zabbix_export: version: '7.0' template_groups: - uuid: 748ad4d098d447d492bb935c907f652f name: Templates/Databases templates: - uuid: 43596328d4d74a5592906a9e08e3fd96 template: 'TiDB PD by HTTP' name: 'TiDB PD by HTTP' description: | The template to monitor PD server of TiDB cluster by Zabbix that works without any external scripts. Most of the metrics are collected in one go, thanks to Zabbix bulk data collection. Don't forget to change the macros {$PD.URL}, {$PD.PORT}. Template `TiDB PD by HTTP` — collects metrics by HTTP agent from PD /metrics endpoint and from monitoring API. You can discuss this template or leave feedback on our forum https://www.zabbix.com/forum/zabbix-suggestions-and-feedback Generated by official Zabbix template tool "Templator" vendor: name: Zabbix version: 7.0-2 groups: - name: Templates/Databases items: - uuid: 5ddd6354810347e4b4995a65d8429daf name: 'Get cluster metrics' type: DEPENDENT key: pd.cluster_status.get_metrics delay: '0' history: '0' value_type: TEXT trends: '0' description: 'Get cluster metrics.' preprocessing: - type: JSONPATH parameters: - '$[?(@.name == "pd_cluster_status")]' error_handler: DISCARD_VALUE master_item: key: pd.get_metrics tags: - tag: component value: raw - uuid: 3a1fd879a08a445cbf438f3d68078111 name: 'Get instance metrics' type: HTTP_AGENT key: pd.get_metrics history: '0' value_type: TEXT trends: '0' description: 'Get TiDB PD instance metrics.' preprocessing: - type: CHECK_NOT_SUPPORTED parameters: - '-1' - type: PROMETHEUS_TO_JSON parameters: - '' url: '{$PD.URL}:{$PD.PORT}/metrics' tags: - tag: component value: raw - uuid: 7eb740eed4eb43a0a449e1c1436e582b name: 'Get instance status' type: HTTP_AGENT key: pd.get_status history: '0' value_type: TEXT trends: '0' description: 'Get TiDB PD instance status info.' preprocessing: - type: CHECK_NOT_SUPPORTED parameters: - '-1' error_handler: CUSTOM_VALUE error_handler_params: '{"status": "0"}' url: '{$PD.URL}:{$PD.PORT}/pd/api/v1/status' tags: - tag: component value: health - tag: component value: raw - uuid: 101266930d0747748bf3cbd9259e2818 name: 'gRPC Commands total, rate' type: DEPENDENT key: pd.grpc_command.rate delay: '0' value_type: FLOAT description: 'The rate at which gRPC commands are completed.' preprocessing: - type: JSONPATH parameters: - '$[?(@.name == "grpc_server_handling_seconds_count")].value.sum()' error_handler: DISCARD_VALUE - type: CHANGE_PER_SECOND parameters: - '' master_item: key: pd.get_metrics tags: - tag: component value: grpc - uuid: d6b8c44bcea14a08b7f5ed85bd596542 name: 'Get gRPC command metrics' type: DEPENDENT key: pd.grpc_commands.get_metrics delay: '0' history: '0' value_type: TEXT trends: '0' description: 'Get gRPC command metrics.' preprocessing: - type: JSONPATH parameters: - '$[?(@.name == "grpc_server_handling_seconds_count")]' error_handler: DISCARD_VALUE master_item: key: pd.get_metrics tags: - tag: component value: raw - uuid: 7d7581a14a4e4de197a000337d7b8c41 name: 'Get region metrics' type: DEPENDENT key: pd.regions.get_metrics delay: '0' history: '0' value_type: TEXT trends: '0' description: 'Get region metrics.' preprocessing: - type: JSONPATH parameters: - '$[?(@.name == "pd_scheduler_region_heartbeat")]' error_handler: DISCARD_VALUE master_item: key: pd.get_metrics tags: - tag: component value: raw - uuid: 6e6cc3d28b884372a2380b4732af438f name: 'Get region label metrics' type: DEPENDENT key: pd.region_labels.get_metrics delay: '0' history: '0' value_type: TEXT trends: '0' description: 'Get region label metrics.' preprocessing: - type: JSONPATH parameters: - '$[?