diff --git a/src/data/quickstarts.json b/src/data/quickstarts.json index ce63cf4c..3eafaf4f 100644 --- a/src/data/quickstarts.json +++ b/src/data/quickstarts.json @@ -3671,14 +3671,14 @@ ], "alerts": [ { - "name": "Apdex Score", - "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", + "name": "High CPU Utilization", + "details": "This alert is triggered when the CPU Utilization is above 90%.", "type": "STATIC", "url": null }, { - "name": "High CPU Utilization", - "details": "This alert is triggered when the CPU Utilization is above 90%.", + "name": "Apdex Score", + "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", "type": "STATIC", "url": null }, @@ -4098,14 +4098,14 @@ ], "alerts": [ { - "name": "Apdex Score", - "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", + "name": "High CPU Utilization", + "details": "This alert is triggered when the CPU Utilization is above 90%.", "type": "STATIC", "url": null }, { - "name": "High CPU Utilization", - "details": "This alert is triggered when the CPU Utilization is above 90%.", + "name": "Apdex Score", + "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", "type": "STATIC", "url": null }, @@ -4230,20 +4230,20 @@ ], "alerts": [ { - "name": "Apdex Score", - "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", + "name": "Transaction Errors", + "details": "This alert is triggered when the the transactions fail more than 10% of the time in 5 minutes.", "type": "STATIC", "url": null }, { - "name": "High CPU Utilization", - "details": "This alert is triggered when the CPU Utilization is above 90%.", + "name": "Apdex Score", + "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", "type": "STATIC", "url": null }, { - "name": "Transaction Errors", - "details": "This alert is triggered when the the transactions fail more than 10% of the time in 5 minutes.", + "name": "High CPU Utilization", + "details": "This alert is triggered when the CPU Utilization is above 90%.", "type": "STATIC", "url": null } @@ -5457,27 +5457,27 @@ ], "dashboards": [ { - "name": "Redis Enterprise Cluster Metrics", + "name": "Redis Enterprise Database CRDT", "description": null, "url": null, "screenshots": [ - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/cluster/cluster01.png" + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/active-active/active_active01.png" ] }, { - "name": "Redis Enterprise Database Metrics", + "name": "Redis Enterprise Cluster Metrics", "description": null, "url": null, "screenshots": [ - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/database/database01.png" + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/cluster/cluster01.png" ] }, { - "name": "Redis Enterprise Database CRDT", + "name": "Redis Enterprise Database Metrics", "description": null, "url": null, "screenshots": [ - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/active-active/active_active01.png" + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/database/database01.png" ] } ], @@ -5529,20 +5529,20 @@ ], "alerts": [ { - "name": "High duration", - "details": "This alert is triggered when the total duration of the web transaction is longer than 10 seconds during 5 minutes", + "name": "Low throughput", + "details": "This alert is triggered when the throughput is 0 for 5 minutes", "type": "STATIC", "url": null }, { - "name": "High error rate", - "details": "This alert is triggered when the error percentage of web transactions is higher than 5% during 5 minutes", + "name": "High duration", + "details": "This alert is triggered when the total duration of the web transaction is longer than 10 seconds during 5 minutes", "type": "STATIC", "url": null }, { - "name": "Low throughput", - "details": "This alert is triggered when the throughput is 0 for 5 minutes", + "name": "High error rate", + "details": "This alert is triggered when the error percentage of web transactions is higher than 5% during 5 minutes", "type": "STATIC", "url": null } @@ -5893,6 +5893,15 @@ "New Relic" ], "dashboards": [ + { + "name": "SAP Dashboards", + "description": "Monitor SAP systems and applications performances", + "url": null, + "screenshots": [ + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/nrm4sap/sap-dashboard01.png", + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/nrm4sap/sap-dashboard02.png" + ] + }, { "name": "SAP