Date: Tue, 11 Jul 2017 10:15:49 -0700
From: Krister Johansen <kjlx@templeofstupid.com>
To: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Thomas-Mich Richter <tmricht@linux.vnet.ibm.com>,
        Brendan Gregg <brendan.d.gregg@gmail.com>,
        Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@redhat.com>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 tip/perf/core 1/6] perf symbols: find symbols in
 different mount namespace
Message-ID: <20170711171548.GB2570@templeofstupid.com>
References: <20170705204511.GD29683@templeofstupid.com>
 <1499305693-1599-1-git-send-email-kjlx@templeofstupid.com>
 <1499305693-1599-2-git-send-email-kjlx@templeofstupid.com>
 <20170706194130.GM27350@kernel.org>
 <20170707193640.GA2554@templeofstupid.com>
 <381cf00c-c540-8c20-7182-ecdd94f2d81c@linux.vnet.ibm.com>
 <20170710223924.GC6865@templeofstupid.com>
 <20170710225249.GC27350@kernel.org>
 <20170710232943.GD6865@templeofstupid.com>
 <20170711125116.GD27350@kernel.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20170711125116.GD27350@kernel.org>
User-Agent: Mutt/1.5.24 (2015-08-30)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1489
Lines: 32

On Tue, Jul 11, 2017 at 09:51:16AM -0300, Arnaldo Carvalho de Melo wrote:
> Right, we need to use the build-id and look it up in a database
> populated somehow.
> 
> perf right now, by default, collects the build-ids in a table, at the
> end of the recording session, trying not to disrupt the monitored
> workload by not processing anything, just reading from the buffers and
> dumping to a file.
> 
> It will also try to populate the build-id, trying first to make a
> hardlink and copying it if it fails.
> 
> If we can get the build-id at the time of the mmap(binary), as part of
> the loading of binaries, that would be ideal, as we're touching the file
> headers anyway and the build-id is a small enough cookie.
> 
> But again, we should first try to do as far as we can with the
> infrastructure we have in the kernel and tooling libraries, lots of
> workloads will be serviced just fine with that.

Sorry, I was slow to pick up on what you're saying here.  I agree that
getting the build-id delivered in an event from the kernel would
accelerate the process of determining whether you have or need to cache
a binary in the build-id cache.  Without such a modification, perf has
to look at each binary to determine whether the build ids match.  If we
got the build-id in the event payload, then we only need to look to see
if the build-id is cached.  If it's not, then we can undertake the more
complicated lookup path.

That would be an improvement over what we can do today.

-K