The bio_blkcg() function turns out to be inconsistent and consequently
dangerous to use. The first part returns a blkcg where a reference is
owned by the bio meaning it does not need to be rcu protected. However,
the third case, the last line, is problematic:
return css_to_blkcg(task_css(current, io_cgrp_id));
This can race against task migration and the cgroup dying. It is also
semantically different as it must be called rcu protected and is
susceptible to failure when trying to get a reference to it.
This patch adds association ahead of calling bio_blkcg() rather than
after. This makes association a required and explicit step along the
code paths for calling bio_blkcg(). In blk-iolatency, association is
moved above the bio_blkcg() call to ensure it will not return %NULL.
BFQ uses the old bio_blkcg() function, but I do not want to address it
in this series due to the complexity. I have created a private version
documenting the inconsistency and noting not to use it.
Signed-off-by: Dennis Zhou <dennis@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
With the legacy request path gone there is no good reason to keep
queue_lock as a pointer, we can always use the embedded lock now.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Fixed floppy and blk-cgroup missing conversions and half done edits.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Unused now that the legacy request path is gone.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
-----BEGIN PGP SIGNATURE-----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=0zM4
-----END PGP SIGNATURE-----
Merge tag 'for-linus-20181102' of git://git.kernel.dk/linux-block
Pull block layer fixes from Jens Axboe:
"The biggest part of this pull request is the revert of the blkcg
cleanup series. It had one fix earlier for a stacked device issue, but
another one was reported. Rather than play whack-a-mole with this,
revert the entire series and try again for the next kernel release.
Apart from that, only small fixes/changes.
Summary:
- Indentation fixup for mtip32xx (Colin Ian King)
- The blkcg cleanup series revert (Dennis Zhou)
- Two NVMe fixes. One fixing a regression in the nvme request
initialization in this merge window, causing nvme-fc to not work.
The other is a suspend/resume p2p resource issue (James, Keith)
- Fix sg discard merge, allowing us to merge in cases where we didn't
before (Jianchao Wang)
- Call rq_qos_exit() after the queue is frozen, preventing a hang
(Ming)
- Fix brd queue setup, fixing an oops if we fail setting up all
devices (Ming)"
* tag 'for-linus-20181102' of git://git.kernel.dk/linux-block:
nvme-pci: fix conflicting p2p resource adds
nvme-fc: fix request private initialization
blkcg: revert blkcg cleanups series
block: brd: associate with queue until adding disk
block: call rq_qos_exit() after queue is frozen
mtip32xx: clean an indentation issue, remove extraneous tabs
block: fix the DISCARD request merge
There are several definitions of those functions/macros in places that
mess with fixed-point load averages. Provide an official version.
[akpm@linux-foundation.org: fix missed conversion in block/blk-iolatency.c]
Link: http://lkml.kernel.org/r/20180828172258.3185-5-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Suren Baghdasaryan <surenb@google.com>
Tested-by: Daniel Drake <drake@endlessm.com>
Cc: Christopher Lameter <cl@linux.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Johannes Weiner <jweiner@fb.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Enderborg <peter.enderborg@sony.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vinayak Menon <vinmenon@codeaurora.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We apply a smoothing to the scale changes in order to keep sawtoothy
behavior from occurring. However our window for checking if we've
missed our target can sometimes be lower than the smoothing interval
(500ms), especially on faster drives like ssd's. In order to deal with
this keep track of the running tally of the previous intervals that we
threw away because we had already done a scale event recently.
This is needed for the ssd case as these low latency drives will have
bursts of latency, and if it happens to be ok for the window that
directly follows the opening of the scale window we could unthrottle
when previous windows we were missing our target.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We use an average latency approach for determining if we're missing our
latency target. This works well for rotational storage where we have
generally consistent latencies, but for ssd's and other low latency
devices you have more of a spikey behavior, which means we often won't
throttle misbehaving groups because a lot of IO completes at drastically
faster times than our latency target. Instead keep track of how many
IO's miss our target and how many IO's are done in our time window. If
the p(90) latency is above our target then we know we need to throttle.
