1/ Taking the i_rwsem for swap IO triggers lockdep warnings regarding
possible deadlocks with "fs_reclaim". These deadlocks could, I believe,
eventuate if a buffered read on the swapfile was attempted.
We don't need coherence with the page cache for a swap file, and
buffered writes are forbidden anyway. There is no other need for
i_rwsem during direct IO. So never take it for swap_rw()
2/ generic_write_checks() explicitly forbids writes to swap, and
performs checks that are not needed for swap. So bypass it
for swap_rw().
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
If we are swapping over NFSv4, we may not be able to allocate memory to
start the state-manager thread at the time when we need it.
So keep it always running when swap is enabled, and just signal it to
start.
This requires updating and testing the cl_swapper count on the root
rpc_clnt after following all ->cl_parent links.
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
rpc tasks can be marked as RPC_TASK_SWAPPER. This causes GFP_MEMALLOC
to be used for some allocations. This is needed in some cases, but not
in all where it is currently provided, and in some where it isn't
provided.
Currently *all* tasks associated with a rpc_client on which swap is
enabled get the flag and hence some GFP_MEMALLOC support.
GFP_MEMALLOC is provided for ->buf_alloc() but only swap-writes need it.
However xdr_alloc_bvec does not get GFP_MEMALLOC - though it often does
need it.
xdr_alloc_bvec is called while the XPRT_LOCK is held. If this blocks,
then it blocks all other queued tasks. So this allocation needs
GFP_MEMALLOC for *all* requests, not just writes, when the xprt is used
for any swap writes.
Similarly, if the transport is not connected, that will block all
requests including swap writes, so memory allocations should get
GFP_MEMALLOC if swap writes are possible.
So with this patch:
1/ we ONLY set RPC_TASK_SWAPPER for swap writes.
2/ __rpc_execute() sets PF_MEMALLOC while handling any task
with RPC_TASK_SWAPPER set, or when handling any task that
holds the XPRT_LOCKED lock on an xprt used for swap.
This removes the need for the RPC_IS_SWAPPER() test
in ->buf_alloc handlers.
3/ xprt_prepare_transmit() sets PF_MEMALLOC after locking
any task to a swapper xprt. __rpc_execute() will clear it.
3/ PF_MEMALLOC is set for all the connect workers.
Reviewed-by: Chuck Lever <chuck.lever@oracle.com> (for xprtrdma parts)
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
NFS_RPC_SWAPFLAGS is only used for READ requests.
It sets RPC_TASK_SWAPPER which gives some memory-allocation priority to
requests. This is not needed for swap READ - though it is for writes
where it is set via a different mechanism.
RPC_TASK_ROOTCREDS causes the 'machine' credential to be used.
This is not needed as the root credential is saved when the swap file is
opened, and this is used for all IO.
So NFS_RPC_SWAPFLAGS isn't needed, and as it is the only user of
RPC_TASK_ROOTCREDS, that isn't needed either.
Remove both.
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
This code is pointless as IS_SWAPFILE is always defined.
So remove it.
Suggested-by: Mark Hemment <markhemm@googlemail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
The fscache cookie APIs including fscache_acquire_cookie() and
fscache_relinquish_cookie() now have very good tracing. Thus,
there is no real need for dfprintks in the NFS fscache interface.
The NFS fscache interface has removed all dfprintks so remove the
NFSDBG_FSCACHE defines.
Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Most of fscache and other NFS IO paths are now using tracepoints.
Remove the dfprintks in the NFS fscache read/write page functions
and replace with tracepoints at the begin and end of the functions.
Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Rename NFS fscache functions in a more consistent fashion
to better reflect when we read from and write to fscache.
Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
A number of places in the fscache interface used nfs_inode when inode could
be used, simplifying the code.
Signed-off-by: Dave Wysochanski <dwysocha@redhat.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
In the presence of trunking transports, it's helpful to make sure
that during the migration event, the GETATTR for fs_location attribute
happens on the main transport.
Signed-off-by: Olga Kornievskaia <kolga@netapp.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
[You don't often get email from khoroshilov@ispras.ru. Learn why this is important at http://aka.ms/LearnAboutSenderIdentification.]
