Drivers now report to the block layer if they support media change
events. If this is not the case, there's no need to allocate the event
structure, and all event handling code can effectively be skipped. This
simplifies code flow in particular for non-removable sd devices.
This effectively reverts commit 75e3f3ee3c ("block: always allocate
genhd->ev if check_events is implemented").
The sysfs files for the events are kept in place even if no events are
supported, as user space may rely on them being present. The only
difference is that an error code is now returned if the user tries to
set poll_msecs.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin Wilck <mwilck@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently, an empty disk->events field tells the block layer not to
forward media change events to user space. This was done in commit
7c88a168da ("block: don't propagate unlisted DISK_EVENTs to userland")
in order to avoid events from "fringe" drivers to be forwarded to user
space. By doing so, the block layer lost the information which events
were supported by a particular block device, and most importantly,
whether or not a given device supports media change events at all.
Prepare for not interpreting the "events" field this way in the future
any more. This is done by adding an additional field "event_flags" to
struct gendisk, and two flag bits that can be set to have the device
treated like one that had the "events" field set to a non-zero value
before. This applies only to the sd and sr drivers, which are changed to
set the new flags.
The new flags are DISK_EVENT_FLAG_POLL to enforce polling of the device
for synchronous events, and DISK_EVENT_FLAG_UEVENT to tell the
blocklayer to generate udev events from kernel events.
In order to add the event_flags field to struct gendisk, the events
field is converted to an "unsigned short"; it doesn't need to hold
values bigger than 2 anyway.
This patch doesn't change behavior.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin Wilck <mwilck@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The async_events field, intended to be used for drivers that support
asynchronous notifications about disk events (aka media change events),
isn't currently used by any driver, and apparently that has been that
way for a long time (if not forever). Remove it.
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin Wilck <mwilck@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We currently have to call nth_page when iterating over pages inside a
bio_vec. Jens complained a while ago that this is fairly expensive.
To mitigate this we can check that that the actual page structures
are contiguous when adding them to the bio, and just do check pointer
arithmetics later on.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Instead of needing a special macro to iterate over all pages in
a bvec just do a second passs over the whole bio. This also matches
what we do on the release side. The release side helper is moved
up to where we need the get helper to clearly express the symmetry.
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
No caller uses bio_iov_iter_get_pages multiple times on a given bio,
and that funtionality isn't all that useful. Removing it will make
some future changes a little easier and also simplifies the function
a bit.
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Return early on error, and add an unlikely annotation for that case.
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The offset in scatterlists is allowed to be larger than the page size,
so don't go to great length to avoid that case and simplify the
arithmetics.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Commit f6970f83ef ("block: don't check if adjacent bvecs in one bio can
be mergeable") changes bvec merge by only considering two bvecs from
different bios. However, if the former bio doesn't inlcude any io bvec,
then the following warning may be triggered:
warning: ‘bvec.bv_offset’ may be used uninitialized in this function [-Wmaybe-uninitialized]
In practice, it shouldn't be triggered.
Fixes it by adding check on former bio, the check shouldn't add any cost
given 'bio->bi_iter' can be hit in cache.
Reported-by: Jens Axboe <axboe@kernel.dk>
Fixes: f6970f83ef ("block: don't check if adjacent bvecs in one bio can be mergeable")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Some of the comments in the bfq files had typos. This patch fixes them.
Signed-off-by: Angelo Ruocco <angeloruocco90@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The 'def' local variable became unused after commit f382fb0bce ("block: remove
legacy IO schedulers"), let's remove it.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Hisao Tanabe <xtanabe@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
As the function is responsible for executing the individual steps supplied
in the steps argument, execute_steps is a more descriptive name than the
rather generic next.
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Originally each of the opal functions that call next include
opal_discovery0 in the array of steps. This is superfluous and
can be done always inside next.
Acked-by: Jon Derrick <jonathan.derrick@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The steps argument is only read by the next function, so it can
be passed directly as an argument rather than via opal_dev.
Normally, the steps is an array on the stack, so the pointer stops
being valid then the function that set opal_dev.steps returns.
If opal_dev.steps was not set to NULL before return it would become
a dangling pointer. When the steps are passed as argument this
becomes easier to see and more difficult to misuse.
Acked-by: Jon Derrick <jonathan.derrick@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Replace integer literals by Opal tokens defined in opal_proto.h where
possible.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jon Derrick <jonathan.derrick@intel.com>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Instead of having multiple places defining the same argument list to get
a specific column of a sed-opal table, provide a generic version and
call it from those functions.
