GFS2: glock statistics gathering

The stats are divided into two sets: those relating to the
super block and those relating to an individual glock. The
super block stats are done on a per cpu basis in order to
try and reduce the overhead of gathering them. They are also
further divided by glock type.

In the case of both the super block and glock statistics,
the same information is gathered in each case. The super
block statistics are used to provide default values for
most of the glock statistics, so that newly created glocks
should have, as far as possible, a sensible starting point.

The statistics are divided into three pairs of mean and
variance, plus two counters. The mean/variance pairs are
smoothed exponential estimates and the algorithm used is
one which will be very familiar to those used to calculation
of round trip times in network code.

The three pairs of mean/variance measure the following
things:

 1. DLM lock time (non-blocking requests)
 2. DLM lock time (blocking requests)
 3. Inter-request time (again to the DLM)

A non-blocking request is one which will complete right
away, whatever the state of the DLM lock in question. That
currently means any requests when (a) the current state of
the lock is exclusive (b) the requested state is either null
or unlocked or (c) the "try lock" flag is set. A blocking
request covers all the other lock requests.

There are two counters. The first is there primarily to show
how many lock requests have been made, and thus how much data
has gone into the mean/variance calculations. The other counter
is counting queueing of holders at the top layer of the glock
code. Hopefully that number will be a lot larger than the number
of dlm lock requests issued.

So why gather these statistics? There are several reasons
we'd like to get a better idea of these timings:

1. To be able to better set the glock "min hold time"
2. To spot performance issues more easily
3. To improve the algorithm for selecting resource groups for
allocation (to base it on lock wait time, rather than blindly
using a "try lock")
Due to the smoothing action of the updates, a step change in
some input quantity being sampled will only fully be taken
into account after 8 samples (or 4 for the variance) and this
needs to be carefully considered when interpreting the
results.

Knowing both the time it takes a lock request to complete and
the average time between lock requests for a glock means we
can compute the total percentage of the time for which the
node is able to use a glock vs. time that the rest of the
cluster has its share. That will be very useful when setting
the lock min hold time.

The other point to remember is that all times are in
nanoseconds. Great care has been taken to ensure that we
measure exactly the quantities that we want, as accurately
as possible. There are always inaccuracies in any
measuring system, but I hope this is as accurate as we
can reasonably make it.

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

1 files changed, 202 insertions, 8 deletions

diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 351a3e797789..dab2526071cc 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -29,6 +29,7 @@
 #include <linux/rcupdate.h>
 #include <linux/rculist_bl.h>
 #include <linux/bit_spinlock.h>
+#include <linux/percpu.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -543,6 +544,11 @@ __acquires(&gl->gl_spin)
 		do_error(gl, 0); /* Fail queued try locks */
 	}
 	gl->gl_req = target;
+	set_bit(GLF_BLOCKING, &gl->gl_flags);
+	if ((gl->gl_req == LM_ST_UNLOCKED) ||
+	    (gl->gl_state == LM_ST_EXCLUSIVE) ||
+	    (lck_flags & (LM_FLAG_TRY|LM_FLAG_TRY_1CB)))
+		clear_bit(GLF_BLOCKING, &gl->gl_flags);
 	spin_unlock(&gl->gl_spin);
 	if (glops->go_xmote_th)
 		glops->go_xmote_th(gl);
@@ -744,6 +750,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 		return -ENOMEM;
 
 	atomic_inc(&sdp->sd_glock_disposal);
+	gl->gl_sbd = sdp;
 	gl->gl_flags = 0;
 	gl->gl_name = name;
 	atomic_set(&gl->gl_ref, 1);
@@ -752,12 +759,17 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	gl->gl_demote_state = LM_ST_EXCLUSIVE;
 	gl->gl_hash = hash;
 	gl->gl_ops = glops;
-	snprintf(gl->gl_strname, GDLM_STRNAME_BYTES, "%8x%16llx", name.ln_type, (unsigned long long)number);
+	gl->gl_dstamp = ktime_set(0, 0);
+	preempt_disable();
+	/* We use the global stats to estimate the initial per-glock stats */
+	gl->gl_stats = this_cpu_ptr(sdp->sd_lkstats)->lkstats[glops->go_type];
+	preempt_enable();
+	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));
 	gl->gl_lksb.sb_lvbptr = gl->gl_lvb;
 	gl->gl_tchange = jiffies;
 	gl->gl_object = NULL;
-	gl->gl_sbd = sdp;
 	gl->gl_hold_time = GL_GLOCK_DFT_HOLD;
 	INIT_DELAYED_WORK(&gl->gl_work, glock_work_func);
 	INIT_WORK(&gl->gl_delete, delete_work_func);
@@ -999,6 +1011,8 @@ fail:
 	}
 	set_bit(GLF_QUEUED, &gl->gl_flags);
 	trace_gfs2_glock_queue(gh, 1);
+	gfs2_glstats_inc(gl, GFS2_LKS_QCOUNT);
+	gfs2_sbstats_inc(gl, GFS2_LKS_QCOUNT);
 	if (likely(insert_pt == NULL)) {
 		list_add_tail(&gh->gh_list, &gl->gl_holders);
 		if (unlikely(gh->gh_flags & LM_FLAG_PRIORITY))
@@ -1658,6 +1672,8 @@ static const char *gflags2str(char *buf, const struct gfs2_glock *gl)
 		*p++ = 'L';
 	if (gl->gl_object)
 		*p++ = 'o';
+	if (test_bit(GLF_BLOCKING, gflags))
+		*p++ = 'b';
 	*p = 0;
 	return buf;
 }
@@ -1714,8 +1730,78 @@ out:
 	return error;
 }
 
+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",
+		   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]);
+	return 0;
+}
+
+static const char *gfs2_gltype[] = {
+	"type",
+	"reserved",
+	"nondisk",
+	"inode",
+	"rgrp",
+	"meta",
+	"iopen",
+	"flock",
+	"plock",
+	"quota",
+	"journal",
+};
+
+static const char *gfs2_stype[] = {
+	[GFS2_LKS_SRTT]		= "srtt",
+	[GFS2_LKS_SRTTVAR]	= "srttvar",
+	[GFS2_LKS_SRTTB]	= "srttb",
+	[GFS2_LKS_SRTTVARB]	= "srttvarb",
+	[GFS2_LKS_SIRT]		= "sirt",
+	[GFS2_LKS_SIRTVAR]	= "sirtvar",
+	[GFS2_LKS_DCOUNT]	= "dlm",
+	[GFS2_LKS_QCOUNT]	= "queue",
+};
+
+#define GFS2_NR_SBSTATS (ARRAY_SIZE(gfs2_gltype) * ARRAY_SIZE(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;
+	s64 value;
+	int i;
+
+	if (index == 0 && subindex != 0)
+		return 0;
 
+	seq_printf(seq, "%-10s %8s:", gfs2_gltype[index],
+		   (index == 0) ? "cpu": gfs2_stype[subindex]);
 
+	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, " %15lld", (long long)value);
+	}
+	seq_putc(seq, '\n');
+	return 0;
+}
 
 int __init gfs2_glock_init(void)
 {
@@ -1828,6 +1914,35 @@ static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
 	return dump_glock(seq, 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;
+	if (*pos >= GFS2_NR_SBSTATS)
+		return NULL;
+	preempt_disable();
+	return SEQ_START_TOKEN;
+}
+
+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();
+		return NULL;
+	}
+	return SEQ_START_TOKEN;
+}
+
+static void gfs2_sbstats_seq_stop(struct seq_file *seq, void *iter_ptr)
+{
+	preempt_enable();
+}
+
 static const struct seq_operations gfs2_glock_seq_ops = {
 	.start = gfs2_glock_seq_start,
 	.next  = gfs2_glock_seq_next,
@@ -1835,7 +1950,21 @@ static const struct seq_operations gfs2_glock_seq_ops = {
 	.show  = gfs2_glock_seq_show,
 };
 
-static int gfs2_debugfs_open(struct inode *inode, struct file *file)
+static const struct seq_operations gfs2_glstats_seq_ops = {
+	.start = gfs2_glock_seq_start,
+	.next  = gfs2_glock_seq_next,
+	.stop  = gfs2_glock_seq_stop,
+	.show  = gfs2_glstats_seq_show,
+};
+
+static const struct seq_operations gfs2_sbstats_seq_ops = {
+	.start = gfs2_sbstats_seq_start,
+	.next  = gfs2_sbstats_seq_next,
+	.stop  = gfs2_sbstats_seq_stop,
+	.show  = gfs2_sbstats_seq_show,
+};
+
+static int gfs2_glocks_open(struct inode *inode, struct file *file)
 {
 	int ret = seq_open_private(file, &gfs2_glock_seq_ops,
 				   sizeof(struct gfs2_glock_iter));
@@ -1847,9 +1976,49 @@ static int gfs2_debugfs_open(struct inode *inode, struct file *file)
 	return ret;
 }
 
-static const struct file_operations gfs2_debug_fops = {
+static int gfs2_glstats_open(struct inode *inode, struct file *file)
+{
+	int ret = seq_open_private(file, &gfs2_glstats_seq_ops,
+				   sizeof(struct gfs2_glock_iter));
+	if (ret == 0) {
+		struct seq_file *seq = file->private_data;
+		struct gfs2_glock_iter *gi = seq->private;
+		gi->sdp = inode->i_private;
+	}
+	return ret;
+}
+
+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));
+	if (ret == 0) {
+		struct seq_file *seq = file->private_data;
+		struct gfs2_glock_iter *gi = seq->private;
+		gi->sdp = inode->i_private;
+	}
+	return ret;
+}
+
+static const struct file_operations gfs2_glocks_fops = {
+	.owner   = THIS_MODULE,
+	.open    = gfs2_glocks_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release_private,
+};
+
+static const struct file_operations gfs2_glstats_fops = {
 	.owner   = THIS_MODULE,
-	.open    = gfs2_debugfs_open,
+	.open    = gfs2_glstats_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release_private,
+};
+
+static const struct file_operations gfs2_sbstats_fops = {
+	.owner   = THIS_MODULE,
+	.open	 = gfs2_sbstats_open,
 	.read    = seq_read,
 	.llseek  = seq_lseek,
 	.release = seq_release_private,
@@ -1863,20 +2032,45 @@ int gfs2_create_debugfs_file(struct gfs2_sbd *sdp)
 	sdp->debugfs_dentry_glocks = debugfs_create_file("glocks",
 							 S_IFREG | S_IRUGO,
 							 sdp->debugfs_dir, sdp,
-							 &gfs2_debug_fops);
+							 &gfs2_glocks_fops);
 	if (!sdp->debugfs_dentry_glocks)
-		return -ENOMEM;
+		goto fail;
+
+	sdp->debugfs_dentry_glstats = debugfs_create_file("glstats",
+							S_IFREG | S_IRUGO,
+							sdp->debugfs_dir, sdp,
+							&gfs2_glstats_fops);
+	if (!sdp->debugfs_dentry_glstats)
+		goto fail;
+
+	sdp->debugfs_dentry_sbstats = debugfs_create_file("sbstats",
+							S_IFREG | S_IRUGO,
+							sdp->debugfs_dir, sdp,
+							&gfs2_sbstats_fops);
+	if (!sdp->debugfs_dentry_sbstats)
+		goto fail;
 
 	return 0;
+fail:
+	gfs2_delete_debugfs_file(sdp);
+	return -ENOMEM;
 }
 
 void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp)
 {
-	if (sdp && sdp->debugfs_dir) {
+	if (sdp->debugfs_dir) {
 		if (sdp->debugfs_dentry_glocks) {
 			debugfs_remove(sdp->debugfs_dentry_glocks);
 			sdp->debugfs_dentry_glocks = NULL;
 		}
+		if (sdp->debugfs_dentry_glstats) {
+			debugfs_remove(sdp->debugfs_dentry_glstats);
+			sdp->debugfs_dentry_glstats = NULL;
+		}
+		if (sdp->debugfs_dentry_sbstats) {
+			debugfs_remove(sdp->debugfs_dentry_sbstats);
+			sdp->debugfs_dentry_sbstats = NULL;
+		}
 		debugfs_remove(sdp->debugfs_dir);
 		sdp->debugfs_dir = NULL;
 	}