remove python.d/riakkv (#18329)
Ilya Mashchenko committed
Aug 14, 2024 at 13:48 UTC
1bd85e939b8f30f51c104982a0e28b45cfcfe1c5
6 files changed
-1016
CMakeLists.txt
-2
@@ -2788,7 +2788,6 @@ install(FILES
2788
src/collectors/python.d.plugin/oracledb/oracledb.conf
2789
src/collectors/python.d.plugin/pandas/pandas.conf
2790
src/collectors/python.d.plugin/retroshare/retroshare.conf
2791
- src/collectors/python.d.plugin/riakkv/riakkv.conf
2791
src/collectors/python.d.plugin/samba/samba.conf
2792
src/collectors/python.d.plugin/spigotmc/spigotmc.conf
2793
src/collectors/python.d.plugin/tor/tor.conf
@@ -2813,7 +2812,6 @@ install(FILES
2812
src/collectors/python.d.plugin/oracledb/oracledb.chart.py
2813
src/collectors/python.d.plugin/pandas/pandas.chart.py
2814
src/collectors/python.d.plugin/retroshare/retroshare.chart.py
2816
- src/collectors/python.d.plugin/riakkv/riakkv.chart.py
2815
src/collectors/python.d.plugin/samba/samba.chart.py
2816
src/collectors/python.d.plugin/spigotmc/spigotmc.chart.py
2817
src/collectors/python.d.plugin/tor/tor.chart.py
src/collectors/python.d.plugin/riakkv/README.md
deleted
-1
@@ -1 +0,0 @@
1
-integrations/riakkv.md
\ No newline at end of file
src/collectors/python.d.plugin/riakkv/integrations/riakkv.md
deleted
-253
@@ -1,253 +0,0 @@
1
-<!--startmeta
2
-custom_edit_url: "https://github.com/netdata/netdata/edit/master/src/collectors/python.d.plugin/riakkv/README.md"
3
-meta_yaml: "https://github.com/netdata/netdata/edit/master/src/collectors/python.d.plugin/riakkv/metadata.yaml"
4
-sidebar_label: "RiakKV"
5
-learn_status: "Published"
6
-learn_rel_path: "Collecting Metrics/Databases"
7
-most_popular: False
8
-message: "DO NOT EDIT THIS FILE DIRECTLY, IT IS GENERATED BY THE COLLECTOR'S metadata.yaml FILE"
9
-endmeta-->
10
-
11
-# RiakKV
12
-
13
-
14
-<img src="https://netdata.cloud/img/riak.svg" width="150"/>
15
-
16
-
17
-Plugin: python.d.plugin
18
-Module: riakkv
19
-
20
-<img src="https://img.shields.io/badge/maintained%20by-Netdata-%2300ab44" />
21
-
22
-## Overview
23
-
24
-This collector monitors RiakKV metrics about throughput, latency, resources and more.'
25
-
26
-
27
-This collector reads the database stats from the `/stats` endpoint.
28
-
29
-This collector is supported on all platforms.
30
-
31
-This collector supports collecting metrics from multiple instances of this integration, including remote instances.
32
-
33
-
34
-### Default Behavior
35
-
36
-#### Auto-Detection
37
-
38
-If the /stats endpoint is accessible, RiakKV instances on the local host running on port 8098 will be autodetected.
39
-
40
-#### Limits
41
-
42
-The default configuration for this integration does not impose any limits on data collection.
43
-
44
-#### Performance Impact
45
-
46
-The default configuration for this integration is not expected to impose a significant performance impact on the system.
47
-
48
-
49
-## Metrics
50
-
51
-Metrics grouped by *scope*.
52
-
53
-The scope defines the instance that the metric belongs to. An instance is uniquely identified by a set of labels.
54
-
55
-
56
-
57
-### Per RiakKV instance
58
-
59
-These metrics refer to the entire monitored application.
60
-
61
-This scope has no labels.
62
-
63
-Metrics:
64
-
65
-| Metric | Dimensions | Unit |
66
-|:------|:----------|:----|
67
-| riak.kv.throughput | gets, puts | operations/s |
68
-| riak.dt.vnode_updates | counters, sets, maps | operations/s |
69
-| riak.search | queries | queries/s |
70
-| riak.search.documents | indexed | documents/s |
71
-| riak.consistent.operations | gets, puts | operations/s |
72
-| riak.kv.latency.get | mean, median, 95, 99, 100 | ms |
73
-| riak.kv.latency.put | mean, median, 95, 99, 100 | ms |
74
-| riak.dt.latency.counter_merge | mean, median, 95, 99, 100 | ms |
75
-| riak.dt.latency.set_merge | mean, median, 95, 99, 100 | ms |
76
-| riak.dt.latency.map_merge | mean, median, 95, 99, 100 | ms |
77
-| riak.search.latency.query | median, min, 95, 99, 999, max | ms |
78
-| riak.search.latency.index | median, min, 95, 99, 999, max | ms |
79
-| riak.consistent.latency.get | mean, median, 95, 99, 100 | ms |
80
-| riak.consistent.latency.put | mean, median, 95, 99, 100 | ms |
81
-| riak.vm | processes | total |
82
-| riak.vm.memory.processes | allocated, used | MB |
83
-| riak.kv.siblings_encountered.get | mean, median, 95, 99, 100 | siblings |
84
-| riak.kv.objsize.get | mean, median, 95, 99, 100 | KB |
85
-| riak.search.vnodeq_size | mean, median, 95, 99, 100 | messages |
86
-| riak.search.index | errors | errors |
87
-| riak.core.protobuf_connections | active | connections |
88
-| riak.core.repairs | read | repairs |
89
-| riak.core.fsm_active | get, put, secondary index, list keys | fsms |
90
-| riak.core.fsm_rejected | get, put | fsms |
91
-| riak.search.index | bad_entry, extract_fail | writes |
92
-
93
-
94
-
95
-## Alerts
96
-
97
-
98
-The following alerts are available:
99
-
100
-| Alert name | On metric | Description |
101
-|:------------|:----------|:------------|
102
-| [ riakkv_1h_kv_get_mean_latency ](https://github.com/netdata/netdata/blob/master/src/health/health.d/riakkv.conf) | riak.kv.latency.get | average time between reception of client GET request and subsequent response to client over the last hour |
103
-| [ riakkv_kv_get_slow ](https://github.com/netdata/netdata/blob/master/src/health/health.d/riakkv.conf) | riak.kv.latency.get | average time between reception of client GET request and subsequent response to the client over the last 3 minutes, compared to the average over the last hour |
104
-| [ riakkv_1h_kv_put_mean_latency ](https://github.com/netdata/netdata/blob/master/src/health/health.d/riakkv.conf) | riak.kv.latency.put | average time between reception of client PUT request and subsequent response to the client over the last hour |
105
-| [ riakkv_kv_put_slow ](https://github.com/netdata/netdata/blob/master/src/health/health.d/riakkv.conf) | riak.kv.latency.put | average time between reception of client PUT request and subsequent response to the client over the last 3 minutes, compared to the average over the last hour |
106
-| [ riakkv_vm_high_process_count ](https://github.com/netdata/netdata/blob/master/src/health/health.d/riakkv.conf) | riak.vm | number of processes running in the Erlang VM |
107
-| [ riakkv_list_keys_active ](https://github.com/netdata/netdata/blob/master/src/health/health.d/riakkv.conf) | riak.core.fsm_active | number of currently running list keys finite state machines |
108
-
109
-
110
-## Setup
111
-
112
-### Prerequisites
113
-
114
-#### Configure RiakKV to enable /stats endpoint
115
-
116
-You can follow the RiakKV configuration reference documentation for how to enable this.
117
-
118
-Source : https://docs.riak.com/riak/kv/2.2.3/configuring/reference/#client-interfaces
119
-
120
-
121
-
122
-### Configuration
123
-
124
-#### File
125
-
126
-The configuration file name for this integration is `python.d/riakkv.conf`.
127
-
128
-
129
-You can edit the configuration file using the `edit-config` script from the
130
-Netdata [config directory](/docs/netdata-agent/configuration/README.md#the-netdata-config-directory).
131
-
132
-```bash
133
-cd /etc/netdata 2>/dev/null || cd /opt/netdata/etc/netdata
134
-sudo ./edit-config python.d/riakkv.conf
135
-```
136
-#### Options
137
-
138
-There are 2 sections:
139
-
140
-* Global variables
141
-* One or more JOBS that can define multiple different instances to monitor.
142
-
143
-The following options can be defined globally: priority, penalty, autodetection_retry, update_every, but can also be defined per JOB to override the global values.
144
-
145
-Additionally, the following collapsed table contains all the options that can be configured inside a JOB definition.
146
-
147
-Every configuration JOB starts with a `job_name` value which will appear in the dashboard, unless a `name` parameter is specified.
148
-
149
-
150
-<details open><summary>Config options</summary>
151
-
152
-| Name | Description | Default | Required |
153
-|:----|:-----------|:-------|:--------:|
154
-| update_every | Sets the default data collection frequency. | 5 | no |
155
-| priority | Controls the order of charts at the netdata dashboard. | 60000 | no |
156
-| autodetection_retry | Sets the job re-check interval in seconds. | 0 | no |
157
-| penalty | Indicates whether to apply penalty to update_every in case of failures. | yes | no |
158
-| url | The url of the server | no | yes |
159
-
160
-</details>
161
-
162
-#### Examples
163
-
164
-##### Basic (default)
165
-
166
-A basic example configuration per job
167
-
168
-```yaml
169
-local:
170
-url: 'http://localhost:8098/stats'
171
-
172
-```
173
-##### Multi-instance
174
-
175
-> **Note**: When you define multiple jobs, their names must be unique.
176
-
177
-Collecting metrics from local and remote instances.
178
-
179
-
180
-<details open><summary>Config</summary>
181
-
182
-```yaml
183
-local:
184
- url: 'http://localhost:8098/stats'
185
-
186
-remote:
187
- url: 'http://192.0.2.1:8098/stats'
188
-
189
-```
190
-</details>
191
-
192
-
193
-
194
-## Troubleshooting
195
-
196
-### Debug Mode
197
-
198
-To troubleshoot issues with the `riakkv` collector, run the `python.d.plugin` with the debug option enabled. The output
199
-should give you clues as to why the collector isn't working.
200
-
201
-- Navigate to the `plugins.d` directory, usually at `/usr/libexec/netdata/plugins.d/`. If that's not the case on
202
- your system, open `netdata.conf` and look for the `plugins` setting under `[directories]`.
203
-
204
- ```bash
205
- cd /usr/libexec/netdata/plugins.d/
206
- ```
207
-
208
-- Switch to the `netdata` user.
