[PATCH 22/25] io-controller: Per io group bdi congestion interface

[Vivek Goyal]

o So far there used to be only one pair or queue  of request descriptors
  (one for sync and one for async) per device and number of requests allocated
  used to decide whether associated bdi is congested or not.

  Now with per io group request descriptor infrastructure, there is a pair
  of request descriptor queue per io group per device. So it might happen
  that overall request queue is not congested but a particular io group
  bio belongs to is congested.

  Or, it could be otherwise that group is not congested but overall queue
  is congested. This can happen if user has not properly set the request
  descriptors limits for queue and groups.
  (q->nr_requests < nr_groups * q->nr_group_requests)

  Hence there is a need for new interface which can query deivce congestion
  status per group. This group is determined by the "struct page" IO will be
  done for. If page is null, then group is determined from the current task
  context.

o This patch introduces new set of function bdi_*_congested_group(), which
  take "struct page" as addition argument. These functions will call the
  block layer and in trun elevator to find out if the io group the page will
  go into is congested or not.

o Currently I have introduced the core functions and migrated most of the users.
  But there might be still some left. This is an ongoing TODO item.

o There are some io_get_io_group() related changes which should be pushed into
  higher patches. Still testing this patch. Will push these changes up in next
  posting.

Signed-off-by: Vivek Goyal <vgoyal@xxxxxxxxxx>
---
 block/blk-core.c            |   21 ++++++++++++++
 block/elevator-fq.c         |   58 ++++++++++++++++++++++++++++++++++++++++
 block/elevator-fq.h         |    6 ++++
 drivers/md/dm-table.c       |   11 +++++---
 drivers/md/dm.c             |    7 +++--
 drivers/md/dm.h             |    3 +-
 drivers/md/linear.c         |    7 +++-
 drivers/md/multipath.c      |    7 +++-
 drivers/md/raid0.c          |    6 +++-
 drivers/md/raid1.c          |    9 ++++--
 drivers/md/raid10.c         |    6 +++-
 drivers/md/raid5.c          |    2 +-
 fs/afs/write.c              |    8 +++++-
 fs/btrfs/disk-io.c          |    6 +++-
 fs/btrfs/extent_io.c        |   12 ++++++++
 fs/btrfs/volumes.c          |    8 ++++-
 fs/cifs/file.c              |   11 +++++++
 fs/ext2/ialloc.c            |    2 +-
 fs/gfs2/aops.c              |   12 ++++++++
 fs/nilfs2/segbuf.c          |    3 +-
 fs/xfs/linux-2.6/xfs_aops.c |    2 +-
 fs/xfs/linux-2.6/xfs_buf.c  |    2 +-
 include/linux/backing-dev.h |   61 ++++++++++++++++++++++++++++++++++++++++-
 include/linux/blkdev.h      |    5 +++
 mm/backing-dev.c            |   62 +++++++++++++++++++++++++++++++++++++++++++
 mm/page-writeback.c         |   11 +++++++
 mm/readahead.c              |    2 +-
 27 files changed, 318 insertions(+), 32 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 2035c20..79fe6a9 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -90,6 +90,27 @@ void blk_queue_congestion_threshold(struct request_queue *q)
 	q->nr_congestion_off = nr;
 }
 
+#ifdef CONFIG_GROUP_IOSCHED
+int blk_queue_io_group_congested(struct backing_dev_info *bdi, int bdi_bits,
+					struct page *page)
+{
+	int ret = 0;
+	struct request_queue *q = bdi->unplug_io_data;
+
+	if (!q && !q->elevator)
+		return bdi_congested(bdi, bdi_bits);
+
+	/* Do we need to hold queue lock? */
+	if (bdi_bits & (1 << BDI_sync_congested))
+		ret |= elv_io_group_congested(q, page, 1);
+
+	if (bdi_bits & (1 << BDI_async_congested))
+		ret |= elv_io_group_congested(q, page, 0);
+
+	return ret;
+}
+#endif
+
 /**
  * blk_get_backing_dev_info - get the address of a queue's backing_dev_info
  * @bdev:	device
diff --git a/block/elevator-fq.c b/block/elevator-fq.c
index c4a2b1e..2a2b68d 100644
--- a/block/elevator-fq.c
+++ b/block/elevator-fq.c
@@ -1102,6 +1102,58 @@ struct request_list *io_group_get_request_list(struct request_queue *q,
 	return &iog->rl;
 }
 
+/* Set io group congestion on and off thresholds */
+void elv_io_group_congestion_threshold(struct request_queue *q,
+						struct io_group *iog)
+{
+	int nr;
+
+	nr = q->nr_group_requests - (q->nr_group_requests / 8) + 1;
+	if (nr > q->nr_group_requests)
+		nr = q->nr_group_requests;
+	iog->nr_congestion_on = nr;
+
+	nr = q->nr_group_requests - (q->nr_group_requests / 8)
+			- (q->nr_group_requests / 16) - 1;
+	if (nr < 1)
+		nr = 1;
+	iog->nr_congestion_off = nr;
+}
+
+static inline int elv_is_iog_congested(struct request_queue *q,
+					struct io_group *iog, int sync)
+{
+	if (iog->rl.count[sync] >= iog->nr_congestion_on)
+		return 1;
+	return 0;
+}
+
+/* Determine if io group page maps to is congested or not */
+int elv_io_group_congested(struct request_queue *q, struct page *page, int sync)
+{
+	struct io_group *iog;
+	int ret = 0;
+
+	rcu_read_lock();
+
+	iog = io_get_io_group(q, page, 0);
+
+	if (!iog) {
+		/*
+		 * Either cgroup got deleted or this is first request in the
+		 * group and associated io group object has not been created
+		 * yet. Map it to root group.
+		 *
+		 * TODO: Fix the case of group not created yet.
+		 */
+		iog = q->elevator->efqd.root_group;
+	}
+
+	ret = elv_is_iog_congested(q, iog, sync);
+	rcu_read_unlock();
+	return ret;
+}
+
 /*
  * Search the io_group for efqd into the hash table (by now only a list)
  * of bgrp.  Must be called under rcu_read_lock().
@@ -1401,6 +1453,7 @@ io_group_chain_alloc(struct request_queue *q, void *key, struct cgroup *cgroup)
 		elv_get_iog(iog);
 
 		blk_init_request_list(&iog->rl);
+		elv_io_group_congestion_threshold(q, iog);
 
 		if (leaf == NULL) {
 			leaf = iog;
@@ -1680,6 +1733,7 @@ static struct io_group *io_alloc_root_group(struct request_queue *q,
 		iog->sched_data.service_tree[i] = IO_SERVICE_TREE_INIT;
 
 	blk_init_request_list(&iog->rl);
+	elv_io_group_congestion_threshold(q, iog);
 
 	iocg = &io_root_cgroup;
 	spin_lock_irq(&iocg->lock);
@@ -1688,6 +1742,10 @@ static struct io_group *io_alloc_root_group(struct request_queue *q,
 	iog->iocg_id = css_id(&iocg->css);
 	spin_unlock_irq(&iocg->lock);
 
+#ifdef CONFIG_DEBUG_GROUP_IOSCHED
+	io_group_path(iog, iog->path, sizeof(iog->path));
+#endif
+
 	return iog;
 }
 
diff --git a/block/elevator-fq.h b/block/elevator-fq.h
index 74a7393..214fb61 100644
--- a/block/elevator-fq.h
+++ b/block/elevator-fq.h
@@ -259,6 +259,10 @@ struct io_group {
 	/* Single ioq per group, used for noop, deadline, anticipatory */
 	struct io_queue *ioq;
 
+	/* io group congestion on and off threshold for request descriptors */
+	unsigned int nr_congestion_on;
+	unsigned int nr_congestion_off;
+
 	/* request list associated with the group */
 	struct request_list rl;
 };
@@ -531,6 +535,8 @@ extern struct io_queue *elv_lookup_ioq_bio(struct request_queue *q,
 						struct bio *bio);
 extern struct request_list *io_group_get_request_list(struct request_queue *q,
 						struct bio *bio);
+extern int elv_io_group_congested(struct request_queue *q, struct page *page,
+					int sync);
 
 /* Sets the single ioq associated with the io group. (noop, deadline, AS) */
 static inline void io_group_set_ioq(struct io_group *iog, struct io_queue *ioq)
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 4899ebe..e3fd6d8 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1175,7 +1175,8 @@ int dm_table_resume_targets(struct dm_table *t)
 	return 0;
 }
 