With this change in place we are seeing the same throttling behavior
with our testcase on ssd's as we see with rotational drives.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There is logic to keep cgroups that haven't done a lot of IO in the most
recent scale window from being punished for over-active higher priority
groups. However for things like ssd's where the windows are pretty
short we'll end up with small numbers of samples, so 5% of samples will
come out to 0 if there aren't enough. Make the floor 1 sample to keep
us from improperly bailing out of scaling down.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Hitting the case where blk_queue_depth() returned 1 uncovered the fact
that iolatency doesn't actually handle this case properly, it simply
doesn't scale down anybody. For this case we should go straight into
applying the time delay, which we weren't doing. Since we already limit
the floor at 1 request this if statement is not needed, and this allows
us to set our depth to 1 which allows us to apply the delay if needed.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
We were using blk_queue_depth() assuming that it would return
nr_requests, but we hit a case in production on drives that had to have
NCQ turned off in order for them to not shit the bed which resulted in a
qd of 1, even though the nr_requests was much larger. iolatency really
only cares about requests we are allowed to queue up, as any io that
get's onto the request list is going to be serviced soonish, so we want
to be throttling before the bio gets onto the request list. To make
iolatency work as expected, simply use q->nr_requests instead of
blk_queue_depth() as that is what we actually care about.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
blkg reference counting now uses percpu_ref rather than atomic_t. Let's
make this consistent with css_tryget. This renames blkg_try_get to
blkg_tryget and now returns a bool rather than the blkg or NULL.
Signed-off-by: Dennis Zhou <dennisszhou@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
bio_issue_init among other things initializes the timestamp for an IO.
Rather than have this logic handled by policies, this consolidates it to
be on the init paths (normal, clone, bounce clone).
Signed-off-by: Dennis Zhou <dennisszhou@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Previously, blkg's were only assigned as needed by blk-iolatency and
blk-throttle. bio->css was also always being associated while blkg was
being looked up and then thrown away in blkcg_bio_issue_check.
This patch begins the cleanup of bio->css and bio->bi_blkg by always
associating a blkg in blkcg_bio_issue_check. This tries to create the
blkg, but if it is not possible, falls back to using the root_blkg of
the request_queue. Therefore, a bio will always be associated with a
blkg. The duplicate association logic is removed from blk-throttle and
blk-iolatency.
Signed-off-by: Dennis Zhou <dennisszhou@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
To know when to create a blkg, the general pattern is to do a
blkg_lookup and if that fails, lock and then do a lookup again and if
that fails finally create. It doesn't make much sense for everyone who
wants to do creation to write this themselves.
This changes blkg_lookup_create to do locking and implement this
pattern. The old blkg_lookup_create is renamed to __blkg_lookup_create.
If a call site wants to do its own error handling or already owns the
queue lock, they can use __blkg_lookup_create. This will be used in
upcoming patches.
Signed-off-by: Dennis Zhou <dennisszhou@gmail.com>
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The accessor function bio_blkcg either returns the blkcg associated with
the bio or finds one in the current context. This can cause an issue
when trying to associate a bio with a blkcg. Particularly, it's the
third case that is problematic:
return css_to_blkcg(task_css(current, io_cgrp_id));
As the above may race against task migration and the cgroup exiting, it
is not always ok to take a reference on the blkcg returned from
bio_blkcg.
This patch adds association ahead of calling bio_blkcg rather than
after. This makes association a required and explicit step along the
code paths for calling bio_blkcg. blk_get_rl is modified as well to get
a reference to the blkcg it may use and blk_put_rl will always put the
reference back. Association is also moved above the bio_blkcg call to
ensure it will not return NULL in blk-iolatency.
BFQ and CFQ utilize this flaw, but due to the complexity, I do not want
to address this in this series. I've created a private version of the
function with notes not to use it describing the flaw. Hopefully soon,
that code can be cleaned up.
