cvs commit: src/sys/geom/eli g_eli.c

Nate Lawson nate at
Mon Jan 29 22:45:58 UTC 2007

Pawel Jakub Dawidek wrote:
> On Mon, Jan 29, 2007 at 10:07:24AM -0800, Nate Lawson wrote:
>> Pawel Jakub Dawidek wrote:
>>> Hmm, I thought that cold is zeroed before smp_started is set?
>> I don't think that's guaranteed.  Besides, there's an easier way to fix your problem.  Instead of calling kthread_create() from your geom create routine directly, queue a 
>> stub request on the thread taskqueue to call kthread_create().
>> For example, see sys/dev/acpica/acpi_acad.c.  We call this from attach()    and then the system thread only runs and then calls acpi_acad_init() once all CPUs are 
>> initialized.  See sys/sys/taskqueue.h for how to add a task to the system thread taskqueue:
>> taskqueue_enqueue(taskqueue_thread, &task);
> If we want to fix it better, I think GEOM should start (tasting at
> least) after all CPUs are online.

Fine, take my suggestion and bump it up a level.  Have GEOM queue an 
event on a taskqueue that will be run once all CPUs are available to 
begin tasting.

And Robert's suggestion sounds good in the long run.


More information about the cvs-src mailing list