* [patch]block cfq: select new workload if priority changed
@ 2010-12-09 5:17 Shaohua Li
2010-12-10 14:56 ` Jeff Moyer
0 siblings, 1 reply; 4+ messages in thread
From: Shaohua Li @ 2010-12-09 5:17 UTC (permalink / raw)
To: lkml; +Cc: Jens Axboe, czoccolo
If priority is changed, continue checking workload_expires and service tree
count of previous workload is meaningless. We should always choose the workload
with lowest key of new priority in such case.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
---
block/cfq-iosched.c | 5 +++++
1 file changed, 5 insertions(+)
Index: linux/block/cfq-iosched.c
===================================================================
--- linux.orig/block/cfq-iosched.c 2010-12-08 19:39:01.000000000 +0800
+++ linux/block/cfq-iosched.c 2010-12-09 10:27:24.000000000 +0800
@@ -2116,6 +2116,7 @@ static void choose_service_tree(struct c
unsigned count;
struct cfq_rb_root *st;
unsigned group_slice;
+ enum wl_prio_t original_prio = cfqd->serving_prio;
if (!cfqg) {
cfqd->serving_prio = IDLE_WORKLOAD;
@@ -2134,6 +2135,9 @@ static void choose_service_tree(struct c
return;
}
+ if (original_prio != cfqd->serving_prio)
+ goto new_workload;
+
/*
* For RT and BE, we have to choose also the type
* (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload
@@ -2148,6 +2152,7 @@ static void choose_service_tree(struct c
if (count && !time_after(jiffies, cfqd->workload_expires))
return;
+new_workload:
/* otherwise select new workload type */
cfqd->serving_type =
cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio);
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [patch]block cfq: select new workload if priority changed
2010-12-09 5:17 [patch]block cfq: select new workload if priority changed Shaohua Li
@ 2010-12-10 14:56 ` Jeff Moyer
2010-12-13 0:39 ` Shaohua Li
0 siblings, 1 reply; 4+ messages in thread
From: Jeff Moyer @ 2010-12-10 14:56 UTC (permalink / raw)
To: Shaohua Li; +Cc: lkml, Jens Axboe, czoccolo
Shaohua Li <shaohua.li@intel.com> writes:
> If priority is changed, continue checking workload_expires and service tree
> count of previous workload is meaningless. We should always choose the workload
I'd change that first sentence to:
If priority is changed, continuing to check workload_expires and
service tree count of the previous workload does not make sense.
> with lowest key of new priority in such case.
>
> Signed-off-by: Shaohua Li <shaohua.li@intel.com>
This makes sense to me.
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [patch]block cfq: select new workload if priority changed
2010-12-10 14:56 ` Jeff Moyer
@ 2010-12-13 0:39 ` Shaohua Li
2010-12-13 13:32 ` Jens Axboe
0 siblings, 1 reply; 4+ messages in thread
From: Shaohua Li @ 2010-12-13 0:39 UTC (permalink / raw)
To: Jeff Moyer; +Cc: lkml, Jens Axboe, czoccolo
On Fri, 2010-12-10 at 22:56 +0800, Jeff Moyer wrote:
> Shaohua Li <shaohua.li@intel.com> writes:
>
> > If priority is changed, continue checking workload_expires and service tree
> > count of previous workload is meaningless. We should always choose the workload
>
> I'd change that first sentence to:
>
> If priority is changed, continuing to check workload_expires and
> service tree count of the previous workload does not make sense.
>
> > with lowest key of new priority in such case.
> >
> > Signed-off-by: Shaohua Li <shaohua.li@intel.com>
>
> This makes sense to me.
>
> Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Thanks, modified the the changelog.
If priority is changed, continuing to check workload_expires and service tree
count of the previous workload does not make sense. We should always choose
the workload with lowest key of new priority in such case.
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
---
block/cfq-iosched.c | 5 +++++
1 file changed, 5 insertions(+)
Index: linux/block/cfq-iosched.c
===================================================================
--- linux.orig/block/cfq-iosched.c 2010-12-08 19:39:01.000000000 +0800
+++ linux/block/cfq-iosched.c 2010-12-09 10:27:24.000000000 +0800
@@ -2116,6 +2116,7 @@ static void choose_service_tree(struct c
unsigned count;
struct cfq_rb_root *st;
unsigned group_slice;
+ enum wl_prio_t original_prio = cfqd->serving_prio;
if (!cfqg) {
cfqd->serving_prio = IDLE_WORKLOAD;
@@ -2134,6 +2135,9 @@ static void choose_service_tree(struct c
return;
}
+ if (original_prio != cfqd->serving_prio)
+ goto new_workload;
+
/*
* For RT and BE, we have to choose also the type
* (SYNC, SYNC_NOIDLE, ASYNC), and to compute a workload
@@ -2148,6 +2152,7 @@ static void choose_service_tree(struct c
if (count && !time_after(jiffies, cfqd->workload_expires))
return;
+new_workload:
/* otherwise select new workload type */
cfqd->serving_type =
cfq_choose_wl(cfqd, cfqg, cfqd->serving_prio);
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [patch]block cfq: select new workload if priority changed
2010-12-13 0:39 ` Shaohua Li
@ 2010-12-13 13:32 ` Jens Axboe
0 siblings, 0 replies; 4+ messages in thread
From: Jens Axboe @ 2010-12-13 13:32 UTC (permalink / raw)
To: Shaohua Li; +Cc: Jeff Moyer, lkml, czoccolo
On 2010-12-13 01:39, Shaohua Li wrote:
> On Fri, 2010-12-10 at 22:56 +0800, Jeff Moyer wrote:
>> Shaohua Li <shaohua.li@intel.com> writes:
>>
>>> If priority is changed, continue checking workload_expires and service tree
>>> count of previous workload is meaningless. We should always choose the workload
>>
>> I'd change that first sentence to:
>>
>> If priority is changed, continuing to check workload_expires and
>> service tree count of the previous workload does not make sense.
>>
>>> with lowest key of new priority in such case.
>>>
>>> Signed-off-by: Shaohua Li <shaohua.li@intel.com>
>>
>> This makes sense to me.
>>
>> Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
> Thanks, modified the the changelog.
Thanks, applied to for-2.6.38/core
--
Jens Axboe
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2010-12-13 13:32 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2010-12-09 5:17 [patch]block cfq: select new workload if priority changed Shaohua Li
2010-12-10 14:56 ` Jeff Moyer
2010-12-13 0:39 ` Shaohua Li
2010-12-13 13:32 ` Jens Axboe
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.