From: bugzilla-daemon@bugzilla.kernel.org Subject: [Bug 15906] performance regression in "umount" of filesystems using barriers Date: Fri, 21 May 2010 02:07:11 GMT Message-ID: <201005210207.o4L27B7r004287@demeter.kernel.org> References: Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" To: linux-ext4@vger.kernel.org Return-path: Received: from demeter.kernel.org ([140.211.167.39]:59857 "EHLO demeter.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753163Ab0EUCHM (ORCPT ); Thu, 20 May 2010 22:07:12 -0400 Received: from demeter.kernel.org (localhost.localdomain [127.0.0.1]) by demeter.kernel.org (8.14.3/8.14.3) with ESMTP id o4L27BCu004288 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=NO) for ; Fri, 21 May 2010 02:07:11 GMT In-Reply-To: Sender: linux-ext4-owner@vger.kernel.org List-ID: https://bugzilla.kernel.org/show_bug.cgi?id=15906 --- Comment #27 from Eric Sandeen 2010-05-21 02:07:01 --- static int pin_sb_for_writeback(struct writeback_control *wbc, struct inode *inode, struct super_block **psb) { struct super_block *sb = inode->i_sb; /* * If this sb is already pinned, nothing more to do. If not and * *psb is non-NULL, unpin the old one first */ if (sb == *psb) return 0; else if (*psb) unpin_sb_for_writeback(psb); /* * Caller must already hold the ref for this */ if (wbc->sync_mode == WB_SYNC_ALL || wbc->sb_pinned) { WARN_ON(!rwsem_is_locked(&sb->s_umount)); <<----- here return 0; } http://git.kernel.org/?p=linux/kernel/git/axboe/linux-2.6-block.git;a=commitdiff;h=e913fc825dc685a444cb4c1d0f9d32f372f5986 is what Jens had upstream, and I think http://git.kernel.org/?p=linux/kernel/git/axboe/linux-2.6-block.git;a=commitdiff;h=30fd1e551a730d942e91109762c942786be0ef7c is the fix for the issue you see here... > Even if the writeout itself isn't a data integrity operation, we need > to ensure that the caller doesn't drop the sb umount sem before we > have actually done the writeback. -- Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are watching the assignee of the bug.