[Cluster-devel] [PATCH 0/6] GFS2: Pre-pull patch posting (merge window)

[Cluster-devel] [PATCH 0/6] GFS2: Pre-pull patch posting (merge window)

[Bob Peterson]

Hi,

Here is a list of patches we've accumulated for GFS2 for the current upstream
merge window. There are only six patches this time: a couple of code
cleanups from Andreas, a change from signed to unsigned for glock statistics,
and two patches that improve GFS2's glock scalability by changing from a
regular hash table to a resizeable hash table.

Regards,

Bob Peterson
Red Hat File Systems

----------------------------------------------------------------

Andreas Gruenbacher (3):
  gfs2: Simplify the seq file code for "sbstats"
  gfs2: Fix a typo in a comment
  gfs2: A minor "sbstats" cleanup

Ben Hutchings (1):
  gfs2: Make statistics unsigned, suitable for use with do_div()

Bob Peterson (2):
  GFS2: Move glock superblock pointer to field gl_name
  GFS2: Use resizable hash table for glocks

 fs/gfs2/glock.c      | 348 ++++++++++++++++++++-------------------------------
 fs/gfs2/glops.c      |  38 +++---
 fs/gfs2/incore.h     |  15 +--
 fs/gfs2/lock_dlm.c   |  12 +-
 fs/gfs2/lops.c       |   6 +-
 fs/gfs2/meta_io.c    |   6 +-
 fs/gfs2/meta_io.h    |   2 +-
 fs/gfs2/quota.c      |  22 ++--
 fs/gfs2/rgrp.c       |  10 +-
 fs/gfs2/trace_gfs2.h |  34 ++---
 fs/gfs2/trans.c      |   4 +-
 11 files changed, 212 insertions(+), 285 deletions(-)

-- 
2.4.3

[Cluster-devel] [PATCH 1/6] gfs2: Simplify the seq file code for "sbstats"

[Bob Peterson]

From: Andreas Gruenbacher <agruenba@redhat.com>

Don't use struct gfs2_glock_iter as the helper data structure for iterating
through "sbstats"; we are not iterating through glocks here.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/glock.c | 31 +++++++++++--------------------
 1 file changed, 11 insertions(+), 20 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index a38e38f..a694413 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1776,10 +1776,10 @@ static const char *gfs2_stype[] = {
 
 static int gfs2_sbstats_seq_show(struct seq_file *seq, void *iter_ptr)
 {
-	struct gfs2_glock_iter *gi = seq->private;
-	struct gfs2_sbd *sdp = gi->sdp;
-	unsigned index = gi->hash >> 3;
-	unsigned subindex = gi->hash & 0x07;
+	struct gfs2_sbd *sdp = seq->private;
+	loff_t pos = *(loff_t *)iter_ptr;
+	unsigned index = pos >> 3;
+	unsigned subindex = pos & 0x07;
 	s64 value;
 	int i;
 
@@ -1930,26 +1930,19 @@ static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
 
 static void *gfs2_sbstats_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	struct gfs2_glock_iter *gi = seq->private;
-
-	gi->hash = *pos;
+	preempt_disable();
 	if (*pos >= GFS2_NR_SBSTATS)
 		return NULL;
-	preempt_disable();
-	return SEQ_START_TOKEN;
+	return pos;
 }
 
 static void *gfs2_sbstats_seq_next(struct seq_file *seq, void *iter_ptr,
 				   loff_t *pos)
 {
-	struct gfs2_glock_iter *gi = seq->private;
 	(*pos)++;
-	gi->hash++;
-	if (gi->hash >= GFS2_NR_SBSTATS) {
-		preempt_enable();
+	if (*pos >= GFS2_NR_SBSTATS)
 		return NULL;
-	}
-	return SEQ_START_TOKEN;
+	return pos;
 }
 
 static void gfs2_sbstats_seq_stop(struct seq_file *seq, void *iter_ptr)
@@ -2012,12 +2005,10 @@ static int gfs2_glstats_open(struct inode *inode, struct file *file)
 
 static int gfs2_sbstats_open(struct inode *inode, struct file *file)
 {
-	int ret = seq_open_private(file, &gfs2_sbstats_seq_ops,
-				   sizeof(struct gfs2_glock_iter));
+	int ret = seq_open(file, &gfs2_sbstats_seq_ops);
 	if (ret == 0) {
 		struct seq_file *seq = file->private_data;
-		struct gfs2_glock_iter *gi = seq->private;
-		gi->sdp = inode->i_private;
+		seq->private = inode->i_private;  /* sdp */
 	}
 	return ret;
 }
@@ -2043,7 +2034,7 @@ static const struct file_operations gfs2_sbstats_fops = {
 	.open	 = gfs2_sbstats_open,
 	.read    = seq_read,
 	.llseek  = seq_lseek,
-	.release = seq_release_private,
+	.release = seq_release,
 };
 
 int gfs2_create_debugfs_file(struct gfs2_sbd *sdp)
-- 
2.4.3

[Cluster-devel] [PATCH 2/6] GFS2: Move glock superblock pointer to field gl_name

[Bob Peterson]

What uniquely identifies a glock in the glock hash table is not
gl_name, but gl_name and its superblock pointer. This patch makes
the gl_name field correspond to a unique glock identifier. That will
allow us to simplify hashing with a future patch, since the hash
algorithm can then take the gl_name and hash its components in one
operation.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Acked-by: Steven Whitehouse <swhiteho@redhat.com>
---
 fs/gfs2/glock.c      | 32 +++++++++++++++-----------------
 fs/gfs2/glops.c      | 38 ++++++++++++++++++++------------------
 fs/gfs2/incore.h     |  9 +++++----
 fs/gfs2/lock_dlm.c   | 10 +++++-----
 fs/gfs2/lops.c       |  6 +++---
 fs/gfs2/meta_io.c    |  6 +++---
 fs/gfs2/meta_io.h    |  2 +-
 fs/gfs2/quota.c      | 22 +++++++++++-----------
 fs/gfs2/rgrp.c       |  2 +-
 fs/gfs2/trace_gfs2.h | 18 +++++++++---------
 fs/gfs2/trans.c      |  4 ++--
 11 files changed, 75 insertions(+), 74 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index a694413..13cba6e 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -119,7 +119,7 @@ static void gfs2_glock_dealloc(struct rcu_head *rcu)
 
 void gfs2_glock_free(struct gfs2_glock *gl)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
 	call_rcu(&gl->gl_rcu, gfs2_glock_dealloc);
 	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
@@ -192,7 +192,7 @@ static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
 
 void gfs2_glock_put(struct gfs2_glock *gl)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct address_space *mapping = gfs2_glock2aspace(gl);
 
 	if (lockref_put_or_lock(&gl->gl_lockref))
@@ -220,7 +220,6 @@ void gfs2_glock_put(struct gfs2_glock *gl)
  */
 
 static struct gfs2_glock *search_bucket(unsigned int hash,
-					const struct gfs2_sbd *sdp,
 					const struct lm_lockname *name)
 {
 	struct gfs2_glock *gl;
@@ -229,8 +228,6 @@ static struct gfs2_glock *search_bucket(unsigned int hash,
 	hlist_bl_for_each_entry_rcu(gl, h, &gl_hash_table[hash], gl_list) {
 		if (!lm_name_equal(&gl->gl_name, name))
 			continue;
-		if (gl->gl_sbd != sdp)
-			continue;
 		if (lockref_get_not_dead(&gl->gl_lockref))
 			return gl;
 	}
@@ -506,7 +503,7 @@ __releases(&gl->gl_spin)
 __acquires(&gl->gl_spin)
 {
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	unsigned int lck_flags = gh ? gh->gh_flags : 0;
 	int ret;
 
@@ -628,7 +625,7 @@ out_unlock:
 static void delete_work_func(struct work_struct *work)
 {
 	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_delete);
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_inode *ip;
 	struct inode *inode;
 	u64 no_addr = gl->gl_name.ln_number;
@@ -704,14 +701,16 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		   struct gfs2_glock **glp)
 {
 	struct super_block *s = sdp->sd_vfs;
-	struct lm_lockname name = { .ln_number = number, .ln_type = glops->go_type };
+	struct lm_lockname name = { .ln_number = number,
+				    .ln_type = glops->go_type,
+				    .ln_sbd = sdp };
 	struct gfs2_glock *gl, *tmp;
 	unsigned int hash = gl_hash(sdp, &name);
 	struct address_space *mapping;
 	struct kmem_cache *cachep;
 
 	rcu_read_lock();
-	gl = search_bucket(hash, sdp, &name);
+	gl = search_bucket(hash, &name);
 	rcu_read_unlock();
 
 	*glp = gl;
@@ -739,7 +738,6 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	}
 
 	atomic_inc(&sdp->sd_glock_disposal);
-	gl->gl_sbd = sdp;
 	gl->gl_flags = 0;
 	gl->gl_name = name;
 	gl->gl_lockref.count = 1;
@@ -772,7 +770,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	}
 
 	spin_lock_bucket(hash);
-	tmp = search_bucket(hash, sdp, &name);
+	tmp = search_bucket(hash, &name);
 	if (tmp) {
 		spin_unlock_bucket(hash);
 		kfree(gl->gl_lksb.sb_lvbptr);
@@ -928,7 +926,7 @@ __releases(&gl->gl_spin)
 __acquires(&gl->gl_spin)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct list_head *insert_pt = NULL;
 	struct gfs2_holder *gh2;
 	int try_futile = 0;
@@ -1006,7 +1004,7 @@ trap_recursive:
 int gfs2_glock_nq(struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	int error = 0;
 
 	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
@@ -1313,7 +1311,7 @@ static int gfs2_should_freeze(const struct gfs2_glock *gl)
 
 void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
 {
-	struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
+	struct lm_lockstruct *ls = &gl->gl_name.ln_sbd->sd_lockstruct;
 
 	spin_lock(&gl->gl_spin);
 	gl->gl_reply = ret;
@@ -1471,7 +1469,7 @@ static void examine_bucket(glock_examiner examiner, const struct gfs2_sbd *sdp,
 
 	rcu_read_lock();
 	hlist_bl_for_each_entry_rcu(gl, pos, head, gl_list) {
-		if ((gl->gl_sbd == sdp) && lockref_get_not_dead(&gl->gl_lockref))
+		if ((gl->gl_name.ln_sbd == sdp) && lockref_get_not_dead(&gl->gl_lockref))
 			examiner(gl);
 	}
 	rcu_read_unlock();
@@ -1569,7 +1567,7 @@ void gfs2_glock_finish_truncate(struct gfs2_inode *ip)
 	int ret;
 
 	ret = gfs2_truncatei_resume(ip);
-	gfs2_assert_withdraw(gl->gl_sbd, ret == 0);
+	gfs2_assert_withdraw(gl->gl_name.ln_sbd, ret == 0);
 
 	spin_lock(&gl->gl_spin);
 	clear_bit(GLF_LOCK, &gl->gl_flags);
@@ -1872,7 +1870,7 @@ static int gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
 			gi->nhash = 0;
 		}
 	/* Skip entries for other sb and dead entries */
-	} while (gi->sdp != gi->gl->gl_sbd ||
+	} while (gi->sdp != gi->gl->gl_name.ln_sbd ||
 		 __lockref_is_dead(&gi->gl->gl_lockref));
 
 	return 0;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index fa3fa5e..1f6c9c3 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -32,13 +32,15 @@ struct workqueue_struct *gfs2_freeze_wq;
 
 static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
 {
-	fs_err(gl->gl_sbd, "AIL buffer %p: blocknr %llu state 0x%08lx mapping %p page state 0x%lx\n",
+	fs_err(gl->gl_name.ln_sbd,
+	       "AIL buffer %p: blocknr %llu state 0x%08lx mapping %p page "
+	       "state 0x%lx\n",
 	       bh, (unsigned long long)bh->b_blocknr, bh->b_state,
 	       bh->b_page->mapping, bh->b_page->flags);
-	fs_err(gl->gl_sbd, "AIL glock %u:%llu mapping %p\n",
+	fs_err(gl->gl_name.ln_sbd, "AIL glock %u:%llu mapping %p\n",
 	       gl->gl_name.ln_type, gl->gl_name.ln_number,
 	       gfs2_glock2aspace(gl));
-	gfs2_lm_withdraw(gl->gl_sbd, "AIL error\n");
+	gfs2_lm_withdraw(gl->gl_name.ln_sbd, "AIL error\n");
 }
 
 /**
@@ -52,7 +54,7 @@ static void gfs2_ail_error(struct gfs2_glock *gl, const struct buffer_head *bh)
 static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync,
 			     unsigned int nr_revokes)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct list_head *head = &gl->gl_ail_list;
 	struct gfs2_bufdata *bd, *tmp;
 	struct buffer_head *bh;
@@ -80,7 +82,7 @@ static void __gfs2_ail_flush(struct gfs2_glock *gl, bool fsync,
 
 static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_trans tr;
 
 	memset(&tr, 0, sizeof(tr));
@@ -109,7 +111,7 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
 
 void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	unsigned int revokes = atomic_read(&gl->gl_ail_count);
 	unsigned int max_revokes = (sdp->sd_sb.sb_bsize - sizeof(struct gfs2_log_descriptor)) / sizeof(u64);
 	int ret;
@@ -139,7 +141,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
 
 static void rgrp_go_sync(struct gfs2_glock *gl)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct address_space *mapping = &sdp->sd_aspace;
 	struct gfs2_rgrpd *rgd;
 	int error;
@@ -179,7 +181,7 @@ static void rgrp_go_sync(struct gfs2_glock *gl)
 
 static void rgrp_go_inval(struct gfs2_glock *gl, int flags)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct address_space *mapping = &sdp->sd_aspace;
 	struct gfs2_rgrpd *rgd = gl->gl_object;
 
@@ -218,7 +220,7 @@ static void inode_go_sync(struct gfs2_glock *gl)
 
 	GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
 
-	gfs2_log_flush(gl->gl_sbd, gl, NORMAL_FLUSH);
+	gfs2_log_flush(gl->gl_name.ln_sbd, gl, NORMAL_FLUSH);
 	filemap_fdatawrite(metamapping);
 	if (ip) {
 		struct address_space *mapping = ip->i_inode.i_mapping;
@@ -252,7 +254,7 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
 {
 	struct gfs2_inode *ip = gl->gl_object;
 
-	gfs2_assert_withdraw(gl->gl_sbd, !atomic_read(&gl->gl_ail_count));
+	gfs2_assert_withdraw(gl->gl_name.ln_sbd, !atomic_read(&gl->gl_ail_count));
 
 	if (flags & DIO_METADATA) {
 		struct address_space *mapping = gfs2_glock2aspace(gl);
@@ -264,9 +266,9 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
 		}
 	}
 
-	if (ip == GFS2_I(gl->gl_sbd->sd_rindex)) {
-		gfs2_log_flush(gl->gl_sbd, NULL, NORMAL_FLUSH);
-		gl->gl_sbd->sd_rindex_uptodate = 0;
+	if (ip == GFS2_I(gl->gl_name.ln_sbd->sd_rindex)) {
+		gfs2_log_flush(gl->gl_name.ln_sbd, NULL, NORMAL_FLUSH);
+		gl->gl_name.ln_sbd->sd_rindex_uptodate = 0;
 	}
 	if (ip && S_ISREG(ip->i_inode.i_mode))
 		truncate_inode_pages(ip->i_inode.i_mapping, 0);
@@ -281,7 +283,7 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
 
 static int inode_go_demote_ok(const struct gfs2_glock *gl)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_holder *gh;
 
 	if (sdp->sd_jindex == gl->gl_object || sdp->sd_rindex == gl->gl_object)
@@ -416,7 +418,7 @@ int gfs2_inode_refresh(struct gfs2_inode *ip)
 static int inode_go_lock(struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl = gh->gh_gl;
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_inode *ip = gl->gl_object;
 	int error = 0;
 
@@ -477,7 +479,7 @@ static void inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
 static void freeze_go_sync(struct gfs2_glock *gl)
 {
 	int error = 0;
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
 	if (gl->gl_state == LM_ST_SHARED &&
 	    test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags)) {
@@ -500,7 +502,7 @@ static void freeze_go_sync(struct gfs2_glock *gl)
 
 static int freeze_go_xmote_bh(struct gfs2_glock *gl, struct gfs2_holder *gh)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_jdesc->jd_inode);
 	struct gfs2_glock *j_gl = ip->i_gl;
 	struct gfs2_log_header_host head;
@@ -545,7 +547,7 @@ static int freeze_go_demote_ok(const struct gfs2_glock *gl)
 static void iopen_go_callback(struct gfs2_glock *gl, bool remote)
 {
 	struct gfs2_inode *ip = (struct gfs2_inode *)gl->gl_object;
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
 	if (!remote || (sdp->sd_vfs->s_flags & MS_RDONLY))
 		return;
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index a1ec7c2..35a55f3 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -203,13 +203,15 @@ enum {
 };
 
 struct lm_lockname {
+	struct gfs2_sbd *ln_sbd;
 	u64 ln_number;
 	unsigned int ln_type;
 };
 
 #define lm_name_equal(name1, name2) \
-        (((name1)->ln_number == (name2)->ln_number) && \
-         ((name1)->ln_type == (name2)->ln_type))
+        (((name1)->ln_number == (name2)->ln_number) &&	\
+	 ((name1)->ln_type == (name2)->ln_type) &&	\
+	 ((name1)->ln_sbd == (name2)->ln_sbd))
 
 
 struct gfs2_glock_operations {
@@ -327,7 +329,6 @@ enum {
 
 struct gfs2_glock {
 	struct hlist_bl_node gl_list;
-	struct gfs2_sbd *gl_sbd;
 	unsigned long gl_flags;		/* GLF_... */
 	struct lm_lockname gl_name;
 
@@ -835,7 +836,7 @@ static inline void gfs2_glstats_inc(struct gfs2_glock *gl, int which)
 
 static inline void gfs2_sbstats_inc(const struct gfs2_glock *gl, int which)
 {
-	const struct gfs2_sbd *sdp = gl->gl_sbd;
+	const struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	preempt_disable();
 	this_cpu_ptr(sdp->sd_lkstats)->lkstats[gl->gl_name.ln_type].stats[which]++;
 	preempt_enable();
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 641383a..c962cfc 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -80,7 +80,7 @@ static inline void gfs2_update_reply_times(struct gfs2_glock *gl)
 
 	preempt_disable();
 	rtt = ktime_to_ns(ktime_sub(ktime_get_real(), gl->gl_dstamp));
-	lks = this_cpu_ptr(gl->gl_sbd->sd_lkstats);
+	lks = this_cpu_ptr(gl->gl_name.ln_sbd->sd_lkstats);
 	gfs2_update_stats(&gl->gl_stats, index, rtt);		/* Local */
 	gfs2_update_stats(&lks->lkstats[gltype], index, rtt);	/* Global */
 	preempt_enable();
@@ -108,7 +108,7 @@ static inline void gfs2_update_request_times(struct gfs2_glock *gl)
 	dstamp = gl->gl_dstamp;
 	gl->gl_dstamp = ktime_get_real();
 	irt = ktime_to_ns(ktime_sub(gl->gl_dstamp, dstamp));
-	lks = this_cpu_ptr(gl->gl_sbd->sd_lkstats);
+	lks = this_cpu_ptr(gl->gl_name.ln_sbd->sd_lkstats);
 	gfs2_update_stats(&gl->gl_stats, GFS2_LKS_SIRT, irt);		/* Local */
 	gfs2_update_stats(&lks->lkstats[gltype], GFS2_LKS_SIRT, irt);	/* Global */
 	preempt_enable();
@@ -253,7 +253,7 @@ static void gfs2_reverse_hex(char *c, u64 value)
 static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
 		     unsigned int flags)
 {
-	struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
+	struct lm_lockstruct *ls = &gl->gl_name.ln_sbd->sd_lockstruct;
 	int req;
 	u32 lkf;
 	char strname[GDLM_STRNAME_BYTES] = "";
@@ -281,7 +281,7 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
 
 static void gdlm_put_lock(struct gfs2_glock *gl)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct lm_lockstruct *ls = &sdp->sd_lockstruct;
 	int lvb_needs_unlock = 0;
 	int error;
@@ -319,7 +319,7 @@ static void gdlm_put_lock(struct gfs2_glock *gl)
 
 static void gdlm_cancel(struct gfs2_glock *gl)
 {
-	struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
+	struct lm_lockstruct *ls = &gl->gl_name.ln_sbd->sd_lockstruct;
 	dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_CANCEL, NULL, gl);
 }
 
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 2c1ae86..7833394 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -70,7 +70,7 @@ static bool buffer_is_rgrp(const struct gfs2_bufdata *bd)
 static void maybe_release_space(struct gfs2_bufdata *bd)
 {
 	struct gfs2_glock *gl = bd->bd_gl;
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_rgrpd *rgd = gl->gl_object;
 	unsigned int index = bd->bd_bh->b_blocknr - gl->gl_name.ln_number;
 	struct gfs2_bitmap *bi = rgd->rd_bits + index;
@@ -585,7 +585,7 @@ static int buf_lo_scan_elements(struct gfs2_jdesc *jd, unsigned int start,
 static void gfs2_meta_sync(struct gfs2_glock *gl)
 {
 	struct address_space *mapping = gfs2_glock2aspace(gl);
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	int error;
 
 	if (mapping == NULL)
@@ -595,7 +595,7 @@ static void gfs2_meta_sync(struct gfs2_glock *gl)
 	error = filemap_fdatawait(mapping);
 
 	if (error)
-		gfs2_io_error(gl->gl_sbd);
+		gfs2_io_error(gl->gl_name.ln_sbd);
 }
 
 static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index b984a6e..0e1d4be 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -114,7 +114,7 @@ const struct address_space_operations gfs2_rgrp_aops = {
 struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno, int create)
 {
 	struct address_space *mapping = gfs2_glock2aspace(gl);
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct page *page;
 	struct buffer_head *bh;
 	unsigned int shift;
@@ -200,7 +200,7 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
 int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 		   struct buffer_head **bhp)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct buffer_head *bh;
 
