[prev in list] [next in list] [prev in thread] [next in thread] 

List:       linux-kernel
Subject:    Re: [patch] voluntary-preempt-2.6.8.1-P4
From:       Lee Revell <rlrevell () joe-job ! com>
Date:       2004-08-19 10:29:02
Message-ID: 1092911341.1739.1.camel () krustophenia ! net
[Download RAW message or body]

On Thu, 2004-08-19 at 04:56, Ingo Molnar wrote:
> > > > Any comments on the unmap_vmas issue?
> > > 
> > > wli indicated he's working on the pagetable zapping critical section
> > > issue - wli?
> 
> actually - the unmap_vmas() issue might be different. Could you change
> the '32' in this part of mm/memory.c:
> 
> # define ZAP_BLOCK_SIZE \
>                 (voluntary_preemption ? (32 * PAGE_SIZE) : __ZAP_BLOCK_SIZE)
> 
> to 16? Does that roughly halve the ~180 usec latency?
> 

Yes, this takes care of it.  Now the dominant latency is the 142us
latency from the via-rhine driver, which is fixed by using the driver
from -mm (specifically it's fixed in bk-netdev.patch).

Lee

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
[prev in list] [next in list] [prev in thread] [next in thread]