GFS2: Use lvbs for storing rgrp information with mount option

Instead of reading in the resource groups when gfs2 is checking
for free space to allocate from, gfs2 can store the necessary infromation
in the resource group's lvb.  Also, instead of searching for unlinked
inodes in every resource group that's checked for free space, gfs2 can
store the number of unlinked but inodes in the lvb, and only check for
unlinked inodes if it will find some.

The first time a resource group is locked, the lvb must initialized.
Since this involves counting the unlinked inodes in the resource group,
this takes a little extra time.  But after that, if the resource group
is locked with GL_SKIP, the buffer head won't be read in unless it's
actually needed.

Enabling the resource groups lvbs is done via the rgrplvb mount option.  If
this option isn't set, the lvbs will still be set and updated, but they won't
be verfied or used by the filesystem.  To safely turn on this option, all of
the nodes mounting the filesystem must be running code with this patch, and
the filesystem must have been completely unmounted since they were updated.

Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

fs/gfs2/glock.c

@@ -769,6 +769,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	gl->gl_stats.stats[GFS2_LKS_DCOUNT] = 0;
 	gl->gl_stats.stats[GFS2_LKS_QCOUNT] = 0;
 	memset(&gl->gl_lksb, 0, sizeof(struct dlm_lksb));
+	memset(gl->gl_lvb, 0, 32 * sizeof(char));
 	gl->gl_lksb.sb_lvbptr = gl->gl_lvb;
 	gl->gl_tchange = jiffies;
 	gl->gl_object = NULL;

fs/gfs2/incore.h

@@ -89,6 +89,7 @@ struct gfs2_rgrpd {
 	u64 rd_igeneration;
 	struct gfs2_bitmap *rd_bits;
 	struct gfs2_sbd *rd_sbd;
+	struct gfs2_rgrp_lvb *rd_rgl;
 	u32 rd_last_alloc;
 	u32 rd_flags;
 #define GFS2_RDF_CHECK		0x10000000 /* check for unlinked inodes */
@@ -470,6 +471,7 @@ struct gfs2_args {
 	unsigned int ar_discard:1;		/* discard requests */
 	unsigned int ar_errors:2;               /* errors=withdraw | panic */
 	unsigned int ar_nobarrier:1;            /* do not send barriers */
+	unsigned int ar_rgrplvb:1;		/* use lvbs for rgrp info */
 	int ar_commit;				/* Commit interval */
 	int ar_statfs_quantum;			/* The fast statfs interval */
 	int ar_quota_quantum;			/* The quota interval */

fs/gfs2/rgrp.c

@@ -660,6 +660,7 @@ static int read_rindex_entry(struct gfs2_inode *ip)
 		goto fail;
 
 	rgd->rd_gl->gl_object = rgd;
+	rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lvb;
 	rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
 	if (rgd->rd_data > sdp->sd_max_rg_data)
 		sdp->sd_max_rg_data = rgd->rd_data;
@@ -769,9 +770,65 @@ static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
 	memset(&str->rg_reserved, 0, sizeof(str->rg_reserved));
 }
 
+static int gfs2_rgrp_lvb_valid(struct gfs2_rgrpd *rgd)
+{
+	struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl;
+	struct gfs2_rgrp *str = (struct gfs2_rgrp *)rgd->rd_bits[0].bi_bh->b_data;
+
+	if (rgl->rl_flags != str->rg_flags || rgl->rl_free != str->rg_free ||
+	    rgl->rl_dinodes != str->rg_dinodes ||
+	    rgl->rl_igeneration != str->rg_igeneration)
+		return 0;
+	return 1;
+}
+
+static void gfs2_rgrp_ondisk2lvb(struct gfs2_rgrp_lvb *rgl, const void *buf)
+{
+	const struct gfs2_rgrp *str = buf;
+
+	rgl->rl_magic = cpu_to_be32(GFS2_MAGIC);
+	rgl->rl_flags = str->rg_flags;
+	rgl->rl_free = str->rg_free;
+	rgl->rl_dinodes = str->rg_dinodes;
+	rgl->rl_igeneration = str->rg_igeneration;
+	rgl->__pad = 0UL;
+}
+
+static void update_rgrp_lvb_unlinked(struct gfs2_rgrpd *rgd, u32 change)
+{
+	struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl;
+	u32 unlinked = be32_to_cpu(rgl->rl_unlinked) + change;
+	rgl->rl_unlinked = cpu_to_be32(unlinked);
+}
+
+static u32 count_unlinked(struct gfs2_rgrpd *rgd)
+{
+	struct gfs2_bitmap *bi;
+	const u32 length = rgd->rd_length;
+	const u8 *buffer = NULL;
+	u32 i, goal, count = 0;
+
+	for (i = 0, bi = rgd->rd_bits; i < length; i++, bi++) {
+		goal = 0;
+		buffer = bi->bi_bh->b_data + bi->bi_offset;
+		WARN_ON(!buffer_uptodate(bi->bi_bh));
+		while (goal < bi->bi_len * GFS2_NBBY) {
+			goal = gfs2_bitfit(buffer, bi->bi_len, goal,
+					   GFS2_BLKST_UNLINKED);
+			if (goal == BFITNOENT)
+				break;
+			count++;
+			goal++;
+		}
+	}
+
+	return count;
+}
+
+
 /**
- * gfs2_rgrp_go_lock - Read in a RG's header and bitmaps
- * @gh: The glock holder for the resource group
+ * gfs2_rgrp_bh_get - Read in a RG's header and bitmaps
+ * @rgd: the struct gfs2_rgrpd describing the RG to read in
  *
  * Read in all of a Resource Group's header and bitmap blocks.
  * Caller must eventually call gfs2_rgrp_relse() to free the bitmaps.
@@ -779,9 +836,8 @@ static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
  * Returns: errno
  */
 
-int gfs2_rgrp_go_lock(struct gfs2_holder *gh)
+int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
 {
-	struct gfs2_rgrpd *rgd = gh->gh_gl->gl_object;
 	struct gfs2_sbd *sdp = rgd->rd_sbd;
 	struct gfs2_glock *gl = rgd->rd_gl;
 	unsigned int length = rgd->rd_length;
@@ -789,6 +845,9 @@ int gfs2_rgrp_go_lock(struct gfs2_holder *gh)
 	unsigned int x, y;
 	int error;
 
+	if (rgd->rd_bits[0].bi_bh != NULL)
+		return 0;
+
 	for (x = 0; x < length; x++) {
 		bi = rgd->rd_bits + x;
 		error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, &bi->bi_bh);
@@ -815,7 +874,20 @@ int gfs2_rgrp_go_lock(struct gfs2_holder *gh)
 		rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
 		rgd->rd_free_clone = rgd->rd_free;
 	}
-
+	if (be32_to_cpu(GFS2_MAGIC) != rgd->rd_rgl->rl_magic) {
+		rgd->rd_rgl->rl_unlinked = cpu_to_be32(count_unlinked(rgd));
+		gfs2_rgrp_ondisk2lvb(rgd->rd_rgl,
+				     rgd->rd_bits[0].bi_bh->b_data);
+	}
+	else if (sdp->sd_args.ar_rgrplvb) {
+		if (!gfs2_rgrp_lvb_valid(rgd)){
+			gfs2_consist_rgrpd(rgd);
+			error = -EIO;
+			goto fail;
+		}
+		if (rgd->rd_rgl->rl_unlinked == 0)
+			rgd->rd_flags &= ~GFS2_RDF_CHECK;
+	}
 	return 0;
 
 fail:
@@ -829,6 +901,39 @@ int gfs2_rgrp_go_lock(struct gfs2_holder *gh)
 	return error;
 }
 
