From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1423414AbXD3Pj2 (ORCPT ); Mon, 30 Apr 2007 11:39:28 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1423380AbXD3Pj2 (ORCPT ); Mon, 30 Apr 2007 11:39:28 -0400 Received: from ug-out-1314.google.com ([66.249.92.168]:35183 "EHLO ug-out-1314.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1423415AbXD3PjZ (ORCPT ); Mon, 30 Apr 2007 11:39:25 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:user-agent:mime-version:to:cc:subject:x-enigmail-version:content-type:content-transfer-encoding; b=hYOAZGEn1kIdjK4SI7PtmKi5KDWSRzYkac0/tXu7ayOP0KKgPneMw7bdSgGJg04vfXhK6D7hSFlLneo4tTCBPntkwkEHluwWZNEh4GNOtG5Xf8zYB18PwaoxsXzIFe4bzjRLkPpiDf1axMPHn3YfoC0N5JYSJJFVwTkAdlmO8q4= Message-ID: <46360DA7.6040003@gmail.com> Date: Mon, 30 Apr 2007 17:39:19 +0200 From: Jiri Slaby User-Agent: Thunderbird 2.0.0.0 (X11/20070326) MIME-Version: 1.0 To: Andrew Morton CC: Linux Kernel Mailing List Subject: 2.6.21-mm1: many processes end up in D state X-Enigmail-Version: 0.95b Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Hi, I have a problem with higher disk loads (e.g. running git-log or yum update). Many processes end up in D state and system is unusable -- I'm not able to run anything but smooth mouse moving when this happens. If I wait for a 20-30sec it becomes usable. This happens in 2.6.21-rc7-mm2 and also in 2007-04-28-05-06 broken-out snapshot. I think 2.6.21-rc6-mm1 worked fine, but I'm uncertain. If it is important, let me know to re-test. sysrq-t: yum D 0000004C 0 2976 2955 (NOTLB) c455bd00 00200082 8c68ea9e 0000004c 00000000 00000000 c455bcdc c455bc9c c455bc9c c2d6a580 8c68ea9e 0000004c c455bcc0 c2d6a694 c1809980 00000000 c455bcd0 c4640c80 000036a0 00000001 c455bcf0 c02a7132 c3682164 00001cde Call Trace: [] io_schedule+0x21/0x2e [] sync_page+0x38/0x43 [] __wait_on_bit_lock+0x40/0x63 [] __lock_page+0x54/0x5c [] do_generic_mapping_read+0x1dc/0x57e [] generic_file_aio_read+0xc9/0x1b5 [] do_sync_read+0xd0/0x106 [] vfs_read+0x89/0x11d [] sys_pread64+0x64/0x68 [] syscall_call+0x7/0xb [<47176012>] 0x47176012 ======================= xterm S 00000051 0 2980 1 (NOTLB) c4678ae0 00000082 b2fbf0ce 00000051 00000000 00000000 00000000 00000000 c4678b30 c469d540 b2fbf0ce 00000051 c4678ab0 c469d654 c1813980 00000001 c4678ad0 c47f0e40 c4678b00 00000286 c4678ae0 c012c077 00000001 00003286 Call Trace: [] schedule_timeout+0x44/0xa4 [] do_select+0x46d/0x55b [] core_sys_select+0x19e/0x2c0 [] sys_select+0xd3/0x18d [] syscall_call+0x7/0xb [<47180f98>] 0x47180f98 ======================= bash S 0000004A 0 2982 2980 (NOTLB) c50b3e80 00000086 ccf4cc7e 0000004a 00000000 c021bed9 00000000 c45c0030 c50b3e30 c45c0030 ccf4cc7e 0000004a c50b3e50 c45c0144 c1809980 00000000 c1809e44 c4517900 00000000 000000b3 c50b3e90 c014f841 c477cb40 c2d79000 Call Trace: [] schedule_timeout+0x6a/0xa4 [] read_chan+0x1b9/0x5b9 [] tty_read+0x75/0xaa [] vfs_read+0x89/0x11d [] sys_read+0x3d/0x64 [] syscall_call+0x7/0xb [<4717883e>] 0x4717883e ======================= metacity S 00000050 0 3005 2429 (NOTLB) c2fd5bb0 00000086 5205656d 00000050 00000000 00000000 00000000 c441c51c 00000246 c45c0540 5205656d 00000050 c2fd5b80 c45c0654 c1809980 00000000 c1813e44 c27f4900 00002cb8 00000246 c2fd5ba0 c0135a80 c2fd5ba8 00002cb2 Call Trace: [] schedule_timeout+0x6a/0xa4 [] do_sys_poll+0x33f/0x46d [] sys_poll+0x41/0x43 [] syscall_call+0x7/0xb [<4717e3a6>] 0x4717e3a6 ======================= ccpd D 0000004C 0 3009 2010 (NOTLB) c50abbb0 00000082 f08ef585 0000004c 00000000 00000000 c180abc0 c22fc788 c50abba0 c505d070 f08ef585 0000004c 00000000 c505d184 c1809980 00000000 c21167f0 c2fc6740 c5794e3c c31eff74 c5794310 c22fc788 00000002 00001e64 Call Trace: [] do_get_write_access+0x310/0x4f5 [] journal_get_write_access+0x1b/0x2a [] __ext3_journal_get_write_access+0x19/0x3f [] ext3_reserve_inode_write+0x53/0x6c [] ext3_mark_inode_dirty+0x20/0x37 [] ext3_dirty_inode+0x6b/0x6d [] __mark_inode_dirty+0x2a/0x16d [] touch_atime+0x84/0xd8 [] do_generic_mapping_read+0x463/0x57e [] generic_file_aio_read+0xc9/0x1b5 [] do_sync_read+0xd0/0x106 [] vfs_read+0x89/0x11d [] kernel_read+0x36/0x48 [] prepare_binprm+0xb2/0xdf [] do_execve+0xe6/0x1e1 [] sys_execve+0x2e/0x7f [] syscall_call+0x7/0xb [<471474da>] 0x471474da ======================= bash D 0000004D 0 3011 2859 (NOTLB) c471dc90 00000082 08f8373c 0000004d 00000000 00000000 c471dc30 c471dc2c c471dc2c c4670540 08f8373c 0000004d c471dc50 c4670654 c1809980 00000000 c471dc60 c2f3f040 00000005 00000001 c471dc80 c02a7132 c591af64 00001eea Call Trace: [] io_schedule+0x21/0x2e [] sync_page+0x38/0x43 [] __wait_on_bit_lock+0x40/0x63 [] __lock_page+0x54/0x5c [] do_generic_mapping_read+0x1dc/0x57e [] generic_file_aio_read+0xc9/0x1b5 [] do_sync_read+0xd0/0x106 [] vfs_read+0x89/0x11d [] kernel_read+0x36/0x48 [] prepare_binprm+0xb2/0xdf [] do_execve+0xe6/0x1e1 [] sys_execve+0x2e/0x7f [] syscall_call+0x7/0xb [<471474da>] 0x471474da ======================= bash D 0000004D 0 3012 2884 (NOTLB) c50d5a80 00000082 a21bfc35 0000004d 00000000 00000000 c180abc0 c2033dd4 c50d5a70 c2f4f070 a21bfc35 0000004d 00000000 c2f4f184 c1809980 00000000 c21167bc c47f0c80 c2033310 c22fc788 c5794e3c c2033dd4 00000002 0000216d Call Trace: [] do_get_write_access+0x310/0x4f5 [] journal_get_write_access+0x1b/0x2a [] __ext3_journal_get_write_access+0x19/0x3f [] ext3_reserve_inode_write+0x53/0x6c [] ext3_mark_inode_dirty+0x20/0x37 [] ext3_dirty_inode+0x6b/0x6d [] __mark_inode_dirty+0x2a/0x16d [] touch_atime+0x84/0xd8 [] __link_path_walk+0x893/0xca4 [] link_path_walk+0x46/0xc3 [] do_path_lookup+0x86/0x1b0 [] __path_lookup_intent_open+0x44/0x7f [] path_lookup_open+0x21/0x27 [] open_exec+0x27/0xa2 [] load_elf_binary+0x1482/0x1acf [] search_binary_handler+0x6e/0x19f [] do_execve+0x14a/0x1e1 [] sys_execve+0x2e/0x7f [] syscall_call+0x7/0xb [<471474da>] 0x471474da ======================= Note that yum works on lvm on raid0 and git too, but on the another md volume. Both ext3s. Drivers are sata_promise and ata_piix (sata disk); CFQ scheduler. Using noop is no change (but seems to be harder to reproduce with it). I figured out that it probably happens when 2+ processes are on both "processors" (HT on P4) and are IO wait (multiload-applet shows red above the half). Swap usage is 0 all the time. regards, -- http://www.fi.muni.cz/~xslaby/ Jiri Slaby faculty of informatics, masaryk university, brno, cz e-mail: jirislaby gmail com, gpg pubkey fingerprint: B674 9967 0407 CE62 ACC8 22A0 32CC 55C3 39D4 7A7E