diff options
author | Kai Krakow <kai@kaishome.de> | 2021-02-10 08:07:25 +0300 |
---|---|---|
committer | Jens Axboe <axboe@kernel.dk> | 2021-02-10 18:06:00 +0300 |
commit | 9f233ffe02e5cef611100cd8c5bcf4de26ca7bef (patch) | |
tree | ce11b65a8b1bf85fa471d182a2a9a106ecf602dc /drivers/md/bcache/super.c | |
parent | d7fae7b4fa152795ab70c680d3a63c7843c9368c (diff) | |
download | linux-9f233ffe02e5cef611100cd8c5bcf4de26ca7bef.tar.xz |
Revert "bcache: Kill btree_io_wq"
This reverts commit 56b30770b27d54d68ad51eccc6d888282b568cee.
With the btree using the `system_wq`, I seem to see a lot more desktop
latency than I should.
After some more investigation, it looks like the original assumption
of 56b3077 no longer is true, and bcache has a very high potential of
congesting the `system_wq`. In turn, this introduces laggy desktop
performance, IO stalls (at least with btrfs), and input events may be
delayed.
So let's revert this. It's important to note that the semantics of
using `system_wq` previously mean that `btree_io_wq` should be created
before and destroyed after other bcache wqs to keep the same
assumptions.
Cc: Coly Li <colyli@suse.de>
Cc: stable@vger.kernel.org # 5.4+
Signed-off-by: Kai Krakow <kai@kaishome.de>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'drivers/md/bcache/super.c')
-rw-r--r-- | drivers/md/bcache/super.c | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index dfbaf6aa3e4f..97405aec4b51 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -2821,6 +2821,7 @@ static void bcache_exit(void) destroy_workqueue(bcache_wq); if (bch_journal_wq) destroy_workqueue(bch_journal_wq); + bch_btree_exit(); if (bcache_major) unregister_blkdev(bcache_major, "bcache"); @@ -2876,6 +2877,9 @@ static int __init bcache_init(void) return bcache_major; } + if (bch_btree_init()) + goto err; + bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0); if (!bcache_wq) goto err; |