(@.name == "pd_regions_label_level")]' error_handler: DISCARD_VALUE master_item: key: pd.get_metrics tags: - tag: component value: raw - uuid: 6d97b65149ef4880ae547fb3e82a68c0 name: 'Get region status metrics' type: DEPENDENT key: pd.region_status.get_metrics delay: '0' history: '0' value_type: TEXT trends: '0' description: 'Get region status metrics.' preprocessing: - type: JSONPATH parameters: - '$[?(@.name == "pd_regions_status")]' error_handler: DISCARD_VALUE master_item: key: pd.get_metrics tags: - tag: component value: raw - uuid: 78c65105fd4a4f24b67176331ee685b5 name: 'Get scheduler metrics' type: DEPENDENT key: pd.scheduler.get_metrics delay: '0' history: '0' value_type: TEXT trends: '0' description: 'Get scheduler metrics.' preprocessing: - type: JSONPATH parameters: - '$[?(@.name == "pd_scheduler_status" && @.labels.type == "allow")]' error_handler: DISCARD_VALUE master_item: key: pd.get_metrics tags: - tag: component value: raw - uuid: c18f702f68bf4fed94a598daffdada8a name: Status type: DEPENDENT key: pd.status delay: '0' value_type: CHAR trends: '0' description: 'Status of PD instance.' valuemap: name: 'Service state' preprocessing: - type: JSONPATH parameters: - $.status error_handler: CUSTOM_VALUE error_handler_params: '1' - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h master_item: key: pd.get_status tags: - tag: component value: health triggers: - uuid: ab1d0d23dad844099e42debb71512887 expression: 'last(/TiDB PD by HTTP/pd.status)=0' name: 'TiDB PD: Instance is not responding' priority: AVERAGE tags: - tag: scope value: availability - uuid: 0b71c8a5104b46ebbeabe0d708b6676e name: Uptime type: DEPENDENT key: pd.uptime delay: '0' value_type: FLOAT units: uptime description: 'The runtime of each PD instance.' preprocessing: - type: JSONPATH parameters: - $.start_timestamp - type: JAVASCRIPT parameters: - 'return (Math.floor(Date.now() / 1000) - Number(value));' master_item: key: pd.get_status tags: - tag: component value: application triggers: - uuid: 9f47a19f6f424df598e74c5a653ebf27 expression: 'last(/TiDB PD by HTTP/pd.uptime)<10m' name: 'TiDB PD: Instance has been restarted' event_name: 'TiDB PD: Instance has been restarted (uptime < 10m)' priority: INFO description: 'Uptime is less than 10 minutes.' manual_close: 'YES' tags: - tag: scope value: notice - uuid: c7e8e9bf01d04e5db25bd8eaafff3b80 name: Version type: DEPENDENT key: pd.version delay: '0' value_type: CHAR trends: '0' description: 'Version of the PD instance.' preprocessing: - type: JSONPATH parameters: - $.version - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 3h master_item: key: pd.get_status tags: - tag: component value: application triggers: - uuid: 6fb6045405af4c89b09750f57ada472a expression: 'last(/TiDB PD by HTTP/pd.version,#1)<>last(/TiDB PD by HTTP/pd.version,#2) and length(last(/TiDB PD by HTTP/pd.version))>0' name: 'TiDB PD: Version has changed' event_name: 'TiDB PD: Version has changed (new version: {ITEM.VALUE})' priority: INFO description: 'PD version has changed. Acknowledge to close the problem manually.' manual_close: 'YES' tags: - tag: scope value: notice discovery_rules: - uuid: cd1f27cf5f1d4f6f84032386ec7f8abb name: 'Cluster metrics discovery' type: DEPENDENT key: pd.cluster.discovery delay: '0' description: 'Discovery cluster specific metrics.' item_prototypes: - uuid: fe49e1de54214fb0ac882feb42fdee3b name: 'Number of regions' type: DEPENDENT key: 'pd.cluster_status.leader_count[{#SINGLETON}]' delay: '0' description: 'The total count of cluster Regions.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "leader_count")].value.first()' master_item: key: pd.cluster_status.get_metrics tags: - tag: component value: cluster - tag: component value: regions - uuid: 0950ba514e05447c8cfe726ec2d76944 name: 'Current peer count' type: DEPENDENT key: 'pd.cluster_status.region_count[{#SINGLETON}]' delay: '0' description: 'The current count of all cluster peers.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "region_count")].value.first()' master_item: key: pd.cluster_status.get_metrics tags: - tag: component value: cluster - tag: component value: peers - uuid: d39f58372e3f464c87b2ec42acdf2061 name: 'Storage capacity' type: DEPENDENT key: 'pd.cluster_status.storage_capacity[{#SINGLETON}]' delay: '0' value_type: FLOAT units: B description: 'The total storage capacity for this TiDB cluster.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "storage_capacity")].value.first()' - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h master_item: key: pd.cluster_status.get_metrics tags: - tag: component value: cluster - tag: component value: storage - uuid: c72e6a2f89d041c4bf764021b9bc182c name: 'Storage size' type: DEPENDENT key: 'pd.cluster_status.storage_size[{#SINGLETON}]' delay: '0' value_type: FLOAT units: B description: 'The storage size that is currently used by the TiDB cluster.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "storage_size")].value.first()' master_item: key: pd.cluster_status.get_metrics tags: - tag: component value: cluster - tag: component value: storage - uuid: 517cea991add45319d30047ac96fd9e4 name: 'Disconnect stores' type: DEPENDENT key: 'pd.cluster_status.store_disconnected[{#SINGLETON}]' delay: '0' description: 'The count of disconnected stores.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "store_disconnected_count")].value.first()' - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h master_item: key: pd.cluster_status.get_metrics tags: - tag: component value: cluster - tag: component value: stores trigger_prototypes: - uuid: 077d39f8ea194081a9d0c5dfdec4d1b5 expression: 'last(/TiDB PD by HTTP/pd.cluster_status.store_disconnected[{#SINGLETON}])>0' name: 'TiDB PD: 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: 'Down stores' type: DEPENDENT key: 'pd.cluster_status.store_down[{#SINGLETON}]' delay: '0' description: 'The count of down stores.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "store_down_count")].value.first()' - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h master_item: key: pd.cluster_status.get_metrics tags: - tag: component value: cluster - tag: component value: stores trigger_prototypes: - uuid: 526b935d3fa04825b7544eb6efd50ab5 expression: 'last(/TiDB PD by HTTP/pd.cluster_status.store_down[{#SINGLETON}])>0' name: 'TiDB PD: There are offline TiKV nodes' priority: AVERAGE description: 'PD has not received a TiKV heartbeat for a long time.' tags: - tag: scope value: availability - uuid: c3bd9d1e0f6c427ab5232e57769030d1 name: 'Lowspace stores' type: DEPENDENT key: 'pd.cluster_status.store_low_space[{#SINGLETON}]' delay: '0' description: 'The count of low space stores.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "store_low_space_count")].value.first()' - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h master_item: key: pd.cluster_status.get_metrics tags: - tag: component value: cluster - tag: component value: stores trigger_prototypes: - uuid: 87ef0f211afd4d58adec05007ef1d263 expression: 'last(/TiDB PD by HTTP/pd.cluster_status.store_low_space[{#SINGLETON}])>0' name: 'TiDB PD: 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: 'Offline stores' type: DEPENDENT key: 'pd.cluster_status.store_offline[{#SINGLETON}]' delay: '0' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "store_offline_count")].value.first()' - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h master_item: key: pd.cluster_status.get_metrics tags: - tag: component value: cluster - tag: component value: stores - uuid: 476a1b6e3c9b4b41ae1637f0e12801c9 name: 'Tombstone stores' type: DEPENDENT key: 'pd.cluster_status.store_tombstone[{#SINGLETON}]' delay: '0' description: 'The count of tombstone stores.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "store_tombstone_count")].value.first()' - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h master_item: key: pd.cluster_status.get_metrics tags: - tag: component value: cluster - tag: component value: stores - uuid: 89db2b996fbe41bdb6b82ccf75139090 name: 'Unhealth stores' type: DEPENDENT key: 'pd.cluster_status.store_unhealth[{#SINGLETON}]' delay: '0' description: 'The count of unhealthy stores.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "store_unhealth_count")].value.first()' - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h master_item: key: pd.cluster_status.get_metrics tags: - tag: component value: cluster - tag: component value: stores - uuid: ff80108e2a5e45779a428a6fd31ea089 name: 'Normal stores' type: DEPENDENT key: 'pd.cluster_status.store_up[{#SINGLETON}]' delay: '0' description: 'The count of healthy storage instances.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "store_up_count")].value.first()' - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h master_item: key: pd.cluster_status.get_metrics tags: - tag: component value: cluster - tag: component value: stores trigger_prototypes: - uuid: 843d566b33bc401390c2a633d08bb033 expression: 'min(/TiDB PD by HTTP/pd.cluster_status.storage_size[{#SINGLETON}],5m)/last(/TiDB PD by HTTP/pd.cluster_status.storage_capacity[{#SINGLETON}])*100>{$PD.STORAGE_USAGE.MAX.WARN}' name: 'TiDB PD: Current storage usage is too high' event_name: 'TiDB PD: Current storage usage is too high (over {$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 name: 'TiDB cluster: Storage Usage[{#SINGLETON}]' graph_items: - color: 199C0D item: host: 'TiDB PD by HTTP' key: 'pd.cluster_status.storage_size[{#SINGLETON}]' - sortorder: '1' color: F63100 item: host: 'TiDB PD by HTTP' key: 'pd.cluster_status.storage_capacity[{#SINGLETON}]' - uuid: 929dfe6f2ad74c9983ef6b11884b3abc name: 'TiDB cluster: Stores number by states[{#SINGLETON}]' graph_items: - color: 199C0D item: host: 'TiDB PD by HTTP' key: 'pd.cluster_status.store_up[{#SINGLETON}]' - sortorder: '1' color: F63100 item: host: 'TiDB PD by HTTP' key: 'pd.cluster_status.store_down[{#SINGLETON}]' - sortorder: '2' color: 00611C item: host: 'TiDB PD by HTTP' key: 'pd.cluster_status.store_unhealth[{#SINGLETON}]' - sortorder: '3' color: F7941D item: host: 'TiDB PD by HTTP' key: 'pd.cluster_status.store_low_space[{#SINGLETON}]' - sortorder: '4' color: FC6EA3 item: host: 'TiDB PD by HTTP' key: 'pd.cluster_status.store_tombstone[{#SINGLETON}]' - sortorder: '5' color: 6C59DC item: host: 'TiDB PD by HTTP' key: 'pd.cluster_status.store_disconnected[{#SINGLETON}]' - sortorder: '6' color: C7A72D item: host: 'TiDB PD by HTTP' key: 'pd.cluster_status.store_offline[{#SINGLETON}]' master_item: key: pd.cluster_status.get_metrics preprocessing: - type: JAVASCRIPT parameters: - 'return JSON.stringify(value != "[]" ? [{ ''{#SINGLETON}'': '''' }] : []);' - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h - uuid: 113c6ba7d7f74051b042241441c43db0 name: 'gRPC commands discovery' type: DEPENDENT key: pd.grpc_command.discovery delay: '0' description: 'Discovery grpc commands specific metrics.' item_prototypes: - uuid: 7b96abc0e68a405ea5693f4f445936fe name: 'gRPC Commands: {#GRPC_METHOD}, rate' type: DEPENDENT key: 'pd.grpc_command.rate[{#GRPC_METHOD}]' delay: '0' value_type: FLOAT description: 'The rate per command type at which gRPC commands are completed.