Linux filesystem development
 help / color / mirror / Atom feed
* [PATCH] erofs: enable buffered RWF_DONTCACHE reads
@ 2026-11-19  3:52 Wenjie Qi
  2026-11-19 21:17 ` Gao Xiang
  0 siblings, 1 reply; 2+ messages in thread
From: Wenjie Qi @ 2026-11-19  3:52 UTC (permalink / raw)
  To: xiang, chao
  Cc: linux-erofs, linux-fsdevel, shengyong1, yangyongpeng, qiwenjie,
	qwjhust

From: Wenjie Qi <qiwenjie@xiaomi.com>

EROFS uses filemap_read() for buffered reads, including the inode-sharing
path, which preserves request flags when cloning the kiocb.

Advertise FOP_DONTCACHE in both file operation tables so preadv2() callers
can request that newly instantiated file-cache folios be dropped after
consumption. This is useful for one-pass reads that need not retain data
in the page cache.

For compressed reads, retain trailing readmore and propagate dropbehind
to the single-folio neighbor lookup. Readahead expansion already marks
new folios through readahead_control. Suppress prefix readmore so it
cannot refill pages already consumed and evicted. Ordinary readmore is
unchanged.

Tested sequential reads of 1-GiB files with 1-MiB requests on NVMe-backed
LZ4 and Zstd EROFS images in x86-64 QEMU/KVM with two vCPUs and 2 GiB RAM.
Each reader ran with memory.max=255852544 (244 MiB) and
memory.swap.max=0. Normal and dontcache ran in ten paired rounds per
layout, alternating their order and using a fresh guest for each run.

Results are arithmetic means of ten runs. Memory values average the
run-level time-weighted memory.current means. Percentage changes are
relative to normal reads:

                    MiB/s                  Mean memory, MiB
 Layout   normal/dontcache  change    normal/dontcache  change
 LZ4      2513.57/6350.61  +152.65%      169.53/17.39   -89.74%
 Zstd     2535.57/4066.49   +60.38%      179.01/18.17   -89.85%

In this test, dontcache reduced average cgroup memory by about 90%,
left no consumed file pages resident and recorded no memcg reclaim
scans or steals. Both layouts were faster in all ten pairs. This
offers a smaller cache footprint for one-pass reads on memory-constrained
systems.

Signed-off-by: Wenjie Qi <qiwenjie@xiaomi.com>
Signed-off-by: Sheng Yong <shengyong1@xiaomi.com>
Reviewed-by: Yongpeng Yang <yangyongpeng@xiaomi.com>
---
 fs/erofs/data.c     |  1 +
 fs/erofs/internal.h |  5 +++--
 fs/erofs/ishare.c   |  1 +
 fs/erofs/zdata.c    | 10 +++++++++-
 4 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/fs/erofs/data.c b/fs/erofs/data.c
index 968303afd..db0bac732 100644
--- a/fs/erofs/data.c
+++ b/fs/erofs/data.c
@@ -537,4 +537,5 @@ const struct file_operations erofs_file_fops = {
 	.get_unmapped_area = thp_get_unmapped_area,
 	.splice_read	= filemap_splice_read,
 	.setlease	= generic_setlease,
+	.fop_flags	= FOP_DONTCACHE,
 };
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index 8363c0c05..cbe58576b 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -321,10 +321,11 @@ static inline unsigned int erofs_inode_datalayout(unsigned int ifmt)
 
 /* reclaiming is never triggered when allocating new folios. */
 static inline struct folio *erofs_grab_folio_nowait(struct address_space *as,
-						    pgoff_t index)
+						    pgoff_t index, bool dropbehind)
 {
 	return __filemap_get_folio(as, index,
-			FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
+			FGP_LOCK | FGP_CREAT | FGP_NOFS | FGP_NOWAIT |
+			(dropbehind ? FGP_DONTCACHE : 0),
 			readahead_gfp_mask(as) & ~__GFP_RECLAIM);
 }
 
diff --git a/fs/erofs/ishare.c b/fs/erofs/ishare.c
index ea146fa8a..585bf4614 100644
--- a/fs/erofs/ishare.c
+++ b/fs/erofs/ishare.c
@@ -190,6 +190,7 @@ const struct file_operations erofs_ishare_fops = {
 	.get_unmapped_area = thp_get_unmapped_area,
 	.splice_read	= erofs_ishare_splice_read,
 	.fadvise	= erofs_ishare_fadvise,
+	.fop_flags	= FOP_DONTCACHE,
 };
 
 struct inode *erofs_real_inode(struct inode *inode, bool *need_iput)
diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
index e981e371d..19e6051f5 100644
--- a/fs/erofs/zdata.c
+++ b/fs/erofs/zdata.c
@@ -512,6 +512,7 @@ struct z_erofs_frontend {
 	struct page *candidate_bvpage;
 	struct z_erofs_pcluster *pcl, *head;
 	enum z_erofs_pclustermode mode;
+	bool dropbehind;
 
 	erofs_off_t headoffset;
 
@@ -1807,6 +1808,10 @@ static void z_erofs_pcluster_readmore(struct z_erofs_frontend *f,
 	erofs_off_t cur, end, headoffset = f->headoffset;
 	int err;
 
+	/* Avoid repopulating a prefix that dropbehind has already evicted. */
+	if (f->dropbehind && !backmost)
+		return;
+
 	if (backmost) {
 		if (rac)
 			end = headoffset + readahead_length(rac) - 1;
@@ -1836,7 +1841,8 @@ static void z_erofs_pcluster_readmore(struct z_erofs_frontend *f,
 		pgoff_t index = cur >> PAGE_SHIFT;
 		struct folio *folio;
 
-		folio = erofs_grab_folio_nowait(f->sharedinode->i_mapping, index);
+		folio = erofs_grab_folio_nowait(f->sharedinode->i_mapping, index,
+						f->dropbehind);
 		if (!IS_ERR_OR_NULL(folio)) {
 			if (folio_test_uptodate(folio))
 				folio_unlock(folio);
@@ -1860,6 +1866,7 @@ static int z_erofs_read_folio(struct file *file, struct folio *folio)
 	int err;
 
 	trace_erofs_read_folio(realinode, folio, false);
+	f.dropbehind = folio_test_dropbehind(folio);
 	z_erofs_pcluster_readmore(&f, NULL, true);
 	err = z_erofs_scan_folio(&f, folio, false);
 	z_erofs_pcluster_readmore(&f, NULL, false);
@@ -1890,6 +1897,7 @@ static void z_erofs_readahead(struct readahead_control *rac)
 	int err;
 
 	trace_erofs_readahead(realinode, readahead_index(rac), nrpages, false);
+	f.dropbehind = rac->dropbehind;
 	z_erofs_pcluster_readmore(&f, rac, true);
 
 	/* traverse from last to first for best metadata I/O performance */

base-commit: 6628e7d4c6b25c8d18f1345e3a20d21829aae7e4
-- 
2.43.0


^ permalink raw reply related	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2026-11-19 21:17 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-11-19  3:52 [PATCH] erofs: enable buffered RWF_DONTCACHE reads Wenjie Qi
2026-11-19 21:17 ` Gao Xiang

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox