From: Trond Myklebust <[email protected]>
When reading a very large directory, we want to try to keep the page
cache up to date if doing so is inexpensive. With the change to allow
readdir to continue reading even when the cache is incomplete, we no
longer need to fall back to uncached readdir in order to scale to large
directories.
Signed-off-by: Trond Myklebust <[email protected]>
---
fs/nfs/dir.c | 23 +++--------------------
1 file changed, 3 insertions(+), 20 deletions(-)
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 9d086ab4f889..dc6acfd14fc7 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -999,28 +999,11 @@ static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
return res;
}
-static bool nfs_readdir_dont_search_cache(struct nfs_readdir_descriptor *desc)
-{
- struct address_space *mapping = desc->file->f_mapping;
- struct inode *dir = file_inode(desc->file);
- unsigned int dtsize = NFS_SERVER(dir)->dtsize;
- loff_t size = i_size_read(dir);
-
- /*
- * Default to uncached readdir if the page cache is empty, and
- * we're looking for a non-zero cookie in a large directory.
- */
- return desc->dir_cookie != 0 && mapping->nrpages == 0 && size > dtsize;
-}
-
/* Search for desc->dir_cookie from the beginning of the page cache */
static int readdir_search_pagecache(struct nfs_readdir_descriptor *desc)
{
int res;
- if (nfs_readdir_dont_search_cache(desc))
- return -EBADCOOKIE;
-
do {
if (desc->page_index == 0) {
desc->current_index = 0;
@@ -1273,10 +1256,10 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
}
if (offset != filp->f_pos) {
filp->f_pos = offset;
- if (!nfs_readdir_use_cookie(filp)) {
+ dir_ctx->page_index = 0;
+ if (!nfs_readdir_use_cookie(filp))
dir_ctx->dir_cookie = 0;
- dir_ctx->page_index = 0;
- } else
+ else
dir_ctx->dir_cookie = offset;
if (offset == 0)
memset(dir_ctx->verf, 0, sizeof(dir_ctx->verf));
--
2.35.1
From: Trond Myklebust <[email protected]>
The heuristic for readdirplus is designed to try to detect 'ls -l' and
similar patterns. It does so by looking for cache hit/miss patterns in
both the attribute cache and in the dcache of the files in a given
directory, and then sets a flag for the readdirplus code to interpret.
The problem with this approach is that a single attribute or dcache miss
can cause the NFS code to force a refresh of the attributes for the
entire set of files contained in the directory.
To be able to make a more nuanced decision, let's sample the number of
hits and misses in the set of open directory descriptors. That allows us
to set thresholds at which we start preferring READDIRPLUS over regular
READDIR, or at which we start to force a re-read of the remaining
readdir cache using READDIRPLUS.
Signed-off-by: Trond Myklebust <[email protected]>
---
fs/nfs/dir.c | 80 +++++++++++++++++++++++++++---------------
fs/nfs/inode.c | 4 +--
fs/nfs/internal.h | 4 +--
fs/nfs/nfstrace.h | 1 -
include/linux/nfs_fs.h | 5 +--
5 files changed, 58 insertions(+), 36 deletions(-)
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index dc6acfd14fc7..098fc1bdaac8 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -87,8 +87,7 @@ alloc_nfs_open_dir_context(struct inode *dir)
nfs_set_cache_invalid(dir,
NFS_INO_INVALID_DATA |
NFS_INO_REVAL_FORCED);
- list_add(&ctx->list, &nfsi->open_files);
- clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags);
+ list_add_tail_rcu(&ctx->list, &nfsi->open_files);
memcpy(ctx->verf, nfsi->cookieverf, sizeof(ctx->verf));
spin_unlock(&dir->i_lock);
return ctx;
@@ -99,9 +98,9 @@ alloc_nfs_open_dir_context(struct inode *dir)
static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_context *ctx)
{
spin_lock(&dir->i_lock);
- list_del(&ctx->list);
+ list_del_rcu(&ctx->list);
spin_unlock(&dir->i_lock);
- kfree(ctx);
+ kfree_rcu(ctx, rcu_head);
}
/*
@@ -594,7 +593,6 @@ static int nfs_readdir_xdr_filler(struct nfs_readdir_descriptor *desc,
/* We requested READDIRPLUS, but the server doesn't grok it */
if (error == -ENOTSUPP && desc->plus) {
NFS_SERVER(inode)->caps &= ~NFS_CAP_READDIRPLUS;
- clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
desc->plus = arg.plus = false;
goto again;
}
@@ -644,51 +642,63 @@ int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
return 1;
}
-static
-bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx)
+#define NFS_READDIR_CACHE_USAGE_THRESHOLD (8UL)
+
+static bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx,
+ unsigned int cache_hits,
+ unsigned int cache_misses)
{
if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS))
return false;
- if (test_and_clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(dir)->flags))
- return true;
- if (ctx->pos == 0)
+ if (ctx->pos == 0 ||
+ cache_hits + cache_misses > NFS_READDIR_CACHE_USAGE_THRESHOLD)
return true;
return false;
}
/*
- * This function is called by the lookup and getattr code to request the
+ * This function is called by the getattr code to request the
* use of readdirplus to accelerate any future lookups in the same
* directory.
*/
-void nfs_advise_use_readdirplus(struct inode *dir)
+void nfs_readdir_record_entry_cache_hit(struct inode *dir)
{
struct nfs_inode *nfsi = NFS_I(dir);
+ struct nfs_open_dir_context *ctx;
if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) &&
- !list_empty(&nfsi->open_files))
- set_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags);
+ S_ISDIR(dir->i_mode)) {
+ rcu_read_lock();
+ list_for_each_entry_rcu (ctx, &nfsi->open_files, list)
+ atomic_inc(&ctx->cache_hits);
+ rcu_read_unlock();
+ }
}
/*
* This function is mainly for use by nfs_getattr().
*
* If this is an 'ls -l', we want to force use of readdirplus.
- * Do this by checking if there is an active file descriptor
- * and calling nfs_advise_use_readdirplus, then forcing a
- * cache flush.
*/
-void nfs_force_use_readdirplus(struct inode *dir)
+void nfs_readdir_record_entry_cache_miss(struct inode *dir)
{
struct nfs_inode *nfsi = NFS_I(dir);
+ struct nfs_open_dir_context *ctx;
if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) &&
- !list_empty(&nfsi->open_files)) {
- set_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags);
- set_bit(NFS_INO_FORCE_READDIR, &nfsi->flags);
+ S_ISDIR(dir->i_mode)) {
+ rcu_read_lock();
+ list_for_each_entry_rcu (ctx, &nfsi->open_files, list)
+ atomic_inc(&ctx->cache_misses);
+ rcu_read_unlock();
}
}
+static void nfs_lookup_advise_force_readdirplus(struct inode *dir)
+{
+ nfs_readdir_record_entry_cache_miss(dir);
+}
+
static
void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry,
unsigned long dir_verifier)
@@ -1122,6 +1132,19 @@ static int uncached_readdir(struct nfs_readdir_descriptor *desc)
return status;
}
+#define NFS_READDIR_CACHE_MISS_THRESHOLD (16UL)
+
+static void nfs_readdir_handle_cache_misses(struct inode *inode,
+ struct nfs_readdir_descriptor *desc,
+ pgoff_t page_index,
+ unsigned int cache_misses)
+{
+ if (desc->ctx->pos == 0 ||
+ cache_misses <= NFS_READDIR_CACHE_MISS_THRESHOLD)
+ return;
+ invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1);
+}
+
/* The file offset position represents the dirent entry number. A
last cookie cache takes care of the common case of reading the
whole directory.
@@ -1133,6 +1156,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs_open_dir_context *dir_ctx = file->private_data;
struct nfs_readdir_descriptor *desc;
+ unsigned int cache_hits, cache_misses;
pgoff_t page_index;
int res;
@@ -1154,7 +1178,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
goto out;
desc->file = file;
desc->ctx = ctx;
- desc->plus = nfs_use_readdirplus(inode, ctx);
desc->page_index_max = -1;
spin_lock(&file->f_lock);
@@ -1168,6 +1191,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
desc->eof = dir_ctx->eof;
nfs_set_dtsize(desc, dir_ctx->dtsize);
memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf));
+ cache_hits = atomic_xchg(&dir_ctx->cache_hits, 0);
+ cache_misses = atomic_xchg(&dir_ctx->cache_misses, 0);
spin_unlock(&file->f_lock);
if (desc->eof) {
@@ -1175,9 +1200,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
goto out_free;
}
- if (test_and_clear_bit(NFS_INO_FORCE_READDIR, &nfsi->flags) &&
- list_is_singular(&nfsi->open_files))
- invalidate_mapping_pages(inode->i_mapping, page_index + 1, -1);
+ desc->plus = nfs_use_readdirplus(inode, ctx, cache_hits, cache_misses);
+ nfs_readdir_handle_cache_misses(inode, desc, page_index, cache_misses);
do {
res = readdir_search_pagecache(desc);
@@ -1196,7 +1220,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
break;
}
if (res == -ETOOSMALL && desc->plus) {
- clear_bit(NFS_INO_ADVISE_RDPLUS, &nfsi->flags);
nfs_zap_caches(inode);
desc->page_index = 0;
desc->plus = false;
@@ -1610,7 +1633,7 @@ nfs_lookup_revalidate_dentry(struct inode *dir, struct dentry *dentry,
nfs_set_verifier(dentry, dir_verifier);
/* set a readdirplus hint that we had a cache miss */
- nfs_force_use_readdirplus(dir);
+ nfs_lookup_advise_force_readdirplus(dir);
ret = 1;
out:
nfs_free_fattr(fattr);
@@ -1667,7 +1690,6 @@ nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
nfs_mark_dir_for_revalidate(dir);
goto out_bad;
}
- nfs_advise_use_readdirplus(dir);
goto out_valid;
}
@@ -1872,7 +1894,7 @@ struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned in
goto out;
/* Notify readdir to use READDIRPLUS */
- nfs_force_use_readdirplus(dir);
+ nfs_lookup_advise_force_readdirplus(dir);
no_entry:
res = d_splice_alias(inode, dentry);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 7cecabf57b95..bbf4357ff727 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -787,7 +787,7 @@ static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry)
if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS))
return;
parent = dget_parent(dentry);
- nfs_force_use_readdirplus(d_inode(parent));
+ nfs_readdir_record_entry_cache_miss(d_inode(parent));
dput(parent);
}
@@ -798,7 +798,7 @@ static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry)
if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS))
return;
parent = dget_parent(dentry);
- nfs_advise_use_readdirplus(d_inode(parent));
+ nfs_readdir_record_entry_cache_hit(d_inode(parent));
dput(parent);
}
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index b5398af53c7f..194840a97e3a 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -366,8 +366,8 @@ extern struct nfs_client *nfs_init_client(struct nfs_client *clp,
const struct nfs_client_initdata *);
/* dir.c */
-extern void nfs_advise_use_readdirplus(struct inode *dir);
-extern void nfs_force_use_readdirplus(struct inode *dir);
+extern void nfs_readdir_record_entry_cache_hit(struct inode *dir);
+extern void nfs_readdir_record_entry_cache_miss(struct inode *dir);
extern unsigned long nfs_access_cache_count(struct shrinker *shrink,
struct shrink_control *sc);
