[lkml]   [2005]   [May]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: [PATCH] cpusets+hotplug+preepmt broken
On Thu, May 12, 2005 at 12:46:54AM +0530, Dinakar Guniguntala wrote:
> cpusets+hotplug+preempt hangs up the machine, if both
> cpuset and hotplug operations are going on simultaneously
> I also get this oops first
> scheduling while atomic:
> [<c040195d>] schedule+0xa4d/0xa60
> [<c0401b25>] wait_for_completion+0xc5/0xf0
> [<c011a200>] default_wake_function+0x0/0x20
> [<c0400cd3>] __down+0x83/0x110
> [<c011a200>] default_wake_function+0x0/0x20
> [<c0400eab>] __down_failed+0x7/0xc
> [<c0141fe7>] .text.lock.cpuset+0x105/0x15e
> [<c011b860>] move_task_off_dead_cpu+0x130/0x1f0
> [<c011ba7c>] migrate_live_tasks+0x8c/0x90
> [<c011be25>] migration_call+0x75/0x2c0
> [<c01423f2>] __stop_machine_run+0x92/0xb0
> [<c012e0dd>] notifier_call_chain+0x2d/0x50
> [<c013a6fb>] cpu_down+0x16b/0x2a0
> [<c027ddfb>] store_online+0x5b/0x80
> [<c027ae15>] sysdev_store+0x35/0x40
> [<c019f43e>] flush_write_buffer+0x3e/0x50
> [<c019f4a8>] sysfs_write_file+0x58/0x80
> [<c0163d26>] vfs_write+0xc6/0x180
> [<c0163eb1>] sys_write+0x51/0x80
> [<c01034e5>] syscall_call+0x7/0xb

This trace is what should be fixed -- we're trying to schedule while
the machine is "stopped" (all cpus except for one spinning with
interrupts off). I'm not too familiar with the cpusets code but I
would like to stay away from nesting these semaphores if at all

Will you share your testcase please?

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to
More majordomo info at
Please read the FAQ at

 \ /
  Last update: 2005-05-11 21:55    [W:0.289 / U:5.256 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site