Compare commits

...

65 Commits

Author SHA1 Message Date
kongfei605
71944c64b4 Merge pull request #65 from flashcatcloud/kongfei_develop
fix redis mode compare problem
2022-08-11 15:52:09 +08:00
kongfei
219beae857 fix redis mode compare problem 2022-08-11 15:35:37 +08:00
kongfei605
180552c1cb Merge pull request #63 from flashcatcloud/kongfei_develop
update to 5.10.3
2022-08-11 14:15:25 +08:00
kongfei
436a216b38 update to 5.10.3 2022-08-11 14:10:46 +08:00
kongfei605
005a673cfa Merge pull request #62 from LinkMaq/bugfix-61
fixed(categraf): Empty docker_socket when kubernetes runtime is not d…
2022-08-10 07:10:24 +08:00
kongfei605
055ffb3002 Merge pull request #60 from LinkMaq/bugfix-54
fixed(database): add subPath for my.cnf  #54
2022-08-10 07:05:17 +08:00
LinkMaq
584a00f668 fixed(categraf): Empty docker_socket when kubernetes runtime is not docker 2022-08-10 00:53:16 +08:00
LinkMaq
c697ffa2dc fixed(database): add subPath for my.cnf #54 2022-08-09 23:41:54 +08:00
kongfei605
6e09f7b074 Merge pull request #59 from flashcatcloud/kongfei_develop
v5.10.2
2022-08-08 10:35:42 +08:00
kongfei
b3cc4112db update to v5.10.2 2022-08-08 10:33:34 +08:00
kongfei
67f43473d7 v5.10.2 2022-08-08 10:32:36 +08:00
kongfei605
36588e5e3d Merge pull request #58 from xiaoziv/fix-nserver-hostname
Update deployment.yaml
2022-08-06 20:40:39 +08:00
xiaoziv
93740aa23f Update deployment.yaml
nserver设置多副本时候,指定hostname会导致多副本的hostname相同,导致规则的分配出现问题
2022-08-05 14:34:10 +08:00
kongfei605
6872d2e5fe Merge pull request #57 from flashcatcloud/kongfei_develop
upgrade v5.10.1
2022-08-03 20:39:27 +08:00
kongfei
fa2abf8f33 upgrade v5.10.1 2022-08-03 20:39:02 +08:00
kongfei605
6ddb9be9a0 Merge pull request #55 from flashcatcloud/kongfei_develop
v5.9.8
2022-07-29 06:26:30 +08:00
kongfei
8fe0978add v5.9.8 2022-07-29 06:25:57 +08:00
kongfei605
8603f7d667 Merge pull request #53 from flashcatcloud/kongfei_develop
v5.9.7
2022-07-27 16:14:17 +08:00
kongfei
d7bb2eb5ea v5.9.7 2022-07-27 16:04:38 +08:00
kongfei605
3464091f5b Merge pull request #52 from flashcatcloud/kongfei_develop
fix dsn only support internal service port
2022-07-25 06:55:45 +08:00
kongfei
5348a4ab1f fix dsn only support internal service port 2022-07-25 06:54:28 +08:00
kongfei605
80c36d00d1 Merge pull request #51 from xiaoziv/fix-database-bug
Fix database url bug
2022-07-25 06:47:44 +08:00
xiaoziv
8b68709276 Update daemonset.yaml 2022-07-22 21:42:37 +08:00
xiaoziv
90acdccee9 Update conf-cm.yaml 2022-07-22 21:39:13 +08:00
xiaoziv
0a14c37633 Update conf-cm.yaml 2022-07-22 21:37:29 +08:00
kongfei605
ee40d6f865 Merge pull request #48 from xiaoziv/pull-secret-support
support imagePullSecrets for n9e & prometheus
2022-07-20 20:29:05 +08:00
xiaoziv
c0e0d614bc Update deployment.yaml
remove nginx additional imagePullSecrets config
2022-07-20 20:06:23 +08:00
kongfei605
6a4bc21e6e Merge pull request #49 from xiaoziv/sql-add-recording-rule-table
Update a-n9e.sql
2022-07-20 19:25:43 +08:00
xiaoziv
27cfa3dd62 Update a-n9e.sql
add recording rule
2022-07-20 18:49:15 +08:00
xiaoziv
07ee7ed200 support imagePullSecrets for n9e & prometheus 2022-07-20 16:20:16 +08:00
kongfei605
47bad75a42 Merge pull request #46 from flashcatcloud/kongfei_develop
v5.9.6
2022-07-09 15:51:57 +08:00
kongfei
ca4877f1a2 v5.9.6 2022-07-09 15:51:03 +08:00
kongfei605
5aa37e029d Merge pull request #45 from flashcatcloud/kongfei_develop
pull n9e image from flashcatcloud
2022-07-06 18:16:53 +08:00
kongfei
253467398f pull n9e image from flashcatcloud 2022-07-06 18:16:07 +08:00
kongfei605
c60ccc4b94 Merge pull request #42 from flashcatcloud/kongfei_develop
update chart version
2022-07-06 08:53:13 +08:00
kongfei
52fef28d3e update chart version 2022-07-06 08:52:33 +08:00
kongfei605
2760d44424 Merge pull request #41 from flashcatcloud/kongfei_develop
v5.9.4
2022-07-06 07:25:03 +08:00
kongfei
4c4119a3f7 update categraf version 2022-07-06 07:19:44 +08:00
kongfei
f9f127e475 delete notify.py 2022-07-06 07:16:39 +08:00
kongfei
881da87a75 v5.9.4 2022-07-05 22:41:51 +08:00
kongfei
0df45b1fa3 correct input.prometheus path 2022-07-01 17:07:10 +08:00
kongfei
614e5b989d collect kubelet metrics 2022-07-01 16:55:00 +08:00
kongfei605
f20a2c3aa6 Merge pull request #39 from flashcatcloud/kongfei_develop
[fix] archives template lost _helper.tpl
2022-06-30 19:17:09 +08:00
kongfei
d2caf4e55f [fix] archives template lost _helper.tpl 2022-06-30 19:05:51 +08:00
kongfei605
f0d5623d46 Merge pull request #37 from flashcatcloud/kongfei_develop
v5.9.3 release
2022-06-28 08:59:57 +08:00
kongfei
e4476aed06 fix typo 2022-06-28 08:49:28 +08:00
kongfei
caec3c387b delete docker action 2022-06-28 08:46:20 +08:00
kongfei
0fbe0db579 release workflow 2022-06-28 08:41:24 +08:00
kongfei
fb69493fe9 v5.9.3 2022-06-28 06:56:16 +08:00
kongfei605
69f72f29f4 Merge pull request #36 from e421083458/master
update prometheus image url from values
2022-06-28 06:55:28 +08:00
e421083458
b059b12b36 update prometheus image url from values 2022-06-28 00:34:09 +08:00
e421083458
5f6e4ee61e update prometheus image url from values 2022-06-27 21:35:41 +08:00
kongfei605
1a0572891f Merge pull request #33 from flashcatcloud/kongfei_develop
fix prometheus external host
2022-06-14 23:29:36 +08:00
kongfei
e2db53b436 update categraf version 2022-06-14 23:28:24 +08:00
kongfei
cddde9190a fix prometheus host info 2022-06-14 23:22:53 +08:00
kongfei605
be7c08a6d5 Merge pull request #32 from flashcatcloud/kongfei_develop
support kubelet plugin
2022-06-14 21:40:55 +08:00
kongfei
9f0d62b031 support kubelet plugin 2022-06-14 17:29:53 +08:00
kongfei605
a11b6ab032 Merge pull request #31 from flashcatcloud/kongfei_develop
Kongfei develop
2022-06-13 15:01:24 +08:00
kongfei
32233d6bf2 update categraf image to v0.1.3 2022-06-13 14:48:35 +08:00
kongfei
4a0b5bc18e categraf use hostNetwork and ClusterFirstWithHostNet 2022-06-13 14:45:57 +08:00
kongfei
dc671dac0f fix volume mounts 2022-06-13 14:23:15 +08:00
kongfei
775adb4f4d add categraf 2022-06-13 14:19:54 +08:00
kongfei
904fbe4d14 add categraf 2022-06-13 14:16:42 +08:00
kongfei
373d778f14 test categraf cm 2022-06-13 09:51:33 +08:00
kongfei605
1532275fb8 Merge pull request #27 from flashcatcloud/kongfei_develop
v5.8.0
2022-05-23 09:58:52 +08:00
72 changed files with 6496 additions and 516 deletions

28
.github/workflows/release.yaml vendored Normal file
View File

@@ -0,0 +1,28 @@
name: Release
on:
push:
tags:
- 'v*'
env:
GO_VERSION: 1.18
jobs:
goreleaser:
runs-on: ubuntu-latest
steps:
- name: Checkout Source Code
uses: actions/checkout@v3
with:
fetch-depth: 0
- name: Setup Go Environment
uses: actions/setup-go@v3
with:
go-version: ${{ env.GO_VERSION }}
- name: Run GoReleaser
uses: goreleaser/goreleaser-action@v3
with:
version: latest
args: release --rm-dist
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

39
.goreleaser.yaml Normal file
View File

@@ -0,0 +1,39 @@
snapshot:
name_template: '{{ .Tag }}'
checksum:
name_template: 'checksums.txt'
changelog:
skip: true
builds:
- skip: true
archives:
- id: n9e-helm
format: tar.gz
format_overrides:
- goos: windows
format: zip
name_template: "{{ .ProjectName }}-v{{ .Version }}"
wrap_in_directory: true
meta: true
files:
- alerts/*
- categraf/*
- dashboards/*
- metrics/*
- scripts/*
- templates/*
- tpl/*
- Chart.yaml
- LICENSE
- n9e-icon.png
- README.md
- README-CN.md
- values.yaml
release:
github:
owner: flashcatcloud
name: n9e-helm
name_template: "v{{ .Version }}"

View File

@@ -27,7 +27,7 @@ sources:
maintainers:
- email: contact-us@flashcat.cloud
name: flashcatcloud
version: 0.1.1
version: 0.1.3
apiVersion: v1
appVersion: 5.8.0
appVersion: 5.9.6
icon: https://raw.githubusercontent.com/flashcatcloud/n9e-helm/master/n9e-icon.png

View File

@@ -0,0 +1,30 @@
[
{
"name": "HTTP地址探测失败",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "http_response_result_code != 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
}
]

View File

@@ -1,58 +1,72 @@
[
{
"name": "数据有丢失风险-同步副本数小于3",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "sum(kafka_topic_partition_in_sync_replica) by (topic) < 3",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "消费能力不足-积压消息数超过50条",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "sum(kafka_topic_partition_current_offset{instance=\"$instance\"}) by (topic) - sum(kafka_consumergroup_current_offset{instance=\"$instance\"}) by (topic) ",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
}
]
{
"name": "数据有丢失风险-副本数小于3",
"note": "",
"prod": "",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "sum(kafka_topic_partition_in_sync_replica) by (topic) < 3",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"service=kafka"
]
},
{
"name": "消费能力不足-延迟超过5分钟",
"note": "",
"prod": "",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "kafka_consumer_lag_millis / 1000 > 300",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"service=kafka"
]
}
]

View File

@@ -0,0 +1,243 @@
[
{
"name": "监控对象失联",
"note": "",
"severity": 1,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "max_over_time(target_up[130s]) == 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"notify_recovered": 1,
"notify_channels": [
"email",
"dingtalk",
"wecom"
],
"notify_repeat_step": 60,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "机器负载-CPU较高请关注",
"note": "",
"severity": 3,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "cpu_usage_idle{cpu=\"cpu-total\"} < 25",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"notify_recovered": 1,
"notify_channels": [
"email",
"dingtalk",
"wecom"
],
"notify_repeat_step": 60,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "机器负载-内存较高,请关注",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "mem_available_percent < 25",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"notify_recovered": 1,
"notify_channels": [
"email",
"dingtalk",
"wecom"
],
"notify_repeat_step": 60,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "硬盘-IO有点繁忙",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "rate(diskio_io_time[1m])/10 > 99",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"notify_recovered": 1,
"notify_channels": [
"email",
"dingtalk",
"wecom"
],
"notify_repeat_step": 60,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "硬盘-预计再有4小时写满",
"note": "",
"severity": 1,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "predict_linear(disk_free[1h], 4*3600) < 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"notify_recovered": 1,
"notify_channels": [
"email",
"dingtalk",
"wecom"
],
"notify_repeat_step": 60,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "网卡-入向有丢包",
"note": "",
"severity": 3,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "increase(net_drop_in[1m]) > 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"notify_recovered": 1,
"notify_channels": [
"email",
"dingtalk",
"wecom"
],
"notify_repeat_step": 60,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "网卡-出向有丢包",
"note": "",
"severity": 3,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "increase(net_drop_out[1m]) > 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"notify_recovered": 1,
"notify_channels": [
"email",
"dingtalk",
"wecom"
],
"notify_repeat_step": 60,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "网络连接-TME_WAIT数量超过2万",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "netstat_tcp_time_wait > 20000",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"notify_recovered": 1,
"notify_channels": [
"email",
"dingtalk",
"wecom"
],
"notify_repeat_step": 60,
"callbacks": [],
"runbook_url": "",
"append_tags": []
}
]

View File

@@ -0,0 +1,302 @@
[
{
"name": "MysqlInnodbLogWaits",
"note": "MySQL innodb log writes stalling",
"severity": 2,
"disabled": 0,
"prom_for_duration": 0,
"prom_ql": "rate(mysql_global_status_innodb_log_waits[15m]) > 10",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=MysqlInnodbLogWaits"
]
},
{
"name": "MysqlSlaveIoThreadNotRunning",
"note": "MySQL Slave IO thread not running",
"severity": 1,
"disabled": 0,
"prom_for_duration": 0,
"prom_ql": "mysql_slave_status_master_server_id > 0 and ON (instance) mysql_slave_status_slave_io_running == 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=MysqlSlaveIoThreadNotRunning"
]
},
{
"name": "MysqlSlaveReplicationLag",
"note": "",
"severity": 1,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "mysql_slave_status_master_server_id > 0 and ON (instance) (mysql_slave_status_seconds_behind_master - mysql_slave_status_sql_delay) > 30",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=MysqlSlaveReplicationLag"
]
},
{
"name": "MysqlSlaveSqlThreadNotRunning",
"note": "MySQL Slave SQL thread not running",
"severity": 1,
"disabled": 0,
"prom_for_duration": 0,
"prom_ql": "mysql_slave_status_master_server_id > 0 and ON (instance) mysql_slave_status_slave_sql_running == 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=MysqlSlaveSqlThreadNotRunning"
]
},
{
"name": "Mysql刚刚有重启请注意",
"note": "MySQL has just been restarted, less than one minute ago",
"severity": 3,
"disabled": 0,
"prom_for_duration": 0,
"prom_ql": "mysql_global_status_uptime < 60",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=MysqlRestarted"
]
},
{
"name": "Mysql实例挂了",
"note": "",
"severity": 1,
"disabled": 0,
"prom_for_duration": 0,
"prom_ql": "mysql_up == 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=MysqlDown"
]
},
{
"name": "Mysql打开了很多文件句柄请注意",
"note": "More than 80% of MySQL files open",
"severity": 2,
"disabled": 0,
"prom_for_duration": 120,
"prom_ql": "avg by (instance) (mysql_global_status_open_files) / avg by (instance)(mysql_global_variables_open_files_limit) * 100 > 80",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=MysqlHighOpenFiles"
]
},
{
"name": "Mysql最近一分钟有慢查询出现",
"note": "MySQL server mysql has some new slow query",
"severity": 2,
"disabled": 0,
"prom_for_duration": 120,
"prom_ql": "increase(mysql_global_status_slow_queries[1m]) > 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=MysqlSlowQueries"
]
},
{
"name": "Mysql有超过60%的连接是running状态",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 120,
"prom_ql": "avg by (instance) (mysql_global_status_threads_running) / avg by (instance) (mysql_global_variables_max_connections) * 100 > 60",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=MysqlHighThreadsRunning"
]
},
{
"name": "Mysql连接数已超过80%",
"note": "More than 80% of MySQL connections are in use",
"severity": 2,
"disabled": 0,
"prom_for_duration": 120,
"prom_ql": "avg by (instance) (mysql_global_status_threads_connected) / avg by (instance) (mysql_global_variables_max_connections) * 100 > 80",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=MysqlTooManyConnections"
]
}
]

View File

@@ -0,0 +1,30 @@
[
{
"name": "网络地址探活失败",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "net_response_result_code != 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
}
]

View File

@@ -0,0 +1,30 @@
[
{
"name": "NTP时间偏移太大",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "ntp_offset_ms > 1000 or ntp_offset_ms < -1000",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
}
]

View File

@@ -0,0 +1,30 @@
[
{
"name": "PING地址探测失败",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "ping_result_code != 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
}
]

View File

@@ -0,0 +1,62 @@
[
{
"name": "进程监控-有进程数为0某进程可能挂了",
"note": "",
"severity": 1,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "procstat_lookup_count == 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"notify_recovered": 1,
"notify_channels": [
"email",
"dingtalk",
"wecom"
],
"notify_repeat_step": 60,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "进程监控-进程句柄限制过小",
"note": "",
"severity": 3,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "procstat_rlimit_num_fds_soft < 2048",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"notify_recovered": 1,
"notify_channels": [
"email",
"dingtalk",
"wecom"
],
"notify_repeat_step": 60,
"callbacks": [],
"runbook_url": "",
"append_tags": []
}
]

View File

@@ -0,0 +1,182 @@
[
{
"name": "Redis Ping 延迟高大于100毫秒",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "redis_ping_use_seconds > 0.1",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=HighPingLatency"
]
},
{
"name": "Redis内存使用率较高",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "redis_maxmemory > 0 and (redis_used_memory / redis_maxmemory) > 0.85",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=RedisHighMemoryUsage"
]
},
{
"name": "Redis出现拒绝连接",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 0,
"prom_ql": "(rate(redis_rejected_connections[5m])) > 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=RedisRejectedConnHigh"
]
},
{
"name": "Redis刚刚有重启请注意",
"note": "",
"severity": 3,
"disabled": 0,
"prom_for_duration": 0,
"prom_ql": "redis_uptime_in_seconds < 600",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=RedisLowUptime"
]
},
{
"name": "Redis较低的命中率",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "rate(redis_keyspace_hits[5m])\n/\n(rate(redis_keyspace_misses[5m]) + rate(redis_keyspace_hits[5m]))\n< 0.9",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=RedisLowHitRatio"
]
},
{
"name": "Redis驱逐率较高",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "(sum(rate(redis_evicted_keys[5m])) / sum(redis_keyspace_keys)) > 0.1",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": [
"alertname=RedisHighKeysEvictionRatio"
]
}
]

45
categraf/conf/config.toml Normal file
View File

@@ -0,0 +1,45 @@
[global]
# whether print configs
print_configs = false
# add label(agent_hostname) to series
# "" -> auto detect hostname
# "xx" -> use specified string xx
# "$hostname" -> auto detect hostname
# "$ip" -> auto detect ip
# "$hostname-$ip" -> auto detect hostname and ip to replace the vars
hostname = "$HOSTNAME"
# will not add label(agent_hostname) if true
omit_hostname = false
# s | ms
precision = "ms"
# global collect interval
interval = 15
[global.labels]
source="categraf"
# region = "shanghai"
# env = "localhost"
[writer_opt]
# default: 2000
batch = 2000
# channel(as queue) size
chan_size = 10000
[[writers]]
url = "http://nightingale-nserver/prometheus/v1/write"
# Basic auth username
basic_auth_user = ""
# Basic auth password
basic_auth_pass = ""
# timeout settings, unit: ms
timeout = 5000
dial_timeout = 2500
max_idle_conns_per_host = 100

View File

@@ -0,0 +1,5 @@
# # collect interval
# interval = 15
# # whether collect per cpu
# collect_per_cpu = false

View File

@@ -0,0 +1,11 @@
# # collect interval
# interval = 15
# # By default stats will be gathered for all mount points.
# # Set mount_points will restrict the stats to only the specified mount points.
# mount_points = ["/"]
# Ignore mount points by filesystem type.
ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]
ignore_mount_points = ["/boot"]

View File

@@ -0,0 +1,6 @@
# # collect interval
# interval = 15
# # By default, categraf will gather stats for all devices including disk partitions.
# # Setting devices will restrict the stats to the specified devices.
# devices = ["sda", "sdb", "vd*"]

View File

@@ -0,0 +1,63 @@
# # collect interval
# interval = 15
[[instances]]
# # append some labels for series
# labels = { region="cloud", product="n9e" }
# # interval = global.interval * interval_times
# interval_times = 1
## Docker Endpoint
## To use TCP, set endpoint = "tcp://[ip]:[port]"
## To use environment variables (ie, docker-machine), set endpoint = "ENV"
endpoint = "unix:///var/run/docker.sock"
## Set to true to collect Swarm metrics(desired_replicas, running_replicas)
gather_services = false
gather_extend_memstats = false
container_id_label_enable = true
container_id_label_short_style = true
## Containers to include and exclude. Globs accepted.
## Note that an empty array for both will include all containers
container_name_include = []
container_name_exclude = []
## Container states to include and exclude. Globs accepted.
## When empty only containers in the "running" state will be captured.
## example: container_state_include = ["created", "restarting", "running", "removing", "paused", "exited", "dead"]
## example: container_state_exclude = ["created", "restarting", "running", "removing", "paused", "exited", "dead"]
# container_state_include = []
# container_state_exclude = []
## Timeout for docker list, info, and stats commands
timeout = "5s"
## Specifies for which classes a per-device metric should be issued
## Possible values are 'cpu' (cpu0, cpu1, ...), 'blkio' (8:0, 8:1, ...) and 'network' (eth0, eth1, ...)
## Please note that this setting has no effect if 'perdevice' is set to 'true'
perdevice_include = []
## Specifies for which classes a total metric should be issued. Total is an aggregated of the 'perdevice' values.
## Possible values are 'cpu', 'blkio' and 'network'
## Total 'cpu' is reported directly by Docker daemon, and 'network' and 'blkio' totals are aggregated by this plugin.
## Please note that this setting has no effect if 'total' is set to 'false'
total_include = ["cpu", "blkio", "network"]
## Which environment variables should we use as a tag
##tag_env = ["JAVA_HOME", "HEAP_SIZE"]
## docker labels to include and exclude as tags. Globs accepted.
## Note that an empty array for both will include all labels as tags
docker_label_include = []
docker_label_exclude = ["annotation*", "io.kubernetes*", "*description*", "*maintainer*", "*hash", "*author*"]
## Optional TLS Config
# use_tls = false
# tls_ca = "/etc/telegraf/ca.pem"
# tls_cert = "/etc/telegraf/cert.pem"
# tls_key = "/etc/telegraf/key.pem"
## Use TLS but skip chain & host verification
# insecure_skip_verify = false

View File

@@ -0,0 +1,2 @@
# # collect interval
# interval = 15

View File

@@ -0,0 +1,124 @@
# # collect interval
# interval = 15
# file: /proc/vmstat
[white_list]
oom_kill = 1
nr_free_pages = 0
nr_alloc_batch = 0
nr_inactive_anon = 0
nr_active_anon = 0
nr_inactive_file = 0
nr_active_file = 0
nr_unevictable = 0
nr_mlock = 0
nr_anon_pages = 0
nr_mapped = 0
nr_file_pages = 0
nr_dirty = 0
nr_writeback = 0
nr_slab_reclaimable = 0
nr_slab_unreclaimable = 0
nr_page_table_pages = 0
nr_kernel_stack = 0
nr_unstable = 0
nr_bounce = 0
nr_vmscan_write = 0
nr_vmscan_immediate_reclaim = 0
nr_writeback_temp = 0
nr_isolated_anon = 0
nr_isolated_file = 0
nr_shmem = 0
nr_dirtied = 0
nr_written = 0
numa_hit = 0
numa_miss = 0
numa_foreign = 0
numa_interleave = 0
numa_local = 0
numa_other = 0
workingset_refault = 0
workingset_activate = 0
workingset_nodereclaim = 0
nr_anon_transparent_hugepages = 0
nr_free_cma = 0
nr_dirty_threshold = 0
nr_dirty_background_threshold = 0
pgpgin = 0
pgpgout = 0
pswpin = 0
pswpout = 0
pgalloc_dma = 0
pgalloc_dma32 = 0
pgalloc_normal = 0
pgalloc_movable = 0
pgfree = 0
pgactivate = 0
pgdeactivate = 0
pgfault = 0
pgmajfault = 0
pglazyfreed = 0
pgrefill_dma = 0
pgrefill_dma32 = 0
pgrefill_normal = 0
pgrefill_movable = 0
pgsteal_kswapd_dma = 0
pgsteal_kswapd_dma32 = 0
pgsteal_kswapd_normal = 0
pgsteal_kswapd_movable = 0
pgsteal_direct_dma = 0
pgsteal_direct_dma32 = 0
pgsteal_direct_normal = 0
pgsteal_direct_movable = 0
pgscan_kswapd_dma = 0
pgscan_kswapd_dma32 = 0
pgscan_kswapd_normal = 0
pgscan_kswapd_movable = 0
pgscan_direct_dma = 0
pgscan_direct_dma32 = 0
pgscan_direct_normal = 0
pgscan_direct_movable = 0
pgscan_direct_throttle = 0
zone_reclaim_failed = 0
pginodesteal = 0
slabs_scanned = 0
kswapd_inodesteal = 0
kswapd_low_wmark_hit_quickly = 0
kswapd_high_wmark_hit_quickly = 0
pageoutrun = 0
allocstall = 0
pgrotated = 0
drop_pagecache = 0
drop_slab = 0
numa_pte_updates = 0
numa_huge_pte_updates = 0
numa_hint_faults = 0
numa_hint_faults_local = 0
numa_pages_migrated = 0
pgmigrate_success = 0
pgmigrate_fail = 0
compact_migrate_scanned = 0
compact_free_scanned = 0
compact_isolated = 0
compact_stall = 0
compact_fail = 0
compact_success = 0
htlb_buddy_alloc_success = 0
htlb_buddy_alloc_fail = 0
unevictable_pgs_culled = 0
unevictable_pgs_scanned = 0
unevictable_pgs_rescued = 0
unevictable_pgs_mlocked = 0
unevictable_pgs_munlocked = 0
unevictable_pgs_cleared = 0
unevictable_pgs_stranded = 0
thp_fault_alloc = 0
thp_fault_fallback = 0
thp_collapse_alloc = 0
thp_collapse_alloc_failed = 0
thp_split = 0
thp_zero_page_alloc = 0
thp_zero_page_alloc_failed = 0
balloon_inflate = 0
balloon_deflate = 0
balloon_migrate = 0

View File

@@ -0,0 +1,41 @@
# # collect interval
# interval = 15
[[instances]]
# # append some labels for series
# labels = { region="cloud", product="n9e" }
# # interval = global.interval * interval_times
# interval_times = 1
# URL for the kubelet
url = "https://127.0.0.1:10250"
gather_system_container_metrics = true
gather_node_metrics = true
gather_pod_container_metrics = true
gather_pod_volume_metrics = true
gather_pod_network_metrics = true
## Use bearer token for authorization. ('bearer_token' takes priority)
## If both of these are empty, we'll use the default serviceaccount:
## at: /var/run/secrets/kubernetes.io/serviceaccount/token
# bearer_token = "/path/to/bearer/token"
## OR
# bearer_token_string = "abc_123"
## Pod labels to be added as tags. An empty array for both include and
## exclude will include all labels.
# label_include = []
# label_exclude = ["*"]
## Set response_timeout (default 5 seconds)
# response_timeout = "5s"
## Optional TLS Config
use_tls = true
# tls_ca = "/etc/categraf/ca.pem"
# tls_cert = "/etc/categraf/cert.pem"
# tls_key = "/etc/categraf/key.pem"
## Use TLS but skip chain & host verification
insecure_skip_verify = true

View File

@@ -0,0 +1,2 @@
# # collect interval
# interval = 15

View File

@@ -0,0 +1,5 @@
# # collect interval
# interval = 15
# # whether collect platform specified metrics
collect_platform_fields = true

View File

@@ -0,0 +1,8 @@
# # collect interval
# interval = 15
# # whether collect protocol stats on Linux
# collect_protocol_stats = false
# # setting interfaces will tell categraf to gather these explicit interfaces
# interfaces = ["eth0"]

View File

@@ -0,0 +1,2 @@
# # collect interval
# interval = 15

View File

@@ -0,0 +1,8 @@
# # collect interval
# interval = 15
# # force use ps command to gather
# force_ps = false
# # force use /proc to gather
# force_proc = false

View File

@@ -0,0 +1,31 @@
# # collect interval
# interval = 15
# [[instances]]
# # executable name (ie, pgrep <search_exec_substring>)
# search_exec_substring = "nginx"
# # pattern as argument for pgrep (ie, pgrep -f <search_cmdline_substring>)
# search_cmdline_substring = "n9e server"
# # windows service name
# search_win_service = ""
# # append some labels for series
# labels = { region="cloud", product="n9e" }
# # interval = global.interval * interval_times
# interval_times = 1
# # mode to use when calculating CPU usage. can be one of 'solaris' or 'irix'
# mode = "irix"
# gather_more_metrics = [
# "threads",
# "fd",
# "io",
# "uptime",
# "cpu",
# "mem",
# "limit"
# ]

View File

@@ -0,0 +1,13 @@
# # collect interval
# interval = 15
[[instances]]
# kubelete metrics & cadvisor
urls = ["https://127.0.0.1:10250/metrics", "https://127.0.0.1:10250/metrics/cadvisor"]
bearer_token_file = "/var/run/secrets/kubernetes.io/serviceaccount/token"
use_tls = true
insecure_skip_verify = true
url_label_key = "instance"
url_label_value = "{{.Host}}"
# if you use dashboards, do not delete this label
labels = {job="categraf"}

View File

@@ -0,0 +1,5 @@
# # collect interval
# interval = 15
# # whether collect metric: system_n_users
# collect_user_number = false

35
categraf/conf/logs.toml Normal file
View File

@@ -0,0 +1,35 @@
[logs]
## key 占位符
api_key = "ef4ahfbwzwwtlwfpbertgq1i6mq0ab1q"
## 是否开启日志采集
enable = false
## 接受日志的server地址
send_to = "127.0.0.1:17878"
## 发送日志的协议 http/tcp
send_type = "http"
## 是否压缩发送
use_compress = false
## 是否采用ssl
send_with_tls = false
##
batch_wait = 5
## 日志offset信息保存目录
run_path = "/opt/categraf/run"
## 最多同时采集多少个日志文件
open_files_limit = 100
## 定期扫描目录下是否有新增日志
scan_period = 10
##
frame_size = 10
##
collect_container_all = true
## 全局的处理规则
[[logs.Processing_rules]]
## 单个日志采集配置
[[logs.items]]
## file/journald
type = "file"
## type=file时 path必填type=journald时 port必填
path = "/opt/tomcat/logs/*.txt"
source = "tomcat"
service = "my_service"

View File

@@ -0,0 +1,19 @@
[
{
"name": "HTTP探测",
"tags": "",
"configs": "",
"chart_groups": [
{
"name": "Default chart group",
"weight": 0,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"max(http_response_result_code) by (target)\",\"legend\":\"UP?\"},{\"expr\":\"max(http_response_response_code) by (target)\",\"refId\":\"B\",\"legend\":\"status code\"},{\"expr\":\"max(http_response_response_time) by (target)\",\"refId\":\"C\",\"legend\":\"latency(s)\"},{\"expr\":\"max(http_response_cert_expire_timestamp) by (target) - time()\",\"refId\":\"D\",\"legend\":\"cert expire\"}],\"name\":\"URL Details\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"labelValuesToRows\",\"aggrDimension\":\"target\"},\"options\":{\"valueMappings\":[],\"standardOptions\":{}},\"overrides\":[{\"properties\":{\"valueMappings\":[{\"type\":\"special\",\"match\":{\"special\":0},\"result\":{\"text\":\"UP\",\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"special\":1,\"from\":1},\"result\":{\"text\":\"DOWN\",\"color\":\"#e90f0f\"}}],\"standardOptions\":{}},\"matcher\":{\"value\":\"A\"}},{\"type\":\"special\",\"matcher\":{\"value\":\"D\"},\"properties\":{\"standardOptions\":{\"util\":\"humantimeSeconds\"}}}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":4,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
}
]
}
]
}
]

View File

@@ -1,63 +1,362 @@
[
{
"name": "Kafka - 模板",
"tags": "Kafka Prometheus ",
"configs": "{\"var\":[{\"name\":\"instance\",\"definition\":\"label_values(kafka_brokers, instance)\"},{\"name\":\"job\",\"definition\":\"label_values(kafka_brokers, job)\"}]}",
"chart_groups": [
{
"name": "overview",
"weight": 0,
"charts": [
{
"name": "Kafka - 模板",
"tags": "Kafka Prometheus",
"configs": {
"var": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"count(count by (topic) (kafka_topic_partitions))\"}],\"name\":\"topics\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{\"value\":50}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":8,\"x\":8,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"kafka_brokers\"}],\"name\":\"brokers\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{\"value\":50}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":8,\"x\":0,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(kafka_topic_partitions)\"}],\"name\":\"partitions\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{\"value\":50}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":8,\"x\":16,\"y\":0,\"i\":\"2\"}}",
"weight": 0
"name": "cluster",
"definition": "label_values(kafka_brokers, cluster)",
"type": "query"
}
]
},
{
"name": "throughput",
"weight": 1,
"charts": [
],
"version": "2.0.0",
"panels": [
{
"configs": "{\"targets\":[{\"expr\":\"sum(rate(kafka_topic_partition_current_offset{instance=\\\"$instance\\\"}[1m])) by (topic)\"}],\"name\":\"Message in per second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
"id": "51502c3a-dd6f-41c7-b8f1-87b88826c96e",
"type": "row",
"name": "overview",
"layout": {
"h": 1,
"w": 24,
"x": 0,
"y": 0,
"i": "51502c3a-dd6f-41c7-b8f1-87b88826c96e",
"isResizable": false
},
"collapsed": true
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(kafka_consumer_lag_millis{instance=\\\"$instance\\\"}) by (consumergroup, topic) \",\"legend\":\"{{consumergroup}} (topic: {{topic}})\"}],\"name\":\"Latency by Consumer Group\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"humantimeMilliseconds\"},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":2,\"i\":\"1\"}}",
"weight": 0
"targets": [
{
"refId": "A",
"expr": "kafka_brokers{cluster=\"$cluster\"}"
}
],
"name": "brokers",
"custom": {
"textMode": "value",
"colorMode": "value",
"calc": "lastNotNull",
"colSpan": 1,
"textSize": {
"value": 50
}
},
"options": {
"standardOptions": {}
},
"version": "2.0.0",
"type": "stat",
"layout": {
"h": 3,
"w": 6,
"x": 0,
"y": 1,
"i": "e2c1d271-ec43-4821-aa19-451e856af755",
"isResizable": true
},
"id": "e2c1d271-ec43-4821-aa19-451e856af755"
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(rate(kafka_consumergroup_current_offset{instance=\\\"$instance\\\"}[1m])) by (topic)\"}],\"name\":\"Message consume per second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"2\"}}",
"weight": 0
"targets": [
{
"refId": "A",
"expr": "count(count by (topic) (kafka_topic_partitions{cluster=\"$cluster\"}))"
}
],
"name": "topics",
"custom": {
"textMode": "value",
"colorMode": "value",
"calc": "lastNotNull",
"colSpan": 1,
"textSize": {
"value": 50
}
},
"options": {
"standardOptions": {}
},
"version": "2.0.0",
"type": "stat",
"layout": {
"h": 3,
"w": 6,
"x": 6,
"y": 1,
"i": "fd3a0b9f-fd67-4360-a94c-869fee7b5b98",
"isResizable": true
},
"id": "fd3a0b9f-fd67-4360-a94c-869fee7b5b98"
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(kafka_topic_partition_current_offset{instance=\\\"$instance\\\"}) by (topic) - sum(kafka_consumergroup_current_offset{instance=\\\"$instance\\\"}) by (topic) \",\"legend\":\"{{consumergroup}} (topic: {{topic}})\"}],\"name\":\"Lag by Consumer Group\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":2,\"i\":\"3\"}}",
"weight": 0
"targets": [
{
"refId": "A",
"expr": "sum(kafka_topic_partitions{cluster=\"$cluster\"})"
}
],
"name": "partitions",
"custom": {
"textMode": "value",
"colorMode": "value",
"calc": "lastNotNull",
"colSpan": 1,
"textSize": {
"value": 50
}
},
"options": {
"standardOptions": {}
},
"version": "2.0.0",
"type": "stat",
"layout": {
"h": 3,
"w": 6,
"x": 12,
"y": 1,
"i": "e228d857-746b-41b6-8d2d-0152453c46f4",
"isResizable": true
},
"id": "e228d857-746b-41b6-8d2d-0152453c46f4"
},
{
"targets": [
{
"refId": "A",
"expr": "sum(kafka_topic_partition_replicas{cluster=\"$cluster\"})"
}
],
"name": "Replicas",
"custom": {
"textMode": "valueAndName",
"colorMode": "value",
"calc": "lastNotNull",
"colSpan": 1,
"textSize": {}
},
"options": {
"standardOptions": {}
},
"version": "2.0.0",
"type": "stat",
"layout": {
"h": 3,
"w": 6,
"x": 18,
"y": 1,
"i": "85438099-8d6b-4817-b9b9-1d0ed36029cd",
"isResizable": true
},
"id": "85438099-8d6b-4817-b9b9-1d0ed36029cd"
},
{
"id": "0db4aac4-86cf-44cd-950e-6c6a99be8ff4",
"type": "row",
"name": "throughput",
"layout": {
"h": 1,
"w": 24,
"x": 0,
"y": 4,
"i": "0db4aac4-86cf-44cd-950e-6c6a99be8ff4",
"isResizable": false
},
"collapsed": true
},
{
"targets": [
{
"expr": "sum(rate(kafka_topic_partition_current_offset{cluster=\"$cluster\"}[1m])) by (topic)"
}
],
"name": "Messages produced per second",
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"fillOpacity": 0.5,
"stack": "off"
},
"version": "2.0.0",
"type": "timeseries",
"layout": {
"h": 7,
"w": 8,
"x": 0,
"y": 5,
"i": "c2ec4036-3081-45cc-b672-024c6df93833",
"isResizable": true
},
"id": "c2ec4036-3081-45cc-b672-024c6df93833"
},
{
"targets": [
{
"expr": "sum(rate(kafka_consumergroup_current_offset{cluster=\"$cluster\"}[1m])) by (topic)"
}
],
"name": "Messages consumed per second",
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"fillOpacity": 0.5,
"stack": "off"
},
"version": "2.0.0",
"type": "timeseries",
"layout": {
"h": 7,
"w": 8,
"x": 8,
"y": 5,
"i": "7ad651a6-c12c-4d46-8d01-749fa776faef",
"isResizable": true
},
"id": "7ad651a6-c12c-4d46-8d01-749fa776faef"
},
{
"targets": [
{
"expr": "sum(kafka_consumer_lag_millis{cluster=\"$cluster\"}) by (consumergroup, topic)",
"legend": "{{consumergroup}} (topic: {{topic}})"
}
],
"name": "Latency by Consumer Group",
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {
"util": "humantimeMilliseconds"
},
"thresholds": {}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"fillOpacity": 0.5,
"stack": "off"
},
"version": "2.0.0",
"type": "timeseries",
"layout": {
"h": 7,
"w": 8,
"x": 16,
"y": 5,
"i": "855aa8f5-0c51-42d4-b9a4-5460b7cd0f5a",
"isResizable": true
},
"id": "855aa8f5-0c51-42d4-b9a4-5460b7cd0f5a"
},
{
"id": "20166830-7f85-4665-8f39-bf904267af29",
"type": "row",
"name": "patition/replicate",
"layout": {
"h": 1,
"w": 24,
"x": 0,
"y": 12,
"i": "20166830-7f85-4665-8f39-bf904267af29",
"isResizable": false
},
"collapsed": true
},
{
"targets": [
{
"refId": "A",
"expr": "kafka_topic_partitions{cluster=\"$cluster\"}",
"legend": "{{topic}}"
}
],
"name": "Partitions per Topic",
"custom": {
"showHeader": true,
"colorMode": "value",
"calc": "lastNotNull",
"displayMode": "seriesToRows"
},
"options": {
"standardOptions": {}
},
"overrides": [
{}
],
"version": "2.0.0",
"type": "table",
"layout": {
"h": 7,
"w": 12,
"x": 0,
"y": 13,
"i": "8837a52e-c9eb-4afa-acc1-c3a5dac72d3b",
"isResizable": true
},
"id": "8837a52e-c9eb-4afa-acc1-c3a5dac72d3b"
},
{
"targets": [
{
"refId": "A",
"expr": "kafka_topic_partition_under_replicated_partition{cluster=\"$cluster\"}",
"legend": "{{topic}}-{{partition}}"
}
],
"name": "Partitions Under Replicated",
"description": "副本不同步预案\n1. Restart the Zookeeper leader.\n2. Restart the broker\\brokers that are not replicating some of the partitions.",
"custom": {
"showHeader": true,
"colorMode": "value",
"calc": "lastNotNull",
"displayMode": "seriesToRows"
},
"options": {
"standardOptions": {}
},
"overrides": [
{}
],
"version": "2.0.0",
"type": "table",
"layout": {
"h": 7,
"w": 12,
"x": 12,
"y": 13,
"i": "dd615767-dda7-4da6-b37f-0d484553aac6",
"isResizable": true
},
"id": "dd615767-dda7-4da6-b37f-0d484553aac6"
}
]
},
{
"name": "patition/replicate",
"weight": 2,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"kafka_topic_partitions{instance=\\\"$instance\\\"}\",\"legend\":\"{{topic}}\"}],\"name\":\"Partitions per Topic\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"seriesToRows\"},\"options\":{\"standardOptions\":{}},\"overrides\":[{}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"kafka_topic_partition_under_replicated_partition\",\"legend\":\"{{topic}}-{{partition}}\"}],\"name\":\"Under Replicated\",\"description\":\"副本不同步预案\\n1. Restart the Zookeeper leader.\\n2. Restart the broker\\\\brokers that are not replicating some of the partitions.\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"seriesToRows\"},\"options\":{\"standardOptions\":{}},\"overrides\":[{}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
}
]
}
]
]
}
]
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,119 @@
[
{
"name": "MySQL Overview - 模板",
"tags": "Prometheus MySQL",
"configs": "{\"var\":[{\"name\":\"instance\",\"definition\":\"label_values(mysql_global_status_uptime, instance)\"}]}",
"chart_groups": [
{
"name": "Basic Info",
"weight": 0,
"charts": [
{
"configs": "{\"targets\":[{\"expr\":\"min(mysql_global_status_uptime{instance=~\\\"$instance\\\"})\"}],\"name\":\"MySQL Uptime\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":1800},\"result\":{\"color\":\"#ec7718\"}},{\"type\":\"range\",\"match\":{\"from\":1800},\"result\":{\"color\":\"#369603\"}}],\"standardOptions\":{\"util\":\"humantimeSeconds\"}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"rate(mysql_global_status_queries{instance=~\\\"$instance\\\"}[5m])\"}],\"name\":\"Current QPS\",\"description\":\"mysql_global_status_queries\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":100},\"result\":{\"color\":\"#05a31f\"}},{\"type\":\"range\",\"match\":{\"from\":100},\"result\":{\"color\":\"#ea3939\"}}],\"standardOptions\":{\"decimals\":2}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"avg(mysql_global_variables_innodb_buffer_pool_size{instance=~\\\"$instance\\\"})\"}],\"name\":\"InnoDB Buffer Pool\",\"description\":\"**InnoDB Buffer Pool Size**\\n\\nInnoDB maintains a storage area called the buffer pool for caching data and indexes in memory. Knowing how the InnoDB buffer pool works, and taking advantage of it to keep frequently accessed data in memory, is one of the most important aspects of MySQL tuning. The goal is to keep the working set in memory. In most cases, this should be between 60%-90% of available memory on a dedicated database host, but depends on many factors.\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{\"util\":\"bytesIEC\"}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(increase(mysql_global_status_table_locks_waited{instance=~\\\"$instance\\\"}[5m]))\"}],\"name\":\"Table Locks Waited(5min)\",\"description\":\"**Table Locks**\\n\\nMySQL takes a number of different locks for varying reasons. In this graph we see how many Table level locks MySQL has requested from the storage engine. In the case of InnoDB, many times the locks could actually be row locks as it only takes table level locks in a few specific cases.\\n\\nIt is most useful to compare Locks Immediate and Locks Waited. If Locks waited is rising, it means you have lock contention. Otherwise, Locks Immediate rising and falling is normal activity.\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":1},\"result\":{\"color\":\"#e70d0d\"}},{\"type\":\"range\",\"match\":{\"to\":1},\"result\":{\"color\":\"#53b503\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
"weight": 0
}
]
},
{
"name": "Connections",
"weight": 1,
"charts": [
{
"configs": "{\"targets\":[{\"expr\":\"sum(mysql_global_status_threads_connected{instance=~\\\"$instance\\\"})\",\"legend\":\"Connections\"},{\"expr\":\"sum(mysql_global_status_max_used_connections{instance=~\\\"$instance\\\"})\",\"legend\":\"Max Used Connections\"},{\"expr\":\"sum(mysql_global_variables_max_connections{instance=~\\\"$instance\\\"})\",\"legend\":\"Max Connections\"},{\"expr\":\"sum(rate(mysql_global_status_aborted_connects{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Aborted Connections\"}],\"name\":\"MySQL Connections\",\"description\":\"**Max Connections** \\n\\nMax Connections is the maximum permitted number of simultaneous client connections. By default, this is 151. Increasing this value increases the number of file descriptors that mysqld requires. If the required number of descriptors are not available, the server reduces the value of Max Connections.\\n\\nmysqld actually permits Max Connections + 1 clients to connect. The extra connection is reserved for use by accounts that have the SUPER privilege, such as root.\\n\\nMax Used Connections is the maximum number of connections that have been in use simultaneously since the server started.\\n\\nConnections is the number of connection attempts (successful or not) to the MySQL server.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(mysql_global_status_threads_connected{instance=~\\\"$instance\\\"})\",\"legend\":\"Threads Connected\"},{\"expr\":\"sum(mysql_global_status_threads_running{instance=~\\\"$instance\\\"})\",\"legend\":\"Threads Running\"}],\"name\":\"MySQL Client Thread Activity\",\"description\":\"Threads Connected is the number of open connections, while Threads Running is the number of threads not sleeping.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
}
]
},
{
"name": "Query Performance",
"weight": 2,
"charts": [
{
"configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_created_tmp_tables{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Created Tmp Tables\"},{\"expr\":\"sum(rate(mysql_global_status_created_tmp_disk_tables{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Created Tmp Disk Tables\"},{\"expr\":\"sum(rate(mysql_global_status_created_tmp_files{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Created Tmp Files\"}],\"name\":\"MySQL Temporary Objects\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.64,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_select_full_join{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Full Join\"},{\"expr\":\"sum(rate(mysql_global_status_select_full_range_join{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Full Range Join\"},{\"expr\":\"sum(rate(mysql_global_status_select_range{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Range\"},{\"expr\":\"sum(rate(mysql_global_status_select_range_check{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Range Check\"},{\"expr\":\"sum(rate(mysql_global_status_select_scan{ instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Select Scan\"}],\"name\":\"MySQL Select Types\",\"description\":\"**MySQL Select Types**\\n\\nAs with most relational databases, selecting based on indexes is more efficient than scanning an entire table's data. Here we see the counters for selects not done with indexes.\\n\\n* ***Select Scan*** is how many queries caused full table scans, in which all the data in the table had to be read and either discarded or returned.\\n* ***Select Range*** is how many queries used a range scan, which means MySQL scanned all rows in a given range.\\n* ***Select Full Join*** is the number of joins that are not joined on an index, this is usually a huge performance hit.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"stack\":\"off\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.41},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_sort_rows{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Sort Rows\"},{\"expr\":\"sum(rate(mysql_global_status_sort_range{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Sort Range\"},{\"expr\":\"sum(rate(mysql_global_status_sort_merge_passes{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Sort Merge Passes\"},{\"expr\":\"sum(rate(mysql_global_status_sort_scan{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Sort Scan\"}],\"name\":\"MySQL Sorts\",\"description\":\"**MySQL Sorts**\\n\\nDue to a query's structure, order, or other requirements, MySQL sorts the rows before returning them. For example, if a table is ordered 1 to 10 but you want the results reversed, MySQL then has to sort the rows to return 10 to 1.\\n\\nThis graph also shows when sorts had to scan a whole table or a given range of a table in order to return the results and which could not have been sorted via an index.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":2,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_slow_queries{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Slow Queries\"}],\"name\":\"MySQL Slow Queries\",\"description\":\"**MySQL Slow Queries**\\n\\nSlow queries are defined as queries being slower than the long_query_time setting. For example, if you have long_query_time set to 3, all queries that take longer than 3 seconds to complete will show on this graph.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"bars\",\"stack\":\"off\",\"fillOpacity\":0.81},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":2,\"i\":\"3\"}}",
"weight": 0
}
]
},
{
"name": "Network",
"weight": 3,
"charts": [
{
"configs": "{\"targets\":[{\"expr\":\"sum(rate(mysql_global_status_bytes_received{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Inbound\"},{\"expr\":\"sum(rate(mysql_global_status_bytes_sent{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"Outbound\"}],\"name\":\"MySQL Network Traffic\",\"description\":\"**MySQL Network Traffic**\\n\\nHere we can see how much network traffic is generated by MySQL. Outbound is network traffic sent from MySQL and Inbound is network traffic MySQL has received.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesSI\",\"decimals\":2},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
}
]
},
{
"name": "Commands, Handlers",
"weight": 4,
"charts": [
{
"configs": "{\"targets\":[{\"expr\":\"topk(10, rate(mysql_global_status_commands_total{instance=~\\\"$instance\\\"}[5m])>0)\",\"legend\":\"Com_{{command}}\"}],\"name\":\"Top Command Counters\",\"description\":\"**Top Command Counters**\\n\\nThe Com_{{xxx}} statement counter variables indicate the number of times each xxx statement has been executed. There is one status variable for each type of statement. For example, Com_delete and Com_update count [``DELETE``](https://dev.mysql.com/doc/refman/5.7/en/delete.html) and [``UPDATE``](https://dev.mysql.com/doc/refman/5.7/en/update.html) statements, respectively. Com_delete_multi and Com_update_multi are similar but apply to [``DELETE``](https://dev.mysql.com/doc/refman/5.7/en/delete.html) and [``UPDATE``](https://dev.mysql.com/doc/refman/5.7/en/update.html) statements that use multiple-table syntax.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":2},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.2,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"rate(mysql_global_status_handlers_total{instance=~\\\"$instance\\\", handler!~\\\"commit|rollback|savepoint.*|prepare\\\"}[5m])\",\"legend\":\"{{handler}}\"}],\"name\":\"MySQL Handlers\",\"description\":\"**MySQL Handlers**\\n\\nHandler statistics are internal statistics on how MySQL is selecting, updating, inserting, and modifying rows, tables, and indexes.\\n\\nThis is in fact the layer between the Storage Engine and MySQL.\\n\\n* `read_rnd_next` is incremented when the server performs a full table scan and this is a counter you don't really want to see with a high value.\\n* `read_key` is incremented when a read is done with an index.\\n* `read_next` is incremented when the storage engine is asked to 'read the next index entry'. A high value means a lot of index scans are being done.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":3},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":2,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"rate(mysql_global_status_handlers_total{instance=~\\\"$instance\\\", handler=~\\\"commit|rollback|savepoint.*|prepare\\\"}[5m])\",\"legend\":\"{{handler}}\"}],\"name\":\"MySQL Transaction Handlers\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":2,\"i\":\"2\"}}",
"weight": 0
}
]
},
{
"name": "Open Files",
"weight": 5,
"charts": [
{
"configs": "{\"targets\":[{\"expr\":\"mysql_global_variables_open_files_limit{instance=~\\\"$instance\\\"}\",\"legend\":\"Open Files Limit\"},{\"expr\":\"mysql_global_status_open_files{instance=~\\\"$instance\\\"}\",\"legend\":\"Open Files\"}],\"name\":\"MySQL Open Files\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
}
]
},
{
"name": "Table Openings",
"weight": 6,
"charts": [
{
"configs": "{\"targets\":[{\"expr\":\"rate(mysql_global_status_table_open_cache_hits{instance=~\\\"$instance\\\"}[5m])\\n/\\n(\\nrate(mysql_global_status_table_open_cache_hits{instance=~\\\"$instance\\\"}[5m])\\n+\\nrate(mysql_global_status_table_open_cache_misses{instance=~\\\"$instance\\\"}[5m])\\n)\",\"legend\":\"Table Open Cache Hit Ratio\"}],\"name\":\"Table Open Cache Hit Ratio Mysql 5.6.6+\",\"description\":\"**MySQL Table Open Cache Status**\\n\\nThe recommendation is to set the `table_open_cache_instances` to a loose correlation to virtual CPUs, keeping in mind that more instances means the cache is split more times. If you have a cache set to 500 but it has 10 instances, each cache will only have 50 cached.\\n\\nThe `table_definition_cache` and `table_open_cache` can be left as default as they are auto-sized MySQL 5.6 and above (ie: do not set them to any value).\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"percentUnit\"},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"mysql_global_status_open_tables{instance=~\\\"$instance\\\"}\",\"legend\":\"Open Tables\"},{\"expr\":\"mysql_global_variables_table_open_cache{instance=~\\\"$instance\\\"}\",\"legend\":\"Table Open Cache\"}],\"name\":\"MySQL Open Tables\",\"description\":\"**MySQL Open Tables**\\n\\nThe recommendation is to set the `table_open_cache_instances` to a loose correlation to virtual CPUs, keeping in mind that more instances means the cache is split more times. If you have a cache set to 500 but it has 10 instances, each cache will only have 50 cached.\\n\\nThe `table_definition_cache` and `table_open_cache` can be left as default as they are auto-sized MySQL 5.6 and above (ie: do not set them to any value).\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
}
]
}
]
}
]

232
dashboards/n9e_server.json Normal file
View File

@@ -0,0 +1,232 @@
{
"name": "夜莺大盘",
"tags": "",
"configs": {
"var": [],
"panels": [
{
"targets": [
{
"refId": "A",
"expr": "rate(n9e_server_samples_received_total[1m])"
}
],
"name": "每秒接收的数据点个数",
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"fillOpacity": 0.5,
"stack": "off"
},
"version": "2.0.0",
"type": "timeseries",
"layout": {
"h": 4,
"w": 12,
"x": 0,
"y": 0,
"i": "53fcb9dc-23f9-41e0-bc5e-121eed14c3a4",
"isResizable": true
},
"id": "53fcb9dc-23f9-41e0-bc5e-121eed14c3a4"
},
{
"targets": [
{
"refId": "A",
"expr": "rate(n9e_server_alerts_total[10m])"
}
],
"name": "每秒产生的告警事件个数",
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"fillOpacity": 0.5,
"stack": "off"
},
"version": "2.0.0",
"type": "timeseries",
"layout": {
"h": 4,
"w": 12,
"x": 12,
"y": 0,
"i": "47fc6252-9cc8-4b53-8e27-0c5c59a47269",
"isResizable": true
},
"id": "f70dcb8b-b58b-4ef9-9e48-f230d9e17140"
},
{
"targets": [
{
"refId": "A",
"expr": "n9e_server_alert_queue_size"
}
],
"name": "告警事件内存队列长度",
"options": {
"tooltip": {
"mode": "all",
"sort": "none"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"fillOpacity": 0.5,
"stack": "off"
},
"version": "2.0.0",
"type": "timeseries",
"layout": {
"h": 4,
"w": 12,
"x": 0,
"y": 4,
"i": "ad1af16c-de0c-45f4-8875-cea4e85d51d0",
"isResizable": true
},
"id": "caf23e58-d907-42b0-9ed6-722c8c6f3c5f"
},
{
"targets": [
{
"refId": "A",
"expr": "n9e_server_http_request_duration_seconds_sum/n9e_server_http_request_duration_seconds_count"
}
],
"name": "数据接收接口平均响应时间(单位:秒)",
"options": {
"tooltip": {
"mode": "all",
"sort": "desc"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"fillOpacity": 0.5,
"stack": "noraml"
},
"version": "2.0.0",
"type": "timeseries",
"layout": {
"h": 4,
"w": 12,
"x": 12,
"y": 4,
"i": "64c3abc2-404c-4462-a82f-c109a21dac91",
"isResizable": true
},
"id": "6b8d2db1-efca-4b9e-b429-57a9d2272bc5"
},
{
"targets": [
{
"refId": "A",
"expr": "n9e_server_sample_queue_size"
}
],
"name": "内存数据队列长度",
"options": {
"tooltip": {
"mode": "all",
"sort": "desc"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"fillOpacity": 0.5,
"stack": "off"
},
"version": "2.0.0",
"type": "timeseries",
"layout": {
"h": 4,
"w": 12,
"x": 0,
"y": 8,
"i": "1c7da942-58c2-40dc-b42f-983e4a35b89b",
"isResizable": true
},
"id": "bd41677d-40d3-482e-bb6e-fbd25df46d87"
},
{
"targets": [
{
"refId": "A",
"expr": "avg(n9e_server_forward_duration_seconds_sum/n9e_server_forward_duration_seconds_count)"
}
],
"name": "数据发往TSDB平均耗时单位",
"options": {
"tooltip": {
"mode": "all",
"sort": "desc"
},
"legend": {
"displayMode": "hidden"
},
"standardOptions": {},
"thresholds": {}
},
"custom": {
"drawStyle": "lines",
"lineInterpolation": "smooth",
"fillOpacity": 0.5,
"stack": "noraml"
},
"version": "2.0.0",
"type": "timeseries",
"layout": {
"h": 4,
"w": 12,
"x": 12,
"y": 8,
"i": "eed94a0b-954f-48ac-82e5-a2eada1c8a3d",
"isResizable": true
},
"id": "c8642e72-f384-46a5-8410-1e6be2953c3c"
}
],
"version": "2.0.0"
}
}

View File

@@ -0,0 +1,19 @@
[
{
"name": "TCP探测",
"tags": "",
"configs": "",
"chart_groups": [
{
"name": "Default chart group",
"weight": 0,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"max(net_response_result_code) by (target)\",\"legend\":\"UP?\"},{\"expr\":\"max(net_response_response_time) by (target)\",\"refId\":\"C\",\"legend\":\"latency(s)\"}],\"name\":\"Targets\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"labelValuesToRows\",\"aggrDimension\":\"target\"},\"options\":{\"valueMappings\":[],\"standardOptions\":{}},\"overrides\":[{\"properties\":{\"valueMappings\":[{\"type\":\"special\",\"match\":{\"special\":0},\"result\":{\"text\":\"UP\",\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"special\":1,\"from\":1},\"result\":{\"text\":\"DOWN\",\"color\":\"#e90f0f\"}}],\"standardOptions\":{}},\"matcher\":{\"value\":\"A\"}}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":4,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
}
]
}
]
}
]

View File

@@ -0,0 +1,127 @@
[
{
"name": "Oracle - 模板",
"tags": "Telegraf",
"configs": "{\"var\":[{\"name\":\"ident\",\"definition\":\"label_values(oracle_up,ident)\",\"options\":[\"tt-fc-log00.nj\"]},{\"name\":\"instance\",\"definition\":\"label_values(oracle_up{ident=\\\"$ident\\\"},instance)\"}]}",
"chart_groups": [
{
"name": "Activities",
"weight": 0,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(oracle_activity_execute_count_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}[2m])\"}],\"name\":\"execute count / second\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{\"decimals\":1}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":6,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(oracle_activity_user_commits_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}[2m])\"}],\"name\":\"user commits / second\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(oracle_activity_user_rollbacks_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}[2m])\"}],\"name\":\"user rollbacks / second\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_up{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"status\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"special\",\"match\":{\"special\":1},\"result\":{\"text\":\"UP\",\"color\":\"#5ea70f\"}},{\"type\":\"special\",\"match\":{\"special\":0},\"result\":{\"text\":\"DOWN\",\"color\":\"#f60f0f\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":0,\"y\":0,\"i\":\"3\"}}",
"weight": 0
}
]
},
{
"name": "Waits",
"weight": 1,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_wait_time_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"legend\":\"{{wait_class}}\"}],\"name\":\"Time waited\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
}
]
},
{
"name": "Tablespace",
"weight": 2,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_tablespace_bytes{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}/oracle_tablespace_max_bytes{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"legend\":\"{{tablespace}}\"}],\"name\":\"Used Percent\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"percentUnit\"},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_tablespace_free{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"legend\":\"{{tablespace}}\"}],\"name\":\"Free space\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
}
]
},
{
"name": "IO and TPS",
"weight": 3,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_io_requests_per_second_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"IO Requests / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_user_transaction_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"TPS\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":8,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_io_megabytes_per_second_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}*1024*1024\"}],\"name\":\"IO Bytes / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":16,\"y\":0,\"i\":\"2\"}}",
"weight": 0
}
]
},
{
"name": "Connections",
"weight": 4,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sessions_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\",status=\\\"ACTIVE\\\"}\",\"legend\":\"\"}],\"name\":\"Sessions\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
}
]
},
{
"name": "Hit Ratio",
"weight": 5,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_buffer_cache_hit_ratio_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"Buffer Cache Hit Ratio\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_redo_allocation_hit_ratio_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"Redo Allocation Hit Ratio\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_row_cache_hit_ratio_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"Row Cache Hit Ratio\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_library_cache_hit_ratio_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"}],\"name\":\"Library Cache Hit Ratio\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
"weight": 0
}
]
},
{
"name": "Physical Read Write",
"weight": 6,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_physical_read_bytes_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"},{\"expr\":\"oracle_sysmetric_Physical_Write_Bytes_Per_Sec{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"refId\":\"B\"}],\"name\":\"Physical Read Write Bytes / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_physical_read_total_bytes_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"},{\"expr\":\"oracle_sysmetric_Physical_Write_Total_Bytes_Per_Sec{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"refId\":\"B\"}],\"name\":\"Physical Read Write Total Bytes / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_physical_read_io_requests_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"},{\"expr\":\"oracle_sysmetric_Physical_Write_IO_Requests_Per_Sec{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"refId\":\"B\"}],\"name\":\"Physical RW IO Requests / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"oracle_sysmetric_physical_read_total_io_requests_per_sec_value{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\"},{\"expr\":\"oracle_sysmetric_Physical_Write_Total_IO_Requests_Per_Sec{ident=\\\"$ident\\\", instance=\\\"$instance\\\"}\",\"refId\":\"B\"}],\"name\":\"Physical RW Total IO Requests / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
"weight": 0
}
]
}
]
}
]

