The patch titled
Subject: readahead: disentangle async and sync readahead
has been added to the -mm mm-unstable branch. Its filename is
readahead-disentangle-async-and-sync-readahead.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/readahead-disentangle-async-and-sync-readahead.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Jan Kara <jack@xxxxxxx>
Subject: readahead: disentangle async and sync readahead
Date: Tue, 25 Jun 2024 12:18:58 +0200
Both async and sync readahead are handled by ondemand_readahead()
function. However there isn't actually much in common. Just move async
related parts into page_cache_ra_async() and sync related parts to
page_cache_ra_sync(). No functional changes.
Link: https://lkml.kernel.org/r/20240625101909.12234-8-jack@xxxxxxx
Signed-off-by: Jan Kara <jack@xxxxxxx>
Reviewed-by: Josef Bacik <josef@xxxxxxxxxxxxxx>
Cc: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/readahead.c | 162 ++++++++++++++++++++++-------------------------
1 file changed, 77 insertions(+), 85 deletions(-)
--- a/mm/readahead.c~readahead-disentangle-async-and-sync-readahead
+++ a/mm/readahead.c
@@ -540,18 +540,11 @@ fallback:
do_page_cache_ra(ractl, ra->size - (index - start), ra->async_size);
}
-/*
- * A minimal readahead algorithm for trivial sequential/random reads.
- */
-static void ondemand_readahead(struct readahead_control *ractl,
- struct folio *folio, unsigned long req_size)
+static unsigned long ractl_max_pages(struct readahead_control *ractl,
+ unsigned long req_size)
{
struct backing_dev_info *bdi = inode_to_bdi(ractl->mapping->host);
- struct file_ra_state *ra = ractl->ra;
- unsigned long max_pages = ra->ra_pages;
- pgoff_t index = readahead_index(ractl);
- pgoff_t expected, prev_index;
- unsigned int order = folio ? folio_order(folio) : 0;
+ unsigned long max_pages = ractl->ra->ra_pages;
/*
* If the request exceeds the readahead window, allow the read to
@@ -559,55 +552,42 @@ static void ondemand_readahead(struct re
*/
if (req_size > max_pages && bdi->io_pages > max_pages)
max_pages = min(req_size, bdi->io_pages);
+ return max_pages;
+}
- /*
- * start of file
- */
- if (!index)
- goto initial_readahead;
-
- /*
- * It's the expected callback index, assume sequential access.
- * Ramp up sizes, and push forward the readahead window.
- */
- expected = round_down(ra->start + ra->size - ra->async_size,
- 1UL << order);
- if (folio && index == expected) {
- ra->start += ra->size;
- ra->size = get_next_ra_size(ra, max_pages);
- ra->async_size = ra->size;
- goto readit;
- }
+void page_cache_sync_ra(struct readahead_control *ractl,
+ unsigned long req_count)
+{
+ pgoff_t index = readahead_index(ractl);
+ bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM);
+ struct file_ra_state *ra = ractl->ra;
+ unsigned long max_pages;
+ pgoff_t prev_index;
/*
- * Hit a marked folio without valid readahead state.
- * E.g. interleaved reads.
- * Query the pagecache for async_size, which normally equals to
- * readahead size. Ramp it up and use it as the new readahead size.
+ * Even if readahead is disabled, issue this request as readahead
+ * as we'll need it to satisfy the requested range. The forced
+ * readahead will do the right thing and limit the read to just the
+ * requested range, which we'll set to 1 page for this case.
*/
- if (folio) {
- pgoff_t start;
-
- rcu_read_lock();
- start = page_cache_next_miss(ractl->mapping, index + 1,
- max_pages);
- rcu_read_unlock();
-
- if (!start || start - index > max_pages)
+ if (!ra->ra_pages || blk_cgroup_congested()) {
+ if (!ractl->file)
return;
+ req_count = 1;
+ do_forced_ra = true;
+ }
- ra->start = start;
- ra->size = start - index; /* old async_size */
- ra->size += req_size;
- ra->size = get_next_ra_size(ra, max_pages);
- ra->async_size = ra->size;
- goto readit;
+ /* be dumb */
+ if (do_forced_ra) {
+ force_page_cache_ra(ractl, req_count);
+ return;
}
+ max_pages = ractl_max_pages(ractl, req_count);
/*
- * oversize read
+ * start of file or oversized read
*/
- if (req_size > max_pages)
+ if (!index || req_count > max_pages)
goto initial_readahead;
/*
@@ -623,7 +603,7 @@ static void ondemand_readahead(struct re
* Query the page cache and look for the traces(cached history pages)
* that a sequential stream would leave behind.
