Re: task hald-addon-stor:2815 blocked for more than 120 seconds.
On Tue, Oct 28, 2008 at 07:25:32AM +1100, Alex Samad wrote: > I have seen it start to happen when my md's resync, a 10 disk raid6 take > a while to resync and I get lots of these messages. In fact any > reshaping/resync'ing activity brings these up. I have re written the > monthly resync to turn off the warning whilst it is running and turn it > back on when it is finished. > > I also use the deadline io schedular I run my resync limited to 20MB/s, and they were happening at other times, not while the raid resync was going on, at least in my case. Given turning off nohz and highres seems to have eliminated them, I would simply say there is a serious bug on SMP machines with nohz/highres in 2.6.26. If it was easier to trigger consistently I would have tried to find the commit that caused it, but it isn't frequent enough (and I like my TV shows to record properly). -- Len Sorensen -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
Re: task hald-addon-stor:2815 blocked for more than 120 seconds.
On Mon, Oct 27, 2008 at 10:25:49AM -0400, Lennart Sorensen wrote: > On Sun, Oct 26, 2008 at 09:05:42PM +0530, Vikram Vincent wrote: > > The following messages keep repeating at regular intervals and I am not sure > > how to deal with them or to ignore them. > > Any suggestions will be useful. > > Thanks. > > Vikram Vincent > > I have seen similar multi minute "hangs" on my Q6600 running amd64 with > 2.6.26 kernel. I have no idea what caused it to start happening in > 2.6.26. I am now running with nohz=off highres=off which seems to have > made the problem go away. 2.6.25 and earlier never do it. It also > seems to always be related to disk IO. > [snip] I have seen it start to happen when my md's resync, a 10 disk raid6 take a while to resync and I get lots of these messages. In fact any reshaping/resync'ing activity brings these up. I have re written the monthly resync to turn off the warning whilst it is running and turn it back on when it is finished. I also use the deadline io schedular Alex > > -- > Len Sorensen > > > -- > To UNSUBSCRIBE, email to [EMAIL PROTECTED] > with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED] > > -- A manager went to the master programmer and showed him the requirements document for a new application. The manager asked the master: "How long will it take to design this system if I assign five programmers to it?" "It will take one year," said the master promptly. "But we need this system immediately or even sooner! How long will it take it I assign ten programmers to it?" The master programmer frowned. "In that case, it will take two years." "And what if I assign a hundred programmers to it?" The master programmer shrugged. "Then the design will never be completed," he said. -- Geoffrey James, "The Tao of Programming" signature.asc Description: Digital signature
Re: task hald-addon-stor:2815 blocked for more than 120 seconds.
On Mon, Oct 27, 2008 at 10:46:18AM -0500, Mark Allums wrote: > I am seeing hangs due to excessive disk activity when Epiphany browser > has been running for too long. I close it or kill it, and switch to > Iceweasel, and the problem resolves. Of course, Iceweasel has its own > issues. This may not be related, but it is a recent phenomenon. Since > I switched from 2.6.25 to 2.6.26. Dual-core Athlon 64 X2 4800, 4 GB. I don't have any browser on that machine. It runs bittornado, mythtv (frong and backend), [EMAIL PROTECTED] client, and some fileserving. -- Len Sorensen -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
Re: task hald-addon-stor:2815 blocked for more than 120 seconds.
Lennart Sorensen wrote: On Sun, Oct 26, 2008 at 09:05:42PM +0530, Vikram Vincent wrote: The following messages keep repeating at regular intervals and I am not sure how to deal with them or to ignore them. Any suggestions will be useful. Thanks. Vikram Vincent I have seen similar multi minute "hangs" on my Q6600 running amd64 with 2.6.26 kernel. I have no idea what caused it to start happening in 2.6.26. I am now running with nohz=off highres=off which seems to have made the problem go away. 2.6.25 and earlier never do it. It also seems to always be related to disk IO. I am seeing hangs due to excessive disk activity when Epiphany browser has been running for too long. I close it or kill it, and switch to Iceweasel, and the problem resolves. Of course, Iceweasel has its own issues. This may not be related, but it is a recent phenomenon. Since I switched from 2.6.25 to 2.6.26. Dual-core Athlon 64 X2 4800, 4 GB. Mark Allums -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
Re: task hald-addon-stor:2815 blocked for more than 120 seconds.
