[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <1381224862-5299-1-git-send-email-m@bjorling.me>
Date: Tue, 8 Oct 2013 11:34:20 +0200
From: Matias Bjørling <m@...rling.me>
To: axboe@...nel.dk, willy@...ux.intel.com
Cc: linux-kernel@...r.kernel.org, linux-nvme@...ts.infradead.org,
Matias Bjørling <m@...rling.me>
Subject: [PATCH RFC 0/2] Convert from bio-based to blk-mq
These patches are against the "new-queue" branch in Axboe's repo:
git://git.kernel.dk/linux-block.git
The nvme driver implements itself as a bio-based driver. This primarily because
of high lock congestion for high-performance nvm devices. To remove the
congestion, a multi-queue block layer is being implemented.
These patches enable mq within the nvme driver. The first patch is a simple
blkmq fix. While the second implements the beginning of the nvme mq support.
Outstanding work:
* Use reserved tags for admin queue. Should this be implemented as an admin
queue within mq?
* Move cmdid into blk mq and use request tagging.
* Notify mq of nvme device stripe size.
* Let mq know and handle BIOVEC_NOT_VIRT_MERGEABLE.
I crave some feedback on whether it's on the right path, before I break the bio
path apart and put it together again.
Matias Bjørling (2):
blk-mq: call exit_hctx on hw queue teardown
NVMe: rfc blk-mq support
block/blk-mq.c | 2 +
drivers/block/nvme-core.c | 404 +++++++++++++++++-----------------------------
include/linux/nvme.h | 3 +-
3 files changed, 155 insertions(+), 254 deletions(-)
--
1.8.1.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists