NFS: Improve heuristic for readdirplus

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 <trond.myklebust@hammerspace.com>

4 files changed, 55 insertions, 34 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 @@ out:
 	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" }, \