From eea8f41cc58849e354ecf8b95bd7f806e1d1f703 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 22 May 2015 17:13:17 -0400 Subject: blkcg: move block/blk-cgroup.h to include/linux/blk-cgroup.h cgroup aware writeback support will require exposing some of blkcg details. In preprataion, move block/blk-cgroup.h to include/linux/blk-cgroup.h. This patch is pure file move. Signed-off-by: Tejun Heo Cc: Vivek Goyal Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index aa819a58ea24..4afac14d4499 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -32,12 +32,12 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include #include "blk.h" -#include "blk-cgroup.h" #include "blk-mq.h" EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); -- cgit v1.2.3 From 4452226ea276e74fc3e252c88d9bb7e8f8e44bf0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 22 May 2015 17:13:26 -0400 Subject: writeback: move backing_dev_info->state into bdi_writeback Currently, a bdi (backing_dev_info) embeds single wb (bdi_writeback) and the role of the separation is unclear. For cgroup support for writeback IOs, a bdi will be updated to host multiple wb's where each wb serves writeback IOs of a different cgroup on the bdi. To achieve that, a wb should carry all states necessary for servicing writeback IOs for a cgroup independently. This patch moves bdi->state into wb. * enum bdi_state is renamed to wb_state and the prefix of all enums is changed from BDI_ to WB_. * Explicit zeroing of bdi->state is removed without adding zeoring of wb->state as the whole data structure is zeroed on init anyway. * As there's still only one bdi_writeback per backing_dev_info, all uses of bdi->state are mechanically replaced with bdi->wb.state introducing no behavior changes. Signed-off-by: Tejun Heo Reviewed-by: Jan Kara Cc: Jens Axboe Cc: Wu Fengguang Cc: drbd-dev@lists.linbit.com Cc: Neil Brown Cc: Alasdair Kergon Cc: Mike Snitzer Signed-off-by: Jens Axboe --- block/blk-core.c | 1 - drivers/block/drbd/drbd_main.c | 10 +++++----- drivers/md/dm.c | 2 +- drivers/md/raid1.c | 4 ++-- drivers/md/raid10.c | 2 +- fs/fs-writeback.c | 14 +++++++------- include/linux/backing-dev.h | 24 ++++++++++++------------ mm/backing-dev.c | 20 ++++++++++---------- 8 files changed, 38 insertions(+), 39 deletions(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index 4afac14d4499..c3ba9c3b08d4 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -621,7 +621,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) q->backing_dev_info.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; - q->backing_dev_info.state = 0; q->backing_dev_info.capabilities = 0; q->backing_dev_info.name = "block"; q->node = node_id; diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 81fde9ef7f8e..a1518539b858 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2359,7 +2359,7 @@ static void drbd_cleanup(void) * @congested_data: User data * @bdi_bits: Bits the BDI flusher thread is currently interested in * - * Returns 1<connection->flags)) { - r |= (1 << BDI_async_congested); + r |= (1 << WB_async_congested); /* Without good local data, we would need to read from remote, * and that would need the worker thread as well, which is * currently blocked waiting for that usermode helper to * finish. */ if (!get_ldev_if_state(device, D_UP_TO_DATE)) - r |= (1 << BDI_sync_congested); + r |= (1 << WB_sync_congested); else put_ldev(device); r &= bdi_bits; @@ -2399,9 +2399,9 @@ static int drbd_congested(void *congested_data, int bdi_bits) reason = 'b'; } - if (bdi_bits & (1 << BDI_async_congested) && + if (bdi_bits & (1 << WB_async_congested) && test_bit(NET_CONGESTED, &first_peer_device(device)->connection->flags)) { - r |= (1 << BDI_async_congested); + r |= (1 << WB_async_congested); reason = reason == 'b' ? 'a' : 'n'; } diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 38837f8ea327..2161ed9329c4 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2074,7 +2074,7 @@ static int dm_any_congested(void *congested_data, int bdi_bits) * the query about congestion status of request_queue */ if (dm_request_based(md)) - r = md->queue->backing_dev_info.state & + r = md->queue->backing_dev_info.wb.state & bdi_bits; else r = dm_table_any_congested(map, bdi_bits); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 9157a29c8dbf..f80f1af61ce7 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -745,7 +745,7 @@ static int raid1_congested(struct mddev *mddev, int bits) struct r1conf *conf = mddev->private; int i, ret = 0; - if ((bits & (1 << BDI_async_congested)) && + if ((bits & (1 << WB_async_congested)) && conf->pending_count >= max_queued_requests) return 1; @@ -760,7 +760,7 @@ static int raid1_congested(struct mddev *mddev, int bits) /* Note the '|| 1' - when read_balance prefers * non-congested targets, it can be removed */ - if ((bits & (1<backing_dev_info, bits); else ret &= bdi_congested(&q->backing_dev_info, bits); diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index e793ab6b3570..fca825718f29 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -914,7 +914,7 @@ static int raid10_congested(struct mddev *mddev, int bits) struct r10conf *conf = mddev->private; int i, ret = 0; - if ((bits & (1 << BDI_async_congested)) && + if ((bits & (1 << WB_async_congested)) && conf->pending_count >= max_queued_requests) return 1; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 32a8bbd7a9ad..983312cea245 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -74,7 +74,7 @@ unsigned int dirtytime_expire_interval = 12 * 60 * 60; */ int writeback_in_progress(struct backing_dev_info *bdi) { - return test_bit(BDI_writeback_running, &bdi->state); + return test_bit(WB_writeback_running, &bdi->wb.state); } EXPORT_SYMBOL(writeback_in_progress); @@ -112,7 +112,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); static void bdi_wakeup_thread(struct backing_dev_info *bdi) { spin_lock_bh(&bdi->wb_lock); - if (test_bit(BDI_registered, &bdi->state)) + if (test_bit(WB_registered, &bdi->wb.state)) mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); spin_unlock_bh(&bdi->wb_lock); } @@ -123,7 +123,7 @@ static void bdi_queue_work(struct backing_dev_info *bdi, trace_writeback_queue(bdi, work); spin_lock_bh(&bdi->wb_lock); - if (!test_bit(BDI_registered, &bdi->state)) { + if (!test_bit(WB_registered, &bdi->wb.state)) { if (work->done) complete(work->done); goto out_unlock; @@ -1057,7 +1057,7 @@ static long wb_do_writeback(struct bdi_writeback *wb) struct wb_writeback_work *work; long wrote = 0; - set_bit(BDI_writeback_running, &wb->bdi->state); + set_bit(WB_writeback_running, &wb->state); while ((work = get_next_work_item(bdi)) != NULL) { trace_writeback_exec(bdi, work); @@ -1079,7 +1079,7 @@ static long wb_do_writeback(struct bdi_writeback *wb) */ wrote += wb_check_old_data_flush(wb); wrote += wb_check_background_flush(wb); - clear_bit(BDI_writeback_running, &wb->bdi->state); + clear_bit(WB_writeback_running, &wb->state); return wrote; } @@ -1099,7 +1099,7 @@ void bdi_writeback_workfn(struct work_struct *work) current->flags |= PF_SWAPWRITE; if (likely(!current_is_workqueue_rescuer() || - !test_bit(BDI_registered, &bdi->state))) { + !test_bit(WB_registered, &wb->state))) { /* * The normal path. Keep writing back @bdi until its * work_list is empty. Note that this path is also taken @@ -1323,7 +1323,7 @@ void __mark_inode_dirty(struct inode *inode, int flags) spin_unlock(&inode->i_lock); spin_lock(&bdi->wb.list_lock); if (bdi_cap_writeback_dirty(bdi)) { - WARN(!test_bit(BDI_registered, &bdi->state), + WARN(!test_bit(WB_registered, &bdi->wb.state), "bdi-%s not registered\n", bdi->name); /* diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index aff923ae8c4b..eb14f988a63e 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -25,13 +25,13 @@ struct device; struct dentry; /* - * Bits in backing_dev_info.state + * Bits in bdi_writeback.state */ -enum bdi_state { - BDI_async_congested, /* The async (write) queue is getting full */ - BDI_sync_congested, /* The sync queue is getting full */ - BDI_registered, /* bdi_register() was done */ - BDI_writeback_running, /* Writeback is in progress */ +enum wb_state { + WB_async_congested, /* The async (write) queue is getting full */ + WB_sync_congested, /* The sync queue is getting full */ + WB_registered, /* bdi_register() was done */ + WB_writeback_running, /* Writeback is in progress */ }; typedef int (congested_fn)(void *, int); @@ -49,6 +49,7 @@ enum bdi_stat_item { struct bdi_writeback { struct backing_dev_info *bdi; /* our parent bdi */ + unsigned long state; /* Always use atomic bitops on this */ unsigned long last_old_flush; /* last old data flush */ struct delayed_work dwork; /* work item used for writeback */ @@ -62,7 +63,6 @@ struct bdi_writeback { struct backing_dev_info { struct list_head bdi_list; unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ - unsigned long state; /* Always use atomic bitops on this */ unsigned int capabilities; /* Device capabilities */ congested_fn *congested_fn; /* Function pointer if device is md/dm */ void *congested_data; /* Pointer to aux data for congested func */ @@ -250,23 +250,23 @@ 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->state & bdi_bits); + return (bdi->wb.state & bdi_bits); } static inline int bdi_read_congested(struct backing_dev_info *bdi) { - return bdi_congested(bdi, 1 << BDI_sync_congested); + return bdi_congested(bdi, 1 << WB_sync_congested); } static inline int bdi_write_congested(struct backing_dev_info *bdi) { - return bdi_congested(bdi, 1 << BDI_async_congested); + return bdi_congested(bdi, 1 << WB_async_congested); } static inline int bdi_rw_congested(struct backing_dev_info *bdi) { - return bdi_congested(bdi, (1 << BDI_sync_congested) | - (1 << BDI_async_congested)); + return bdi_congested(bdi, (1 << WB_sync_congested) | + (1 << WB_async_congested)); } enum { diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 6dc4580df2af..b23cf0ea5912 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -96,7 +96,7 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v) nr_io, nr_more_io, nr_dirty_time, - !list_empty(&bdi->bdi_list), bdi->state); + !list_empty(&bdi->bdi_list), bdi->wb.state); #undef K return 0; @@ -280,7 +280,7 @@ void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi) timeout = msecs_to_jiffies(dirty_writeback_interval * 10); spin_lock_bh(&bdi->wb_lock); - if (test_bit(BDI_registered, &bdi->state)) + if (test_bit(WB_registered, &bdi->wb.state)) queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout); spin_unlock_bh(&bdi->wb_lock); } @@ -315,7 +315,7 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent, bdi->dev = dev; bdi_debug_register(bdi, dev_name(dev)); - set_bit(BDI_registered, &bdi->state); + set_bit(WB_registered, &bdi->wb.state); spin_lock_bh(&bdi_lock); list_add_tail_rcu(&bdi->bdi_list, &bdi_list); @@ -339,7 +339,7 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) { /* Make sure nobody queues further work */ spin_lock_bh(&bdi->wb_lock); - if (!test_and_clear_bit(BDI_registered, &bdi->state)) { + if (!test_and_clear_bit(WB_registered, &bdi->wb.state)) { spin_unlock_bh(&bdi->wb_lock); return; } @@ -492,11 +492,11 @@ static atomic_t nr_bdi_congested[2]; void clear_bdi_congested(struct backing_dev_info *bdi, int sync) { - enum bdi_state bit; + enum wb_state bit; wait_queue_head_t *wqh = &congestion_wqh[sync]; - bit = sync ? BDI_sync_congested : BDI_async_congested; - if (test_and_clear_bit(bit, &bdi->state)) + bit = sync ? WB_sync_congested : WB_async_congested; + if (test_and_clear_bit(bit, &bdi->wb.state)) atomic_dec(&nr_bdi_congested[sync]); smp_mb__after_atomic(); if (waitqueue_active(wqh)) @@ -506,10 +506,10 @@ EXPORT_SYMBOL(clear_bdi_congested); void set_bdi_congested(struct backing_dev_info *bdi, int sync) { - enum bdi_state bit; + enum wb_state bit; - bit = sync ? BDI_sync_congested : BDI_async_congested; - if (!test_and_set_bit(bit, &bdi->state)) + bit = sync ? WB_sync_congested : WB_async_congested; + if (!test_and_set_bit(bit, &bdi->wb.state)) atomic_inc(&nr_bdi_congested[sync]); } EXPORT_SYMBOL(set_bdi_congested); -- cgit v1.2.3 From 89e9b9e07a390c50980d10aa37a04631db5a23ab Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 22 May 2015 17:13:36 -0400 Subject: writeback: add {CONFIG|BDI_CAP|FS}_CGROUP_WRITEBACK cgroup writeback requires support from both bdi and filesystem sides. Add BDI_CAP_CGROUP_WRITEBACK and FS_CGROUP_WRITEBACK to indicate support and enable BDI_CAP_CGROUP_WRITEBACK on block based bdi's by default. Also, define CONFIG_CGROUP_WRITEBACK which is enabled if both MEMCG and BLK_CGROUP are enabled. inode_cgwb_enabled() which determines whether a given inode's both bdi and fs support cgroup writeback is added. Signed-off-by: Tejun Heo Cc: Jens Axboe Cc: Jan Kara Signed-off-by: Jens Axboe --- block/blk-core.c | 2 +- include/linux/backing-dev.h | 32 +++++++++++++++++++++++++++++++- include/linux/fs.h | 1 + init/Kconfig | 5 +++++ 4 files changed, 38 insertions(+), 2 deletions(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index c3ba9c3b08d4..c114a61590bc 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -621,7 +621,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) q->backing_dev_info.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_CACHE_SIZE; - q->backing_dev_info.capabilities = 0; + q->backing_dev_info.capabilities = BDI_CAP_CGROUP_WRITEBACK; q->backing_dev_info.name = "block"; q->node = node_id; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index bfdaa18ba0a1..6bb31234e6a9 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -134,12 +134,15 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_NO_WRITEBACK: Don't write pages back * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. + * + * BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 #define BDI_CAP_NO_ACCT_WB 0x00000004 #define BDI_CAP_STABLE_WRITES 0x00000008 #define BDI_CAP_STRICTLIMIT 0x00000010 +#define BDI_CAP_CGROUP_WRITEBACK 0x00000020 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) @@ -229,4 +232,31 @@ static inline int bdi_sched_wait(void *word) return 0; } -#endif /* _LINUX_BACKING_DEV_H */ +#ifdef CONFIG_CGROUP_WRITEBACK + +/** + * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode + * @inode: inode of interest + * + * cgroup writeback requires support from both the bdi and filesystem. + * Test whether @inode has both. + */ +static inline bool inode_cgwb_enabled(struct inode *inode) +{ + struct backing_dev_info *bdi = inode_to_bdi(inode); + + return bdi_cap_account_dirty(bdi) && + (bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) && + (inode->i_sb->s_type->fs_flags & FS_CGROUP_WRITEBACK); +} + +#else /* CONFIG_CGROUP_WRITEBACK */ + +static inline bool inode_cgwb_enabled(struct inode *inode) +{ + return false; +} + +#endif /* CONFIG_CGROUP_WRITEBACK */ + +#endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index ce100b87fba3..74e0ae0626a8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1897,6 +1897,7 @@ struct file_system_type { #define FS_HAS_SUBTYPE 4 #define FS_USERNS_MOUNT 8 /* Can be mounted by userns root */ #define FS_USERNS_DEV_MOUNT 16 /* A userns mount does not imply MNT_NODEV */ +#define FS_CGROUP_WRITEBACK 32 /* Supports cgroup-aware writeback */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ struct dentry *(*mount) (struct file_system_type *, int, const char *, void *); diff --git a/init/Kconfig b/init/Kconfig index dc24dec60232..d4f763332f9f 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1141,6 +1141,11 @@ config DEBUG_BLK_CGROUP Enable some debugging help. Currently it exports additional stat files in a cgroup which can be useful for debugging. +config CGROUP_WRITEBACK + bool + depends on MEMCG && BLK_CGROUP + default y + endif # CGROUPS config CHECKPOINT_RESTORE -- cgit v1.2.3 From d40f75a06dd675808eed385d490ba9468200b23f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 22 May 2015 17:13:42 -0400 Subject: writeback, blkcg: restructure blk_{set|clear}_queue_congested() blk_{set|clear}_queue_congested() take @q and set or clear, respectively, the congestion state of its bdi's root wb. Because bdi used to be able to handle congestion state only on the root wb, the callers of those functions tested whether the congestion is on the root blkcg and skipped if not. This is cumbersome and makes implementation of per cgroup bdi_writeback congestion state propagation difficult. This patch renames blk_{set|clear}_queue_congested() to blk_{set|clear}_congested(), and makes them take request_list instead of request_queue and test whether the specified request_list is the root one before updating bdi_writeback congestion state. This makes the tests in the callers unnecessary and simplifies them. As there are no external users of these functions, the definitions are moved from include/linux/blkdev.h to block/blk-core.c. This patch doesn't introduce any noticeable behavior difference. Signed-off-by: Tejun Heo Cc: Jens Axboe Cc: Jan Kara Cc: Vivek Goyal Signed-off-by: Jens Axboe --- block/blk-core.c | 62 ++++++++++++++++++++++++++++++-------------------- include/linux/blkdev.h | 19 ---------------- 2 files changed, 37 insertions(+), 44 deletions(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index c114a61590bc..f46a43ef1a94 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -63,6 +63,28 @@ struct kmem_cache *blk_requestq_cachep; */ static struct workqueue_struct *kblockd_workqueue; +static void blk_clear_congested(struct request_list *rl, int sync) +{ + if (rl != &rl->q->root_rl) + return; +#ifdef CONFIG_CGROUP_WRITEBACK + clear_wb_congested(rl->blkg->wb_congested, sync); +#else + clear_wb_congested(rl->q->backing_dev_info.wb.congested, sync); +#endif +} + +static void blk_set_congested(struct request_list *rl, int sync) +{ + if (rl != &rl->q->root_rl) + return; +#ifdef CONFIG_CGROUP_WRITEBACK + set_wb_congested(rl->blkg->wb_congested, sync); +#else + set_wb_congested(rl->q->backing_dev_info.wb.congested, sync); +#endif +} + void blk_queue_congestion_threshold(struct request_queue *q) { int nr; @@ -842,13 +864,8 @@ static void __freed_request(struct request_list *rl, int sync) { struct request_queue *q = rl->q; - /* - * bdi isn't aware of blkcg yet. As all async IOs end up root - * blkcg anyway, just use root blkcg state. - */ - if (rl == &q->root_rl && - rl->count[sync] < queue_congestion_off_threshold(q)) - blk_clear_queue_congested(q, sync); + if (rl->count[sync] < queue_congestion_off_threshold(q)) + blk_clear_congested(rl, sync); if (rl->count[sync] + 1 <= q->nr_requests) { if (waitqueue_active(&rl->wait[sync])) @@ -881,25 +898,25 @@ static void freed_request(struct request_list *rl, unsigned int flags) int blk_update_nr_requests(struct request_queue *q, unsigned int nr) { struct request_list *rl; + int on_thresh, off_thresh; spin_lock_irq(q->queue_lock); q->nr_requests = nr; blk_queue_congestion_threshold(q); + on_thresh = queue_congestion_on_threshold(q); + off_thresh = queue_congestion_off_threshold(q); - /* congestion isn't cgroup aware and follows root blkcg for now */ - rl = &q->root_rl; - - if (rl->count[BLK_RW_SYNC] >= queue_congestion_on_threshold(q)) - blk_set_queue_congested(q, BLK_RW_SYNC); - else if (rl->count[BLK_RW_SYNC] < queue_congestion_off_threshold(q)) - blk_clear_queue_congested(q, BLK_RW_SYNC); + blk_queue_for_each_rl(rl, q) { + if (rl->count[BLK_RW_SYNC] >= on_thresh) + blk_set_congested(rl, BLK_RW_SYNC); + else