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, 118 insertions, 5 deletions

diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 8944d1e..f8411bd 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -18,14 +18,106 @@
 #include "glock.h"
 #include "util.h"
 #include "sys.h"
+#include "trace_gfs2.h"
 
 extern struct workqueue_struct *gfs2_control_wq;
 
+/**
+ * gfs2_update_stats - Update time based stats
+ * @mv: Pointer to mean/variance structure to update
+ * @sample: New data to include
+ *
+ * @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
+ * 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.
+ *
+ * Note that the index points at the array entry containing the smoothed
+ * mean value, and the variance is always in the following entry
+ *
+ * Reference: TCP/IP Illustrated, vol 2, p. 831,832
+ * All times are in units of integer nanoseconds. Unlike the TCP/IP case,
+ * they are not scaled fixed point.
+ */
+
+static inline void gfs2_update_stats(struct gfs2_lkstats *s, unsigned index,
+				     s64 sample)
+{
+	s64 delta = sample - s->stats[index];
+	s->stats[index] += (delta >> 3);
+	index++;
+	s->stats[index] += ((abs64(delta) - s->stats[index]) >> 2);
+}
+
+/**
+ * gfs2_update_reply_times - Update locking statistics
+ * @gl: The glock to update
+ *
+ * This assumes that gl->gl_dstamp has been set earlier.
+ *
+ * The rtt (lock round trip time) is an estimate of the time
+ * taken to perform a dlm lock request. We update it on each
+ * reply from the dlm.
+ *
+ * The blocking flag is set on the glock for all dlm requests
+ * which may potentially block due to lock requests from other nodes.
+ * DLM requests where the current lock state is exclusive, the
+ * requested state is null (or unlocked) or where the TRY or
+ * TRY_1CB flags are set are classified as non-blocking. All
+ * other DLM requests are counted as (potentially) blocking.
+ */
+static inline void gfs2_update_reply_times(struct gfs2_glock *gl)
+{
+	struct gfs2_pcpu_lkstats *lks;
+	const unsigned gltype = gl->gl_name.ln_type;
+	unsigned index = test_bit(GLF_BLOCKING, &gl->gl_flags) ?
+			 GFS2_LKS_SRTTB : GFS2_LKS_SRTT;
+	s64 rtt;
+
+	preempt_disable();
+	rtt = ktime_to_ns(ktime_sub(ktime_get_real(), gl->gl_dstamp));
+	lks = this_cpu_ptr(gl->gl_sbd->sd_lkstats);
+	gfs2_update_stats(&gl->gl_stats, index, rtt);		/* Local */
+	gfs2_update_stats(&lks->lkstats[gltype], index, rtt);	/* Global */
+	preempt_enable();
+
+	trace_gfs2_glock_lock_time(gl, rtt);
+}
+
+/**
+ * gfs2_update_request_times - Update locking statistics
+ * @gl: The glock to update
+ *
+ * The irt (lock inter-request times) measures the average time
+ * between requests to the dlm. It is updated immediately before
+ * each dlm call.
+ */
+
+static inline void gfs2_update_request_times(struct gfs2_glock *gl)
+{
+	struct gfs2_pcpu_lkstats *lks;
+	const unsigned gltype = gl->gl_name.ln_type;
+	ktime_t dstamp;
+	s64 irt;
+
+	preempt_disable();
+	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);
+	gfs2_update_stats(&gl->gl_stats, GFS2_LKS_SIRT, irt);		/* Local */
+	gfs2_update_stats(&lks->lkstats[gltype], GFS2_LKS_SIRT, irt);	/* Global */
+	preempt_enable();
+}
+ 
 static void gdlm_ast(void *arg)
 {
 	struct gfs2_glock *gl = arg;
 	unsigned ret = gl->gl_state;
 
+	gfs2_update_reply_times(gl);
 	BUG_ON(gl->gl_lksb.sb_flags & DLM_SBF_DEMOTED);
 
 	if (gl->gl_lksb.sb_flags & DLM_SBF_VALNOTVALID)
@@ -111,7 +203,7 @@ static int make_mode(const unsigned int lmstate)
 static u32 make_flags(const u32 lkid, const unsigned int gfs_flags,
 		      const int req)
 {
-	u32 lkf = 0;
+	u32 lkf = DLM_LKF_VALBLK;
 
 	if (gfs_flags & LM_FLAG_TRY)
 		lkf |= DLM_LKF_NOQUEUE;
@@ -138,26 +230,43 @@ static u32 make_flags(const u32 lkid, const unsigned int gfs_flags,
 	if (lkid != 0) 
 		lkf |= DLM_LKF_CONVERT;
 
-	lkf |= DLM_LKF_VALBLK;
-
 	return lkf;
 }
 
+static void gfs2_reverse_hex(char *c, u64 value)
+{
+	while (value) {
+		*c-- = hex_asc[value & 0x0f];
+		value >>= 4;
+	}
+}
+
 static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
 		     unsigned int flags)
 {
 	struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
 	int req;
 	u32 lkf;
+	char strname[GDLM_STRNAME_BYTES] = "";
 
 	req = make_mode(req_state);
 	lkf = make_flags(gl->gl_lksb.sb_lkid, flags, req);
-
+	gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT);
+	gfs2_sbstats_inc(gl, GFS2_LKS_DCOUNT);
+	if (gl->gl_lksb.sb_lkid) {
+		gfs2_update_request_times(gl);
+	} else {
+		memset(strname, ' ', GDLM_STRNAME_BYTES - 1);
+		strname[GDLM_STRNAME_BYTES - 1] = '\0';
+		gfs2_reverse_hex(strname + 7, gl->gl_name.ln_type);
+		gfs2_reverse_hex(strname + 23, gl->gl_name.ln_number);
+		gl->gl_dstamp = ktime_get_real();
+	}
 	/*
 	 * Submit the actual lock request.
 	 */
 
-	return dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, gl->gl_strname,
+	return dlm_lock(ls->ls_dlm, req, &gl->gl_lksb, lkf, strname,
 			GDLM_STRNAME_BYTES - 1, 0, gdlm_ast, gl, gdlm_bast);
 }
 
@@ -172,6 +281,10 @@ static void gdlm_put_lock(struct gfs2_glock *gl)
 		return;
 	}
 
+	clear_bit(GLF_BLOCKING, &gl->gl_flags);
+	gfs2_glstats_inc(gl, GFS2_LKS_DCOUNT);
+	gfs2_sbstats_inc(gl, GFS2_LKS_DCOUNT);
+	gfs2_update_request_times(gl);
 	error = dlm_unlock(ls->ls_dlm, gl->gl_lksb.sb_lkid, DLM_LKF_VALBLK,
 			   NULL, gl);
 	if (error) {