From 75df713627f28f88b901b329c8857747545fd4ab Mon Sep 17 00:00:00 2001
From: Suresh Jayaraman <sjayaraman@suse.de>
Date: Wed, 21 Sep 2011 10:00:16 +0200
Subject: block: document blk-plug
Thus spake Andrew Morton:
"And I have the usual maintainability whine. If someone comes up to
vmscan.c and sees it calling blk_start_plug(), how are they supposed to
work out why that call is there? They go look at the blk_start_plug()
definition and it is undocumented. I think we can do better than this?"
Adapted from the LWN article - http://lwn.net/Articles/438256/ by Jens
Axboe and from an earlier attempt by Shaohua Li to document blk-plug.
[akpm@linux-foundation.org: grammatical and spelling tweaks]
Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de>
Cc: Shaohua Li <shaohua.li@intel.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
include/linux/blkdev.h | 24 +++++++++++++++---------
1 file changed, 15 insertions(+), 9 deletions(-)
(limited to 'include/linux')
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c712efdafc3..1978655faa3 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -860,17 +860,23 @@ struct request_queue *blk_alloc_queue_node(gfp_t, int);
extern void blk_put_queue(struct request_queue *);
/*
- * Note: Code in between changing the blk_plug list/cb_list or element of such
- * lists is preemptable, but such code can't do sleep (or be very careful),
- * otherwise data is corrupted. For details, please check schedule() where
- * blk_schedule_flush_plug() is called.
+ * blk_plug permits building a queue of related requests by holding the I/O
+ * fragments for a short period. This allows merging of sequential requests
+ * into single larger request. As the requests are moved from a per-task list to
+ * the device's request_queue in a batch, this results in improved scalability
+ * as the lock contention for request_queue lock is reduced.
+ *
+ * It is ok not to disable preemption when adding the request to the plug list
+ * or when attempting a merge, because blk_schedule_flush_list() will only flush
+ * the plug list when the task sleeps by itself. For details, please see
+ * schedule() where blk_schedule_flush_plug() is called.
*/
struct blk_plug {
- unsigned long magic;
- struct list_head list;
- struct list_head cb_list;
- unsigned int should_sort;
- unsigned int count;
+ unsigned long magic; /* detect uninitialized use-cases */
+ struct list_head list; /* requests */
+ struct list_head cb_list; /* md requires an unplug callback */
+ unsigned int should_sort; /* list to be sorted before flushing? */
+ unsigned int count; /* number of queued requests */
};
#define BLK_MAX_REQUEST_COUNT 16
--
cgit v1.2.3-70-g09d2