View File

@@ -0,0 +1,19 @@
[
{
"name": "PING探测",
"tags": "",
"configs": "",
"chart_groups": [
{
"name": "Default chart group",
"weight": 0,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"max(ping_result_code) by (target)\",\"legend\":\"UP?\"},{\"expr\":\"max(ping_percent_packet_loss) by (target)\",\"refId\":\"B\",\"legend\":\"Packet Loss %\"},{\"expr\":\"max(httpresponse_response_time) by (target)\",\"refId\":\"C\",\"legend\":\"latency(s)\"}],\"name\":\"Ping\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"labelValuesToRows\",\"aggrDimension\":\"target\"},\"options\":{\"valueMappings\":[],\"standardOptions\":{}},\"overrides\":[{\"properties\":{\"valueMappings\":[{\"type\":\"special\",\"match\":{\"special\":0},\"result\":{\"text\":\"UP\",\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"special\":1,\"from\":1},\"result\":{\"text\":\"DOWN\",\"color\":\"#e90f0f\"}}],\"standardOptions\":{}},\"matcher\":{\"value\":\"A\"}}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":4,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
}
]
}
]
}
]

View File

@@ -0,0 +1,221 @@
[
{
"name": "RabbitMQ 3.8+",
"tags": "",
"configs": "{\"var\":[{\"definition\":\"label_values(rabbitmq_identity_info, rabbitmq_cluster)\",\"name\":\"rabbitmq_cluster\"}]}",
"chart_groups": [
{
"name": "Overview",
"weight": 0,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queue_messages_ready * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Ready messages\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10000},\"result\":{\"color\":\"#4a90e2\"}},{\"type\":\"range\",\"match\":{\"from\":100000},\"result\":{\"color\":\"#f50a0a\"}},{\"type\":\"range\",\"match\":{\"to\":9999},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":7,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_published_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Incoming messages / s\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":50},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":5,\"x\":7,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_channels * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) - sum(rabbitmq_channel_consumers * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Publishers\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":12,\"y\":0,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_connections * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Connections\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":16,\"y\":0,\"i\":\"3\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queues * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Queues\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":20,\"y\":0,\"i\":\"4\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queue_messages_unacked * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Unacknowledged messages\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":99},\"result\":{\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"from\":100},\"result\":{\"color\":\"#4a90e2\"}},{\"type\":\"range\",\"match\":{\"from\":500},\"result\":{\"color\":\"#d0021b\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":7,\"x\":0,\"y\":1,\"i\":\"5\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_redelivered_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\nsum(rate(rabbitmq_channel_messages_delivered_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\nsum(rate(rabbitmq_channel_messages_delivered_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\nsum(rate(rabbitmq_channel_get_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\nsum(rate(rabbitmq_channel_get_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Outgoing messages / s\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":50},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":5,\"x\":7,\"y\":1,\"i\":\"6\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_channel_consumers * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Consumers\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":12,\"y\":1,\"i\":\"7\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_channels * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Channels\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"from\":10},\"result\":{\"color\":\"#417505\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":16,\"y\":1,\"i\":\"8\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_build_info * on(instance) group_left(rabbitmq_cluster) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Nodes\",\"custom\":{\"textMode\":\"valueAndName\",\"colorMode\":\"background\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":null,\"from\":3},\"result\":{\"color\":\"#417505\"}},{\"type\":\"range\",\"match\":{\"from\":8},\"result\":{\"color\":\"#e70909\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":4,\"x\":20,\"y\":1,\"i\":\"9\"}}",
"weight": 0
}
]
},
{
"name": "Nodes",
"weight": 1,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_build_info * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"nodes\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"labelsOfSeriesToRows\",\"columns\":[\"rabbitmq_cluster\",\"rabbitmq_node\",\"rabbitmq_version\",\"erlang_version\"]},\"options\":{\"standardOptions\":{}},\"overrides\":[{}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":1,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"(rabbitmq_resident_memory_limit_bytes * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) -\\n(rabbitmq_process_resident_memory_bytes * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"Memory available before publishers blocked\",\"description\":\"If the value is zero or less, the memory alarm will be triggered and all publishing connections across all cluster nodes will be blocked.\\n\\nThis value can temporarily go negative because the memory alarm is triggered with a slight delay.\\n\\nThe kernel's view of the amount of memory used by the node can differ from what the node itself can observe. This means that this value can be negative for a sustained period of time.\\n\\nBy default nodes use resident set size (RSS) to compute how much memory they use. This strategy can be changed (see the guides below).\\n\\n* [Alarms](https://www.rabbitmq.com/alarms.html)\\n* [Memory Alarms](https://www.rabbitmq.com/memory.html)\\n* [Reasoning About Memory Use](https://www.rabbitmq.com/memory-use.html)\\n* [Blocked Connection Notifications](https://www.rabbitmq.com/connection-blocked.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":0,\"y\":1,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_disk_space_available_bytes * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"Disk space available before publishers blocked\",\"description\":\"This metric is reported for the partition where the RabbitMQ data directory is stored.\\n\\nIf the value is zero or less, the disk alarm will be triggered and all publishing connections across all cluster nodes will be blocked.\\n\\nThis value can temporarily go negative because the free disk space alarm is triggered with a slight delay.\\n\\n* [Alarms](https://www.rabbitmq.com/alarms.html)\\n* [Disk Space Alarms](https://www.rabbitmq.com/disk-alarms.html)\\n* [Disk Space](https://www.rabbitmq.com/production-checklist.html#resource-limits-disk-space)\\n* [Persistence Configuration](https://www.rabbitmq.com/persistence-conf.html)\\n* [Blocked Connection Notifications](https://www.rabbitmq.com/connection-blocked.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":8,\"y\":1,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"(rabbitmq_process_max_fds * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) -\\n(rabbitmq_process_open_fds * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"File descriptors available\",\"description\":\"When this value reaches zero, new connections will not be accepted and disk write operations may fail.\\n\\nClient libraries, peer nodes and CLI tools will not be able to connect when the node runs out of available file descriptors.\\n\\n* [Open File Handles Limit](https://www.rabbitmq.com/production-checklist.html#resource-limits-file-handle-limit)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":8,\"x\":16,\"y\":1,\"i\":\"3\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"(rabbitmq_process_max_tcp_sockets * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) -\\n(rabbitmq_process_open_tcp_sockets * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\"}],\"name\":\"TCP sockets available\",\"description\":\"When this value reaches zero, new connections will not be accepted.\\n\\nClient libraries, peer nodes and CLI tools will not be able to connect when the node runs out of available file descriptors.\\n\\n* [Networking and RabbitMQ](https://www.rabbitmq.com/networking.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":8,\"x\":16,\"y\":2,\"i\":\"4\"}}",
"weight": 0
}
]
},
{
"name": "QUEUED MESSAGES",
"weight": 2,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queue_messages_ready * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages ready to be delivered to consumers\",\"description\":\"Total number of ready messages ready to be delivered to consumers.\\n\\nAim to keep this value as low as possible. RabbitMQ behaves best when messages are flowing through it. It's OK for publishers to occasionally outpace consumers, but the expectation is that consumers will eventually process all ready messages.\\n\\nIf this metric keeps increasing, your system will eventually run out of memory and/or disk space. Consider using TTL or Queue Length Limit to prevent unbounded message growth.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\\n* [Queue Length Limit](https://www.rabbitmq.com/maxlength.html)\\n* [Time-To-Live and Expiration](https://www.rabbitmq.com/ttl.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rabbitmq_queue_messages_unacked * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages pending consumer acknowledgement\",\"description\":\"The total number of messages that are either in-flight to consumers, currently being processed by consumers or simply waiting for the consumer acknowledgements to be processed by the queue. Until the queue processes the message acknowledgement, the message will remain unacknowledged.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\\n* [Confirms and Acknowledgements](https://www.rabbitmq.com/confirms.html)\\n* [Consumer Prefetch](https://www.rabbitmq.com/consumer-prefetch.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
}
]
},
{
"name": "INCOMING MESSAGES",
"weight": 3,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_published_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages published / s\",\"description\":\"The incoming message rate before any routing rules are applied.\\n\\nIf this value is lower than the number of messages published to queues, it may indicate that some messages are delivered to more than one queue.\\n\\nIf this value is higher than the number of messages published to queues, messages cannot be routed and will either be dropped or returned to publishers.\\n\\n* [Publishers](https://www.rabbitmq.com/publishers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_confirmed_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages confirmed to publishers / s\",\"description\":\"The rate of messages confirmed by the broker to publishers. Publishers must opt-in to receive message confirmations.\\n\\nIf this metric is consistently at zero it may suggest that publisher confirms are not used by clients. The safety of published messages is likely to be at risk.\\n\\n* [Publisher Confirms](https://www.rabbitmq.com/confirms.html#publisher-confirms)\\n* [Publisher Confirms and Data Safety](https://www.rabbitmq.com/publishers.html#data-safety)\\n* [When Will Published Messages Be Confirmed by the Broker?](https://www.rabbitmq.com/confirms.html#when-publishes-are-confirmed)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_queue_messages_published_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages routed to queues / s\",\"description\":\"The rate of messages received from publishers and successfully routed to the master queue replicas.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\\n* [Publishers](https://www.rabbitmq.com/publishers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":1,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_unconfirmed[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages unconfirmed to publishers / s\",\"description\":\"The rate of messages received from publishers that have publisher confirms enabled and the broker has not confirmed yet.\\n\\n* [Publishers](https://www.rabbitmq.com/publishers.html)\\n* [Confirms and Acknowledgements](https://www.rabbitmq.com/confirms.html)\\n* [When Will Published Messages Be Confirmed by the Broker?](https://www.rabbitmq.com/confirms.html#when-publishes-are-confirmed)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":1,\"i\":\"3\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_unroutable_dropped_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Unroutable messages dropped / s\",\"description\":\"The rate of messages that cannot be routed and are dropped. \\n\\nAny value above zero means message loss and likely suggests a routing problem on the publisher end.\\n\\n* [Unroutable Message Handling](https://www.rabbitmq.com/publishers.html#unroutable)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":2,\"i\":\"4\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_unroutable_returned_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Unroutable messages returned to publishers / s\",\"description\":\"The rate of messages that cannot be routed and are returned back to publishers.\\n\\nSustained values above zero may indicate a routing problem on the publisher end.\\n\\n* [Unroutable Message Handling](https://www.rabbitmq.com/publishers.html#unroutable)\\n* [When Will Published Messages Be Confirmed by the Broker?](https://www.rabbitmq.com/confirms.html#when-publishes-are-confirmed)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":2,\"i\":\"5\"}}",
"weight": 0
}
]
},
{
"name": "OUTGOING MESSAGES",
"weight": 4,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(\\n (rate(rabbitmq_channel_messages_delivered_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) +\\n (rate(rabbitmq_channel_messages_delivered_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"})\\n) by(rabbitmq_node)\"}],\"name\":\"Messages delivered / s\",\"description\":\"The rate of messages delivered to consumers. It includes messages that have been redelivered.\\n\\nThis metric does not include messages that have been fetched by consumers using `basic.get` (consumed by polling).\\n\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_redelivered_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages redelivered / s\",\"description\":\"The rate of messages that have been redelivered to consumers. It includes messages that have been requeued automatically and redelivered due to channel exceptions or connection closures.\\n\\nHaving some redeliveries is expected, but if this metric is consistently non-zero, it is worth investigating why.\\n\\n* [Negative Acknowledgement and Requeuing of Deliveries](https://www.rabbitmq.com/confirms.html#consumer-nacks-requeue)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_delivered_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages delivered with manual ack / s\",\"description\":\"The rate of message deliveries to consumers that use manual acknowledgement mode.\\n\\nWhen this mode is used, RabbitMQ waits for consumers to acknowledge messages before more messages can be delivered.\\n\\nThis is the safest way of consuming messages.\\n\\n* [Consumer Acknowledgements](https://www.rabbitmq.com/confirms.html)\\n* [Consumer Prefetch](https://www.rabbitmq.com/consumer-prefetch.html)\\n* [Consumer Acknowledgement Modes, Prefetch and Throughput](https://www.rabbitmq.com/confirms.html#channel-qos-prefetch-throughput)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":1,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_delivered_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages delivered auto ack / s\",\"description\":\"The rate of message deliveries to consumers that use automatic acknowledgement mode.\\n\\nWhen this mode is used, RabbitMQ does not wait for consumers to acknowledge message deliveries.\\n\\nThis mode is fire-and-forget and does not offer any delivery safety guarantees. It tends to provide higher throughput and it may lead to consumer overload and higher consumer memory usage.\\n\\n* [Consumer Acknowledgement Modes, Prefetch and Throughput](https://www.rabbitmq.com/confirms.html#channel-qos-prefetch-throughput)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":1,\"i\":\"3\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_messages_acked_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Messages acknowledged / s\",\"description\":\"The rate of message acknowledgements coming from consumers that use manual acknowledgement mode.\\n\\n* [Consumer Acknowledgements](https://www.rabbitmq.com/confirms.html)\\n* [Consumer Prefetch](https://www.rabbitmq.com/consumer-prefetch.html)\\n* [Consumer Acknowledgement Modes, Prefetch and Throughput](https://www.rabbitmq.com/confirms.html#channel-qos-prefetch-throughput)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":2,\"i\":\"4\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_get_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Polling operations with auto ack / s\",\"description\":\"The rate of messages delivered to polling consumers that use automatic acknowledgement mode.\\n\\nThe use of polling consumers is highly inefficient and therefore strongly discouraged.\\n\\n* [Fetching individual messages](https://www.rabbitmq.com/consumers.html#fetching)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":2,\"i\":\"5\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_get_empty_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Polling operations that yield no result / s\",\"description\":\"The rate of polling consumer operations that yield no result.\\n\\nAny value above zero means that RabbitMQ resources are wasted by polling consumers.\\n\\nCompare this metric to the other polling consumer metrics to see the inefficiency rate.\\n\\nThe use of polling consumers is highly inefficient and therefore strongly discouraged.\\n\\n* [Fetching individual messages](https://www.rabbitmq.com/consumers.html#fetching)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":3,\"i\":\"6\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channel_get_ack_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Polling operations with manual ack / s\",\"description\":\"The rate of messages delivered to polling consumers that use manual acknowledgement mode.\\n\\nThe use of polling consumers is highly inefficient and therefore strongly discouraged.\\n\\n* [Fetching individual messages](https://www.rabbitmq.com/consumers.html#fetching)\\n* [Consumers](https://www.rabbitmq.com/consumers.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":12,\"y\":3,\"i\":\"7\"}}",
"weight": 0
}
]
},
{
"name": "QUEUES",
"weight": 5,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_queues * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"Total queues\",\"description\":\"Total number of queue masters per node. \\n\\nThis metric makes it easy to see sub-optimal queue distribution in a cluster.\\n\\n* [Queue Masters, Data Locality](https://www.rabbitmq.com/ha.html#master-migration-data-locality)\\n* [Queues](https://www.rabbitmq.com/queues.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_queues_declared_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Queues declared / s\",\"description\":\"The rate of queue declarations performed by clients.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of queue churn or high rates of connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":4,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_queues_created_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Queues created / s\",\"description\":\"The rate of new queues created (as opposed to redeclarations).\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of queue churn or high rates of connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":4,\"x\":16,\"y\":0,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_queues_deleted_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Queues deleted / s\",\"description\":\"The rate of queues deleted.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of queue churn or high rates of connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [Queues](https://www.rabbitmq.com/queues.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":4,\"x\":20,\"y\":0,\"i\":\"3\"}}",
"weight": 0
}
]
},
{
"name": "CHANNELS",
"weight": 6,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_channels * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"Total channels\",\"description\":\"Total number of channels on all currently opened connections.\\n\\nIf this metric grows monotonically it is highly likely a channel leak in one of the applications. Confirm channel leaks by using the _Channels opened_ and _Channels closed_ metrics.\\n\\n* [Channel Leak](https://www.rabbitmq.com/channels.html#channel-leaks)\\n* [Channels](https://www.rabbitmq.com/channels.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channels_opened_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Channels opened / s\",\"description\":\"The rate of new channels opened by applications across all connections. Channels are expected to be long-lived.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of channel churn or mass connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [High Channel Churn](https://www.rabbitmq.com/channels.html#high-channel-churn)\\n* [Channels](https://www.rabbitmq.com/channels.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_channels_closed_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Channels closed / s\",\"description\":\"The rate of channels closed by applications across all connections. Channels are expected to be long-lived.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of channel churn or mass connection recovery. Confirm connection recovery rates by using the _Connections opened_ metric.\\n\\n* [High Channel Churn](https://www.rabbitmq.com/channels.html#high-channel-churn)\\n* [Channels](https://www.rabbitmq.com/channels.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"2\"}}",
"weight": 0
}
]
},
{
"name": "CONNECTIONS",
"weight": 7,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_connections_closed_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Connections closed / s\",\"description\":\"The rate of connections closed. Connections are expected to be long-lived.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of connection churn or mass connection recovery.\\n\\n* [Connections](https://www.rabbitmq.com/connections.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rabbitmq_connections * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}\"}],\"name\":\"Total connections\",\"description\":\"Total number of client connections.\\n\\nIf this metric grows monotonically it is highly likely a connection leak in one of the applications. Confirm connection leaks by using the _Connections opened_ and _Connections closed_ metrics.\\n\\n* [Connection Leak](https://www.rabbitmq.com/connections.html#monitoring)\\n* [Connections](https://www.rabbitmq.com/connections.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(rate(rabbitmq_connections_opened_total[60s]) * on(instance) group_left(rabbitmq_cluster, rabbitmq_node) rabbitmq_identity_info{rabbitmq_cluster=\\\"$rabbitmq_cluster\\\"}) by(rabbitmq_node)\"}],\"name\":\"Connections opened / s\",\"description\":\"The rate of new connections opened by clients. Connections are expected to be long-lived.\\n\\nLow sustained values above zero are to be expected. High rates may be indicative of connection churn or mass connection recovery.\\n\\n* [Connection Leak](https://www.rabbitmq.com/connections.html#monitoring)\\n* [Connections](https://www.rabbitmq.com/connections.html)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
}
]
}
]
}
]

