bcache: set max writeback rate when I/O request is idle
Subsystems (2)
A message that is not in the archive (sent off-list or not yet received): [email protected]
PATCH 1/1 bcache: set max writeback rate when I/O request is idle
From: Coly Li <[email protected]>
Commit b1092c9af9ed ("bcache: allow quick writeback when backing idle") allows the writeback rate to be faster if there is no I/O request on a bcache device. It works well if there is only one bcache device attached to the cache set. If there are many bcache devices attached to a cache set, it may introduce performance regression because multiple faster writeback threads of the idle bcache devices will compete the btree level locks with the bcache device who have I/O requests coming.
This patch fixes the above issue by only permitting fast writebac when all bcache devices attached on the cache set are idle. And if one of the bcache devices has new I/O request coming, minimized all writeback throughput immediately and let PI controller __update_writeback_rate() to decide the upcoming writeback rate for each bcache device.
Also when all bcache devices are idle, limited wrieback rate to a small number is wast of thoughput, especially when backing devices are slower non-rotation devices (e.g. SATA SSD). This patch sets a max writeback rate for each backing device if the whole cache set is idle. A faster writeback rate in idle time means new I/Os may have more available space for dirty data, and people may observe a better write performance then.
Please note bcache may change its cache mode in run time, and this patch still works if the cache mode is switched from writeback mode and there is still dirty data on cache.
--- drivers/md/bcache/bcache.h | 10 ++--- drivers/md/bcache/request.c | 54 ++++++++++++++++++++++++- drivers/md/bcache/super.c | 4 ++ drivers/md/bcache/sysfs.c | 14 +++++-- drivers/md/bcache/util.c | 2 +- drivers/md/bcache/util.h | 2 +- drivers/md/bcache/writeback.c | 91 +++++++++++++++++++++++++++++-------------- 7 files changed, 133 insertions(+), 44 deletions(-)
drivers/md/bcache/bcache.h +3 -7
@@ -328,13 +328,6 @@ struct cached_dev {*/ atomic_t has_dirty; -/* -* Set to zero by things that touch the backing volume-- except -* writeback. Incremented by writeback. Used to determine when to -* accelerate idle writeback. -*/ -atomic_t backing_idle; -struct bch_ratelimit writeback_rate;struct delayed_work writeback_rate_update;
@@ -514,6 +507,8 @@ struct cache_set {struct cache_accounting accounting;unsigned long flags; +atomic_t idle_counter; +atomic_t at_max_writeback_rate;struct cache_sb sb;
@@ -523,6 +518,7 @@ struct cache_set {struct bcache_device **devices;unsigned devices_max_used; +atomic_t attached_dev_nr;struct list_head cached_devs;uint64_t cached_dev_sectors;struct closure caching;
drivers/md/bcache/request.c +53 -1
66 lines not on this page · raw message
drivers/md/bcache/super.c +4 -0
@@ -696,6 +696,8 @@ static void bcache_device_detach(struct bcache_device *d) {lockdep_assert_held (&bch_register_lock); +atomic_dec (&d->c->attached_dev_nr); +if (test_bit (BCACHE_DEV_DETACHING , &d->flags)) {struct uuid_entry *u = d->c->uuids + d->id;
@@ -1138,6 +1140,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,bch_cached_dev_run (dc);bcache_device_link (&dc->disk, c,"bdev" ); +atomic_inc (&c->attached_dev_nr);/* Allow the writeback thread to proceed */ up_write (&dc->writeback_lock);
@@ -1687,6 +1690,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) c->block_bits =ilog2 (sb->block_size); c->nr_uuids =bucket_bytes (c) /sizeof (struct uuid_entry ); c->devices_max_used =0 ; +atomic_set (&c->attached_dev_nr,0 ); c->btree_pages =bucket_pages (c);if (c->btree_pages >BTREE_MAX_PAGES ) c->btree_pages = max_t(int, c->btree_pages / 4,
drivers/md/bcache/sysfs.c +10 -4