if (rl->count[BLK_RW_SYNC] < off_thresh) + blk_clear_congested(rl, BLK_RW_SYNC); - if (rl->count[BLK_RW_ASYNC] >= queue_congestion_on_threshold(q)) - blk_set_queue_congested(q, BLK_RW_ASYNC); - else if (rl->count[BLK_RW_ASYNC] < queue_congestion_off_threshold(q)) - blk_clear_queue_congested(q, BLK_RW_ASYNC); + if (rl->count[BLK_RW_ASYNC] >= on_thresh) + blk_set_congested(rl, BLK_RW_ASYNC); + else if (rl->count[BLK_RW_ASYNC] < off_thresh) + blk_clear_congested(rl, BLK_RW_ASYNC); - blk_queue_for_each_rl(rl, q) { if (rl->count[BLK_RW_SYNC] >= q->nr_requests) { blk_set_rl_full(rl, BLK_RW_SYNC); } else { @@ -1009,12 +1026,7 @@ static struct request *__get_request(struct request_list *rl, int rw_flags, } } } - /* - * bdi isn't aware of blkcg yet. As all async IOs end up - * root blkcg anyway, just use root blkcg state. - */ - if (rl == &q->root_rl) - blk_set_queue_congested(q, is_sync); + blk_set_congested(rl, is_sync); } /* diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 60d2726a6b62..ab4a27852f1b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -790,25 +790,6 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, extern void blk_queue_bio(struct request_queue *q, struct bio *bio); -/* - * A queue has just exitted congestion. Note this in the global counter of - * congested queues, and wake up anyone who was waiting for requests to be - * put back. - */ -static inline void blk_clear_queue_congested(struct request_queue *q, int sync) -{ - clear_bdi_congested(&q->backing_dev_info, sync); -} - -/* - * A queue has just entered congestion. Flag that in the queue's VM-visible - * state flags and increment the global gounter of congested queues. - */ -static inline void blk_set_queue_congested(struct request_queue *q, int sync) -{ - set_bdi_congested(&q->backing_dev_info, sync); -} - 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); -- cgit v1.2.3 From 482cf79cdf6669667a914ffd4cbc57a762b55fef Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 22 May 2015 17:13:43 -0400 Subject: writeback, blkcg: propagate non-root blkcg congestion state Now that bdi layer can handle per-blkcg bdi_writeback_congested state, blk_{set|clear}_congested() can propagate non-root blkcg congestion state to them. This can be easily achieved by disabling the root_rl tests in blk_{set|clear}_congested(). Note that we still need those tests when !CONFIG_CGROUP_WRITEBACK as otherwise we'll end up flipping root blkcg wb's congestion state for events happening on other blkcgs. v2: Updated for bdi_writeback_congested. Signed-off-by: Tejun Heo Cc: Jens Axboe Cc: Jan Kara Cc: Vivek Goyal Signed-off-by: Jens Axboe --- block/blk-core.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) (limited to 'block/blk-core.c') diff --git a/block/blk-core.c b/block/blk-core.c index f46a43ef1a94..a4a2dbe46fe3 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -65,23 +65,26 @@ static struct workqueue_struct *kblockd_workqueue; static void blk_clear_congested(struct request_list *rl, int sync) { - if (rl != &rl->q->root_rl) - return; #ifdef CONFIG_CGROUP_WRITEBACK clear_wb_congested(rl->blkg->wb_congested, sync); #else - clear_wb_congested(rl->q->backing_dev_info.wb.congested, sync); + /* + * If !CGROUP_WRITEBACK, all blkg's map to bdi->wb and we shouldn't + * flip its congestion state for events on other blkcgs. + */ + if (rl == &rl->q->root_rl) + clear_wb_congested(rl->q->backing_dev_info.wb.congested, sync); #endif } static void blk_set_congested(struct request_list *rl, int sync) { - if (rl != &rl->q->root_rl) - return; #ifdef CONFIG_CGROUP_WRITEBACK set_wb_congested(rl->blkg->wb_congested, sync); #else - set_wb_congested(rl->q->backing_dev_info.wb.congested, sync); + /* see blk_clear_congested() */ + if (rl == &rl->q->root_rl) + set_wb_congested(rl->q->backing_dev_info.wb.congested, sync); #endif } -- cgit v1.2.3