Merge branch 'for-2.6.33' of git://git.kernel.dk/linux-2.6-block

* 'for-2.6.33' of git://git.kernel.dk/linux-2.6-block:
  cfq: set workload as expired if it doesn't have any slice left
  Fix a CFQ crash in "for-2.6.33" branch of block tree
  cfq: Remove wait_request flag when idle time is being deleted
  cfq-iosched: commenting non-obvious initialization
  cfq-iosched: Take care of corner cases of group losing share due to deletion
  cfq-iosched: Get rid of cfqq wait_busy_done flag
  cfq: Optimization for close cooperating queue searching
  block,xd: Delay allocation of DMA buffers until device is known
  drbd: Following the hmac change to SHASH (see linux commit 8bd1209cfff)
  cfq-iosched: reduce write depth only if sync was delayed

1 files changed, 75 insertions, 19 deletions

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index cfb0b2f..e2f8046 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -283,7 +283,7 @@ struct cfq_data {
 	 */
 	struct cfq_queue oom_cfqq;
 
-	unsigned long last_end_sync_rq;
+	unsigned long last_delayed_sync;
 
 	/* List of cfq groups being managed on this device*/
 	struct hlist_head cfqg_list;
@@ -319,7 +319,6 @@ enum cfqq_state_flags {
 	CFQ_CFQQ_FLAG_coop,		/* cfqq is shared */
 	CFQ_CFQQ_FLAG_deep,		/* sync cfqq experienced large depth */
 	CFQ_CFQQ_FLAG_wait_busy,	/* Waiting for next request */
-	CFQ_CFQQ_FLAG_wait_busy_done,	/* Got new request. Expire the queue */
 };
 
 #define CFQ_CFQQ_FNS(name)						\
@@ -348,7 +347,6 @@ CFQ_CFQQ_FNS(sync);
 CFQ_CFQQ_FNS(coop);
 CFQ_CFQQ_FNS(deep);
 CFQ_CFQQ_FNS(wait_busy);
-CFQ_CFQQ_FNS(wait_busy_done);
 #undef CFQ_CFQQ_FNS
 
 #ifdef CONFIG_DEBUG_CFQ_IOSCHED
@@ -1574,7 +1572,6 @@ __cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 
 	cfq_clear_cfqq_wait_request(cfqq);
 	cfq_clear_cfqq_wait_busy(cfqq);
-	cfq_clear_cfqq_wait_busy_done(cfqq);
 
 	/*
 	 * store what was left of this slice, if the queue idled/timed out
@@ -1750,6 +1747,12 @@ static struct cfq_queue *cfq_close_cooperator(struct cfq_data *cfqd,
 		return NULL;
 
 	/*
+	 * Don't search priority tree if it's the only queue in the group.
+	 */
+	if (cur_cfqq->cfqg->nr_cfqq == 1)
+		return NULL;
+
+	/*
 	 * We should notice if some of the queues are cooperating, eg
 	 * working closely on the same area of the disk. In that case,
 	 * we can group them together and don't waste time idling.
@@ -2110,7 +2113,9 @@ static void cfq_choose_cfqg(struct cfq_data *cfqd)
 		cfqd->workload_expires = jiffies + cfqg->saved_workload_slice;
 		cfqd->serving_type = cfqg->saved_workload;
 		cfqd->serving_prio = cfqg->saved_serving_prio;
-	}
+	} else
+		cfqd->workload_expires = jiffies - 1;
+
 	choose_service_tree(cfqd, cfqg);
 }
 
@@ -2128,14 +2133,35 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 
 	if (!cfqd->rq_queued)
 		return NULL;
+
 	/*
-	 * The active queue has run out of time, expire it and select new.
+	 * We were waiting for group to get backlogged. Expire the queue
 	 */
-	if ((cfq_slice_used(cfqq) || cfq_cfqq_wait_busy_done(cfqq))
-	     && !cfq_cfqq_must_dispatch(cfqq))
+	if (cfq_cfqq_wait_busy(cfqq) && !RB_EMPTY_ROOT(&cfqq->sort_list))
 		goto expire;
 