Overflow check in not needed anymore after we switch to kmalloc_array().
Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Fixes: a4f743a6bb20 ("NFSv4.1: Convert open-coded array allocation calls to kmalloc_array()")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
As a preparation for moving to -std=gnu11, turn off the
-Wshift-negative-value option. This warning is enabled by gcc when
building with -Wextra for c99 or higher, but not for c89. Since
the kernel already relies on well-defined overflow behavior,
the warning is not helpful and can simply be disabled in
all locations that use -Wextra.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com> # LLVM/Clang v13.0.0 (x86-64)
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
This just puts trace_ext4_fc_commit_start(sb) & ktime_get()
for measuring FC commit time, after the check of whether sb
supports JOURNAL_FAST_COMMIT or not.
Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/d53cf3e535924ec0a1eb41a560e96561b0727e7a.1647057583.git.riteshh@linux.ibm.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Below commit removed all references of EXT4_FC_COMMIT_FAILED.
commit 0915e464cb274 ("ext4: simplify updating of fast commit stats")
Just remove it since it is not used anymore.
Signed-off-by: Ritesh Harjani <riteshh@linux.ibm.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Harshad Shirwadkar <harshadshirwadkar@gmail.com>
Link: https://lore.kernel.org/r/c941357e476be07a1138c7319ca5faab7fb80fc6.1647057583.git.riteshh@linux.ibm.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Recently I've got a report of BUG_ON trigerring during transaction
commit in ext4_journalled_writepage_callback() because we've spotted a
dirty page without buffers. Add WARN_ON_ONCE to
ext4_journalled_set_page_dirty() to catch the problematic condition
earlier where we have better chance of understanding which code path is
creating dirty data without preparing the page properly. Also update the
comment with current information when we are at it.
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20220310101832.5645-1-jack@suse.cz
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
After moving to the new mount API, mb_optimize_scan mount option
handling was not working as expected due to the parsed value always
being overwritten by default. Refactor and fix this to the expected
behavior described below:
* mb_optimize_scan=1 - On
* mb_optimize_scan=0 - Off
* mb_optimize_scan not passed - On if no. of BGs > threshold else off
* Remounts retain previous value unless we explicitly pass the option
with a new value
Fixes: cebe85d570cf ("ext4: switch to the new mount api")
Cc: stable@kernel.org
Reported-by: Ritesh Harjani <riteshh@linux.ibm.com>
Signed-off-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Reviewed-by: Ritesh Harjani <riteshh@linux.ibm.com>
Link: https://lore.kernel.org/r/c98970fe99f26718586d02e942f293300fb48ef3.1646732698.git.ojaswin@linux.ibm.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Julia and the kernel test robot report that the prep handling for this
command inadvertently checks one field twice:
fs/io_uring.c:4338:42-56: duplicated argument to && or ||
Get rid of it.
Reported-by: kernel test robot <lkp@intel.com>
Reported-by: Julia Lawall <julia.lawall@lip6.fr>
Fixes: 4f57f06ce218 ("io_uring: add support for IORING_OP_MSG_RING command")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Merge misc fixes from David Howells:
"A set of patches for watch_queue filter issues noted by Jann. I've
added in a cleanup patch from Christophe Jaillet to convert to using
formal bitmap specifiers for the note allocation bitmap.
Also two filesystem fixes (afs and cachefiles)"
* emailed patches from David Howells <dhowells@redhat.com>:
cachefiles: Fix volume coherency attribute
afs: Fix potential thrashing in afs writeback
watch_queue: Make comment about setting ->defunct more accurate
watch_queue: Fix lack of barrier/sync/lock between post and read
watch_queue: Free the alloc bitmap when the watch_queue is torn down
watch_queue: Fix the alloc bitmap size to reflect notes allocated
watch_queue: Use the bitmap API when applicable
watch_queue: Fix to always request a pow-of-2 pipe ring size
watch_queue: Fix to release page in ->release()
watch_queue, pipe: Free watchqueue state after clearing pipe ring
watch_queue: Fix filter limit check
A network filesystem may set coherency data on a volume cookie, and if
given, cachefiles will store this in an xattr on the directory in the
cache corresponding to the volume.
