From: "Darrick J. Wong" <djwong@kernel.org>
To: tytso@mit.edu
Cc: John@groves.net, bernd@bsbernd.com,
linux-fsdevel@vger.kernel.org, linux-ext4@vger.kernel.org,
miklos@szeredi.hu, amir73il@gmail.com, joannelkoong@gmail.com,
neal@gompa.dev
Subject: [PATCH 20/20] fuse4fs: create incore reverse orphan list
Date: Wed, 20 Aug 2025 18:13:05 -0700 [thread overview]
Message-ID: <175573713168.20753.5541232630143908826.stgit@frogsfrogsfrogs> (raw)
In-Reply-To: <175573712721.20753.5223489399594191991.stgit@frogsfrogsfrogs>
From: Darrick J. Wong <djwong@kernel.org>
Create an incore orphan list so that removing open unlinked inodes
doesn't take forever.
Signed-off-by: "Darrick J. Wong" <djwong@kernel.org>
---
misc/fuse4fs.c | 178 +++++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 174 insertions(+), 4 deletions(-)
diff --git a/misc/fuse4fs.c b/misc/fuse4fs.c
index 3f88e98a20c203..cd7e30eaeb7757 100644
--- a/misc/fuse4fs.c
+++ b/misc/fuse4fs.c
@@ -351,10 +351,20 @@ static inline int u_log2(unsigned int arg)
return l;
}
+/* inode is not on unlinked list */
+#define FUSE4FS_NULL_INO ((ext2_ino_t)~0ULL)
+
struct fuse4fs_inode {
struct cache_node i_cnode;
ext2_ino_t i_ino;
unsigned int i_open_count;
+
+ /*
+ * FUSE4FS_NULL_INO: inode is not on the orphan list
+ * 0: inode is the first on the orphan list
+ * otherwise: inode is in the middle of the list
+ */
+ ext2_ino_t i_prev_orphan;
};
struct fuse4fs_ikey {
@@ -396,12 +406,15 @@ static struct cache_node *icache_alloc(struct cache *c, cache_key_t key)
return NULL;
fi->i_ino = ikey->i_ino;
+ fi->i_prev_orphan = FUSE4FS_NULL_INO;
return &fi->i_cnode;
}
static bool icache_flush(struct cache *c, struct cache_node *node)
{
- return false;
+ struct fuse4fs_inode *fi = ICNODE(node);
+
+ return fi->i_prev_orphan != FUSE4FS_NULL_INO;
}
static void icache_relse(struct cache *c, struct cache_node *node)
@@ -2164,10 +2177,31 @@ static int fuse4fs_add_to_orphans(struct fuse4fs *ff, ext2_ino_t ino,
struct ext2_inode_large *inode)
{
ext2_filsys fs = ff->fs;
+ struct fuse4fs_inode *fi;
+ ext2_ino_t orphan_ino = fs->super->s_last_orphan;
+ errcode_t err;
dbg_printf(ff, "%s: orphan ino=%d dtime=%d next=%d\n",
__func__, ino, inode->i_dtime, fs->super->s_last_orphan);
+ /* Make the first orphan on the list point back to us */
+ if (orphan_ino != 0) {
+ err = fuse4fs_iget(ff, orphan_ino, &fi);
+ if (err)
+ return translate_error(fs, orphan_ino, err);
+
+ fi->i_prev_orphan = ino;
+ fuse4fs_iput(ff, fi);
+ }
+
+ /* Add ourselves to the head of the orphan list */
+ err = fuse4fs_iget(ff, ino, &fi);
+ if (err)
+ return translate_error(fs, ino, err);
+
+ fi->i_prev_orphan = 0;
+ fuse4fs_iput(ff, fi);
+
inode->i_dtime = fs->super->s_last_orphan;
fs->super->s_last_orphan = ino;
ext2fs_mark_super_dirty(fs);
@@ -2175,24 +2209,158 @@ static int fuse4fs_add_to_orphans(struct fuse4fs *ff, ext2_ino_t ino,
return 0;
}
+/*
+ * Given the orphan list excerpt: prev_orphan -> ino -> next_orphan, set
+ * next_orphan's backpointer to ino's backpointer (prev_orphan), having removed
+ * ino from the orphan list.
+ */
+static int fuse2fs_update_next_orphan_backlink(struct fuse4fs *ff,
+ ext2_ino_t prev_orphan,
+ ext2_ino_t ino,
+ ext2_ino_t next_orphan)
+{
+ struct fuse4fs_inode *fi;
+ errcode_t err;
+ int ret = 0;
+
+ err = fuse4fs_iget(ff, next_orphan, &fi);
+ if (err)
+ return translate_error(ff->fs, next_orphan, err);
+
+ dbg_printf(ff, "%s: ino=%d cached next=%d nextprev=%d prev=%d\n",
+ __func__, ino, next_orphan, fi->i_prev_orphan,
+ prev_orphan);
+
+ if (fi->i_prev_orphan != ino) {
+ ret = translate_error(ff->fs, next_orphan,
+ EXT2_ET_FILESYSTEM_CORRUPTED);
+ goto out_iput;
+ }
+
+ fi->i_prev_orphan = prev_orphan;
+out_iput:
+ fuse4fs_iput(ff, fi);
+ return ret;
+}
+
+/*
+ * Remove ino from the orphan list the fast way. Returns 1 for success, 0 if
+ * it didn't do anything, or a negative errno.
+ */
+static int fuse4fs_fast_remove_from_orphans(struct fuse4fs *ff, ext2_ino_t ino,
+ struct ext2_inode_large *inode)
+{
+ struct ext2_inode_large orphan;
+ ext2_filsys fs = ff->fs;
+ struct fuse4fs_inode *fi;
+ ext2_ino_t prev_orphan;
+ ext2_ino_t next_orphan = 0;
+ errcode_t err;
+ int ret = 0;
+
+ err = fuse4fs_iget(ff, ino, &fi);
+ if (err)
+ return translate_error(fs, ino, err);
+
+ prev_orphan = fi->i_prev_orphan;
+ switch (prev_orphan) {
+ case 0:
+ /* First inode in the list */
+ dbg_printf(ff, "%s: ino=%d cached superblock\n", __func__, ino);
+
+ fs->super->s_last_orphan = inode->i_dtime;
+ next_orphan = inode->i_dtime;
+ inode->i_dtime = 0;
+ ext2fs_mark_super_dirty(fs);
+ fi->i_prev_orphan = FUSE4FS_NULL_INO;
+ break;
+ case FUSE4FS_NULL_INO:
+ /* unknown */
+ dbg_printf(ff, "%s: ino=%d broken list??\n", __func__, ino);
+ ret = 0;
+ goto out_iput;
+ default:
+ /* We're in the middle of the list */
+ err = fuse4fs_read_inode(fs, prev_orphan, &orphan);
+ if (err) {
+ ret = translate_error(fs, prev_orphan, err);
+ goto out_iput;
+ }
+
+ dbg_printf(ff,
+ "%s: ino=%d cached prev=%d prevnext=%d next=%d\n",
+ __func__, ino, prev_orphan, orphan.i_dtime,
+ inode->i_dtime);
+
+ if (orphan.i_dtime != ino) {
+ ret = translate_error(fs, prev_orphan,
+ EXT2_ET_FILESYSTEM_CORRUPTED);
+ goto out_iput;
+ }
+
+ fi->i_prev_orphan = FUSE4FS_NULL_INO;
+ orphan.i_dtime = inode->i_dtime;
+ next_orphan = inode->i_dtime;
+ inode->i_dtime = 0;
+
+ err = fuse4fs_write_inode(fs, prev_orphan, &orphan);
+ if (err) {
+ ret = translate_error(fs, prev_orphan, err);
+ goto out_iput;
+ }
+
+ break;
+ }
+
+ /*
+ * Make the next orphaned inode point back to the our own previous list
+ * entry
+ */
+ if (next_orphan != 0) {
+ ret = fuse2fs_update_next_orphan_backlink(ff, prev_orphan, ino,
+ next_orphan);
+ if (ret)
+ goto out_iput;
+ }
+ ret = 1;
+
+out_iput:
+ fuse4fs_iput(ff, fi);
+ return ret;
+}
+
static int fuse4fs_remove_from_orphans(struct fuse4fs *ff, ext2_ino_t ino,
struct ext2_inode_large *inode)
{
ext2_filsys fs = ff->fs;
ext2_ino_t prev_orphan;
+ ext2_ino_t next_orphan;
errcode_t err;
+ int ret;
dbg_printf(ff, "%s: super=%d ino=%d next=%d\n",
__func__, fs->super->s_last_orphan, ino, inode->i_dtime);
- /* If we're lucky, the ondisk superblock points to us */
+ /*
+ * Fast way: use the incore list, which doesn't include any orphans
+ * that were already on the superblock when we mounted.