On Sun, Oct 26, 2008 at 09:05:42PM +0530, Vikram Vincent wrote: > The following messages keep repeating at regular intervals and I am not sure > how to deal with them or to ignore them. > Any suggestions will be useful. > Thanks. > Vikram Vincent I have seen similar multi minute "hangs" on my Q6600 running amd64 with 2.6.26 kernel. I have no idea what caused it to start happening in 2.6.26. I am now running with nohz=off highres=off which seems to have made the problem go away. 2.6.25 and earlier never do it. It also seems to always be related to disk IO. > [ 691.490083] INFO: task hald-addon-stor:2815 blocked for more than 120 > seconds. > [ 691.490092] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables > this message. > [ 691.490095] hald-addon-st D 7fff 0 2815 2777 > [ 691.490104] 81003c981878 0082 a0120dff > a004bb00 > [ 691.490117] a004bb00 81003dbe7020 81003da16080 > 81003dbe72a8 > [ 691.490128] a004bb90 81002e0cd400 a004bb00 > 0004 > [ 691.490139] Call Trace: > [ 691.494062] [] :ide_cd_mod:cdrom_newpc_intr+0x0/0x5e1 > [ 691.494077] [] > :ide_cd_mod:cdrom_do_newpc_cont+0x0/0x2b > [ 691.494089] [] schedule_timeout+0x1e/0xad > [ 691.494114] [] :ide_core:ide_do_request+0x8c7/0x92a > [ 691.494136] [] :ide_core:ide_do_request+0x1c/0x92a > [ 691.494143] [] wait_for_common+0xcf/0x13a > [ 691.494149] [] default_wake_function+0x0/0xe > [ 691.494171] [] :ide_core:ide_do_drive_cmd+0xe2/0x109 > [ 691.494186] [] :ide_cd_mod:ide_cd_queue_pc+0x42/0xca > [ 691.494194] [] :ide_cd_mod:ide_cd_queue_pc+0x42/0xca > [ 691.494202] [] blk_rq_init+0x1c/0x85 > [ 691.494216] [] > :ide_cd_mod:cdrom_read_tocentry+0xb1/0xc3 > [ 691.494246] [] blk_end_sync_rq+0x0/0x2e > [ 691.494260] [] :ide_cd_mod:ide_cd_read_toc+0x101/0x3d6 > [ 691.494277] [] > :ide_cd_mod:idecd_revalidate_disk+0x14/0x1b > [ 691.494283] [] get_super+0x1a/0x8d > [ 691.494289] [] __invalidate_device+0x3a/0x42 > [ 691.494294] [] check_disk_change+0x4f/0x76 > [ 691.494306] [] :cdrom:cdrom_open+0x983/0xa14 > [ 691.494315] [] dput+0x1c/0xdd > [ 691.494320] [] kobject_get+0x12/0x17 > [ 691.494325] [] get_disk+0x40/0x5b > [ 691.494331] [] exact_lock+0xc/0x14 > [ 691.494342] [] :ide_cd_mod:idecd_open+0x5b/0x89 > [ 691.494346] [] blkdev_open+0x0/0x5d > [ 691.494352] [] do_open+0xd1/0x2e8 > [ 691.494361] [] blkdev_open+0x0/0x5d > [ 691.494366] [] blkdev_open+0x2e/0x5d > [ 691.494373] [] __dentry_open+0x12c/0x238 > [ 691.494383] [] do_filp_open+0x3d7/0x7c4 > [ 691.494394] [] :cdrom:cdrom_release+0x1a7/0x1e4 > [ 691.494407] [] iput+0x27/0x60 > [ 691.494416] [] get_unused_fd_flags+0x71/0x115 > [ 691.494424] [] do_sys_open+0x46/0xc3 > [ 691.494432] [] system_call_after_swapgs+0x8a/0x8f > [ 691.49] -- Len Sorensen -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]