The function that sets the xattr just stores the contents of the volume
coherency buffer directly into the xattr, with nothing added; the
checking function, on the other hand, has a cut'n'paste error whereby it
tries to interpret the xattr contents as would be the xattr on an
ordinary file (using the cachefiles_xattr struct). This results in a
failure to match the coherency data because the buffer ends up being
shifted by 18 bytes.
Fix this by defining a structure specifically for the volume xattr and
making both the setting and checking functions use it.
Since the volume coherency doesn't work if used, take the opportunity to
insert a reserved field for future use, set it to 0 and check that it is
0. Log mismatch through the appropriate tracepoint.
Note that this only affects cifs; 9p, afs, ceph and nfs don't use the
volume coherency data at the moment.
Fixes: 32e150037dce ("fscache, cachefiles: Store the volume coherency data")
Reported-by: Rohith Surabattula <rohiths.msft@gmail.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
cc: Steve French <smfrench@gmail.com>
cc: linux-cifs@vger.kernel.org
cc: linux-cachefs@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In afs_writepages_region(), if the dirty page we find is undergoing
writeback or write to cache, but the sync_mode is WB_SYNC_NONE, we go
round the loop trying the same page again and again with no pausing or
waiting unless and until another thread manages to clear the writeback
and fscache flags.
Fix this with three measures:
(1) Advance start to after the page we found.
(2) Break out of the loop and return if rescheduling is requested.
(3) Arbitrarily give up after a maximum of 5 skips.
Fixes: 31143d5d515e ("AFS: implement basic file write support")
Reported-by: Marc Dionne <marc.dionne@auristor.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Tested-by: Marc Dionne <marc.dionne@auristor.com>
Acked-by: Marc Dionne <marc.dionne@auristor.com>
Link: https://lore.kernel.org/r/164692725757.2097000.2060513769492301854.stgit@warthog.procyon.org.uk/ # v1
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There's nothing to synchronise post_one_notification() versus
pipe_read(). Whilst posting is done under pipe->rd_wait.lock, the
reader only takes pipe->mutex which cannot bar notification posting as
that may need to be made from contexts that cannot sleep.
Fix this by setting pipe->head with a barrier in post_one_notification()
and reading pipe->head with a barrier in pipe_read().
If that's not sufficient, the rd_wait.lock will need to be taken,
possibly in a ->confirm() op so that it only applies to notifications.
The lock would, however, have to be dropped before copy_page_to_iter()
is invoked.
Fixes: c73be61cede5 ("pipe: Add general notification queue support")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In free_pipe_info(), free the watchqueue state after clearing the pipe
ring as each pipe ring descriptor has a release function, and in the
case of a notification message, this is watch_queue_pipe_buf_release()
which tries to mark the allocation bitmap that was previously released.
Fix this by moving the put of the pipe's ref on the watch queue to after
the ring has been cleared. We still need to call watch_queue_clear()
before doing that to make sure that the pipe is disconnected from any
notification sources first.
Fixes: c73be61cede5 ("pipe: Add general notification queue support")
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
These have been incorrect since the function was introduced.
A proper kerneldoc comment is added since this function, though
static, is part of an external interface.
Reported-by: Dai Ngo <dai.ngo@oracle.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
The common practice is to name function instances the same as the
method names, but with a uniquifying prefix. Commit aef9583b234a
("NFSD: Get reference of lockowner when coping file_lock") missed
this -- the new function names should both have been of the form
"nfsd4_lm_*".
Before more lock manager operations are added in NFSD, rename these
two functions for consistency.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Eventually support for NFSv2 in the Linux NFS server is to be
deprecated and then removed.
However, NFSv2 is the "always supported" version that is available
as soon as CONFIG_NFSD is set. Before NFSv2 support can be removed,
we need to choose a different "always supported" version.
This patch removes CONFIG_NFSD_V3 so that NFSv3 is always supported,
as NFSv2 is today. When NFSv2 support is removed, NFSv3 will become
the only "always supported" NFS version.
The defconfigs still need to be updated to remove CONFIG_NFSD_V3=y.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Now that all of the definitions have moved out of tracehook.h into
ptrace.h, sched/signal.h, resume_user_mode.h there is nothing left in
tracehook.h so remove it.
