscure mkfs options. Only filesystem recovery will
use it otherwise. 


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