lkml.org 
[lkml]   [2015]   [Jul]   [14]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 3/3] block: by default, limit maximum discard size to 64MB
Date
Lots of devices exhibit very high latencies for big discards, hurting
reads and writes. By default, limit the max discard we will build to
64MB. This value has shown good results across a number of devices.

This will potentially hurt discard throughput, from a provisioning
point of view (when the user does mkfs.xfs, for instance, and mkfs
issues a full device discard). If that becomes an issue, we could
have different behavior for provisioning vs runtime discards.

Signed-off-by: Jens Axboe <axboe@fb.com>
---
block/blk-settings.c | 2 ++
include/linux/blkdev.h | 5 +++++
2 files changed, 7 insertions(+)

diff --git a/block/blk-settings.c b/block/blk-settings.c
index b38d8d723276..b98d26fcbf81 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -306,6 +306,8 @@ void blk_queue_max_discard_sectors(struct request_queue *q,
{
q->limits.max_hw_discard_sectors = max_discard_sectors;
q->limits.max_discard_sectors = max_discard_sectors;
+ if (q->limits.max_discard_sectors > BLK_DISCARD_MAX_SECTORS)
+ q->limits.max_discard_sectors = BLK_DISCARD_MAX_SECTORS;
}
EXPORT_SYMBOL(blk_queue_max_discard_sectors);

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 243f29e779ec..3a01b16397c4 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1141,6 +1141,11 @@ enum blk_default_limits {
BLK_SAFE_MAX_SECTORS = 255,
BLK_MAX_SEGMENT_SIZE = 65536,
BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL,
+
+ /*
+ * Default to max 64MB of discards, to keep latencies in check
+ */
+ BLK_DISCARD_MAX_SECTORS = (64 * 1024 * 1024UL) >> 9,
};

#define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
--
2.4.1.168.g1ea28e1


\
 
 \ /
  Last update: 2015-07-14 21:21    [W:0.089 / U:0.092 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site