Jens Axboe 9491ae4aad mm: don't cap request size based on read-ahead setting ... We ran into a funky issue, where someone doing 256K buffered reads saw 128K requests at the device level. Turns out it is read-ahead capping the request size, since we use 128K as the default setting. This doesn't make a lot of sense - if someone is issuing 256K reads, they should see 256K reads, regardless of the read-ahead setting, if the underlying device can support a 256K read in a single command. This patch introduces a bdi hint, io_pages. This is the soft max IO size for the lower level, I've hooked it up to the bdev settings here. Read-ahead is modified to issue the maximum of the user request size, and the read-ahead max size, but capped to the max request size on the device side. The latter is done to avoid reading ahead too much, if the application asks for a huge read. With this patch, the kernel behaves like the application expects. Link: http://lkml.kernel.org/r/1479498073-8657-1-git-send-email-axboe@fb.com Signed-off-by: Jens Axboe <axboe@fb.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>		2016-12-12 18:55:08 -08:00
..
partitions
badblocks.c	badblocks: badblocks_set/clear update unacked_exist	2016-10-21 15:45:47 -06:00
bio-integrity.c
bio.c	block: export bio_free_pages to other modules	2016-09-22 07:48:03 -06:00
blk-cgroup.c	blkcg: Unlock blkcg_pol_mutex only once when cpd == NULL	2016-09-30 10:31:20 +02:00
blk-core.c
blk-exec.c
blk-flush.c	block: flush: fix IO hang in case of flood fua req	2016-10-26 07:49:27 -06:00
blk-integrity.c
blk-ioc.c
blk-lib.c	block: require write_same and discard requests align to logical block size	2016-10-11 15:06:30 -07:00
blk-map.c	Don't feed anything but regular iovec's to blk_rq_map_user_iov	2016-12-07 08:23:35 -08:00
blk-merge.c
blk-mq-cpumap.c
blk-mq-pci.c	blk_mq: linux/blk-mq.h does not include all the headers it depends on	2016-09-19 08:21:51 -06:00
blk-mq-sysfs.c	blk-mq: register device instead of disk	2016-09-21 07:56:16 -06:00
blk-mq-tag.c	Merge branch 'for-4.9/block-irq' of git://git.kernel.dk/linux-block	2016-10-09 17:29:33 -07:00
blk-mq-tag.h	Merge branch 'for-4.9/block-irq' of git://git.kernel.dk/linux-block	2016-10-09 17:29:33 -07:00
blk-mq.c	blk-mq: update hardware and software queues for sleeping alloc	2016-10-27 09:56:03 -06:00
blk-mq.h	Merge branch 'for-4.9/block-smp' of git://git.kernel.dk/linux-block	2016-10-09 17:32:20 -07:00
blk-settings.c	mm: don't cap request size based on read-ahead setting	2016-12-12 18:55:08 -08:00
blk-softirq.c	This adds a new gcc plugin named "latent_entropy". It is designed to	2016-10-15 10:03:15 -07:00
blk-sysfs.c	mm: don't cap request size based on read-ahead setting	2016-12-12 18:55:08 -08:00
blk-tag.c
blk-throttle.c	blk-throttle: Extend slice if throttle group is not empty	2016-09-19 15:12:41 -06:00
blk-timeout.c
blk.h
bounce.c
bsg-lib.c
bsg.c
cfq-iosched.c	cfq: fix starvation of asynchronous writes	2016-09-23 10:01:24 -06:00
cmdline-parser.c
compat_ioctl.c
deadline-iosched.c
elevator.c
genhd.c
ioctl.c	block: invalidate the page cache when issuing BLKZEROOUT	2016-10-11 15:06:30 -07:00
ioprio.c
Kconfig	Merge branch 'for-4.9/block-irq' of git://git.kernel.dk/linux-block	2016-10-09 17:29:33 -07:00
Kconfig.iosched
Makefile	Merge branch 'for-4.9/block-smp' of git://git.kernel.dk/linux-block	2016-10-09 17:32:20 -07:00
noop-iosched.c
partition-generic.c
scsi_ioctl.c
t10-pi.c