View File

@@ -0,0 +1,77 @@
[
{
"name": "Redis Overview - 模板",
"tags": "Redis Prometheus",
"configs": "{\"var\":[{\"name\":\"instance\",\"definition\":\"label_values(redis_uptime_in_seconds,instance)\",\"selected\":\"10.206.0.16:6379\"}]}",
"chart_groups": [
{
"name": "Basic Info",
"weight": 0,
"charts": [
{
"configs": "{\"targets\":[{\"expr\":\"min(redis_uptime_in_seconds{instance=~\\\"$instance\\\"})\"}],\"name\":\"Redis Uptime\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{\"util\":\"humantimeSeconds\"}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(redis_connected_clients{instance=~\\\"$instance\\\"})\"}],\"name\":\"Connected Clients\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"redis_used_memory{instance=~\\\"$instance\\\"}\"}],\"name\":\"Memory Used\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"valueMappings\":[{\"type\":\"range\",\"match\":{\"to\":128000000},\"result\":{\"color\":\"#079e05\"}},{\"type\":\"range\",\"match\":{\"from\":128000000},\"result\":{\"color\":\"#f10909\"}}],\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":0}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"redis_maxmemory{instance=~\\\"$instance\\\"}\"}],\"name\":\"Max Memory Limit\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{}},\"options\":{\"standardOptions\":{\"util\":\"bytesIEC\"}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
"weight": 0
}
]
},
{
"name": "Commands",
"weight": 1,
"charts": [
{
"configs": "{\"targets\":[{\"expr\":\"rate(redis_total_commands_processed{instance=~\\\"$instance\\\"}[5m])\"}],\"name\":\"Commands Executed / sec\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"irate(redis_keyspace_hits{instance=~\\\"$instance\\\"}[5m])\",\"legend\":\"hits\"},{\"expr\":\"irate(redis_keyspace_misses{instance=~\\\"$instance\\\"}[5m])\",\"legend\":\"misses\"}],\"name\":\"Hits / Misses per Sec\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"noraml\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":8,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"topk(5, irate(redis_cmdstat_calls{instance=~\\\"$instance\\\"} [1m]))\",\"legend\":\"{{command}}\"}],\"name\":\"Top Commands\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":16,\"y\":0,\"i\":\"2\"}}",
"weight": 0
}
]
},
{
"name": "Keys",
"weight": 2,
"charts": [
{
"configs": "{\"targets\":[{\"expr\":\"sum (redis_keyspace_keys{instance=~\\\"$instance\\\"}) by (db)\",\"legend\":\"{{db}}\"}],\"name\":\"Total Items per DB\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(rate(redis_expired_keys{instance=~\\\"$instance\\\"}[5m])) by (instance)\",\"legend\":\"expired\"},{\"expr\":\"sum(rate(redis_evicted_keys{instance=~\\\"$instance\\\"}[5m])) by (instance)\",\"legend\":\"evicted\"}],\"name\":\"Expired / Evicted\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":8,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(redis_keyspace_keys{instance=~\\\"$instance\\\"}) - sum(redis_keyspace_expires{instance=~\\\"$instance\\\"}) \",\"legend\":\"not expiring\"},{\"expr\":\"sum(redis_keyspace_expires{instance=~\\\"$instance\\\"}) \",\"legend\":\"expiring\"}],\"name\":\"Expiring vs Not-Expiring Keys\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"noraml\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":16,\"y\":0,\"i\":\"2\"}}",
"weight": 0
}
]
},
{
"name": "Network",
"weight": 3,
"charts": [
{
"configs": "{\"targets\":[{\"expr\":\"sum(rate(redis_total_net_input_bytes{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"input\"},{\"expr\":\"sum(rate(redis_total_net_output_bytes{instance=~\\\"$instance\\\"}[5m]))\",\"legend\":\"output\"}],\"name\":\"Network I/O\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":2},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
}
]
}
]
}
]

View File

@@ -0,0 +1,63 @@
[
{
"name": "Tomcat - 模板",
"tags": "Categraf",
"configs": "{\"var\":[{\"name\":\"instance\",\"definition\":\"label_values(tomcat_up, instance)\"}],\"links\":[{\"title\":\"n9e\",\"url\":\"https://n9e.gitee.io/\",\"targetBlank\":true}]}",
"chart_groups": [
{
"name": "connector",
"weight": 0,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(tomcat_connector_bytes_sent{instance=\\\"$instance\\\"}[1m])\",\"legend\":\"sent\"},{\"expr\":\"rate(tomcat_connector_bytes_received{instance=\\\"$instance\\\"}[1m])\",\"refId\":\"B\",\"legend\":\"received\"}],\"name\":\"Traffic Bytes / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\"},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(tomcat_connector_request_count{instance=\\\"$instance\\\"}[1m])\",\"legend\":\"tomcat_connector_request_count\"},{\"expr\":\"rate(tomcat_connector_error_count{instance=\\\"$instance\\\"}[1m])\",\"refId\":\"B\",\"legend\":\"tomcat_connector_error_count\"}],\"name\":\"Request count / Second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_connector_max_threads{instance=\\\"$instance\\\"}\",\"legend\":\"max_threads\"},{\"expr\":\"tomcat_connector_current_thread_count{instance=\\\"$instance\\\"}\",\"refId\":\"B\",\"legend\":\"current_thread_count\"},{\"expr\":\"tomcat_connector_current_threads_busy{instance=\\\"$instance\\\"}\",\"refId\":\"C\",\"legend\":\"current_threads_busy\"}],\"name\":\"Tread\",\"description\":\"max_threads: The maximum number of allowed worker threads.\\ncurrent_thread_count: The number of threads managed by the thread pool\\ncurrent_threads_busy: The number of threads that are in use\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":2,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(tomcat_connector_processing_time{instance=\\\"$instance\\\"}[1m])\",\"legend\":\"{{name}}-processing_time\"}],\"name\":\"Processing time\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":2,\"i\":\"3\"}}",
"weight": 0
}
]
},
{
"name": "mem used",
"weight": 1,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memory_max{instance=\\\"$instance\\\"}\",\"legend\":\"max\"},{\"expr\":\"tomcat_jvm_memory_total{instance=\\\"$instance\\\"}\",\"refId\":\"B\",\"legend\":\"used\"},{\"expr\":\"tomcat_jvm_memory_free{instance=\\\"$instance\\\"}\",\"refId\":\"C\",\"legend\":\"free\"}],\"name\":\"Mem Used\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":24,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
}
]
},
{
"name": "memorypool",
"weight": 2,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memorypool_used{instance=\\\"$instance\\\"}\",\"legend\":\"{{name}}\"}],\"name\":\"Used\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memorypool_max{instance=\\\"$instance\\\"}\",\"legend\":\"{{name}}\"}],\"name\":\"Max\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memorypool_committed{instance=\\\"$instance\\\"}\",\"legend\":\"{{name}}\"}],\"name\":\"Committed\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"tomcat_jvm_memorypool_init{instance=\\\"$instance\\\"}\",\"legend\":\"{{name}}\"}],\"name\":\"Init\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
"weight": 0
}
]
}
]
}
]

