The invariant of io_wq_work_list is that it's empty IFF ->first is NULL,
so no need to initially set ->last. With now having more users of the
list it may play a role, i.e. used in each tw iteration and on every
completion flushing.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/c464ab5cab6e46a858c6d39c107e92b3b5291f13.1633373302.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Even after fully inlining io_alloc_req() my compiler does a NULL check
in the path of successful allocation, no hacks like an empty dereference
help it. Restructure io_alloc_req() by splitting out refilling part, so
the compiler generate a slightly better binary.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/eda17571bdc7248d8e617b23e7132a5416e4680b.1633373302.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_req_complete_state() is inlined and used in lots of places, so we
want to keep it concise. Move adding a request into a completion batch
list from io_req_complete_state() into the consumer, i.e.
__io_queue_sqe().
before vs after
text data bss dec hex filename
91894 14002 8 105904 19db0 ./fs/io_uring.o
91046 14002 8 105056 19a60 ./fs/io_uring.o
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/4afca4e11abfd4cc8e99777fdcaf4d34cf4d022d.1633373302.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We want ->comp_list in the second cacheline, which is hotter comparing
to the 3rd. Swap the field with ->link, which is not as hot and
controlled by flags and so not accessed unless there is a link.
By the way add a couple of comments for io_kiocb fields.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/9d9dde31f8f62279a5f48c575bbc27b8290edc0c.1633373302.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For some reason non-off IORING_OP_TIMEOUT always fails links, it's
pretty inconvenient and unnecessary limits chaining after it to hard
linking, which is far from ideal, e.g. doesn't pair well with timeout
cancellation. Add a flag forcing it to not fail links on -ETIME.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/17c7ec0fb7a6113cc6be8cdaedcada0ba836ac0e.1633199723.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Put an explicit check for number of requests to submit. First,
we can turn while into do-while and it generates better code, and second
that if can be cheaper, e.g. by using CPU flags after sub in
io_sqring_entries().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/5926baadd20c28feab7a5e1725fedf32e4553ff7.1632516769.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If a request completed inline the result should only be zero, it's a
grave error otherwise. So, when we see REQ_F_COMPLETE_INLINE it's not
even necessary to check the return code, and the flag check can be moved
earlier.
It's one "if" less for inline completions, and same two checks for it
normally completing (ret == 0). Those are two cases we care about the
most.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/ebd4e397a9c26d96c99b24447acc309741041a83.1632516769.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Extract slow paths from __io_queue_sqe() into a function and inline the
hot path. With that we have everything completely inlined on the
submission path up until io_issue_sqe().
-> io_submit_sqes()
-> io_submit_sqe() (inlined)
-> io_queue_sqe() (inlined)
-> __io_queue_sqe() (inlined)
-> io_issue_sqe()
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/f1606864d95d7f26dc28c7eec3dc6ed6ec32618a.1632516769.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We don't want the slow path of io_queue_sqe to be inlined, so extract a
function from it.
text data bss dec hex filename
91950 13986 8 105944 19dd8 ./fs/io_uring.o
91758 13986 8 105752 19d18 ./fs/io_uring.o
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/fb01253911f8fb374268f65b1ba939b54ca6583f.1632516769.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
req->ctx->active_drain is a bit too expensive, partially because of two
dereferences. Do a trick, if we see it set in io_init_req(), set
REQ_F_FORCE_ASYNC and it automatically goes through a slower path where
we can catch it. It's nearly free to do in io_init_req() because there
is already ->restricted check and it's in the same byte of a bitmask.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/d7e7ddc63c15e8a300833132abb3eb8fd3918aef.1632516769.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There are two call sites of io_queue_sqe() in io_submit_sqe(), combine
them into one, because io_queue_sqe() is inline and we don't want to
bloat binary, and will become even bigger
text data bss dec hex filename
92126 13986 8 106120 19e88 ./fs/io_uring.o
91966 13986 8 105960 19de8 ./fs/io_uring.o
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/506124b8e767f0a4576f7a459f6aea3d13fb4dda.1632516769.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
First, convert rest of iopoll bits to single linked lists, and also
replace per-request list_add_tail() with splicing a part of slist.
With that, use io_free_batch_list() to put/free requests. The main
advantage of it is that it's now the only user of struct req_batch and
friends, and so they can be inlined. The main overhead there was
per-request call to not-inlined io_req_free_batch(), which is expensive
enough.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/b37fc6d5954b241e025eead7ab92c6f44a42f229.1632516769.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Convert explicit barrier around iopoll_completed to smp_load_acquire()
and smp_store_release(). Similar on the callback side, but replaces a
single smp_rmb() with per-request smp_load_acquire(), neither imply any
extra CPU ordering for x86. Use READ_ONCE as usual where it doesn't
matter.
Use it to move filling CQEs by iopoll earlier, that will be necessary
to avoid traversing the list one extra time in the future.
Suggested-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/8bd663cb15efdc72d6247c38ee810964e744a450.1632516769.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The main loop of io_do_iopoll() iterates and does ->iopoll() until it
meets a first completed request, then it continues from that position
and splices requests to pass them through io_iopoll_complete().
Split the loop in two for clearness, iopolling and reaping completed
requests from the list.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/a7f6fd27a94845e5dc925a47a4a9765a92e514fb.1632516769.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Apart from just using lists (i.e. io_wq_work_list), we also want to have
stacks, which are a bit faster, and have some interoperability between
them. Add a stack implementation based on io_wq_work_node and some
helpers.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/5d3a412a5ac0d47e0f0499d70d2207d70a68925e.1632516769.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently we collect requests for completion batching in an array.
Replace them with a singly linked list. It's as fast as arrays but
doesn't take some much space in ctx, and will be used in future patches.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/a666826f2854d17e9fb9417fb302edfeb750f425.1632516769.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We don't really need to pass the number of requests to complete into
io_do_iopoll(), a flag whether to enforce non-spin mode is enough.
