diff options
Diffstat (limited to 'src/web/api/queries/trimmed_mean')
| -rw-r--r-- | src/web/api/queries/trimmed_mean/README.md | 60 | ||||
| -rw-r--r-- | src/web/api/queries/trimmed_mean/trimmed_mean.c | 7 | ||||
| -rw-r--r-- | src/web/api/queries/trimmed_mean/trimmed_mean.h | 169 |
3 files changed, 236 insertions, 0 deletions
diff --git a/src/web/api/queries/trimmed_mean/README.md b/src/web/api/queries/trimmed_mean/README.md new file mode 100644 index 000000000..969023292 --- /dev/null +++ b/src/web/api/queries/trimmed_mean/README.md @@ -0,0 +1,60 @@ +<!-- +title: "Trimmed Mean" +sidebar_label: "Trimmed Mean" +description: "Use trimmed-mean in API queries and health entities to find the average value from a sample, eliminating any unwanted spikes in the returned metrics." +custom_edit_url: https://github.com/netdata/netdata/edit/master/src/web/api/queries/trimmed_mean/README.md +learn_status: "Published" +learn_topic_type: "References" +learn_rel_path: "Developers/Web/Api/Queries" +--> + +# Trimmed Mean + +The trimmed mean is the average value of a series excluding the smallest and biggest points. + +Netdata applies linear interpolation on the last point, if the percentage requested to be excluded does not give a +round number of points. + +The following percentile aliases are defined: + +- `trimmed-mean1` +- `trimmed-mean2` +- `trimmed-mean3` +- `trimmed-mean5` +- `trimmed-mean10` +- `trimmed-mean15` +- `trimmed-mean20` +- `trimmed-mean25` + +The default `trimmed-mean` is an alias for `trimmed-mean5`. +Any percentage may be requested using the `group_options` query parameter. + +## how to use + +Use it in alerts like this: + +``` + alarm: my_alert + on: my_chart +lookup: trimmed-mean5 -1m unaligned of my_dimension + warn: $this > 1000 +``` + +`trimmed-mean` does not change the units. For example, if the chart units is `requests/sec`, the result +will be again expressed in the same units. + +It can also be used in APIs and badges as `&group=trimmed-mean` in the URL and the additional parameter `group_options` +may be used to request any percentage (e.g. `&group=trimmed-mean&group_options=29`). + +## Examples + +Examining last 1 minute `successful` web server responses: + +-  +-  +-  +-  + +## References + +- <https://en.wikipedia.org/wiki/Truncated_mean>. diff --git a/src/web/api/queries/trimmed_mean/trimmed_mean.c b/src/web/api/queries/trimmed_mean/trimmed_mean.c new file mode 100644 index 000000000..c50db7ed6 --- /dev/null +++ b/src/web/api/queries/trimmed_mean/trimmed_mean.c @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#include "trimmed_mean.h" + +// ---------------------------------------------------------------------------- +// median + diff --git a/src/web/api/queries/trimmed_mean/trimmed_mean.h b/src/web/api/queries/trimmed_mean/trimmed_mean.h new file mode 100644 index 000000000..3c09015bf --- /dev/null +++ b/src/web/api/queries/trimmed_mean/trimmed_mean.h @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-3.0-or-later + +#ifndef NETDATA_API_QUERIES_TRIMMED_MEAN_H +#define NETDATA_API_QUERIES_TRIMMED_MEAN_H + +#include "../query.h" +#include "../rrdr.h" + +struct tg_trimmed_mean { + size_t series_size; + size_t next_pos; + NETDATA_DOUBLE percent; + + NETDATA_DOUBLE *series; +}; + +static inline void tg_trimmed_mean_create_internal(RRDR *r, const char *options, NETDATA_DOUBLE def) { + long entries = r->view.group; + if(entries < 10) entries = 10; + + struct tg_trimmed_mean *g = (struct tg_trimmed_mean *)onewayalloc_callocz(r->internal.owa, 1, sizeof(struct tg_trimmed_mean)); + g->series = onewayalloc_mallocz(r->internal.owa, entries * sizeof(NETDATA_DOUBLE)); + g->series_size = (size_t)entries; + + g->percent = def; + if(options && *options) { + g->percent = str2ndd(options, NULL); + if(!netdata_double_isnumber(g->percent)) g->percent = 0.0; + if(g->percent < 0.0) g->percent = 0.0; + if(g->percent > 50.0) g->percent = 50.0; + } + + g->percent = 1.0 - ((g->percent / 100.0) * 2.0); + r->time_grouping.data = g; +} + +static inline void tg_trimmed_mean_create_1(RRDR *r, const char *options) { + tg_trimmed_mean_create_internal(r, options, 1.0); +} +static inline void tg_trimmed_mean_create_2(RRDR *r, const char *options) { + tg_trimmed_mean_create_internal(r, options, 2.0); +} +static inline void tg_trimmed_mean_create_3(RRDR *r, const char *options) { + tg_trimmed_mean_create_internal(r, options, 3.0); +} +static inline void tg_trimmed_mean_create_5(RRDR *r, const char *options) { + tg_trimmed_mean_create_internal(r, options, 5.0); +} +static inline void tg_trimmed_mean_create_10(RRDR *r, const char *options) { + tg_trimmed_mean_create_internal(r, options, 10.0); +} +static inline void tg_trimmed_mean_create_15(RRDR *r, const char *options) { + tg_trimmed_mean_create_internal(r, options, 15.0); +} +static inline void tg_trimmed_mean_create_20(RRDR *r, const char *options) { + tg_trimmed_mean_create_internal(r, options, 20.0); +} +static inline void tg_trimmed_mean_create_25(RRDR *r, const char *options) { + tg_trimmed_mean_create_internal(r, options, 25.0); +} + +// resets when switches dimensions +// so, clear everything to restart +static inline void tg_trimmed_mean_reset(RRDR *r) { + struct tg_trimmed_mean *g = (struct tg_trimmed_mean *)r->time_grouping.data; + g->next_pos = 0; +} + +static inline void tg_trimmed_mean_free(RRDR *r) { + struct tg_trimmed_mean *g = (struct tg_trimmed_mean *)r->time_grouping.data; + if(g) onewayalloc_freez(r->internal.owa, g->series); + + onewayalloc_freez(r->internal.owa, r->time_grouping.data); + r->time_grouping.data = NULL; +} + +static inline void tg_trimmed_mean_add(RRDR *r, NETDATA_DOUBLE value) { + struct tg_trimmed_mean *g = (struct tg_trimmed_mean *)r->time_grouping.data; + + if(unlikely(g->next_pos >= g->series_size)) { + g->series = onewayalloc_doublesize( r->internal.owa, g->series, g->series_size * sizeof(NETDATA_DOUBLE)); + g->series_size *= 2; + } + + g->series[g->next_pos++] = value; +} + +static inline NETDATA_DOUBLE tg_trimmed_mean_flush(RRDR *r, RRDR_VALUE_FLAGS *rrdr_value_options_ptr) { + struct tg_trimmed_mean *g = (struct tg_trimmed_mean *)r->time_grouping.data; + + NETDATA_DOUBLE value; + size_t available_slots = g->next_pos; + + if(unlikely(!available_slots)) { + value = 0.0; + *rrdr_value_options_ptr |= RRDR_VALUE_EMPTY; + } + else if(available_slots == 1) { + value = g->series[0]; + } + else { + sort_series(g->series, available_slots); + + NETDATA_DOUBLE min = g->series[0]; + NETDATA_DOUBLE max = g->series[available_slots - 1]; + + if (min != max) { + size_t slots_to_use = (size_t)((NETDATA_DOUBLE)available_slots * g->percent); + if(!slots_to_use) slots_to_use = 1; + + NETDATA_DOUBLE percent_to_use = (NETDATA_DOUBLE)slots_to_use / (NETDATA_DOUBLE)available_slots; + NETDATA_DOUBLE percent_delta = g->percent - percent_to_use; + + NETDATA_DOUBLE percent_interpolation_slot = 0.0; + NETDATA_DOUBLE percent_last_slot = 0.0; + if(percent_delta > 0.0) { + NETDATA_DOUBLE percent_to_use_plus_1_slot = (NETDATA_DOUBLE)(slots_to_use + 1) / (NETDATA_DOUBLE)available_slots; + NETDATA_DOUBLE percent_1slot = percent_to_use_plus_1_slot - percent_to_use; + + percent_interpolation_slot = percent_delta / percent_1slot; + percent_last_slot = 1 - percent_interpolation_slot; + } + + int start_slot, stop_slot, step, last_slot, interpolation_slot; + if(min >= 0.0 && max >= 0.0) { + start_slot = (int)((available_slots - slots_to_use) / 2); + stop_slot = start_slot + (int)slots_to_use; + last_slot = stop_slot - 1; + interpolation_slot = stop_slot; + step = 1; + } + else { + start_slot = (int)available_slots - 1 - (int)((available_slots - slots_to_use) / 2); + stop_slot = start_slot - (int)slots_to_use; + last_slot = stop_slot + 1; + interpolation_slot = stop_slot; + step = -1; + } + + value = 0.0; + for(int slot = start_slot; slot != stop_slot ; slot += step) + value += g->series[slot]; + + size_t counted = slots_to_use; + if(percent_interpolation_slot > 0.0 && interpolation_slot >= 0 && interpolation_slot < (int)available_slots) { + value += g->series[interpolation_slot] * percent_interpolation_slot; + value += g->series[last_slot] * percent_last_slot; + counted++; + } + + value = value / (NETDATA_DOUBLE)counted; + } + else + value = min; + } + + if(unlikely(!netdata_double_isnumber(value))) { + value = 0.0; + *rrdr_value_options_ptr |= RRDR_VALUE_EMPTY; + } + + //log_series_to_stderr(g->series, g->next_pos, value, "trimmed_mean"); + + g->next_pos = 0; + + return value; +} + +#endif //NETDATA_API_QUERIES_TRIMMED_MEAN_H |