Co-authored-by: David Kozub <zub@linux.fjfi.cvut.cz>
Signed-off-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Define OPAL_LIFECYCLE token and use it instead of literals in
get_lsp_lifecycle.
Acked-by: Jon Derrick <jonathan.derrick@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Split the header generation from the (normal) memcpy part if a
bytestring is copied into the command buffer. This allows in-place
generation of the bytestring content. For example, copy_from_user may be
used without an intermediate buffer.
Signed-off-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Add function address (and if available its symbol) to the message if a
step function fails.
Signed-off-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jon Derrick <jonathan.derrick@intel.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
response_get_token had already been in place, its functionality had
been duplicated within response_get_{u64,bytestring} with the same error
handling. Unify the handling by reusing response_get_token within the
other functions.
Co-authored-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Signed-off-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
response_get_{string,u64} include error handling for argument resp being
NULL but response_get_token does not handle this.
Make all three of response_get_{string,u64,token} handle NULL resp in
the same way.
Co-authored-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Signed-off-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Every step starts with resetting the cmd buffer as well as the comid and
constructs the appropriate OPAL_CALL command. Consequently, those
actions may be combined into one generic function. On should take care
that the opening and closing tokens for the argument list are already
emitted by cmd_start and cmd_finalize respectively and thus must not be
additionally added.
Co-authored-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Signed-off-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jon Derrick <jonathan.derrick@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Every step ends by calling cmd_finalize (via finalize_and_send)
yet every step adds the token OPAL_ENDLIST on its own. Moving
this into cmd_finalize decreases code duplication.
Co-authored-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Signed-off-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jon Derrick <jonathan.derrick@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
All add_token_* functions have a common set of conditions that have to
be checked. Use a common function for those checks in order to avoid
different behaviour as well as code duplication.
Acked-by: Jon Derrick <jonathan.derrick@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Co-authored-by: David Kozub <zub@linux.fjfi.cvut.cz>
Signed-off-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Also the values of OPAL_UID_LENGTH and OPAL_METHOD_LENGTH are the same,
it is weird to use OPAL_UID_LENGTH for the definition of the methods.
Signed-off-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This should make no change in functionality.
The formatting changes were triggered by checkpatch.pl.
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Reviewed-by: Jon Derrick <jonathan.derrick@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The implementation of IOC_OPAL_ENABLE_DISABLE_MBR handled the value
opal_mbr_data.enable_disable incorrectly: enable_disable is expected
to be one of OPAL_MBR_ENABLE(0) or OPAL_MBR_DISABLE(1). enable_disable
was passed directly to set_mbr_done and set_mbr_enable_disable where
is was interpreted as either OPAL_TRUE(1) or OPAL_FALSE(0). The end
result was that calling IOC_OPAL_ENABLE_DISABLE_MBR with OPAL_MBR_ENABLE
actually disabled the shadow MBR and vice versa.
This patch adds correct conversion from OPAL_MBR_DISABLE/ENABLE to
OPAL_FALSE/TRUE. The change affects existing programs using
IOC_OPAL_ENABLE_DISABLE_MBR but this is typically used only once when
setting up an Opal drive.
Acked-by: Jon Derrick <jonathan.derrick@intel.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Scott Bauer <sbauer@plzdonthack.me>
Signed-off-by: David Kozub <zub@linux.fjfi.cvut.cz>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently support for 64-bit sector_t and blkcnt_t is optional on 32-bit
architectures. These types are required to support block device and/or
file sizes larger than 2 TiB, and have generally defaulted to on for
a long time. Enabling the option only increases the i386 tinyconfig
size by 145 bytes, and many data structures already always use
64-bit values for their in-core and on-disk data structures anyway,
so there should not be a large change in dynamic memory usage either.
Dropping this option removes a somewhat weird non-default config that
has cause various bugs or compiler warnings when actually used.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
With the introduction of BIO_NO_PAGE_REF we've used up all available bits
in bio::bi_flags.
Convert the defines of the flags to an enum and add a BUILD_BUG_ON() call
to make sure no-one adds a new one and thus overrides the BVEC_POOL_IDX
causing crashes.
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Now both passthrough and FS IO have supported multi-page bvec, and
bvec merging has been handled actually when adding page to bio, then
adjacent bvecs won't be mergeable any more if they belong to same bio.
So only try to merge bvecs if they are from different bios.
