@@ -1351,6 +1351,79 @@ struct cgroup_subsys io_cgrp_subsys = {
};
EXPORT_SYMBOL_GPL(io_cgrp_subsys);
+#ifdef CONFIG_CGROUP_WRITEBACK
+/**
+ * blkcg_wb_waiters_on_bdi - check for writeback waiters on a block device
+ * @blkcg: current blkcg cgroup
+ * @bdi: block device to check
+ *
+ * Return true if any other blkcg is waiting for writeback on the target block
+ * device, false otherwise.
+ */
+bool blkcg_wb_waiters_on_bdi(struct blkcg *blkcg, struct backing_dev_info *bdi)
+{
+ struct blkcg *wait_blkcg;
+ bool ret = false;
+
+ if (unlikely(!bdi))
+ return false;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(wait_blkcg, &bdi->cgwb_waiters, cgwb_wait_node)
+ if (wait_blkcg != blkcg) {
+ ret = true;
+ break;
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
+/**
+ * blkcg_start_wb_wait_on_bdi - add current blkcg to writeback waiters list
+ * @bdi: target block device
+ *
+ * Add current blkcg to the list of writeback waiters on target block device.
+ */
+void blkcg_start_wb_wait_on_bdi(struct backing_dev_info *bdi)
+{
+ struct blkcg *blkcg;
+
+ rcu_read_lock();
+ blkcg = blkcg_from_current();
+ if (blkcg) {
+ css_get(&blkcg->css);
+ spin_lock(&bdi->cgwb_waiters_lock);
+ list_add_rcu(&blkcg->cgwb_wait_node, &bdi->cgwb_waiters);
+ spin_unlock(&bdi->cgwb_waiters_lock);
+ }
+ rcu_read_unlock();
+}
+
+/**
+ * blkcg_stop_wb_wait_on_bdi - remove current blkcg from writeback waiters list
+ * @bdi: target block device
+ *
+ * Remove current blkcg from the list of writeback waiters on target block
+ * device.
+ */
+void blkcg_stop_wb_wait_on_bdi(struct backing_dev_info *bdi)
+{
+ struct blkcg *blkcg;
+
+ rcu_read_lock();
+ blkcg = blkcg_from_current();
+ if (blkcg) {
+ spin_lock(&bdi->cgwb_waiters_lock);
+ list_del_rcu(&blkcg->cgwb_wait_node);
+ spin_unlock(&bdi->cgwb_waiters_lock);
+ css_put(&blkcg->css);
+ }
+ rcu_read_unlock();
+ synchronize_rcu();
+}
+#endif
+
/**
* blkcg_activate_policy - activate a blkcg policy on a request_queue
* @q: request_queue of interest
@@ -970,9 +970,13 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
{
bool rw = bio_data_dir(bio);
unsigned long bps_wait = 0, iops_wait = 0, max_wait = 0;
+ struct throtl_data *td = tg->td;
+ struct request_queue *q = td->queue;
+ struct backing_dev_info *bdi = q->backing_dev_info;
+ struct blkcg_gq *blkg = tg_to_blkg(tg);
/*
- * Currently whole state machine of group depends on first bio
+ * Currently whole state machine of group depends on first bio
* queued in the group bio list. So one should not be calling
* this function with a different bio if there are other bios
* queued.
@@ -981,8 +985,9 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
bio != throtl_peek_queued(&tg->service_queue.queued[rw]));
/* If tg->bps = -1, then BW is unlimited */
- if (tg_bps_limit(tg, rw) == U64_MAX &&
- tg_iops_limit(tg, rw) == UINT_MAX) {
+ if (blkcg_wb_waiters_on_bdi(blkg->blkcg, bdi) ||
+ (tg_bps_limit(tg, rw) == U64_MAX &&
+ tg_iops_limit(tg, rw) == UINT_MAX)) {
if (wait)
*wait = 0;
return true;
@@ -28,6 +28,7 @@
#include <linux/tracepoint.h>
#include <linux/device.h>
#include <linux/memcontrol.h>
+#include <linux/blk-cgroup.h>
#include "internal.h"
/*
@@ -2446,6 +2447,8 @@ void sync_inodes_sb(struct super_block *sb)
return;
WARN_ON(!rwsem_is_locked(&sb->s_umount));
+ blkcg_start_wb_wait_on_bdi(bdi);
+
/* protect against inode wb switch, see inode_switch_wbs_work_fn() */
bdi_down_write_wb_switch_rwsem(bdi);
bdi_split_work_to_wbs(bdi, &work, false);
@@ -2453,6 +2456,8 @@ void sync_inodes_sb(struct super_block *sb)
bdi_up_write_wb_switch_rwsem(bdi);
wait_sb_inodes(sb);
+
+ blkcg_stop_wb_wait_on_bdi(bdi);
}
EXPORT_SYMBOL(sync_inodes_sb);
@@ -16,6 +16,7 @@
#include <linux/pagemap.h>
#include <linux/quotaops.h>
#include <linux/backing-dev.h>
+#include <linux/blk-cgroup.h>
#include "internal.h"
#define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \
@@ -76,8 +77,13 @@ static void sync_inodes_one_sb(struct super_block *sb, void *arg)
static void sync_fs_one_sb(struct super_block *sb, void *arg)
{
