Jens Axboe [Fri, 30 May 2014 14:25:36 +0000 (08:25 -0600)]
blk-mq: make the sysfs mq/ layout reflect current mappings
Currently blk-mq registers all the hardware queues in sysfs,
regardless of whether it uses them (e.g. they have CPU mappings)
or not. The unused hardware queues lack the cpux/ directories,
and the other sysfs entries (like active, pending, etc) are all
zeroes.
Change this so that sysfs correctly reflects the current mappings
of the hardware queues.
Shaohua Li [Fri, 30 May 2014 14:06:42 +0000 (08:06 -0600)]
blk-mq: blk_mq_tag_to_rq should handle flush request
flush request is special, which borrows the tag from the parent
request. Hence blk_mq_tag_to_rq needs special handling to return
the flush request from the tag.
Signed-off-by: Shaohua Li <shli@fusionio.com> Signed-off-by: Jens Axboe <axboe@fb.com>
Jens Axboe [Thu, 29 May 2014 17:00:11 +0000 (11:00 -0600)]
blk-mq: request initialization optimizations
We currently clear a lot more than we need to, so make that a bit
more clever. Make some of the init dependent on features, like
only setting start_time if we are going to use it.
Jens Axboe [Thu, 29 May 2014 15:53:32 +0000 (09:53 -0600)]
block: add queue flag for disabling SG merging
If devices are not SG starved, we waste a lot of time potentially
collapsing SG segments. Enough that 1.5% of the CPU time goes
to this, at only 400K IOPS. Add a queue flag, QUEUE_FLAG_NO_SG_MERGE,
which just returns the number of vectors in a bio instead of looping
over all segments and checking for collapsible ones.
Add a BLK_MQ_F_SG_MERGE flag so that drivers can opt-in on the sg
merging, if they so desire.
Jens Axboe [Thu, 29 May 2014 14:09:00 +0000 (08:09 -0600)]
block: remove 'magic' from struct blk_plug
I don't think we've ever caught any bugs with this, and there's the
list poisoning for the plug lists to catch uninitialized cases.
So remove the magic member and save 8 bytes in the struct.
Jens Axboe [Wed, 28 May 2014 16:15:41 +0000 (10:15 -0600)]
blk-mq: add file comments and update copyright notices
None of the blk-mq files have an explanatory comment at the top
for what that particular file does. Add that and add appropriate
copyright notices as well.
The current logic for blocking tag allocation is rather confusing, as we
first allocated and then free again a tag in blk_mq_wait_for_tags, just
to attempt a non-blocking allocation and then repeat if someone else
managed to grab the tag before us.
Instead change blk_mq_alloc_request_pinned to simply do a blocking tag
allocation itself and use the request we get back from it.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
blk-mq: add helper to insert requests from irq context
Both the cache flush state machine and the SCSI midlayer want to submit
requests from irq context, and the current per-request requeue_work
unfortunately causes corruption due to sharing with the csd field for
flushes. Replace them with a per-request_queue list of requests to
be requeued.
Based on an earlier test by Ming Lei.
Signed-off-by: Christoph Hellwig <hch@lst.de> Reported-by: Ming Lei <tom.leiming@gmail.com> Tested-by: Ming Lei <tom.leiming@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
Jens Axboe [Tue, 27 May 2014 23:46:48 +0000 (17:46 -0600)]
blk-mq: allow non-softirq completions
Right now we export two ways of completing a request:
1) blk_mq_complete_request(). This uses an IPI (if needed) and
completes through q->softirq_done_fn(). It also works with
timeouts.
2) blk_mq_end_io(). This completes inline, and ignores any timeout
state of the request.
Let blk_mq_complete_request() handle non-softirq_done_fn completions
as well, by just completing inline. If a driver has enough completion
ports to place completions correctly, it need not define a
mq_ops->complete() and we can avoid an indirect function call by
doing the completion inline.
Jens Axboe [Tue, 27 May 2014 18:06:53 +0000 (12:06 -0600)]
blk-mq: pass in suggested NUMA node to ->alloc_hctx()
Drivers currently have to figure this out on their own, and they
are missing information to do it properly. The ones that did
attempt to do it, do it wrong.
