Revert "bcache: Kill btree_io_wq"
authorKai Krakow <kai@kaishome.de>
Wed, 10 Feb 2021 05:07:25 +0000 (13:07 +0800)
committerJens Axboe <axboe@kernel.dk>
Wed, 10 Feb 2021 15:06:00 +0000 (08:06 -0700)
commit9f233ffe02e5cef611100cd8c5bcf4de26ca7bef
treece11b65a8b1bf85fa471d182a2a9a106ecf602dc
parentd7fae7b4fa152795ab70c680d3a63c7843c9368c
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>
drivers/md/bcache/bcache.h
drivers/md/bcache/btree.c
drivers/md/bcache/super.c