[PATCH 12/23] io-controller: Wait for requests to complete from last queue before new queue is scheduled

From: Vivek Goyal
Date: Fri Aug 28 2009 - 17:35:31 EST

o Currently one can dispatch requests from multiple queues to the disk. This
is true for hardware which supports queuing. So if a disk support queue
depth of 31 it is possible that 20 requests are dispatched from queue 1
and then next queue is scheduled in which dispatches more requests.

o This multiple queue dispatch introduces issues for accurate accounting of
disk time consumed by a particular queue. For example, if one async queue
is scheduled in, it can dispatch 31 requests to the disk and then it will
be expired and a new sync queue might get scheduled in. These 31 requests
might take a long time to finish but this time is never accounted to the
async queue which dispatched these requests.

o This patch introduces the functionality where we wait for all the requests
to finish from previous queue before next queue is scheduled in. That way
a queue is more accurately accounted for disk time it has consumed. Note
this still does not take care of errors introduced by disk write caching.

o Because above behavior can result in reduced throughput, this behavior will
be enabled only if user sets "fairness" tunable to 1.

o This patch helps in achieving more isolation between reads and buffered
writes in different cgroups. buffered writes typically utilize full queue
depth and then expire the queue. On the contarary, sequential reads
typicaly driver queue depth of 1. So despite the fact that writes are
using more disk time it is never accounted to write queue because we don't
wait for requests to finish after dispatching these. This patch helps
do more accurate accounting of disk time, especially for buffered writes
hence providing better fairness hence better isolation between two cgroups
running read and write workloads.

Signed-off-by: Vivek Goyal <vgoyal@xxxxxxxxxx>
block/cfq-iosched.c | 1 +
block/elevator-fq.c | 21 ++++++++++++++++++++-
block/elevator-fq.h | 10 +++++++++-
3 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 11ae473..52c4710 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -2123,6 +2123,7 @@ static struct elv_fs_entry cfq_attrs[] = {
+ ELV_ATTR(fairness),
diff --git a/block/elevator-fq.c b/block/elevator-fq.c
index 6ea5be4..840b73b 100644
--- a/block/elevator-fq.c
+++ b/block/elevator-fq.c
@@ -681,6 +681,8 @@ SHOW_FUNCTION(elv_slice_sync_show, efqd->elv_slice[1], 1);
SHOW_FUNCTION(elv_slice_async_show, efqd->elv_slice[0], 1);
+SHOW_FUNCTION(elv_fairness_show, efqd->fairness, 0);

@@ -705,6 +707,8 @@ STORE_FUNCTION(elv_slice_sync_store, &efqd->elv_slice[1], 1, UINT_MAX, 1);
STORE_FUNCTION(elv_slice_async_store, &efqd->elv_slice[0], 1, UINT_MAX, 1);
+STORE_FUNCTION(elv_fairness_store, &efqd->fairness, 0, 1, 0);

void elv_schedule_dispatch(struct request_queue *q)
@@ -2271,6 +2275,17 @@ void *elv_select_ioq(struct request_queue *q, int force)

+ if (efqd->fairness && !force && ioq && ioq->dispatched) {
+ /*
+ * If there are request dispatched from this queue, don't
+ * dispatch requests from new queue till all the requests from
+ * this queue have completed.
+ */
+ elv_log_ioq(efqd, ioq, "select: wait for requests to finish"
+ " disp=%lu", ioq->dispatched);
+ ioq = NULL;
+ goto keep_queue;
+ }
ioq = elv_set_active_ioq(q, new_ioq);
@@ -2386,6 +2401,10 @@ void elv_ioq_completed_request(struct request_queue *q, struct request *rq)
goto done;

+ /* Wait for requests to finish from this queue */
+ if (efqd->fairness && elv_ioq_nr_dispatched(ioq))
+ goto done;
/* Expire the queue */
goto done;
@@ -2396,7 +2415,7 @@ void elv_ioq_completed_request(struct request_queue *q, struct request *rq)
* If this is the last queue in the group and we did not
* decide to idle on queue, idle on group.
- if (elv_iog_should_idle(ioq) && !ioq->dispatched
+ if (elv_iog_should_idle(ioq) && !elv_ioq_nr_dispatched(ioq)
&& !timer_pending(&efqd->idle_slice_timer)) {
* If queue has used up its slice, wait for the
diff --git a/block/elevator-fq.h b/block/elevator-fq.h
index 0a34c7f..b9f3fc7 100644
--- a/block/elevator-fq.h
+++ b/block/elevator-fq.h
@@ -180,6 +180,12 @@ struct elv_fq_data {

/* Fallback dummy ioq for extreme OOM conditions */
struct io_queue oom_ioq;
+ /*
+ * If set to 1, waits for all request completions from current
+ * queue before new queue is scheduled in
+ */
+ unsigned int fairness;

/* Logging facilities. */
@@ -437,7 +443,9 @@ extern ssize_t elv_slice_sync_store(struct elevator_queue *q, const char *name,
extern ssize_t elv_slice_async_show(struct elevator_queue *q, char *name);
extern ssize_t elv_slice_async_store(struct elevator_queue *q, const char *name,
size_t count);
+extern ssize_t elv_fairness_show(struct elevator_queue *q, char *name);
+extern ssize_t elv_fairness_store(struct elevator_queue *q, const char *name,
+ size_t count);
/* Functions used by elevator.c */
extern struct elv_fq_data *elv_alloc_fq_data(struct request_queue *q,
struct elevator_queue *e);

To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/