All of lore.kernel.org
 help / color / mirror / Atom feed
From: Coly Li <colyli@suse.de>
To: axboe@kernel.dk
Cc: linux-bcache@vger.kernel.org, linux-block@vger.kernel.org,
	Coly Li <colyli@suse.de>
Subject: [PATCH 01/37] bcache: don't set max writeback rate if gc is running
Date: Fri, 28 Jun 2019 19:59:24 +0800	[thread overview]
Message-ID: <20190628120000.40753-2-colyli@suse.de> (raw)
In-Reply-To: <20190628120000.40753-1-colyli@suse.de>

When gc is running, user space I/O processes may wait inside
bcache code, so no new I/O coming. Indeed this is not a real idle
time, maximum writeback rate should not be set in such situation.
Otherwise a faster writeback thread may compete locks with gc thread
and makes garbage collection slower, which results a longer I/O
freeze period.

This patch checks c->gc_mark_valid in set_at_max_writeback_rate(). If
c->gc_mark_valid is 0 (gc running), set_at_max_writeback_rate() returns
false, then update_writeback_rate() will not set writeback rate to
maximum value even c->idle_counter reaches an idle threshold.

Now writeback thread won't interfere gc thread performance.

Signed-off-by: Coly Li <colyli@suse.de>
---
 drivers/md/bcache/writeback.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 73f0efac2b9f..262f7ef20992 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -122,6 +122,9 @@ static void __update_writeback_rate(struct cached_dev *dc)
 static bool set_at_max_writeback_rate(struct cache_set *c,
 				       struct cached_dev *dc)
 {
+	/* Don't set max writeback rate if gc is running */
+	if (!c->gc_mark_valid)
+		return false;
 	/*
 	 * Idle_counter is increased everytime when update_writeback_rate() is
 	 * called. If all backing devices attached to the same cache set have
-- 
2.16.4


  reply	other threads:[~2019-06-28 12:00 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-28 11:59 [PATCH 00/37] bcache patches for Linux v5.3 Coly Li
2019-06-28 11:59 ` Coly Li [this message]
2019-06-28 11:59 ` [PATCH 02/37] bcache: check c->gc_thread by IS_ERR_OR_NULL in cache_set_flush() Coly Li
2019-06-28 11:59 ` [PATCH 03/37] bcache: fix return value error in bch_journal_read() Coly Li
2019-06-28 11:59 ` [PATCH 04/37] Revert "bcache: set CACHE_SET_IO_DISABLE in bch_cached_dev_error()" Coly Li
2019-06-28 11:59 ` [PATCH 05/37] bcache: avoid flushing btree node in cache_set_flush() if io disabled Coly Li
2019-06-28 11:59 ` [PATCH 06/37] bcache: ignore read-ahead request failure on backing device Coly Li
2019-06-28 11:59 ` [PATCH 07/37] bcache: add io error counting in write_bdev_super_endio() Coly Li
2019-06-28 11:59 ` [PATCH 08/37] bcache: remove unnecessary prefetch() in bset_search_tree() Coly Li
2019-06-28 11:59 ` [PATCH 09/37] bcache: use sysfs_match_string() instead of __sysfs_match_string() Coly Li
2019-06-28 11:59 ` [PATCH 10/37] bcache: add return value check to bch_cached_dev_run() Coly Li
2019-06-28 11:59 ` [PATCH 11/37] bcache: remove unncessary code in bch_btree_keys_init() Coly Li
2019-06-28 11:59 ` [PATCH 12/37] bcache: check CACHE_SET_IO_DISABLE in allocator code Coly Li
2019-06-28 11:59 ` [PATCH 13/37] bcache: check CACHE_SET_IO_DISABLE bit in bch_journal() Coly Li
2019-06-28 11:59 ` [PATCH 14/37] bcache: more detailed error message to bcache_device_link() Coly Li
2019-06-28 11:59 ` [PATCH 15/37] bcache: add more error message in bch_cached_dev_attach() Coly Li
2019-06-28 11:59 ` [PATCH 16/37] bcache: improve error message in bch_cached_dev_run() Coly Li
2019-06-28 11:59 ` [PATCH 17/37] bcache: remove "XXX:" comment line from run_cache_set() Coly Li
2019-06-28 11:59 ` [PATCH 18/37] bcache: make bset_search_tree() be more understandable Coly Li
2019-06-28 11:59 ` [PATCH 19/37] bcache: add pendings_cleanup to stop pending bcache device Coly Li
2019-06-28 11:59 ` [PATCH 20/37] bcache: fix mistaken sysfs entry for io_error counter Coly Li
2019-06-28 11:59 ` [PATCH 21/37] bcache: destroy dc->writeback_write_wq if failed to create dc->writeback_thread Coly Li
2019-06-28 11:59 ` [PATCH 22/37] bcache: stop writeback kthread and kworker when bch_cached_dev_run() failed Coly Li
2019-06-28 11:59 ` [PATCH 23/37] bcache: avoid a deadlock in bcache_reboot() Coly Li
2019-06-28 11:59 ` [PATCH 24/37] bcache: acquire bch_register_lock later in cached_dev_detach_finish() Coly Li
2019-06-28 11:59 ` [PATCH 25/37] bcache: acquire bch_register_lock later in cached_dev_free() Coly Li
2019-06-28 11:59 ` [PATCH 26/37] bcache: fix potential deadlock in cached_def_free() Coly Li
2019-06-28 11:59 ` [PATCH 27/37] bcache: add code comments for journal_read_bucket() Coly Li
2019-06-28 11:59 ` [PATCH 28/37] bcache: set largest seq to ja->seq[bucket_index] in journal_read_bucket() Coly Li
2019-06-28 11:59 ` [PATCH 29/37] bcache: shrink btree node cache after bch_btree_check() Coly Li
2019-06-28 11:59 ` [PATCH 30/37] bcache: Revert "bcache: free heap cache_set->flush_btree in bch_journal_free" Coly Li
2019-06-28 11:59 ` [PATCH 31/37] bcache: Revert "bcache: fix high CPU occupancy during journal" Coly Li
2019-06-28 11:59 ` [PATCH 32/37] bcache: only clear BTREE_NODE_dirty bit when it is set Coly Li
2019-06-28 11:59 ` [PATCH 33/37] bcache: add comments for mutex_lock(&b->write_lock) Coly Li
2019-06-28 11:59 ` [PATCH 34/37] bcache: remove retry_flush_write from struct cache_set Coly Li
2019-06-28 11:59 ` [PATCH 35/37] bcache: fix race in btree_flush_write() Coly Li
2019-06-28 11:59 ` [PATCH 36/37] bcache: performance improvement for btree_flush_write() Coly Li
2019-06-28 12:00 ` [PATCH 37/37] bcache: add reclaimed_journal_buckets to struct cache_set Coly Li
2019-06-28 13:42 ` [PATCH 00/37] bcache patches for Linux v5.3 Jens Axboe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190628120000.40753-2-colyli@suse.de \
    --to=colyli@suse.de \
    --cc=axboe@kernel.dk \
    --cc=linux-bcache@vger.kernel.org \
    --cc=linux-block@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.