Messages in this thread | | | Date | Thu, 4 Sep 2008 13:09:01 +0200 | From | Ingo Molnar <> | Subject | Re: oltp ~10% regression with 2.6.27-rc5 on stoakley machine |
| |
* Lin Ming <ming.m.lin@intel.com> wrote:
> I observed schedstats of sysbench, there's more > "nr_failed_migrations_hot" > > 2.6.27-rc4: se.nr_failed_migrations_hot 11 > 2.6.27-rc5: se.nr_failed_migrations_hot 95 > > task migration failed because of task_hot, the system is un-balanced?
would be nice to get a representative (==steady state) scheduler trace from the critical portions of that workload. See:
http://people.redhat.com/mingo/sched-devel.git/readme-tracer.txt
Ingo
| |