- if (!sb_rdonly(sb) && sb->s_op->sync_fs)
+ struct backing_dev_info *bdi = sb->s_bdi;
+
+ if (!sb_rdonly(sb) && sb->s_op->sync_fs) {
+ blkcg_start_wb_wait_on_bdi(bdi);
sb->s_op->sync_fs(sb, *(int *)arg);
+ blkcg_stop_wb_wait_on_bdi(bdi);
+ }
}
static void fdatawrite_one_bdev(struct block_device *bdev, void *arg)
@@ -191,6 +191,8 @@ struct backing_dev_info {
struct rb_root cgwb_congested_tree; /* their congested states */
struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */
struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */
+ struct list_head cgwb_waiters; /* list of all waiters for writeback */
+ spinlock_t cgwb_waiters_lock; /* protect cgwb_waiters list */
#else
struct bdi_writeback_congested *wb_congested;
#endif
@@ -56,6 +56,7 @@ struct blkcg {
struct list_head all_blkcgs_node;
#ifdef CONFIG_CGROUP_WRITEBACK
+ struct list_head cgwb_wait_node;
struct list_head cgwb_list;
refcount_t cgwb_refcnt;
#endif
@@ -252,6 +253,12 @@ static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css)
return css ? container_of(css, struct blkcg, css) : NULL;
}
+static inline struct blkcg *blkcg_from_current(void)
+{
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ return css_to_blkcg(blkcg_css());
+}
+
/**
* __bio_blkcg - internal, inconsistent version to get blkcg
*
@@ -454,6 +461,10 @@ static inline void blkcg_cgwb_put(struct blkcg *blkcg)
blkcg_destroy_blkgs(blkcg);
}
+bool blkcg_wb_waiters_on_bdi(struct blkcg *blkcg, struct backing_dev_info *bdi);
+void blkcg_start_wb_wait_on_bdi(struct backing_dev_info *bdi);
+void blkcg_stop_wb_wait_on_bdi(struct backing_dev_info *bdi);
+
#else
static inline void blkcg_cgwb_get(struct blkcg *blkcg) { }
@@ -464,6 +475,14 @@ static inline void blkcg_cgwb_put(struct blkcg *blkcg)
blkcg_destroy_blkgs(blkcg);
}
+static inline bool
+blkcg_wb_waiters_on_bdi(struct blkcg *blkcg, struct backing_dev_info *bdi)
+{
+ return false;
+}
+static inline void blkcg_start_wb_wait_on_bdi(struct backing_dev_info *bdi) { }
+static inline void blkcg_stop_wb_wait_on_bdi(struct backing_dev_info *bdi) { }
+
#endif
/**
@@ -772,6 +791,7 @@ static inline void blkcg_bio_issue_init(struct bio *bio)
static inline bool blkcg_bio_issue_check(struct request_queue *q,
struct bio *bio)
{
+ struct backing_dev_info *bdi = q->backing_dev_info;
struct blkcg_gq *blkg;
bool throtl = false;
@@ -788,6 +808,9 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
blkg = bio->bi_blkg;
+ if (blkcg_wb_waiters_on_bdi(blkg->blkcg, bdi))
+ bio_set_flag(bio, BIO_THROTTLED);
+
throtl = blk_throtl_bio(q, blkg, bio);
if (!throtl) {
@@ -686,10 +686,12 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
{
int ret;
+ INIT_LIST_HEAD(&bdi->cgwb_waiters);
INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC);
bdi->cgwb_congested_tree = RB_ROOT;
mutex_init(&bdi->cgwb_release_mutex);
init_rwsem(&bdi->wb_switch_rwsem);
+ spin_lock_init(&bdi->cgwb_waiters_lock);
ret = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL);
if (!ret) {
Prevent priority inversion problem when a high-priority blkcg issues a sync() and it is forced to wait the completion of all the writeback I/O generated by any other low-priority blkcg, causing massive latencies to processes that shouldn't be I/O-throttled at all. The idea is to save a list of blkcg's that are waiting for writeback: every time a sync() is executed the current blkcg is added to the list. Then, when I/O is throttled, if there's a blkcg waiting for writeback different than the current blkcg, no throttling is applied (we can probably refine this logic later, i.e., a better policy could be to adjust the throttling I/O rate using the blkcg with the highest speed from the list of waiters - priority inheritance, kinda). Signed-off-by: Andrea Righi <righi.andrea@gmail.com> --- block/blk-cgroup.c | 73 ++++++++++++++++++++++++++++++++ block/blk-throttle.c | 11 +++-- fs/fs-writeback.c | 5 +++ fs/sync.c | 8 +++- include/linux/backing-dev-defs.h | 2 + include/linux/blk-cgroup.h | 23 ++++++++++ mm/backing-dev.c | 2 + 7 files changed, 120 insertions(+), 4 deletions(-)