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.grpc_method == "{#GRPC_METHOD}")].value.first()' - type: CHANGE_PER_SECOND parameters: - '' master_item: key: pd.grpc_commands.get_metrics tags: - tag: component value: grpc - tag: grpc_method value: '{#GRPC_METHOD}' master_item: key: pd.grpc_commands.get_metrics preprocessing: - type: JAVASCRIPT parameters: - | var lookup = {}, result = []; JSON.parse(value).forEach(function (item) { var grpc_method = item.labels.grpc_method; if (!(lookup[grpc_method])) { lookup[grpc_method] = 1; result.push({ "{#GRPC_METHOD}": grpc_method }); } }); return JSON.stringify(result); - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h - uuid: 2cb28d7c862d442a84b5942eb4b54e2f name: 'Region discovery' type: DEPENDENT key: pd.region.discovery delay: '0' description: 'Discovery region specific metrics.' item_prototypes: - uuid: 024bf1d31bbd40a49d683d962887c6e0 name: 'Region heartbeat: error, rate' type: DEPENDENT key: 'pd.region_heartbeat.error.rate[{#STORE_ADDRESS}]' delay: '0' value_type: FLOAT description: 'The count of heartbeats with the error status per second.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "report" && @.labels.status == "err")].value.sum()' error_handler: CUSTOM_VALUE error_handler_params: '0' - type: CHANGE_PER_SECOND parameters: - '' master_item: key: 'pd.region_heartbeat.get_metrics[{#STORE_ADDRESS}]' tags: - tag: address value: '{#STORE_ADDRESS}' - tag: component value: regions - uuid: 963c4d34d2664e6aba984f746b80b5c4 name: 'Get metrics: {#STORE_ADDRESS}' type: DEPENDENT key: 'pd.region_heartbeat.get_metrics[{#STORE_ADDRESS}]' delay: '0' history: '0' value_type: TEXT trends: '0' description: 'Get region metrics for {#STORE_ADDRESS}.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.address == "{#STORE_ADDRESS}")]' error_handler: DISCARD_VALUE master_item: key: pd.regions.get_metrics tags: - tag: address value: '{#STORE_ADDRESS}' - tag: component value: raw - uuid: 1d1d686f5c544a89a691a9b75e5c3b11 name: 'Region heartbeat: active, rate' type: DEPENDENT key: 'pd.region_heartbeat.ok.rate[{#STORE_ADDRESS}]' delay: '0' value_type: FLOAT description: 'The count of heartbeats with the ok status per second.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "report" && @.labels.status == "ok")].value.sum()' error_handler: CUSTOM_VALUE error_handler_params: '0' - type: CHANGE_PER_SECOND parameters: - '' master_item: key: 'pd.region_heartbeat.get_metrics[{#STORE_ADDRESS}]' tags: - tag: address value: '{#STORE_ADDRESS}' - tag: component value: regions - uuid: c44f934ce8a144afa95252041535ef44 name: 'Region schedule push: total, rate' type: DEPENDENT key: 'pd.region_heartbeat.push.err.rate[{#STORE_ADDRESS}]' delay: '0' value_type: FLOAT preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "push")].value.sum()' error_handler: CUSTOM_VALUE error_handler_params: '0' - type: CHANGE_PER_SECOND parameters: - '' master_item: key: 'pd.region_heartbeat.get_metrics[{#STORE_ADDRESS}]' tags: - tag: address value: '{#STORE_ADDRESS}' - tag: component value: regions - uuid: ea76344669de4251a0e7bef35d70494a name: 'Region heartbeat: total, rate' type: DEPENDENT key: 'pd.region_heartbeat.rate[{#STORE_ADDRESS}]' delay: '0' value_type: FLOAT description: 'The count of heartbeats reported to PD per instance per second.