A-Team_Digital_Solutions/android_kernel_motorola_sm6375
Watch
2
0
Fork
You've already forked android_kernel_motorola_sm6375
 0
mirror of https://github.com/BobTheBlinker/android_kernel_motorola_sm6375.git synced 2026-10-28 10:41:38 -04:00
Code Issues Projects Releases Packages Wiki Activity

block: strict rq_affinity

Browse source 
Some systems benefit from completions always being steered to the strict
requester cpu rather than the looser "per-socket" steering that
blk_cpu_to_group() attempts by default. This is because the first
CPU in the group mask ends up being completely overloaded with work,
while the others (including the original submitter) has power left
to spare.

Allow the strict mode to be set by writing '2' to the sysfs control
file. This is identical to the scheme used for the nomerges file,
where '2' is a more aggressive setting than just being turned on.

echo 2 > /sys/block/<bdev>/queue/rq_affinity

Cc: Christoph Hellwig <[email protected]>
Cc: Roland Dreier <[email protected]>
Tested-by: Dave Jiang <[email protected]>
Signed-off-by: Dan Williams <[email protected]>
Signed-off-by: Jens Axboe <[email protected]>
This commit is contained in:
Dan Williams 2011-07-23 20:44:25 +02:00 • committed by Jens Axboe
commit 5757a6d76c
5 changed files with 27 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

13
block/blk-sysfs.c
View file

@ -244,8 +244,9 @@ static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
static ssize_t queue_rq_affinity_show(struct request_queue *q, char *page)
{
bool set = test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags);
bool force = test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags);
return queue_var_show(set, page);
return queue_var_show(set << force, page);
}
static ssize_t
@ -257,10 +258,14 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
ret = queue_var_store(&val, page, count);
spin_lock_irq(q->queue_lock);
if (val)
if (val) {
queue_flag_set(QUEUE_FLAG_SAME_COMP, q);
else
queue_flag_clear(QUEUE_FLAG_SAME_COMP, q);
if (val == 2)
queue_flag_set(QUEUE_FLAG_SAME_FORCE, q);
} else {
queue_flag_clear(QUEUE_FLAG_SAME_COMP, q);
queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q);
}
spin_unlock_irq(q->queue_lock);
#endif
return ret;