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

Pull more block layer updates from Jens Axboe: "A followup pull request, with some parts that either needed a bit more testing before going in, merge sync, or just later arriving fixes. This contains: - Timer related updates from Kees. These were purposefully delayed since I didn't want to pull in a later v4.14-rc tag to my block tree. - ide-cd prep sense buffer fix from Bart. Also delayed, as not to clash with the late fix we put into 4.14-rc. - Small BFQ updates series from Luca and Paolo. - Single nvmet fix from James, fixing a non-functional case there. - Bio fast clone fix from Michael, which made bcache return the wrong data for some cases. - Legacy IO path regression hang fix from Ming" * 'for-linus' of git://git.kernel.dk/linux-block: bio: ensure __bio_clone_fast copies bi_partno nvmet_fc: fix better length checking block: wake up all tasks blocked in get_request() block, bfq: move debug blkio stats behind CONFIG_DEBUG_BLK_CGROUP block, bfq: update blkio stats outside the scheduler lock block, bfq: add missing invocations of bfqg_stats_update_io_add/remove doc, block, bfq: update max IOPS sustainable with BFQ ide: Make ide_cdrom_prep_fs() initialize the sense buffer pointer md: Convert timers to use timer_setup() block: swim3: Convert timers to use timer_setup() block/aoe: Convert timers to use timer_setup() amifloppy: Convert timers to use timer_setup() block/floppy: Convert callback to pass timer_list
chewitt · Nov 17, 2017 · 06ede5f · 06ede5f
2 parents a3841f9 + 62530ed
commit 06ede5f
Show file tree

Hide file tree

Showing 19 changed files with 311 additions and 166 deletions.
diff --git a/Documentation/block/bfq-iosched.txt b/Documentation/block/bfq-iosched.txt
@@ -20,12 +20,27 @@ for that device, by setting low_latency to 0. See Section 3 for
 details on how to configure BFQ for the desired tradeoff between
 latency and throughput, or on how to maximize throughput.
 
-On average CPUs, the current version of BFQ can handle devices
-performing at most ~30K IOPS; at most ~50 KIOPS on faster CPUs. As a
-reference, 30-50 KIOPS correspond to very high bandwidths with
-sequential I/O (e.g., 8-12 GB/s if I/O requests are 256 KB large), and
-to 120-200 MB/s with 4KB random I/O. BFQ is currently being tested on
-multi-queue devices too.
+BFQ has a non-null overhead, which limits the maximum IOPS that a CPU
+can process for a device scheduled with BFQ. To give an idea of the
+limits on slow or average CPUs, here are, first, the limits of BFQ for
+three different CPUs, on, respectively, an average laptop, an old
+desktop, and a cheap embedded system, in case full hierarchical
+support is enabled (i.e., CONFIG_BFQ_GROUP_IOSCHED is set), but
+CONFIG_DEBUG_BLK_CGROUP is not set (Section 4-2):
+- Intel i7-4850HQ: 400 KIOPS
+- AMD A8-3850: 250 KIOPS
+- ARM CortexTM-A53 Octa-core: 80 KIOPS
+
+If CONFIG_DEBUG_BLK_CGROUP is set (and of course full hierarchical
+support is enabled), then the sustainable throughput with BFQ
+decreases, because all blkio.bfq* statistics are created and updated
+(Section 4-2). For BFQ, this leads to the following maximum
+sustainable throughputs, on the same systems as above:
+- Intel i7-4850HQ: 310 KIOPS
+- AMD A8-3850: 200 KIOPS
+- ARM CortexTM-A53 Octa-core: 56 KIOPS
+
+BFQ works for multi-queue devices too.
 
 The table of contents follow. Impatients can just jump to Section 3.
 
@@ -500,6 +515,22 @@ BFQ-specific files is "blkio.bfq." or "io.bfq." For example, the group
 parameter to set the weight of a group with BFQ is blkio.bfq.weight
 or io.bfq.weight.
 
+As for cgroups-v1 (blkio controller), the exact set of stat files
+created, and kept up-to-date by bfq, depends on whether
+CONFIG_DEBUG_BLK_CGROUP is set. If it is set, then bfq creates all
+the stat files documented in
+Documentation/cgroup-v1/blkio-controller.txt. If, instead,
+CONFIG_DEBUG_BLK_CGROUP is not set, then bfq creates only the files
+blkio.bfq.io_service_bytes
+blkio.bfq.io_service_bytes_recursive
+blkio.bfq.io_serviced
+blkio.bfq.io_serviced_recursive
+
+The value of CONFIG_DEBUG_BLK_CGROUP greatly influences the maximum
+throughput sustainable with bfq, because updating the blkio.bfq.*
+stats is rather costly, especially for some of the stats enabled by
+CONFIG_DEBUG_BLK_CGROUP.
+
 Parameters to set
 -----------------
 

diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
@@ -24,7 +24,7 @@
 
 #include "bfq-iosched.h"
 
