Zach Brown <[EMAIL PROTECTED]> writes:
>> We could check ctx->reqs_active before scheduling to determine whether
>> or not we are waiting for I/O, but this would require taking the
>> context lock in order to be accurate. Given that the test would be
>> only for the sake of book keeping, it
> We could check ctx->reqs_active before scheduling to determine whether
> or not we are waiting for I/O, but this would require taking the
> context lock in order to be accurate. Given that the test would be
> only for the sake of book keeping, it might be okay to do it outside
> of the lock.
>
Miklos Szeredi <[EMAIL PROTECTED]> writes:
> On 2.6.24, top started showing 100% iowait on one CPU when a UML
> instance was running (but completely idle). I've traced it to this
> commit [1]. Reverting it cures the problem.
Hi,
The UML code sits in io_getevents waiting for an event to be
On 2.6.24, top started showing 100% iowait on one CPU when a UML
instance was running (but completely idle). I've traced it to this
commit. Reverting it cures the problem.
Miklos
commit 41d10da3717409de33d5441f2f6d8f072ab3fbb6
Author: Jeff Moyer <[EMAIL PROTECTED]>
Date: Tue Oct 16
On 2.6.24, top started showing 100% iowait on one CPU when a UML
instance was running (but completely idle). I've traced it to this
commit. Reverting it cures the problem.
Miklos
commit 41d10da3717409de33d5441f2f6d8f072ab3fbb6
Author: Jeff Moyer [EMAIL PROTECTED]
Date: Tue Oct 16 23:27:20
Miklos Szeredi [EMAIL PROTECTED] writes:
On 2.6.24, top started showing 100% iowait on one CPU when a UML
instance was running (but completely idle). I've traced it to this
commit [1]. Reverting it cures the problem.
Hi,
The UML code sits in io_getevents waiting for an event to be
We could check ctx-reqs_active before scheduling to determine whether
or not we are waiting for I/O, but this would require taking the
context lock in order to be accurate. Given that the test would be
only for the sake of book keeping, it might be okay to do it outside
of the lock.
Zach Brown [EMAIL PROTECTED] writes:
We could check ctx-reqs_active before scheduling to determine whether
or not we are waiting for I/O, but this would require taking the
context lock in order to be accurate. Given that the test would be
only for the sake of book keeping, it might be okay
8 matches
Mail list logo
