diff options
Diffstat (limited to 'templates/db/tidb_http')
3 files changed, 508 insertions, 220 deletions
diff --git a/templates/db/tidb_http/tidb_pd_http/template_db_tidb_pd_http.yaml b/templates/db/tidb_http/tidb_pd_http/template_db_tidb_pd_http.yaml index 69e23bcb624..e8b1c768a80 100644 --- a/templates/db/tidb_http/tidb_pd_http/template_db_tidb_pd_http.yaml +++ b/templates/db/tidb_http/tidb_pd_http/template_db_tidb_pd_http.yaml @@ -1,6 +1,6 @@ zabbix_export: version: '6.0' - date: '2021-12-16T07:40:17Z' + date: '2022-01-26T10:37:09Z' groups: - uuid: 748ad4d098d447d492bb935c907f652f @@ -19,7 +19,7 @@ zabbix_export: You can discuss this template or leave feedback on our forum https://www.zabbix.com/forum/zabbix-suggestions-and-feedback - Template tooling version used: 0.40 + Template tooling version used: 0.41 groups: - name: Templates/Databases @@ -45,8 +45,8 @@ zabbix_export: url: '{$PD.URL}:{$PD.PORT}/metrics' tags: - - tag: Application - value: 'Zabbix raw items' + tag: component + value: raw - uuid: 7eb740eed4eb43a0a449e1c1436e582b name: 'PD: Get instance status' @@ -66,8 +66,11 @@ zabbix_export: url: '{$PD.URL}:{$PD.PORT}/pd/api/v1/status' tags: - - tag: Application - value: 'Zabbix raw items' + tag: component + value: health + - + tag: component + value: raw - uuid: 101266930d0747748bf3cbd9259e2818 name: 'PD: GRPC Commands total, rate' @@ -91,8 +94,8 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'PD instance' + tag: component + value: grpc - uuid: c18f702f68bf4fed94a598daffdada8a name: 'PD: Status' @@ -120,14 +123,18 @@ zabbix_export: key: pd.get_status tags: - - tag: Application - value: 'PD instance' + tag: component + value: health triggers: - uuid: ab1d0d23dad844099e42debb71512887 expression: 'last(/TiDB PD by HTTP/pd.status)=0' name: 'PD: Instance is not responding' priority: AVERAGE + tags: + - + tag: scope + value: availability - uuid: 0b71c8a5104b46ebbeabe0d708b6676e name: 'PD: Uptime' @@ -153,8 +160,8 @@ zabbix_export: key: pd.get_status tags: - - tag: Application - value: 'PD instance' + tag: component + value: application triggers: - uuid: 9f47a19f6f424df598e74c5a653ebf27 @@ -163,6 +170,10 @@ zabbix_export: priority: INFO description: 'Uptime is less than 10 minutes' manual_close: 'YES' + tags: + - + tag: scope + value: notice - uuid: c7e8e9bf01d04e5db25bd8eaafff3b80 name: 'PD: Version' @@ -186,8 +197,8 @@ zabbix_export: key: pd.get_status tags: - - tag: Application - value: 'PD instance' + tag: component + value: application triggers: - uuid: 6fb6045405af4c89b09750f57ada472a @@ -196,6 +207,10 @@ zabbix_export: priority: INFO description: 'PD version has changed. Ack to close.' manual_close: 'YES' + tags: + - + tag: scope + value: notice discovery_rules: - uuid: cd1f27cf5f1d4f6f84032386ec7f8abb @@ -222,8 +237,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: cluster + - + tag: component + value: regions - uuid: 0950ba514e05447c8cfe726ec2d76944 name: 'TiDB cluster: Current peer count' @@ -241,8 +259,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: cluster + - + tag: component + value: peers - uuid: d39f58372e3f464c87b2ec42acdf2061 name: 'TiDB cluster: Storage capacity' @@ -266,8 +287,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: cluster + - + tag: component + value: storage - uuid: c72e6a2f89d041c4bf764021b9bc182c name: 'TiDB cluster: Storage size' @@ -287,8 +311,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: cluster + - + tag: component + value: storage - uuid: 517cea991add45319d30047ac96fd9e4 name: 'TiDB cluster: Disconnect stores' @@ -310,8 +337,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: cluster + - + tag: component + value: stores trigger_prototypes: - uuid: 077d39f8ea194081a9d0c5dfdec4d1b5 @@ -319,6 +349,10 @@ zabbix_export: name: 'TiDB cluster: There are disconnected TiKV nodes' priority: WARNING description: 'PD does not receive a TiKV heartbeat within 20 seconds. Normally