 	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
@@ -362,7 +362,7 @@ int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
 
 struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
 {
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct buffer_head *first_bh, *bh;
 	u32 max_ra = gfs2_tune_get(sdp, gt_max_readahead) >>
 			  sdp->sd_sb.sb_bsize_shift;
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
index ac5d802..8ca1615 100644
--- a/fs/gfs2/meta_io.h
+++ b/fs/gfs2/meta_io.h
@@ -44,7 +44,7 @@ static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping)
 {
 	struct inode *inode = mapping->host;
 	if (mapping->a_ops == &gfs2_meta_aops)
-		return (((struct gfs2_glock *)mapping) - 1)->gl_sbd;
+		return (((struct gfs2_glock *)mapping) - 1)->gl_name.ln_sbd;
 	else if (mapping->a_ops == &gfs2_rgrp_aops)
 		return container_of(mapping, struct gfs2_sbd, sd_aspace);
 	else
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 9b61f92..3a31226 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -119,7 +119,7 @@ static void gfs2_qd_dispose(struct list_head *list)
 
 	while (!list_empty(list)) {
 		qd = list_entry(list->next, struct gfs2_quota_data, qd_lru);
-		sdp = qd->qd_gl->gl_sbd;
+		sdp = qd->qd_gl->gl_name.ln_sbd;
 
 		list_del(&qd->qd_lru);
 
@@ -302,7 +302,7 @@ static int qd_get(struct gfs2_sbd *sdp, struct kqid qid,
 
 static void qd_hold(struct gfs2_quota_data *qd)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
 	gfs2_assert(sdp, !__lockref_is_dead(&qd->qd_lockref));
 	lockref_get(&qd->qd_lockref);
 }
@@ -367,7 +367,7 @@ static void slot_put(struct gfs2_quota_data *qd)
 
 static int bh_get(struct gfs2_quota_data *qd)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
 	unsigned int block, offset;
 	struct buffer_head *bh;
@@ -414,7 +414,7 @@ fail:
 
 static void bh_put(struct gfs2_quota_data *qd)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
 
 	mutex_lock(&sdp->sd_quota_mutex);
 	gfs2_assert(sdp, qd->qd_bh_count);
@@ -486,7 +486,7 @@ static int qd_fish(struct gfs2_sbd *sdp, struct gfs2_quota_data **qdp)
 
 static void qd_unlock(struct gfs2_quota_data *qd)
 {
-	gfs2_assert_warn(qd->qd_gl->gl_sbd,
+	gfs2_assert_warn(qd->qd_gl->gl_name.ln_sbd,
 			 test_bit(QDF_LOCKED, &qd->qd_flags));
 	clear_bit(QDF_LOCKED, &qd->qd_flags);
 	bh_put(qd);
@@ -614,7 +614,7 @@ static int sort_qd(const void *a, const void *b)
 
 static void do_qc(struct gfs2_quota_data *qd, s64 change)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
 	struct gfs2_quota_change *qc = qd->qd_bh_qc;
 	s64 x;
@@ -831,7 +831,7 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
 
 static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
 {
-	struct gfs2_sbd *sdp = (*qda)->qd_gl->gl_sbd;
+	struct gfs2_sbd *sdp = (*qda)->qd_gl->gl_name.ln_sbd;
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
 	struct gfs2_alloc_parms ap = { .aflags = 0, };
 	unsigned int data_blocks, ind_blocks;
@@ -922,7 +922,7 @@ out:
 		gfs2_glock_dq_uninit(&ghs[qx]);
 	mutex_unlock(&ip->i_inode.i_mutex);
 	kfree(ghs);
-	gfs2_log_flush(ip->i_gl->gl_sbd, ip->i_gl, NORMAL_FLUSH);
+	gfs2_log_flush(ip->i_gl->gl_name.ln_sbd, ip->i_gl, NORMAL_FLUSH);
 	return error;
 }
 
@@ -954,7 +954,7 @@ static int update_qd(struct gfs2_sbd *sdp, struct gfs2_quota_data *qd)
 static int do_glock(struct gfs2_quota_data *qd, int force_refresh,
 		    struct gfs2_holder *q_gh)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
 	struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
 	struct gfs2_holder i_gh;
 	int error;
@@ -1037,7 +1037,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 
 static int need_sync(struct gfs2_quota_data *qd)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
 	struct gfs2_tune *gt = &sdp->sd_tune;
 	s64 value;
 	unsigned int num, den;
@@ -1125,7 +1125,7 @@ out:
 
 static int print_message(struct gfs2_quota_data *qd, char *type)
 {
-	struct gfs2_sbd *sdp = qd->qd_gl->gl_sbd;
+	struct gfs2_sbd *sdp = qd->qd_gl->gl_name.ln_sbd;
 
 	fs_info(sdp, "quota %s for %s %u\n",
 		type,
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index c6c6232..c92ae7fd 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1860,7 +1860,7 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip
 static bool gfs2_rgrp_congested(const struct gfs2_rgrpd *rgd, int loops)
 {
 	const struct gfs2_glock *gl = rgd->rd_gl;
-	const struct gfs2_sbd *sdp = gl->gl_sbd;
+	const struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_lkstats *st;
 	s64 r_dcount, l_dcount;
 	s64 l_srttb, a_srttb = 0;
diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h
index 20c007d..fff47d0 100644
--- a/fs/gfs2/trace_gfs2.h
+++ b/fs/gfs2/trace_gfs2.h
@@ -104,7 +104,7 @@ TRACE_EVENT(gfs2_glock_state_change,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= gl->gl_sbd->sd_vfs->s_dev;
+		__entry->dev		= gl->gl_name.ln_sbd->sd_vfs->s_dev;
 		__entry->glnum		= gl->gl_name.ln_number;
 		__entry->gltype		= gl->gl_name.ln_type;
 		__entry->cur_state	= glock_trace_state(gl->gl_state);
@@ -140,7 +140,7 @@ TRACE_EVENT(gfs2_glock_put,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= gl->gl_sbd->sd_vfs->s_dev;
+		__entry->dev		= gl->gl_name.ln_sbd->sd_vfs->s_dev;
 		__entry->gltype		= gl->gl_name.ln_type;
 		__entry->glnum		= gl->gl_name.ln_number;
 		__entry->cur_state	= glock_trace_state(gl->gl_state);
@@ -174,7 +174,7 @@ TRACE_EVENT(gfs2_demote_rq,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= gl->gl_sbd->sd_vfs->s_dev;
+		__entry->dev		= gl->gl_name.ln_sbd->sd_vfs->s_dev;
 		__entry->gltype		= gl->gl_name.ln_type;
 		__entry->glnum		= gl->gl_name.ln_number;
 		__entry->cur_state	= glock_trace_state(gl->gl_state);
@@ -209,7 +209,7 @@ TRACE_EVENT(gfs2_promote,
 	),
 
 	TP_fast_assign(
-		__entry->dev	= gh->gh_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->dev	= gh->gh_gl->gl_name.ln_sbd->sd_vfs->s_dev;
 		__entry->glnum	= gh->gh_gl->gl_name.ln_number;
 		__entry->gltype	= gh->gh_gl->gl_name.ln_type;
 		__entry->first	= first;
@@ -239,7 +239,7 @@ TRACE_EVENT(gfs2_glock_queue,
 	),
 