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Inside __blk_segment_map_sg(), page sized bvec mapping is optimized
a bit with one standalone branch.
So reuse __blk_bvec_map_sg() to do that.
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The argument of 'request_queue' isn't used by __blk_bvec_map_sg(),
so remove it.
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Now block IO stack is basically ready for supporting multi-page bvec,
however it isn't enabled on passthrough IO.
One reason is that passthrough IO is dispatched to LLD directly and bio
split is bypassed, so the bio has to be built correctly for dispatch to
LLD from the beginning.
Implement multi-page support for passthrough IO by limitting each bvec
as block device's segment and applying all kinds of queue limit in
blk_add_pc_page(). Then we don't need to calculate segments any more for
passthrough IO any more, turns out code is simplified much.
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
When the added page is merged to last same page in bio_add_pc_page(),
the user may need to put this page for avoiding page leak.
bio_map_user_iov() needs this kind of handling, and now it deals with
it by itself in hack style.
Moves the handling of put page into __bio_add_pc_page(), so
bio_map_user_iov() may be simplified a bit, and maybe more users
can benefit from this change.
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Now the check for deciding if one page is mergeable to current bvec
becomes a bit complicated, and we need to reuse the code before
adding pc page.
So move the check in one dedicated helper.
No function change.
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
REQ_PC is out of date, so replace it with passthrough IO.
Also remove the local variable of 'prev' since we can reuse
the top local variable of 'bvec'.
No function change.
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For normal filesystem IO, each page is added via blk_add_page(),
in which bvec(page) merge has been handled already, and basically
not possible to merge two adjacent bvecs in one bio.
So not try to merge two adjacent bvecs in blk_queue_split().
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
XEN has special page merge requirement, see xen_biovec_phys_mergeable().
We can't merge pages into one bvec simply for XEN.
So move XEN's specific check on page merge into __bio_try_merge_page(),
then abvoid to break XEN by multi-page bvec.
Cc: ris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: xen-devel@lists.xenproject.org
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
xen_biovec_phys_mergeable() only needs .bv_page of the 2nd bio bvec
for checking if the two bvecs can be merged, so pass page to
xen_biovec_phys_mergeable() directly.
No function change.
Cc: ris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: xen-devel@lists.xenproject.org
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
bfq saves the state of a queue each time a merge occurs, to be
able to resume such a state when the queue is associated again
with its original process, on a split.
Unfortunately bfq does not save & restore also the weight of the
queue. If the weight is not correctly resumed when the queue is
recycled, then the weight of the recycled queue could differ
from the weight of the original queue.
This commit adds the missing save & resume of the weight.
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Francesco Pollicino <fra.fra.800@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The function "bfq_log_bfqq" prints the pid of the process
associated with the queue passed as input.
Unfortunately, if the queue is shared, then more than one process
is associated with the queue. The pid that gets printed in this
case is the pid of one of the associated processes.
Which process gets printed depends on the exact sequence of merge
events the queue underwent. So printing such a pid is rather
useless and above all is often rather confusing because it
reports a random pid between those of the associated processes.
This commit addresses this issue by printing SHARED instead of a pid
if the queue is shared.
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Francesco Pollicino <fra.fra.800@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If many bfq_queues belonging to the same group happen to be created
shortly after each other, then the processes associated with these
queues have typically a common goal. In particular, bursts of queue
creations are usually caused by services or applications that spawn
many parallel threads/processes. Examples are systemd during boot, or
git grep. If there are no other active queues, then, to help these
processes get their job done as soon as possible, the best thing to do
is to reach a high throughput. To this goal, it is usually better to
not grant either weight-raising or device idling to the queues
associated with these processes. And this is exactly what BFQ
currently does.
There is however a drawback: if, in contrast, some other queues are
already active, then the newly created queues must be protected from
the I/O flowing through the already existing queues. In this case, the
best thing to do is the opposite as in the other case: it is much
better to grant weight-raising and device idling to the newly-created
queues, if they deserve it. This commit addresses this issue by doing
so if there are already other active queues.
This change also helps eliminating false positives, which occur when
the newly-created queues do not belong to an actual large burst of
creations, but some background task (e.g., a service) happens to
trigger the creation of new queues in the middle, i.e., very close to
when the victim queues are created. These false positive may cause
total loss of control on process latencies.
