[PATCH v1 2/4] ceph: track average/stdev r/w/m latency

[Venky Shankar <vshankar@redhat.com>]

The math involved in tracking average and standard deviation
for r/w/m latencies looks incorrect. Fix that up. Also, change
the variable name that tracks standard deviation (*_sq_sum) to
*_stdev.

Signed-off-by: Venky Shankar <vshankar@redhat.com>
---
 fs/ceph/debugfs.c |  6 +++---
 fs/ceph/metric.c  | 45 ++++++++++++++++++++++++---------------------
 fs/ceph/metric.h  |  9 ++++++---
 3 files changed, 33 insertions(+), 27 deletions(-)

diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index f9ff70704423..9153bc233e08 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -176,7 +176,7 @@ static int metric_show(struct seq_file *s, void *p)
 	avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
 	min = m->read_latency_min;
 	max = m->read_latency_max;
-	sq = m->read_latency_sq_sum;
+	sq = m->read_latency_stdev;
 	spin_unlock(&m->read_latency_lock);
 	CEPH_METRIC_SHOW("read", total, avg, min, max, sq);
 
@@ -186,7 +186,7 @@ static int metric_show(struct seq_file *s, void *p)
 	avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
 	min = m->write_latency_min;
 	max = m->write_latency_max;
-	sq = m->write_latency_sq_sum;
+	sq = m->write_latency_stdev;
 	spin_unlock(&m->write_latency_lock);
 	CEPH_METRIC_SHOW("write", total, avg, min, max, sq);
 
@@ -196,7 +196,7 @@ static int metric_show(struct seq_file *s, void *p)
 	avg = total > 0 ? DIV64_U64_ROUND_CLOSEST(sum, total) : 0;
 	min = m->metadata_latency_min;
 	max = m->metadata_latency_max;
-	sq = m->metadata_latency_sq_sum;
+	sq = m->metadata_latency_stdev;
 	spin_unlock(&m->metadata_latency_lock);
 	CEPH_METRIC_SHOW("metadata", total, avg, min, max, sq);
 
diff --git a/fs/ceph/metric.c b/fs/ceph/metric.c
index 19bca20cf7e1..e00b1c2ce25b 100644
--- a/fs/ceph/metric.c
+++ b/fs/ceph/metric.c
@@ -184,21 +184,24 @@ int ceph_metric_init(struct ceph_client_metric *m)
 		goto err_i_caps_mis;
 
 	spin_lock_init(&m->read_latency_lock);
-	m->read_latency_sq_sum = 0;
+	m->read_latency_stdev = 0;
+	m->avg_read_latency = 0;
 	m->read_latency_min = KTIME_MAX;
 	m->read_latency_max = 0;
 	m->total_reads = 0;
 	m->read_latency_sum = 0;
 
 	spin_lock_init(&m->write_latency_lock);
-	m->write_latency_sq_sum = 0;
+	m->write_latency_stdev = 0;
+	m->avg_write_latency = 0;
 	m->write_latency_min = KTIME_MAX;
 	m->write_latency_max = 0;
 	m->total_writes = 0;
 	m->write_latency_sum = 0;
 
 	spin_lock_init(&m->metadata_latency_lock);
-	m->metadata_latency_sq_sum = 0;
+	m->metadata_latency_stdev = 0;
+	m->avg_metadata_latency = 0;
 	m->metadata_latency_min = KTIME_MAX;
 	m->metadata_latency_max = 0;
 	m->total_metadatas = 0;
@@ -250,10 +253,10 @@ void ceph_metric_destroy(struct ceph_client_metric *m)
 }
 
 static inline void __update_latency(ktime_t *totalp, ktime_t *lsump,
-				    ktime_t *min, ktime_t *max,
-				    ktime_t *sq_sump, ktime_t lat)
+				    ktime_t *lavgp, ktime_t *min, ktime_t *max,
+				    ktime_t *lstdev, ktime_t lat)
 {
-	ktime_t total, avg, sq, lsum;
+	ktime_t total, avg, stdev, lsum;
 
 	total = ++(*totalp);
 	lsum = (*lsump += lat);
@@ -263,15 +266,15 @@ static inline void __update_latency(ktime_t *totalp, ktime_t *lsump,
 	if (unlikely(lat > *max))
 		*max = lat;
 
-	if (unlikely(total == 1))
-		return;
-
-	/* the sq is (lat - old_avg) * (lat - new_avg) */
-	avg = DIV64_U64_ROUND_CLOSEST((lsum - lat), (total - 1));
-	sq = lat - avg;
-	avg = DIV64_U64_ROUND_CLOSEST(lsum, total);
-	sq = sq * (lat - avg);
-	*sq_sump += sq;
+	if (unlikely(total == 1)) {
+		*lavgp = lat;
+		*lstdev = 0;
+	} else {
+		avg = *lavgp + div64_s64(lat - *lavgp, total);
+		stdev = *lstdev + (lat - *lavgp)*(lat - avg);
+		*lstdev = int_sqrt(div64_u64(stdev, total - 1));
+		*lavgp = avg;
+	}
 }
 
 void ceph_update_read_latency(struct ceph_client_metric *m,
@@ -285,8 +288,8 @@ void ceph_update_read_latency(struct ceph_client_metric *m,
 
 	spin_lock(&m->read_latency_lock);
 	__update_latency(&m->total_reads, &m->read_latency_sum,
-			 &m->read_latency_min, &m->read_latency_max,
-			 &m->read_latency_sq_sum, lat);
+			 &m->avg_read_latency, &m->read_latency_min,
+			 &m->read_latency_max, &m->read_latency_stdev, lat);
 	spin_unlock(&m->read_latency_lock);
 }
 
@@ -301,8 +304,8 @@ void ceph_update_write_latency(struct ceph_client_metric *m,
 
 	spin_lock(&m->write_latency_lock);
 	__update_latency(&m->total_writes, &m->write_latency_sum,
-			 &m->write_latency_min, &m->write_latency_max,
-			 &m->write_latency_sq_sum, lat);
+			 &m->avg_write_latency, &m->write_latency_min,
+			 &m->write_latency_max, &m->write_latency_stdev, lat);
 	spin_unlock(&m->write_latency_lock);
 }
 
@@ -317,7 +320,7 @@ void ceph_update_metadata_latency(struct ceph_client_metric *m,
 
 	spin_lock(&m->metadata_latency_lock);
 	__update_latency(&m->total_metadatas, &m->metadata_latency_sum,
-			 &m->metadata_latency_min, &m->metadata_latency_max,
-			 &m->metadata_latency_sq_sum, lat);
+			 &m->avg_metadata_latency, &m->metadata_latency_min,
+			 &m->metadata_latency_max, &m->metadata_latency_stdev, lat);
 	spin_unlock(&m->metadata_latency_lock);
 }
diff --git a/fs/ceph/metric.h b/fs/ceph/metric.h
index 1151d64dbcbc..136689fa0aec 100644
--- a/fs/ceph/metric.h
+++ b/fs/ceph/metric.h
@@ -108,21 +108,24 @@ struct ceph_client_metric {
 	spinlock_t read_latency_lock;
 	u64 total_reads;
 	ktime_t read_latency_sum;
-	ktime_t read_latency_sq_sum;
+	ktime_t avg_read_latency;
+	ktime_t read_latency_stdev;
 	ktime_t read_latency_min;
 	ktime_t read_latency_max;
 
 	spinlock_t write_latency_lock;
 	u64 total_writes;
 	ktime_t write_latency_sum;
-	ktime_t write_latency_sq_sum;
+	ktime_t avg_write_latency;
+	ktime_t write_latency_stdev;
 	ktime_t write_latency_min;
 	ktime_t write_latency_max;
 
 	spinlock_t metadata_latency_lock;
 	u64 total_metadatas;
 	ktime_t metadata_latency_sum;
-	ktime_t metadata_latency_sq_sum;
+	ktime_t avg_metadata_latency;
+	ktime_t metadata_latency_stdev;
 	ktime_t metadata_latency_min;
 	ktime_t metadata_latency_max;
 
-- 
2.27.0