Messages in this thread | | | Date | Sat, 15 Jun 2002 14:23:49 -0700 | From | Andrew Morton <> | Subject | Re: [PATCH] 2.5.21 IDE 91 |
| |
rwhron@earthlink.net wrote: > > > Does this patch get the throughput back? > > That makes all the difference to dbench. Throughput > for dbench 128 up over 40% compared to vanilla 2.5.21.
ho hum. Now we need to work out why a larger request queue whacks dbench, whether it penalises workloads which we actually care about and if so, what the appropriate size really should be. If indeed that algorithms are optimal. urgh.
Thanks again, Randy.
- - 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/
| |