Re: [PATCH] perf tool: Fix ppid for synthesized fork events

[David Ahern <dsahern@gmail.com>]

On 3/25/15 6:22 AM, Joe Mario wrote:
> We ran "time perf mem record -a -e cpu/mem-loads,ldlat=50/pp -e
> cpu/mem-stores/pp sleep 10" on a system that was running SPECjbb2013 in
> the background.  There were about 10,000 java threads with about 500 to
> 800 in a runnable state at any given time.   We ran it on a 4 socket x86
> IVB server.
>
> We had two perf binaries.  One with your patch and one without it.
> Because the benchmark doesn't always have a constant load, we ran the
> above perf command in a loop alternating between the patched and
> unpatched version.   The elapsed wall clock times ("real" field from
> time) for the perf with your patch was typically >= 50% longer than the
> equivalent unpatched perf.

Sent a v2 with performance numbers on my end.

Adding -BN to the record removes processing of the events for build-ids. 
I also chose to use -e cpu-clock -F 1000 with -- usleep 1 to trim what 
perf-record is doing to *only* reading /proc files and generating COMM 
and FORK events.

David