-int dm_table_any_congested(struct dm_table *t, int bdi_bits)
+int dm_table_any_congested(struct dm_table *t, int bdi_bits, struct page *page,
+				int group)
 {
 	struct dm_dev_internal *dd;
 	struct list_head *devices = dm_table_get_devices(t);
@@ -1185,9 +1186,11 @@ int dm_table_any_congested(struct dm_table *t, int bdi_bits)
 		struct request_queue *q = bdev_get_queue(dd->dm_dev.bdev);
 		char b[BDEVNAME_SIZE];
 
-		if (likely(q))
-			r |= bdi_congested(&q->backing_dev_info, bdi_bits);
-		else
+		if (likely(q)) {
+			struct backing_dev_info *bdi = &q->backing_dev_info;
+			r |= group ? bdi_congested_group(bdi, bdi_bits, page)
+				: bdi_congested(bdi, bdi_bits);
+		} else
 			DMWARN_LIMIT("%s: any_congested: nonexistent device %s",
 				     dm_device_name(t->md),
 				     bdevname(dd->dm_dev.bdev, b));
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3c6d4ee..320ef4c 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1608,7 +1608,8 @@ static void dm_unplug_all(struct request_queue *q)
 	}
 }
 
-static int dm_any_congested(void *congested_data, int bdi_bits)
+static int dm_any_congested(void *congested_data, int bdi_bits,
+					struct page *page, int group)
 {
 	int r = bdi_bits;
 	struct mapped_device *md = congested_data;
@@ -1625,8 +1626,8 @@ static int dm_any_congested(void *congested_data, int bdi_bits)
 				r = md->queue->backing_dev_info.state &
 				    bdi_bits;
 			else
-				r = dm_table_any_congested(map, bdi_bits);
-
+				r = dm_table_any_congested(map, bdi_bits, page,
+								 group);
 			dm_table_put(map);
 		}
 	}
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 23278ae..9c4c5a5 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -57,7 +57,8 @@ struct list_head *dm_table_get_devices(struct dm_table *t);
 void dm_table_presuspend_targets(struct dm_table *t);
 void dm_table_postsuspend_targets(struct dm_table *t);
 int dm_table_resume_targets(struct dm_table *t);
-int dm_table_any_congested(struct dm_table *t, int bdi_bits);
+int dm_table_any_congested(struct dm_table *t, int bdi_bits, struct page *page,
+				int group);
 int dm_table_any_busy_target(struct dm_table *t);
 int dm_table_set_type(struct dm_table *t);
 unsigned dm_table_get_type(struct dm_table *t);
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 15c8b7b..f227075 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -102,7 +102,7 @@ static void linear_unplug(struct request_queue *q)
 	rcu_read_unlock();
 }
 
-static int linear_congested(void *data, int bits)
+static int linear_congested(void *data, int bits, struct page *page, int group)
 {
 	mddev_t *mddev = data;
 	linear_conf_t *conf;
@@ -113,7 +113,10 @@ static int linear_congested(void *data, int bits)
 
 	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev);
-		ret |= bdi_congested(&q->backing_dev_info, bits);
+		struct backing_dev_info *bdi = &q->backing_dev_info;
+
+		ret |= group ? bdi_congested_group(bdi, bits, page) :
+			bdi_congested(bdi, bits);
 	}
 
 	rcu_read_unlock();
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index cbe368f..87bb1dd 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -192,7 +192,8 @@ static void multipath_status (struct seq_file *seq, mddev_t *mddev)
 	seq_printf (seq, "]");
 }
 
-static int multipath_congested(void *data, int bits)
+static int multipath_congested(void *data, int bits, struct page *page,
+					int group)
 {
 	mddev_t *mddev = data;
 	multipath_conf_t *conf = mddev->private;
@@ -203,8 +204,10 @@ static int multipath_congested(void *data, int bits)
 		mdk_rdev_t *rdev = rcu_dereference(conf->multipaths[i].rdev);
 		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			struct request_queue *q = bdev_get_queue(rdev->bdev);
+			struct backing_dev_info *bdi = &q->backing_dev_info;
 
-			ret |= bdi_congested(&q->backing_dev_info, bits);
+			ret |= group ? bdi_congested_group(bdi, bits, page)
+				: bdi_congested(bdi, bits);
 			/* Just like multipath_map, we just check the
 			 * first available device
 			 */
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index ab4a489..f7813e7 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -37,7 +37,7 @@ static void raid0_unplug(struct request_queue *q)
 	}
 }
 
