cfq-iosched: idling on deep seeky sync queues

Seeky sync queues with large depth can gain unfairly big share of disk
 time, at the expense of other seeky queues. This patch ensures that
 idling will be enabled for queues with I/O depth at least 4, and small
 think time. The decision to enable idling is sticky, until an idle
 window times out without seeing a new request.

The reasoning behind the decision is that, if an application is using
large I/O depth, it is already optimized to make full utilization of
the hardware, and therefore we reserve a slice of exclusive use for it.

Reported-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Corrado Zoccolo <czoccolo@gmail.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 2c1086a..15f7238 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -260,6 +260,7 @@
 	CFQ_CFQQ_FLAG_slice_new,	/* no requests dispatched in slice */
 	CFQ_CFQQ_FLAG_sync,		/* synchronous queue */
 	CFQ_CFQQ_FLAG_coop,		/* cfqq is shared */
+	CFQ_CFQQ_FLAG_deep,		/* sync cfqq experienced large depth */
 };
 
 #define CFQ_CFQQ_FNS(name)						\
@@ -286,6 +287,7 @@
 CFQ_CFQQ_FNS(slice_new);
 CFQ_CFQQ_FNS(sync);
 CFQ_CFQQ_FNS(coop);
+CFQ_CFQQ_FNS(deep);
 #undef CFQ_CFQQ_FNS
 
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)	\
@@ -2350,8 +2352,12 @@
 
 	enable_idle = old_idle = cfq_cfqq_idle_window(cfqq);
 
+	if (cfqq->queued[0] + cfqq->queued[1] >= 4)
+		cfq_mark_cfqq_deep(cfqq);
+
 	if (!atomic_read(&cic->ioc->nr_tasks) || !cfqd->cfq_slice_idle ||
-	    (sample_valid(cfqq->seek_samples) && CFQQ_SEEKY(cfqq)))
+	    (!cfq_cfqq_deep(cfqq) && sample_valid(cfqq->seek_samples)
+	     && CFQQ_SEEKY(cfqq)))
 		enable_idle = 0;
 	else if (sample_valid(cic->ttime_samples)) {
 		if (cic->ttime_mean > cfqd->cfq_slice_idle)
@@ -2849,6 +2855,11 @@
 		 */
 		if (!RB_EMPTY_ROOT(&cfqq->sort_list))
 			goto out_kick;
+
+		/*
+		 * Queue depth flag is reset only when the idle didn't succeed
+		 */
+		cfq_clear_cfqq_deep(cfqq);
 	}
 expire:
 	cfq_slice_expired(cfqd, timed_out);