Skip to content

N
nightingale

DiDi / nightingale
9 个月 前同步成功

通知 46
Star 7053
Fork 1161
N
nightingale

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

提交 995c5794 编写于 作者: N ning
浏览文件
操作

docs: update built-in alert rule

上级 7b58696b
展开全部 隐藏空白更改
内联 并排
Showing with 7730 addition and 2358 deletion
center/router/router_builtin.go
浏览文件 @ 995c5794
......@@ -91,6 +91,9 @@ func (rt *Router) builtinBoardCateGets(c *gin.Context) {
boardCate.Name = dir
files, err := file.FilesUnder(fp + "/" + dir + "/dashboards")
ginx.Dangerous(err)
if len(files) == 0 {
continue
}
var boards []Payload
for _, f := range files {
......@@ -243,6 +246,9 @@ func (rt *Router) builtinAlertRules(c *gin.Context) {
alertCate.Name = dir
files, err := file.FilesUnder(fp + "/" + dir + "/alerts")
ginx.Dangerous(err)
if len(files) == 0 {
continue
}
alertRules := make(map[string][]models.AlertRule)
for _, f := range files {
......
integrations/HTTP/alerts/http_response_by_categraf.json
浏览文件 @ 995c5794
[
{
"name": "http detect failed",
"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": [
{
"cate": "prometheus",
"datasource_ids": [
52
],
"name": "http detect failed",
"note": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "http_response_result_code != 0",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_days_of_weeks": [
[
"1",
"2",
"3",
......@@ -17,14 +56,18 @@
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
}
]
\ No newline at end of file
]
],
"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": [],
"annotations": null,
"extra_config": null
}
]
\ No newline at end of file
integrations/Kafka/alerts/kafka_by_categraf.json
浏览文件 @ 995c5794
[
{
"cate": "prometheus",
"datasource_ids": [
52
],
"name": "kafka 数据有丢失风险-副本数小于3",
"note": "",
"prod": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "sum(kafka_topic_partition_in_sync_replica) by (topic) < 3",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "sum(kafka_topic_partition_in_sync_replica) by (topic) < 3",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
......@@ -51,20 +69,40 @@
"append_tags": [
"service=kafka",
"type=categraf"
]
],
"annotations": null,
"extra_config": null
},
{
"cate": "prometheus",
"datasource_ids": [
52
],
"name": "kafka 服务宕机",
"note": "",
"prod": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 1,
"severities": [
1
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "kafka_broker_info{service=~\"kafka\"} < 1",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "kafka_broker_info{service=~\"kafka\"} < 1",
"severity": 1
}
],
"severity": 0
},
"prom_eval_interval": 60,
"enable_stime": "00:00",
"enable_stimes": [
......@@ -105,20 +143,40 @@
"append_tags": [
"type=categraf",
"service=kafka"
]
],
"annotations": null,
"extra_config": null
},
{
"cate": "prometheus",
"datasource_ids": [
52
],
"name": "kafka 消费能力不足-延迟超过5分钟",
"note": "",
"prod": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "max(kafka_consumer_lag_millis) by (topic, consumergroup) / 1000 > 300",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "max(kafka_consumer_lag_millis) by (topic, consumergroup) / 1000 > 300",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
......@@ -159,6 +217,8 @@
"append_tags": [
"service=kafka",
"type=categraf"
]
],
"annotations": null,
"extra_config": null
}
]
\ No newline at end of file
integrations/Kafka/alerts/kafka_by_exporter.json
浏览文件 @ 995c5794
[
{
"name": "Risk of data loss - number of replicas less than 3 - exporter",
"cate": "prometheus",
"datasource_ids": [
52
],
"name": "Insufficient consumption ability - delay exceeds 5 minutes - exporter",
"note": "",
"prod": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "sum(kafka_topic_partition_in_sync_replica) by (topic) < 3 - exporter",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "kafka_consumer_lag_millis / 1000 > 300",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -22,6 +47,17 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"1",
"2",
"3",
"4",
"5",
"6",
"0"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
......@@ -32,22 +68,49 @@
"runbook_url": "",
"append_tags": [
"service=kafka"
]
],
"annotations": null,
"extra_config": null
},
{
"name": "Insufficient consumption ability - delay exceeds 5 minutes - exporter",
"cate": "prometheus",
"datasource_ids": [
52
],
"name": "Risk of data loss - number of replicas less than 3 - exporter",
"note": "",
"prod": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "kafka_consumer_lag_millis / 1000 > 300",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "sum(kafka_topic_partition_in_sync_replica) by (topic) < 3 - exporter",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -57,6 +120,17 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"1",
"2",
"3",
"4",
"5",
"6",
"0"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
......@@ -67,6 +141,8 @@
"runbook_url": "",
"append_tags": [
"service=kafka"
]
],
"annotations": null,
"extra_config": null
}
]
\ No newline at end of file
integrations/Linux/alerts/linux_by_exporter.json
浏览文件 @ 995c5794
[
{
"name": "Insufficient inode resources - usage exceeds 90% - node exporter",
"cate": "prometheus",
"datasource_ids": [
0
],
"name": "A certain disk is unable to read/write normally",
"note": "",
"severity": 2,
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 1,
"severities": [
1
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "(100 - ((node_filesystem_files_free * 100) / node_filesystem_files))>90",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "(node_filesystem_device_error{instance=\"$node\",mountpoint!~\"/var/lib/.*\",mountpoint!~\"/run.*\"}) > 0",
"severity": 1
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -18,25 +47,68 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"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": []
"append_tags": [],
"annotations": null,
"extra_config": null
},
{
"name": "Insufficient memory resources - utilization is greater than 75% - node exporter",
"note": "Expansion or upgrading of configuration is required",
"severity": 2,
"cate": "prometheus",
"datasource_ids": [
0
],
"name": "Disk needs to be cleaned - utilization has reached 92% - node exporter",
"note": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 1,
"severities": [
1
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "(node_memory_MemTotal_bytes - node_memory_MemFree_bytes - (node_memory_Cached_bytes + node_memory_Buffers_bytes))/node_memory_MemTotal_bytes*100 > 75",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "(100 - ((node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes) ) > 92 ",
"severity": 1
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -46,27 +118,70 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"1",
"2",
"3",
"4",
"5",
"6",
"0"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [
"dingtalk"
],
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
"append_tags": [],
"annotations": null,
"extra_config": null
},
{
"name": "Insufficient memory resources - utilization is greater than 95% - node exporter",
"cate": "prometheus",
"datasource_ids": [
0
],
"name": "Insufficient computational resources - average load per core of the machine is greater than 10 - node exporter",
"note": "",
"severity": 1,
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "(node_memory_MemTotal_bytes - node_memory_MemFree_bytes - (node_memory_Cached_bytes + node_memory_Buffers_bytes))/node_memory_MemTotal_bytes*100 > 95",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "avg (node_load1) by (instance)/count(count(node_cpu_seconds_total) by (cpu,instance)) by (instance) >10",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -76,27 +191,68 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"1",
"2",
"3",
"4",
"5",
"6",
"0"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [
"dingtalk"
],
"notify_channels": [],
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
"append_tags": [],
"annotations": null,
"extra_config": null
},
{
"cate": "prometheus",
"datasource_ids": [
0
],
"name": "Insufficient file handles - usage exceeds 90% - node exporter",
"note": "You can increase the file handle limit or expand the capacity",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "(node_filefd_allocated{instance=\"$node\"}/node_filefd_maximum{instance=\"$node\"}*100) > 90",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "(node_filefd_allocated{instance=\"$node\"}/node_filefd_maximum{instance=\"$node\"}*100) > 90",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -106,25 +262,68 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"1",
"2",
"3",
"4",
"5",
"6",
"0"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
"append_tags": [],
"annotations": null,
"extra_config": null
},
{
"name": "A certain disk is unable to read/write normally",
"cate": "prometheus",
"datasource_ids": [
0
],
"name": "Insufficient inode resources - usage exceeds 90% - node exporter",
"note": "",
"severity": 1,
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "(node_filesystem_device_error{instance=\"$node\",mountpoint!~\"/var/lib/.*\",mountpoint!~\"/run.*\"}) > 0",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "(100 - ((node_filesystem_files_free * 100) / node_filesystem_files))>90",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -134,25 +333,68 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"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": []
"append_tags": [],
"annotations": null,
"extra_config": null
},
{
"name": "Disk needs to be cleaned - utilization has reached 92% - node exporter",
"note": "",
"severity": 1,
"cate": "prometheus",
"datasource_ids": [
0
],
"name": "Insufficient memory resources - utilization is greater than 75% - node exporter",
"note": "Expansion or upgrading of configuration is required",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "(100 - ((node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes) ) > 92 ",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "(node_memory_MemTotal_bytes - node_memory_MemFree_bytes - (node_memory_Cached_bytes + node_memory_Buffers_bytes))/node_memory_MemTotal_bytes*100 > 75",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -162,27 +404,70 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"1",