+ */
+ ret = fuse4fs_fast_remove_from_orphans(ff, ino, inode);
+ if (ret < 0)
+ return ret;
+ if (ret == 1)
+ return 0;
+
+ /* Slow way: If we're lucky, the ondisk superblock points to us */
if (fs->super->s_last_orphan == ino) {
dbg_printf(ff, "%s: superblock\n", __func__);
+ next_orphan = inode->i_dtime;
fs->super->s_last_orphan = inode->i_dtime;
inode->i_dtime = 0;
ext2fs_mark_super_dirty(fs);
- return 0;
+ return fuse2fs_update_next_orphan_backlink(ff, 0, ino,
+ next_orphan);
}
/* Otherwise walk the ondisk orphan list. */
@@ -2212,6 +2380,7 @@ static int fuse4fs_remove_from_orphans(struct fuse4fs *ff, ext2_ino_t ino,
dbg_printf(ff, "%s: prev=%d\n",
__func__, prev_orphan);
+ next_orphan = inode->i_dtime;
orphan.i_dtime = inode->i_dtime;
inode->i_dtime = 0;
@@ -2219,7 +2388,8 @@ static int fuse4fs_remove_from_orphans(struct fuse4fs *ff, ext2_ino_t ino,
if (err)
return translate_error(fs, prev_orphan, err);
- return 0;
+ return fuse2fs_update_next_orphan_backlink(ff,
+ prev_orphan, ino, next_orphan);
}
dbg_printf(ff, "%s: orphan=%d next=%d\n",
next prev parent reply other threads:[~2025-08-21 1:13 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-21 0:37 [RFC v4] fuse: use fs-iomap for better performance so we can containerize ext4 Darrick J. Wong
2025-08-21 0:49 ` [PATCHSET RFC v4 1/6] fuse4fs: fork a low level fuse server Darrick J. Wong
2025-08-21 1:08 ` [PATCH 01/20] fuse2fs: port fuse2fs to lowlevel libfuse API Darrick J. Wong
2025-08-21 1:08 ` [PATCH 02/20] fuse4fs: drop fuse 2.x support code Darrick J. Wong
2025-08-21 1:08 ` [PATCH 03/20] fuse4fs: namespace some helpers Darrick J. Wong
2025-08-21 1:08 ` [PATCH 04/20] fuse4fs: convert to low level API Darrick J. Wong
2025-08-21 1:09 ` [PATCH 05/20] libsupport: port the kernel list.h to libsupport Darrick J. Wong
2025-08-21 1:09 ` [PATCH 06/20] libsupport: add a cache Darrick J. Wong
2025-08-21 1:09 ` [PATCH 07/20] cache: disable debugging Darrick J. Wong
2025-08-21 1:09 ` [PATCH 08/20] cache: use modern list iterator macros Darrick J. Wong
2025-08-21 1:10 ` [PATCH 09/20] cache: embed struct cache in the owner Darrick J. Wong
2025-08-21 1:10 ` [PATCH 10/20] cache: pass cache pointer to callbacks Darrick J. Wong
2025-08-21 1:10 ` [PATCH 11/20] cache: pass a private data pointer through cache_walk Darrick J. Wong
2025-08-21 1:11 ` [PATCH 12/20] cache: add a helper to grab a new refcount for a cache_node Darrick J. Wong
2025-08-21 1:11 ` [PATCH 13/20] cache: return results of a cache flush Darrick J. Wong
2025-08-21 1:11 ` [PATCH 14/20] cache: add a "get only if incore" flag to cache_node_get Darrick J. Wong
2025-08-21 1:11 ` [PATCH 15/20] cache: support gradual expansion Darrick J. Wong
2025-08-21 1:12 ` [PATCH 16/20] cache: implement automatic shrinking Darrick J. Wong
2025-08-21 1:12 ` [PATCH 17/20] fuse4fs: add cache to track open files Darrick J. Wong
2025-08-21 1:12 ` [PATCH 18/20] fuse4fs: use the orphaned inode list Darrick J. Wong
2025-08-21 1:12 ` [PATCH 19/20] fuse4fs: implement FUSE_TMPFILE Darrick J. Wong
2025-08-21 1:13 ` Darrick J. Wong [this message]
2025-08-21 0:49 ` [PATCHSET RFC v4 2/6] libext2fs: refactoring for fuse2fs iomap support Darrick J. Wong
2025-08-21 1:13 ` [PATCH 01/10] libext2fs: make it possible to extract the fd from an IO manager Darrick J. Wong
2025-08-21 1:13 ` [PATCH 02/10] libext2fs: always fsync the device when flushing the cache Darrick J. Wong
2025-08-21 1:13 ` [PATCH 03/10] libext2fs: always fsync the device when closing the unix IO manager Darrick J. Wong
2025-08-21 1:14 ` [PATCH 04/10] libext2fs: only fsync the unix fd if we wrote to the device Darrick J. Wong
2025-08-21 1:14 ` [PATCH 05/10] libext2fs: invalidate cached blocks when freeing them Darrick J. Wong
2025-08-21 1:14 ` [PATCH 06/10] libext2fs: only flush affected blocks in unix_write_byte Darrick J. Wong
2025-08-21 1:14 ` [PATCH 07/10] libext2fs: allow unix_write_byte when the write would be aligned Darrick J. Wong
2025-08-21 1:15 ` [PATCH 08/10] libext2fs: allow clients to ask to write full superblocks Darrick J. Wong
2025-08-21 1:15 ` [PATCH 09/10] libext2fs: allow callers to disallow I/O to file data blocks Darrick J. Wong
2025-08-21 1:15 ` [PATCH 10/10] libext2fs: add posix advisory locking to the unix IO manager Darrick J. Wong
2025-08-21 0:49 ` [PATCHSET RFC v4 3/6] fuse2fs: use fuse iomap data paths for better file I/O performance Darrick J. Wong
2025-08-21 1:15 ` [PATCH 01/19] fuse2fs: implement bare minimum iomap for file mapping reporting Darrick J. Wong
2025-08-21 1:16 ` [PATCH 02/19] fuse2fs: add iomap= mount option Darrick J. Wong
2025-08-21 1:16 ` [PATCH 03/19] fuse2fs: implement iomap configuration Darrick J. Wong
2025-08-21 1:16 ` [PATCH 04/19] fuse2fs: register block devices for use with iomap Darrick J. Wong
2025-08-21 1:17 ` [PATCH 05/19] fuse2fs: implement directio file reads Darrick J. Wong
2025-08-21 1:17 ` [PATCH 06/19] fuse2fs: add extent dump function for debugging Darrick J. Wong
2025-08-21 1:17 ` [PATCH 07/19] fuse2fs: implement direct write support Darrick J. Wong
2025-08-21 1:17 ` [PATCH 08/19] fuse2fs: turn on iomap for pagecache IO Darrick J. Wong
2025-08-21 1:18 ` [PATCH 09/19] fuse2fs: don't zero bytes in punch hole Darrick J. Wong
2025-08-21 1:18 ` [PATCH 10/19] fuse2fs: don't do file data block IO when iomap is enabled Darrick J. Wong
2025-08-21 1:18 ` [PATCH 11/19] fuse2fs: avoid fuseblk mode if fuse-iomap support is likely Darrick J. Wong
2025-08-21 1:18 ` [PATCH 12/19] fuse2fs: enable file IO to inline data files Darrick J. Wong