a TiKV heartbeat comes in every 10 seconds.' + tags: + - + tag: scope + value: availability - uuid: 7125a7c858264f339e879c1389c6c027 name: 'TiDB cluster: Down stores' @@ -340,8 +374,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: cluster + - + tag: component + value: stores trigger_prototypes: - uuid: 526b935d3fa04825b7544eb6efd50ab5 @@ -349,6 +386,10 @@ zabbix_export: name: 'TiDB cluster: There are offline TiKV nodes' priority: AVERAGE description: 'PD has not received a TiKV heartbeat for a long time.' + tags: + - + tag: scope + value: availability - uuid: c3bd9d1e0f6c427ab5232e57769030d1 name: 'TiDB cluster: Lowspace stores' @@ -370,8 +411,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: cluster + - + tag: component + value: stores trigger_prototypes: - uuid: 87ef0f211afd4d58adec05007ef1d263 @@ -379,6 +423,10 @@ zabbix_export: name: 'TiDB cluster: There are low space TiKV nodes' priority: AVERAGE description: 'Indicates that there is no sufficient space on the TiKV node.' + tags: + - + tag: scope + value: capacity - uuid: 3c24fb49463b45f199dbc3955e87d01b name: 'TiDB cluster: Offline stores' @@ -399,8 +447,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: cluster + - + tag: component + value: stores - uuid: 476a1b6e3c9b4b41ae1637f0e12801c9 name: 'TiDB cluster: Tombstone stores' @@ -422,8 +473,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: cluster + - + tag: component + value: stores - uuid: 89db2b996fbe41bdb6b82ccf75139090 name: 'TiDB cluster: Unhealth stores' @@ -445,8 +499,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: cluster + - + tag: component + value: stores - uuid: ff80108e2a5e45779a428a6fd31ea089 name: 'TiDB cluster: Normal stores' @@ -468,8 +525,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: cluster + - + tag: component + value: stores trigger_prototypes: - uuid: 843d566b33bc401390c2a633d08bb033 @@ -477,6 +537,10 @@ zabbix_export: name: 'TiDB cluster: Current storage usage is too high (over {$PD.STORAGE_USAGE.MAX.WARN}% for 5m)' priority: WARNING description: 'Over {$PD.STORAGE_USAGE.MAX.WARN}% of the cluster space is occupied.' + tags: + - + tag: scope + value: capacity graph_prototypes: - uuid: 270de7aa73cf454cb147a3f5b39ebb35 @@ -540,8 +604,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'PD instance' + tag: component + value: grpc + - + tag: grpc_method + value: '{#GRPC_METHOD}' master_item: key: pd.get_metrics preprocessing: @@ -602,8 +669,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB Store [{#STORE_ADDRESS}]' + tag: address + value: '{#STORE_ADDRESS}' + - + tag: component + value: regions - uuid: 1d1d686f5c544a89a691a9b75e5c3b11 name: 'PD: Region heartbeat: active, rate' @@ -628,8 +698,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB Store [{#STORE_ADDRESS}]' + tag: address + value: '{#STORE_ADDRESS}' + - + tag: component + value: regions - uuid: c44f934ce8a144afa95252041535ef44 name: 'PD: Region schedule push: total, rate' @@ -653,8 +726,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB Store [{#STORE_ADDRESS}]' + tag: address + value: '{#STORE_ADDRESS}' + - + tag: component + value: regions - uuid: ea76344669de4251a0e7bef35d70494a name: 'PD: Region heartbeat: total, rate' @@ -679,8 +755,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB Store [{#STORE_ADDRESS}]' + tag: address + value: '{#STORE_ADDRESS}' + - + tag: component + value: regions master_item: key: pd.get_metrics preprocessing: @@ -735,8 +814,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: regions + - + tag: type + value: '{#TYPE}' master_item: key: pd.get_metrics preprocessing: @@ -784,8 +866,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: regions + - + tag: type + value: '{#TYPE}' trigger_prototypes: - uuid: 2bc6b48bbfd8436e80903ea947571501 @@ -794,6 +879,10 @@ zabbix_export: discover: NO_DISCOVER priority: WARNING description: 'The number of Regions with an unresponsive peer reported by the Raft leader.' + tags: + - + tag: scope + value: availability - uuid: 1f80bd81d11345f59699617113a0cad5 expression: 'min(/TiDB PD by HTTP/pd.region_status[{#TYPE}],5m)>{$PD.MISS_REGION.MAX.WARN}' @@ -801,6 +890,10 @@ zabbix_export: discover: NO_DISCOVER priority: WARNING description: 'The number of Region replicas is smaller than the value of max-replicas. When a TiKV machine is down and its downtime exceeds max-down-time, it usually leads to missing replicas for some Regions during a period of time. When a TiKV node is made offline, it might result in a small number of Regions with missing replicas.' + tags: + - + tag: scope + value: availability master_item: key: pd.get_metrics preprocessing: @@ -883,8 +976,11 @@ zabbix_export: key: pd.get_metrics tags: - - tag: Application - value: 'TiDB cluster' + tag: component + value: scheduler + - + tag: scheduler + value: '{#KIND}' master_item: key: pd.get_metrics preprocessing: @@ -906,6 +1002,16 @@ zabbix_export: type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h + tags: + - + tag: class + value: database + - + tag: target + value: pd + - + tag: target + value: tidb macros: - macro: '{$PD.MISS_REGION.MAX.WARN}' diff --git a/templates/db/tidb_http/tidb_tidb_http/template_db_tidb_tidb_http.yaml b/templates/db/tidb_http/tidb_tidb_http/template_db_tidb_tidb_http.yaml index 5f3a1c91946..39f70dfd01b 100644 --- a/templates/db/tidb_http/tidb_tidb_http/template_db_tidb_tidb_http.yaml +++ b/templates/db/tidb_http/tidb_tidb_http/template_db_tidb_tidb_http.yaml @@ -1,6 +1,6 @@ zabbix_export: version: '6.0' - date: '2021-12-16T07:09:48Z' + date: '2022-01-26T10:39:26Z' groups: - uuid: 748ad4d098d447d492bb935c907f652f @@ -19,7 +19,7 @@ zabbix_export: You can discuss this template or leave feedback on our forum https://www.zabbix.com/forum/zabbix-suggestions-and-feedback - Template tooling version used: 0.40 + Template tooling version used: 0.41 groups: - name: Templates/Databases @@ -51,8 +51,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: cpu - uuid: e1da33fc95ab46bcbe6bc6a68154d172 name: 'TiDB: DDL waiting jobs' @@ -71,14 +71,18 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: operations triggers: - uuid: 4125d55d9931455091d2f3a0b25e9678 expression: 'min(/TiDB by HTTP/tidb.ddl_waiting_jobs,5m)>{$TIDB.DDL.WAITING.MAX.WARN}' name: 'TiDB: Too many DDL waiting jobs (over {$TIDB.DDL.WAITING.MAX.WARN} for 5m)' priority: WARNING + tags: + - + tag: scope + value: performance - uuid: 0fe0c1dee67e469d9d38193ef7b040ec name: 'TiDB: Load schema failed, rate' @@ -102,14 +106,18 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: domain triggers: - uuid: b4948f37af804c01a2b8887f9e89ec90 expression: 'min(/TiDB by HTTP/tidb.domain_load_schema.failed.rate,5m)>{$TIDB.SCHEMA_LOAD_ERRORS.MAX.WARN}' name: 'TiDB: Too many schema lease errors (over {$TIDB.SCHEMA_LOAD_ERRORS.MAX.WARN} for 5m)' priority: AVERAGE + tags: + - + tag: scope + value: availability - uuid: b0e960ddac4d43a3860e8a06dfe09e03 name: 'TiDB: Load schema total, rate' @@ -132,8 +140,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: domain - uuid: 8fffe502bd2f42368e60d2110f1c3319 name: 'TiDB: Failed Query, rate' @@ -157,8 +165,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: sql - uuid: 954f5e433a7c44128d7772b87d493270 name: 'TiDB: Get instance metrics' @@ -180,8 +188,8 @@ zabbix_export: url: '{$TIDB.URL}:{$TIDB.PORT}/metrics' tags: - - tag: Application - value: 'Zabbix raw items' + tag: component + value: raw - uuid: e95ebe1050b8404f8274e243203fdecc name: 'TiDB: Get instance status' @@ -201,8 +209,11 @@ zabbix_export: url: '{$TIDB.URL}:{$TIDB.PORT}/status' tags: - - tag: Application - value: 'Zabbix raw items' + tag: component + value: health + - + tag: component + value: raw - uuid: 14cf8296365048a59fd42f03966b1e1e name: 'TiDB: Goroutine count' @@ -220,8 +231,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: goroutines - uuid: 78e60bd44e3e4a4a859705c94ef94420 name: 'TiDB: Heap memory usage' @@ -241,14 +252,18 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: memory triggers: - uuid: 575a4821ed8c4a1881b7f9bd264b1929 expression: 'min(/TiDB by HTTP/tidb.heap_bytes,5m)>{$TIDB.HEAP.USAGE.MAX.WARN}' name: 'TiDB: Heap memory usage is too high (over {$TIDB.HEAP.USAGE.MAX.WARN} for 5m)' priority: WARNING + tags: + - + tag: scope + value: capacity - uuid: 104c09cb47f640fb804c136a09aa3bd2 name: 'TiDB: Keep alive, rate' @@ -273,8 +288,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: health triggers: - uuid: eb3c09904fa843d78401b00eff4f6a08 @@ -282,6 +297,10 @@ zabbix_export: name: 'TiDB: Too few keep alive operations (less {$TIDB.MONITOR_KEEP_ALIVE.MAX.WARN} for 5m)' priority: AVERAGE description: 'Indicates whether the TiDB process still exists. If the number of times for tidb_monitor_keep_alive_total increases less than 10 per minute, the TiDB process might already exit and an alert is triggered.' + tags: + - + tag: scope + value: availability - uuid: d3ef55b9fd8b4a2aa1cbbc48f15203cb name: 'TiDB: Time jump back, rate' @@ -305,14 +324,18 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: application triggers: - uuid: c3c1f6eab224453b92534d5393aca2b7 expression: 'min(/TiDB by HTTP/tidb.monitor_time_jump_back.rate,5m)>{$TIDB.TIME_JUMP_BACK.MAX.WARN}' name: 'TiDB: Too many time jump backs (over {$TIDB.TIME_JUMP_BACK.MAX.WARN} for 5m)' priority: WARNING + tags: + - + tag: scope + value: performance - uuid: dce76be0ccbe44969bb09ad29d599790 name: 'TiDB: PD TSO commands, rate' @@ -336,8 +359,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: pd-commands - uuid: 2bde50849f5541c3ac8aa5b26f5b8b52 name: 'TiDB: PD TSO requests, rate' @@ -361,8 +384,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: pd-commands - uuid: ad8764623b8e46238efc0a94f0766a5b name: 'TiDB: Open file descriptors, max' @@ -381,8 +404,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: fds - uuid: 04b3d6bf810c449db1e4b79be6b263a9 name: 'TiDB: Open file descriptors' @@ -401,8 +424,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: fds - uuid: fbee374d0fda4679a693ccccc26e5713 name: 'TiDB: RSS memory usage' @@ -422,8 +445,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: memory - uuid: 651140aae7334994a31d24568c08a9ab name: 'TiDB: Total "error" server query, rate' @@ -447,8 +470,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: queries - uuid: 00374eab11a14ab1b4e636996519ab80 name: 'TiDB: Total "ok" server query, rate' @@ -472,8 +495,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: queries - uuid: 938e7bb83c714e198db55f3bb009daaf name: 'TiDB: Total server query, rate' @@ -497,8 +520,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: queries - uuid: 84824ff459b74679b33e34a1f1e8cc69 name: 'TiDB: Schema lease "change" errors, rate' @@ -524,8 +547,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: sessions - uuid: fe35df7cc7de4b0b8d616b042da99d69 name: 'TiDB: Schema lease "outdate" errors , rate' @@ -551,8 +574,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: sessions triggers: - uuid: b077eb1afe6a4da79707987324fb40c8 @@ -560,6 +583,10 @@ zabbix_export: name: 'TiDB: Too many schema lease errors (over {$TIDB.SCHEMA_LEASE_ERRORS.MAX.WARN} for 5m)' priority: AVERAGE description: 'The latest schema information is not reloaded in TiDB within one lease.' + tags: + - + tag: scope + value: availability - uuid: fe8cf5e5c7704db797e76fd9d64e6d17 name: 'TiDB: SQL statements, rate' @@ -582,8 +609,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: sql - uuid: ed86585a496b4b438c521c4765d76b11 name: 'TiDB: Status' @@ -611,14 +638,18 @@ zabbix_export: key: tidb.get_status tags: - - tag: Application - value: 'TiDB node' + tag: component + value: health triggers: - uuid: 82a638ac4a3f4b349ee7bb0d53bc1f29 expression: 'last(/TiDB by HTTP/tidb.status)=0' name: 