Re: [perfmon2] Intel Nehalem : OFFCORE_RESPONSE_0 event Implementation

2010-07-15 Thread stephane eranian
Hi, On Wed, Jul 14, 2010 at 1:16 PM, Zoltán Majó wrote: > Hi Stephane, > > >> That is why I have the event commented out. You need to find a way >> to encode the event and then have the kernel decode and use the >> extra MSR. That is not there yet. I had planned to fix this but got >> caught up w

Re: [perfmon2] mix sampling and counting failed

2010-07-15 Thread stephane eranian
On Thu, Jul 15, 2010 at 9:44 AM, lulu he wrote: > Hi stephane, > I think I don't explain my problem clear. > According to the pfmon usersguide, if I do as you say like this, > pfmon --verbose --smpl-show-top=20 >  --no-cmd-output -eINSTRUCTIONS_RETIRED,LAST_LEVEL_CACHE_MISSES >  --long-smpl-period

Re: [perfmon2] [PATCH 1/3] Add CONFIG_NO_PYTHON to disable building python directory

2010-07-15 Thread Corey Ashford
On 07/14/2010 08:29 PM, stephane eranian wrote: > Patch applied. > > I simply renamed CONFIG_NO_PYTHON > to CONFIG_PFMLIB_NOPYTHONN for consistence reason. Thanks Stephane! - Corey -- This SF.net email is sponsored by Sp

Re: [perfmon2] mix sampling and counting failed

2010-07-15 Thread lulu he
Hi stephane, I think I don't explain my problem clear. According to the pfmon usersguide, if I do as you say like this, pfmon --verbose --smpl-show-top=20 --no-cmd-output -eINSTRUCTIONS_RETIRED,LAST_LEVEL_CACHE_MISSES --long-smpl-periods=1,4000 --follow-all -- samples is recorder every X