-static int raid0_congested(void *data, int bits)
+static int raid0_congested(void *data, int bits, struct page *page, int group)
 {
 	mddev_t *mddev = data;
 	raid0_conf_t *conf = mddev->private;
@@ -46,8 +46,10 @@ static int raid0_congested(void *data, int bits)
 
 	for (i = 0; i < mddev->raid_disks && !ret ; i++) {
 		struct request_queue *q = bdev_get_queue(devlist[i]->bdev);
+		struct backing_dev_info *bdi = &q->backing_dev_info;
 
-		ret |= bdi_congested(&q->backing_dev_info, bits);
+		ret |= group ? bdi_congested_group(bdi, bits, page)
+				: bdi_congested(bdi, bits);
 	}
 	return ret;
 }
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 89939a7..6132848 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -570,7 +570,7 @@ static void raid1_unplug(struct request_queue *q)
 	md_wakeup_thread(mddev->thread);
 }
 
-static int raid1_congested(void *data, int bits)
+static int raid1_congested(void *data, int bits, struct page *page, int group)
 {
 	mddev_t *mddev = data;
 	conf_t *conf = mddev->private;
@@ -581,14 +581,17 @@ static int raid1_congested(void *data, int bits)
 		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
 		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			struct request_queue *q = bdev_get_queue(rdev->bdev);
+			struct backing_dev_info *bdi = &q->backing_dev_info;
 
 			/* Note the '|| 1' - when read_balance prefers
 			 * non-congested targets, it can be removed
 			 */
 			if ((bits & (1<<BDI_async_congested)) || 1)
-				ret |= bdi_congested(&q->backing_dev_info, bits);
+				ret |= group ? bdi_congested_group(bdi, bits,
+					page) : bdi_congested(bdi, bits);
 			else
-				ret &= bdi_congested(&q->backing_dev_info, bits);
+				ret &= group ? bdi_congested_group(bdi, bits,
+					page) : bdi_congested(bdi, bits);
 		}
 	}
 	rcu_read_unlock();
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index ae12cea..3d9c6b0 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -625,7 +625,7 @@ static void raid10_unplug(struct request_queue *q)
 	md_wakeup_thread(mddev->thread);
 }
 
-static int raid10_congested(void *data, int bits)
+static int raid10_congested(void *data, int bits, struct page *page, int group)
 {
 	mddev_t *mddev = data;
 	conf_t *conf = mddev->private;
@@ -636,8 +636,10 @@ static int raid10_congested(void *data, int bits)
 		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
 		if (rdev && !test_bit(Faulty, &rdev->flags)) {
 			struct request_queue *q = bdev_get_queue(rdev->bdev);
+			struct backing_dev_info *bdi = &q->backing_dev_info;
 
-			ret |= bdi_congested(&q->backing_dev_info, bits);
+			ret |= group ? bdi_congested_group(bdi, bits, page)
+				: bdi_congested(bdi, bits);
 		}
 	}
 	rcu_read_unlock();
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index f9f991e..16e4d1a 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3323,7 +3323,7 @@ static void raid5_unplug_device(struct request_queue *q)
 	unplug_slaves(mddev);
 }
 
-static int raid5_congested(void *data, int bits)
+static int raid5_congested(void *data, int bits, struct page *page, int group)
 {
 	mddev_t *mddev = data;
 	raid5_conf_t *conf = mddev->private;
diff --git a/fs/afs/write.c b/fs/afs/write.c
index c2e7a7f..aa8b359 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -455,7 +455,7 @@ int afs_writepage(struct page *page, struct writeback_control *wbc)
 	}
 
 	wbc->nr_to_write -= ret;
-	if (wbc->nonblocking && bdi_write_congested(bdi))
+	if (wbc->nonblocking && bdi_or_group_write_congested(bdi, page))
 		wbc->encountered_congestion = 1;
 
 	_leave(" = 0");
@@ -491,6 +491,12 @@ static int afs_writepages_region(struct address_space *mapping,
 			return 0;
 		}
 
