From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from forward11o.cmail.yandex.net ([37.9.109.178]:51097 "EHLO forward11o.cmail.yandex.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751374AbdBBMbB (ORCPT ); Thu, 2 Feb 2017 07:31:01 -0500 Received: from smtp2p.mail.yandex.net (smtp2p.mail.yandex.net [IPv6:2a02:6b8:0:1472:2741:0:8b6:7]) by forward11o.cmail.yandex.net (Yandex) with ESMTP id 372CE213F9 for ; Thu, 2 Feb 2017 15:23:48 +0300 (MSK) Received: from smtp2p.mail.yandex.net (localhost.localdomain [127.0.0.1]) by smtp2p.mail.yandex.net (Yandex) with ESMTP id A86551A8006F for ; Thu, 2 Feb 2017 15:23:47 +0300 (MSK) From: Andrew Perepechko To: linux-fsdevel@vger.kernel.org Subject: quota: dqio_mutex design Date: Thu, 02 Feb 2017 15:23:44 +0300 Message-ID: <10928956.Fla3vXZ7d9@panda> MIME-Version: 1.0 Content-Transfer-Encoding: 7Bit Content-Type: text/plain; charset="us-ascii" Sender: linux-fsdevel-owner@vger.kernel.org List-ID: Hello! We have a heavy metadata related workload (ext4, quota journalling) and profiling shows that there's significant dqio_mutex contention. >>From the quota code, it looks like every time dqio_mutex is taken it protects access to only one quota file. Is it possible to split dqio_mutex for each of MAXQUOTAS so that e.g. 2 parallel dquot_commit()'s can be running for user and group quota update? Am I missing any dqio_mutex function that requires dqio_mutex to be monolithic? Thank you, Andrew