View File

@@ -1,7 +1,9 @@
set names utf8mb4;
drop database if exists n9e_v5;
create database n9e_v5;
use n9e_v5;
CREATE TABLE `users` (
`id` bigint unsigned not null auto_increment,
`username` varchar(64) not null comment 'login name, cannot rename',
@@ -12,6 +14,7 @@ CREATE TABLE `users` (
`portrait` varchar(255) not null default '' comment 'portrait image url',
`roles` varchar(255) not null comment 'Admin | Standard | Guest, split by space',
`contacts` varchar(1024) comment 'json e.g. {wecom:xx, dingtalk_robot_token:yy}',
`maintainer` tinyint(1) not null default 0,
`create_at` bigint not null default 0,
`create_by` varchar(64) not null default '',
`update_at` bigint not null default 0,
@@ -19,7 +22,9 @@ CREATE TABLE `users` (
PRIMARY KEY (`id`),
UNIQUE KEY (`username`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
insert into `users`(id, username, nickname, password, roles, create_at, create_by, update_at, update_by) values(1, 'root', '超管', 'root.2020', 'Admin', unix_timestamp(now()), 'system', unix_timestamp(now()), 'system');
CREATE TABLE `user_group` (
`id` bigint unsigned not null auto_increment,
`name` varchar(128) not null default '',
@@ -32,14 +37,18 @@ CREATE TABLE `user_group` (
KEY (`create_by`),
KEY (`update_at`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
insert into user_group(id, name, create_at, create_by, update_at, update_by) values(1, 'demo-root-group', unix_timestamp(now()), 'root', unix_timestamp(now()), 'root');
CREATE TABLE `user_group_member` (
`group_id` bigint unsigned not null,
`user_id` bigint unsigned not null,
KEY (`group_id`),
KEY (`user_id`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
insert into user_group_member(group_id, user_id) values(1, 1);
CREATE TABLE `configs` (
`id` bigint unsigned not null auto_increment,
`ckey` varchar(191) not null,
@@ -47,6 +56,7 @@ CREATE TABLE `configs` (
PRIMARY KEY (`id`),
UNIQUE KEY (`ckey`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
CREATE TABLE `role` (
`id` bigint unsigned not null auto_increment,
`name` varchar(191) not null default '',
@@ -54,15 +64,18 @@ CREATE TABLE `role` (
PRIMARY KEY (`id`),
UNIQUE KEY (`name`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
insert into `role`(name, note) values('Admin', 'Administrator role');
insert into `role`(name, note) values('Standard', 'Ordinary user role');
insert into `role`(name, note) values('Guest', 'Readonly user role');
CREATE TABLE `role_operation`(
`role_name` varchar(128) not null,
`operation` varchar(191) not null,
KEY (`role_name`),
KEY (`operation`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
-- Admin is special, who has no concrete operation but can do anything.
insert into `role_operation`(role_name, operation) values('Guest', '/metric/explorer');
insert into `role_operation`(role_name, operation) values('Guest', '/object/explorer');
@@ -110,6 +123,11 @@ insert into `role_operation`(role_name, operation) values('Standard', '/job-tpls
insert into `role_operation`(role_name, operation) values('Standard', '/job-tasks');
insert into `role_operation`(role_name, operation) values('Standard', '/job-tasks/add');
insert into `role_operation`(role_name, operation) values('Standard', '/job-tasks/put');
insert into `role_operation`(role_name, operation) values('Standard', '/recording-rules');
insert into `role_operation`(role_name, operation) values('Standard', '/recording-rules/add');
insert into `role_operation`(role_name, operation) values('Standard', '/recording-rules/put');
insert into `role_operation`(role_name, operation) values('Standard', '/recording-rules/del');
-- for alert_rule | collect_rule | mute | dashboard grouping
CREATE TABLE `busi_group` (
`id` bigint unsigned not null auto_increment,
@@ -123,7 +141,9 @@ CREATE TABLE `busi_group` (
PRIMARY KEY (`id`),
UNIQUE KEY (`name`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
insert into busi_group(id, name, create_at, create_by, update_at, update_by) values(1, 'Default Busi Group', unix_timestamp(now()), 'root', unix_timestamp(now()), 'root');
CREATE TABLE `busi_group_member` (
`id` bigint unsigned not null auto_increment,
`busi_group_id` bigint not null comment 'busi group id',
@@ -133,7 +153,9 @@ CREATE TABLE `busi_group_member` (
KEY (`busi_group_id`),
KEY (`user_group_id`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
insert into busi_group_member(busi_group_id, user_group_id, perm_flag) values(1, 1, "rw");
-- for dashboard new version
CREATE TABLE `board` (
`id` bigint unsigned not null auto_increment,
@@ -147,12 +169,14 @@ CREATE TABLE `board` (
PRIMARY KEY (`id`),
UNIQUE KEY (`group_id`, `name`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
-- for dashboard new version
CREATE TABLE `board_payload` (
`id` bigint unsigned not null comment 'dashboard id',
`payload` mediumtext not null,
UNIQUE KEY (`id`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
-- deprecated
CREATE TABLE `dashboard` (
`id` bigint unsigned not null auto_increment,
@@ -167,6 +191,7 @@ CREATE TABLE `dashboard` (
PRIMARY KEY (`id`),
UNIQUE KEY (`group_id`, `name`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
-- deprecated
-- auto create the first subclass 'Default chart group' of dashboard
CREATE TABLE `chart_group` (
@@ -177,6 +202,7 @@ CREATE TABLE `chart_group` (
PRIMARY KEY (`id`),
KEY (`dashboard_id`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
-- deprecated
CREATE TABLE `chart` (
`id` bigint unsigned not null auto_increment,
@@ -186,6 +212,7 @@ CREATE TABLE `chart` (
PRIMARY KEY (`id`),
KEY (`group_id`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
CREATE TABLE `chart_share` (
`id` bigint unsigned not null auto_increment,
`cluster` varchar(128) not null,
@@ -195,6 +222,7 @@ CREATE TABLE `chart_share` (
primary key (`id`),
key (`create_at`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
CREATE TABLE `alert_rule` (
`id` bigint unsigned not null auto_increment,
`group_id` bigint not null default 0 comment 'busi group id',
@@ -205,10 +233,10 @@ CREATE TABLE `alert_rule` (
`algorithm` varchar(255) not null default '',
`algo_params` varchar(255),
`delay` int not null default 0,
`severity` tinyint(1) not null comment '0:Emergency 1:Warning 2:Notice',
`severity` tinyint(1) not null comment '1:Emergency 2:Warning 3:Notice',
`disabled` tinyint(1) not null comment '0:enabled 1:disabled',
`prom_for_duration` int not null comment 'prometheus for, unit:s',
`prom_ql` varchar(8192) not null comment 'promql',
`prom_ql` text not null comment 'promql',
`prom_eval_interval` int not null comment 'evaluate interval',
`enable_stime` char(5) not null default '00:00',
`enable_etime` char(5) not null default '23:59',
@@ -218,6 +246,7 @@ CREATE TABLE `alert_rule` (
`notify_channels` varchar(255) not null default '' comment 'split by space: sms voice email dingtalk wecom',
`notify_groups` varchar(255) not null default '' comment 'split by space: 233 43',
`notify_repeat_step` int not null default 0 comment 'unit: min',
`notify_max_number` int not null default 0 comment '',
`recover_duration` int not null default 0 comment 'unit: s',
`callbacks` varchar(255) not null default '' comment 'split by space: http://a.com/api/x http://a.com/api/y',
`runbook_url` varchar(255),
@@ -230,9 +259,11 @@ CREATE TABLE `alert_rule` (
KEY (`group_id`),
KEY (`update_at`)
) ENGINE=InnoDB DEFAULT CHARSET = utf8mb4;
CREATE TABLE `alert_mute` (
`id` bigint unsigned not null auto_increment,
`group_id` bigint not null default 0 comment 'busi group id',
`prod` varchar(255) not null default '',
`cluster` varchar(128) not null,
`tags` varchar(4096) not null default '' comment 'json,map,tagkey->regexp|value',
`cause` varchar(255) not null default '',
@@ -244,6 +275,7 @@ CREATE TABLE `alert_mute` (
KEY (`create_at`),
KEY (`group_id`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
CREATE TABLE `alert_subscribe` (
`id` bigint unsigned not null auto_increment,
`group_id` bigint not null default 0 comment 'busi group id',
@@ -263,6 +295,7 @@ CREATE TABLE `alert_subscribe` (
KEY (`update_at`),
KEY (`group_id`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
CREATE TABLE `target` (
`id` bigint unsigned not null auto_increment,
`group_id` bigint not null default 0 comment 'busi group id',
@@ -275,6 +308,7 @@ CREATE TABLE `target` (
UNIQUE KEY (`ident`),
KEY (`group_id`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
-- case1: target_idents; case2: target_tags
-- CREATE TABLE `collect_rule` (
-- `id` bigint unsigned not null auto_increment,
@@ -295,6 +329,7 @@ CREATE TABLE `target` (
-- PRIMARY KEY (`id`),
-- KEY (`group_id`, `type`, `name`)
-- ) ENGINE=InnoDB DEFAULT CHARSET = utf8mb4;
CREATE TABLE `metric_view` (
`id` bigint unsigned not null auto_increment,
`name` varchar(191) not null default '',
@@ -306,7 +341,28 @@ CREATE TABLE `metric_view` (
PRIMARY KEY (`id`),
KEY (`create_by`)
) ENGINE=InnoDB DEFAULT CHARSET = utf8mb4;
insert into metric_view(name, cate, configs) values('Host View', 0, '{"filters":[{"oper":"=","label":"__name__","value":"cpu_usage_idle"}],"dynamicLabels":[],"dimensionLabels":[{"label":"ident","value":""}]}');
CREATE TABLE `recording_rule` (
`id` bigint unsigned not null auto_increment,
`group_id` bigint not null default '0' comment 'group_id',
`cluster` varchar(128) not null,
`name` varchar(255) not null comment 'new metric name',
`note` varchar(255) not null comment 'rule note',
`disabled` tinyint(1) not null comment '0:enabled 1:disabled',
`prom_ql` varchar(8192) not null comment 'promql',
`prom_eval_interval` int not null comment 'evaluate interval',
`append_tags` varchar(255) default '' comment 'split by space: service=n9e mod=api',
`create_at` bigint default '0',
`create_by` varchar(64) default '',
`update_at` bigint default '0',
`update_by` varchar(64) default '',
PRIMARY KEY (`id`),
KEY `group_id` (`group_id`),
KEY `update_at` (`update_at`)
) ENGINE=InnoDB DEFAULT CHARSET = utf8mb4;
CREATE TABLE `alert_aggr_view` (
`id` bigint unsigned not null auto_increment,
`name` varchar(191) not null default '',
@@ -318,8 +374,10 @@ CREATE TABLE `alert_aggr_view` (
PRIMARY KEY (`id`),
KEY (`create_by`)
) ENGINE=InnoDB DEFAULT CHARSET = utf8mb4;
insert into alert_aggr_view(name, rule, cate) values('By BusiGroup, Severity', 'field:group_name::field:severity', 0);
insert into alert_aggr_view(name, rule, cate) values('By RuleName', 'field:rule_name', 0);
CREATE TABLE `alert_cur_event` (
`id` bigint unsigned not null comment 'use alert_his_event.id',
`cluster` varchar(128) not null,
@@ -341,8 +399,10 @@ CREATE TABLE `alert_cur_event` (
`notify_channels` varchar(255) not null default '' comment 'split by space: sms voice email dingtalk wecom',
`notify_groups` varchar(255) not null default '' comment 'split by space: 233 43',
`notify_repeat_next` bigint not null default 0 comment 'next timestamp to notify, get repeat settings from rule',
`notify_cur_number` int not null default 0 comment '',
`target_ident` varchar(191) not null default '' comment 'target ident, also in tags',
`target_note` varchar(191) not null default '' comment 'target note',
`first_trigger_time` bigint,
`trigger_time` bigint not null,
`trigger_value` varchar(255) not null,
`tags` varchar(1024) not null default '' comment 'merge data_tags rule_tags, split by ,,',
@@ -352,6 +412,7 @@ CREATE TABLE `alert_cur_event` (
KEY (`trigger_time`, `group_id`),
KEY (`notify_repeat_next`)
) ENGINE=InnoDB DEFAULT CHARSET = utf8mb4;
CREATE TABLE `alert_his_event` (
`id` bigint unsigned not null AUTO_INCREMENT,
`is_recovered` tinyint(1) not null,
@@ -373,8 +434,10 @@ CREATE TABLE `alert_his_event` (
`notify_recovered` tinyint(1) not null comment 'whether notify when recovery',
`notify_channels` varchar(255) not null default '' comment 'split by space: sms voice email dingtalk wecom',
`notify_groups` varchar(255) not null default '' comment 'split by space: 233 43',
`notify_cur_number` int not null default 0 comment '',
`target_ident` varchar(191) not null default '' comment 'target ident, also in tags',
`target_note` varchar(191) not null default '' comment 'target note',
`first_trigger_time` bigint,
`trigger_time` bigint not null,
`trigger_value` varchar(255) not null,
`recover_time` bigint not null default 0,
@@ -385,6 +448,7 @@ CREATE TABLE `alert_his_event` (
KEY (`rule_id`),
KEY (`trigger_time`, `group_id`)
) ENGINE=InnoDB DEFAULT CHARSET = utf8mb4;
CREATE TABLE `task_tpl`
(
`id` int unsigned NOT NULL AUTO_INCREMENT,
@@ -405,6 +469,7 @@ CREATE TABLE `task_tpl`
PRIMARY KEY (`id`),
KEY (`group_id`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
CREATE TABLE `task_tpl_host`
(
`ii` int unsigned NOT NULL AUTO_INCREMENT,
@@ -413,6 +478,7 @@ CREATE TABLE `task_tpl_host`
PRIMARY KEY (`ii`),
KEY (`id`, `host`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
CREATE TABLE `task_record`
(
`id` bigint unsigned not null comment 'ibex task id',
@@ -433,4 +499,4 @@ CREATE TABLE `task_record`
PRIMARY KEY (`id`),
KEY (`create_at`, `group_id`),
KEY (`create_by`)
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;
) ENGINE = InnoDB DEFAULT CHARSET = utf8mb4;

View File

@@ -240,6 +240,12 @@ app: "{{ template "nightingale.name" . }}"
{{- end }}
{{- end -}}
{{- define "nightingale.redis.mode" -}}
{{- with .Values.redis }}
{{- ternary "standalone" .external.mode (eq .type "internal") }}
{{- end }}
{{- end -}}
/*scheme://[redis:password@]host:port[/master_set]*/
{{- define "nightingale.redis.url" -}}
{{- with .Values.redis }}
@@ -261,8 +267,8 @@ app: "{{ template "nightingale.name" . }}"
{{- printf "%s-prometheus" (include "nightingale.fullname" .) -}}
{{- end -}}
{{- define "nightingale.telegraf" -}}
{{- printf "%s-telegraf" (include "nightingale.fullname" .) -}}
{{- define "nightingale.categraf" -}}
{{- printf "%s-categraf" (include "nightingale.fullname" .) -}}
{{- end -}}
{{- define "nightingale.nwebapi" -}}

View File

@@ -14,12 +14,12 @@
# limitations under the License.
#
*/}}
{{- if eq .Values.telegraf.type "internal" -}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ServiceAccount
metadata:
name: "{{ template "nightingale.telegraf" . }}"
name: "{{ template "nightingale.categraf" . }}"
labels:
{{ include "nightingale.labels" . | indent 4 }}
component: telegraf
component: categraf
{{- end }}

View File

@@ -14,27 +14,15 @@
# limitations under the License.
#
*/}}
{{- if eq .Values.telegraf.type "internal" -}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: Service
kind: ConfigMap
metadata:
name: "{{ template "nightingale.telegraf" . }}"
labels:
{{ include "nightingale.labels" . | indent 4 }}
spec:
ports:
- name: "8125"
port: 8125
protocol: UDP
targetPort: 8125
- name: "8092"
port: 8092
protocol: UDP
targetPort: 8092
- name: "8094"
port: 8094
targetPort: 8094
selector:
{{ include "nightingale.matchLabels" . | indent 4 }}
component: telegraf
name: categraf-config
data:
config.toml: |-
{{ .Files.Get "categraf/conf/config.toml" | indent 4 }}
logs.toml: |-
{{ .Files.Get "categraf/conf/logs.toml" | indent 4 }}
{{- end -}}

View File

@@ -0,0 +1,25 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-cpu
data:
{{ (.Files.Glob "categraf/conf/input.cpu/*.toml").AsConfig | indent 2 }}
{{- end -}}

View File

@@ -0,0 +1,192 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: "{{ template "nightingale.categraf" . }}"
labels:
{{ include "nightingale.labels" . | indent 4 }}
component: categraf
spec:
selector:
matchLabels:
{{ include "nightingale.matchLabels" . | indent 6 }}
component: categraf
template:
metadata:
labels:
{{ include "nightingale.labels" . | indent 8 }}
component: categraf
annotations:
{{- if .Values.categraf.podAnnotations }}
{{ toYaml .Values.categraf.podAnnotations | indent 8 }}
{{- end }}
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: kubernetes.io/os
operator: In
values:
- linux
dnsPolicy: ClusterFirstWithHostNet
hostNetwork: true
restartPolicy: Always
tolerations:
- effect: NoSchedule
operator: Exists
serviceAccountName: {{ template "nightingale.categraf" . }}
containers:
- env:
- name: TZ
value: Asia/Shanghai
- name: HOSTNAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
- name: HOSTIP
valueFrom:
fieldRef:
fieldPath: status.hostIP
- name: "HOST_PROC"
value: "/hostfs/proc"
- name: "HOST_SYS"
value: "/hostfs/sys"
- name: "HOST_MOUNT_PREFIX"
value: "/hostfs"
image: {{ .Values.categraf.internal.image.repository }}:{{ .Values.categraf.internal.image.tag }}
name: categraf
volumeMounts:
- mountPath: /etc/categraf/conf/config.toml
name: categraf-config
subPath: config.toml
- mountPath: /etc/categraf/conf/logs.toml
name: categraf-config
subPath: logs.toml
- mountPath: /etc/categraf/conf/input.cpu
name: input-cpu
- mountPath: /etc/categraf/conf/input.mem
name: input-mem
- mountPath: /etc/categraf/conf/input.disk
name: input-disk
- mountPath: /etc/categraf/conf/input.diskio
name: input-diskio
- mountPath: /etc/categraf/conf/input.net
name: input-net
- mountPath: /etc/categraf/conf/input.netstat
name: input-netstat
{{- if and ( eq .Values.categraf.type "internal") ( .Values.categraf.internal.docker_socket) }}
- mountPath: /etc/categraf/conf/input.docker
name: input-docker
{{- end }}
- mountPath: /etc/categraf/conf/input.kubernetes
name: input-kubernetes
- mountPath: /etc/categraf/conf/input.prometheus
name: input-kubelet-metrics
- mountPath: /etc/categraf/conf/input.kernel
name: input-kernel
- mountPath: /etc/categraf/conf/input.kernel_vmstat
name: input-kernel-vmstat
- mountPath: /etc/categraf/conf/input.linux_sysctl_fs
name: input-sysctl-fs
- mountPath: /etc/categraf/conf/input.processes
name: input-processes
- mountPath: /etc/categraf/conf/input.system
name: input-system
- mountPath: /var/run/utmp
name: hostroutmp
readOnly: true
- mountPath: /hostfs
name: hostrofs
readOnly: true
{{- if and ( eq .Values.categraf.type "internal") ( .Values.categraf.internal.docker_socket) }}
- name: docker-socket
mountPath: {{ trimPrefix "unix://" .Values.categraf.internal.docker_socket }}
{{- end }}
volumes:
- name: categraf-config
configMap:
name: categraf-config
items:
- key: config.toml
path: config.toml
- key: logs.toml
path: logs.toml
- name: input-cpu
configMap:
name: input-cpu
- name: input-mem
configMap:
name: input-mem
- name: input-disk
configMap:
name: input-disk
- name: input-diskio
configMap:
name: input-diskio
- name: input-net
configMap:
name: input-net
- name: input-netstat
configMap:
name: input-netstat
{{- if and ( eq .Values.categraf.type "internal") ( .Values.categraf.internal.docker_socket) }}
- name: input-docker
configMap:
name: input-docker
{{- end }}
- name: input-kubernetes
configMap:
name: input-kubernetes
- name: input-kubelet-metrics
configMap:
name: input-kubelet-metrics
- name: input-kernel
configMap:
name: input-kernel
- name: input-kernel-vmstat
configMap:
name: input-kernel-vmstat
- name: input-sysctl-fs
configMap:
name: input-sysctl-fs
- name: input-processes
configMap:
name: input-processes
- name: input-system
configMap:
name: input-system
- name: hostrofs
hostPath:
path: /
- name: hostroutmp
hostPath:
path: /var/run/utmp
{{- if and ( eq .Values.categraf.type "internal") ( .Values.categraf.internal.docker_socket) }}
- name: docker-socket
hostPath:
path: {{ trimPrefix "unix://" .Values.categraf.internal.docker_socket }}
type: Socket
{{- end }}
{{- end -}}

View File

@@ -0,0 +1,25 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-disk
data:
{{ (.Files.Glob "categraf/conf/input.disk/*.toml").AsConfig | indent 2 }}
{{- end -}}

View File

@@ -0,0 +1,25 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-diskio
data:
{{ (.Files.Glob "categraf/conf/input.diskio/*.toml").AsConfig | indent 2 }}
{{- end -}}

View File

@@ -0,0 +1,27 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
{{- if .Values.categraf.internal.docker_socket -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-docker
data:
{{ (.Files.Glob "categraf/conf/input.docker/*.toml").AsConfig | indent 2 }}
{{- end -}}
{{- end -}}

View File

@@ -0,0 +1,25 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-kernel
data:
{{ (.Files.Glob "categraf/conf/input.kernel/*.toml").AsConfig | indent 2 }}
{{- end -}}

View File

@@ -0,0 +1,25 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-kernel-vmstat
data:
{{ (.Files.Glob "categraf/conf/input.kernel_vmstat/*.toml").AsConfig | indent 2 }}
{{- end -}}

View File

@@ -0,0 +1,24 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-kubelet-metrics
data:
{{ (.Files.Glob "categraf/conf/input.prometheus/*.toml").AsConfig | indent 2 }}
{{- end -}}

View File

@@ -0,0 +1,25 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-kubernetes
data:
{{ (.Files.Glob "categraf/conf/input.kubernetes/*.toml").AsConfig | indent 2 }}
{{- end -}}

View File

@@ -0,0 +1,25 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-mem
data:
{{ (.Files.Glob "categraf/conf/input.mem/*.toml").AsConfig | indent 2 }}
{{- end -}}

View File

@@ -0,0 +1,25 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-net
data:
{{ (.Files.Glob "categraf/conf/input.net/*.toml").AsConfig | indent 2 }}
{{- end -}}

View File

@@ -0,0 +1,25 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-netstat
data:
{{ (.Files.Glob "categraf/conf/input.netstat/*.toml").AsConfig | indent 2 }}
{{- end -}}

View File

@@ -0,0 +1,25 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-processes
data:
{{ (.Files.Glob "categraf/conf/input.processes/*.toml").AsConfig | indent 2 }}
{{- end -}}

View File

@@ -14,15 +14,15 @@
# limitations under the License.
#
*/}}
{{- if eq .Values.telegraf.type "internal" -}}
{{- if eq .Values.categraf.type "internal" -}}
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: "{{ template "nightingale.telegraf" . }}-stats-viewer"
name: "{{ template "nightingale.categraf" . }}-stats-viewer"
labels:
{{ include "nightingale.labels" . | indent 4 }}
component: telegraf
rbac.authorization.k8s.io/aggregate-view-telegraf-stats: "true"
component: categraf
rbac.authorization.k8s.io/aggregate-view-categraf-stats: "true"
rules:
- apiGroups: ["metrics.k8s.io"]
resources: ["pods"]
@@ -36,11 +36,11 @@ rules:
kind: ClusterRole
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: "{{ template "nightingale.telegraf" . }}"
name: "{{ template "nightingale.categraf" . }}"
aggregationRule:
clusterRoleSelectors:
- matchLabels:
rbac.authorization.k8s.io/aggregate-view-telegraf-stats: "true"
rbac.authorization.k8s.io/aggregate-view-categraf-stats: "true"
- matchLabels:
rbac.authorization.k8s.io/aggregate-to-view: "true"
rules: [] # Rules are automatically filled in by the controller manager.

