On 12/20/10 17:11, Mark Kettenis wrote:
quoted text
>> Date: Mon, 20 Dec 2010 16:12:24 +0100
>> From: Claudio Jeker<cjeker@diehard.n-r-g.com>
>>
>> With the change in rev. 1.99 of subr_pool() changing the limit
>> will no longer set the high watermark as well.
>> This causes i386 to stop forwading packets on very busy systems because
>> the pool thread is not fast enough to replenish the pool. So reintroduce
>> the pool_sethiwat() in this particular case as a workaround.
>
> Sorry, claudio, but I think you need to fix the driver(s) that have
> this issue.  Even with adjusting the pool limits you may still end up
> with an empty ring, and the driver should be able to restart itself if
> mbufs come available again.  A potential way to fix this is to start a
> timeout if you end up with an empty ring because of mbug allocation
> failures, and attempt to refill the ring when the timout fires.
>

I didn't look at the code, but this patch seems to fix PR 6524.