To maximise responsiveness, BFQ raises the weight, and performs device
idling, for bfq_queues associated with processes deemed as
interactive. In particular, weight raising has a maximum duration,
equal to the time needed to start a large application. If a
weight-raised process goes on doing I/O beyond this maximum duration,
it loses weight-raising.
This mechanism is evidently vulnerable to the following false
positives: I/O-bound applications that will go on doing I/O for much
longer than the duration of weight-raising. These applications have
basically no benefit from being weight-raised at the beginning of
their I/O. On the opposite end, while being weight-raised, these
applications
a) unjustly steal throughput to applications that may truly need
low latency;
b) make BFQ uselessly perform device idling; device idling results
in loss of device throughput with most flash-based storage, and may
increase latencies when used purposelessly.
This commit adds a countermeasure to reduce both the above
problems. To introduce this countermeasure, we provide the following
extra piece of information (full details in the comments added by this
commit). During the start-up of the large application used as a
reference to set the duration of weight-raising, involved processes
transfer at most ~110K sectors each. Accordingly, a process initially
deemed as interactive has no right to be weight-raised any longer,
once transferred 110K sectors or more.
Basing on this consideration, this commit early-ends weight-raising
for a bfq_queue if the latter happens to have received an amount of
service at least equal to 110K sectors (actually, a little bit more,
to keep a safety margin). I/O-bound applications that reach a high
throughput, such as file copy, get to this threshold much before the
allowed weight-raising period finishes. Thus this early ending of
weight-raising reduces the amount of time during which these
applications cause the problems described above.
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Asynchronous I/O can easily starve synchronous I/O (both sync reads
and sync writes), by consuming all request tags. Similarly, storms of
synchronous writes, such as those that sync(2) may trigger, can starve
synchronous reads. In their turn, these two problems may also cause
BFQ to loose control on latency for interactive and soft real-time
applications. For example, on a PLEXTOR PX-256M5S SSD, LibreOffice
Writer takes 0.6 seconds to start if the device is idle, but it takes
more than 45 seconds (!) if there are sequential writes in the
background.
This commit addresses this issue by limiting the maximum percentage of
tags that asynchronous I/O requests and synchronous write requests can
consume. In particular, this commit grants a higher threshold to
synchronous writes, to prevent the latter from being starved by
asynchronous I/O.
According to the above test, LibreOffice Writer now starts in about
1.2 seconds on average, regardless of the background workload, and
apart from some rare outlier. To check this improvement, run, e.g.,
sudo ./comm_startup_lat.sh bfq 5 5 seq 10 "lowriter --terminate_after_init"
for the comm_startup_lat benchmark in the S suite [1].
[1] https://github.com/Algodev-github/S
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In BFQ and CFQ, two processes are said to be cooperating if they do
I/O in such a way that the union of their I/O requests yields a
sequential I/O pattern. To get such a sequential I/O pattern out of
the non-sequential pattern of each cooperating process, BFQ and CFQ
merge the queues associated with these processes. In more detail,
cooperating processes, and thus their associated queues, usually
start, or restart, to do I/O shortly after each other. This is the
case, e.g., for the I/O threads of KVM/QEMU and of the dump
utility. Basing on this assumption, this commit allows a bfq_queue to
be merged only during a short time interval (100ms) after it starts,
or re-starts, to do I/O. This filtering provides two important
benefits.
First, it greatly reduces the probability that two non-cooperating
processes have their queues merged by mistake, if they just happen to
do I/O close to each other for a short time interval. These spurious
merges cause loss of service guarantees. A low-weight bfq_queue may
unjustly get more than its expected share of the throughput: if such a
low-weight queue is merged with a high-weight queue, then the I/O for
the low-weight queue is served as if the queue had a high weight. This
may damage other high-weight queues unexpectedly. For instance,
because of this issue, lxterminal occasionally took 7.5 seconds to
start, instead of 6.5 seconds, when some sequential readers and
writers did I/O in the background on a FUJITSU MHX2300BT HDD. The
reason is that the bfq_queues associated with some of the readers or
the writers were merged with the high-weight queues of some processes
that had to do some urgent but little I/O. The readers then exploited
the inherited high weight for all or most of their I/O, during the
start-up of terminal. The filtering introduced by this commit
eliminated any outlier caused by spurious queue merges in our start-up
time tests.