So just pass in the suggested node directly to the alloc
function.
Jens Axboe [Fri, 23 May 2014 20:14:57 +0000 (14:14 -0600)]
blk-mq: allow setting of per-request timeouts
Currently blk-mq uses the queue timeout for all requests. But
for some commands, drivers may want to set a specific timeout
for special requests. Allow this to be passed in through
request->timeout, and use it if set.
Sam Bradshaw [Fri, 23 May 2014 19:30:16 +0000 (13:30 -0600)]
blk-mq: export blk_mq_tag_busy_iter
Export the blk-mq in-flight tag iterator for driver consumption.
This is particularly useful in exception paths or SRSI where
in-flight IOs need to be cancelled and/or reissued. The NVMe driver
conversion will use this.
Jens Axboe [Thu, 22 May 2014 16:40:51 +0000 (10:40 -0600)]
blk-mq: split make request handler for multi and single queue
We want slightly different behavior from them:
- On single queue devices, we currently use the per-process plug
for deferred IO and for merging.
- On multi queue devices, we don't use the per-process plug, but
we want to go straight to hardware for SYNC IO.
Split blk_mq_make_request() into a blk_sq_make_request() for single
queue devices, and retain blk_mq_make_request() for multi queue
devices. Then we don't need multiple checks for q->nr_hw_queues
in the request mapping.
Jens Axboe [Wed, 21 May 2014 20:01:15 +0000 (14:01 -0600)]
blk-mq: save memory by freeing requests on unused hardware queues
Depending on the topology of the machine and the number of queues
exposed by a device, we can end up in a situation where some of
the hardware queues are unused (as in, they don't map to any
software queues). For this case, free up the memory used by the
request map, as we will not use it. This can be a substantial
amount of memory, depending on the number of queues vs CPUs and
the queue depth of the device.
Robert Elliott [Tue, 20 May 2014 21:46:26 +0000 (16:46 -0500)]
blk-mq: Micro-optimize blk_queue_nomerges() check
In blk_mq_make_request(), do the blk_queue_nomerges() check
outside the call to blk_attempt_plug_merge() to eliminate
function call overhead when nomerges=2 (disabled)
Signed-off-by: Robert Elliott <elliott@hp.com> Signed-off-by: Jens Axboe <axboe@fb.com>
Jens Axboe [Tue, 20 May 2014 21:17:27 +0000 (15:17 -0600)]
blk-mq: initialize q->nr_requests after calling blk_queue_make_request()
blk_queue_make_requests() overwrites our set value for q->nr_requests,
turning it into the default of 128. Set this appropriately after
initializing queue values in blk_queue_make_request().
Jens Axboe [Tue, 20 May 2014 17:49:02 +0000 (11:49 -0600)]
blk-mq: allow changing of queue depth through sysfs
For request_fn based devices, the block layer exports a 'nr_requests'
file through sysfs to allow adjusting of queue depth on the fly.
Currently this returns -EINVAL for blk-mq, since it's not wired up.
Wire this up for blk-mq, so that it now also always dynamic
adjustments of the allowed queue depth for any given block device
managed by blk-mq.
Jens Axboe [Tue, 20 May 2014 02:01:52 +0000 (20:01 -0600)]
block: move mm/bounce.c to block/
Continue moving some of the block files that are scattered around.
bounce.c contains only code for bouncing the contents of a bio.
It's block proper code, not mm code.
Suggested-by: Ming Lei <tom.leiming@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
Jens Axboe [Mon, 19 May 2014 15:23:55 +0000 (09:23 -0600)]
blk-mq: switch ctx pending map to the sparser blk_align_bitmap
Each hardware queue has a bitmap of software queues with pending
requests. When new IO is queued on a software queue, the bit is
set, and when IO is pruned on a hardware queue run, the bit is
cleared. This causes a lot of traffic. Switch this from the regular
BITS_PER_LONG bitmap to a sparser layout, similarly to what was
done for blk-mq tagging.
20% performance increase was observed for single threaded IO, and
about 15% performanc increase on multiple threads driving the
same device.
Jens Axboe [Mon, 19 May 2014 14:16:41 +0000 (08:16 -0600)]
block: move bio.c and bio-integrity.c from fs/ to block/
They really belong in block/, especially now since it's not in
drivers/block/ anymore. Additionally, the get_maintainer script
gets it wrong when in fs/.
Suggested-by: Christoph Hellwig <hch@infradead.org> Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Signed-off-by: Jens Axboe <axboe@fb.com>
Jens Axboe [Tue, 13 May 2014 21:10:52 +0000 (15:10 -0600)]
blk-mq: improve support for shared tags maps
This adds support for active queue tracking, meaning that the
blk-mq tagging maintains a count of active users of a tag set.
This allows us to maintain a notion of fairness between users,
so that we can distribute the tag depth evenly without starving
some users while allowing others to try unfair deep queues.
If sharing of a tag set is detected, each hardware queue will
track the depth of its own queue. And if this exceeds the total
depth divided by the number of active queues, the user is actively
throttled down.
The active queue count is done lazily to avoid bouncing that data
between submitter and completer. Each hardware queue gets marked
active when it allocates its first tag, and gets marked inactive
when 1) the last tag is cleared, and 2) the queue timeout grace
period has passed.
Ming Lei [Sat, 10 May 2014 21:43:14 +0000 (15:43 -0600)]
blk-mq: bitmap tag: select random tag betweet 0 and (depth - 1)
The selected tag should be selected at random between 0 and
(depth - 1) with probability 1/depth, instead between 0 and
(depth - 2) with probability 1/(depth - 1).
Signed-off-by: Ming Lei <tom.leiming@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
Ming Lei [Sat, 10 May 2014 17:01:48 +0000 (01:01 +0800)]
blk-mq: bitmap tag: use clear_bit_unlock in bt_clear_tag()
The unlock memory barrier need to order access to req in free
path and clearing tag bit, otherwise either request free path
may see a allocated request, or initialized request in allocate
path might be modified by the ongoing free path.
Signed-off-by: Ming Lei <tom.leiming@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
Jens Axboe [Fri, 9 May 2014 21:48:23 +0000 (15:48 -0600)]
block: only calculate part_in_flight() once
We first check if we have inflight IO, then retrieve that
same number again. Usually this isn't that costly since the
chance of having the data dirtied in between is small, but
there's no reason for calling part_in_flight() twice.
Jens Axboe [Fri, 9 May 2014 20:54:08 +0000 (14:54 -0600)]
blk-mq: fix race in IO start accounting
Commit 593ffe46 opened up a small race where we could attempt to
account IO completion on a request, racing with IO start accounting.
Fix this up by ensuring that we've accounted for IO start before
inserting the request.
Jens Axboe [Fri, 9 May 2014 19:41:15 +0000 (13:41 -0600)]
blk-mq: use sparser tag layout for lower queue depth
For best performance, spreading tags over multiple cachelines
makes the tagging more efficient on multicore systems. But since
we have 8 * sizeof(unsigned long) tags per cacheline, we don't
always get a nice spread.
Attempt to spread the tags over at least 4 cachelines, using fewer
number of bits per unsigned long if we have to. This improves
tagging performance in setups with 32-128 tags. For higher depths,
the spread is the same as before (BITS_PER_LONG tags per cacheline).
Jens Axboe [Fri, 9 May 2014 15:36:49 +0000 (09:36 -0600)]
blk-mq: implement new and more efficient tagging scheme
blk-mq currently uses percpu_ida for tag allocation. But that only
works well if the ratio between tag space and number of CPUs is
sufficiently high. For most devices and systems, that is not the
case. The end result if that we either only utilize the tag space
partially, or we end up attempting to fully exhaust it and run
into lots of lock contention with stealing between CPUs. This is
not optimal.
This new tagging scheme is a hybrid bitmap allocator. It uses
two tricks to both be SMP friendly and allow full exhaustion
of the space:
1) We cache the last allocated (or freed) tag on a per blk-mq
software context basis. This allows us to limit the space
we have to search. The key element here is not caching it
in the shared tag structure, otherwise we end up dirtying
more shared cache lines on each allocate/free operation.
2) The tag space is split into cache line sized groups, and
each context will start off randomly in that space. Even up
to full utilization of the space, this divides the tag users
efficiently into cache line groups, avoiding dirtying the same
one both between allocators and between allocator and freeer.
This scheme shows drastically better behaviour, both on small
tag spaces but on large ones as well. It has been tested extensively
to show better performance for all the cases blk-mq cares about.
Jens Axboe [Wed, 7 May 2014 16:26:44 +0000 (10:26 -0600)]
blk-mq: add basic round-robin of what CPU to queue workqueue work on
Right now we just pick the first CPU in the mask, but that can
easily overload that one. Add some basic batching and round-robin
all the entries in the mask instead.
Refactor the logic around adding a new bio to a software queue,
so we nest the ctx->lock where we really need it (merge and
insertion) and don't hold it when we don't (init and IO start
accounting).
blk_mq_wait_for_tags() is only able to wait for "normal" tags,
not reserved tags. Pass in which one we should attempt to get
a tag for, so that waiting for reserved tags will work.
Reserved tags are used for internal commands, which are usually
serialized. Hence no waiting generally takes place, but we should
ensure that it actually works if users need that functionality.
This will be needed for pending changes to the scsi midlayer that now
calls lower level block APIs, as well as any blk-mq driver that wants to
contribute to the random pool.
The blk-mq code is using it's own version of the I/O completion affinity
tunables, which causes a few issues:
- the rq_affinity sysfs file doesn't work for blk-mq devices, even if it
still is present, thus breaking existing tuning setups.
- the rq_affinity = 1 mode, which is the defauly for legacy request based
drivers isn't implemented at all.
- blk-mq drivers don't implement any completion affinity with the default
flag settings.
This patches removes the blk-mq ipi_redirect flag and sysfs file, as well
as the internal BLK_MQ_F_SHOULD_IPI flag and replaces it with code that
respects the queue-wide rq_affinity flags and also implements the
rq_affinity = 1 mode.
This means I/O completion affinity can now only be tuned block-queue wide
instead of per context, which seems more sensible to me anyway.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
If a requeue event races with a timeout, we can get into the
situation where we attempt to complete a request from the
timeout handler when it's not start anymore. This causes a crash.
So have the timeout handler check that REQ_ATOM_STARTED is still
set on the request - if not, we ignore the event. If this happens,
the request has now been marked as complete. As a consequence, we
need to ensure to clear REQ_ATOM_COMPLETE in blk_mq_start_request(),
as to maintain proper request state.
We need selective clearing of the request to make the init-at-free
time completely safe. Otherwise we end up stomping on
rq->atomic_flags, which we don't want to do.
Ming Lei [Sat, 19 Apr 2014 10:00:19 +0000 (18:00 +0800)]
blk-mq: initialize req->q in allocation
The patch basically reverts the patch of(blk-mq:
initialize request on allocation) in Jens's tree(already
in -next), and only initialize req->q in allocation
for two reasons:
- presumed cache hotness on completion
- blk_rq_tagged(rq) depends on reset of req->mq_ctx
Signed-off-by: Ming Lei <tom.leiming@gmail.com> Signed-off-by: Jens Axboe <axboe@fb.com>
Since we are now, by default, applying timer slack to expiry times,
the logic for when to modify a timer in the block code is suboptimal.
The block layer keeps a forward rolling timer per queue for all
requests, and modifies this timer if a request has a shorter timeout
than what the current expiry time is. However, this breaks down
when our rounded timer values get applied slack. Then each new
request ends up modifying the timer, since we're still a little
in front of the timer + slack.
Fix this by allowing a tolerance of HZ / 2, the timeout handling
doesn't need to be very precise. This drastically cuts down
the number of timer modifications we have to make.
