On Thu, 4 Sep 2014, Gary Mohr wrote:
> snbep_unc_cbo0::UNC_C_TOR_INSERTS:MISS_ALL:cpu=0
> snbep_unc_cbo0::UNC_C_TOR_INSERTS:NID_MISS_ALL:nf=0x1:cpu=0
> ...
> I will try using these events with perf. It is not my favorite tool but
> if it will either show that these events should work together or help
> convince others that something in the kernel is not working correctly,
> it is worth the effort.
Sorry for the delay responding, it was the first week of classes and
things were a bit crazy around here.
If you did want to try these things under perf, the perf names for
the first two events you list are
uncore_cbox_0/event=0x35,umask=0xa/
uncore_cbox_0/event=0x35,umask=0x4a,filter_nid=0x1/
So you can try something like
perf stat -a -e
\{"uncore_cbox_0/event=0x35,umask=0xa/","uncore_cbox_0/event=0x35,umask=0x4a,filter_nid=0x1/"\}
/bin/ls
Although even with the "{}" grouping (which I thought would force GROUPing
of the events, it looks like perf doesn't. And the perf code is so
horrible I haven't forced myself to go looking why yet.
Vince
------------------------------------------------------------------------------
Want excitement?
Manually upgrade your production database.
When you want reliability, choose Perforce
Perforce version control. Predictably reliable.
http://pubads.g.doubleclick.net/gampad/clk?id=157508191&iu=/4140/ostg.clktrk
_______________________________________________
perfmon2-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/perfmon2-devel