+		if (wbc->nonblocking && bdi_write_congested_group(bdi, page)) {
+			wbc->encountered_congestion = 1;
+			page_cache_release(page);
+			break;
+		}
+
 		/* at this point we hold neither mapping->tree_lock nor lock on
 		 * the page itself: the page may be truncated or invalidated
 		 * (changing page->mapping to NULL), or even swizzled back from
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index d28d29c..cd7cf6c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1249,7 +1249,8 @@ struct btrfs_root *btrfs_read_fs_root(struct btrfs_fs_info *fs_info,
 	return root;
 }
 
-static int btrfs_congested_fn(void *congested_data, int bdi_bits)
+static int btrfs_congested_fn(void *congested_data, int bdi_bits,
+					struct page *page, int group)
 {
 	struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data;
 	int ret = 0;
@@ -1260,7 +1261,8 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 		if (!device->bdev)
 			continue;
 		bdi = blk_get_backing_dev_info(device->bdev);
-		if (bdi && bdi_congested(bdi, bdi_bits)) {
+		if (bdi && (group ? bdi_congested_group(bdi, bdi_bits, page) :
+		    bdi_congested(bdi, bdi_bits))) {
 			ret = 1;
 			break;
 		}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 6826018..fd7d53f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2368,6 +2368,18 @@ retry:
 		unsigned i;
 
 		scanned = 1;
+
+		/*
+		 * If the io group page will go into is congested, bail out.
+		 */
+		if (wbc->nonblocking
+		    && bdi_write_congested_group(bdi, pvec.pages[0])) {
+			wbc->encountered_congestion = 1;
+			done = 1;
+			pagevec_release(&pvec);
+			break;
+		}
+
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 3ab80e9..7ab5dea 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -165,6 +165,7 @@ static noinline int run_scheduled_bios(struct btrfs_device *device)
 	unsigned long limit;
 	unsigned long last_waited = 0;
 	int force_reg = 0;
+	struct page *page;
 
 	bdi = blk_get_backing_dev_info(device->bdev);
 	fs_info = device->dev_root->fs_info;
@@ -276,8 +277,11 @@ loop_lock:
 		 * is now congested.  Back off and let other work structs
 		 * run instead
 		 */
-		if (pending && bdi_write_congested(bdi) && batch_run > 32 &&
-		    fs_info->fs_devices->open_devices > 1) {
+		if (pending)
+			page = bio_iovec_idx(pending, 0)->bv_page;
+
+		if (pending && bdi_or_group_write_congested(bdi, page) &&
+		    num_run > 32 && fs_info->fs_devices->open_devices > 1) {
 			struct io_context *ioc;
 
 			ioc = current->io_context;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 0686684..365ca1b 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1466,6 +1466,17 @@ retry:
 		n_iov = 0;
 		bytes_to_write = 0;
 
+		/*
+		 * If the io group page will go into is congested, bail out.
+		 */
+		if (wbc->nonblocking &&
+		    bdi_write_congested_group(bdi, pvec.pages[0])) {
+			wbc->encountered_congestion = 1;
+			done = 1;
+			pagevec_release(&pvec);
+			break;
+		}
+
 		for (i = 0; i < nr_pages; i++) {
 			page = pvec.pages[i];
 			/*
diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 15387c9..090a961 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -179,7 +179,7 @@ static void ext2_preread_inode(struct inode *inode)
 	struct backing_dev_info *bdi;
 
 	bdi = inode->i_mapping->backing_dev_info;
-	if (bdi_read_congested(bdi))
+	if (bdi_or_group_read_congested(bdi, NULL))
 		return;
 	if (bdi_write_congested(bdi))
 		return;
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 03ebb43..5b9c93b 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -371,6 +371,18 @@ retry:
 					       PAGECACHE_TAG_DIRTY,
 					       min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
 		scanned = 1;
+
+		/*
+		 * If io group page belongs to is congested. bail out.
+		 */
+		if (wbc->nonblocking
+		    && bdi_write_congested_group(bdi, pvec.pages[0])) {
+			wbc->encountered_congestion = 1;
+			done = 1;
+			pagevec_release(&pvec);
+			break;
+		}
+
 		ret = gfs2_write_jdata_pagevec(mapping, wbc, &pvec, nr_pages, end);
 		if (ret)
 			done = 1;
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 9e3fe17..aa29612 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -266,8 +266,9 @@ static int nilfs_submit_seg_bio(struct nilfs_write_info *wi, int mode)
 {
 	struct bio *bio = wi->bio;
 	int err;
+	struct page *page = bio_iovec_idx(bio, 0)->bv_page;
 
