From: Jan Kara Subject: [PATCH 0/4 RFC] writeback: Dirty list handling changes Date: Thu, 20 Mar 2014 15:30:52 +0100 Message-ID: <1395325856-8171-1-git-send-email-jack@suse.cz> Cc: Wu Fengguang , Andrew Morton , dchinner@redhat.com, Jan Kara To: linux-fsdevel@vger.kernel.org Return-path: Received: from cantor2.suse.de ([195.135.220.15]:53224 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756393AbaCTOb1 (ORCPT ); Thu, 20 Mar 2014 10:31:27 -0400 Sender: linux-fsdevel-owner@vger.kernel.org List-ID: Hello, so I was recently thinking about how writeback code shuffles inodes between lists and also how redirty_tail() clobbers dirtied_when timestamp (which broke my sync(2) optimization). This patch series came out of that. Patch 1 is a clear win and just needs an independent review that I didn't forget about something. Patch 3 changes writeback list handling - IMHO it makes the logic somewhat more straightforward as we don't have to bother shuffling inodes between lists and we also don't need to clobber dirtied_when timestamp. But opinions may differ... Patches passed xfstests run so they should be reasonably sound but I also want to do some targetted tests for sync livelocks, busylocks, etc. before patches get merged. But before spending too much time with that I wanted to check what other people think about it. Honza