 	TP_fast_assign(
-		__entry->dev	= gh->gh_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->dev	= gh->gh_gl->gl_name.ln_sbd->sd_vfs->s_dev;
 		__entry->glnum	= gh->gh_gl->gl_name.ln_number;
 		__entry->gltype	= gh->gh_gl->gl_name.ln_type;
 		__entry->queue	= queue;
@@ -278,7 +278,7 @@ TRACE_EVENT(gfs2_glock_lock_time,
 	),
 
 	TP_fast_assign(
-		__entry->dev            = gl->gl_sbd->sd_vfs->s_dev;
+		__entry->dev            = gl->gl_name.ln_sbd->sd_vfs->s_dev;
 		__entry->glnum          = gl->gl_name.ln_number;
 		__entry->gltype         = gl->gl_name.ln_type;
 		__entry->status		= gl->gl_lksb.sb_status;
@@ -333,7 +333,7 @@ TRACE_EVENT(gfs2_pin,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= bd->bd_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->dev		= bd->bd_gl->gl_name.ln_sbd->sd_vfs->s_dev;
 		__entry->pin		= pin;
 		__entry->len		= bd->bd_bh->b_size;
 		__entry->block		= bd->bd_bh->b_blocknr;
@@ -449,7 +449,7 @@ TRACE_EVENT(gfs2_bmap,
 	),
 
 	TP_fast_assign(
-		__entry->dev            = ip->i_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->dev            = ip->i_gl->gl_name.ln_sbd->sd_vfs->s_dev;
 		__entry->lblock		= lblock;
 		__entry->pblock		= buffer_mapped(bh) ?  bh->b_blocknr : 0;
 		__entry->inum		= ip->i_no_addr;
@@ -489,7 +489,7 @@ TRACE_EVENT(gfs2_block_alloc,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= rgd->rd_gl->gl_sbd->sd_vfs->s_dev;
+		__entry->dev		= rgd->rd_gl->gl_name.ln_sbd->sd_vfs->s_dev;
 		__entry->start		= block;
 		__entry->inum		= ip->i_no_addr;
 		__entry->len		= len;
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 88bff24..b95d0d6 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -158,7 +158,7 @@ static struct gfs2_bufdata *gfs2_alloc_bufdata(struct gfs2_glock *gl,
 void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
 {
 	struct gfs2_trans *tr = current->journal_info;
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct address_space *mapping = bh->b_page->mapping;
 	struct gfs2_inode *ip = GFS2_I(mapping->host);
 	struct gfs2_bufdata *bd;
@@ -224,7 +224,7 @@ static void meta_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
 void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
 {
 
-	struct gfs2_sbd *sdp = gl->gl_sbd;
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_bufdata *bd;
 
 	lock_buffer(bh);
-- 
2.4.3

[Cluster-devel] [PATCH 3/6] GFS2: Use resizable hash table for glocks

[Bob Peterson]

This patch changes the glock hash table from a normal hash table to
a resizable hash table, which scales better. This also simplifies
a lot of code.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Acked-by: Steven Whitehouse <swhiteho@redhat.com>
---
 fs/gfs2/glock.c  | 264 +++++++++++++++++++++----------------------------------
 fs/gfs2/incore.h |   4 +-
 2 files changed, 102 insertions(+), 166 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 13cba6e..edb15ee 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -34,6 +34,7 @@
 #include <linux/percpu.h>
 #include <linux/list_sort.h>
 #include <linux/lockref.h>
+#include <linux/rhashtable.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -50,9 +51,8 @@
 #include "trace_gfs2.h"
 
 struct gfs2_glock_iter {
-	int hash;			/* hash bucket index           */
-	unsigned nhash;			/* Index within current bucket */
 	struct gfs2_sbd *sdp;		/* incore superblock           */
+	struct rhashtable_iter hti;	/* rhashtable iterator         */
 	struct gfs2_glock *gl;		/* current glock struct        */
 	loff_t last_pos;		/* last position               */
 };
@@ -70,44 +70,19 @@ static DEFINE_SPINLOCK(lru_lock);
 
 #define GFS2_GL_HASH_SHIFT      15
 #define GFS2_GL_HASH_SIZE       (1 << GFS2_GL_HASH_SHIFT)
-#define GFS2_GL_HASH_MASK       (GFS2_GL_HASH_SIZE - 1)
 
-static struct hlist_bl_head gl_hash_table[GFS2_GL_HASH_SIZE];
-static struct dentry *gfs2_root;
-
-/**
- * gl_hash() - Turn glock number into hash bucket number
- * @lock: The glock number
- *
- * Returns: The number of the corresponding hash bucket
- */
-
-static unsigned int gl_hash(const struct gfs2_sbd *sdp,
-			    const struct lm_lockname *name)
-{
-	unsigned int h;
-
-	h = jhash(&name->ln_number, sizeof(u64), 0);
-	h = jhash(&name->ln_type, sizeof(unsigned int), h);
-	h = jhash(&sdp, sizeof(struct gfs2_sbd *), h);
-	h &= GFS2_GL_HASH_MASK;
-
-	return h;
-}
-
-static inline void spin_lock_bucket(unsigned int hash)
-{
-	hlist_bl_lock(&gl_hash_table[hash]);
-}
+static struct rhashtable_params ht_parms = {
+	.nelem_hint = GFS2_GL_HASH_SIZE * 3 / 4,
+	.key_len = sizeof(struct lm_lockname),
+	.key_offset = offsetof(struct gfs2_glock, gl_name),
+	.head_offset = offsetof(struct gfs2_glock, gl_node),
+};
 
-static inline void spin_unlock_bucket(unsigned int hash)
-{
-	hlist_bl_unlock(&gl_hash_table[hash]);
-}
+static struct rhashtable gl_hash_table;
 
-static void gfs2_glock_dealloc(struct rcu_head *rcu)
+void gfs2_glock_free(struct gfs2_glock *gl)
 {
-	struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu);
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
 	if (gl->gl_ops->go_flags & GLOF_ASPACE) {
 		kmem_cache_free(gfs2_glock_aspace_cachep, gl);
@@ -115,13 +90,6 @@ static void gfs2_glock_dealloc(struct rcu_head *rcu)
 		kfree(gl->gl_lksb.sb_lvbptr);
 		kmem_cache_free(gfs2_glock_cachep, gl);
 	}
-}
-
-void gfs2_glock_free(struct gfs2_glock *gl)
-{
-	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-
-	call_rcu(&gl->gl_rcu, gfs2_glock_dealloc);
 	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
 		wake_up(&sdp->sd_glock_wait);
 }
@@ -202,9 +170,7 @@ void gfs2_glock_put(struct gfs2_glock *gl)
 
 	gfs2_glock_remove_from_lru(gl);
 	spin_unlock(&gl->gl_lockref.lock);
-	spin_lock_bucket(gl->gl_hash);
-	hlist_bl_del_rcu(&gl->gl_list);
-	spin_unlock_bucket(gl->gl_hash);
+	rhashtable_remove_fast(&gl_hash_table, &gl->gl_node, ht_parms);
 	GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders));
 	GLOCK_BUG_ON(gl, mapping && mapping->nrpages);
 	trace_gfs2_glock_put(gl);
@@ -212,30 +178,6 @@ void gfs2_glock_put(struct gfs2_glock *gl)
 }
 