Data Ingestion Estimate", "description": "Get an overview of the data volume ingested from SAP systems", @@ -5908,15 +5917,6 @@ "screenshots": [ "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/nrm4sap-datacollect/sap-data-collection01.png" ] - }, - { - "name": "SAP Dashboards", - "description": "Monitor SAP systems and applications performances", - "url": null, - "screenshots": [ - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/nrm4sap/sap-dashboard01.png", - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/nrm4sap/sap-dashboard02.png" - ] } ], "alerts": [ @@ -6413,12 +6413,6 @@ } ], "alerts": [ - { - "name": "Index Health", - "details": "This alert triggers when the reported health of an Elasticsearch index is 'red'.", - "type": "STATIC", - "url": null - }, { "name": "Cluster Health", "details": "This alert triggers when the reported health of an Elasticsearch cluster is 'red'.", @@ -6437,6 +6431,12 @@ "type": "STATIC", "url": null }, + { + "name": "Index Health", + "details": "This alert triggers when the reported health of an Elasticsearch index is 'red'.", + "type": "STATIC", + "url": null + }, { "name": "Indexing Latency Threshold", "details": "This alert will trigger when the Indexing latency for an Elasticsearch cluster's primary shards is >5ms.\nThis is measured by: # of Docs Indexed / Time spent Indexing (ms) for the evaluated time window.\nIncreased Flush Latency is an indication that you are trying to index too many documents at one time and you may need to reconfigured your settings to increase performance.", @@ -8541,6 +8541,100 @@ } ] }, + { + "title": "Etcd (remote write)", + "name": "etcd", + "description": "## What is Etcd?\n\nEtcd is a strongly consistent, distributed key-value store that provides a reliable way to store data that needs to be accessed by a distributed system or cluster of machines. It gracefully handles leader elections during network partitions and can tolerate machine failure, even in the leader node\n\n## Quickstart details\n\nThis quickstart was built based on `etcd` metrics sent to New Relic through remote write configurations with Prometheus Agent or Prometheus server.", + "packUrl": "https://github.com/newrelic/newrelic-quickstarts/tree/main/quickstarts/etcd", + "id": "83b4ef64-9af6-4bec-9707-674fa82c2837", + "level": "COMMUNITY", + "logoUrl": "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/quickstarts/etcd/logo.png", + "summary": "A curated dashboard based on Prometheus metrics which helps you understand the health of your Etcd cluster. This quickstart was built based on `etcd` metrics sent to New Relic through remote write configurations with Prometheus Agent or Prometheus server.", + "websiteUrl": null, + "keywords": [ + "etcd", + "kubernetes", + "k8s", + "prometheus", + "remote-write" + ], + "authors": [ + "New Relic", + "Brad Schmitt", + "Raga Potti" + ], + "dashboards": [ + { + "name": "Etcd (Prometheus)", + "description": "A dashboard for etcd based on metrics sent to New Relic using Prometheus Agent or Prometheus server.", + "url": null, + "screenshots": [ + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/etcd/etcd-dashboard-1.jpg", + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/etcd/etcd-dashboard-2.jpg" + ] + } + ], + "alerts": [ + { + "name": "Number Of Failed Server Proposals", + "details": "This alert is triggered when more than 5 proposals are failing in last 5 minutes", + "type": "STATIC", + "url": null + }, + { + "name": "High Commit Duration", + "details": "This alert is triggered when commit duration is high in instance", + "type": "STATIC", + "url": null + }, + { + "name": "Higher Number Of Failed GRPC requests", + "details": "This alert is triggered when more than 5 gRPC requests are failing in last 5 minutes", + "type": "STATIC", + "url": null + }, + { + "name": "Latency Of Fsync Called By Wal", + "details": "This alert is triggered when fsync durations are high in an instance", + "type": "STATIC", + "url": null + }, + { + "name": "Leader Changes", + "details": "This alert is triggered when more than 3 leader changes occured", + "type": "STATIC", + "url": null + }, + { + "name": "No Leader", + "details": "This alert is triggered when the etcd member has no leader", + "type": "STATIC", + "url": null + } + ], + "documentation": [ + { + "name": "Etcd Metrics Documentation", + "description": "Learn more about the Prometheus metrics available for Etcd", + "url": "https://etcd.io/docs/v3.5/metrics/" + }, + { + "name": "Prometheus installation docs", + "description": "Use Prometheus remote_write or Prometheus Agent", + "url": "https://docs.newrelic.com/docs/infrastructure/prometheus-integrations/install-configure-remote-write/set-your-prometheus-remote-write-integration/" + } + ], + "installPlans": [ + { + "name": "Prometheus remote write", + "id": "setup-prometheus" + }, + { + "name": "Prometheus Agent Mode", + "id": "setup-prometheus-agent-mode" + } + ] + }, { "title": "Amazon EC2", "name": "aws-ec2", @@ -9146,95 +9240,6 @@ } ] }, - { - "title": "Etcd", - "name": "etcd", - "description": "## What is Etcd?\n\nEtcd is a strongly consistent, distributed key-value store that provides a reliable way to store data that needs to be accessed by a distributed system or cluster of machines. It gracefully handles leader elections during network partitions and can tolerate machine failure, even in the leader node\n\n## Quickstart details\n\nThis quickstart was built based on `etcd` metrics sent to New Relic using Prometheus remote write. If using with the Prometheus OpenMetrics Integration, the dashboard widgets will require some modification.", - "packUrl": "https://github.com/newrelic/newrelic-quickstarts/tree/main/quickstarts/etcd", - "id": "83b4ef64-9af6-4bec-9707-674fa82c2837", - "level": "COMMUNITY", - "logoUrl": "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/quickstarts/etcd/logo.png", - "summary": "A curated dashboard based on Prometheus metrics which helps you understand the health of your Etcd cluster.", - "websiteUrl": null, - "keywords": [ - "etcd", - "kubernetes", - "k8s", - "prometheus", - "remote-write" - ], - "authors": [ - "New Relic", - "Brad Schmitt", - "Raga Potti" - ], - "dashboards": [ - { - "name": "Etcd Overview", - "description": "A dashboard for etcd based on Prometheus remote write metrics", - "url": null, - "screenshots": [ - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/etcd/dashboard.png" - ] - } - ], - "alerts": [ - { - "name": "High Commit Duration", - "details": "This alert is triggered when commit duration is high in instance", - "type": "STATIC", - "url": null - }, - { - "name": "Higher Number Of Failed GRPC requests", - "details": "This alert is triggered when more than 5 gRPC requests are failing in last 5 minutes", - "type": "STATIC", - "url": null - }, - { - "name": "Latency Of Fsync Called By Wal", - "details": "This alert is triggered when fsync durations are high in an instance", - "type": "STATIC", - "url": null - }, - { - "name": "Leader Changes", - "details": "This alert is triggered when more than 3 leader changes occured", - "type": "STATIC", - "url": null - }, - { - "name": "No Leader", - "details": "This alert is triggered when the etcd member has no leader", - "type": "STATIC", - "url": null - }, - { - "name": "Number Of Failed Server Proposals", - "details": "This alert is triggered when more than 5 proposals are failing in last 5 minutes", - "type": "STATIC", - "url": null - } - ], - "documentation": [ - { - "name": "Etcd Metrics Documentation", - "description": "Learn more about the Prometheus metrics available for Etcd", - "url": "https://etcd.io/docs/v3.5/metrics/" - }, - { - "name": "Prometheus Remote Write Configuration", - "description": "Configure your Prometheus Server to remote write metrics to New Relic", - "url": "https://docs.newrelic.com/docs/infrastructure/prometheus-integrations/install-configure-remote-write/set-your-prometheus-remote-write-integration/" - } - ], - "installPlans": [ - { - "name": "Prometheus remote write", - "id": "setup-prometheus" - } - ] - }, { "title": "Apache Camel Java Agent Extension", "name": "camel", @@ -10750,20 +10755,20 @@ ], "alerts": [ { - "name": "Apdex Score", - "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", + "name": "Transaction Errors", + "details": "This alert is triggered when the the transactions fail more than 10% of the time in 5 minutes.", "type": "STATIC", "url": null }, { - "name": "Memory Usage", - "details": "This alert is triggered when Memory usage is above 90%", + "name": "Apdex Score", + "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", "type": "STATIC", "url": null }, { - "name": "Transaction Errors", - "details": "This alert is triggered when the the transactions fail more than 10% of the time in 5 minutes.", + "name": "Memory Usage", + "details": "This alert is triggered when Memory usage is above 90%", "type": "STATIC", "url": null } @@ -12828,19 +12833,19 @@ ], "dashboards": [ { - "name": "Lacework Compliance Violations", + "name": "Lacework Security Overview", "description": null, "url": null, "screenshots": [ - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/lacework-compliance-violations/lacework-compliance-violations.png" + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/lacework-security-overview/lacework-security-overview.png" ] }, { - "name": "Lacework Security Overview", + "name": "Lacework Compliance Violations", "description": null, "url": null, "screenshots": [ - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/lacework-security-overview/lacework-security-overview.png" + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/lacework-compliance-violations/lacework-compliance-violations.png" ] }, { @@ -13177,14 +13182,14 @@ ], "alerts": [ { - "name": "Fastly CDN - Error Count by POP", - "details": "Excessive errors from a specific Fastly POP may indicate content deliver issues\nAlert examines error count and checks for 3σ (standard deviations)\nExceeding 3σ must exist for at least 5 minutes before the condition will trigger a notification", + "name": "Fastly CDN - Response Time (ms) by POP", + "details": "Excessive response time may impact customer experience\nAlert examines response time in milliseconds and checks for 3σ (standard deviations)\nExceeding 3σ must exist for at least 5 minutes before the condition will trigger a notification", "type": "BASELINE", "url": null }, { - "name": "Fastly CDN - Response Time (ms) by POP", - "details": "Excessive response time may impact customer experience\nAlert examines response time in milliseconds and checks for 3σ (standard deviations)\nExceeding 3σ must exist for at least 5 minutes before the condition will trigger a notification", + "name": "Fastly CDN - Error Count by POP", + "details": "Excessive errors from a specific Fastly POP may indicate content deliver issues\nAlert examines error count and checks for 3σ (standard deviations)\nExceeding 3σ must exist for at least 5 minutes before the condition will trigger a notification", "type": "BASELINE", "url": null } @@ -16049,14 +16054,14 @@ ], "alerts": [ { - "name": "High error rate", - "details": "This alert is triggered when the error percentage of web transactions is higher than 5% during 5 minutes", + "name": "High duration", + "details": "This alert is triggered when the total duration of the web transaction is longer than 10 seconds during 5 minutes", "type": "STATIC", "url": null }, { - "name": "High duration", - "details": "This alert is triggered when the total duration of the web transaction is longer than 10 seconds during 5 minutes", + "name": "High error rate", + "details": "This alert is triggered when the error percentage of web transactions is higher than 5% during 5 minutes", "type": "STATIC", "url": null }, @@ -16252,14 +16257,14 @@ ], "alerts": [ { - "name": "Transaction Errors", - "details": "This alert is triggered when the the transactions fail more than 10% of the time in 5 minutes.", + "name": "High CPU Utilization", + "details": "This alert is triggered when the CPU Utilization is above 90%.", "type": "STATIC", "url": null }, { - "name": "High CPU Utilization", - "details": "This alert is triggered when the CPU Utilization is above 90%.", + "name": "Transaction Errors", + "details": "This alert is triggered when the the transactions fail more than 10% of the time in 5 minutes.", "type": "STATIC", "url": null } @@ -16365,6 +16370,12 @@ } ], "alerts": [ + { + "name": "Transaction Errors", + "details": "This alert is triggered when the the transactions fail more than 10% of the time in 5 minutes.", + "type": "STATIC", + "url": null + }, { "name": "Apdex Score", "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", @@ -16382,12 +16393,6 @@ "details": "This alert is triggered when Memory usage is above 90%", "type": "STATIC", "url": null - }, - { - "name": "Transaction Errors", - "details": "This alert is triggered when the the transactions fail more than 10% of the time in 5 minutes.", - "type": "STATIC", - "url": null } ], "documentation": [ @@ -17103,14 +17108,14 @@ ], "alerts": [ { - "name": "Apdex Score", - "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", + "name": "High CPU Utilization", + "details": "This alert is triggered when the CPU Utilization is above 90%.", "type": "STATIC", "url": null }, { - "name": "High CPU Utilization", - "details": "This alert is triggered when the CPU Utilization is above 90%.", + "name": "Apdex Score", + "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", "type": "STATIC", "url": null }, @@ -18120,20 +18125,20 @@ ], "alerts": [ { - "name": "Failed Checkpoints", - "details": "This alert is triggered when the failed checkpoints is higher than 3 during 5 minutes.", + "name": "Task Manager Direct Memory Used", + "details": "This alert is triggered when the task manager direct memory used is higher than 100 MB during 5 minutes.", "type": "STATIC", "url": null }, { - "name": "Job Manager Heap Memory Usage", - "details": "This alert is triggered when the job manager heap memory usage is higher than 10 MB during 5 minutes.", + "name": "Failed Checkpoints", + "details": "This alert is triggered when the failed checkpoints is higher than 3 during 5 minutes.", "type": "STATIC", "url": null }, { - "name": "Task Manager Direct Memory Used", - "details": "This alert is triggered when the task manager direct memory used is higher than 100 MB during 5 minutes.", + "name": "Job Manager Heap Memory Usage", + "details": "This alert is triggered when the job manager heap memory usage is higher than 10 MB during 5 minutes.", "type": "STATIC", "url": null }, @@ -19444,20 +19449,20 @@ ], "alerts": [ { - "name": "Apdex Score", - "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", + "name": "Memory Usage", + "details": "This alert is triggered when Memory usage is above 90%", "type": "STATIC", "url": null }, { - "name": "High CPU Utilization", - "details": "This alert is triggered when the CPU Utilization is above 90%.", + "name": "Apdex Score", + "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", "type": "STATIC", "url": null }, { - "name": "Memory Usage", - "details": "This alert is triggered when Memory usage is above 90%", + "name": "High CPU Utilization", + "details": "This alert is triggered when the CPU Utilization is above 90%.", "type": "STATIC", "url": null }, @@ -20752,83 +20757,6 @@ } ] }, - { - "title": "CoreDNS Metrics", - "name": "coredns", - "description": "The CoreDNS quickstart provides a dashboard and set of alerts that provides a holistic view of the CoreDNS instances in your environment from telemetry collected through Prometheus Remote Write. This dashboard gives visibility into CoreDNS versions, status, request/response times, and cache statistics.", - "packUrl": "https://github.com/newrelic/newrelic-quickstarts/tree/main/quickstarts/coredns", - "id": "c9ac4abb-4a61-4eee-9e1e-79506806684e", - "level": "VERIFIED", - "logoUrl": "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/quickstarts/coredns/coredns-logo.png", - "summary": "Easily install a curated dashboard and alerts to monitor the health of your CoreDNS instances.", - "websiteUrl": null, - "keywords": [ - "coredns", - "prometheus", - "remote write", - "remote_write", - "remote-write", - "promql", - "grafana" - ], - "authors": [ - "New Relic", - "Brad Schmitt", - "Raga Potti" - ], - "dashboards": [ - { - "name": "CoreDNS Metrics", - "description": null, - "url": null, - "screenshots": [ - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/coredns/coredns-1.jpg", - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/coredns/coredns-2.jpg", - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/coredns/coredns-3.jpg", - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/coredns/coredns-4.jpg" - ] - } - ], - "alerts": [ - { - "name": "CoreDNS Error Rate", - "details": "This alert will trigger if the CoreDNS error rate for response codes NXDOMAIN, SERVFAIL, or REFUSED is