Signed-off-by: Dennis Zhou <dennisszhou@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Fixes gcc '-Wunused-but-set-variable' warning:
block/blk-iolatency.c: In function 'scale_change':
block/blk-iolatency.c:301:7: warning:
variable 'changed' set but not used [-Wunused-but-set-variable]
block/blk-iolatency.c: In function 'iolatency_set_limit':
block/blk-iolatency.c:765:24: warning:
variable 'blkiolat' set but not used [-Wunused-but-set-variable]
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Currently, avg_lat is calculated by accumulating the mean of every
window in a long running cumulative average. As time goes on, the metric
becomes less and less useful due to the accumulated history.
This patch reuses the same calculation done in load averages to make the
avg_lat metric more lively. Unlike load averages, the avg only advances
when a window elapses (due to an io). Idle periods extend the most
recent window. Bucketing is used to limit the history of avg_lat by
binding it to the window size. So, the window range for 1/exp (decay
rate) is [1 min, 2.5 min) when windows elapse immediately.
The current sample window size is exposed in the debug info to enable
calculation of the window range.
Signed-off-by: Dennis Zhou <dennisszhou@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
At this point we have a ref on the blkg, we need to drop it if we don't
have a iolat.
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In our longer tests we noticed that some boxes would degrade to the
point of uselessness. This is because we truncate the current time when
saving it in our bio, but I was using the raw current time to subtract
from. So once the box had been up a certain amount of time it would
appear as if our IO's were taking several years to complete. Fix this
by truncating the current time so it matches the issue time. Verified
this worked by running with this patch for a week on our test tier.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Early versions of these patches had us waiting for seconds at a time
during submission, so we had to adjust the timing window we monitored
for latency. Now we don't do things like that so this is unnecessary
code.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
max_depth used to be a u64, but I changed it to a unsigned int but
didn't convert my comparisons over everywhere. Fix by using UINT_MAX
everywhere instead of (u64)-1.
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
On 32-bit architectures, dividing a 64-bit number needs to use the
do_div() function or something like it to avoid a link failure:
block/blk-iolatency.o: In function `iolatency_prfill_limit':
blk-iolatency.c:(.text+0x8cc): undefined reference to `__aeabi_uldivmod'
Using div_u64() gives us the best output and avoids the need for an
explicit cast.
Fixes: d706751215 ("block: introduce blk-iolatency io controller")
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Current IO controllers for the block layer are less than ideal for our
use case. The io.max controller is great at hard limiting, but it is
not work conserving. This patch introduces io.latency. You provide a
latency target for your group and we monitor the io in short windows to
make sure we are not exceeding those latency targets. This makes use of
the rq-qos infrastructure and works much like the wbt stuff. There are
a few differences from wbt
- It's bio based, so the latency covers the whole block layer in addition to
the actual io.
- We will throttle all IO types that comes in here if we need to.
- We use the mean latency over the 100ms window. This is because writes can
be particularly fast, which could give us a false sense of the impact of
other workloads on our protected workload.
- By default there's no throttling, we set the queue_depth to INT_MAX so that
we can have as many outstanding bio's as we're allowed to. Only at
throttle time do we pay attention to the actual queue depth.
- We backcharge cgroups for root cg issued IO and induce artificial
delays in order to deal with cases like metadata only or swap heavy
workloads.
In testing this has worked out relatively well. Protected workloads
will throttle noisy workloads down to 1 io at time if they are doing
normal IO on their own, or induce up to a 1 second delay per syscall if
they are doing a lot of root issued IO (metadata/swap IO).
Our testing has revolved mostly around our production web servers where
we have hhvm (the web server application) in a protected group and
everything else in another group. We see slightly higher requests per
second (RPS) on the test tier vs the control tier, and much more stable
RPS across all machines in the test tier vs the control tier.
Another test we run is a slow memory allocator in the unprotected group.
Before this would eventually push us into swap and cause the whole box
to die and not recover at all. With these patches we see slight RPS
drops (usually 10-15%) before the memory consumer is properly killed and
things recover within seconds.
Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