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "report")].value.sum()' error_handler: CUSTOM_VALUE error_handler_params: '0' - type: CHANGE_PER_SECOND parameters: - '' master_item: key: 'pd.region_heartbeat.get_metrics[{#STORE_ADDRESS}]' tags: - tag: address value: '{#STORE_ADDRESS}' - tag: component value: regions master_item: key: pd.regions.get_metrics preprocessing: - type: JAVASCRIPT parameters: - | var lookup = {}, result = []; JSON.parse(value).forEach(function (item) { var address = item.labels.address; if (!(lookup[address])) { lookup[address] = 1; result.push({ "{#STORE_ADDRESS}": address }); } }); return JSON.stringify(result); - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h - uuid: 771ba9e078a14ca489eb2acf906080e9 name: 'Region labels discovery' type: DEPENDENT key: pd.region_labels.discovery delay: '0' description: 'Discovery region labels specific metrics.' item_prototypes: - uuid: 117efc3f2fe64c51a18cd3be162185ea name: 'Regions label: {#TYPE}' type: DEPENDENT key: 'pd.region_labels[{#TYPE}]' delay: '0' value_type: FLOAT description: 'The number of Regions in different label levels.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "{#TYPE}")].value.first()' master_item: key: pd.region_labels.get_metrics tags: - tag: component value: regions - tag: type value: '{#TYPE}' master_item: key: pd.region_labels.get_metrics preprocessing: - type: JAVASCRIPT parameters: - | output = JSON.parse(value).map(function (item) { return { "{#TYPE}": item.labels.type, }; }); return JSON.stringify({ "data": output }); - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h - uuid: ffbf9adaa72842fdbb49c008625c1575 name: 'Region status discovery' type: DEPENDENT key: pd.region_status.discovery delay: '0' description: 'Discovery region status specific metrics.' item_prototypes: - uuid: 45ef4940b0454492b70116d8958c9b11 name: 'Regions status: {#TYPE}' type: DEPENDENT key: 'pd.region_status[{#TYPE}]' delay: '0' value_type: FLOAT description: 'The health status of Regions indicated via the count of unusual Regions including pending peers, down peers, extra peers, offline peers, missing peers, learner peers and incorrect namespaces.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.type == "{#TYPE}")].value.first()' master_item: key: pd.region_status.get_metrics tags: - tag: component value: regions - tag: type value: '{#TYPE}' trigger_prototypes: - uuid: 2bc6b48bbfd8436e80903ea947571501 expression: 'min(/TiDB PD by HTTP/pd.region_status[{#TYPE}],5m)>0' name: 'TiDB PD: There are unresponsive peers' discover: NO_DISCOVER priority: WARNING description: 'The number of Regions with an unresponsive peer reported by the Raft leader.' tags: - tag: scope value: availability - uuid: 1f80bd81d11345f59699617113a0cad5 expression: 'min(/TiDB PD by HTTP/pd.region_status[{#TYPE}],5m)>{$PD.MISS_REGION.MAX.WARN}' name: 'TiDB PD: Too many missed regions' event_name: 'TiDB PD: Too many missed regions (over {$PD.MISS_REGION.MAX.WARN} in 5m)' discover: NO_DISCOVER priority: WARNING description: 'The number of Region replicas is smaller than the value of max-replicas. When a TiKV machine is down and its downtime exceeds max-down-time, it usually leads to missing replicas for some Regions during a period of time. When a TiKV node is made offline, it might result in a small number of Regions with missing replicas.' tags: - tag: scope value: availability master_item: key: pd.region_status.get_metrics