On Mon, Nov 11, 2002 at 08:04:00AM +0100, Jens Axboe wrote:
> I've already done exactly this (mempool per queue, global slab). I'll
> share it later today.
> But yes, lets see some numbers on huge queues first. Otherwise we can
> just fall back to using a decent 128/512 split for reads/writes, or
> whatever is a good split.
This just got real hard real fast and we'll be waiting at least a week
for "real" results from me.
Sorry, I can't fix vendor drivers on-demand. Recent SCSI changes broke
the out-of-tree crap and I don't have the driver and/or in-kernel SCSI/FC
expertise to deal with it.
Bill
-
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/
This archive was generated by hypermail 2b29 : Fri Nov 15 2002 - 22:00:21 EST