209
-
210
- ```bash
211
- sudo -u netdata -s
212
- ```
213
-
214
-- Run the `python.d.plugin` to debug the collector:
215
-
216
- ```bash
217
- ./python.d.plugin riakkv debug trace
218
- ```
219
-
220
-### Getting Logs
221
-
222
-If you're encountering problems with the `riakkv` collector, follow these steps to retrieve logs and identify potential issues:
223
-
224
-- **Run the command** specific to your system (systemd, non-systemd, or Docker container).
225
-- **Examine the output** for any warnings or error messages that might indicate issues. These messages should provide clues about the root cause of the problem.
226
-
227
-#### System with systemd
228
-
229
-Use the following command to view logs generated since the last Netdata service restart:
230
-
231
-```bash
232
-journalctl _SYSTEMD_INVOCATION_ID="$(systemctl show --value --property=InvocationID netdata)" --namespace=netdata --grep riakkv
233
-```
234
-
235
-#### System without systemd
236
-
237
-Locate the collector log file, typically at `/var/log/netdata/collector.log`, and use `grep` to filter for collector's name:
238
-
239
-```bash
240
-grep riakkv /var/log/netdata/collector.log
241
-```
242
-
243
-**Note**: This method shows logs from all restarts. Focus on the **latest entries** for troubleshooting current issues.
244
-
245
-#### Docker Container
246
-
247
-If your Netdata runs in a Docker container named "netdata" (replace if different), use this command:
248
-
249
-```bash
250
-docker logs netdata 2>&1 | grep riakkv
251
-```
252
-
253
-
src/collectors/python.d.plugin/riakkv/metadata.yaml
deleted
-358
@@ -1,358 +0,0 @@
1
-plugin_name: python.d.plugin
2
-modules:
3
- - meta:
4
- plugin_name: python.d.plugin
5
- module_name: riakkv
6
- monitored_instance:
7
- name: RiakKV
8
- link: "https://riak.com/products/riak-kv/index.html"
9
- categories:
10
- - data-collection.database-servers
11
- icon_filename: "riak.svg"
12
- related_resources:
13
- integrations:
14
- list: []
15
- info_provided_to_referring_integrations:
16
- description: ""
17
- keywords:
18
- - database
19
- - nosql
20
- - big data
21
- most_popular: false
22
- overview:
23
- data_collection:
24
- metrics_description: |
25
- This collector monitors RiakKV metrics about throughput, latency, resources and more.'
26
- method_description: "This collector reads the database stats from the `/stats` endpoint."
27
- supported_platforms:
28
- include: []
29
- exclude: []
30
- multi_instance: true
31
- additional_permissions:
32
- description: ""
33
- default_behavior:
34
- auto_detection:
35
- description: "If the /stats endpoint is accessible, RiakKV instances on the local host running on port 8098 will be autodetected."
36
- limits:
37
- description: ""
38
- performance_impact:
39
- description: ""
40
- setup:
41
- prerequisites:
42
- list:
43
- - title: Configure RiakKV to enable /stats endpoint
44
- description: |
45
- You can follow the RiakKV configuration reference documentation for how to enable this.
46
-
47
- Source : https://docs.riak.com/riak/kv/2.2.3/configuring/reference/#client-interfaces
48
- configuration:
49
- file:
50
- name: "python.d/riakkv.conf"
51
- options:
52
- description: |
53
- There are 2 sections:
54
-
55
- * Global variables
56
- * One or more JOBS that can define multiple different instances to monitor.
57
-
58
- The following options can be defined globally: priority, penalty, autodetection_retry, update_every, but can also be defined per JOB to override the global values.
59
-
60
- Additionally, the following collapsed table contains all the options that can be configured inside a JOB definition.
61
-
62
- Every configuration JOB starts with a `job_name` value which will appear in the dashboard, unless a `name` parameter is specified.
63
- folding:
64
- title: "Config options"
65
- enabled: true
66
- list:
67
- - name: update_every
68
- description: Sets the default data collection frequency.
69
- default_value: 5
70
- required: false
71
- - name: priority
72
- description: Controls the order of charts at the netdata dashboard.
73
- default_value: 60000
74
- required: false
75
- - name: autodetection_retry
76
- description: Sets the job re-check interval in seconds.
77
- default_value: 0
78
- required: false
79
- - name: penalty
80
- description: Indicates whether to apply penalty to update_every in case of failures.
81
- default_value: yes
82
- required: false
83
- - name: url
84
- description: The url of the server
85
- default_value: no
86
- required: true
87
- examples:
88
- folding:
89
- enabled: true
90
- title: "Config"
91
- list:
92
- - name: Basic (default)
93
- folding:
94
- enabled: false
95
- description: A basic example configuration per job
96
- config: |
97
- local:
98
- url: 'http://localhost:8098/stats'
99
- - name: Multi-instance
100
- description: |
101
- > **Note**: When you define multiple jobs, their names must be unique.
102
-
103
- Collecting metrics from local and remote instances.