'TiDB: Instance is not responding' priority: AVERAGE + tags: + - + tag: scope + value: availability - uuid: b5db09e71f2341b8ac1b9e48cbdefc82 name: 'TiDB: Server connections' @@ -636,8 +667,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: connections - uuid: 73992d4be61e443eafcc03aaa1bbf4a5 name: 'TiDB: Server critical error, rate' @@ -660,8 +691,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: server - uuid: f1e2436ced3c456a85650e0622715777 name: 'TiDB: Server panic, rate' @@ -685,8 +716,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: server triggers: - uuid: c457465731c947eab7b477186d8ba876 @@ -694,6 +725,10 @@ zabbix_export: name: 'TiDB: There are panicked TiDB threads' priority: AVERAGE description: 'When a panic occurs, an alert is triggered. The thread is often recovered, otherwise, TiDB will frequently restart.' + tags: + - + tag: scope + value: availability - uuid: 8a63b326356f4fdbb9cb6e73437348be name: 'TiDB: KV backoff, rate' @@ -718,8 +753,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: tikv-commands - uuid: aef7cdfd07f1420c970f20c821fed8dd name: 'TiDB: Lock resolves, rate' @@ -743,8 +778,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: tikv-commands - uuid: c116313e63fa45d89bf44772cc9cb3b8 name: 'TiDB: TiClient region errors, rate' @@ -768,14 +803,18 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: regions triggers: - uuid: d3cb81c46e414ff2a7e411a877b899ef expression: 'min(/TiDB by HTTP/tidb.tikvclient_region_err.rate,5m)>{$TIDB.REGION_ERROR.MAX.WARN}' name: 'TiDB: Too many region related errors (over {$TIDB.REGION_ERROR.MAX.WARN} for 5m)' priority: AVERAGE + tags: + - + tag: scope + value: performance - uuid: 8ddf164df8c9404ba9f7c0f87db3bc2f name: 'TiDB: KV commands, rate' @@ -799,8 +838,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: tikv-commands - uuid: 20c0fffd66c84a16bb4d8f7882c896bc name: 'TiDB: Uptime' @@ -826,8 +865,8 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: application triggers: - uuid: 91adc4c6b9364693891faf58c8cced75 @@ -836,6 +875,10 @@ zabbix_export: priority: INFO description: 'Uptime is less than 10 minutes' manual_close: 'YES' + tags: + - + tag: scope + value: notice - uuid: 65fa2b077073467387b39bef035b0644 name: 'TiDB: Version' @@ -859,8 +902,8 @@ zabbix_export: key: tidb.get_status tags: - - tag: Application - value: 'TiDB node' + tag: component + value: application triggers: - uuid: 5f863fc0944848fdad145f42c94dbea3 @@ -869,6 +912,10 @@ zabbix_export: priority: INFO description: 'TiDB version has changed. Ack to close.' manual_close: 'YES' + tags: + - + tag: scope + value: notice discovery_rules: - uuid: 4db735b652eb451d911f6dc01de6b1ba @@ -901,8 +948,11 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: tikv-commands + - + tag: type + value: '{#TYPE}' master_item: key: tidb.get_metrics preprocessing: @@ -954,8 +1004,11 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: queries + - + tag: type + value: '{#TYPE}' - uuid: 125bdd3eb1b643f4ad00d58fbed455f6 name: 'TiDB: Server query "OK": {#TYPE}, rate' @@ -979,8 +1032,11 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: queries + - + tag: type + value: '{#TYPE}' master_item: key: tidb.get_metrics preprocessing: @@ -1038,8 +1094,11 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: sql + - + tag: type + value: '{#TYPE}' master_item: key: tidb.get_metrics preprocessing: @@ -1091,8 +1150,11 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: tikv-backoff + - + tag: type + value: '{#TYPE}' master_item: key: tidb.get_metrics preprocessing: @@ -1145,8 +1207,11 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: gc + - + tag: type + value: '{#TYPE}' trigger_prototypes: - uuid: 2d24956d0a4f459fad155590376696c1 @@ -1154,6 +1219,10 @@ zabbix_export: name: 'TiDB: Too many failed GC-related operations (over {$TIDB.GC_ACTIONS.ERRORS.MAX.WARN} in 5m)' discover: NO_DISCOVER priority: WARNING + tags: + - + tag: scope + value: performance master_item: key: tidb.get_metrics preprocessing: @@ -1223,8 +1292,11 @@ zabbix_export: key: tidb.get_metrics tags: - - tag: Application - value: 'TiDB node' + tag: component + value: locks + - + tag: type + value: '{#TYPE}' master_item: key: tidb.get_metrics preprocessing: @@ -1245,6 +1317,13 @@ zabbix_export: type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h + tags: + - + tag: class + value: database + - + tag: target + value: tidb macros: - macro: '{$TIDB.DDL.WAITING.MAX.WARN}' @@ -1308,6 +1387,10 @@ zabbix_export: name: 'TiDB: Current number of open files is too high (over {$TIDB.OPEN.FDS.MAX.WARN}% for 5m)' priority: WARNING description: 'Heavy file descriptor usage (i.e., near the process''s file descriptor limit) indicates a potential file descriptor exhaustion issue.' + tags: + - + tag: scope + value: capacity graphs: - uuid: ee25671d0b5446348341be56967a74b2 diff --git a/templates/db/tidb_http/tidb_tikv_http/template_db_tidb_tikv_http.yaml b/templates/db/tidb_http/tidb_tikv_http/template_db_tidb_tikv_http.yaml index ae5033259aa..91f70555682 100644 --- a/templates/db/tidb_http/tidb_tikv_http/template_db_tidb_tikv_http.yaml +++ b/templates/db/tidb_http/tidb_tikv_http/template_db_tidb_tikv_http.yaml @@ -1,6 +1,6 @@ zabbix_export: version: '6.0' - date: '2021-12-16T07:40:23Z' + date: '2022-01-26T10:37:43Z' groups: - uuid: 748ad4d098d447d492bb935c907f652f @@ -19,7 +19,7 @@ zabbix_export: You can discuss this template or leave feedback on our forum https://www.zabbix.com/forum/zabbix-suggestions-and-feedback - Template tooling version used: 0.40 + Template tooling version used: 0.41 groups: - name: Templates/Databases @@ -46,8 +46,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: scheduler - uuid: b5ce79ee79804e76bb7b91e17915159c name: 'TiKV: Scheduler: Low priority commands total, rate' @@ -70,8 +70,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: scheduler - uuid: df3fa02457ac47168fad251727b300ff name: 'TiKV: Scheduler: Normal priority commands total, rate' @@ -94,8 +94,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: scheduler - uuid: dbf8288b5cab4e8a95b5e7c4355676bd name: 'TiKV: Coprocessor: Requests, rate' @@ -119,8 +119,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: coprocessor - uuid: d6185382a1974b9194e68bea4f14eb75 name: 'TiKV: Coprocessor: Errors, rate' @@ -145,14 +145,43 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: coprocessor triggers: - uuid: 31eca27ff6ce4ed78ee428ed3b8d8806 expression: 'min(/TiDB TiKV by HTTP/tikv.coprocessor_request_error.rate,5m)>{$TIKV.COPOCESSOR.ERRORS.MAX.WARN}' name: 'TiKV: Too many coprocessor request error (over {$TIKV.COPOCESSOR.ERRORS.MAX.WARN} in 5m)' priority: WARNING + tags: + - + tag: scope + value: performance + - + uuid: 5567ebf02fb6441dbb6672e1bc77b3ab + name: 'TiKV: Coprocessor: Response size, rate' + type: DEPENDENT + key: tikv.coprocessor_response_bytes.rate + delay: '0' + history: 7d + value_type: FLOAT + units: Bps + description: 'The total size of coprocessor response per second.' + preprocessing: + - + type: JSONPATH + parameters: + - '$[?(@.name == "tikv_coprocessor_response_bytes")].value.first()' + - + type: CHANGE_PER_SECOND + parameters: + - '' + master_item: + key: tikv.get_metrics + tags: + - + tag: component + value: coprocessor - uuid: 237f6ba2973e472d8c20de1d61b4695c name: 'TiKV: Coprocessor: RocksDB ops, rate' @@ -176,23 +205,23 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: coprocessor - - uuid: 5567ebf02fb6441dbb6672e1bc77b3ab - name: 'TiKV: Coprocessor: Response size, rate' + uuid: bfcec759c0894cf89c5267fc6b3862d7 + name: 'TiKV: Coprocessor: Scan keys, rate' type: DEPENDENT - key: tikv.coprocessor_scan_keys.rate + key: tikv.coprocessor_scan_keys_sum.rate delay: '0' history: 7d value_type: FLOAT - units: Bps - description: 'The total size of coprocessor response per second.' + units: Ops + description: 'Total number of scan keys observed per request per second.' preprocessing: - type: JSONPATH parameters: - - '$[?