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Sync random I/O is likely to be confused with soft real-time I/O,
because it is characterized by limited throughput and apparently
isochronous arrival pattern. To avoid false positives, this commits
prevents bfq_queues containing only random (seeky) I/O from being
tagged as soft real-time.
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
To boost throughput with a set of processes doing interleaved I/O
(i.e., a set of processes whose individual I/O is random, but whose
merged cumulative I/O is sequential), BFQ merges the queues associated
with these processes, i.e., redirects the I/O of these processes into a
common, shared queue. In the shared queue, I/O requests are ordered by
their position on the medium, thus sequential I/O gets dispatched to
the device when the shared queue is served.
Queue merging costs execution time, because, to detect which queues to
merge, BFQ must maintain a list of the head I/O requests of active
queues, ordered by request positions. Measurements showed that this
costs about 10% of BFQ's total per-request processing time.
Request processing time becomes more and more critical as the speed of
the underlying storage device grows. Yet, fortunately, queue merging
is basically useless on the very devices that are so fast to make
request processing time critical. To reach a high throughput, these
devices must have many requests queued at the same time. But, in this
configuration, the internal scheduling algorithms of these devices do
also the job of queue merging: they reorder requests so as to obtain
as much as possible a sequential I/O pattern. As a consequence, with
processes doing interleaved I/O, the throughput reached by one such
device is likely to be the same, with and without queue merging.
In view of this fact, this commit disables queue merging, and all
related housekeeping, for non-rotational devices with internal
queueing. The total, single-lock-protected, per-request processing
time of BFQ drops to, e.g., 1.9 us on an Intel Core i7-2760QM@2.40GHz
(time measured with simple code instrumentation, and using the
throughput-sync.sh script of the S suite [1], in performance-profiling
mode). To put this result into context, the total,
single-lock-protected, per-request execution time of the lightest I/O
scheduler available in blk-mq, mq-deadline, is 0.7 us (mq-deadline is
~800 LOC, against ~10500 LOC for BFQ).
Disabling merging provides a further, remarkable benefit in terms of
throughput. Merging tends to make many workloads artificially more
uneven, mainly because of shared queues remaining non empty for
incomparably more time than normal queues. So, if, e.g., one of the
queues in a set of merged queues has a higher weight than a normal
queue, then the shared queue may inherit such a high weight and, by
staying almost always active, may force BFQ to perform I/O plugging
most of the time. This evidently makes it harder for BFQ to let the
device reach a high throughput.
As a practical example of this problem, and of the benefits of this
commit, we measured again the throughput in the nasty scenario
considered in previous commit messages: dbench test (in the Phoronix
suite), with 6 clients, on a filesystem with journaling, and with the
journaling daemon enjoying a higher weight than normal processes. With
this commit, the throughput grows from ~150 MB/s to ~200 MB/s on a
PLEXTOR PX-256M5 SSD. This is the same peak throughput reached by any
of the other I/O schedulers. As such, this is also likely to be the
maximum possible throughput reachable with this workload on this
device, because I/O is mostly random, and the other schedulers
basically just pass I/O requests to the drive as fast as possible.
[1] https://github.com/Algodev-github/S
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Tested-by: Francesco Pollicino <fra.fra.800@gmail.com>
Signed-off-by: Alessio Masola <alessio.masola@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The processes associated with a bfq_queue, say Q, may happen to
generate their cumulative I/O at a lower rate than the rate at which
the device could serve the same I/O. This is rather probable, e.g., if
only one process is associated with Q and the device is an SSD. It
results in Q becoming often empty while in service. If BFQ is not
allowed to switch to another queue when Q becomes empty, then, during
the service of Q, there will be frequent "service holes", i.e., time
intervals during which Q gets empty and the device can only consume
the I/O already queued in its hardware queues. This easily causes
considerable losses of throughput.
To counter this problem, BFQ implements a request injection mechanism,
which tries to fill the above service holes with I/O requests taken
from other bfq_queues. The hard part in this mechanism is finding the
right amount of I/O to inject, so as to both boost throughput and not
break Q's bandwidth and latency guarantees. To this goal, the current
version of this mechanism measures the bandwidth enjoyed by Q while it
is being served, and tries to inject the maximum possible amount of
extra service that does not cause Q's bandwidth to decrease too
much.
This solution has an important shortcoming. For bandwidth measurements
to be stable and reliable, Q must remain in service for a much longer
time than that needed to serve a single I/O request. Unfortunately,
this does not hold with many workloads. This commit addresses this
issue by changing the way the amount of injection allowed is
dynamically computed. It tunes injection as a function of the service
times of single I/O requests of Q, instead of Q's
bandwidth. Single-request service times are evidently meaningful even
if Q gets very few I/O requests completed while it is in service.