preprocessing: - type: JAVASCRIPT parameters: - | output = JSON.parse(value).map(function (item) { return { "{#TYPE}": item.labels.type, }; }); return JSON.stringify({ "data": output }); - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h overrides: - name: 'Too many missed regions trigger' step: '1' filter: conditions: - macro: '{#TYPE}' value: miss_peer_region_count formulaid: A operations: - operationobject: TRIGGER_PROTOTYPE operator: LIKE value: 'Too many missed regions' discover: DISCOVER status: ENABLED - name: 'Unresponsive peers trigger' step: '2' filter: conditions: - macro: '{#TYPE}' value: down_peer_region_count formulaid: A operations: - operationobject: TRIGGER_PROTOTYPE operator: LIKE value: 'There are unresponsive peers' discover: DISCOVER status: ENABLED - uuid: b4b8007810ad4f7ba8da212cdde5b71b name: 'Running scheduler discovery' type: DEPENDENT key: pd.scheduler.discovery delay: '0' description: 'Discovery scheduler specific metrics.' item_prototypes: - uuid: c6748a20540f49b293795bc72480dda7 name: 'Scheduler status: {#KIND}' type: DEPENDENT key: 'pd.scheduler[{#KIND}]' delay: '0' value_type: FLOAT description: 'The current running schedulers.' preprocessing: - type: JSONPATH parameters: - '$[?(@.labels.kind == "{#KIND}")].value.first()' error_handler: CUSTOM_VALUE error_handler_params: '0' master_item: key: pd.scheduler.get_metrics tags: - tag: component value: scheduler - tag: scheduler value: '{#KIND}' master_item: key: pd.scheduler.get_metrics preprocessing: - type: JAVASCRIPT parameters: - | output = JSON.parse(value).map(function (item) { return { "{#KIND}": item.labels.kind, }; }); return JSON.stringify({ "data": output }); - type: DISCARD_UNCHANGED_HEARTBEAT parameters: - 1h tags: - tag: class value: database - tag: target value: pd - tag: target value: tidb macros: - macro: '{$PD.MISS_REGION.MAX.WARN}' value: '100' description: 'Maximum number of missed regions' - macro: '{$PD.PORT}' value: '2379' description: 'The port of PD server metrics web endpoint' - macro: '{$PD.STORAGE_USAGE.MAX.WARN}' value: '80' description: 'Maximum percentage of cluster space used' - macro: '{$PD.URL}' value: localhost description: 'PD server URL' dashboards: - uuid: 5111f9dc22c645e09fd8d936ad71c792 name: 'PD: Overview' pages: - name: Main widgets: - type: item name: Status width: '12' fields: - type: ITEM name: itemid.0 value: host: 'TiDB PD by HTTP' key: pd.status - type: INTEGER name: show.0 value: '2' - type: INTEGER name: show.1 value: '4' - type: graphprototype 'y': '2' width: '36' height: '5' fields: - type: INTEGER name: columns value: '1' - type: GRAPH_PROTOTYPE name: graphid.0 value: host: 'TiDB PD by HTTP' name: 'TiDB cluster: Storage Usage[{#SINGLETON}]' - type: STRING name: reference value: AAAAA - type: item name: Uptime x: '12' width: '12' fields: - type: ITEM name: itemid.0 value: host: 'TiDB PD by HTTP' key: pd.uptime - type: INTEGER name: show.0 value: '2' - type: INTEGER name: show.1 value: '4' - type: item name: Version x: '24' width: '12' fields: - type: ITEM name: itemid.0 value: host: 'TiDB PD by HTTP' key: pd.version - type: INTEGER name: show.0 value: '2' - type: graphprototype x: '36' 'y': '2' width: '36' height: '5' fields: - type: INTEGER name: columns value: '1' - type: GRAPH_PROTOTYPE name: graphid.0 value: host: 'TiDB PD by HTTP' name: 'TiDB cluster: Stores number by states[{#SINGLETON}]' - type: STRING name: reference value: AAAAB valuemaps: - uuid: bce54cbdf2b8487985f9c7847a4c4918 name: 'Service state' mappings: - value: '0' newvalue: Down - value: '1' newvalue: Up