View File

@@ -14,20 +14,20 @@
# limitations under the License.
#
*/}}
{{- if eq .Values.telegraf.type "internal" -}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: "{{ template "nightingale.telegraf" . }}"
name: "{{ template "nightingale.categraf" . }}"
labels:
{{ include "nightingale.labels" . | indent 4 }}
component: telegraf
component: categraf
subjects:
- kind: ServiceAccount
name: {{ template "nightingale.telegraf" . }}
name: {{ template "nightingale.categraf" . }}
namespace: {{ .Release.Namespace }}
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: "{{ template "nightingale.telegraf" . }}"
name: "{{ template "nightingale.categraf" . }}"
{{- end -}}

View File

@@ -0,0 +1,25 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-sysctl-fs
data:
{{ (.Files.Glob "categraf/conf/input.linux_sysctl_fs/*.toml").AsConfig | indent 2 }}
{{- end -}}

View File

@@ -0,0 +1,25 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.categraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: input-system
data:
{{ (.Files.Glob "categraf/conf/input.system/*.toml").AsConfig | indent 2 }}
{{- end -}}

View File

@@ -73,6 +73,7 @@ spec:
- mountPath: /var/lib/mysql/
name: database-data
- mountPath: /etc/my.cnf
subPath: my.cnf
name: database-config
- mountPath: /docker-entrypoint-initdb.d
name: database-initdb-config

View File

@@ -87,8 +87,9 @@ data:
[Redis]
Address = "{{ template "nightingale.redis.addr" . }}"
Password = "{{ template "nightingale.redis.password" . }}"
RedisType = "{{ template "nightingale.redis.mode"}}"
[DB]
DSN="{{ template "nightingale.database.username" . }}:{{ template "nightingale.database.rawPassword" . }}@tcp({{ template "nightingale.database" . }}:{{ template "nightingale.database.servicePort" . }})/{{ template "nightingale.database.name" . }}?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
DSN="{{ template "nightingale.database.username" . }}:{{ template "nightingale.database.rawPassword" . }}@tcp({{ template "nightingale.database.host" . }}:{{ template "nightingale.database.port" . }})/{{ template "nightingale.database.name" . }}?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
Debug = false
DBType = "mysql"
MaxLifetime = 7200
@@ -96,7 +97,7 @@ data:
MaxIdleConns = 50
TablePrefix = ""
[Reader]
Url = "http://{{ template "nightingale.prometheus" . }}:{{ template "nightingale.prometheus.servicePort" . }}"
Url = "http://{{ template "nightingale.prometheus.host" . }}:{{ template "nightingale.prometheus.servicePort" . }}"
BasicAuthUser = "{{ template "nightingale.prometheus.username" . }}"
BasicAuthPass = "{{ template "nightingale.prometheus.rawPassword" . }}"
Timeout = 30000
@@ -113,11 +114,11 @@ data:
QueueMaxSize = 200000
QueuePopSize = 2000
[[Writers]]
Url = "http://{{ template "nightingale.prometheus" . }}:{{ template "nightingale.prometheus.servicePort" . }}/api/v1/write"
Url = "http://{{ template "nightingale.prometheus.host" . }}:{{ template "nightingale.prometheus.servicePort" . }}/api/v1/write"
BasicAuthUser = "{{ template "nightingale.prometheus.username" . }}"
BasicAuthPass = "{{ template "nightingale.prometheus.rawPassword" . }}"
Timeout = 30000
DialTimeout = 10000
Timeout = 10000
DialTimeout = 3000
TLSHandshakeTimeout = 30000
ExpectContinueTimeout = 1000
IdleConnTimeout = 90000

View File

@@ -38,6 +38,10 @@ spec:
{{ toYaml .Values.nserver.podAnnotations | indent 8 }}
{{- end }}
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
containers:
- args:
- /app/n9e
@@ -62,7 +66,7 @@ spec:
name: nserver-template
- mountPath: /app/etc/script
name: nserver-script
hostname: nserver
# hostname: nserver
restartPolicy: Always
volumes:
- name: nserver-config

View File

@@ -27,6 +27,8 @@ data:
MetricsYamlFile = "/app/etc/metrics.yaml"
BuiltinAlertsDir = "/app/etc/alerts"
BuiltinDashboardsDir = "/app/etc/dashboards"
ClustersFrom = "config"
ClustersFromAPIs = []
[[NotifyChannels]]
Label = "邮箱"
Key = "email"
@@ -69,6 +71,10 @@ data:
AccessExpired = 1500
RefreshExpired = 10080
RedisKeyPrefix = "/jwt/"
[ProxyAuth]
Enable = false
HeaderUserNameKey = "X-User-Name"
DefaultRoles = ["Standard"]
[BasicAuth]
user001 = "ccc26da7b9aba533cbb263a36c07dcc5"
[AnonymousAccess]
@@ -105,8 +111,9 @@ data:
[Redis]
Address = "{{ template "nightingale.redis.addr" . }}"
Password = "{{ template "nightingale.redis.password" . }}"
RedisType = "{{ template "nightingale.redis.mode" . }}"
[DB]
DSN = "{{ template "nightingale.database.username" . }}:{{ template "nightingale.database.rawPassword" . }}@tcp({{ template "nightingale.database" . }}:{{ template "nightingale.database.servicePort" . }})/{{ template "nightingale.database.name" . }}?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
DSN = "{{ template "nightingale.database.username" . }}:{{ template "nightingale.database.rawPassword" . }}@tcp({{ template "nightingale.database.host" . }}:{{ template "nightingale.database.port" . }})/{{ template "nightingale.database.name" . }}?charset=utf8mb4&parseTime=True&loc=Local&allowNativePasswords=true"
Debug = true
DBType = "mysql"
MaxLifetime = 7200
@@ -115,21 +122,19 @@ data:
TablePrefix = ""
[[Clusters]]
Name = "Default"
Prom = "http://{{ template "nightingale.prometheus" . }}:{{ template "nightingale.prometheus.servicePort" .}}"
Prom = "http://{{ template "nightingale.prometheus.host" . }}:{{ template "nightingale.prometheus.servicePort" .}}"
BasicAuthUser = ""
BasicAuthPass = ""
Timeout = 30000
DialTimeout = 10000
TLSHandshakeTimeout = 30000
ExpectContinueTimeout = 1000
IdleConnTimeout = 90000
KeepAlive = 30000
MaxConnsPerHost = 0
MaxIdleConns = 100
DialTimeout = 3000
MaxIdleConnsPerHost = 100
[Ibex]
Address = "http://ibex:10090"
BasicAuthUser = "ibex"
BasicAuthPass = "ibex"
Timeout = 3000
[TargetMetrics]
TargetUp = '''max(max_over_time(target_up{ident=~"(%s)"}[%dm])) by (ident)'''
LoadPerCore = '''max(max_over_time(system_load_norm_1{ident=~"(%s)"}[%dm])) by (ident)'''
MemUtil = '''100-max(max_over_time(mem_available_percent{ident=~"(%s)"}[%dm])) by (ident)'''
{{- end -}}

View File

@@ -38,6 +38,10 @@ spec:
{{ toYaml .Values.nwebapi.podAnnotations | indent 8 }}
{{- end }}
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
containers:
- args:
- /app/n9e

View File

@@ -36,6 +36,10 @@ spec:
{{ include "nightingale.labels" . | indent 8 }}
component: prometheus
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
containers:
- args:
- --config.file=/etc/prometheus/prometheus.yml
@@ -47,7 +51,7 @@ spec:
env:
- name: TZ
value: Asia/Shanghai
image: prom/prometheus
image: {{ .Values.prometheus.internal.image.repository }}:{{ .Values.prometheus.internal.image.tag }}
name: prometheus
ports:
- containerPort: 9090

View File

@@ -1,69 +0,0 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.telegraf.type "internal" -}}
apiVersion: v1
kind: ConfigMap
metadata:
name: telegraf-config
data:
telegraf.conf: |-
[global_tags]
[agent]
interval = "15s"
round_interval = true
metric_batch_size = 1000
metric_buffer_limit = 10000
collection_jitter = "0s"
flush_interval = "10s"
flush_jitter = "0s"
precision = ""
hostname = "$HOSTNAME"
omit_hostname = false
[[outputs.opentsdb]]
host = "http://{{ template "nightingale.nserver" . }}"
port = {{ template "nightingale.nserver.servicePort" . }}
http_batch_size = 50
http_path = "/opentsdb/put"
debug = false
separator = "_"
[[inputs.cpu]]
percpu = true
totalcpu = true
collect_cpu_time = false
report_active = false
[[inputs.disk]]
ignore_fs = ["tmpfs", "devtmpfs", "devfs", "iso9660", "overlay", "aufs", "squashfs"]
[[inputs.diskio]]
[[inputs.kernel]]
[[inputs.mem]]
[[inputs.processes]]
[[inputs.swap]]
[[inputs.system]]
[[inputs.net]]
ignore_protocol_stats = true
[[inputs.netstat]]
{{- if .Values.telegraf.internal.docker_socket }}
[[inputs.docker]]
endpoint = {{ .Values.telegraf.internal.docker_socket | quote }}
{{- end }}
[[inputs.kubernetes]]
url = "https://$HOSTIP:10250"
bearer_token = "/var/run/secrets/kubernetes.io/serviceaccount/token"
insecure_skip_verify = true
{{- end -}}

View File

@@ -1,107 +0,0 @@
{{/*
# Copyright 2022 flashcat.cloud | 快猫星云
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
*/}}
{{- if eq .Values.telegraf.type "internal" -}}
{{- $telegraf := .Values.persistence.persistentVolumeClaim.telgraf -}}
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: "{{ template "nightingale.telegraf" . }}"
labels:
{{ include "nightingale.labels" . | indent 4 }}
component: telegraf
spec:
selector:
matchLabels:
{{ include "nightingale.matchLabels" . | indent 6 }}
component: telegraf
template:
metadata:
labels:
{{ include "nightingale.labels" . | indent 8 }}
component: telegraf
annotations:
{{- if .Values.telegraf.podAnnotations }}
{{ toYaml .Values.telegraf.podAnnotations | indent 8 }}
{{- end }}
spec:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: kubernetes.io/os
operator: In
values:
- linux
dnsPolicy: ClusterFirst
restartPolicy: Always
tolerations:
- effect: NoSchedule
operator: Exists
serviceAccountName: {{ template "nightingale.telegraf" . }}
containers:
- env:
- name: TZ
value: Asia/Shanghai
- name: HOSTNAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
- name: HOSTIP
valueFrom:
fieldRef:
fieldPath: status.hostIP
- name: "HOST_PROC"
value: "/hostfs/proc"
- name: "HOST_SYS"
value: "/hostfs/sys"
- name: "HOST_MOUNT_PREFIX"
value: "/hostfs"
image: {{ .Values.telegraf.internal.image.repository }}:{{ .Values.telegraf.internal.image.tag }}
name: telegraf
ports:
- containerPort: 8125
protocol: UDP
- containerPort: 8092
protocol: UDP
- containerPort: 8094
volumeMounts:
- mountPath: /etc/telegraf
name: telegraf-config
- mountPath: /var/run/utmp
name: hostroutmp
readOnly: true
- mountPath: /hostfs
name: hostrofs
readOnly: true
- name: docker-socket
mountPath: {{ trimPrefix "unix://" .Values.telegraf.internal.docker_socket }}
volumes:
- name: telegraf-config
configMap:
name: telegraf-config
- name: hostrofs
hostPath:
path: /
- name: hostroutmp
hostPath:
path: /var/run/utmp
- name: docker-socket
hostPath:
path: {{ trimPrefix "unix://" .Values.telegraf.internal.docker_socket }}
type: Socket
{{- end -}}

26
tpl/README.md Normal file
View File

@@ -0,0 +1,26 @@
# 告警消息模版文件
模版中可以使用的变量参考`AlertCurEvent`对象
模版语法如何使用可以参考[html/template](https://pkg.go.dev/html/template)
## 如何在告警模版中添加监控详情url
假设web的地址是http://127.0.0.1:18000/, 实际使用时用web地址替换该地址
在监控模版中添加以下行:
* dingtalk / wecom / feishu
```markdown
[监控详情](http://127.0.0.1:18000/metric/explorer?promql={{ .PromQl | escape }})
```
* mailbody
```html
<tr>
<th>监控详情:</th>
<td>
<a href="http://127.0.0.1:18000/metric/explorer?promql={{ .PromQl | escape }}" target="_blank">点击查看</a>
</td>
</tr>
```

View File

@@ -162,6 +162,7 @@ redis:
addr: "192.168.0.2:6379"
sentinelMasterSet: ""
password: ""
mode: "standalone"
podAnnotations: {}
prometheus:
@@ -185,18 +186,21 @@ prometheus:
password: ""
podAnnotations: {}
telegraf:
categraf:
type: internal
internal:
serviceAccountName: ""
automountServiceAccountToken: false
image:
repository: docker.io/library/telegraf
tag: 1.22-alpine
repository: flashcatcloud/categraf
tag: latest
nodeSelector: {}
tolerations: []
affinity: {}
priorityClassName:
## Parm: categraf.internal.docker_socket Desc: the path of docker socket on kubelet node.
## "unix:///var/run/docker.sock" is default, if your kubernetes runtime is container or others, empty this variable.
## docker_socket: ""
docker_socket: unix:///var/run/docker.sock
external:
host: "192.168.0.3"
@@ -211,8 +215,8 @@ nwebapi:
serviceAccountName: ""
automountServiceAccountToken: false
image:
repository: docker.io/ulric2019/nightingale
tag: 5.8.0
repository: flashcatcloud/nightingale
tag: 5.10.3
nodeSelector: {}
tolerations: []
affinity: {}
@@ -229,8 +233,8 @@ nserver:
serviceAccountName: ""
automountServiceAccountToken: false
image:
repository: docker.io/ulric2019/nightingale
tag: 5.8.0
repository: flashcatcloud/nightingale
tag: 5.10.3
nodeSelector: {}
tolerations: []
affinity: {}