104
- config: |
105
- local:
106
- url: 'http://localhost:8098/stats'
107
-
108
- remote:
109
- url: 'http://192.0.2.1:8098/stats'
110
- troubleshooting:
111
- problems:
112
- list: []
113
- alerts:
114
- - name: riakkv_1h_kv_get_mean_latency
115
- link: https://github.com/netdata/netdata/blob/master/src/health/health.d/riakkv.conf
116
- metric: riak.kv.latency.get
117
- info: average time between reception of client GET request and subsequent response to client over the last hour
118
- - name: riakkv_kv_get_slow
119
- link: https://github.com/netdata/netdata/blob/master/src/health/health.d/riakkv.conf
120
- metric: riak.kv.latency.get
121
- info: average time between reception of client GET request and subsequent response to the client over the last 3 minutes, compared to the average over the last hour
122
- - name: riakkv_1h_kv_put_mean_latency
123
- link: https://github.com/netdata/netdata/blob/master/src/health/health.d/riakkv.conf
124
- metric: riak.kv.latency.put
125
- info: average time between reception of client PUT request and subsequent response to the client over the last hour
126
- - name: riakkv_kv_put_slow
127
- link: https://github.com/netdata/netdata/blob/master/src/health/health.d/riakkv.conf
128
- metric: riak.kv.latency.put
129
- info: average time between reception of client PUT request and subsequent response to the client over the last 3 minutes, compared to the average over the last hour
130
- - name: riakkv_vm_high_process_count
131
- link: https://github.com/netdata/netdata/blob/master/src/health/health.d/riakkv.conf
132
- metric: riak.vm
133
- info: number of processes running in the Erlang VM
134
- - name: riakkv_list_keys_active
135
- link: https://github.com/netdata/netdata/blob/master/src/health/health.d/riakkv.conf
136
- metric: riak.core.fsm_active
137
- info: number of currently running list keys finite state machines
138
- metrics:
139
- folding:
140
- title: Metrics
141
- enabled: false
142
- description: ""
143
- availability: []
144
- scopes:
145
- - name: global
146
- description: "These metrics refer to the entire monitored application."
147
- labels: []
148
- metrics:
149
- - name: riak.kv.throughput
150
- description: Reads & writes coordinated by this node
151
- unit: "operations/s"
152
- chart_type: line
153
- dimensions:
154
- - name: gets
155
- - name: puts
156
- - name: riak.dt.vnode_updates
157
- description: Update operations coordinated by local vnodes by data type
158
- unit: "operations/s"
159
- chart_type: line
160
- dimensions:
161
- - name: counters
162
- - name: sets
163
- - name: maps
164
- - name: riak.search
165
- description: Search queries on the node
166
- unit: "queries/s"
167
- chart_type: line
168
- dimensions:
169
- - name: queries
170
- - name: riak.search.documents
171
- description: Documents indexed by search
172
- unit: "documents/s"
173
- chart_type: line
174
- dimensions:
175
- - name: indexed
176
- - name: riak.consistent.operations
177
- description: Consistent node operations
178
- unit: "operations/s"
179
- chart_type: line
180
- dimensions:
181
- - name: gets
182
- - name: puts
183
- - name: riak.kv.latency.get
184
- description: Time between reception of a client GET request and subsequent response to client
185
- unit: "ms"
186
- chart_type: line
187
- dimensions:
188
- - name: mean
189
- - name: median
190
- - name: "95"
191
- - name: "99"
192
- - name: "100"
193
- - name: riak.kv.latency.put
194
- description: Time between reception of a client PUT request and subsequent response to client
195
- unit: "ms"
196
- chart_type: line
197
- dimensions:
198
- - name: mean
199
- - name: median
200
- - name: "95"
201
- - name: "99"
202
- - name: "100"
203
- - name: riak.dt.latency.counter_merge
204
- description: Time it takes to perform an Update Counter operation
205
- unit: "ms"
206
- chart_type: line
207
- dimensions:
208
- - name: mean
209
- - name: median
210
- - name: "95"
211
- - name: "99"
212
- - name: "100"
213
- - name: riak.dt.latency.set_merge
214
- description: Time it takes to perform an Update Set operation
215
- unit: "ms"
216
- chart_type: line
217
- dimensions:
218
- - name: mean
219
- - name: median
220
- - name: "95"
221
- - name: "99"
222
- - name: "100"
223
- - name: riak.dt.latency.map_merge
224
- description: Time it takes to perform an Update Map operation
225
- unit: "ms"
226
- chart_type: line
227
- dimensions:
228
- - name: mean
229
- - name: median
230
- - name: "95"
231
- - name: "99"
232
- - name: "100"
233
- - name: riak.search.latency.query
234
- description: Search query latency
235
- unit: "ms"
236
- chart_type: line
237
- dimensions:
238
- - name: median
239
- - name: min
240
- - name: "95"
241
- - name: "99"
242
- - name: "999"
243
- - name: max
244
- - name: riak.search.latency.index
245
- description: Time it takes Search to index a new document
246
- unit: "ms"
247
- chart_type: line
248
- dimensions:
249
- - name: median
250
- - name: min
251
- - name: "95"
252
- - name: "99"
253
- - name: "999"
254
- - name: max
255
- - name: riak.consistent.latency.get
256
- description: Strongly consistent read latency
257
- unit: "ms"
258
- chart_type: line
259
- dimensions:
260
- - name: mean
261
- - name: median
262
- - name: "95"
263
- - name: "99"
264
- - name: "100"
265
- - name: riak.consistent.latency.put
266
- description: Strongly consistent write latency
267
- unit: "ms"
268
- chart_type: line
269
- dimensions:
270
- - name: mean
271
- - name: median
272
- - name: "95"
273
- - name: "99"
274
- - name: "100"
275
- - name: riak.vm
276
- description: Total processes running in the Erlang VM
277
- unit: "total"
278
- chart_type: line
279
- dimensions:
280
- - name: processes
281
- - name: riak.vm.memory.processes
282
- description: Memory allocated & used by Erlang processes
283
- unit: "MB"
284
- chart_type: line
285
- dimensions:
286
- - name: allocated
287
- - name: used
288
- - name: riak.kv.siblings_encountered.get
289
- description: Number of siblings encountered during GET operations by this node during the past minute
290
- unit: "siblings"
291
- chart_type: line
292
- dimensions:
293
- - name: mean
294
- - name: median
295
- - name: "95"
296
- - name: "99"
297
- - name: "100"
298
- - name: riak.kv.objsize.get
299
- description: Object size encountered by this node during the past minute
300
- unit: "KB"
301
- chart_type: line
302
- dimensions:
303
- - name: mean
304
- - name: median
305
- - name: "95"
306
- - name: "99"
307
- - name: "100"
308
- - name: riak.search.vnodeq_size
309
- description: Number of unprocessed messages in the vnode message queues of Search on this node in the past minute
310
- unit: "messages"
311
- chart_type: line
312
- dimensions:
313
- - name: mean
314
- - name: median
315
- - name: "95"
316
- - name: "99"
317
- - name: "100"
318
- - name: riak.search.index
319
- description: Number of document index errors encountered by Search
320
- unit: "errors"
321
- chart_type: line
322
- dimensions:
323
- - name: errors
324
- - name: riak.core.protobuf_connections
325
- description: Protocol buffer connections by status
326
- unit: "connections"
327
- chart_type: line
328
- dimensions:
329
- - name: active
330
- - name: riak.core.repairs
331
- description: Number of repair operations this node has coordinated
332
- unit: "repairs"
333
- chart_type: line
334
- dimensions:
335
- - name: read
336
- - name: riak.core.fsm_active
337
- description: Active finite state machines by kind
338
- unit: "fsms"
339
- chart_type: line
340
- dimensions:
341
- - name: get
342
- - name: put
343
- - name: secondary index
344
- - name: list keys
345
- - name: riak.core.fsm_rejected
346
- description: Finite state machines being rejected by Sidejobs overload protection
347
- unit: "fsms"
348
- chart_type: line
349
- dimensions:
350
- - name: get
351
- - name: put
352
- - name: riak.search.index
353
- description: Number of writes to Search failed due to bad data format by reason
354
- unit: "writes"
355
- chart_type: line
356
- dimensions:
357
- - name: bad_entry
358
- - name: extract_fail
src/collectors/python.d.plugin/riakkv/riakkv.chart.py
deleted
-334
@@ -1,334 +0,0 @@
1
-# -*- coding: utf-8 -*-
2
-# Description: riak netdata python.d module
3
-#
4
-# See also:
5
-# https://docs.riak.com/riak/kv/latest/using/reference/statistics-monitoring/index.html
6
-
7
-from json import loads
8
-
9
-from bases.FrameworkServices.UrlService import UrlService
10
-
11
-# Riak updates the metrics at the /stats endpoint every 1 second.
12
-# If we use `update_every = 1` here, that means we might get weird jitter in the graph,
13
-# so the default is set to 2 seconds to prevent it.
14
-update_every = 2
15
-
16
-# charts order (can be overridden if you want less charts, or different order)
17
-ORDER = [
18
- # Throughput metrics
19
- # https://docs.riak.com/riak/kv/latest/using/reference/statistics-monitoring/index.html#throughput-metrics
20
- # Collected in totals.
21
- "kv.node_operations", # K/V node operations.
22
- "dt.vnode_updates", # Data type vnode updates.
23
- "search.queries", # Search queries on the node.
24
- "search.documents", # Documents indexed by Search.
25
- "consistent.operations", # Consistent node operations.
26
-
27
- # Latency metrics
28
- # https://docs.riak.com/riak/kv/latest/using/reference/statistics-monitoring/index.html#throughput-metrics
29
- # Collected for the past minute in milliseconds,
30
- # returned from riak in microseconds.
31
- "kv.latency.get", # K/V GET FSM traversal latency.
32
- "kv.latency.put", # K/V PUT FSM traversal latency.
33
- "dt.latency.counter", # Update Counter Data type latency.
34
- "dt.latency.set", # Update Set Data type latency.
35
- "dt.latency.map", # Update Map Data type latency.
36
- "search.latency.query", # Search query latency.
37
- "search.latency.index", # Time it takes for search to index a new document.
38
- "consistent.latency.get", # Strong consistent read latency.
39
- "consistent.latency.put", # Strong consistent write latency.
40
-
41
- # Erlang resource usage metrics
42
- # https://docs.riak.com/riak/kv/latest/using/reference/statistics-monitoring/index.html#erlang-resource-usage-metrics
43
- # Processes collected as a gauge,
44
- # memory collected as Megabytes, returned as bytes from Riak.
45
- "vm.processes", # Number of processes currently running in the Erlang VM.
46
- "vm.memory.processes", # Total amount of memory allocated & used for Erlang processes.
47
-
48
- # General Riak Load / Health metrics
49
- # https://docs.riak.com/riak/kv/latest/using/reference/statistics-monitoring/index.html#general-riak-load-health-metrics
50
- # The following are collected by Riak over the past minute:
51
- "kv.siblings_encountered.get", # Siblings encountered during GET operations by this node.
52
- "kv.objsize.get", # Object size encountered by this node.
53
- "search.vnodeq_size", # Number of unprocessed messages in the vnode message queues (Search).
54
- # The following are calculated in total, or as gauges:
55
- "search.index_errors", # Errors of the search subsystem while indexing documents.
