Re: [PATCH] Add support for IBM Power event codes longer than sizeof int

Henry May/Rochester/IBM@IBMUS wrote on 11/21/2014 11:02:11 AM:

> From: Henry May/Rochester/IBM@IBMUS
> To: [email protected]
> Cc: William Cohen <[email protected]>, oprofile-list <oprofile-
> [email protected]>
> Date: 11/21/2014 11:03 AM
> Subject: Re: [PATCH] Add support for IBM Power event codes longer 
> than sizeof int
> 
> 
> 
> 
> 
> 
> [email protected] wrote on 11/21/2014 09:00:00 AM:
> 
> > From: [email protected] 
> > To: Henry May/Rochester/IBM@IBMUS, [email protected] 
> > Cc: oprofile-list <[email protected]>, William 
> > Cohen <[email protected]> 
> > Date: 11/21/2014 09:00 AM 
> > Subject: Re: [PATCH] Add support for IBM Power event codes longer 
> > than sizeof int 
> > 
> > On 11/20/2014 06:37 PM, Henry May wrote:
> > > 
> > > 
> > > Henry May
> > > IBM InfoSphere Streams Performance
> > > [email protected]
> > > 720-342-8873
> > > Tie: 963-8873
> > > 
> > > 
> > > [email protected] wrote on 11/19/2014 04:51:24 PM:
> > > 
> > >> From: [email protected]
> > >> To: oprofile-list <[email protected]>, Henry May/
> > >> Rochester/IBM@IBMUS, William Cohen <[email protected]>
> > >> Date: 11/19/2014 04:51 PM
> > >> Subject: [PATCH] Add support for IBM Power event codes longer 
> > than sizeof int
> > >>
> > >> Hi, Henry,
> > >> The patch below addresses the issue you raised yesterday on the 
oprofile
> > >> list (subject "PM_L1MISS_LAT_EXC_xxx events").  At first, I looked 
into
> > >> what it would take to add general support for long event codes,but 
I soon
> > >> discovered that it would entail a change to the sample file format, 
and
> > >> I was loathe to do that just for eight events from IBM POWER8. I 
verified
> > >> that there are no other events for any architecture other than 
> these eight
> > >> that have event codes longer than an integer. So I implemented a 
bit of a
> > >> hack, using the concept of a unit mask as an event qualifier. It's 
an OK
> > >> fit, conceptually, it's just a bit hacky because no other ppc64 
events
> > >> use unit masks.  But the fix was fairly small and simple, so I 
think it's
> > >> fine.
> > >>
> > >> Please give it a test and let me know how it works for you.
> > > I tested the patch and it only works with PM_L1MISS_LAT_EXC_256. 
> > Does not work with 32, 1024, or 2048.  Currently trying another 
> > iteration of the patch.
> > Henry,
> > My apologies. The testing I did for this patch used a full event 
> > specification -- e.g, PM_L1MISS_LAT_EXC_256:0x0:1:1 -- and the patch
> > worked for all events. But I get the same results you do if I use 
> > ocount or operf with just the event name. I've found the bug in the 
> > patch and as you alluded to above, you're already testing it. So 
> > when you have your test results, please post here.
> ocount accepts all counter specifications now, but the 
> PM_L1MISS_EXC_LAT counts look bogus: 
> 
>   latency | PM_L1MISS_EXC_LAT  | PM_RC_LIFETIME_EXC 
>        32 |        25,000,000  |          6,000,000 
>       256 |        30,000,000  |            660,000 
>      1024 |        64,000,000  |             35,000 
>      2048 |        10,000,000  |              1,000 
> 
> I would have expected the pattern exhibited by RC_LIFETIME_EXC, but 
> it could be that I am misinterpreting the meaning of the counters. 
> Are the L1MISS_EXC_LAT counters counting the number of events that 
> exceed the threshold, or the number of cycles accumulated by the 
> events that exceed the threshold? 
Maynard suggested I compare the results of 
perf stat -e r67200201E6,r67200101E8,r67200301EA,r67200401EC -a sleep 10
and 
ocount -s -e 
PM_L1MISS_LAT_EXC_32,PM_L1MISS_LAT_EXC_256,PM_L1MISS_LAT_EXC_1024,PM_L1MISS_LAT_EXC_2048 
-i 10000:1
There are some differences between what I am doing and this simple test 
(notably, I specified numerous counters and I'm scaling by the % time 
counted), but I think it demonstrates that ocount is doing the right 
thing:
[root@pftul3 ~]# perf stat -e 
r67200201E6,r67200101E8,r67200301EA,r67200401EC -a sleep 10

 Performance counter stats for 'sleep 10':

        11,310,770 r67200201E6      [100.00%]
        10,444,981 r67200101E8      [100.00%]
         4,184,751 r67200301EA      [100.00%]
         1,041,813 r67200401EC  

      10.001551448 seconds time elapsed

[root@pftul3 ~]# ocount -s -e 
PM_L1MISS_LAT_EXC_32,PM_L1MISS_LAT_EXC_256,PM_L1MISS_LAT_EXC_1024,PM_L1MISS_LAT_EXC_2048 
-i 10000:1
ocount: Press Ctl-c or 'kill -SIGINT 53289' to stop counting

Current time (seconds since epoch): 1416599245
Event counts (actual) for the whole system:
        Event                          Count                    % time 
counted
        PM_L1MISS_LAT_EXC_1024         4,276,539                100.00
        PM_L1MISS_LAT_EXC_2048         1,054,995                100.00
        PM_L1MISS_LAT_EXC_256          10,348,682               100.00
        PM_L1MISS_LAT_EXC_32           11,168,651               100.00
Patch looks good.
Henry
> > 
> > -Maynard
> > >>
> > >> Thanks!
> > >> -Maynard
> > >>
> > >> 
------------------------------------------------------------------------
> > >
> > [snip]
> > 
> 
------------------------------------------------------------------------------
> Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server
> from Actuate! Instantly Supercharge Your Business Reports and Dashboards
> with Interactivity, Sharing, Native Excel Exports, App Integration & 
more
> Get technology previously reserved for billion-dollar corporations, FREE
> 
http://pubads.g.doubleclick.net/gampad/clk?id=157005751&iu=/4140/ostg.clktrk

> _______________________________________________
> oprofile-list mailing list
> [email protected]
> https://lists.sourceforge.net/lists/listinfo/oprofile-list

------------------------------------------------------------------------------
Download BIRT iHub F-Type - The Free Enterprise-Grade BIRT Server
from Actuate! Instantly Supercharge Your Business Reports and Dashboards
with Interactivity, Sharing, Native Excel Exports, App Integration & more
Get technology previously reserved for billion-dollar corporations, FREE
http://pubads.g.doubleclick.net/gampad/clk?id=157005751&iu=/4140/ostg.clktrk

_______________________________________________
oprofile-list mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/oprofile-list