This filtering also provides a little boost of the throughput
sustainable by BFQ: 3-4%, depending on the CPU. The reason is that,
once a bfq_queue cannot be merged any longer, this commit makes BFQ
stop updating the data needed to handle merging for the queue.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Angelo Ruocco <angeloruocco90@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
BFQ currently creates, and updates, its own instance of the whole
set of blkio statistics that cfq creates. Yet, from the comments
of Tejun Heo in [1], it turned out that most of these statistics
are meant/useful only for debugging. This commit makes BFQ create
the latter, debugging statistics only if the option
CONFIG_DEBUG_BLK_CGROUP is set.
By doing so, this commit also enables BFQ to enjoy a high perfomance
boost. The reason is that, if CONFIG_DEBUG_BLK_CGROUP is not set, then
BFQ has to update far fewer statistics, and, in particular, not the
heaviest to update. To give an idea of the benefits, if
CONFIG_DEBUG_BLK_CGROUP is not set, then, on an Intel i7-4850HQ, and
with 8 threads doing random I/O in parallel on null_blk (configured
with 0 latency), the throughput of BFQ grows from 310 to 400 KIOPS
(+30%). We have measured similar or even much higher boosts with other
CPUs: e.g., +45% with an ARM CortexTM-A53 Octa-core. Our results have
been obtained and can be reproduced very easily with the script in [1].
[1] https://www.spinics.net/lists/linux-block/msg18943.html
Suggested-by: Tejun Heo <tj@kernel.org>
Suggested-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Luca Miccio <lucmiccio@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
To provide a very smooth service, bfq starts to serve a bfq_queue
only if the queue is 'eligible', i.e., if the same queue would
have started to be served in the ideal, perfectly fair system that
bfq simulates internally. This is obtained by associating each
queue with a virtual start time, and by computing a special system
virtual time quantity: a queue is eligible only if the system
virtual time has reached the virtual start time of the
queue. Finally, bfq guarantees that, when a new queue must be set
in service, there is always at least one eligible entity for each
active parent entity in the scheduler. To provide this guarantee,
the function __bfq_lookup_next_entity pushes up, for each parent
entity on which it is invoked, the system virtual time to the
minimum among the virtual start times of the entities in the
active tree for the parent entity (more precisely, the push up
occurs if the system virtual time happens to be lower than all
such virtual start times).
There is however a circumstance in which __bfq_lookup_next_entity
cannot push up the system virtual time for a parent entity, even
if the system virtual time is lower than the virtual start times
of all the child entities in the active tree. It happens if one of
the child entities is in service. In fact, in such a case, there
is already an eligible entity, the in-service one, even if it may
not be not present in the active tree (because in-service entities
may be removed from the active tree).
Unfortunately, in the last re-design of the
hierarchical-scheduling engine, the reset of the pointer to the
in-service entity for a given parent entity--reset to be done as a
consequence of the expiration of the in-service entity--always
happens after the function __bfq_lookup_next_entity has been
invoked. This causes the function to think that there is still an
entity in service for the parent entity, and then that the system
virtual time cannot be pushed up, even if actually such a
no-more-in-service entity has already been properly reinserted
into the active tree (or in some other tree if no more
active). Yet, the system virtual time *had* to be pushed up, to be
ready to correctly choose the next queue to serve. Because of the
lack of this push up, bfq may wrongly set in service a queue that
had been speculatively pre-computed as the possible
next-in-service queue, but that would no more be the one to serve
after the expiration and the reinsertion into the active trees of
the previously in-service entities.