+int update_rgrp_lvb(struct gfs2_rgrpd *rgd)
+{
+	u32 rl_flags;
+
+	if (rgd->rd_flags & GFS2_RDF_UPTODATE)
+		return 0;
+
+	if (be32_to_cpu(GFS2_MAGIC) != rgd->rd_rgl->rl_magic)
+		return gfs2_rgrp_bh_get(rgd);
+
+	rl_flags = be32_to_cpu(rgd->rd_rgl->rl_flags);
+	rl_flags &= ~GFS2_RDF_MASK;
+	rgd->rd_flags &= GFS2_RDF_MASK;
+	rgd->rd_flags |= (rl_flags | GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
+	if (rgd->rd_rgl->rl_unlinked == 0)
+		rgd->rd_flags &= ~GFS2_RDF_CHECK;
+	rgd->rd_free = be32_to_cpu(rgd->rd_rgl->rl_free);
+	rgd->rd_free_clone = rgd->rd_free;
+	rgd->rd_dinodes = be32_to_cpu(rgd->rd_rgl->rl_dinodes);
+	rgd->rd_igeneration = be64_to_cpu(rgd->rd_rgl->rl_igeneration);
+	return 0;
+}
+
+int gfs2_rgrp_go_lock(struct gfs2_holder *gh)
+{
+	struct gfs2_rgrpd *rgd = gh->gh_gl->gl_object;
+	struct gfs2_sbd *sdp = rgd->rd_sbd;
+
+	if (gh->gh_flags & GL_SKIP && sdp->sd_args.ar_rgrplvb)
+		return 0;
+	return gfs2_rgrp_bh_get((struct gfs2_rgrpd *)gh->gh_gl->gl_object);
+}
+
 /**
  * gfs2_rgrp_go_unlock - Release RG bitmaps read in with gfs2_rgrp_bh_get()
  * @gh: The glock holder for the resource group
@@ -842,8 +947,10 @@ void gfs2_rgrp_go_unlock(struct gfs2_holder *gh)
 
 	for (x = 0; x < length; x++) {
 		struct gfs2_bitmap *bi = rgd->rd_bits + x;
-		brelse(bi->bi_bh);
-		bi->bi_bh = NULL;
+		if (bi->bi_bh) {
+			brelse(bi->bi_bh);
+			bi->bi_bh = NULL;
+		}
 	}
 
 }
@@ -987,6 +1094,7 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
 				rgd->rd_flags |= GFS2_RGF_TRIMMED;
 				gfs2_trans_add_bh(rgd->rd_gl, bh, 1);
 				gfs2_rgrp_out(rgd, bh->b_data);
+				gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, bh->b_data);
 				gfs2_trans_end(sdp);
 			}
 		}
@@ -1116,6 +1224,9 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
 	int error, rg_locked, flags = LM_FLAG_TRY;
 	int loops = 0;
 
+	if (sdp->sd_args.ar_rgrplvb)
+		flags |= GL_SKIP;
+
 	if (ip->i_rgd && rgrp_contains_block(ip->i_rgd, ip->i_goal))
 		rgd = begin = ip->i_rgd;
 	else
@@ -1133,22 +1244,34 @@ static int get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
 		} else {
 			error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
 						   flags, &rs->rs_rgd_gh);
+			if (!error && sdp->sd_args.ar_rgrplvb) {
+				error = update_rgrp_lvb(rgd);
+				if (error) {
+					gfs2_glock_dq_uninit(&rs->rs_rgd_gh);
+					return error;
+				}
+			}
 		}
 		switch (error) {
 		case 0:
 			if (try_rgrp_fit(rgd, ip)) {
+				if (sdp->sd_args.ar_rgrplvb)
+					gfs2_rgrp_bh_get(rgd);
 				ip->i_rgd = rgd;
 				return 0;
 			}
-			if (rgd->rd_flags & GFS2_RDF_CHECK)
+			if (rgd->rd_flags & GFS2_RDF_CHECK) {
+				if (sdp->sd_args.ar_rgrplvb)
+					gfs2_rgrp_bh_get(rgd);
 				try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr);
+			}
 			if (!rg_locked)
 				gfs2_glock_dq_uninit(&rs->rs_rgd_gh);
 			/* fall through */
 		case GLR_TRYFAILED:
 			rgd = gfs2_rgrpd_get_next(rgd);
 			if (rgd == begin) {
-				flags = 0;
+				flags &= ~LM_FLAG_TRY;
 				loops++;
 			}
 			break;
@@ -1529,6 +1652,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
 
 	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
+	gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, rgd->rd_bits[0].bi_bh->b_data);
 
 	gfs2_statfs_change(sdp, 0, -(s64)*nblocks, dinode ? 1 : 0);
 	if (dinode)
@@ -1575,6 +1699,7 @@ void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta)
 	rgd->rd_flags &= ~GFS2_RGF_TRIMMED;
 	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
+	gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, rgd->rd_bits[0].bi_bh->b_data);
 
 	/* Directories keep their data in the metadata address space */
 	if (meta || ip->i_depth)
@@ -1611,6 +1736,8 @@ void gfs2_unlink_di(struct inode *inode)
 	trace_gfs2_block_alloc(ip, rgd, blkno, 1, GFS2_BLKST_UNLINKED);
 	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
+	gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, rgd->rd_bits[0].bi_bh->b_data);
+	update_rgrp_lvb_unlinked(rgd, 1);
 }
 
 static void gfs2_free_uninit_di(struct gfs2_rgrpd *rgd, u64 blkno)
@@ -1630,6 +1757,8 @@ static void gfs2_free_uninit_di(struct gfs2_rgrpd *rgd, u64 blkno)
 
 	gfs2_trans_add_bh(rgd->rd_gl, rgd->rd_bits[0].bi_bh, 1);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
+	gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, rgd->rd_bits[0].bi_bh->b_data);
+	update_rgrp_lvb_unlinked(rgd, -1);
 
 	gfs2_statfs_change(sdp, 0, +1, -1);
 }

fs/gfs2/super.c

@@ -78,6 +78,8 @@ enum {
 	Opt_quota_quantum,
 	Opt_barrier,
 	Opt_nobarrier,
+	Opt_rgrplvb,
+	Opt_norgrplvb,
 	Opt_error,
 };
 
@@ -115,6 +117,8 @@ static const match_table_t tokens = {
 	{Opt_quota_quantum, "quota_quantum=%d"},
 	{Opt_barrier, "barrier"},
 	{Opt_nobarrier, "nobarrier"},
+	{Opt_rgrplvb, "rgrplvb"},
+	{Opt_norgrplvb, "norgrplvb"},
 	{Opt_error, NULL}
 };
 
@@ -267,6 +271,12 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
 		case Opt_nobarrier:
 			args->ar_nobarrier = 1;
 			break;
+		case Opt_rgrplvb:
+			args->ar_rgrplvb = 1;
+			break;
+		case Opt_norgrplvb:
+			args->ar_rgrplvb = 0;
+			break;
 		case Opt_error:
 		default:
 			printk(KERN_WARNING "GFS2: invalid mount option: %s\n", o);
@@ -1379,6 +1389,8 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root)
 		seq_printf(s, ",nobarrier");
 	if (test_bit(SDF_DEMOTE, &sdp->sd_flags))
 		seq_printf(s, ",demote_interface_used");
+	if (args->ar_rgrplvb)
+		seq_printf(s, ",rgrplvb");
 	return 0;
 }
 

include/linux/gfs2_ondisk.h

@@ -170,6 +170,16 @@ struct gfs2_rindex {
 #define GFS2_RGF_NOALLOC	0x00000008
 #define GFS2_RGF_TRIMMED	0x00000010
 
+struct gfs2_rgrp_lvb {
+	__be32 rl_magic;
+	__be32 rl_flags;
+	__be32 rl_free;
+	__be32 rl_dinodes;
+	__be64 rl_igeneration;
+	__be32 rl_unlinked;
+	__be32 __pad;
+};
+
 struct gfs2_rgrp {
 	struct gfs2_meta_header rg_header;