56
- "core.pbc", # Number of currently active protocol buffer connections.
57
- "core.repairs", # Total read repair operations coordinated by this node.
58
- "core.fsm_active", # Active finite state machines by kind.
59
- "core.fsm_rejected", # Rejected finite state machines by kind.
60
-
61
- # General Riak Search Load / Health metrics
62
- # https://docs.riak.com/riak/kv/latest/using/reference/statistics-monitoring/index.html#general-riak-search-load-health-metrics
63
- # Reported as counters.
64
- "search.errors", # Write and read errors of the Search subsystem.
65
-]
66
-
67
-CHARTS = {
68
- # Throughput metrics
69
- "kv.node_operations": {
70
- "options": [None, "Reads & writes coordinated by this node", "operations/s", "throughput", "riak.kv.throughput",
71
- "line"],
72
- "lines": [
73
- ["node_gets_total", "gets", "incremental"],
74
- ["node_puts_total", "puts", "incremental"]
75
- ]
76
- },
77
- "dt.vnode_updates": {
78
- "options": [None, "Update operations coordinated by local vnodes by data type", "operations/s", "throughput",
79
- "riak.dt.vnode_updates", "line"],
80
- "lines": [
81
- ["vnode_counter_update_total", "counters", "incremental"],
82
- ["vnode_set_update_total", "sets", "incremental"],
83
- ["vnode_map_update_total", "maps", "incremental"],
84
- ]
85
- },
86
- "search.queries": {
87
- "options": [None, "Search queries on the node", "queries/s", "throughput", "riak.search", "line"],
88
- "lines": [
89
- ["search_query_throughput_count", "queries", "incremental"]
90
- ]
91
- },
92
- "search.documents": {
93
- "options": [None, "Documents indexed by search", "documents/s", "throughput", "riak.search.documents", "line"],
94
- "lines": [
95
- ["search_index_throughput_count", "indexed", "incremental"]
96
- ]
97
- },
98
- "consistent.operations": {
99
- "options": [None, "Consistent node operations", "operations/s", "throughput", "riak.consistent.operations",
100
- "line"],
101
- "lines": [
102
- ["consistent_gets_total", "gets", "incremental"],
103
- ["consistent_puts_total", "puts", "incremental"],
104
- ]
105
- },
106
-
107
- # Latency metrics
108
- "kv.latency.get": {
109
- "options": [None, "Time between reception of a client GET request and subsequent response to client", "ms",
110
- "latency", "riak.kv.latency.get", "line"],
111
- "lines": [
112
- ["node_get_fsm_time_mean", "mean", "absolute", 1, 1000],
113
- ["node_get_fsm_time_median", "median", "absolute", 1, 1000],
114
- ["node_get_fsm_time_95", "95", "absolute", 1, 1000],
115
- ["node_get_fsm_time_99", "99", "absolute", 1, 1000],
116
- ["node_get_fsm_time_100", "100", "absolute", 1, 1000],
117
- ]
118
- },
119
- "kv.latency.put": {
120
- "options": [None, "Time between reception of a client PUT request and subsequent response to client", "ms",
121
- "latency", "riak.kv.latency.put", "line"],
122
- "lines": [
123
- ["node_put_fsm_time_mean", "mean", "absolute", 1, 1000],
124
- ["node_put_fsm_time_median", "median", "absolute", 1, 1000],
125
- ["node_put_fsm_time_95", "95", "absolute", 1, 1000],
126
- ["node_put_fsm_time_99", "99", "absolute", 1, 1000],
127
- ["node_put_fsm_time_100", "100", "absolute", 1, 1000],
128
- ]
129
- },
130
- "dt.latency.counter": {
131
- "options": [None, "Time it takes to perform an Update Counter operation", "ms", "latency",
132
- "riak.dt.latency.counter_merge", "line"],
133
- "lines": [
134
- ["object_counter_merge_time_mean", "mean", "absolute", 1, 1000],
135
- ["object_counter_merge_time_median", "median", "absolute", 1, 1000],
136
- ["object_counter_merge_time_95", "95", "absolute", 1, 1000],
137
- ["object_counter_merge_time_99", "99", "absolute", 1, 1000],
138
- ["object_counter_merge_time_100", "100", "absolute", 1, 1000],
139
- ]
140
- },
141
- "dt.latency.set": {
142
- "options": [None, "Time it takes to perform an Update Set operation", "ms", "latency",
143
- "riak.dt.latency.set_merge", "line"],
144
- "lines": [
145
- ["object_set_merge_time_mean", "mean", "absolute", 1, 1000],
146
- ["object_set_merge_time_median", "median", "absolute", 1, 1000],
147
- ["object_set_merge_time_95", "95", "absolute", 1, 1000],
148
- ["object_set_merge_time_99", "99", "absolute", 1, 1000],
149
- ["object_set_merge_time_100", "100", "absolute", 1, 1000],
150
- ]
151
- },
152
- "dt.latency.map": {
153
- "options": [None, "Time it takes to perform an Update Map operation", "ms", "latency",
154
- "riak.dt.latency.map_merge", "line"],
155
- "lines": [
156
- ["object_map_merge_time_mean", "mean", "absolute", 1, 1000],
157
- ["object_map_merge_time_median", "median", "absolute", 1, 1000],
158
- ["object_map_merge_time_95", "95", "absolute", 1, 1000],
159
- ["object_map_merge_time_99", "99", "absolute", 1, 1000],
160
- ["object_map_merge_time_100", "100", "absolute", 1, 1000],
161
- ]
162
- },
163
- "search.latency.query": {
164
- "options": [None, "Search query latency", "ms", "latency", "riak.search.latency.query", "line"],
165
- "lines": [
166
- ["search_query_latency_median", "median", "absolute", 1, 1000],
167
- ["search_query_latency_min", "min", "absolute", 1, 1000],
168
- ["search_query_latency_95", "95", "absolute", 1, 1000],
169
- ["search_query_latency_99", "99", "absolute", 1, 1000],
170
- ["search_query_latency_999", "999", "absolute", 1, 1000],
171
- ["search_query_latency_max", "max", "absolute", 1, 1000],
172
- ]
173
- },
174
- "search.latency.index": {
175
- "options": [None, "Time it takes Search to index a new document", "ms", "latency", "riak.search.latency.index",
176
- "line"],
177
- "lines": [
178
- ["search_index_latency_median", "median", "absolute", 1, 1000],
179
- ["search_index_latency_min", "min", "absolute", 1, 1000],
180
- ["search_index_latency_95", "95", "absolute", 1, 1000],
181
- ["search_index_latency_99", "99", "absolute", 1, 1000],
182
- ["search_index_latency_999", "999", "absolute", 1, 1000],
183
- ["search_index_latency_max", "max", "absolute", 1, 1000],
184
- ]
185
- },
186
-
187
- # Riak Strong Consistency metrics
188
- "consistent.latency.get": {
189
- "options": [None, "Strongly consistent read latency", "ms", "latency", "riak.consistent.latency.get", "line"],
190
- "lines": [
191
- ["consistent_get_time_mean", "mean", "absolute", 1, 1000],
192
- ["consistent_get_time_median", "median", "absolute", 1, 1000],
193
- ["consistent_get_time_95", "95", "absolute", 1, 1000],
194
- ["consistent_get_time_99", "99", "absolute", 1, 1000],
195
- ["consistent_get_time_100", "100", "absolute", 1, 1000],
196
- ]
197
- },
198
- "consistent.latency.put": {
199
- "options": [None, "Strongly consistent write latency", "ms", "latency", "riak.consistent.latency.put", "line"],
200
- "lines": [
201
- ["consistent_put_time_mean", "mean", "absolute", 1, 1000],
202
- ["consistent_put_time_median", "median", "absolute", 1, 1000],
203
- ["consistent_put_time_95", "95", "absolute", 1, 1000],
204
- ["consistent_put_time_99", "99", "absolute", 1, 1000],
205
- ["consistent_put_time_100", "100", "absolute", 1, 1000],
206
- ]
207
- },
208
-
209
- # BEAM metrics
210
- "vm.processes": {
211
- "options": [None, "Total processes running in the Erlang VM", "total", "vm", "riak.vm", "line"],
212
- "lines": [
213
- ["sys_process_count", "processes", "absolute"],
214
- ]
215
- },
216
- "vm.memory.processes": {
217
- "options": [None, "Memory allocated & used by Erlang processes", "MB", "vm", "riak.vm.memory.processes",
218
- "line"],
219
- "lines": [
220
- ["memory_processes", "allocated", "absolute", 1, 1024 * 1024],
221
- ["memory_processes_used", "used", "absolute", 1, 1024 * 1024]
222
- ]
223
- },
224
-
225
- # General Riak Load/Health metrics
226
- "kv.siblings_encountered.get": {
227
- "options": [None, "Number of siblings encountered during GET operations by this node during the past minute",
228
- "siblings", "load", "riak.kv.siblings_encountered.get", "line"],
229
- "lines": [
230
- ["node_get_fsm_siblings_mean", "mean", "absolute"],
231
- ["node_get_fsm_siblings_median", "median", "absolute"],
232
- ["node_get_fsm_siblings_95", "95", "absolute"],
233
- ["node_get_fsm_siblings_99", "99", "absolute"],
234
- ["node_get_fsm_siblings_100", "100", "absolute"],
235
- ]
236
- },
237
- "kv.objsize.get": {
238
- "options": [None, "Object size encountered by this node during the past minute", "KB", "load",
239
- "riak.kv.objsize.get", "line"],
240
- "lines": [
241
- ["node_get_fsm_objsize_mean", "mean", "absolute", 1, 1024],
242
- ["node_get_fsm_objsize_median", "median", "absolute", 1, 1024],
243
- ["node_get_fsm_objsize_95", "95", "absolute", 1, 1024],
244
- ["node_get_fsm_objsize_99", "99", "absolute", 1, 1024],
245
- ["node_get_fsm_objsize_100", "100", "absolute", 1, 1024],
246
- ]
247
- },
248
- "search.vnodeq_size": {
249
- "options": [None,
250
- "Number of unprocessed messages in the vnode message queues of Search on this node in the past minute",
251
- "messages", "load", "riak.search.vnodeq_size", "line"],
252
- "lines": [
253
- ["riak_search_vnodeq_mean", "mean", "absolute"],
254
- ["riak_search_vnodeq_median", "median", "absolute"],
255
- ["riak_search_vnodeq_95", "95", "absolute"],
256
- ["riak_search_vnodeq_99", "99", "absolute"],
257
- ["riak_search_vnodeq_100", "100", "absolute"],
258
- ]
259
- },
260
- "search.index_errors": {
261
- "options": [None, "Number of document index errors encountered by Search", "errors", "load",
262
- "riak.search.index", "line"],
263
- "lines": [
264
- ["search_index_fail_count", "errors", "absolute"]
265
- ]
266
- },
267
- "core.pbc": {
268
- "options": [None, "Protocol buffer connections by status", "connections", "load",
269
- "riak.core.protobuf_connections", "line"],
270
- "lines": [
271
- ["pbc_active", "active", "absolute"],
272
- # ["pbc_connects", "established_pastmin", "absolute"]
273
- ]
274
- },
275
- "core.repairs": {
276
- "options": [None, "Number of repair operations this node has coordinated", "repairs", "load",
277
- "riak.core.repairs", "line"],
278
- "lines": [
279
- ["read_repairs", "read", "absolute"]
280
- ]
281
- },
282
- "core.fsm_active": {
283
- "options": [None, "Active finite state machines by kind", "fsms", "load", "riak.core.fsm_active", "line"],
284
- "lines": [
285
- ["node_get_fsm_active", "get", "absolute"],
286
- ["node_put_fsm_active", "put", "absolute"],
287
- ["index_fsm_active", "secondary index", "absolute"],
288
- ["list_fsm_active", "list keys", "absolute"]
289
- ]
290
- },
291
- "core.fsm_rejected": {
292
- # Writing "Sidejob's" here seems to cause some weird issues: it results in this chart being rendered in
293
- # its own context and additionally, moves the entire Riak graph all the way up to the top of the Netdata
294
- # dashboard for some reason.