2025-08-21 1:19 ` [PATCH 13/19] fuse2fs: set iomap-related inode flags Darrick J. Wong
2025-08-21 1:19 ` [PATCH 14/19] fuse2fs: add strictatime/lazytime mount options Darrick J. Wong
2025-08-21 1:19 ` [PATCH 15/19] fuse2fs: configure block device block size Darrick J. Wong
2025-08-21 1:19 ` [PATCH 16/19] fuse4fs: don't use inode number translation when possible Darrick J. Wong
2025-08-21 1:20 ` [PATCH 17/19] fuse4fs: separate invalidation Darrick J. Wong
2025-08-21 1:20 ` [PATCH 18/19] fuse2fs: implement statx Darrick J. Wong
2025-08-21 1:20 ` [PATCH 19/19] fuse2fs: enable atomic writes Darrick J. Wong
2025-08-21 0:50 ` [PATCHSET RFC v4 4/6] fuse2fs: use fuse iomap data paths for better file I/O performance Darrick J. Wong
2025-08-21 1:20 ` [PATCH 1/2] fuse2fs: enable caching of iomaps Darrick J. Wong
2025-08-21 1:21 ` [PATCH 2/2] fuse2fs: be smarter about caching iomaps Darrick J. Wong
2025-08-21 0:50 ` [PATCHSET RFC v4 5/6] fuse2fs: handle timestamps and ACLs correctly when iomap is enabled Darrick J. Wong
2025-08-21 1:21 ` [PATCH 1/8] fuse2fs: skip permission checking on utimens " Darrick J. Wong
2025-08-21 1:21 ` [PATCH 2/8] fuse2fs: let the kernel tell us about acl/mode updates Darrick J. Wong
2025-08-21 1:21 ` [PATCH 3/8] fuse2fs: better debugging for file mode updates Darrick J. Wong
2025-08-21 1:22 ` [PATCH 4/8] fuse2fs: debug timestamp updates Darrick J. Wong
2025-08-21 1:22 ` [PATCH 5/8] fuse2fs: use coarse timestamps for iomap mode Darrick J. Wong
2025-08-21 1:22 ` [PATCH 6/8] fuse2fs: add tracing for retrieving timestamps Darrick J. Wong
2025-08-21 1:23 ` [PATCH 7/8] fuse2fs: enable syncfs Darrick J. Wong
2025-08-21 1:23 ` [PATCH 8/8] fuse2fs: skip the gdt write in op_destroy if syncfs is working Darrick J. Wong
2025-08-21 0:50 ` [PATCHSET RFC v4 6/6] fuse2fs: improve block and inode caching Darrick J. Wong
2025-08-21 1:23 ` [PATCH 1/6] libsupport: add caching IO manager Darrick J. Wong
2025-08-21 1:23 ` [PATCH 2/6] iocache: add the actual buffer cache Darrick J. Wong
2025-08-21 1:24 ` [PATCH 3/6] iocache: bump buffer mru priority every 50 accesses Darrick J. Wong
2025-08-21 1:24 ` [PATCH 4/6] fuse2fs: enable caching IO manager Darrick J. Wong
2025-08-21 1:24 ` [PATCH 5/6] fuse2fs: increase inode cache size Darrick J. Wong
2025-08-21 1:24 ` [PATCH 6/6] libext2fs: improve caching for inodes Darrick J. Wong
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=175573713168.20753.5541232630143908826.stgit@frogsfrogsfrogs \
--to=djwong@kernel.org \
--cc=John@groves.net \
--cc=amir73il@gmail.com \
--cc=bernd@bsbernd.com \
--cc=joannelkoong@gmail.com \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=miklos@szeredi.hu \
--cc=neal@gompa.dev \
--cc=tytso@mit.edu \
/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