aufs: dirwh option

This is a feature to optimize for rmdir and rename dir.
When the number of whiteouts under the target dir is very many, it may
take a long time to remove them all. To prevent this, 'dirwh=%d' option
specifies the watermark to decide when to remove them.

For details, see aufs manual in aufs-util.git.
Signed-off-by: J. R. Okajima <hooanon05g@gmail.com>

fs/aufs/dir.h

@@ -82,6 +82,8 @@ int au_test_empty(struct dentry *dentry, struct au_nhash *whlist);
 unsigned int au_rdhash_est(loff_t sz);
 int au_nhash_alloc(struct au_nhash *nhash, unsigned int num_hash, gfp_t gfp);
 void au_nhash_wh_free(struct au_nhash *whlist);
+int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt,
+			    int limit);
 int au_nhash_test_known_wh(struct au_nhash *whlist, char *name, int nlen);
 int au_nhash_append_wh(struct au_nhash *whlist, char *name, int nlen, ino_t ino,
 		       unsigned int d_type, aufs_bindex_t bindex);

fs/aufs/i_op_del.c

@@ -206,7 +206,7 @@ out:
 static int renwh_and_rmdir(struct dentry *dentry, aufs_bindex_t bindex,
 			   struct au_nhash *whlist, struct inode *dir)
 {
-	int err;
+	int rmdir_later, err, dirwh;
 	struct dentry *h_dentry;
 	struct super_block *sb;
 	struct inode *inode;
@@ -222,6 +222,16 @@ static int renwh_and_rmdir(struct dentry *dentry, aufs_bindex_t bindex,
 	inode = d_inode(dentry);
 	au_hn_free(au_hi(inode, bindex));
 
+	if (!au_test_fs_remote(h_dentry->d_sb)) {
+		dirwh = au_sbi(sb)->si_dirwh;
+		rmdir_later = (dirwh <= 1);
+		if (!rmdir_later)
+			rmdir_later = au_nhash_test_longer_wh(whlist, bindex,
+							      dirwh);
+		if (rmdir_later)
+			return rmdir_later;
+	}
+
 	err = au_whtmp_rmdir(dir, bindex, h_dentry, whlist);
 	if (unlikely(err)) {
 		AuIOErr("rmdir %pd, b%d failed, %d. ignored\n",

fs/aufs/i_op_ren.c

@@ -238,16 +238,26 @@ static int au_ren_or_cpup(struct au_ren_args *a)
 /* cf. aufs_rmdir() */
 static int au_ren_del_whtmp(struct au_ren_args *a)
 {
+	int err;
 	struct inode *dir;
 
 	dir = a->dst_dir;
 	SiMustAnyLock(dir->i_sb);
-	au_nhash_wh_free(&a->thargs->whlist);
-	a->thargs->whlist = a->whlist;
-	a->whlist.nh_num = 0;
-	au_whtmp_kick_rmdir(dir, a->btgt, a->h_dst, a->thargs);
-	dput(a->h_dst);
-	a->thargs = NULL;
+	if (!au_nhash_test_longer_wh(&a->whlist, a->btgt,
+				     au_sbi(dir->i_sb)->si_dirwh)
+	    || au_test_fs_remote(a->h_dst->d_sb)) {
+		err = au_whtmp_rmdir(dir, a->btgt, a->h_dst, &a->whlist);
+		if (unlikely(err))
+			pr_warn("failed removing whtmp dir %pd (%d), "
+				"ignored.\n", a->h_dst, err);
+	} else {
+		au_nhash_wh_free(&a->thargs->whlist);
+		a->thargs->whlist = a->whlist;
+		a->whlist.nh_num = 0;
+		au_whtmp_kick_rmdir(dir, a->btgt, a->h_dst, a->thargs);
+		dput(a->h_dst);
+		a->thargs = NULL;
+	}
 
 	return 0;
 }

fs/aufs/opts.c

@@ -18,7 +18,7 @@ enum {
 	Opt_br,
 	Opt_add, Opt_del, Opt_mod, Opt_append, Opt_prepend,
 	Opt_idel, Opt_imod,
-	Opt_rdcache, Opt_rdblk, Opt_rdhash,
+	Opt_dirwh, Opt_rdcache, Opt_rdblk, Opt_rdhash,
 	Opt_rdblk_def, Opt_rdhash_def,
 	Opt_xino, Opt_noxino,
 	Opt_trunc_xino, Opt_trunc_xino_v, Opt_notrunc_xino,
@@ -54,6 +54,8 @@ static match_table_t options = {
 	{Opt_mod, "mod:%s"},
 	/* {Opt_imod, "imod:%d:%s"}, */
 
+	{Opt_dirwh, "dirwh=%d"},
+
 	{Opt_xino, "xino=%s"},
 	{Opt_noxino, "noxino"},
 	{Opt_trunc_xino, "trunc_xino"},
@@ -518,6 +520,9 @@ static void dump_opts(struct au_opts *opts)
 				  u.add->bindex, u.add->pathname, u.add->perm,
 				  u.add->path.dentry);
 			break;
+		case Opt_dirwh:
+			AuDbg("dirwh %d\n", opt->dirwh);
+			break;
 		case Opt_rdcache:
 			AuDbg("rdcache %d\n", opt->rdcache);
 			break;
@@ -990,6 +995,13 @@ int au_opts_parse(struct super_block *sb, char *str, struct au_opts *opts)
 			opt->type = token;
 			break;
 
