Commit 9491ae4a authored by Jens Axboe's avatar Jens Axboe Committed by Linus Torvalds

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.comSigned-off-by: default avatarJens Axboe <axboe@fb.com>
Acked-by: default avatarJohannes Weiner <hannes@cmpxchg.org>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent f1f5929c
...@@ -249,6 +249,7 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto ...@@ -249,6 +249,7 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors); max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors);
max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS); max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS);
limits->max_sectors = max_sectors; limits->max_sectors = max_sectors;
q->backing_dev_info.io_pages = max_sectors >> (PAGE_SHIFT - 9);
} }
EXPORT_SYMBOL(blk_queue_max_hw_sectors); EXPORT_SYMBOL(blk_queue_max_hw_sectors);
......
...@@ -212,6 +212,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) ...@@ -212,6 +212,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
spin_lock_irq(q->queue_lock); spin_lock_irq(q->queue_lock);
q->limits.max_sectors = max_sectors_kb << 1; q->limits.max_sectors = max_sectors_kb << 1;
q->backing_dev_info.io_pages = max_sectors_kb >> (PAGE_SHIFT - 10);
spin_unlock_irq(q->queue_lock); spin_unlock_irq(q->queue_lock);
return ret; return ret;
......
...@@ -136,6 +136,7 @@ struct bdi_writeback { ...@@ -136,6 +136,7 @@ struct bdi_writeback {
struct backing_dev_info { struct backing_dev_info {
struct list_head bdi_list; struct list_head bdi_list;
unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ unsigned long ra_pages; /* max readahead in PAGE_SIZE units */
unsigned long io_pages; /* max allowed IO size */
unsigned int capabilities; /* Device capabilities */ unsigned int capabilities; /* Device capabilities */
congested_fn *congested_fn; /* Function pointer if device is md/dm */ congested_fn *congested_fn; /* Function pointer if device is md/dm */
void *congested_data; /* Pointer to aux data for congested func */ void *congested_data; /* Pointer to aux data for congested func */
......
...@@ -209,10 +209,19 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, ...@@ -209,10 +209,19 @@ int __do_page_cache_readahead(struct address_space *mapping, struct file *filp,
int force_page_cache_readahead(struct address_space *mapping, struct file *filp, int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
pgoff_t offset, unsigned long nr_to_read) pgoff_t offset, unsigned long nr_to_read)
{ {
struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
struct file_ra_state *ra = &filp->f_ra;
unsigned long max_pages;
if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages)) if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages))
return -EINVAL; return -EINVAL;
nr_to_read = min(nr_to_read, inode_to_bdi(mapping->host)->ra_pages); /*
* If the request exceeds the readahead window, allow the read to
* be up to the optimal hardware IO size
*/
max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages);
nr_to_read = min(nr_to_read, max_pages);
while (nr_to_read) { while (nr_to_read) {
int err; int err;
...@@ -369,9 +378,17 @@ ondemand_readahead(struct address_space *mapping, ...@@ -369,9 +378,17 @@ ondemand_readahead(struct address_space *mapping,
bool hit_readahead_marker, pgoff_t offset, bool hit_readahead_marker, pgoff_t offset,
unsigned long req_size) unsigned long req_size)
{ {
unsigned long max = ra->ra_pages; struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
unsigned long max_pages = ra->ra_pages;
pgoff_t prev_offset; pgoff_t prev_offset;
/*
* If the request exceeds the readahead window, allow the read to
* be up to the optimal hardware IO size
*/
if (req_size > max_pages && bdi->io_pages > max_pages)
max_pages = min(req_size, bdi->io_pages);
/* /*
* start of file * start of file
*/ */
...@@ -385,7 +402,7 @@ ondemand_readahead(struct address_space *mapping, ...@@ -385,7 +402,7 @@ ondemand_readahead(struct address_space *mapping,
if ((offset == (ra->start + ra->size - ra->async_size) || if ((offset == (ra->start + ra->size - ra->async_size) ||
offset == (ra->start + ra->size))) { offset == (ra->start + ra->size))) {
ra->start += ra->size; ra->start += ra->size;
ra->size = get_next_ra_size(ra, max); ra->size = get_next_ra_size(ra, max_pages);
ra->async_size = ra->size; ra->async_size = ra->size;
goto readit; goto readit;
} }
...@@ -400,16 +417,16 @@ ondemand_readahead(struct address_space *mapping, ...@@ -400,16 +417,16 @@ ondemand_readahead(struct address_space *mapping,
pgoff_t start; pgoff_t start;
rcu_read_lock(); rcu_read_lock();
start = page_cache_next_hole(mapping, offset + 1, max); start = page_cache_next_hole(mapping, offset + 1, max_pages);
rcu_read_unlock(); rcu_read_unlock();
if (!start || start - offset > max) if (!start || start - offset > max_pages)
return 0; return 0;
ra->start = start; ra->start = start;
ra->size = start - offset; /* old async_size */ ra->size = start - offset; /* old async_size */
ra->size += req_size; ra->size += req_size;
ra->size = get_next_ra_size(ra, max); ra->size = get_next_ra_size(ra, max_pages);
ra->async_size = ra->size; ra->async_size = ra->size;
goto readit; goto readit;
} }
...@@ -417,7 +434,7 @@ ondemand_readahead(struct address_space *mapping, ...@@ -417,7 +434,7 @@ ondemand_readahead(struct address_space *mapping,
/* /*
* oversize read * oversize read
*/ */
if (req_size > max) if (req_size > max_pages)
goto initial_readahead; goto initial_readahead;
/* /*
...@@ -433,7 +450,7 @@ ondemand_readahead(struct address_space *mapping, ...@@ -433,7 +450,7 @@ ondemand_readahead(struct address_space *mapping,
* Query the page cache and look for the traces(cached history pages) * Query the page cache and look for the traces(cached history pages)
* that a sequential stream would leave behind. * that a sequential stream would leave behind.
*/ */
if (try_context_readahead(mapping, ra, offset, req_size, max)) if (try_context_readahead(mapping, ra, offset, req_size, max_pages))
goto readit; goto readit;
/* /*
...@@ -444,7 +461,7 @@ ondemand_readahead(struct address_space *mapping, ...@@ -444,7 +461,7 @@ ondemand_readahead(struct address_space *mapping,
initial_readahead: initial_readahead:
ra->start = offset; ra->start = offset;
ra->size = get_init_ra_size(req_size, max); ra->size = get_init_ra_size(req_size, max_pages);
ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size; ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size;
readit: readit:
...@@ -454,7 +471,7 @@ ondemand_readahead(struct address_space *mapping, ...@@ -454,7 +471,7 @@ ondemand_readahead(struct address_space *mapping,
* the resulted next readahead window into the current one. * the resulted next readahead window into the current one.
*/ */
if (offset == ra->start && ra->size == ra->async_size) { if (offset == ra->start && ra->size == ra->async_size) {
ra->async_size = get_next_ra_size(ra, max); ra->async_size = get_next_ra_size(ra, max_pages);
ra->size += ra->async_size; ra->size += ra->async_size;
} }
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment