summaryrefslogtreecommitdiffstats
path: root/web/api/queries/stddev
diff options
context:
space:
mode:
Diffstat (limited to 'web/api/queries/stddev')
-rw-r--r--web/api/queries/stddev/Makefile.am8
-rw-r--r--web/api/queries/stddev/README.md93
-rw-r--r--web/api/queries/stddev/stddev.c173
-rw-r--r--web/api/queries/stddev/stddev.h18
4 files changed, 292 insertions, 0 deletions
diff --git a/web/api/queries/stddev/Makefile.am b/web/api/queries/stddev/Makefile.am
new file mode 100644
index 0000000..161784b
--- /dev/null
+++ b/web/api/queries/stddev/Makefile.am
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+AUTOMAKE_OPTIONS = subdir-objects
+MAINTAINERCLEANFILES = $(srcdir)/Makefile.in
+
+dist_noinst_DATA = \
+ README.md \
+ $(NULL)
diff --git a/web/api/queries/stddev/README.md b/web/api/queries/stddev/README.md
new file mode 100644
index 0000000..2fca47d
--- /dev/null
+++ b/web/api/queries/stddev/README.md
@@ -0,0 +1,93 @@
+<!--
+title: "standard deviation (`stddev`)"
+custom_edit_url: https://github.com/netdata/netdata/edit/master/web/api/queries/stddev/README.md
+-->
+
+# standard deviation (`stddev`)
+
+The standard deviation is a measure that is used to quantify the amount of variation or dispersion
+of a set of data values.
+
+A low standard deviation indicates that the data points tend to be close to the mean (also called the
+expected value) of the set, while a high standard deviation indicates that the data points are spread
+out over a wider range of values.
+
+## how to use
+
+Use it in alarms like this:
+
+```
+ alarm: my_alarm
+ on: my_chart
+lookup: stddev -1m unaligned of my_dimension
+ warn: $this > 1000
+```
+
+`stdev` does not change the units. For example, if the chart units is `requests/sec`, the standard
+deviation will be again expressed in the same units.
+
+It can also be used in APIs and badges as `&group=stddev` in the URL.
+
+## Examples
+
+Examining last 1 minute `successful` web server responses:
+
+- ![](https://registry.my-netdata.io/api/v1/badge.svg?chart=web_log_nginx.response_statuses&dimensions=success&group=min&after=-60&label=min)
+- ![](https://registry.my-netdata.io/api/v1/badge.svg?chart=web_log_nginx.response_statuses&dimensions=success&group=average&after=-60&label=average&value_color=yellow)
+- ![](https://registry.my-netdata.io/api/v1/badge.svg?chart=web_log_nginx.response_statuses&dimensions=success&group=stddev&after=-60&label=standard+deviation&value_color=orange)
+- ![](https://registry.my-netdata.io/api/v1/badge.svg?chart=web_log_nginx.response_statuses&dimensions=success&group=max&after=-60&label=max)
+
+## References
+
+Check <https://en.wikipedia.org/wiki/Standard_deviation>.
+
+---
+
+# Coefficient of variation (`cv`)
+
+> This query is also available as `rsd`.
+
+The coefficient of variation (`cv`), also known as relative standard deviation (`rsd`),
+is a standardized measure of dispersion of a probability distribution or frequency distribution.
+
+It is defined as the ratio of the **standard deviation** to the **mean**.
+
+In simple terms, it gives the percentage of change. So, if the average value of a metric is 1000
+and its standard deviation is 100 (meaning that it variates from 900 to 1100), then `cv` is 10%.
+
+This is an easy way to check the % variation, without using absolute values.
+
+For example, you may trigger an alarm if your web server requests/sec `cv` is above 20 (`%`)
+over the last minute. So if your web server was serving 1000 reqs/sec over the last minute,
+it will trigger the alarm if had spikes below 800/sec or above 1200/sec.
+
+## how to use
+
+Use it in alarms like this:
+
+```
+ alarm: my_alarm
+ on: my_chart
+lookup: cv -1m unaligned of my_dimension
+ units: %
+ warn: $this > 20
+```
+
+The units reported by `cv` is always `%`.
+
+It can also be used in APIs and badges as `&group=cv` in the URL.
+
+## Examples
+
+Examining last 1 minute `successful` web server responses:
+
+- ![](https://registry.my-netdata.io/api/v1/badge.svg?chart=web_log_nginx.response_statuses&dimensions=success&group=min&after=-60&label=min)
+- ![](https://registry.my-netdata.io/api/v1/badge.svg?chart=web_log_nginx.response_statuses&dimensions=success&group=average&after=-60&label=average&value_color=yellow)
+- ![](https://registry.my-netdata.io/api/v1/badge.svg?chart=web_log_nginx.response_statuses&dimensions=success&group=cv&after=-60&label=coefficient+of+variation&value_color=orange&units=pcent)
+- ![](https://registry.my-netdata.io/api/v1/badge.svg?chart=web_log_nginx.response_statuses&dimensions=success&group=max&after=-60&label=max)
+
+## References
+
+Check <https://en.wikipedia.org/wiki/Coefficient_of_variation>.
+
+
diff --git a/web/api/queries/stddev/stddev.c b/web/api/queries/stddev/stddev.c
new file mode 100644
index 0000000..92a67b4
--- /dev/null
+++ b/web/api/queries/stddev/stddev.c
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-3.0-or-later
+
+#include "stddev.h"
+
+
+// ----------------------------------------------------------------------------
+// stddev
+
+// this implementation comes from:
+// https://www.johndcook.com/blog/standard_deviation/
+
+struct grouping_stddev {
+ long count;
+ NETDATA_DOUBLE m_oldM, m_newM, m_oldS, m_newS;
+};
+
+void grouping_create_stddev(RRDR *r, const char *options __maybe_unused) {
+ r->internal.grouping_data = onewayalloc_callocz(r->internal.owa, 1, sizeof(struct grouping_stddev));
+}
+
+// resets when switches dimensions
+// so, clear everything to restart
+void grouping_reset_stddev(RRDR *r) {
+ struct grouping_stddev *g = (struct grouping_stddev *)r->internal.grouping_data;
+ g->count = 0;
+}
+
+void grouping_free_stddev(RRDR *r) {
+ onewayalloc_freez(r->internal.owa, r->internal.grouping_data);
+ r->internal.grouping_data = NULL;
+}
+
+void grouping_add_stddev(RRDR *r, NETDATA_DOUBLE value) {
+ struct grouping_stddev *g = (struct grouping_stddev *)r->internal.grouping_data;
+
+ g->count++;
+
+ // See Knuth TAOCP vol 2, 3rd edition, page 232
+ if (g->count == 1) {
+ g->m_oldM = g->m_newM = value;
+ g->m_oldS = 0.0;
+ }
+ else {
+ g->m_newM = g->m_oldM + (value - g->m_oldM) / g->count;
+ g->m_newS = g->m_oldS + (value - g->m_oldM) * (value - g->m_newM);
+
+ // set up for next iteration
+ g->m_oldM = g->m_newM;
+ g->m_oldS = g->m_newS;
+ }
+}
+
+static inline NETDATA_DOUBLE mean(struct grouping_stddev *g) {
+ return (g->count > 0) ? g->m_newM : 0.0;
+}
+
+static inline NETDATA_DOUBLE variance(struct grouping_stddev *g) {
+ return ( (g->count > 1) ? g->m_newS/(NETDATA_DOUBLE)(g->count - 1) : 0.0 );
+}
+static inline NETDATA_DOUBLE stddev(struct grouping_stddev *g) {
+ return sqrtndd(variance(g));
+}
+
+NETDATA_DOUBLE grouping_flush_stddev(RRDR *r, RRDR_VALUE_FLAGS *rrdr_value_options_ptr) {
+ struct grouping_stddev *g = (struct grouping_stddev *)r->internal.grouping_data;
+
+ NETDATA_DOUBLE value;
+
+ if(likely(g->count > 1)) {
+ value = stddev(g);
+
+ if(!netdata_double_isnumber(value)) {
+ value = 0.0;
+ *rrdr_value_options_ptr |= RRDR_VALUE_EMPTY;
+ }
+ }
+ else if(g->count == 1) {
+ value = 0.0;
+ }
+ else {
+ value = 0.0;
+ *rrdr_value_options_ptr |= RRDR_VALUE_EMPTY;
+ }
+
+ grouping_reset_stddev(r);
+
+ return value;
+}
+
+// https://en.wikipedia.org/wiki/Coefficient_of_variation
+NETDATA_DOUBLE grouping_flush_coefficient_of_variation(RRDR *r, RRDR_VALUE_FLAGS *rrdr_value_options_ptr) {
+ struct grouping_stddev *g = (struct grouping_stddev *)r->internal.grouping_data;
+
+ NETDATA_DOUBLE value;
+
+ if(likely(g->count > 1)) {
+ NETDATA_DOUBLE m = mean(g);
+ value = 100.0 * stddev(g) / ((m < 0)? -m : m);
+
+ if(unlikely(!netdata_double_isnumber(value))) {
+ value = 0.0;
+ *rrdr_value_options_ptr |= RRDR_VALUE_EMPTY;
+ }
+ }
+ else if(g->count == 1) {
+ // one value collected
+ value = 0.0;
+ }
+ else {
+ // no values collected
+ value = 0.0;
+ *rrdr_value_options_ptr |= RRDR_VALUE_EMPTY;
+ }
+
+ grouping_reset_stddev(r);
+
+ return value;
+}
+
+
+/*
+ * Mean = average
+ *
+NETDATA_DOUBLE grouping_flush_mean(RRDR *r, RRDR_VALUE_FLAGS *rrdr_value_options_ptr) {
+ struct grouping_stddev *g = (struct grouping_stddev *)r->internal.grouping_data;
+
+ NETDATA_DOUBLE value;
+
+ if(unlikely(!g->count)) {
+ value = 0.0;
+ *rrdr_value_options_ptr |= RRDR_VALUE_EMPTY;
+ }
+ else {
+ value = mean(g);
+
+ if(!isnormal(value)) {
+ value = 0.0;
+ *rrdr_value_options_ptr |= RRDR_VALUE_EMPTY;
+ }
+ }
+
+ grouping_reset_stddev(r);
+
+ return value;
+}
+ */
+
+/*
+ * It is not advised to use this version of variance directly
+ *
+NETDATA_DOUBLE grouping_flush_variance(RRDR *r, RRDR_VALUE_FLAGS *rrdr_value_options_ptr) {
+ struct grouping_stddev *g = (struct grouping_stddev *)r->internal.grouping_data;
+
+ NETDATA_DOUBLE value;
+
+ if(unlikely(!g->count)) {
+ value = 0.0;
+ *rrdr_value_options_ptr |= RRDR_VALUE_EMPTY;
+ }
+ else {
+ value = variance(g);
+
+ if(!isnormal(value)) {
+ value = 0.0;
+ *rrdr_value_options_ptr |= RRDR_VALUE_EMPTY;
+ }
+ }
+
+ grouping_reset_stddev(r);
+
+ return value;
+}
+*/ \ No newline at end of file
diff --git a/web/api/queries/stddev/stddev.h b/web/api/queries/stddev/stddev.h
new file mode 100644
index 0000000..4b8ffcd
--- /dev/null
+++ b/web/api/queries/stddev/stddev.h
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-3.0-or-later
+
+#ifndef NETDATA_API_QUERIES_STDDEV_H
+#define NETDATA_API_QUERIES_STDDEV_H
+
+#include "../query.h"
+#include "../rrdr.h"
+
+void grouping_create_stddev(RRDR *r, const char *options __maybe_unused);
+void grouping_reset_stddev(RRDR *r);
+void grouping_free_stddev(RRDR *r);
+void grouping_add_stddev(RRDR *r, NETDATA_DOUBLE value);
+NETDATA_DOUBLE grouping_flush_stddev(RRDR *r, RRDR_VALUE_FLAGS *rrdr_value_options_ptr);
+NETDATA_DOUBLE grouping_flush_coefficient_of_variation(RRDR *r, RRDR_VALUE_FLAGS *rrdr_value_options_ptr);
+// NETDATA_DOUBLE grouping_flush_mean(RRDR *r, RRDR_VALUE_FLAGS *rrdr_value_options_ptr);
+// NETDATA_DOUBLE grouping_flush_variance(RRDR *r, RRDR_VALUE_FLAGS *rrdr_value_options_ptr);
+
+#endif //NETDATA_API_QUERIES_STDDEV_H