(@.name == "tikv_coprocessor_response_bytes")].value.first()' + - '$[?(@.name == "tikv_coprocessor_scan_keys")].value.sum()' - type: CHANGE_PER_SECOND parameters: @@ -201,8 +230,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: coprocessor - uuid: a76665b7a9924f8cbd4a455bc248d790 name: 'TiKV: CPU util' @@ -230,8 +259,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: cpu - uuid: 4558a5a11c304584bf24a7c3d2eace23 name: 'TiKV: Bytes read' @@ -251,8 +280,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: storage - uuid: 0d44c3c9a7f34905b0404ae39a3bc881 name: 'TiKV: Bytes write' @@ -272,8 +301,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: storage - uuid: f79d5daea61842b18e39c7289657ddf5 name: 'TiKV: Store size' @@ -293,8 +322,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: storage - uuid: 418bcc8c0bc440468efe833bef02929d name: 'TiKV: Get instance metrics' @@ -316,8 +345,8 @@ zabbix_export: url: '{$TIKV.URL}:{$TIKV.PORT}/metrics' tags: - - tag: Application - value: 'Zabbix raw items' + tag: component + value: raw - uuid: fed3db7222fa41a8bf51d2ad860a22d4 name: 'TiKV: Total query, rate' @@ -341,8 +370,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: queries - uuid: c68db41c184d44d98445cc66489ef39c name: 'TiKV: Total query errors, rate' @@ -367,8 +396,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: grpc - uuid: 7afa5147a1e247a5b8914d8739d31f15 name: 'TiKV: Server: failure messages total, rate' @@ -392,8 +421,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: application - uuid: e6137dd87faa496497b23cadaa37dca9 name: 'TiKV: Regions, count' @@ -411,8 +440,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: regions - uuid: 2ab7643435794ec6b5a2c3eb1dd7e913 name: 'TiKV: Regions, leader' @@ -430,8 +459,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: regions - uuid: 1c480fa23eaa42bcb367bb5afdcb65b9 name: 'TiKV: RSS memory usage' @@ -451,8 +480,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: memory - uuid: 62f856cf22804262aef64e9369049332 name: 'TiKV: Scheduler: Commands total, rate' @@ -477,38 +506,37 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: scheduler - - uuid: 8b7c2dc8c60e491db76cafd2d0e1234b - name: 'TiKV: Snapshot: Pending tasks' + uuid: 33a1b2f676134cf1b81771fbaf152f59 + name: 'TiKV: Scheduler: Pending commands' type: DEPENDENT key: tikv.scheduler_contex delay: '0' history: 7d - description: 'The number of tasks currently running by the worker or pending.' + description: 'The total number of pending commands. The scheduler receives commands from clients, executes them against the MVCC layer storage engine.' preprocessing: - type: JSONPATH parameters: - - '$[?(@.name == "tikv_worker_pending_task_total")].value.first()' + - '$[?(@.name == "tikv_scheduler_contex_total")].value.first()' master_item: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: scheduler triggers: - - uuid: be07ed23d6e040bd90866a4981d3c712 + uuid: 0f21c02b8e1c45d9bbe0c3313cea1a23 expression: 'min(/TiDB TiKV by HTTP/tikv.scheduler_contex,5m)>{$TIKV.PENDING_COMMANDS.MAX.WARN}' name: 'TiKV: Too many pending commands (over {$TIKV.PENDING_COMMANDS.MAX.WARN} for 5m)' priority: AVERAGE - - - uuid: f26874f910e34933983685ae43a90bee - expression: 'min(/TiDB TiKV by HTTP/tikv.scheduler_contex,5m)>{$TIKV.PENDING_TASKS.MAX.WARN}' - name: 'TiKV: Too many pending commands (over {$TIKV.PENDING_TASKS.MAX.WARN} for 5m)' - priority: AVERAGE + tags: + - + tag: scope + value: performance - uuid: 8f5c9d2b9eca4a489d764420ee06e4b6 name: 'TiKV: Scheduler: Busy, rate' @@ -532,8 +560,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: scheduler - uuid: 0a2d0a119bcd406aadfc5c014186c5d3 name: 'TiKV: Snapshot: Applying' @@ -551,8 +579,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: snapshot - uuid: 58559be859d64887a1b919e36aa1e336 name: 'TiKV: Snapshot: Receiving' @@ -570,8 +598,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: snapshot - uuid: 0ae6a2024ed3488498e22bc542d27619 name: 'TiKV: Snapshot: Sending' @@ -589,8 +617,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: snapshot - uuid: ce31318a420d40668e62a47fe19d3d40 name: 'TiKV: Storage: commands total, rate' @@ -613,8 +641,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: commands - uuid: fbfaa0d967c049c0a1bbcec5afea4bf2 name: 'TiKV: Available size' @@ -634,8 +662,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: storage - uuid: 1e0c1c071b604e77998797c2f9d41dfc name: 'TiKV: Capacity size' @@ -655,8 +683,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: storage - uuid: f2632dbd773140398a7d61608d85f392 name: 'TiKV: Uptime' @@ -682,8 +710,8 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: application triggers: - uuid: ca06602fa0b64a2ba0c51ed4835c52b2 @@ -692,6 +720,39 @@ zabbix_export: priority: INFO description: 'Uptime is less than 10 minutes' manual_close: 'YES' + tags: + - + tag: scope + value: notice + - + uuid: 8b7c2dc8c60e491db76cafd2d0e1234b + name: 'TiKV: Snapshot: Pending tasks' + type: DEPENDENT + key: tikv.worker_pending_task + delay: '0' + history: 7d + description: 'The number of tasks currently running by the worker or pending.' + preprocessing: + - + type: JSONPATH + parameters: + - '$[?(@.name == "tikv_worker_pending_task_total")].value.first()' + master_item: + key: tikv.get_metrics + tags: + - + tag: component + value: snapshot + triggers: + - + uuid: f26874f910e34933983685ae43a90bee + expression: 'min(/TiDB TiKV by HTTP/tikv.worker_pending_task,5m)>{$TIKV.PENDING_TASKS.MAX.WARN}' + name: 'TiKV: Too many pending tasks (over {$TIKV.PENDING_TASKS.MAX.WARN} for 5m)' + priority: AVERAGE + tags: + - + tag: scope + value: performance discovery_rules: - uuid: f1c7de94679e40a4ac6f569e05ad61d0 @@ -724,8 +785,11 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: coprocessor + - + tag: request + value: '{#REQ_TYPE}' - uuid: 08060401409b4fff97430c595fec7b82 name: 'TiKV: Coprocessor: {#REQ_TYPE} errors, rate' @@ -750,8 +814,11 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: coprocessor + - + tag: request + value: '{#REQ_TYPE}' - uuid: bff6ee970f7349edba6cac1cd0da70ed name: 'TiKV: Coprocessor: {#REQ_TYPE} RocksDB ops, rate' @@ -775,8 +842,11 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: coprocessor + - + tag: request + value: '{#REQ_TYPE}' - uuid: 8ef93de8a25b4f35b2e54f6ced4a5bd2 name: 'TiKV: Coprocessor: {#REQ_TYPE} scan keys, rate' @@ -800,8 +870,11 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: coprocessor + - + tag: request + value: '{#REQ_TYPE}' master_item: key: tikv.get_metrics preprocessing: @@ -850,8 +923,11 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: grpc + - + tag: type + value: '{#TYPE}' master_item: key: tikv.get_metrics preprocessing: @@ -904,8 +980,11 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: scheduler + - + tag: stage + value: '{#STAGE}' master_item: key: tikv.get_metrics preprocessing: @@ -963,8 +1042,14 @@ zabbix_export: key: tikv.get_metrics tags: - - tag: Application - value: 'TiKV node' + tag: component + value: stores + - + tag: message-type + value: '{#TYPE}' + - + tag: store + value: '{#STORE_ID}' trigger_prototypes: - uuid: 1f65b64824d64852aaa609df5f3e27fd @@ -973,6 +1058,10 @@ zabbix_export: discover: NO_DISCOVER priority: WARNING description: 'Indicates that the remote TiKV cannot be connected.' + tags: + - + tag: scope + value: availability master_item: key: tikv.get_metrics preprocessing: @@ -1013,6 +1102,16 @@ zabbix_export: value: 'Too many failure messages' status: ENABLED discover: DISCOVER + tags: + - + tag: class + value: database + - + tag: target + value: tidb + - + tag: target + value: tikv macros: - macro: '{$TIKV.COPOCESSOR.ERRORS.MAX.WARN}' |