As a testbed for this new solution, we measured the throughput reached
by BFQ for one of the nastiest workloads and configurations for this
scheduler: the workload generated by the dbench test (in the Phoronix
suite), with 6 clients, on a filesystem with journaling, and with the
journaling daemon enjoying a higher weight than normal processes.
With this commit, the throughput grows from ~100 MB/s to ~150 MB/s on
a PLEXTOR PX-256M5.
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Tested-by: Francesco Pollicino <fra.fra.800@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In most cases, it is detrimental for throughput to plug I/O dispatch
when the in-service bfq_queue becomes temporarily empty (plugging is
performed to wait for the possible arrival, soon, of new I/O from the
in-service queue). There is however a case where plugging is needed
for service guarantees. If a bfq_queue, say Q, has a higher weight
than some other active bfq_queue, and is sync, i.e., contains sync
I/O, then, to guarantee that Q does receive a higher share of the
throughput than other lower-weight queues, it is necessary to plug I/O
dispatch when Q remains temporarily empty while being served.
For this reason, BFQ performs I/O plugging when some active bfq_queue
has a higher weight than some other active bfq_queue. But this is
unnecessarily overkill. In fact, if the in-service bfq_queue actually
has a weight lower than or equal to the other queues, then the queue
*must not* be guaranteed a higher share of the throughput than the
other queues. So, not plugging I/O cannot cause any harm to the
queue. And can boost throughput.
Taking advantage of this fact, this commit does not plug I/O for sync
bfq_queues with a weight lower than or equal to the weights of the
other queues. Here is an example of the resulting throughput boost
with the dbench workload, which is particularly nasty for BFQ. With
the dbench test in the Phoronix suite, BFQ reaches its lowest total
throughput with 6 clients on a filesystem with journaling, in case the
journaling daemon has a higher weight than normal processes. Before
this commit, the total throughput was ~80 MB/sec on a PLEXTOR PX-256M5,
after this commit it is ~100 MB/sec.
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
If a sync bfq_queue has a higher weight than some other queue, and
remains temporarily empty while in service, then, to preserve the
bandwidth share of the queue, it is necessary to plug I/O dispatching
until a new request arrives for the queue. In addition, a timeout
needs to be set, to avoid waiting for ever if the process associated
with the queue has actually finished its I/O.
Even with the above timeout, the device is however not fed with new
I/O for a while, if the process has finished its I/O. If this happens
often, then throughput drops and latencies grow. For this reason, the
timeout is kept rather low: 8 ms is the current default.
Unfortunately, such a low value may cause, on the opposite end, a
violation of bandwidth guarantees for a process that happens to issue
new I/O too late. The higher the system load, the higher the
probability that this happens to some process. This is a problem in
scenarios where service guarantees matter more than throughput. One
important case are weight-raised queues, which need to be granted a
very high fraction of the bandwidth.
To address this issue, this commit lower-bounds the plugging timeout
for weight-raised queues to 20 ms. This simple change provides
relevant benefits. For example, on a PLEXTOR PX-256M5S, with which
gnome-terminal starts in 0.6 seconds if there is no other I/O in
progress, the same applications starts in
- 0.8 seconds, instead of 1.2 seconds, if ten files are being read
sequentially in parallel
- 1 second, instead of 2 seconds, if, in parallel, five files are
being read sequentially, and five more files are being written
sequentially
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We now wrap sbitmap waitqueues in an active counter, so we can avoid
iterating wakeups unless we have waiters there. This works as long as
everyone that's manipulating the waitqueues use the proper helpers. For
the tag wait case for shared tags, however, we add ourselves to the
waitqueue without incrementing/decrementing the ->ws_active count. This
means that wakeups can take a long time to happen.
Fix this by manually doing the inc/dec as needed for the wait queue
handling.
Reported-by: Michael Leun <kbug@newton.leun.net>
Tested-by: Michael Leun <kbug@newton.leun.net>
Cc: stable@vger.kernel.org
Reviewed-by: Omar Sandoval <osandov@fb.com>
Fixes: 5d2ee7122c ("sbitmap: optimize wakeup check")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
For now, blk_mq_hctx_has_pending() checks any of ctx, hctx->dispatch
or io scheduler have pending work. So, update the comment accordingly.
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