-	if (wi->nbio > 0 && bdi_write_congested(wi->bdi)) {
+	if (wi->nbio > 0 && bdi_or_group_write_congested(wi->bdi, page)) {
 		wait_for_completion(&wi->bio_event);
 		wi->nbio--;
 		if (unlikely(atomic_read(&wi->err))) {
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index 7ec89fc..2a515ab 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -891,7 +891,7 @@ xfs_convert_page(
 
 			bdi = inode->i_mapping->backing_dev_info;
 			wbc->nr_to_write--;
-			if (bdi_write_congested(bdi)) {
+			if (bdi_or_group_write_congested(bdi, page)) {
 				wbc->encountered_congestion = 1;
 				done = 1;
 			} else if (wbc->nr_to_write <= 0) {
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index 1418b91..e95c97e 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -714,7 +714,7 @@ xfs_buf_readahead(
 	struct backing_dev_info *bdi;
 
 	bdi = target->bt_mapping->backing_dev_info;
-	if (bdi_read_congested(bdi))
+	if (bdi_or_group_read_congested(bdi, NULL))
 		return;
 
 	flags |= (XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD);
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 0ec2c59..f06fdbf 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -29,7 +29,7 @@ enum bdi_state {
 	BDI_unused,		/* Available bits start here */
 };
 
-typedef int (congested_fn)(void *, int);
+typedef int (congested_fn)(void *, int, struct page *, int);
 
 enum bdi_stat_item {
 	BDI_RECLAIMABLE,
@@ -209,7 +209,7 @@ int writeback_in_progress(struct backing_dev_info *bdi);
 static inline int bdi_congested(struct backing_dev_info *bdi, int bdi_bits)
 {
 	if (bdi->congested_fn)
-		return bdi->congested_fn(bdi->congested_data, bdi_bits);
+		return bdi->congested_fn(bdi->congested_data, bdi_bits, NULL, 0);
 	return (bdi->state & bdi_bits);
 }
 
@@ -229,6 +229,63 @@ static inline int bdi_rw_congested(struct backing_dev_info *bdi)
 				  (1 << BDI_async_congested));
 }
 
+#ifdef CONFIG_GROUP_IOSCHED
+extern int bdi_congested_group(struct backing_dev_info *bdi, int bdi_bits,
+				struct page *page);
+
+extern int bdi_read_congested_group(struct backing_dev_info *bdi,
+						struct page *page);
+
+extern int bdi_or_group_read_congested(struct backing_dev_info *bdi,
+					struct page *page);
+
+extern int bdi_write_congested_group(struct backing_dev_info *bdi,
+					struct page *page);
+
+extern int bdi_or_group_write_congested(struct backing_dev_info *bdi,
+					struct page *page);
+
+extern int bdi_rw_congested_group(struct backing_dev_info *bdi,
+					struct page *page);
+#else /* CONFIG_GROUP_IOSCHED */
+static inline int bdi_congested_group(struct backing_dev_info *bdi,
+					int bdi_bits, struct page *page)
+{
+	return bdi_congested(bdi, bdi_bits);
+}
+
+static inline int bdi_read_congested_group(struct backing_dev_info *bdi,
+						struct page *page)
+{
+	return bdi_read_congested(bdi);
+}
+
+static inline int bdi_or_group_read_congested(struct backing_dev_info *bdi,
+						struct page *page)
+{
+	return bdi_read_congested(bdi);
+}
+
+static inline int bdi_write_congested_group(struct backing_dev_info *bdi,
+						struct page *page)
+{
+	return bdi_write_congested(bdi);
+}
+
+static inline int bdi_or_group_write_congested(struct backing_dev_info *bdi,
+						struct page *page)
+{
+	return bdi_write_congested(bdi);
+}
+
+static inline int bdi_rw_congested_group(struct backing_dev_info *bdi,
+						struct page *page)
+{
+	return bdi_rw_congested(bdi);
+}
+
+#endif /* CONFIG_GROUP_IOSCHED */
+
 void clear_bdi_congested(struct backing_dev_info *bdi, int rw);
 void set_bdi_congested(struct backing_dev_info *bdi, int rw);
 long congestion_wait(int rw, long timeout);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 655440c..e8565b1 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -897,6 +897,11 @@ static inline void blk_set_queue_congested(struct request_queue *q, int rw)
 	set_bdi_congested(&q->backing_dev_info, rw);
 }
 
