On 8/7/13 3:27 PM, Arnaldo Carvalho de Melo wrote:
Em Mon, Aug 05, 2013 at 09:41:36PM -0400, David Ahern escreveu:
This is useful to spot high latency blips. It is normal for HLT
reasons to have long exit times, so strip those from the threshold
check.
So 'perf trace' has a similar option:
[acme@zoo linux]$ perf trace --help
<SNIP>
--duration <float>
show only events with duration > N.M ms
<SNIP>
While you used:
+ OPT_U64('T', "threshold", &kvm->threshold,
+ "show events other than HALT that take longer than threshold
usecs"),
I prefer 'duration', and haven't assigned a single letter to it, they
are scarce and we have shell long option completion, what do you think?
The term was chosen, for 'perf trace' on the original patchset:
http://lwn.net/Articles/415728/
- Arnaldo
No preference really. I need to send out an update to the man page. I
can update this patch as well and re-send.
David
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