-#ifdef CONFIG_BFQ_GROUP_IOSCHED
+#if defined(CONFIG_BFQ_GROUP_IOSCHED) &&  defined(CONFIG_DEBUG_BLK_CGROUP)
 
 /* bfqg stats flags */
 enum bfqg_stats_flags {
@@ -152,6 +152,57 @@ void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg)
 	bfqg_stats_update_group_wait_time(stats);
 }
 
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+			      unsigned int op)
+{
+	blkg_rwstat_add(&bfqg->stats.queued, op, 1);
+	bfqg_stats_end_empty_time(&bfqg->stats);
+	if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue))
+		bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq));
+}
+
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op)
+{
+	blkg_rwstat_add(&bfqg->stats.queued, op, -1);
+}
+
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
+{
+	blkg_rwstat_add(&bfqg->stats.merged, op, 1);
+}
+
+void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
+				  uint64_t io_start_time, unsigned int op)
+{
+	struct bfqg_stats *stats = &bfqg->stats;
+	unsigned long long now = sched_clock();
+
+	if (time_after64(now, io_start_time))
+		blkg_rwstat_add(&stats->service_time, op,
+				now - io_start_time);
+	if (time_after64(io_start_time, start_time))
+		blkg_rwstat_add(&stats->wait_time, op,
+				io_start_time - start_time);
+}
+
+#else /* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
+
+void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
+			      unsigned int op) { }
+void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
+void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
+void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
+				  uint64_t io_start_time, unsigned int op) { }
+void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
+void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
+void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
+void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { }
+void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { }
+
+#endif /* CONFIG_BFQ_GROUP_IOSCHED && CONFIG_DEBUG_BLK_CGROUP */
+
+#ifdef CONFIG_BFQ_GROUP_IOSCHED
+
 /*
  * blk-cgroup policy-related handlers
  * The following functions help in converting between blk-cgroup
@@ -229,42 +280,10 @@ void bfqg_and_blkg_put(struct bfq_group *bfqg)
 	blkg_put(bfqg_to_blkg(bfqg));
 }
 
-void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
-			      unsigned int op)
-{
-	blkg_rwstat_add(&bfqg->stats.queued, op, 1);
-	bfqg_stats_end_empty_time(&bfqg->stats);
-	if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue))
-		bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq));
-}
-
-void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op)
-{
-	blkg_rwstat_add(&bfqg->stats.queued, op, -1);
-}
-
-void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op)
-{
-	blkg_rwstat_add(&bfqg->stats.merged, op, 1);
-}
-
-void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
-				  uint64_t io_start_time, unsigned int op)
-{
-	struct bfqg_stats *stats = &bfqg->stats;
-	unsigned long long now = sched_clock();
-
-	if (time_after64(now, io_start_time))
-		blkg_rwstat_add(&stats->service_time, op,
-				now - io_start_time);
-	if (time_after64(io_start_time, start_time))
-		blkg_rwstat_add(&stats->wait_time, op,
-				io_start_time - start_time);
-}
-
 /* @stats = 0 */
 static void bfqg_stats_reset(struct bfqg_stats *stats)
 {
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	/* queued stats shouldn't be cleared */
 	blkg_rwstat_reset(&stats->merged);
 	blkg_rwstat_reset(&stats->service_time);
@@ -276,6 +295,7 @@ static void bfqg_stats_reset(struct bfqg_stats *stats)
 	blkg_stat_reset(&stats->group_wait_time);
 	blkg_stat_reset(&stats->idle_time);
 	blkg_stat_reset(&stats->empty_time);
+#endif
 }
 
 /* @to += @from */
@@ -284,6 +304,7 @@ static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from)
 	if (!to || !from)
 		return;
 
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	/* queued stats shouldn't be cleared */
 	blkg_rwstat_add_aux(&to->merged, &from->merged);
 	blkg_rwstat_add_aux(&to->service_time, &from->service_time);
@@ -296,6 +317,7 @@ static void bfqg_stats_add_aux(struct bfqg_stats *to, struct bfqg_stats *from)
 	blkg_stat_add_aux(&to->group_wait_time, &from->group_wait_time);
 	blkg_stat_add_aux(&to->idle_time, &from->idle_time);
 	blkg_stat_add_aux(&to->empty_time, &from->empty_time);
+#endif
 }
 