This commit addresses this issue by making
__bfq_lookup_next_entity properly push up the system virtual time
if an expiration is occurring.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The logic that decides whether to idle the device is scattered across
three functions. Almost all of the logic is in the function
bfq_bfqq_may_idle, but (1) part of the decision is made in
bfq_update_idle_window, and (2) the function bfq_bfqq_must_idle may
switch off idling regardless of the output of bfq_bfqq_may_idle. In
addition, both bfq_update_idle_window and bfq_bfqq_must_idle make
their decisions as a function of parameters that are used, for similar
purposes, also in bfq_bfqq_may_idle. This commit addresses these
issues by moving all the logic into bfq_bfqq_may_idle.
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Groups of BFQ queues are represented by generic entities in BFQ. When
a queue belonging to a parent entity is deactivated, the parent entity
may need to be deactivated too, in case the deactivated queue was the
only active queue for the parent entity. This deactivation may need to
be propagated upwards if the entity belongs, in its turn, to a further
higher-level entity, and so on. In particular, the upward propagation
of deactivation stops at the first parent entity that remains active
even if one of its child entities has been deactivated.
To decide whether the last non-deactivation condition holds for a
parent entity, BFQ checks whether the field next_in_service is still
not NULL for the parent entity, after the deactivation of one of its
child entity. If it is not NULL, then there are certainly other active
entities in the parent entity, and deactivations can stop.
Unfortunately, this check misses a corner case: if in_service_entity
is not NULL, then next_in_service may happen to be NULL, although the
parent entity is evidently active. This happens if: 1) the entity
pointed by in_service_entity is the only active entity in the parent
entity, and 2) according to the definition of next_in_service, the
in_service_entity cannot be considered as next_in_service. See the
comments on the definition of next_in_service for details on this
second point.
Hitting the above corner case causes crashes.
To address this issue, this commit:
1) Extends the above check on only next_in_service to controlling both
next_in_service and in_service_entity (if any of them is not NULL,
then no further deactivation is performed)
2) Improves the (important) comments on how next_in_service is defined
and updated; in particular it fixes a few rather obscure paragraphs
Reported-by: Eric Wheeler <bfq-sched@lists.ewheeler.net>
Reported-by: Rick Yiu <rick_yiu@htc.com>
Reported-by: Tom X Nguyen <tom81094@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Eric Wheeler <bfq-sched@lists.ewheeler.net>
Tested-by: Rick Yiu <rick_yiu@htc.com>
Tested-by: Laurentiu Nicola <lnicola@dend.ro>
Tested-by: Tom X Nguyen <tom81094@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently cfq/bfq/blk-throttle output cgroup info in trace in their own
way. Now we have standard blktrace API for this, so convert them to use
it.
Note, this changes the behavior a little bit. cgroup info isn't output
by default, we only do this with 'blk_cgroup' option enabled. cgroup
info isn't output as a string by default too, we only do this with
'blk_cgname' option enabled. Also cgroup info is output in different
position of the note string. I think these behavior changes aren't a big
issue (actually we make trace data shorter which is good), since the
blktrace note is solely for debugging.
Signed-off-by: Shaohua Li <shli@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The start time of eligible entity should be less than or equal to
the current virtual time, and the entity in idle tree has a finish
time being greater than the current virtual time.
Signed-off-by: Hou Tao <houtao1@huawei.com>
Reviewed-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
On each deactivation or re-scheduling (after being served) of a
bfq_queue, BFQ invokes the function __bfq_entity_update_weight_prio(),
to perform pending updates of ioprio, weight and ioprio class for the
bfq_queue. BFQ also invokes this function on I/O-request dispatches,
to raise or lower weights more quickly when needed, thereby improving
latency. However, the entity representing the bfq_queue may be on the
active (sub)tree of a service tree when this happens, and, although
with a very low probability, the bfq_queue may happen to also have a
pending change of its ioprio class. If both conditions hold when
__bfq_entity_update_weight_prio() is invoked, then the entity moves to
a sort of hybrid state: the new service tree for the entity, as
returned by bfq_entity_service_tree(), differs from service tree on
which the entity still is. The functions that handle activations and
deactivations of entities do not cope with such a hybrid state (and
would need to become more complex to cope).
