Date: Tue, 19 May 2015 19:05:29 -0300
From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Alexei Starovoitov <ast@plumgrid.com>
Cc: Namhyung Kim <namhyung@kernel.org>, Wang Nan <wangnan0@huawei.com>,
        paulus@samba.org, a.p.zijlstra@chello.nl, mingo@redhat.com,
        jolsa@kernel.org, dsahern@gmail.com, daniel@iogearbox.net,
        brendan.d.gregg@gmail.com, masami.hiramatsu.pt@hitachi.com,
        lizefan@huawei.com, linux-kernel@vger.kernel.org, pi3orama@163.com
Subject: Re: [RFC PATCH v3 00/37] perf tools: introduce 'perf bpf' command to
 load eBPF programs.
Message-ID: <20150519220529.GA26111@kernel.org>
References: <20150518204416.GJ18563@kernel.org>
 <555A541F.6090606@plumgrid.com>
 <20150518212013.GB13946@kernel.org>
 <555A5D96.2070509@plumgrid.com>
 <20150519134458.GC13946@kernel.org>
 <20150519160448.GD29162@danjae.kornet>
 <20150519164040.GB19921@kernel.org>
 <555BA112.6090505@plumgrid.com>
 <20150519211033.GF19921@kernel.org>
 <555BAE33.5060502@plumgrid.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <555BAE33.5060502@plumgrid.com>
User-Agent: Mutt/1.5.23 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1991
Lines: 55

Em Tue, May 19, 2015 at 02:42:11PM -0700, Alexei Starovoitov escreveu:
> On 5/19/15 2:10 PM, Arnaldo Carvalho de Melo wrote:
> >
> >This all should use infrastructure in perf for symbol resolving,
> >callcahins, etc.
> 
> yes. 100%
> 
> >Right, but if we do a:
> >
> >perf script -i perf.data bpf_file.c
> >
> >Then there would be a short circuit effect of just doing the
> >aggregation and/or reporting.

Ok, can you point me to this bpf_file.c, an example? So that we can talk
about the parts of it that would be short circuited when not loading the
bpf_file.o, etc.
 
> That can work, but I don't see why I would use bpf for
> scripting on top of perf.data. If trace is already collected,
> the existing perl/python scripts will work fine.

> >Well, we could have a tee like mode where perf.data file could be
> >generated so that we could run it again after doing some change on the
> >aggregation code, so that we wouldn't have to re-run the data collection
> >parts, that could be about some condition hard to capture, etc.
> 
> true, but again I don't think in such scenario you'd need bpf.
> bpf is needed when the number of events is huge and the user
> needs to aggregate/process them in-kernel.
> 
> >>I guess I'm saying let's not get too much ahead of ourselves ;)
> >
> >No problem, but then we need to talk at this moment not to add new stuff
> >that we think should not be added, like 'perf bpf' :-)
> 
> ahh, that's where you going :) Sure. I don't mind avoiding that

:-) If there is no need, why add a new command? I.e. if all that is
wanted can be used by integrating eBPF into existing commands, that
could be best.

> unbearable abbreviation if we can :)

:-)

> 'perf script file.[oc]' command line works for me.

- Arnaldo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/