On 26-Feb-2000 Andi Kleen wrote:
> dimitris@cthulhu.engr.sgi.com (Dimitris Michailidis) writes:
>>
>> All tests I've tried (lat_ctx, dbench, parallel make, etc.) show
>> improvement
>> with this patch. However, I noticed that context switch times have gone
>> down
>> the toilet in recent kernel versions. On my machine lat_ctx -s 0 2 used
>> to be
>> a bit over 2. With 2.3.47 it has sky rocketed to 4.25 and with the patch
>> it
>> reduces to 3.95. All I know at this point is that it happened sometime
>> after
>> 2.3.40.
>
> Is this on SMP or UP ? 2.3.43 introduced the softnet changes, which among
> others include a completely new implementation of bottom halves.
This was MP (4 Xeon @500MHz). As another data point, on the same machine,
dbench 32 has a throughput of about 42MB/s with 2.3.40. With stock 2.3.47
it's just under 7MB/s and the CPUs have a much lower utilization (27% out of
the 4 CPUs versus 100+% with 2.3.40).
-- Dimitris Michailidis dimitris@engr.sgi.com- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Tue Feb 29 2000 - 21:00:16 EST