*/
- if (try_context_readahead(ractl->mapping, ra, index, req_size,
+ if (try_context_readahead(ractl->mapping, ra, index, req_count,
max_pages))
goto readit;
@@ -631,53 +611,31 @@ static void ondemand_readahead(struct re
* standalone, small random read
* Read as is, and do not pollute the readahead state.
*/
- do_page_cache_ra(ractl, req_size, 0);
+ do_page_cache_ra(ractl, req_count, 0);
return;
initial_readahead:
ra->start = index;
- ra->size = get_init_ra_size(req_size, max_pages);
- ra->async_size = ra->size > req_size ? ra->size - req_size :
- ra->size >> 1;
-
+ ra->size = get_init_ra_size(req_count, max_pages);
+ ra->async_size = ra->size > req_count ? ra->size - req_count :
+ ra->size >> 1;
readit:
ractl->_index = ra->start;
- page_cache_ra_order(ractl, ra, order);
-}
-
-void page_cache_sync_ra(struct readahead_control *ractl,
- unsigned long req_count)
-{
- bool do_forced_ra = ractl->file && (ractl->file->f_mode & FMODE_RANDOM);
-
- /*
- * Even if readahead is disabled, issue this request as readahead
- * as we'll need it to satisfy the requested range. The forced
- * readahead will do the right thing and limit the read to just the
- * requested range, which we'll set to 1 page for this case.
- */
- if (!ractl->ra->ra_pages || blk_cgroup_congested()) {
- if (!ractl->file)
- return;
- req_count = 1;
- do_forced_ra = true;
- }
-
- /* be dumb */
- if (do_forced_ra) {
- force_page_cache_ra(ractl, req_count);
- return;
- }
-
- ondemand_readahead(ractl, NULL, req_count);
+ page_cache_ra_order(ractl, ra, 0);
}
EXPORT_SYMBOL_GPL(page_cache_sync_ra);
void page_cache_async_ra(struct readahead_control *ractl,
struct folio *folio, unsigned long req_count)
{
+ unsigned long max_pages;
+ struct file_ra_state *ra = ractl->ra;
+ pgoff_t index = readahead_index(ractl);
+ pgoff_t expected, start;
+ unsigned int order = folio_order(folio);
+
/* no readahead */
- if (!ractl->ra->ra_pages)
+ if (!ra->ra_pages)
return;
/*
@@ -691,7 +649,41 @@ void page_cache_async_ra(struct readahea
if (blk_cgroup_congested())
return;
- ondemand_readahead(ractl, folio, req_count);
+ max_pages = ractl_max_pages(ractl, req_count);
+ /*
+ * It's the expected callback index, assume sequential access.
+ * Ramp up sizes, and push forward the readahead window.
+ */
+ expected = round_down(ra->start + ra->size - ra->async_size,
+ 1UL << order);
+ if (index == expected) {
+ ra->start += ra->size;
+ ra->size = get_next_ra_size(ra, max_pages);
+ ra->async_size = ra->size;
+ goto readit;
+ }
+
+ /*
+ * Hit a marked folio without valid readahead state.
+ * E.g. interleaved reads.
+ * Query the pagecache for async_size, which normally equals to
+ * readahead size. Ramp it up and use it as the new readahead size.
+ */
+ rcu_read_lock();
+ start = page_cache_next_miss(ractl->mapping, index + 1, max_pages);
+ rcu_read_unlock();
+
+ if (!start || start - index > max_pages)
+ return;
+
+ ra->start = start;
+ ra->size = start - index; /* old async_size */
+ ra->size += req_count;
+ ra->size = get_next_ra_size(ra, max_pages);
+ ra->async_size = ra->size;
+readit:
+ ractl->_index = ra->start;
+ page_cache_ra_order(ractl, ra, order);
}
EXPORT_SYMBOL_GPL(page_cache_async_ra);
_
Patches currently in -mm which might be from jack@xxxxxxx are
revert-mm-writeback-fix-possible-divide-by-zero-in-wb_dirty_limits-again.patch
mm-avoid-overflows-in-dirty-throttling-logic.patch
readahead-make-sure-sync-readahead-reads-needed-page.patch
filemap-fix-page_cache_next_miss-when-no-hole-found.patch
readahead-properly-shorten-readahead-when-falling-back-to-do_page_cache_ra.patch
readahead-drop-pointless-index-from-force_page_cache_ra.patch
readahead-drop-index-argument-of-page_cache_async_readahead.patch
readahead-drop-dead-code-in-page_cache_ra_order.patch
readahead-drop-dead-code-in-ondemand_readahead.patch
readahead-disentangle-async-and-sync-readahead.patch
readahead-fold-try_context_readahead-into-its-single-caller.patch
readahead-simplify-gotos-in-page_cache_sync_ra.patch