"2",
"3",
"4",
"5",
"6",
"0"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [
"dingtalk"
],
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
"append_tags": [],
"annotations": null,
"extra_config": null
},
{
"name": "System conntrack needs to be adjusted - usage exceeds 80% - node exporter",
"cate": "prometheus",
"datasource_ids": [
0
],
"name": "Insufficient memory resources - utilization is greater than 95% - node exporter",
"note": "",
"severity": 2,
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 1,
"severities": [
1
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "node_nf_conntrack_entries / node_nf_conntrack_entries_limit*100 > 80",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "(node_memory_MemTotal_bytes - node_memory_MemFree_bytes - (node_memory_Cached_bytes + node_memory_Buffers_bytes))/node_memory_MemTotal_bytes*100 > 95",
"severity": 1
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -192,25 +477,70 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"1",
"2",
"3",
"4",
"5",
"6",
"0"
]
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_channels": [
"dingtalk"
],
"notify_repeat_step": 60,
"notify_max_number": 0,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
"append_tags": [],
"annotations": null,
"extra_config": null
},
{
"name": "System experiences OOM - node exporter",
"cate": "prometheus",
"datasource_ids": [
0
],
"name": "Packet loss in the inbound direction of the network card - node exporter",
"note": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "increase(node_vmstat_oom_kill[1m]) > 0",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "rate(node_network_receive_drop_total{device=~\"e.*\"}[1m]) > 3",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -220,25 +550,68 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"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": []
"append_tags": [],
"annotations": null,
"extra_config": null
},
{
"name": "Packet loss in the inbound direction of the network card - node exporter",
"cate": "prometheus",
"datasource_ids": [
0
],
"name": "Packet loss in the outbound direction of the network card - node exporter",
"note": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "rate(node_network_receive_drop_total{device=~\"e.*\"}[1m]) > 3",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "rate(node_network_transmit_drop_total{device=~\"e.*\"}[1m]) > 3",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -248,25 +621,68 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"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": []
"append_tags": [],
"annotations": null,
"extra_config": null
},
{
"name": "Packet loss in the outbound direction of the network card - node exporter",
"cate": "prometheus",
"datasource_ids": [
0
],
"name": "System conntrack needs to be adjusted - usage exceeds 80% - node exporter",
"note": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "rate(node_network_transmit_drop_total{device=~\"e.*\"}[1m]) > 3",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "node_nf_conntrack_entries / node_nf_conntrack_entries_limit*100 > 80",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -276,25 +692,68 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"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": []
"append_tags": [],
"annotations": null,
"extra_config": null
},
{
"name": "Insufficient computational resources - average load per core of the machine is greater than 10 - node exporter",
"cate": "prometheus",
"datasource_ids": [
0
],
"name": "System experiences OOM - node exporter",
"note": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "avg (node_load1) by (instance)/count(count(node_cpu_seconds_total) by (cpu,instance)) by (instance) >10",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "increase(node_vmstat_oom_kill[1m]) > 0",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -304,25 +763,68 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"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": []
"append_tags": [],
"annotations": null,
"extra_config": null
},
{
"cate": "prometheus",
"datasource_ids": [
0
],
"name": "Too many running processes - exceeding 3000 - node exporter",
"note": "",
"prod": "metric",
"algorithm": "",
"algo_params": null,
"delay": 0,
"severity": 2,
"severities": [
2
],
"disabled": 1,
"prom_for_duration": 60,
"prom_ql": "node_procs_running > 3000",
"prom_ql": "",
"rule_config": {
"algo_params": null,
"inhibit": false,
"prom_ql": "",
"queries": [
{
"prom_ql": "node_procs_running > 3000",
"severity": 2
}
],
"severity": 0
},
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_stimes": [
"00:00"
],
"enable_etime": "23:59",
"enable_etimes": [
"23:59"
],
"enable_days_of_week": [
"1",
"2",
......@@ -332,13 +834,27 @@
"6",
"0"
],
"enable_days_of_weeks": [
[
"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": []
"append_tags": [],
"annotations": null,
"extra_config": null
}
]
\ No newline at end of file
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或