LGTM except for formatting / an extra newline (will fix) -- in my test branch for possible 4.16
Reviewed-by: Michael Lyle <[email protected]> On 01/26/2018 12:23 AM, [email protected] wrote: > From: Tang Junhui <[email protected]> > > Sometimes, Journal takes up a lot of CPU, we need statistics > to know what's the journal is doing. So this patch provide > some journal statistics: > 1) reclaim: how many times the journal try to reclaim resource, > usually the journal bucket or/and the pin are exhausted. > 2) flush_write: how many times the journal try to flush btree node > to cache device, usually the journal bucket are exhausted. > 3) retry_flush_write: how many times the journal retry to flush > the next btree node, usually the previous tree node have been > flushed by other thread. > we show these statistic by sysfs interface. Through these statistics > We can totally see the status of journal module when the CPU is too > high. > > Signed-off-by: Tang Junhui <[email protected]> > --- > drivers/md/bcache/bcache.h | 5 +++++ > drivers/md/bcache/journal.c | 5 +++++ > drivers/md/bcache/sysfs.c | 15 +++++++++++++++ > 3 files changed, 25 insertions(+) > > diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h > index abd31e8..0432e28 100644 > --- a/drivers/md/bcache/bcache.h > +++ b/drivers/md/bcache/bcache.h > @@ -647,6 +647,11 @@ struct cache_set { > atomic_long_t writeback_keys_done; > atomic_long_t writeback_keys_failed; > > + > + atomic_long_t reclaim; > + atomic_long_t flush_write; > + atomic_long_t retry_flush_write; > + > enum { > ON_ERROR_UNREGISTER, > ON_ERROR_PANIC, > diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c > index 02a98dd..47fd0b8 100644 > --- a/drivers/md/bcache/journal.c > +++ b/drivers/md/bcache/journal.c > @@ -372,6 +372,8 @@ static void btree_flush_write(struct cache_set *c) > */ > struct btree *b, *best; > unsigned i; > + > + atomic_long_inc(&c->flush_write); > retry: > best = NULL; > > @@ -392,6 +394,7 @@ static void btree_flush_write(struct cache_set *c) > if (!btree_current_write(b)->journal) { > mutex_unlock(&b->write_lock); > /* We raced */ > + atomic_long_inc(&c->retry_flush_write); > goto retry; > } > > @@ -471,6 +474,8 @@ static void journal_reclaim(struct cache_set *c) > unsigned iter, n = 0; > atomic_t p; > > + atomic_long_inc(&c->reclaim); > + > while (!atomic_read(&fifo_front(&c->journal.pin))) > fifo_pop(&c->journal.pin, p); > > diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c > index 234b2f5..0afbf1a 100644 > --- a/drivers/md/bcache/sysfs.c > +++ b/drivers/md/bcache/sysfs.c > @@ -65,6 +65,9 @@ > > read_attribute(state); > read_attribute(cache_read_races); > +read_attribute(reclaim); > +read_attribute(flush_write); > +read_attribute(retry_flush_write); > read_attribute(writeback_keys_done); > read_attribute(writeback_keys_failed); > read_attribute(io_errors); > @@ -543,6 +546,15 @@ static unsigned bch_average_key_size(struct cache_set *c) > sysfs_print(cache_read_races, > atomic_long_read(&c->cache_read_races)); > > + sysfs_print(reclaim, > + atomic_long_read(&c->reclaim)); > + > + sysfs_print(flush_write, > + atomic_long_read(&c->flush_write)); > + > + sysfs_print(retry_flush_write, > + atomic_long_read(&c->retry_flush_write)); > + > sysfs_print(writeback_keys_done, > atomic_long_read(&c->writeback_keys_done)); > sysfs_print(writeback_keys_failed, > @@ -729,6 +741,9 @@ static void bch_cache_set_internal_release(struct kobject > *k) > > &sysfs_bset_tree_stats, > &sysfs_cache_read_races, > + &sysfs_reclaim, > + &sysfs_flush_write, > + &sysfs_retry_flush_write, > &sysfs_writeback_keys_done, > &sysfs_writeback_keys_failed, > >
