From mboxrd@z Thu Jan 1 00:00:00 1970 From: bugzilla-daemon@bugzilla.kernel.org Subject: [Bug 86471] drastic reduction of write performance after the termination of mysqld Date: Fri, 17 Oct 2014 16:29:29 +0000 Message-ID: References: Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE To: linux-ext4@vger.kernel.org Return-path: Received: from mail.kernel.org ([198.145.19.201]:36297 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752822AbaJQQ3b convert rfc822-to-8bit (ORCPT ); Fri, 17 Oct 2014 12:29:31 -0400 Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id A47C7200ED for ; Fri, 17 Oct 2014 16:29:30 +0000 (UTC) Received: from bugzilla2.web.kernel.org (bugzilla2.web.kernel.org [172.20.200.52]) by mail.kernel.org (Postfix) with ESMTP id AB9C42021B for ; Fri, 17 Oct 2014 16:29:29 +0000 (UTC) In-Reply-To: Sender: linux-ext4-owner@vger.kernel.org List-ID: https://bugzilla.kernel.org/show_bug.cgi?id=3D86471 --- Comment #2 from Markus K=C3=B6nigshaus --- Hi Theodore, even after a very long wait, the performance remain so low. The perform= ance is also low when you copy files. I have used dd, so I create only reproduc= ible write access. I have now tested the ext3 FS, same result. After some debugging I found out, there is a delay in start_this_handle= (look at the timing), with echo 5 > /sys/kernel/debug/jbd/jbd-debug I get: >> before mysqlshutdown: =2E.. [ 40.400755] fs/jbd/transaction.c: (journal_stop, 1380): h_ref 2 -> 1 [ 40.400755]=20 [ 40.400765] fs/jbd/transaction.c: (journal_stop, 1384): Handle df03e= 000 going down [ 40.400765]=20 [ 40.400789] fs/jbd/transaction.c: (journal_start, 290): from journal= _start [ 40.400789]=20 [ 40.400801] fs/jbd/transaction.c: (start_this_handle, 110): New hand= le df03e000 going live. [ 40.400801]=20 [ 40.400813] fs/jbd/transaction.c: (start_this_handle, 229): Handle d= f03e000 given 14 credits (total 21, free 14286) =2E.. >> after mysqlshutdown: =2E.. [ 61.383886] fs/jbd/transaction.c: (journal_stop, 1380): h_ref 2 -> 1 [ 61.383886]=20 [ 61.383896] fs/jbd/transaction.c: (journal_stop, 1384): Handle df03e= 000 going down [ 61.383896]=20 [ 61.393528] fs/jbd/transaction.c: (start_this_handle, 110): New hand= le df03e000 going live. [ 61.393528]=20 [ 61.393541] fs/jbd/transaction.c: (start_this_handle, 229): Handle d= f03e000 given 14 credits (total 21, free 14271) =2E.. I try to isolate the problem in more detail next week, I would welcome = tips and help for my try. Regards, Markus --=20 You are receiving this mail because: You are watching the assignee of the bug.-- To unsubscribe from this list: send the line "unsubscribe linux-ext4" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html