295
- "options": [None, "Finite state machines being rejected by Sidejobs overload protection", "fsms", "load",
296
- "riak.core.fsm_rejected", "line"],
297
- "lines": [
298
- ["node_get_fsm_rejected", "get", "absolute"],
299
- ["node_put_fsm_rejected", "put", "absolute"]
300
- ]
301
- },
302
-
303
- # General Riak Search Load / Health metrics
304
- "search.errors": {
305
- "options": [None, "Number of writes to Search failed due to bad data format by reason", "writes", "load",
306
- "riak.search.index", "line"],
307
- "lines": [
308
- ["search_index_bad_entry_count", "bad_entry", "absolute"],
309
- ["search_index_extract_fail_count", "extract_fail", "absolute"],
310
- ]
311
- }
312
-}
313
-
314
-
315
-class Service(UrlService):
316
- def __init__(self, configuration=None, name=None):
317
- UrlService.__init__(self, configuration=configuration, name=name)
318
- self.order = ORDER
319
- self.definitions = CHARTS
320
-
321
- def _get_data(self):
322
- """
323
- Format data received from http request
324
- :return: dict
325
- """
326
- raw = self._get_raw_data()
327
- if not raw:
328
- return None
329
-
330
- try:
331
- return loads(raw)
332
- except (TypeError, ValueError) as err:
333
- self.error(err)
334
- return None
src/collectors/python.d.plugin/riakkv/riakkv.conf
deleted
-68
@@ -1,68 +0,0 @@
1
-# netdata python.d.plugin configuration for riak
2
-#
3
-# This file is in YaML format. Generally the format is:
4
-#
5
-# name: value
6
-#
7
-# There are 2 sections:
8
-# - global variables
9
-# - one or more JOBS
10
-#
11
-# JOBS allow you to collect values from multiple sources.
12
-# Each source will have its own set of charts.
13
-#
14
-# JOB parameters have to be indented (using spaces only, example below).
15
-
16
-# ----------------------------------------------------------------------
17
-# Global Variables
18
-# These variables set the defaults for all JOBs, however each JOB
19
-# may define its own, overriding the defaults.
20
-
21
-# update_every sets the default data collection frequency.
22
-# If unset, the python.d.plugin default is used.
23
-# update_every: 1
24
-
25
-# priority controls the order of charts at the netdata dashboard.
26
-# Lower numbers move the charts towards the top of the page.
27
-# If unset, the default for python.d.plugin is used.
28
-# priority: 60000
29
-
30
-# penalty indicates whether to apply penalty to update_every in case of failures.
31
-# Penalty will increase every 5 failed updates in a row. Maximum penalty is 10 minutes.
32
-# penalty: yes
33
-
34
-# autodetection_retry sets the job re-check interval in seconds.
35
-# The job is not deleted if check fails.
36
-# Attempts to start the job are made once every autodetection_retry.
37
-# This feature is disabled by default.
38
-# autodetection_retry: 0
39
-
40
-# ----------------------------------------------------------------------
41
-# JOBS (data collection sources)
42
-#
43
-# The default JOBS share the same *name*. JOBS with the same name
44
-# are mutually exclusive. Only one of them will be allowed running at
45
-# any time. This allows autodetection to try several alternatives and
46
-# pick the one that works.
47
-#
48
-# Any number of jobs is supported.
49
-#
50
-# All python.d.plugin JOBS (for all its modules) support a set of
51
-# predefined parameters. These are:
52
-#
53
-# job_name:
54
-# name: myname # the JOB's name as it will appear at the
55
-# # dashboard (by default is the job_name)
56
-# # JOBs sharing a name are mutually exclusive
57
-# update_every: 1 # the JOB's data collection frequency
58
-# priority: 60000 # the JOB's order on the dashboard
59
-# penalty: yes # the JOB's penalty
60
-# autodetection_retry: 0 # the JOB's re-check interval in seconds
61
-#
62
-#
63
-# ----------------------------------------------------------------------
64
-# AUTO-DETECTION JOBS
65
-# only one of them will run (they have the same name)
66
-
67
-local:
68
- url : 'http://localhost:8098/stats'