 /*
@@ -342,6 +364,7 @@ void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg)
 
 static void bfqg_stats_exit(struct bfqg_stats *stats)
 {
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	blkg_rwstat_exit(&stats->merged);
 	blkg_rwstat_exit(&stats->service_time);
 	blkg_rwstat_exit(&stats->wait_time);
@@ -353,10 +376,12 @@ static void bfqg_stats_exit(struct bfqg_stats *stats)
 	blkg_stat_exit(&stats->group_wait_time);
 	blkg_stat_exit(&stats->idle_time);
 	blkg_stat_exit(&stats->empty_time);
+#endif
 }
 
 static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
 {
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 	if (blkg_rwstat_init(&stats->merged, gfp) ||
 	    blkg_rwstat_init(&stats->service_time, gfp) ||
 	    blkg_rwstat_init(&stats->wait_time, gfp) ||
@@ -371,6 +396,7 @@ static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
 		bfqg_stats_exit(stats);
 		return -ENOMEM;
 	}
+#endif
 
 	return 0;
 }
@@ -887,6 +913,7 @@ static ssize_t bfq_io_set_weight(struct kernfs_open_file *of,
 	return bfq_io_set_weight_legacy(of_css(of), NULL, weight);
 }
 
+#ifdef CONFIG_DEBUG_BLK_CGROUP
 static int bfqg_print_stat(struct seq_file *sf, void *v)
 {
 	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)), blkg_prfill_stat,
@@ -991,6 +1018,7 @@ static int bfqg_print_avg_queue_size(struct seq_file *sf, void *v)
 			  0, false);
 	return 0;
 }
+#endif /* CONFIG_DEBUG_BLK_CGROUP */
 
 struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node)
 {
@@ -1028,15 +1056,6 @@ struct cftype bfq_blkcg_legacy_files[] = {
 	},
 
 	/* statistics, covers only the tasks in the bfqg */
-	{
-		.name = "bfq.time",
-		.private = offsetof(struct bfq_group, stats.time),
-		.seq_show = bfqg_print_stat,
-	},
-	{
-		.name = "bfq.sectors",
-		.seq_show = bfqg_print_stat_sectors,
-	},
 	{
 		.name = "bfq.io_service_bytes",
 		.private = (unsigned long)&blkcg_policy_bfq,
@@ -1047,6 +1066,16 @@ struct cftype bfq_blkcg_legacy_files[] = {
 		.private = (unsigned long)&blkcg_policy_bfq,
 		.seq_show = blkg_print_stat_ios,
 	},
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+	{
+		.name = "bfq.time",
+		.private = offsetof(struct bfq_group, stats.time),
+		.seq_show = bfqg_print_stat,
+	},
+	{
+		.name = "bfq.sectors",
+		.seq_show = bfqg_print_stat_sectors,
+	},
 	{
 		.name = "bfq.io_service_time",
 		.private = offsetof(struct bfq_group, stats.service_time),
@@ -1067,17 +1096,9 @@ struct cftype bfq_blkcg_legacy_files[] = {
 		.private = offsetof(struct bfq_group, stats.queued),
 		.seq_show = bfqg_print_rwstat,
 	},
+#endif /* CONFIG_DEBUG_BLK_CGROUP */
 
 	/* the same statictics which cover the bfqg and its descendants */
-	{
-		.name = "bfq.time_recursive",
-		.private = offsetof(struct bfq_group, stats.time),
-		.seq_show = bfqg_print_stat_recursive,
-	},
-	{
-		.name = "bfq.sectors_recursive",
-		.seq_show = bfqg_print_stat_sectors_recursive,
-	},
 	{
 		.name = "bfq.io_service_bytes_recursive",
 		.private = (unsigned long)&blkcg_policy_bfq,
@@ -1088,6 +1109,16 @@ struct cftype bfq_blkcg_legacy_files[] = {
 		.private = (unsigned long)&blkcg_policy_bfq,
 		.seq_show = blkg_print_stat_ios_recursive,
 	},
+#ifdef CONFIG_DEBUG_BLK_CGROUP
+	{
+		.name = "bfq.time_recursive",
+		.private = offsetof(struct bfq_group, stats.time),
+		.seq_show = bfqg_print_stat_recursive,
+	},
+	{
+		.name = "bfq.sectors_recursive",
+		.seq_show = bfqg_print_stat_sectors_recursive,
+	},
 	{
 		.name = "bfq.io_service_time_recursive",
 		.private = offsetof(struct bfq_group, stats.service_time),
@@ -1132,6 +1163,7 @@ struct cftype bfq_blkcg_legacy_files[] = {
 		.private = offsetof(struct bfq_group, stats.dequeue),
 		.seq_show = bfqg_print_stat,
 	},
+#endif	/* CONFIG_DEBUG_BLK_CGROUP */
 	{ }	/* terminate */
 };
 
@@ -1147,18 +1179,6 @@ struct cftype bfq_blkg_files[] = {
 
 #else	/* CONFIG_BFQ_GROUP_IOSCHED */
 
-void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
-			      unsigned int op) { }
-void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { }
-void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { }
-void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
-				  uint64_t io_start_time, unsigned int op) { }
-void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { }
-void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { }
-void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { }
-void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg) { }
-void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) { }
-
 void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		   struct bfq_group *bfqg) {}