extern unsigned long nfs_access_cache_scan(struct shrinker *shrink,
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 45a310b586ce..3672f6703ee7 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -36,7 +36,6 @@
#define nfs_show_nfsi_flags(v) \
__print_flags(v, "|", \
- { BIT(NFS_INO_ADVISE_RDPLUS), "ADVISE_RDPLUS" }, \
{ BIT(NFS_INO_STALE), "STALE" }, \
{ BIT(NFS_INO_ACL_LRU_SET), "ACL_LRU_SET" }, \
{ BIT(NFS_INO_INVALIDATING), "INVALIDATING" }, \
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 691a27936849..20a4cf0acad2 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -101,6 +101,8 @@ struct nfs_open_context {
struct nfs_open_dir_context {
struct list_head list;
+ atomic_t cache_hits;
+ atomic_t cache_misses;
unsigned long attr_gencount;
__be32 verf[NFS_DIR_VERIFIER_SIZE];
__u64 dir_cookie;
@@ -110,6 +112,7 @@ struct nfs_open_dir_context {
unsigned int dtsize;
signed char duped;
bool eof;
+ struct rcu_head rcu_head;
};
/*
@@ -274,13 +277,11 @@ struct nfs4_copy_state {
/*
* Bit offsets in flags field
*/
-#define NFS_INO_ADVISE_RDPLUS (0) /* advise readdirplus */
#define NFS_INO_STALE (1) /* possible stale inode */
#define NFS_INO_ACL_LRU_SET (2) /* Inode is on the LRU list */
#define NFS_INO_INVALIDATING (3) /* inode is being invalidated */
#define NFS_INO_PRESERVE_UNLINKED (4) /* preserve file if removed while open */
#define NFS_INO_FSCACHE (5) /* inode can be cached by FS-Cache */
-#define NFS_INO_FORCE_READDIR (7) /* force readdirplus */
#define NFS_INO_LAYOUTCOMMIT (9) /* layoutcommit required */
#define NFS_INO_LAYOUTCOMMITTING (10) /* layoutcommit inflight */
#define NFS_INO_LAYOUTSTATS (11) /* layoutstats inflight */
--
2.35.1
From: Trond Myklebust <[email protected]>
If attribute caching is turned off, then use of readdirplus is not going
to help stat() performance.
Readdirplus also doesn't help if a file is being written to, since we
will have to flush those writes in order to sync the mtime/ctime.
Signed-off-by: Trond Myklebust <[email protected]>
---
fs/nfs/inode.c | 45 +++++++++++++++++++++++++--------------------
1 file changed, 25 insertions(+), 20 deletions(-)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index bbf4357ff727..e51d86707fca 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -780,26 +780,32 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr,
}
EXPORT_SYMBOL_GPL(nfs_setattr_update_inode);
-static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry)
+/*
+ * Don't request help from readdirplus if the file is being written to,
+ * or if attribute caching is turned off
+ */
+static bool nfs_getattr_readdirplus_enable(const struct inode *inode)
{
- struct dentry *parent;
+ return nfs_server_capable(inode, NFS_CAP_READDIRPLUS) &&
+ !nfs_have_writebacks(inode) && NFS_MAXATTRTIMEO(inode) > 5 * HZ;
+}
- if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS))
- return;
- parent = dget_parent(dentry);
- nfs_readdir_record_entry_cache_miss(d_inode(parent));
- dput(parent);
+static void nfs_readdirplus_parent_cache_miss(struct dentry *dentry)
+{
+ if (!IS_ROOT(dentry)) {
+ struct dentry *parent = dget_parent(dentry);
+ nfs_readdir_record_entry_cache_miss(d_inode(parent));
+ dput(parent);
+ }
}
static void nfs_readdirplus_parent_cache_hit(struct dentry *dentry)
{
- struct dentry *parent;
-
- if (!nfs_server_capable(d_inode(dentry), NFS_CAP_READDIRPLUS))
- return;
- parent = dget_parent(dentry);
- nfs_readdir_record_entry_cache_hit(d_inode(parent));
- dput(parent);
+ if (!IS_ROOT(dentry)) {
+ struct dentry *parent = dget_parent(dentry);
