Messages in this thread |  | | From | Namhyung Kim <> | | Subject | Re: [PATCH 00/11] perf tool: Add PERF_SAMPLE_READ sample read support | | Date | Mon, 22 Oct 2012 17:51:01 +0900 |
| |
On Mon, 22 Oct 2012 10:09:31 +0200, Jiri Olsa wrote: > On Sun, Oct 21, 2012 at 06:38:49PM +0200, Ingo Molnar wrote: >> > # >> > # Samples: 86 of event 'anon group { cycles, cache-misses }' >> > # Event count (approx.): 34863674 >> > # >> > # Overhead Period Command Shared Object Symbol >> > # ................ ........................ ....... ................. ................................ >> >> Might make sense to consider this column enumeration: >> >> # >> # cycles >> # | cache-misses >> # | | >> > # v v >> > # >> > 16.56% 19.47% 5773450 475 ls [kernel.kallsyms] [k] native_sched_clock >> > 10.87% 0.74% 3789088 18 ls [kernel.kallsyms] [k] rtl8169_interrupt > > no problem in '--stdio' mode I guess.. not sure in '--tui/--gtk', Namhyung?
I thought a similar way but met a problem. We have other output columns than 'overhead' like 'period' in this example. What about others? Adding all event names for each column will just increase the column width so bothers user IMHO - especially for pmu format events.
So I ended up printing those events on the header:
# Samples: 86 of event 'anon group { cycles, cache-misses }'
Thanks, Namhyung
|  |