@@ -170,7 +170,8 @@ SHOW(__bch_cached_dev)var_printf (writeback_running,"%i" );var_print (writeback_delay);var_print (writeback_percent); -sysfs_hprint (writeback_rate, dc->writeback_rate.rate <<9 ); +sysfs_hprint (writeback_rate, +atomic_long_read (&dc->writeback_rate.rate) <<9 );sysfs_hprint (io_errors,atomic_read (&dc->io_errors));sysfs_printf (io_error_limit,"%i" , dc->error_limit);sysfs_printf (io_disable,"%i" , dc->io_disable);
@@ -188,7 +189,8 @@ SHOW(__bch_cached_dev)char change[20 ];s64 next_io; -bch_hprint (rate, dc->writeback_rate.rate <<9 ); +bch_hprint (rate, +atomic_long_read (&dc->writeback_rate.rate) <<9 );bch_hprint (dirty,bcache_dev_sectors_dirty (&dc->disk) <<9 );bch_hprint (target, dc->writeback_rate_target <<9 );bch_hprint (proportional,dc->writeback_rate_proportional <<9 );
@@ -255,8 +257,12 @@ STORE(__cached_dev)sysfs_strtoul_clamp (writeback_percent, dc->writeback_percent,0 ,40 ); -sysfs_strtoul_clamp (writeback_rate, - dc->writeback_rate.rate,1 ,INT_MAX ); +if (attr == &sysfs_writeback_rate) { +int v; + +sysfs_strtoul_clamp (writeback_rate, v,1 ,INT_MAX ); +atomic_long_set (&dc->writeback_rate.rate, v); + } sysfs_strtoul_clamp(writeback_rate_update_seconds, dc->writeback_rate_update_seconds,
drivers/md/bcache/util.c +1 -1
@@ -200,7 +200,7 @@ uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done) {uint64_t now =local_clock (); - d->next +=div_u64 (done *NSEC_PER_SEC , d->rate); + d->next +=div_u64 (done *NSEC_PER_SEC ,atomic_long_read (&d->rate));/* Bound the time. Don't let us fall further than 2 seconds behind * (this prevents unnecessary backlog that would make it impossible
drivers/md/bcache/util.h +1 -1
@@ -442,7 +442,7 @@ struct bch_ratelimit {* Rate at which we want to do work, in units per second * The units here correspond to the units passed to bch_next_delay() */ -uint32_t rate; +atomic_long_t rate; };static inline void bch_ratelimit_reset (struct bch_ratelimit *d)
drivers/md/bcache/writeback.c +61 -30
119 lines not on this page · raw message
Signature · 1 line
2.16.4
Greg KH
maintainerQuoted 27 lines · Kai Krakow
From: Coly Li <[email protected]>
Commit
b1092c9af9ed("bcache: allow quick writeback when backing idle") allows the writeback rate to be faster if there is no I/O request on a bcache device. It works well if there is only one bcache device attached to the cache set. If there are many bcache devices attached to a cache set, it may introduce performance regression because multiple faster writeback threads of the idle bcache devices will compete the btree level locks with the bcache device who have I/O requests coming.This patch fixes the above issue by only permitting fast writebac when all bcache devices attached on the cache set are idle. And if one of the bcache devices has new I/O request coming, minimized all writeback throughput immediately and let PI controller
__update_writeback_rate()to decide the upcoming writeback rate for each bcache device.Also when all bcache devices are idle, limited wrieback rate to a small number is wast of thoughput, especially when backing devices are slower non-rotation devices (e.g. SATA SSD). This patch sets a max writeback rate for each backing device if the whole cache set is idle. A faster writeback rate in idle time means new I/Os may have more available space for dirty data, and people may observe a better write performance then.
Please note bcache may change its cache mode in run time, and this patch still works if the cache mode is switched from writeback mode and there is still dirty data on cache.
Quoted 9 lines
Fixes Commit b1092c9af9ed ("bcache: allow quick writeback when backing idle")Cc [email protected] #4.16+Signed-off-by Coly Li <[email protected]>Tested-by Kai Krakow <[email protected]>Tested-by Stefan Priebe <[email protected]>Cc Michael Lyle <[email protected]>Signed-off-by Jens Axboe <[email protected]>(cherry picked from commit ea8c5356d39048bc94bae068228f51ddbecc6b89)Signed-off-by Kai Krakow <[email protected]>
Given the size of this, and the fact that no one responded, I'm going to drop this from my review queue now, sorry. If you get some testers, please feel free to resend it.
thanks,
greg k-h