+ nfs_readdir_record_entry_cache_hit(d_inode(parent));
+ dput(parent);
+ }
}
static u32 nfs_get_valid_attrmask(struct inode *inode)
@@ -835,6 +841,7 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
int err = 0;
bool force_sync = query_flags & AT_STATX_FORCE_SYNC;
bool do_update = false;
+ bool readdirplus_enabled = nfs_getattr_readdirplus_enable(inode);
trace_nfs_getattr_enter(inode);
@@ -843,7 +850,8 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
STATX_INO | STATX_SIZE | STATX_BLOCKS;
if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) {
- nfs_readdirplus_parent_cache_hit(path->dentry);
+ if (readdirplus_enabled)
+ nfs_readdirplus_parent_cache_hit(path->dentry);
goto out_no_revalidate;
}
@@ -893,15 +901,12 @@ int nfs_getattr(struct user_namespace *mnt_userns, const struct path *path,
do_update |= cache_validity & NFS_INO_INVALID_BLOCKS;
if (do_update) {
- /* Update the attribute cache */
- if (!(server->flags & NFS_MOUNT_NOAC))
+ if (readdirplus_enabled)
nfs_readdirplus_parent_cache_miss(path->dentry);
- else
- nfs_readdirplus_parent_cache_hit(path->dentry);
err = __nfs_revalidate_inode(server, inode);
if (err)
goto out;
- } else
+ } else if (readdirplus_enabled)
nfs_readdirplus_parent_cache_hit(path->dentry);
out_no_revalidate:
/* Only return attributes that were revalidated. */
--
2.35.1
From: Trond Myklebust <[email protected]>
Instead of pretending that we know the ratio of directory info vs
readdirplus attribute info, just set the 'dircount' field to the same
value as the 'maxcount' field.
Signed-off-by: Trond Myklebust <[email protected]>
---
fs/nfs/nfs3xdr.c | 7 ++++---
fs/nfs/nfs4xdr.c | 6 +++---
2 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 7ab60ad98776..d6779ceeb39e 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -1261,6 +1261,8 @@ static void nfs3_xdr_enc_readdir3args(struct rpc_rqst *req,
static void encode_readdirplus3args(struct xdr_stream *xdr,
const struct nfs3_readdirargs *args)
{
+ uint32_t dircount = args->count;
+ uint32_t maxcount = args->count;
__be32 *p;
encode_nfs_fh3(xdr, args->fh);
@@ -1273,9 +1275,8 @@ static void encode_readdirplus3args(struct xdr_stream *xdr,
* readdirplus: need dircount + buffer size.
* We just make sure we make dircount big enough
*/
- *p++ = cpu_to_be32(args->count >> 3);
-
- *p = cpu_to_be32(args->count);
+ *p++ = cpu_to_be32(dircount);
+ *p = cpu_to_be32(maxcount);
}
static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 8e70b92df4cc..b7780b97dc4d 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1605,7 +1605,8 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
FATTR4_WORD0_RDATTR_ERROR,
FATTR4_WORD1_MOUNTED_ON_FILEID,
};
- uint32_t dircount = readdir->count >> 1;
+ uint32_t dircount = readdir->count;
+ uint32_t maxcount = readdir->count;
__be32 *p, verf[2];
uint32_t attrlen = 0;
unsigned int i;
@@ -1618,7 +1619,6 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
FATTR4_WORD1_SPACE_USED|FATTR4_WORD1_TIME_ACCESS|
FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
attrs[2] |= FATTR4_WORD2_SECURITY_LABEL;
- dircount >>= 1;
}
/* Use mounted_on_fileid only if the server supports it */
if (!(readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID))
@@ -1634,7 +1634,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
encode_nfs4_verifier(xdr, &readdir->verifier);
p = reserve_space(xdr, 12 + (attrlen << 2));
*p++ = cpu_to_be32(dircount);
- *p++ = cpu_to_be32(readdir->count);
+ *p++ = cpu_to_be32(maxcount);
*p++ = cpu_to_be32(attrlen);
for (i = 0; i < attrlen; i++)
*p++ = cpu_to_be32(attrs[i]);
--
2.35.1