 /**
- * search_bucket() - Find struct gfs2_glock by lock number
- * @bucket: the bucket to search
- * @name: The lock name
- *
- * Returns: NULL, or the struct gfs2_glock with the requested number
- */
-
-static struct gfs2_glock *search_bucket(unsigned int hash,
-					const struct lm_lockname *name)
-{
-	struct gfs2_glock *gl;
-	struct hlist_bl_node *h;
-
-	hlist_bl_for_each_entry_rcu(gl, h, &gl_hash_table[hash], gl_list) {
-		if (!lm_name_equal(&gl->gl_name, name))
-			continue;
-		if (lockref_get_not_dead(&gl->gl_lockref))
-			return gl;
-	}
-
-	return NULL;
-}
-
-/**
  * may_grant - check if its ok to grant a new lock
  * @gl: The glock
  * @gh: The lock request which we wish to grant
@@ -704,14 +646,14 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	struct lm_lockname name = { .ln_number = number,
 				    .ln_type = glops->go_type,
 				    .ln_sbd = sdp };
-	struct gfs2_glock *gl, *tmp;
-	unsigned int hash = gl_hash(sdp, &name);
+	struct gfs2_glock *gl, *tmp = NULL;
 	struct address_space *mapping;
 	struct kmem_cache *cachep;
+	int ret, tries = 0;
 
-	rcu_read_lock();
-	gl = search_bucket(hash, &name);
-	rcu_read_unlock();
+	gl = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms);
+	if (gl && !lockref_get_not_dead(&gl->gl_lockref))
+		gl = NULL;
 
 	*glp = gl;
 	if (gl)
@@ -738,13 +680,13 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	}
 
 	atomic_inc(&sdp->sd_glock_disposal);
+	gl->gl_node.next = NULL;
 	gl->gl_flags = 0;
 	gl->gl_name = name;
 	gl->gl_lockref.count = 1;
 	gl->gl_state = LM_ST_UNLOCKED;
 	gl->gl_target = LM_ST_UNLOCKED;
 	gl->gl_demote_state = LM_ST_EXCLUSIVE;
-	gl->gl_hash = hash;
 	gl->gl_ops = glops;
 	gl->gl_dstamp = ktime_set(0, 0);
 	preempt_disable();
@@ -769,22 +711,34 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		mapping->writeback_index = 0;
 	}
 
-	spin_lock_bucket(hash);
-	tmp = search_bucket(hash, &name);
-	if (tmp) {
-		spin_unlock_bucket(hash);
-		kfree(gl->gl_lksb.sb_lvbptr);
-		kmem_cache_free(cachep, gl);
-		atomic_dec(&sdp->sd_glock_disposal);
-		gl = tmp;
-	} else {
-		hlist_bl_add_head_rcu(&gl->gl_list, &gl_hash_table[hash]);
-		spin_unlock_bucket(hash);
+again:
+	ret = rhashtable_lookup_insert_fast(&gl_hash_table, &gl->gl_node,
+					    ht_parms);
+	if (ret == 0) {
+		*glp = gl;
+		return 0;
 	}
 
-	*glp = gl;
+	if (ret == -EEXIST) {
+		ret = 0;
+		tmp = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms);
+		if (tmp == NULL || !lockref_get_not_dead(&tmp->gl_lockref)) {
+			if (++tries < 100) {
+				cond_resched();
+				goto again;
+			}
+			tmp = NULL;
+			ret = -ENOMEM;
+		}
+	} else {
+		WARN_ON_ONCE(ret);
+	}
+	kfree(gl->gl_lksb.sb_lvbptr);
+	kmem_cache_free(cachep, gl);
+	atomic_dec(&sdp->sd_glock_disposal);
+	*glp = tmp;
 
-	return 0;
+	return ret;
 }
 
 /**
@@ -1460,31 +1414,26 @@ static struct shrinker glock_shrinker = {
  *
  */
 
-static void examine_bucket(glock_examiner examiner, const struct gfs2_sbd *sdp,
-			  unsigned int hash)
+static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
 {
 	struct gfs2_glock *gl;
-	struct hlist_bl_head *head = &gl_hash_table[hash];
-	struct hlist_bl_node *pos;
+	struct rhash_head *pos, *next;
+	const struct bucket_table *tbl;
+	int i;
 
 	rcu_read_lock();
-	hlist_bl_for_each_entry_rcu(gl, pos, head, gl_list) {
-		if ((gl->gl_name.ln_sbd == sdp) && lockref_get_not_dead(&gl->gl_lockref))
-			examiner(gl);
+	tbl = rht_dereference_rcu(gl_hash_table.tbl, &gl_hash_table);
+	for (i = 0; i < tbl->size; i++) {
+		rht_for_each_entry_safe(gl, pos, next, tbl, i, gl_node) {
+			if ((gl->gl_name.ln_sbd == sdp) &&
+			    lockref_get_not_dead(&gl->gl_lockref))
+				examiner(gl);
+		}
 	}
 	rcu_read_unlock();
 	cond_resched();
 }
 
-static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
-{
-	unsigned x;
-
-	for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
-		examine_bucket(examiner, sdp, x);
-}
-
-
 /**
  * thaw_glock - thaw out a glock which has an unprocessed reply waiting
  * @gl: The glock to thaw
@@ -1802,20 +1751,24 @@ static int gfs2_sbstats_seq_show(struct seq_file *seq, void *iter_ptr)
 
 int __init gfs2_glock_init(void)
 {
-	unsigned i;
-	for(i = 0; i < GFS2_GL_HASH_SIZE; i++) {
-		INIT_HLIST_BL_HEAD(&gl_hash_table[i]);
-	}
+	int ret;
+
+	ret = rhashtable_init(&gl_hash_table, &ht_parms);
+	if (ret < 0)
+		return ret;
 
 	glock_workqueue = alloc_workqueue("glock_workqueue", WQ_MEM_RECLAIM |
 					  WQ_HIGHPRI | WQ_FREEZABLE, 0);
-	if (!glock_workqueue)
+	if (!glock_workqueue) {
+		rhashtable_destroy(&gl_hash_table);
 		return -ENOMEM;
+	}
 	gfs2_delete_workqueue = alloc_workqueue("delete_workqueue",
 						WQ_MEM_RECLAIM | WQ_FREEZABLE,
 						0);
 	if (!gfs2_delete_workqueue) {
 		destroy_workqueue(glock_workqueue);
+		rhashtable_destroy(&gl_hash_table);
 		return -ENOMEM;
 	}
 
@@ -1827,72 +1780,41 @@ int __init gfs2_glock_init(void)
 void gfs2_glock_exit(void)
 {
 	unregister_shrinker(&glock_shrinker);
+	rhashtable_destroy(&gl_hash_table);
 	destroy_workqueue(glock_workqueue);
 	destroy_workqueue(gfs2_delete_workqueue);
 }
 
-static inline struct gfs2_glock *glock_hash_chain(unsigned hash)
+static void gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
 {
-	return hlist_bl_entry(hlist_bl_first_rcu(&gl_hash_table[hash]),
-			      struct gfs2_glock, gl_list);
-}
-
-static inline struct gfs2_glock *glock_hash_next(struct gfs2_glock *gl)
-{
-	return hlist_bl_entry(rcu_dereference(gl->gl_list.next),
-			      struct gfs2_glock, gl_list);
-}
-
-static int gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
-{
-	struct gfs2_glock *gl;
-
 	do {
-		gl = gi->gl;
-		if (gl) {
-			gi->gl = glock_hash_next(gl);
-			gi->nhash++;
-		} else {
-			if (gi->hash >= GFS2_GL_HASH_SIZE) {
-				rcu_read_unlock();
-				return 1;
-			}
-			gi->gl = glock_hash_chain(gi->hash);
-			gi->nhash = 0;
-		}
-		while (gi->gl == NULL) {
-			gi->hash++;
-			if (gi->hash >= GFS2_GL_HASH_SIZE) {
-				rcu_read_unlock();
-				return 1;
-			}
-			gi->gl = glock_hash_chain(gi->hash);
-			gi->nhash = 0;
+		gi->gl = rhashtable_walk_next(&gi->hti);
+		if (IS_ERR(gi->gl)) {
+			if (PTR_ERR(gi->gl) == -EAGAIN)
+				continue;
+			gi->gl = NULL;
 		}
 	/* Skip entries for other sb and dead entries */
-	} while (gi->sdp != gi->gl->gl_name.ln_sbd ||
-		 __lockref_is_dead(&gi->gl->gl_lockref));
-
-	return 0;
+	} while ((gi->gl) && ((gi->sdp != gi->gl->gl_name.ln_sbd) ||
+			      __lockref_is_dead(&gi->gl->gl_lockref)));
 }
 
 static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
 {
 	struct gfs2_glock_iter *gi = seq->private;
 	loff_t n = *pos;
+	int ret;
 
 	if (gi->last_pos <= *pos)
-		n = gi->nhash + (*pos - gi->last_pos);
-	else
-		gi->hash = 0;
+		n = (*pos - gi->last_pos);
 
-	gi->nhash = 0;
-	rcu_read_lock();
+	ret = rhashtable_walk_start(&gi->hti);
+	if (ret)
+		return NULL;
 
 	do {
-		if (gfs2_glock_iter_next(gi))
-			return NULL;
-	} while (n--);
+		gfs2_glock_iter_next(gi);
+	} while (gi->gl && n--);
 
 	gi->last_pos = *pos;
 	return gi->gl;
@@ -1905,9 +1827,7 @@ static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr,
 
 	(*pos)++;
 	gi->last_pos = *pos;
-	if (gfs2_glock_iter_next(gi))
-		return NULL;
-
+	gfs2_glock_iter_next(gi);
 	return gi->gl;
 }
 
@@ -1915,9 +1835,8 @@ static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr)
 {
 	struct gfs2_glock_iter *gi = seq->private;
 
-	if (gi->gl)
-		rcu_read_unlock();
 	gi->gl = NULL;
+	rhashtable_walk_stop(&gi->hti);
 }
 
 static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
@@ -1978,14 +1897,28 @@ static int gfs2_glocks_open(struct inode *inode, struct file *file)
 	if (ret == 0) {
 		struct seq_file *seq = file->private_data;
 		struct gfs2_glock_iter *gi = seq->private;
+
 		gi->sdp = inode->i_private;
+		gi->last_pos = 0;
 		seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN);
 		if (seq->buf)
 			seq->size = GFS2_SEQ_GOODSIZE;
+		gi->gl = NULL;
+		ret = rhashtable_walk_init(&gl_hash_table, &gi->hti);
 	}
 	return ret;
 }
 
+static int gfs2_glocks_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct gfs2_glock_iter *gi = seq->private;
+
+	gi->gl = NULL;
+	rhashtable_walk_exit(&gi->hti);
+	return seq_release_private(inode, file);
+}
+
 static int gfs2_glstats_open(struct inode *inode, struct file *file)
 {
 	int ret = seq_open_private(file, &gfs2_glstats_seq_ops,
@@ -1994,9 +1927,12 @@ static int gfs2_glstats_open(struct inode *inode, struct file *file)
 		struct seq_file *seq = file->private_data;
 		struct gfs2_glock_iter *gi = seq->private;
 		gi->sdp = inode->i_private;
+		gi->last_pos = 0;
 		seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN);
 		if (seq->buf)
 			seq->size = GFS2_SEQ_GOODSIZE;
+		gi->gl = NULL;
+		ret = rhashtable_walk_init(&gl_hash_table, &gi->hti);
 	}
 	return ret;
 }
@@ -2016,7 +1952,7 @@ static const struct file_operations gfs2_glocks_fops = {
 	.open    = gfs2_glocks_open,
 	.read    = seq_read,
 	.llseek  = seq_lseek,
-	.release = seq_release_private,
+	.release = gfs2_glocks_release,
 };
 
 static const struct file_operations gfs2_glstats_fops = {
@@ -2024,7 +1960,7 @@ static const struct file_operations gfs2_glstats_fops = {
 	.open    = gfs2_glstats_open,
 	.read    = seq_read,
 	.llseek  = seq_lseek,
-	.release = seq_release_private,
+	.release = gfs2_glocks_release,
 };
 
 static const struct file_operations gfs2_sbstats_fops = {
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 35a55f3..e300f74 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -22,6 +22,7 @@
 #include <linux/ktime.h>
 #include <linux/percpu.h>
 #include <linux/lockref.h>
+#include <linux/rhashtable.h>
 
 #define DIO_WAIT	0x00000010
 #define DIO_METADATA	0x00000020
@@ -342,7 +343,6 @@ struct gfs2_glock {
 		     gl_req:2,		/* State in last dlm request */
 		     gl_reply:8;	/* Last reply from the dlm */
 
-	unsigned int gl_hash;
 	unsigned long gl_demote_time; /* time of first demote request */
 	long gl_hold_time;
 	struct list_head gl_holders;
@@ -368,7 +368,7 @@ struct gfs2_glock {
 			loff_t end;
 		} gl_vm;
 	};
-	struct rcu_head gl_rcu;
+	struct rhash_head gl_node;
 };
 
 #define GFS2_MIN_LVB_SIZE 32	/* Min size of LVB that gfs2 supports */
-- 
2.4.3

[Cluster-devel] [PATCH 4/6] gfs2: Make statistics unsigned, suitable for use with do_div()

[Bob Peterson]

From: Ben Hutchings <ben@decadent.org.uk>

None of these statistics can meaningfully be negative, and the
numerator for do_div() must have the type u64.  The generic
implementation of do_div() used on some 32-bit architectures asserts
that, resulting in a compiler error in gfs2_rgrp_congested().

Fixes: 0166b197c2ed ("GFS2: Average in only non-zero round-trip times ...")

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/glock.c      | 22 +++++++++++-----------
 fs/gfs2/incore.h     |  2 +-
 fs/gfs2/rgrp.c       |  8 ++++----
 fs/gfs2/trace_gfs2.h | 16 ++++++++--------
 4 files changed, 24 insertions(+), 24 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index edb15ee..37d4db1 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1680,17 +1680,17 @@ static int gfs2_glstats_seq_show(struct seq_file *seq, void *iter_ptr)
 {
 	struct gfs2_glock *gl = iter_ptr;
 
-	seq_printf(seq, "G: n:%u/%llx rtt:%lld/%lld rttb:%lld/%lld irt:%lld/%lld dcnt: %lld qcnt: %lld\n",
+	seq_printf(seq, "G: n:%u/%llx rtt:%llu/%llu rttb:%llu/%llu irt:%llu/%llu dcnt: %llu qcnt: %llu\n",
 		   gl->gl_name.ln_type,
 		   (unsigned long long)gl->gl_name.ln_number,
-		   (long long)gl->gl_stats.stats[GFS2_LKS_SRTT],
-		   (long long)gl->gl_stats.stats[GFS2_LKS_SRTTVAR],
-		   (long long)gl->gl_stats.stats[GFS2_LKS_SRTTB],
-		   (long long)gl->gl_stats.stats[GFS2_LKS_SRTTVARB],
-		   (long long)gl->gl_stats.stats[GFS2_LKS_SIRT],
-		   (long long)gl->gl_stats.stats[GFS2_LKS_SIRTVAR],
-		   (long long)gl->gl_stats.stats[GFS2_LKS_DCOUNT],
-		   (long long)gl->gl_stats.stats[GFS2_LKS_QCOUNT]);
+		   (unsigned long long)gl->gl_stats.stats[GFS2_LKS_SRTT],
+		   (unsigned long long)gl->gl_stats.stats[GFS2_LKS_SRTTVAR],
+		   (unsigned long long)gl->gl_stats.stats[GFS2_LKS_SRTTB],
+		   (unsigned long long)gl->gl_stats.stats[GFS2_LKS_SRTTVARB],
+		   (unsigned long long)gl->gl_stats.stats[GFS2_LKS_SIRT],
+		   (unsigned long long)gl->gl_stats.stats[GFS2_LKS_SIRTVAR],
+		   (unsigned long long)gl->gl_stats.stats[GFS2_LKS_DCOUNT],
+		   (unsigned long long)gl->gl_stats.stats[GFS2_LKS_QCOUNT]);
 	return 0;
 }
 
@@ -1727,7 +1727,7 @@ static int gfs2_sbstats_seq_show(struct seq_file *seq, void *iter_ptr)
 	loff_t pos = *(loff_t *)iter_ptr;
 	unsigned index = pos >> 3;
 	unsigned subindex = pos & 0x07;
-	s64 value;
+	u64 value;
 	int i;
 
 	if (index == 0 && subindex != 0)
@@ -1743,7 +1743,7 @@ static int gfs2_sbstats_seq_show(struct seq_file *seq, void *iter_ptr)
 		} else {
 			value = lkstats->lkstats[index - 1].stats[subindex];
 		}
-		seq_printf(seq, " %15lld", (long long)value);
+		seq_printf(seq, " %15llu", (long long)value);
 	}
 	seq_putc(seq, '\n');
 	return 0;
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index e300f74..121ed08 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -244,7 +244,7 @@ enum {
 };
 
 struct gfs2_lkstats {
-	s64 stats[GFS2_NR_LKSTATS];
+	u64 stats[GFS2_NR_LKSTATS];
 };
 
 enum {
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index c92ae7fd..475985d 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1862,11 +1862,11 @@ static bool gfs2_rgrp_congested(const struct gfs2_rgrpd *rgd, int loops)
 	const struct gfs2_glock *gl = rgd->rd_gl;
 	const struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_lkstats *st;
-	s64 r_dcount, l_dcount;
-	s64 l_srttb, a_srttb = 0;
+	u64 r_dcount, l_dcount;
+	u64 l_srttb, a_srttb = 0;
 	s64 srttb_diff;
-	s64 sqr_diff;
-	s64 var;
+	u64 sqr_diff;
+	u64 var;
 	int cpu, nonzero = 0;
 
 	preempt_disable();
diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h
index fff47d0..49ac55d 100644
--- a/fs/gfs2/trace_gfs2.h
+++ b/fs/gfs2/trace_gfs2.h
@@ -267,14 +267,14 @@ TRACE_EVENT(gfs2_glock_lock_time,
 		__field(	int,	status		)
 		__field(	char,	flags		)
 		__field(	s64,	tdiff		)
-		__field(	s64,	srtt		)
-		__field(	s64,	srttvar		)
-		__field(	s64,	srttb		)
-		__field(	s64,	srttvarb	)
-		__field(	s64,	sirt		)
-		__field(	s64,	sirtvar		)
-		__field(	s64,	dcount		)
-		__field(	s64,	qcount		)
+		__field(	u64,	srtt		)
+		__field(	u64,	srttvar		)
+		__field(	u64,	srttb		)
+		__field(	u64,	srttvarb	)
+		__field(	u64,	sirt		)
+		__field(	u64,	sirtvar		)
+		__field(	u64,	dcount		)
+		__field(	u64,	qcount		)
 	),
 
 	TP_fast_assign(
-- 
2.4.3

[Cluster-devel] [PATCH 5/6] gfs2: Fix a typo in a comment

[Bob Peterson]

From: Andreas Gruenbacher <agruenba@redhat.com>

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/lock_dlm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index c962cfc..284c154 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -31,7 +31,7 @@ extern struct workqueue_struct *gfs2_control_wq;
  *
  * @delta is the difference between the current rtt sample and the
  * running average srtt. We add 1/8 of that to the srtt in order to
- * update the current srtt estimate. The varience estimate is a bit
+ * update the current srtt estimate. The variance estimate is a bit
  * more complicated. We subtract the abs value of the @delta from
  * the current variance estimate and add 1/4 of that to the running
  * total.
-- 
2.4.3

[Cluster-devel] [PATCH 6/6] gfs2: A minor "sbstats" cleanup

[Bob Peterson]

From: Andreas Gruenbacher <agruenba@redhat.com>

It seems cleaner to avoid the temporary value here.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/glock.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 37d4db1..9bd1244 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -1727,7 +1727,6 @@ static int gfs2_sbstats_seq_show(struct seq_file *seq, void *iter_ptr)
 	loff_t pos = *(loff_t *)iter_ptr;
 	unsigned index = pos >> 3;
 	unsigned subindex = pos & 0x07;
-	u64 value;
 	int i;
 
 	if (index == 0 && subindex != 0)
@@ -1738,12 +1737,12 @@ static int gfs2_sbstats_seq_show(struct seq_file *seq, void *iter_ptr)
 
 	for_each_possible_cpu(i) {
                 const struct gfs2_pcpu_lkstats *lkstats = per_cpu_ptr(sdp->sd_lkstats, i);
-		if (index == 0) {
-			value = i;
-		} else {
-			value = lkstats->lkstats[index - 1].stats[subindex];
-		}
-		seq_printf(seq, " %15llu", (long long)value);
+
+		if (index == 0)
+			seq_printf(seq, " %15u", i);
+		else
+			seq_printf(seq, " %15llu", (unsigned long long)lkstats->
+				   lkstats[index - 1].stats[subindex]);
 	}
 	seq_putc(seq, '\n');
 	return 0;
-- 
2.4.3

[Cluster-devel] [PATCH 2/6] GFS2: Move glock superblock pointer to field gl_name

[Andreas Gruenbacher]

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>

[Cluster-devel] [PATCH 3/6] GFS2: Use resizable hash table for glocks

[Andreas Gruenbacher]

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>

[Cluster-devel] [PATCH 4/6] gfs2: Make statistics unsigned, suitable for use with do_div()

[Andreas Gruenbacher]

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>

[Cluster-devel] [PATCH 0/6] GFS2: Pre-pull patch posting (merge window)

[Andreas Gruenbacher]

Bob,

2015-09-02 22:02 GMT+02:00 Bob Peterson <rpeterso@redhat.com>:
> Here is a list of patches we've accumulated for GFS2 for the current upstream
> merge window. There are only six patches this time: a couple of code
> cleanups from Andreas, a change from signed to unsigned for glock statistics,
> and two patches that improve GFS2's glock scalability by changing from a
> regular hash table to a resizeable hash table.

they are all looking good, thanks.

Andreas