Currently, request_queue has one request_list to allocate requests
from regardless of blkcg of the IO being issued. When the unified
request pool is used up, cfq proportional IO limits become meaningless
- whoever grabs the next request being freed wins the race regardless
of the configured weights.
This can be easily demonstrated by creating a blkio cgroup w/ very low
weight, put a program which can issue a lot of random direct IOs there
and running a sequential IO from a different cgroup. As soon as the
request pool is used up, the sequential IO bandwidth crashes.
This patch implements per-blkg request_list. Each blkg has its own
request_list and any IO allocates its request from the matching blkg
making blkcgs completely isolated in terms of request allocation.
* Root blkcg uses the request_list embedded in each request_queue,
which was renamed to @q->root_rl from @q->rq. While making blkcg rl
handling a bit harier, this enables avoiding most overhead for root
blkcg.
* Queue fullness is properly per request_list but bdi isn't blkcg
aware yet, so congestion state currently just follows the root
blkcg. As writeback isn't aware of blkcg yet, this works okay for
async congestion but readahead may get the wrong signals. It's
better than blkcg completely collapsing with shared request_list but
needs to be improved with future changes.
* After this change, each block cgroup gets a full request pool making
resource consumption of each cgroup higher. This makes allowing
non-root users to create cgroups less desirable; however, note that
allowing non-root users to directly manage cgroups is already
severely broken regardless of this patch - each block cgroup
consumes kernel memory and skews IO weight (IO weights are not
hierarchical).
v2: queue-sysfs.txt updated and patch description udpated as suggested
by Vivek.
v3: blk_get_rl() wasn't checking error return from
blkg_lookup_create() and may cause oops on lookup failure. Fix it
by falling back to root_rl on blkg lookup failures. This problem
was spotted by Rakesh Iyer <rni@google.com>.
v4: Updated to accomodate 458f27a982 "block: Avoid missed wakeup in
request waitqueue". blk_drain_queue() now wakes up waiters on all
blkg->rl on the target queue.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
There are numerous broken references to Documentation files (in other
Documentation files, in comments, etc.). These broken references are
caused by typo's in the references, and by renames or removals of the
Documentation files. Some broken references are simply odd.
Fix these broken references, sometimes by dropping the irrelevant text
they were part of.
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
There are always questions about why CFQ is idling on various conditions.
Recent ones is Christoph asking again why to idle on REQ_NOIDLE. His
assertion is that XFS is relying more and more on workqueues and is
concerned that CFQ idling on IO from every workqueue will impact
XFS badly.
So he suggested that I add some more documentation about CFQ idling
and that can provide more clarity on the topic and also gives an
opprotunity to poke a hole in theory and lead to improvements.
So here is my attempt at that. Any comments are welcome.
Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Some systems benefit from completions always being steered to the strict
requester cpu rather than the looser "per-socket" steering that
blk_cpu_to_group() attempts by default. This is because the first
CPU in the group mask ends up being completely overloaded with work,
while the others (including the original submitter) has power left
to spare.
Allow the strict mode to be set by writing '2' to the sysfs control
file. This is identical to the scheme used for the nomerges file,
where '2' is a more aggressive setting than just being turned on.
echo 2 > /sys/block/<bdev>/queue/rq_affinity
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Roland Dreier <roland@purestorage.com>
Tested-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Code has been converted over to the new explicit on-stack plugging,
and delay users have been converted to use the new API for that.
So lets kill off the old plugging along with aops->sync_page().
Signed-off-by: Jens Axboe <jaxboe@fusionio.com>
Updated 'nomerges' tunable to accept a value of '2' - indicating that _no_
merges at all are to be attempted (not even the simple one-hit cache).
The following table illustrates the additional benefit - 5 minute runs of
a random I/O load were applied to a dozen devices on a 16-way x86_64 system.
nomerges Throughput %System Improvement (tput / %sys)
-------- ------------ ----------- -------------------------
0 12.45 MB/sec 0.669365609
1 12.50 MB/sec 0.641519199 0.40% / 2.71%
2 12.52 MB/sec 0.639849750 0.56% / 2.96%
Signed-off-by: Alan D. Brunelle <alan.brunelle@hp.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
We do per-device plugging, get rid of any references to tq_disk as that
has been dead since 2.6.5 or so.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
These lines appear in this file twice - removed one occurrence.
Signed-off-by: Avishay Traeger <avishay@il.ibm.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
biodoc.txt mentions that elevator functions marked with * are mandatory, but
no function is marked with *. Mark the 3 functions which should be
implemented by any io scheduler.
Signed-off-by: Nikanth Karthikesan <knikanth@suse.de>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Move DMA-mapping.txt to Documentation/PCI/.
DMA-mapping.txt was supposed to be moved from Documentation/ to
Documentation/PCI/. The 00-INDEX files in those two directories
were updated, along with a few other text files, but the file
itself somehow escaped being moved, so move it and update more
text files and source files with its new location.
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Acked-by: Greg Kroah-Hartman <gregkh@suse.de>
cc: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
