[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]

Re: Success with new futex code from 2.6.0-test5



On Wed, 10 Sep 2003, Bill Soudan wrote:

> I made the .config changes prior to appling Jamie's patch -- they didn't
> seem to have any major effect.  Though I didn't specifically measure the
> difference, I made sure the symbols that caught your attention were no
> longer in the oprofile results.  I still had the same issue, however,
> until I applied Jamie's patch.

ok.

> If you'd like measurements for some reason, I'd be happy to get them.

no need - i only wanted to know for sure that the 'freeze' things was
indeed caused by suboptimal locking in the futex code. It was then
probably just some 4-CPU race for the same lock, causing some real bad
cacheline movements between CPUs.

	Ingo




[Date Prev][Date Next]   [Thread Prev][Thread Next]   [Thread Index] [Date Index] [Author Index]