Message-ID: <553A4B76.9040207@huawei.com>
Date: Fri, 24 Apr 2015 21:56:06 +0800
From: Yunlong Song <yunlong.song@huawei.com>
User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:31.0) Gecko/20100101 Thunderbird/31.3.0
MIME-Version: 1.0
To: David Ahern <dsahern@gmail.com>, <a.p.zijlstra@chello.nl>,
        <paulus@samba.org>, <mingo@redhat.com>,
        Arnaldo Carvalho de Melo <acme@kernel.org>
CC: <linux-kernel@vger.kernel.org>, <wangnan0@huawei.com>
Subject: Re: [Question] How does perf still record the stack of a specified
 pid even when that process is interrupted and CPU is scheduled to other process
References: <553A45CA.8020808@huawei.com> <553A49FC.9010002@gmail.com>
In-Reply-To: <553A49FC.9010002@gmail.com>
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1003
Lines: 29

On 2015/4/24 21:49, David Ahern wrote:
> On 4/24/15 7:31 AM, Yunlong Song wrote:
>> [Profiling Problem]
>>
>> Although perf can record the events (with call stack) of a specified pid, e.g. using
>> "perf record -g iozone -s 262144 -r 64 -i 0 -i 2". But we find iozone is interrupted
> 
> That command tells perf to *only* collect data for iozone. This command:
> 
>     perf record -g -a -- iozone ....
> 
> tells perf to collect samples system wide as long as the iozone process is alive.
> 
> 
> 

But we only want the records of iozone rather than the overall system, since other process
will interfere the targeted I/O stack of the specific 1% case, and we cannot figure out the
"clean" specific stack which takes up 60% time.

-- 
Thanks,
Yunlong Song

--
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/