On 04/02/2013 04:35 PM, Alex Shi wrote: > On 04/02/2013 03:23 PM, Michael Wang wrote: [snip] >> >> The reason may caused by wake_affine()'s higher overhead, and pgbench is >> really sensitive to this stuff... > > Thanks for testing. Could you like to remove the last patch and test it > again? I want to know if the last patch has effect on pgbench.
Amazing, without the last one, pgbench show very good improvement, higher than 10ms throttle, lower than 100ms throttle, I need confirm this with a night-through testing. I will look into those patches in detail later, I think it addressed part of the wake_affine() issue (make the decision more accurately), that's nice ;-) Regards, Michael Wang > -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/