Add a helper to unconditionally kick contexts of a queue. This will
be needed by the SCSI layer to provide fair queueing between multiple
devices on a single host.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
Split out the bottom half of blk_mq_end_io so that drivers can perform
work when they know a request has been completed, but before it has been
freed. This also obsoletes blk_mq_end_io_partial as drivers can now
pass any value to blk_update_request directly.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
blk-mq: kill preempt disable/enable in blk_mq_work_fn()
blk_mq_work_fn() is always invoked off the bounded workqueues,
so it can happily preempt among the queues in that set without
causing any issues for blk-mq.
blk-mq: don't use preempt_count() to check for right CPU
UP or CONFIG_PREEMPT_NONE will return 0, and what we really
want to check is whether or not we are on the right CPU.
So don't make PREEMPT part of this, just test the CPU in
the mask directly.
blk-mq: split out tag initialization, support shared tags
Add a new blk_mq_tag_set structure that gets set up before we initialize
the queue. A single blk_mq_tag_set structure can be shared by multiple
queues.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Modular export of blk_mq_{alloc,free}_tagset added by me.
If we want to share tag and request allocation between queues we cannot
initialize the request at init/free time, but need to initialize it
at allocation time as it might get used for different queues over its
lifetime.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
blk-mq: add ->init_request and ->exit_request methods
The current blk_mq_init_commands/blk_mq_free_commands interface has a
two problems:
1) Because only the constructor is passed to blk_mq_init_commands there
is no easy way to clean up when a comman initialization failed. The
current code simply leaks the allocations done in the constructor.
2) There is no good place to call blk_mq_free_commands: before
blk_cleanup_queue there is no guarantee that all outstanding
commands have completed, so we can't free them yet. After
blk_cleanup_queue the queue has usually been freed. This can be
worked around by grabbing an unconditional reference before calling
blk_cleanup_queue and dropping it after blk_mq_free_commands is
done, although that's not exatly pretty and driver writers are
guaranteed to get it wrong sooner or later.
Both issues are easily fixed by making the request constructor and
destructor normal blk_mq_ops methods.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
blk-mq: make ->flush_rq fully transparent to drivers
Drivers shouldn't have to care about the block layer setting aside a
request to implement the flush state machine. We already override the
mq context and tag to make it more transparent, but so far haven't deal
with the driver private data in the request. Make sure to override this
as well, and while we're at it add a proper helper sitting in blk-mq.c
that implements the full impersonation.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
Drivers can reach their private data easily using the blk_mq_rq_to_pdu
helper and don't need req->special. By not initializing it code can
be simplified nicely, and we also shave off a few more instructions from
the I/O path.
Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jens Axboe <axboe@fb.com>
This was used in the olden days, back when onions were proper
yellow. Basically it mapped to the current buffer to be
transferred. With highmem being added more than a decade ago,
most drivers map pages out of a bio, and rq->buffer isn't
pointing at anything valid.
Convert old style drivers to just use bio_data().
For the discard payload use case, just reference the page
in the bio.
cifs: Use min_t() when comparing "size_t" and "unsigned long"
On 32 bit, size_t is "unsigned int", not "unsigned long", causing the
following warning when comparing with PAGE_SIZE, which is always "unsigned
long":
fs/cifs/file.c: In function ‘cifs_readdata_to_iov’:
fs/cifs/file.c:2757: warning: comparison of distinct pointer types lacks a cast
Introduced by commit efa1e6c0ba2e ("cifs_iovec_read: keep iov_iter
between the calls of cifs_readdata_to_iov()"), which changed the
signedness of "remaining" and the code from min_t() to min().
Merge branch 'slab/next' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux
Pull slab changes from Pekka Enberg:
"The biggest change is byte-sized freelist indices which reduces slab
freelist memory usage:
https://lkml.org/lkml/2013/12/2/64"
* 'slab/next' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux:
mm: slab/slub: use page->list consistently instead of page->lru
mm/slab.c: cleanup outdated comments and unify variables naming
slab: fix wrongly used macro
slub: fix high order page allocation problem with __GFP_NOFAIL
slab: Make allocations with GFP_ZERO slightly more efficient
slab: make more slab management structure off the slab
slab: introduce byte sized index for the freelist of a slab
slab: restrict the number of objects in a slab
slab: introduce helper functions to get/set free object
slab: factor out calculate nr objects in cache_estimate