Merging upstream version 1.46.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

3 files changed, 278 insertions, 0 deletions

diff --git a/src/web/api/queries/stddev/README.md b/src/web/api/queries/stddev/README.md
new file mode 100644
index 00000000..76cfee1f
--- /dev/null
+++ b/src/web/api/queries/stddev/README.md
@@ -0,0 +1,97 @@
+<!--
+title: "standard deviation (`stddev`)"
+sidebar_label: "standard deviation (`stddev`)"
+custom_edit_url: https://github.com/netdata/netdata/edit/master/src/web/api/queries/stddev/README.md
+learn_status: "Published"
+learn_topic_type: "References"
+learn_rel_path: "Developers/Web/Api/Queries"
+-->
+
+# 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 alerts like this:
+
+```
+ alarm: my_alert
+    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 alert 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 alert if had spikes below 800/sec or above 1200/sec.
+
+## how to use
+
+Use it in alerts like this:
+
+```
+ alarm: my_alert
+    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/src/web/api/queries/stddev/stddev.c b/src/web/api/queries/stddev/stddev.c
new file mode 100644
index 00000000..8f543119
--- /dev/null
+++ b/src/web/api/queries/stddev/stddev.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-3.0-or-later
+
+#include "stddev.h"
+
+
+// ----------------------------------------------------------------------------
+// stddev
+
+/*
+ * Mean = average
+ *
+NETDATA_DOUBLE grouping_flush_mean(RRDR *r, RRDR_VALUE_FLAGS *rrdr_value_options_ptr) {
+    struct grouping_stddev *g = (struct grouping_stddev *)r->grouping.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->grouping.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/src/web/api/queries/stddev/stddev.h b/src/web/api/queries/stddev/stddev.h
new file mode 100644
index 00000000..f7a1a06c
--- /dev/null
+++ b/src/web/api/queries/stddev/stddev.h
@@ -0,0 +1,120 @@
+// 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"
+
+// this implementation comes from:
+// https://www.johndcook.com/blog/standard_deviation/
+
+struct tg_stddev {
+    long count;
+    NETDATA_DOUBLE m_oldM, m_newM, m_oldS, m_newS;
+};
+
+static inline void tg_stddev_create(RRDR *r, const char *options __maybe_unused) {
+    r->time_grouping.data = onewayalloc_callocz(r->internal.owa, 1, sizeof(struct tg_stddev));
+}
+
+// resets when switches dimensions
+// so, clear everything to restart
+static inline void tg_stddev_reset(RRDR *r) {
+    struct tg_stddev *g = (struct tg_stddev *)r->time_grouping.data;
+    g->count = 0;
+}
+
+static inline void tg_stddev_free(RRDR *r) {
+    onewayalloc_freez(r->internal.owa, r->time_grouping.data);
+    r->time_grouping.data = NULL;
+}
+
+static inline void tg_stddev_add(RRDR *r, NETDATA_DOUBLE value) {
+    struct tg_stddev *g = (struct tg_stddev *)r->time_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 tg_stddev_mean(struct tg_stddev *g) {
+    return (g->count > 0) ? g->m_newM : 0.0;
+}
+
+static inline NETDATA_DOUBLE tg_stddev_variance(struct tg_stddev *g) {
+    return ( (g->count > 1) ? g->m_newS/(NETDATA_DOUBLE)(g->count - 1) : 0.0 );
+}
+static inline NETDATA_DOUBLE tg_stddev_stddev(struct tg_stddev *g) {
+    return sqrtndd(tg_stddev_variance(g));
+}
+
+static inline NETDATA_DOUBLE tg_stddev_flush(RRDR *r, RRDR_VALUE_FLAGS *rrdr_value_options_ptr) {
+    struct tg_stddev *g = (struct tg_stddev *)r->time_grouping.data;
+
+    NETDATA_DOUBLE value;
+
+    if(likely(g->count > 1)) {
+        value = tg_stddev_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;
+    }
+
+    tg_stddev_reset(r);
+
+    return  value;
+}
+
+// https://en.wikipedia.org/wiki/Coefficient_of_variation
+static inline NETDATA_DOUBLE tg_stddev_coefficient_of_variation_flush(RRDR *r, RRDR_VALUE_FLAGS *rrdr_value_options_ptr) {
+    struct tg_stddev *g = (struct tg_stddev *)r->time_grouping.data;
+
+    NETDATA_DOUBLE value;
+
+    if(likely(g->count > 1)) {
+        NETDATA_DOUBLE m = tg_stddev_mean(g);
+        value = 100.0 * tg_stddev_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;
+    }
+
+    tg_stddev_reset(r);
+
+    return  value;
+}
+
+#endif //NETDATA_API_QUERIES_STDDEV_H