Messages in this thread | | | Subject | Re: tbench regression with 2.6.33-rc1 | From | Lin Ming <> | Date | Tue, 29 Dec 2009 13:19:19 +0800 |
| |
On Tue, 2009-12-29 at 13:24 +0800, Mike Galbraith wrote: > On Tue, 2009-12-29 at 10:09 +0800, Lin Ming wrote: > > And also no regression if I run tbench with RT scheduler on tulsa > > machine, as below command, > > > > schedtool -R -p 20 -e tbench_srv & > > schedtool -R -p 20 -e tbench 32 > > Hm, odd. I'd expect tbench to suffer when run SCHED_RR, and here it > does, achieving roughly 85% of lowest SCHED_OTHER throughput.
Here is some misunderstanding. I compared SCHED_RR tbench with 2.6.32 and 2.6.33-rc1 and no regression found.
For the same kernel, SCHED_RR tbench only achieved ~40% of SCHED_OTHER throughput.
Lin Ming
| |