+		case Opt_dirwh:
+			if (unlikely(match_int(&a->args[0], &opt->dirwh)))
+				break;
+			err = 0;
+			opt->type = token;
+			break;
+
 		case Opt_rdcache:
 			if (unlikely(match_int(&a->args[0], &n))) {
 				pr_err("bad integer in %s\n", opt_str);
@@ -1216,6 +1228,10 @@ static int au_opt_simple(struct super_block *sb, struct au_opt *opt,
 		sbinfo->si_wbr_copyup_ops = au_wbr_copyup_ops + opt->wbr_copyup;
 		break;
 
+	case Opt_dirwh:
+		sbinfo->si_dirwh = opt->dirwh;
+		break;
+
 	case Opt_rdcache:
 		sbinfo->si_rdcache
 			= msecs_to_jiffies(opt->rdcache * MSEC_PER_SEC);

fs/aufs/opts.h

@@ -138,6 +138,7 @@ struct au_opt {
 		struct au_opt_add	add;
 		struct au_opt_del	del;
 		struct au_opt_mod	mod;
+		int			dirwh;
 		int			rdcache;
 		unsigned int		rdblk;
 		unsigned int		rdhash;

fs/aufs/sbinfo.c

@@ -88,6 +88,7 @@ int au_si_alloc(struct super_block *sb)
 	sbinfo->si_rdcache = msecs_to_jiffies(AUFS_RDCACHE_DEF * MSEC_PER_SEC);
 	sbinfo->si_rdblk = AUFS_RDBLK_DEF;
 	sbinfo->si_rdhash = AUFS_RDHASH_DEF;
+	sbinfo->si_dirwh = AUFS_DIRWH_DEF;
 
 	for (i = 0; i < AuPlink_NHASH; i++)
 		INIT_HLIST_BL_HEAD(sbinfo->si_plink + i);

fs/aufs/super.c

@@ -268,6 +268,8 @@ static int aufs_show_options(struct seq_file *m, struct dentry *dentry)
 	if (v != AuWbrCopyup_Def)
 		seq_printf(m, ",cpup=%s", au_optstr_wbr_copyup(v));
 
+	AuUInt(DIRWH, dirwh, sbinfo->si_dirwh);
+
 	v = jiffies_to_msecs(sbinfo->si_rdcache) / MSEC_PER_SEC;
 	AuUInt(RDCACHE, rdcache, v);
 

fs/aufs/super.h

@@ -130,6 +130,14 @@ struct au_sbinfo {
 	unsigned int		si_rdblk;	/* deblk size */
 	unsigned int		si_rdhash;	/* hash size */
 
+	/*
+	 * If the number of whiteouts are larger than si_dirwh, leave all of
+	 * them after au_whtmp_ren to reduce the cost of rmdir(2).
+	 * future fsck.aufs or kernel thread will remove them later.
+	 * Otherwise, remove all whiteouts and the dir in rmdir(2).
+	 */
+	unsigned int		si_dirwh;
+
 	/* pseudo_link list */
 	struct hlist_bl_head	si_plink[AuPlink_NHASH];
 	wait_queue_head_t	si_plink_wq;

fs/aufs/vdir.c

@@ -141,6 +141,24 @@ static void au_nhash_de_free(struct au_nhash *delist)
 
 /* ---------------------------------------------------------------------- */
 
+int au_nhash_test_longer_wh(struct au_nhash *whlist, aufs_bindex_t btgt,
+			    int limit)
+{
+	int num;
+	unsigned int u, n;
+	struct hlist_head *head;
+	struct au_vdir_wh *pos;
+
+	num = 0;
+	n = whlist->nh_num;
+	head = whlist->nh_head;
+	for (u = 0; u < n; u++, head++)
+		hlist_for_each_entry(pos, head, wh_hash)
+			if (pos->wh_bindex == btgt && ++num > limit)
+				return 1;
+	return 0;
+}
+
 static struct hlist_head *au_name_hash(struct au_nhash *nhash,
 				       unsigned char *name,
 				       unsigned int len)

include/uapi/linux/aufs_type.h

@@ -73,6 +73,7 @@ typedef int16_t aufs_bindex_t;
 #define AUFS_XINO_DEFPATH	"/tmp/" AUFS_XINO_FNAME
 #define AUFS_XINO_DEF_SEC	30 /* seconds */
 #define AUFS_XINO_DEF_TRUNC	45 /* percentage */
+#define AUFS_DIRWH_DEF		3
 #define AUFS_RDCACHE_DEF	10 /* seconds */
 #define AUFS_RDCACHE_MAX	3600 /* seconds */
 #define AUFS_RDBLK_DEF		512 /* bytes */