 	/*
+	 * The active queue has run out of time, expire it and select new.
+	 */
+	if (cfq_slice_used(cfqq) && !cfq_cfqq_must_dispatch(cfqq)) {
+		/*
+		 * If slice had not expired at the completion of last request
+		 * we might not have turned on wait_busy flag. Don't expire
+		 * the queue yet. Allow the group to get backlogged.
+		 *
+		 * The very fact that we have used the slice, that means we
+		 * have been idling all along on this queue and it should be
+		 * ok to wait for this request to complete.
+		 */
+		if (cfqq->cfqg->nr_cfqq == 1 && RB_EMPTY_ROOT(&cfqq->sort_list)
+		    && cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
+			cfqq = NULL;
+			goto keep_queue;
+		} else
+			goto expire;
+	}
+
+	/*
 	 * The active queue has requests and isn't expired, allow it to
 	 * dispatch.
 	 */
@@ -2264,7 +2290,7 @@ static bool cfq_may_dispatch(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	 * based on the last sync IO we serviced
 	 */
 	if (!cfq_cfqq_sync(cfqq) && cfqd->cfq_latency) {
-		unsigned long last_sync = jiffies - cfqd->last_end_sync_rq;
+		unsigned long last_sync = jiffies - cfqd->last_delayed_sync;
 		unsigned int depth;
 
 		depth = last_sync / cfqd->cfq_slice[1];
@@ -3165,10 +3191,6 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 	cfqq->last_request_pos = blk_rq_pos(rq) + blk_rq_sectors(rq);
 
 	if (cfqq == cfqd->active_queue) {
-		if (cfq_cfqq_wait_busy(cfqq)) {
-			cfq_clear_cfqq_wait_busy(cfqq);
-			cfq_mark_cfqq_wait_busy_done(cfqq);
-		}
 		/*
 		 * Remember that we saw a request from this process, but
 		 * don't start queuing just yet. Otherwise we risk seeing lots
@@ -3183,6 +3205,7 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq,
 			if (blk_rq_bytes(rq) > PAGE_CACHE_SIZE ||
 			    cfqd->busy_queues > 1) {
 				del_timer(&cfqd->idle_slice_timer);
+				cfq_clear_cfqq_wait_request(cfqq);
 				__blk_run_queue(cfqd->queue);
 			} else
 				cfq_mark_cfqq_must_dispatch(cfqq);
@@ -3251,6 +3274,35 @@ static void cfq_update_hw_tag(struct cfq_data *cfqd)
 		cfqd->hw_tag = 0;
 }
 
+static bool cfq_should_wait_busy(struct cfq_data *cfqd, struct cfq_queue *cfqq)
+{
+	struct cfq_io_context *cic = cfqd->active_cic;
+
+	/* If there are other queues in the group, don't wait */
+	if (cfqq->cfqg->nr_cfqq > 1)
+		return false;
+
+	if (cfq_slice_used(cfqq))
+		return true;
+
+	/* if slice left is less than think time, wait busy */
+	if (cic && sample_valid(cic->ttime_samples)
+	    && (cfqq->slice_end - jiffies < cic->ttime_mean))
+		return true;
+
+	/*
+	 * If think times is less than a jiffy than ttime_mean=0 and above
+	 * will not be true. It might happen that slice has not expired yet
+	 * but will expire soon (4-5 ns) during select_queue(). To cover the
+	 * case where think time is less than a jiffy, mark the queue wait
+	 * busy if only 1 jiffy is left in the slice.
+	 */
+	if (cfqq->slice_end - jiffies == 1)
+		return true;
+
+	return false;
+}
+
 static void cfq_completed_request(struct request_queue *q, struct request *rq)
 {
 	struct cfq_queue *cfqq = RQ_CFQQ(rq);
@@ -3273,7 +3325,8 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 
 	if (sync) {
 		RQ_CIC(rq)->last_end_request = now;
-		cfqd->last_end_sync_rq = now;
+		if (!time_after(rq->start_time + cfqd->cfq_fifo_expire[1], now))
+			cfqd->last_delayed_sync = now;
 	}
 
 	/*
@@ -3289,11 +3342,10 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		}
 
 		/*
-		 * If this queue consumed its slice and this is last queue
-		 * in the group, wait for next request before we expire
-		 * the queue
+		 * Should we wait for next request to come in before we expire
+		 * the queue.
 		 */
-		if (cfq_slice_used(cfqq) && cfqq->cfqg->nr_cfqq == 1) {
+		if (cfq_should_wait_busy(cfqd, cfqq)) {
 			cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
 			cfq_mark_cfqq_wait_busy(cfqq);
 		}
@@ -3711,7 +3763,11 @@ static void *cfq_init_queue(struct request_queue *q)
 	cfqd->cfq_latency = 1;
 	cfqd->cfq_group_isolation = 0;
 	cfqd->hw_tag = -1;
-	cfqd->last_end_sync_rq = jiffies;
+	/*
+	 * we optimistically start assuming sync ops weren't delayed in last
+	 * second, in order to have larger depth for async operations.
+	 */
+	cfqd->last_delayed_sync = jiffies - HZ;
 	INIT_RCU_HEAD(&cfqd->rcu);
 	return cfqd;
 }