Update the few files that were depending upon tracehook.h to bring in
definitions to use the headers they need directly.
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20220309162454.123006-13-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
There are a small handful of reasons besides pending signals that the
kernel might want to break out of interruptible sleeps. The flag
TIF_NOTIFY_SIGNAL and the helpers that set and clear TIF_NOTIFY_SIGNAL
provide that the infrastructure for breaking out of interruptible
sleeps and entering the return to user space slow path for those
cases.
Expand tracehook_notify_signal inline in it's callers and remove it,
which makes clear that TIF_NOTIFY_SIGNAL and task_work are separate
concepts.
Update the comment on set_notify_signal to more accurately describe
it's purpose.
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20220309162454.123006-9-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
By default, io_uring will stop submitting a batch of requests if we run
into an error submitting a request. This isn't strictly necessary, as
the error result is passed out-of-band via a CQE anyway. And it can be
a bit confusing for some applications.
Provide a way to setup a ring that will continue submitting on error,
when the error CQE has been posted.
There's still one case that will break out of submission. If we fail
allocating a request, then we'll still return -ENOMEM. We could in theory
post a CQE for that condition too even if we never got a request. Leave
that for a potential followup.
Reported-by: Dylan Yudaken <dylany@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Wrap the test of task->task_works in a helper function to make
it clear what is being tested.
All of the other readers of task->task_work use READ_ONCE and this is
even necessary on current as other processes can update
task->task_work. So for consistency I have added READ_ONCE into
task_work_pending.
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lkml.kernel.org/r/20220309162454.123006-7-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
If we are using provided buffers, it's less than useful to have a buffer
selected and pinned if a request needs to go async or arms poll for
notification trigger on when we can process it.
Recycle the buffer in those events, so we don't pin it for the duration
of the request.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Most of the logic in io_read() deals with regular files, and in some ways
it would make sense to split the handling into S_IFREG and others. But
at least for retry, we don't need to bother setting up a bunch of state
just to abort in the loop later. In particular, don't bother forcing
setup of async data for a normal non-vectored read when we don't need it.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
One of the key architectual tenets is to keep the parameters for
io-uring stable. After the call has been submitted, its value can
be changed. Unfortunaltely this is not the case for the current statx
implementation.
IO-Uring change:
This changes replaces the const char * filename pointer in the io_statx
structure with a struct filename *. In addition it also creates the
filename object during the prepare phase.
With this change, the opcode also needs to invoke cleanup, so the
filename object gets freed after processing the request.
fs change:
This replaces the const char* __user filename parameter in the two
functions do_statx and vfs_statx with a struct filename *. In addition
to be able to correctly construct a filename object a new helper
function getname_statx_lookup_flags is introduced. The function makes
sure that do_statx and vfs_statx is invoked with the correct lookup flags.
Signed-off-by: Stefan Roesch <shr@fb.com>
Link: https://lore.kernel.org/r/20220225185326.1373304-2-shr@fb.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The sqpoll thread can be used for performing the napi busy poll in a
similar way that it does io polling for file systems supporting direct
access bypassing the page cache.
The other way that io_uring can be used for napi busy poll is by
calling io_uring_enter() to get events.
If the user specify a timeout value, it is distributed between polling
and sleeping by using the systemwide setting
/proc/sys/net/core/busy_poll.
The changes have been tested with this program:
https://github.com/lano1106/io_uring_udp_ping
and the result is:
Without sqpoll:
NAPI busy loop disabled:
rtt min/avg/max/mdev = 40.631/42.050/58.667/1.547 us
NAPI busy loop enabled:
rtt min/avg/max/mdev = 30.619/31.753/61.433/1.456 us
With sqpoll:
NAPI busy loop disabled:
rtt min/avg/max/mdev = 42.087/44.438/59.508/1.533 us
NAPI busy loop enabled:
rtt min/avg/max/mdev = 35.779/37.347/52.201/0.924 us
Co-developed-by: Hao Xu <haoxu@linux.alibaba.com>
Signed-off-by: Hao Xu <haoxu@linux.alibaba.com>
Signed-off-by: Olivier Langlois <olivier@trillion01.com>
Link: https://lore.kernel.org/r/810bd9408ffc510ff08269e78dca9df4af0b9e4e.1646777484.git.olivier@trillion01.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This adds support for IORING_OP_MSG_RING, which allows an SQE to signal
another ring. That allows either waking up someone waiting on the ring,
or even passing a 64-bit value via the user_data field in the CQE.
sqe->fd must contain the fd of a ring that should receive the CQE.
sqe->off will be propagated to the cqe->user_data on the target ring,
and sqe->len will be propagated to cqe->res. The results CQE will have
IORING_CQE_F_MSG set in its flags, to indicate that this CQE was generated
from a messaging request rather than a SQE issued locally on that ring.
This effectively allows passing a 64-bit and a 32-bit quantify between
the two rings.
This request type has the following request specific error cases:
- -EBADFD. Set if the sqe->fd doesn't point to a file descriptor that is
of the io_uring type.
- -EOVERFLOW. Set if we were not able to deliver a request to the target
ring.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In testing high frequency workloads with provided buffers, we spend a
lot of time in allocating and freeing the buffer units themselves.
Rather than repeatedly free and alloc them, add a recycling cache
instead. There are two caches:
- ctx->io_buffers_cache. This is the one we grab from in the submission
path, and it's protected by ctx->uring_lock. For inline completions,
we can recycle straight back to this cache and not need any extra
locking.
- ctx->io_buffers_comp. If we're not under uring_lock, then we use this
list to recycle buffers. It's protected by the completion_lock.
On adding a new buffer, check io_buffers_cache. If it's empty, check if
we can splice entries from the io_buffers_comp_cache.
This reduces about 5-10% of overhead from provided buffers, bringing it
pretty close to the non-provided path.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Lots of workloads use multiple threads, in which case the file table is
shared between them. This makes getting and putting the ring file
descriptor for each io_uring_enter(2) system call more expensive, as it
involves an atomic get and put for each call.
Similarly to how we allow registering normal file descriptors to avoid
this overhead, add support for an io_uring_register(2) API that allows
to register the ring fds themselves:
1) IORING_REGISTER_RING_FDS - takes an array of io_uring_rsrc_update
structs, and registers them with the task.
2) IORING_UNREGISTER_RING_FDS - takes an array of io_uring_src_update
structs, and unregisters them.
When a ring fd is registered, it is internally represented by an offset.
This offset is returned to the application, and the application then
uses this offset and sets IORING_ENTER_REGISTERED_RING for the
io_uring_enter(2) system call. This works just like using a registered
file descriptor, rather than a real one, in an SQE, where
IOSQE_FIXED_FILE gets set to tell io_uring that we're using an internal
offset/descriptor rather than a real file descriptor.
In initial testing, this provides a nice bump in performance for
threaded applications in real world cases where the batch count (eg
number of requests submitted per io_uring_enter(2) invocation) is low.
In a microbenchmark, submitting NOP requests, we see the following
increases in performance:
Requests per syscall Baseline Registered Increase
----------------------------------------------------------------
1 ~7030K ~8080K +15%
2 ~13120K ~14800K +13%
4 ~22740K ~25300K +11%
Co-developed-by: Xiaoguang Wang <xiaoguang.wang@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There is a slight optimisation to be had by calculating the correct pos
pointer inside io_kiocb_update_pos and then using that later.
It seems code size drops by a bit:
000000000000a1b0 0000000000000400 t io_read
000000000000a5b0 0000000000000319 t io_write
vs
000000000000a1b0 00000000000003f6 t io_read
000000000000a5b0 0000000000000310 t io_write
Signed-off-by: Dylan Yudaken <dylany@fb.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Update kiocb->ki_pos at execution time rather than in io_prep_rw().
io_prep_rw() happens before the job is enqueued to a worker and so the
offset might be read multiple times before being executed once.
Ensures that the file position in a set of _linked_ SQEs will be only
obtained after earlier SQEs have completed, and so will include their
incremented file position.
Signed-off-by: Dylan Yudaken <dylany@fb.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
io_kiocb_ppos is called in both branches, and it seems that the compiler
does not fuse this. Fusing removes a few bytes from loop_rw_iter.
