From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S932868AbbIYRyX (ORCPT <rfc822;w@1wt.eu>);
	Fri, 25 Sep 2015 13:54:23 -0400
Received: from userp1040.oracle.com ([156.151.31.81]:34121 "EHLO
	userp1040.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S932681AbbIYRyU (ORCPT
	<rfc822;linux-kernel@vger.kernel.org>);
	Fri, 25 Sep 2015 13:54:20 -0400
Message-ID: <56058A34.8050900@oracle.com>
Date: Fri, 25 Sep 2015 10:53:56 -0700
From: Ashish Samant <ashish.samant@oracle.com>
Reply-To: ashish.samant@oracle.com
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.2.0
MIME-Version: 1.0
To: Miklos Szeredi <miklos@szeredi.hu>
CC: Linux-Fsdevel <linux-fsdevel@vger.kernel.org>,
        Kernel Mailing List <linux-kernel@vger.kernel.org>,
        fuse-devel <fuse-devel@lists.sourceforge.net>,
        Srinivas Eeda <srinivas.eeda@oracle.com>
Subject: Re: fuse scalability part 1
References: <20150518151336.GA9960@tucsk>	<56044C66.1090207@oracle.com> <CAJfpegsgjV2ePkdjZDAi5GoJ5M-Zeoy10v-5p+bzyHVAnGQpuA@mail.gmail.com>
In-Reply-To: <CAJfpegsgjV2ePkdjZDAi5GoJ5M-Zeoy10v-5p+bzyHVAnGQpuA@mail.gmail.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
X-Source-IP: aserv0021.oracle.com [141.146.126.233]
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org


On 09/25/2015 05:11 AM, Miklos Szeredi wrote:
> On Thu, Sep 24, 2015 at 9:17 PM, Ashish Samant <ashish.samant@oracle.com> wrote:
>
>> We did some performance testing without these patches and with these patches
>> (with -o clone_fd  option specified). We did 2 types of tests:
>>
>> 1. Throughput test : We did some parallel dd tests to read/write to FUSE
>> based database fs on a system with 8 numa nodes and 288 cpus. The
>> performance here is almost equal to the the per-numa patches we submitted a
>> while back.Please find results attached.
> Interesting.  This means, that serving the request on a different NUMA
> node as the one where the request originated doesn't appear to make
> the performance much worse.
>
> Thanks,
> Miklos
Yes. The main performance gain is due to the reduced contention on one 
spinlock(fc->lock) , especially with a large number of requests.
Splitting fc->fiq per cloned device will definitely improve performance 
further and we can  experiment further with per numa / cpu cloned device.

Thanks,
Ashish