summaryrefslogtreecommitdiff
path: root/Documentation
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-08-01 09:02:41 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-08-01 09:02:41 -0700
commit8cf1a3fce0b95050b63d451c9d561da0da2aa4d6 (patch)
tree0dc7f93474c3be601a5893900db1418dfd60ba5d /Documentation
parentfcff06c438b60f415af5983efe92811d6aa02ad1 (diff)
parent80799fbb7d10c30df78015b3fa21f7ffcfc0eb2c (diff)
Merge branch 'for-3.6/core' of git://git.kernel.dk/linux-block
Pull core block IO bits from Jens Axboe: "The most complicated part if this is the request allocation rework by Tejun, which has been queued up for a long time and has been in for-next ditto as well. There are a few commits from yesterday and today, mostly trivial and obvious fixes. So I'm pretty confident that it is sound. It's also smaller than usual." * 'for-3.6/core' of git://git.kernel.dk/linux-block: block: remove dead func declaration block: add partition resize function to blkpg ioctl block: uninitialized ioc->nr_tasks triggers WARN_ON block: do not artificially constrain max_sectors for stacking drivers blkcg: implement per-blkg request allocation block: prepare for multiple request_lists block: add q->nr_rqs[] and move q->rq.elvpriv to q->nr_rqs_elvpriv blkcg: inline bio_blkcg() and friends block: allocate io_context upfront block: refactor get_request[_wait]() block: drop custom queue draining used by scsi_transport_{iscsi|fc} mempool: add @gfp_mask to mempool_create_node() blkcg: make root blkcg allocation use %GFP_KERNEL blkcg: __blkg_lookup_create() doesn't need radix preload
Diffstat (limited to 'Documentation')
-rw-r--r--Documentation/block/queue-sysfs.txt7
1 files changed, 7 insertions, 0 deletions
diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt
index d8147b336c35..6518a55273e7 100644
--- a/Documentation/block/queue-sysfs.txt
+++ b/Documentation/block/queue-sysfs.txt
@@ -38,6 +38,13 @@ read or write requests. Note that the total allocated number may be twice
this amount, since it applies only to reads or writes (not the accumulated
sum).
+To avoid priority inversion through request starvation, a request
+queue maintains a separate request pool per each cgroup when
+CONFIG_BLK_CGROUP is enabled, and this parameter applies to each such
+per-block-cgroup request pool. IOW, if there are N block cgroups,
+each request queue may have upto N request pools, each independently
+regulated by nr_requests.
+
read_ahead_kb (RW)
------------------
Maximum number of kilobytes to read-ahead for filesystems on this block