+#ifdef CONFIG_GROUP_IOSCHED
+extern int blk_queue_io_group_congested(struct backing_dev_info *bdi,
+					int bdi_bits, struct page *page);
+#endif
+
 extern void blk_start_queue(struct request_queue *q);
 extern void blk_stop_queue(struct request_queue *q);
 extern void blk_sync_queue(struct request_queue *q);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 493b468..cef038d 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -7,6 +7,7 @@
 #include <linux/module.h>
 #include <linux/writeback.h>
 #include <linux/device.h>
+#include "../block/elevator-fq.h"
 
 void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
 {
@@ -328,3 +329,64 @@ long congestion_wait(int rw, long timeout)
 }
 EXPORT_SYMBOL(congestion_wait);
 
+/*
+ * With group IO scheduling, there are request descriptors per io group per
+ * queue. So generic notion of whether queue is congested or not is not
+ * very accurate. Queue might not be congested but the io group in which
+ * request will go might actually be congested.
+ *
+ * Hence to get the correct idea about congestion level, one should query
+ * the io group congestion status on the queue. Pass in the page information
+ * which can be used to determine the io group of the page and congestion
+ * status can be determined accordingly.
+ *
+ * If page info is not passed, io group is determined from the current task
+ * context.
+ */
+#ifdef CONFIG_GROUP_IOSCHED
+int bdi_congested_group(struct backing_dev_info *bdi, int bdi_bits,
+				struct page *page)
+{
+	if (bdi->congested_fn)
+		return bdi->congested_fn(bdi->congested_data, bdi_bits, page, 1);
+
+	return blk_queue_io_group_congested(bdi, bdi_bits, page);
+}
+EXPORT_SYMBOL(bdi_congested_group);
+
+int bdi_read_congested_group(struct backing_dev_info *bdi, struct page *page)
+{
+	return bdi_congested_group(bdi, 1 << BDI_sync_congested, page);
+}
+EXPORT_SYMBOL(bdi_read_congested_group);
+
+/* Checks if either bdi or associated group is read congested */
+int bdi_or_group_read_congested(struct backing_dev_info *bdi,
+						struct page *page)
+{
+	return bdi_read_congested(bdi) || bdi_read_congested_group(bdi, page);
+}
+EXPORT_SYMBOL(bdi_or_group_read_congested);
+
+int bdi_write_congested_group(struct backing_dev_info *bdi, struct page *page)
+{
+	return bdi_congested_group(bdi, 1 << BDI_async_congested, page);
+}
+EXPORT_SYMBOL(bdi_write_congested_group);
+
+/* Checks if either bdi or associated group is write congested */
+int bdi_or_group_write_congested(struct backing_dev_info *bdi,
+						struct page *page)
+{
+	return bdi_write_congested(bdi) || bdi_write_congested_group(bdi, page);
+}
+EXPORT_SYMBOL(bdi_or_group_write_congested);
+
+int bdi_rw_congested_group(struct backing_dev_info *bdi, struct page *page)
+{
+	return bdi_congested_group(bdi, (1 << BDI_sync_congested) |
+				  (1 << BDI_async_congested), page);
+}
+EXPORT_SYMBOL(bdi_rw_congested_group);
+
+#endif /* CONFIG_GROUP_IOSCHED */
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 31d3675..5ad9453 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -982,6 +982,17 @@ retry:
 		if (nr_pages == 0)
 			break;
 
+		/*
+		 * If the io group page will go into is congested, bail out.
+		 */
+		if (wbc->nonblocking
+		    && bdi_write_congested_group(bdi, pvec.pages[0])) {
+			wbc->encountered_congestion = 1;
+			done = 1;
+			pagevec_release(&pvec);
+			break;
+		}
+
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
diff --git a/mm/readahead.c b/mm/readahead.c
index aa1aa23..22e0639 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -542,7 +542,7 @@ page_cache_async_readahead(struct address_space *mapping,
 	/*
 	 * Defer asynchronous read-ahead on IO congestion.
 	 */
-	if (bdi_read_congested(mapping->backing_dev_info))
+	if (bdi_or_group_read_congested(mapping->backing_dev_info, NULL))
 		return;
 
 	/* do read-ahead */
-- 
1.6.0.6

--
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/