Before:
$ nm -S fs/io_uring.o | grep loop_rw_iter
0000000000002430 0000000000000124 t loop_rw_iter
After:
$ nm -S fs/io_uring.o | grep loop_rw_iter
0000000000002430 000000000000010d t loop_rw_iter
Signed-off-by: Dylan Yudaken <dylany@fb.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This makes the io-uring tracepoints consistent. Where it makes sense
the tracepoints start with the following four fields:
- context (ring)
- request
- user_data
- opcode.
Signed-off-by: Stefan Roesch <shr@fb.com>
Link: https://lore.kernel.org/r/20220214180430.70572-3-shr@fb.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This introduces the __fill_cqe function. This is necessary
to correctly issue the io_uring_complete tracepoint.
Signed-off-by: Stefan Roesch <shr@fb.com>
Link: https://lore.kernel.org/r/20220214180430.70572-2-shr@fb.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
wqe->lock is abused, it now protects acct->work_list, hash stuff,
nr_workers, wqe->free_list and so on. Lets first get the work_list out
of the wqe-lock mess by introduce a specific lock for work list. This
is the first step to solve the huge contension between work insertion
and work consumption.
good thing:
- split locking for bound and unbound work list
- reduce contension between work_list visit and (worker's)free_list.
For the hash stuff, since there won't be a work with same file in both
bound and unbound work list, thus they won't visit same hash entry. it
works well to use the new lock to protect hash stuff.
Results:
set max_unbound_worker = 4, test with echo-server:
nice -n -15 ./io_uring_echo_server -p 8081 -f -n 1000 -l 16
(-n connection, -l workload)
before this patch:
Samples: 2M of event 'cycles:ppp', Event count (approx.): 1239982111074
Overhead Command Shared Object Symbol
28.59% iou-wrk-10021 [kernel.vmlinux] [k] native_queued_spin_lock_slowpath
8.89% io_uring_echo_s [kernel.vmlinux] [k] native_queued_spin_lock_slowpath
6.20% iou-wrk-10021 [kernel.vmlinux] [k] _raw_spin_lock
2.45% io_uring_echo_s [kernel.vmlinux] [k] io_prep_async_work
2.36% iou-wrk-10021 [kernel.vmlinux] [k] _raw_spin_lock_irqsave
2.29% iou-wrk-10021 [kernel.vmlinux] [k] io_worker_handle_work
1.29% io_uring_echo_s [kernel.vmlinux] [k] io_wqe_enqueue
1.06% iou-wrk-10021 [kernel.vmlinux] [k] io_wqe_worker
1.06% io_uring_echo_s [kernel.vmlinux] [k] _raw_spin_lock
1.03% iou-wrk-10021 [kernel.vmlinux] [k] __schedule
0.99% iou-wrk-10021 [kernel.vmlinux] [k] tcp_sendmsg_locked
with this patch:
Samples: 1M of event 'cycles:ppp', Event count (approx.): 708446691943
Overhead Command Shared Object Symbol
16.86% iou-wrk-10893 [kernel.vmlinux] [k] native_queued_spin_lock_slowpat
9.10% iou-wrk-10893 [kernel.vmlinux] [k] _raw_spin_lock
4.53% io_uring_echo_s [kernel.vmlinux] [k] native_queued_spin_lock_slowpat
2.87% iou-wrk-10893 [kernel.vmlinux] [k] io_worker_handle_work
2.57% iou-wrk-10893 [kernel.vmlinux] [k] _raw_spin_lock_irqsave
2.56% io_uring_echo_s [kernel.vmlinux] [k] io_prep_async_work
1.82% io_uring_echo_s [kernel.vmlinux] [k] _raw_spin_lock
1.33% iou-wrk-10893 [kernel.vmlinux] [k] io_wqe_worker
1.26% io_uring_echo_s [kernel.vmlinux] [k] try_to_wake_up
spin_lock failure from 25.59% + 8.89% = 34.48% to 16.86% + 4.53% = 21.39%
TPS is similar, while cpu usage is from almost 400% to 350%
Signed-off-by: Hao Xu <haoxu@linux.alibaba.com>
Link: https://lore.kernel.org/r/20220206095241.121485-2-haoxu@linux.alibaba.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
