From: Luis Chamberlain <mcgrof@kernel.org>
To: hare@suse.de, willy@infradead.org, dave@stgolabs.net,
david@fromorbit.com, djwong@kernel.org, kbusch@kernel.org
Cc: john.g.garry@oracle.com, hch@lst.de, ritesh.list@gmail.com,
linux-fsdevel@vger.kernel.org, linux-xfs@vger.kernel.org,
linux-mm@kvack.org, linux-block@vger.kernel.org,
gost.dev@samsung.com, p.raghav@samsung.com, da.gomez@samsung.com,
kernel@pankajraghav.com, mcgrof@kernel.org
Subject: [PATCH 5/5] fs/buffer: reduce stack usage on bh_read_iter()
Date: Tue, 17 Dec 2024 18:26:26 -0800 [thread overview]
Message-ID: <20241218022626.3668119-6-mcgrof@kernel.org> (raw)
In-Reply-To: <20241218022626.3668119-1-mcgrof@kernel.org>
Now that we can read asynchronously buffer heads from a folio in
chunks, we can chop up bh_read_iter() with a smaller array size.
Use an array of 8 to avoid stack growth warnings on systems with
huge base page sizes.
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
---
fs/buffer.c | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/fs/buffer.c b/fs/buffer.c
index b8ba72f2f211..bfa9c09b8597 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2415,7 +2415,10 @@ static void bh_read_batch_async(struct folio *folio,
(__tmp); \
(__tmp) = bh_next(__tmp, __head))
+#define MAX_BUF_CHUNK 8
+
struct bh_iter {
+ int chunk_number;
sector_t iblock;
get_block_t *get_block;
bool any_get_block_error;
@@ -2424,7 +2427,7 @@ struct bh_iter {
};
/*
- * Reads up to MAX_BUF_PER_PAGE buffer heads at a time on a folio on the given
+ * Reads up to MAX_BUF_CHUNK buffer heads at a time on a folio on the given
* block range iblock to lblock and helps update the number of buffer-heads
* which were not uptodate or unmapped for which we issued an async read for
* on iter->bh_folio_reads for the full folio. Returns the last buffer-head we
@@ -2436,10 +2439,11 @@ static struct buffer_head *bh_read_iter(struct folio *folio,
struct inode *inode,
struct bh_iter *iter, sector_t lblock)
{
- struct buffer_head *arr[MAX_BUF_PER_PAGE];
+ struct buffer_head *arr[MAX_BUF_CHUNK];
struct buffer_head *bh = pivot, *last;
int nr = 0, i = 0;
size_t blocksize = head->b_size;
+ int chunk_idx = MAX_BUF_CHUNK * iter->chunk_number;
bool no_reads = false;
bool fully_mapped = false;
@@ -2447,7 +2451,8 @@ static struct buffer_head *bh_read_iter(struct folio *folio,
/* collect buffers not uptodate and not mapped yet */
for_each_bh_pivot(bh, last, head) {
- BUG_ON(nr >= MAX_BUF_PER_PAGE);
+ if (nr >= MAX_BUF_CHUNK)
+ break;
if (buffer_uptodate(bh)) {
iter->iblock++;
@@ -2487,8 +2492,7 @@ static struct buffer_head *bh_read_iter(struct folio *folio,
}
iter->bh_folio_reads += nr;
-
- WARN_ON_ONCE(!bh_is_last(last, head));
+ iter->chunk_number++;
if (bh_is_last(last, head)) {
if (!iter->bh_folio_reads)
@@ -2518,6 +2522,7 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
struct buffer_head *bh, *head;
struct bh_iter iter = {
.get_block = get_block,
+ .chunk_number = 0,
.unmapped = 0,
.any_get_block_error = false,
.bh_folio_reads = 0,
--
2.43.0
next prev parent reply other threads:[~2024-12-18 2:26 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-12-18 2:26 [PATCH 0/5] fs/buffer: strack reduction on async read Luis Chamberlain
2024-12-18 2:26 ` [PATCH 1/5] fs/buffer: move async batch read code into a helper Luis Chamberlain
2024-12-18 2:26 ` [PATCH 2/5] fs/buffer: simplify block_read_full_folio() with bh_offset() Luis Chamberlain
2024-12-18 2:26 ` [PATCH 3/5] fs/buffer: add a for_each_bh() for block_read_full_folio() Luis Chamberlain
2024-12-18 19:20 ` Matthew Wilcox
2024-12-18 2:26 ` [PATCH 4/5] fs/buffer: add iteration support " Luis Chamberlain
2024-12-18 2:26 ` Luis Chamberlain [this message]
2024-12-18 2:47 ` [PATCH 5/5] fs/buffer: reduce stack usage on bh_read_iter() Luis Chamberlain
2024-12-18 20:05 ` [PATCH 0/5] fs/buffer: strack reduction on async read Matthew Wilcox
2024-12-19 2:27 ` Luis Chamberlain
2024-12-19 3:51 ` Matthew Wilcox
2024-12-30 17:30 ` Luis Chamberlain
2025-01-31 16:54 ` Luis Chamberlain
2025-01-31 22:01 ` Matthew Wilcox
2025-02-03 14:00 ` Luis Chamberlain
2024-12-19 6:28 ` Christoph Hellwig
2024-12-19 17:53 ` Luis Chamberlain
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20241218022626.3668119-6-mcgrof@kernel.org \
--to=mcgrof@kernel.org \
--cc=da.gomez@samsung.com \
--cc=dave@stgolabs.net \
--cc=david@fromorbit.com \
--cc=djwong@kernel.org \
--cc=gost.dev@samsung.com \
--cc=hare@suse.de \
--cc=hch@lst.de \
--cc=john.g.garry@oracle.com \
--cc=kbusch@kernel.org \
--cc=kernel@pankajraghav.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-xfs@vger.kernel.org \
--cc=p.raghav@samsung.com \
--cc=ritesh.list@gmail.com \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox