From: David Ahern <dsahern@gmail.com>
To: Ingo Molnar <mingo@kernel.org>
Cc: linux-kernel@vger.kernel.org, acme@ghostprotocols.net,
fweisbec@gmail.com, peterz@infradead.org, jolsa@redhat.com,
namhyung@kernel.org, xiaoguangrong@linux.vnet.ibm.com
Subject: Re: [PATCH 10/13] perf kvm: add live mode
Date: Thu, 09 May 2013 07:54:26 -0600 [thread overview]
Message-ID: <518BAA92.2030101@gmail.com> (raw)
In-Reply-To: <20130509085137.GA8813@gmail.com>
On 5/9/13 2:51 AM, Ingo Molnar wrote:
> 1)
>
> Regarding the basic syntax - is the 'perf stat kvm' command already used
> up? If not then it might make sense to alias 'perf kvm stat live' to 'perf
> kvm stat', making it really easy to use:
>
> perf kvm stat
> perf kvm stat -p <pid>
>
> etc. I'd expect most 'perf kvm stat' users to utilize this syntax - so it
> makes sense to make 'live' the default and main command.
The default is for 'perf kvm stat' to call cmd_stat (i.e, perf kvm stat
== perf stat with perf_guest flag set to 1).
>
> 2)
>
> Another suggestion: it would be nice to allow a "--repeat <n>" option as
> well, for a limited number of iterations - similar to what the 'top' tool
> allows:
>
> top -b -d <delay> -n <iterations>
>
> --repeat 0 means infinite repeats, --repeat 1 means a single step.
Missed that option in perf-top. Let me take a look at it.
> 3)
>
> It might make sense to create 'perf kvm stat top' which is a small
> variation to 'perf kvm stat live': it outputs a perf stat output per
> second, but also outputs a clear-screen sequence before the output.
>
> To keep it simple you could do this with plain console text output, not
> libslang, the C code to generate a clear screen sequence can be generated
> via this shell oneliner:
>
> echo 'prinf("'$(clear)'");' > clearscreen.c
>
> This way people could see constantly updating top-alike KVM statistics.
Ok, once the basic live command is pulled into Arnaldo's tree I can look
at variations like these last 2 suggestions.
David
next prev parent reply other threads:[~2013-05-09 13:54 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-05-09 4:31 [PATCH 00/13] perf: kvm live mode David Ahern
2013-05-09 4:31 ` [PATCH 01/13] perf evlist: restore methods removed in earlier cleanup David Ahern
2013-05-09 4:31 ` [PATCH 02/13] perf evlist: move tracepoint processing code to evlist.c David Ahern
2013-05-09 4:31 ` [PATCH 03/13] perf evlist: add initialzation function for tracepoints David Ahern
2013-05-09 8:40 ` Namhyung Kim
2013-05-09 4:31 ` [PATCH 04/13] perf session: export a few functions for event processing David Ahern
2013-05-10 12:14 ` Jiri Olsa
2013-05-10 14:07 ` David Ahern
2013-05-09 4:31 ` [PATCH 05/13] perf top: move CONSOLE_CLEAR to header file David Ahern
2013-05-09 4:31 ` [PATCH 06/13] perf kvm: handle realloc failures David Ahern
2013-05-09 4:31 ` [PATCH 07/13] perf kvm: split out tracepoints from record args David Ahern
2013-05-10 12:39 ` Jiri Olsa
2013-05-26 0:10 ` David Ahern
2013-05-09 4:31 ` [PATCH 08/13] perf stats: fix divide by 0 in variance David Ahern
2013-05-09 4:31 ` [PATCH 09/13] perf stats: add max and min stats David Ahern
2013-05-09 4:31 ` [PATCH 10/13] perf kvm: add live mode David Ahern
2013-05-09 8:45 ` Namhyung Kim
2013-05-09 13:56 ` David Ahern
2013-05-09 8:51 ` Ingo Molnar
2013-05-09 13:54 ` David Ahern [this message]
2013-05-10 0:28 ` Namhyung Kim
2013-05-10 0:34 ` David Ahern
2013-05-10 8:08 ` Ingo Molnar
2013-05-09 12:32 ` Runzhen
2013-05-09 13:29 ` David Ahern
2013-05-09 4:31 ` [PATCH 11/13] perf kvm: add min and max stats to display David Ahern
2013-05-09 4:31 ` [PATCH 12/13] perf kvm: option to print events that exceed a threshold David Ahern
2013-05-09 4:31 ` [PATCH 13/13] perf kvm: debug for missing vmexit/vmentry event David Ahern
2013-05-09 12:53 ` [PATCH 00/13] perf: kvm live mode Xiao Guangrong
2013-05-13 9:40 ` Gleb Natapov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=518BAA92.2030101@gmail.com \
--to=dsahern@gmail.com \
--cc=acme@ghostprotocols.net \
--cc=fweisbec@gmail.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=peterz@infradead.org \
--cc=xiaoguangrong@linux.vnet.ibm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.