Should be straightforward, maybe except io_iopoll_check(). We pass !min
there, because we do never enter with the number of already reaped
requests is larger than the specified @min, apart from the first
iteration, where nr_events is 0 and so the final check should be
identical.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/782b39d1d8ec584eae15bca0a1feb6f0571fe5b8.1632516769.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Hint the compiler that it's not as likely to have creds different from
current attached to a request. The current code generation is far from
ideal, hopefully it can help to some compilers to remove duplicated jump
tables and so.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/e7815251ac4bf5a4a23d298c752f029ae19f3837.1632516769.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
IOSQE_IO_DRAIN is quite marginal and we don't care too much about
IOSQE_BUFFER_SELECT. Save to ifs and hide both of them under
SQE_VALID_FLAGS check. Now we first check whether it uses a "safe"
subset, i.e. without DRAIN and BUFFER_SELECT, and only if it's not
true we test the rest of the flags.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/dccfb9ab2ab0969a2d8dc59af88fa0ce44eeb1d5.1631703764.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Now completions are done from task context, that means that it's either
the task itself, task_work or io-wq worker. In all those cases the ctx
will be staying alive by mutexing, explicit referencing or req references
by iowq. Remove extra ctx pinning from io_req_complete_post().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/60a0e96434c16ab4fe587651448290d61ec9a113.1631703756.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Developers may need some uring info to help themselves debug and address
issues in production. This includes sqring/cqring head/tail and the
detailed sqe/cqe info, which is very useful when an application is hung
on a ring.
Signed-off-by: Hao Xu <haoxu@linux.alibaba.com>
Link: https://lore.kernel.org/r/20210913130854.38542-1-haoxu@linux.alibaba.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We don't do io_submit_flush_completions() when there is no requests
enqueued, and every single caller checks for it. Hide that check into
the function not forgetting about inlining. That will make it much
easier for changing the empty check condition in the future.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/d7ff8cef5da1b38e8ea648f5aad9a315ddfc7b57.1631115443.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
->ios_left is only used to decide whether to plug or not, kill it to
avoid this extra accounting, just use the initial submission number.
There is no much difference in regards of enabling plugging, where this
one does it in a few more cases, but all major ones should be covered
well.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/f13993bcf5b477f9a7d52881fc49f9457ea9870a.1631115443.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
While task_work_add() in io_workqueue_create() is true,
then duplicate code is executed:
-> clear_bit_unlock(0, &worker->create_state);
-> io_worker_release(worker);
-> atomic_dec(&acct->nr_running);
-> io_worker_ref_put(wq);
-> return false;
-> clear_bit_unlock(0, &worker->create_state); // back to io_workqueue_create()
-> io_worker_release(worker);
-> kfree(worker);
The io_worker_release() and clear_bit_unlock() are executed twice.
Fixes: 3146cba99a ("io-wq: make worker creation resilient against signals")
Signed-off-by: Bixuan Cui <cuibixuan@huawei.com>
Link: https://lore.kernel.org/r/20210911085847.34849-1-cuibixuan@huawei.com
Reviwed-by: Hao Xu <haoxu@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
I recently had to look at a production problem where a request ended
up getting the dreaded -EINVAL error on submit. The most used and
hence useless of error codes, as it just tells you that something
was wrong with your request, but not more than that.
Let's dump the full sqe contents if we run into an issue failure,
that'll allow easier diagnosing of a wide variety of issues.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We added RQF_ELV to tell whether there's an IO scheduler attached, and
RQF_ELVPRIV tells us whether there's an IO scheduler with private data
attached. Don't check RQF_ELV in blk_mq_free_request(), what we care
about here is just if we have scheduler private data attached.
This fixes a boot crash
Fixes: 2ff0682da6 ("block: store elevator state in request")
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Reported-by: syzbot+eb8104072aeab6cc1195@syzkaller.appspotmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Trivial to do now, just need our own io_comp_batch on the stack and pass
that in to the usual command completion handling.
I pondered making this dependent on how many entries we had to process,
but even for a single entry there's no discernable difference in
performance or latency. Running a sync workload over io_uring:
t/io_uring -b512 -d1 -s1 -c1 -p0 -F1 -B1 -n2 /dev/nvme1n1 /dev/nvme2n1
yields the below performance before the patch:
IOPS=254820, BW=124MiB/s, IOS/call=1/1, inflight=(1 1)
IOPS=251174, BW=122MiB/s, IOS/call=1/1, inflight=(1 1)
IOPS=250806, BW=122MiB/s, IOS/call=1/1, inflight=(1 1)
and the following after:
IOPS=255972, BW=124MiB/s, IOS/call=1/1, inflight=(1 1)
IOPS=251920, BW=123MiB/s, IOS/call=1/1, inflight=(1 1)
IOPS=251794, BW=122MiB/s, IOS/call=1/1, inflight=(1 1)
which definitely isn't slower, about the same if you factor in a bit of
variance. For peak performance workloads, benchmarking shows a 2%
improvement.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Wire up using an io_comp_batch for f_op->iopoll(). If the lower stack
supports it, we can handle high rates of polled IO more efficiently.
This raises the single core efficiency on my system from ~6.1M IOPS to
~6.6M IOPS running a random read workload at depth 128 on two gen2
Optane drives.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Take advantage of struct io_comp_batch, if passed in to the nvme poll
handler. If it's set, rather than complete each request individually
inline, store them in the io_comp_batch list. We only do so for requests
that will complete successfully, anything else will be completed inline as
before.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Instead of calling blk_mq_end_request() on a single request, add a helper
that takes the new struct io_comp_batch and completes any request stored
in there.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