This commit addresses this issue by just making
__bfq_entity_update_weight_prio() not perform also a possible pending
change of ioprio class, when invoked on an I/O-request dispatch for a
bfq_queue. Such a change is thus postponed to when
__bfq_entity_update_weight_prio() is invoked on deactivation or
re-scheduling of the bfq_queue.
Reported-by: Marco Piazza <mpiazza@gmail.com>
Reported-by: Laurentiu Nicola <lnicola@dend.ro>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Marco Piazza <mpiazza@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In blk-cgroup, operations on blkg objects are protected with the
request_queue lock. This is no more the lock that protects
I/O-scheduler operations in blk-mq. In fact, the latter are now
protected with a finer-grained per-scheduler-instance lock. As a
consequence, although blkg lookups are also rcu-protected, blk-mq I/O
schedulers may see inconsistent data when they access blkg and
blkg-related objects. BFQ does access these objects, and does incur
this problem, in the following case.
The blkg_lookup performed in bfq_get_queue, being protected (only)
through rcu, may happen to return the address of a copy of the
original blkg. If this is the case, then the blkg_get performed in
bfq_get_queue, to pin down the blkg, is useless: it does not prevent
blk-cgroup code from destroying both the original blkg and all objects
directly or indirectly referred by the copy of the blkg. BFQ accesses
these objects, which typically causes a crash for NULL-pointer
dereference of memory-protection violation.
Some additional protection mechanism should be added to blk-cgroup to
address this issue. In the meantime, this commit provides a quick
temporary fix for BFQ: cache (when safe) blkg data that might
disappear right after a blkg_lookup.
In particular, this commit exploits the following facts to achieve its
goal without introducing further locks. Destroy operations on a blkg
invoke, as a first step, hooks of the scheduler associated with the
blkg. And these hooks are executed with bfqd->lock held for BFQ. As a
consequence, for any blkg associated with the request queue an
instance of BFQ is attached to, we are guaranteed that such a blkg is
not destroyed, and that all the pointers it contains are consistent,
while that instance is holding its bfqd->lock. A blkg_lookup performed
with bfqd->lock held then returns a fully consistent blkg, which
remains consistent until this lock is held. In more detail, this holds
even if the returned blkg is a copy of the original one.
Finally, also the object describing a group inside BFQ needs to be
protected from destruction on the blkg_free of the original blkg
(which invokes bfq_pd_free). This commit adds private refcounting for
this object, to let it disappear only after no bfq_queue refers to it
any longer.
This commit also removes or updates some stale comments on locking
issues related to blk-cgroup operations.
Reported-by: Tomas Konir <tomas.konir@gmail.com>
Reported-by: Lee Tibbert <lee.tibbert@gmail.com>
Reported-by: Marco Piazza <mpiazza@gmail.com>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Tested-by: Tomas Konir <tomas.konir@gmail.com>
Tested-by: Lee Tibbert <lee.tibbert@gmail.com>
Tested-by: Marco Piazza <mpiazza@gmail.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
If we don't have CGROUPS enabled, the compile ends in the
following misery:
In file included from ../block/bfq-iosched.c:105:0:
../block/bfq-iosched.h:819:22: error: array type has incomplete element type
extern struct cftype bfq_blkcg_legacy_files[];
^
../block/bfq-iosched.h:820:22: error: array type has incomplete element type
extern struct cftype bfq_blkg_files[];
^
Move the declarations under the right ifdef.
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
The BFQ I/O scheduler features an optimal fair-queuing
(proportional-share) scheduling algorithm, enriched with several
mechanisms to boost throughput and reduce latency for interactive and
real-time applications. This makes BFQ a large and complex piece of
code. This commit addresses this issue by splitting BFQ into three
main, independent components, and by moving each component into a
separate source file:
1. Main algorithm: handles the interaction with the kernel, and
decides which requests to dispatch; it uses the following two further
components to achieve its goals.
2. Scheduling engine (Hierarchical B-WF2Q+ scheduling algorithm):
computes the schedule, using weights and budgets provided by the above
component.
3. cgroups support: handles group operations (creation, destruction,
move, ...).
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@fb.com>
Paolo Valente