On Wed, Apr 25 2007, Jens Axboe wrote:
> On Wed, Apr 25 2007, Vasily Tarasov wrote:
> > >> @@ -1806,7 +1765,11 @@ static int cfq_may_queue(request_queue_t
> > >> * so just lookup a possibly existing queue, or return 'may
> > >> queue'
> > >> * if that fails
> > >> */
On Wed, Apr 25 2007, Vasily Tarasov wrote:
> >> @@ -1806,7 +1765,11 @@ static int cfq_may_queue(request_queue_t
> >> * so just lookup a possibly existing queue, or return 'may queue'
> >> * if that fails
> >> */
> >> - cfqq = cfq_find_cfq_hash(cfqd, key, tsk->ioprio);
> >> + cic = cfq
>> @@ -1806,7 +1765,11 @@ static int cfq_may_queue(request_queue_t
>> * so just lookup a possibly existing queue, or return 'may queue'
>> * if that fails
>> */
>> -cfqq = cfq_find_cfq_hash(cfqd, key, tsk->ioprio);
>> +cic = cfq_get_io_context_noalloc(cfqd, tsk);
>> +i
From: Vasily Tarasov <[EMAIL PROTECTED]>
>> -if (key != CFQ_KEY_ASYNC)
>> +if (!is_sync)
>> cfq_mark_cfqq_idle_window(cfqq);
>> +else
>> +cfq_mark_cfqq_sync(cfqq);
>
> Woops, should be
>
> if (is_sync) {
>
On Wed, Apr 25 2007, Jens Axboe wrote:
> On Tue, Apr 24 2007, Vasily Tarasov wrote:
> > @@ -1806,7 +1765,11 @@ static int cfq_may_queue(request_queue_t
> > * so just lookup a possibly existing queue, or return 'may queue'
> > * if that fails
> > */
> > - cfqq = cfq_find_cfq_hash(cf
On Tue, Apr 24 2007, Vasily Tarasov wrote:
> @@ -1806,7 +1765,11 @@ static int cfq_may_queue(request_queue_t
>* so just lookup a possibly existing queue, or return 'may queue'
>* if that fails
>*/
> - cfqq = cfq_find_cfq_hash(cfqd, key, tsk->ioprio);
> + cic = cfq_ge
On Tue, Apr 24 2007, Jens Axboe wrote:
> On Tue, Apr 24 2007, Jens Axboe wrote:
> > - if (key != CFQ_KEY_ASYNC)
> > + if (!is_sync)
> > cfq_mark_cfqq_idle_window(cfqq);
> > + else
> > + cfq_mark_cfqq_sync(cfqq);
>
> Woops, should
On Tue, Apr 24 2007, Jens Axboe wrote:
> - if (key != CFQ_KEY_ASYNC)
> + if (!is_sync)
> cfq_mark_cfqq_idle_window(cfqq);
> + else
> + cfq_mark_cfqq_sync(cfqq);
Woops, should be
if (is_sync) {
cf
On Tue, Apr 24 2007, Jens Axboe wrote:
> On Tue, Apr 24 2007, Vasily Tarasov wrote:
> > From: Vasily Tarasov <[EMAIL PROTECTED]>
> >
> > cfq hash is no more necessary. We always can get cfqq from io context.
> > cfq_get_io_context_noalloc() function is introduced, because we don't want
> > to
>
On Tue, Apr 24 2007, Vasily Tarasov wrote:
> From: Vasily Tarasov <[EMAIL PROTECTED]>
>
> cfq hash is no more necessary. We always can get cfqq from io context.
> cfq_get_io_context_noalloc() function is introduced, because we don't want to
> allocate cic on merging and checking may_queue.
> In o
From: Vasily Tarasov <[EMAIL PROTECTED]>
cfq hash is no more necessary. We always can get cfqq from io context.
cfq_get_io_context_noalloc() function is introduced, because we don't want to
allocate cic on merging and checking may_queue.
In order to identify sync queue we've used hash key = CFQ_K
>> From: Vasily Tarasov <[EMAIL PROTECTED]>
>>
>> cfq hash is no more necessary. We always can get cfqq from io context.
>> cfq_get_io_context_noalloc() function is introduced, because we don't want
>> to
>> allocate cic on merging and checking may_queue.
>> In order to identify sync queue we've
On Tue, Apr 24 2007, Vasily Tarasov wrote:
> From: Vasily Tarasov <[EMAIL PROTECTED]>
>
> cfq hash is no more necessary. We always can get cfqq from io context.
> cfq_get_io_context_noalloc() function is introduced, because we don't want to
> allocate cic on merging and checking may_queue.
> In o
From: Vasily Tarasov <[EMAIL PROTECTED]>
cfq hash is no more necessary. We always can get cfqq from io context.
cfq_get_io_context_noalloc() function is introduced, because we don't want to
allocate cic on merging and checking may_queue.
In order to identify sync queue we've used hash key = CFQ_K
14 matches
Mail list logo