above 2 standard deviations for more than 5 minutes.", - "type": "BASELINE", - "url": null - }, - { - "name": "CoreDNS Panics", - "details": "This alert will trigger if the CoreDNS panic rate is above 0 at least once in 5 minutes", - "type": "STATIC", - "url": null - }, - { - "name": "CoreDNS Request Duration", - "details": "This alert will trigger if the CoreDNS request duration 95th percentile is above or below 2 standard deviations for more than 5 minutes", - "type": "BASELINE", - "url": null - }, - { - "name": "CoreDNS Request Rate", - "details": "This alert will trigger if the CoreDNS requests per second is above or below 2 standard deviations for more than 5 minutes", - "type": "BASELINE", - "url": null - } - ], - "documentation": [ - { - "name": "Prometheus installation docs", - "description": "Use Prometheus remote_write or New Relic's Prometheus OpenMetrics integration\n", - "url": "https://docs.newrelic.com/docs/infrastructure/prometheus-integrations/install-configure-remote-write/set-your-prometheus-remote-write-integration/" - } - ], - "installPlans": [ - { - "name": "Prometheus remote write", - "id": "setup-prometheus" - } - ] - }, { "title": "OKHTTP", "name": "okhttp", @@ -20895,20 +20823,20 @@ ], "alerts": [ { - "name": "High error rate", - "details": "This alert is triggered when the error percentage of web transactions is higher than 5% during 5 minutes", + "name": "Low throughput", + "details": "This alert is triggered when the throughput is 0 for 5 minutes", "type": "STATIC", "url": null }, { - "name": "High duration", - "details": "This alert is triggered when the total duration of the web transaction is longer than 10 seconds during 5 minutes", + "name": "High error rate", + "details": "This alert is triggered when the error percentage of web transactions is higher than 5% during 5 minutes", "type": "STATIC", "url": null }, { - "name": "Low throughput", - "details": "This alert is triggered when the throughput is 0 for 5 minutes", + "name": "High duration", + "details": "This alert is triggered when the total duration of the web transaction is longer than 10 seconds during 5 minutes", "type": "STATIC", "url": null } @@ -20992,6 +20920,87 @@ } ] }, + { + "title": "CoreDNS Metrics (remote write)", + "name": "coredns", + "description": "The CoreDNS quickstart includes a dashboard and set of alerts that provides a holistic view of the CoreDNS instances in your environment. Information contained in the dasshboard includes CoreDNS versions, status, request/response times, and cache statistics. This quickstart was built and tested based on CoreDNS metrics sent to New Relic through remote write configurations with Prometheus Agent or Prometheus Server.", + "packUrl": "https://github.com/newrelic/newrelic-quickstarts/tree/main/quickstarts/coredns", + "id": "c9ac4abb-4a61-4eee-9e1e-79506806684e", + "level": "VERIFIED", + "logoUrl": "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/quickstarts/coredns/coredns-logo.png", + "summary": "Easily install a curated dashboard and alerts to monitor the health of your CoreDNS instances. This quickstart was built and tested based on CoreDNS metrics sent to New Relic through remote write configurations with Prometheus Agent or Prometheus Server.", + "websiteUrl": null, + "keywords": [ + "coredns", + "prometheus", + "remote write", + "remote_write", + "remote-write", + "promql", + "grafana" + ], + "authors": [ + "New Relic", + "Brad Schmitt", + "Raga Potti" + ], + "dashboards": [ + { + "name": "CoreDNS (Prometheus)", + "description": "A dashboard for CoreDNS based on metrics sent to New Relic using Prometheus Agent or Prometheus server.", + "url": null, + "screenshots": [ + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/coredns/coredns-dashboard-1.jpg", + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/coredns/coredns-dashboard-2.jpg", + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/coredns/coredns-dashboard-3.jpg", + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/coredns/coredns-dashboard-4.jpg" + ] + } + ], + "alerts": [ + { + "name": "CoreDNS Error Rate", + "details": "This alert will trigger if the CoreDNS error rate for response codes NXDOMAIN, SERVFAIL, or REFUSED is above 2 standard deviations for more than 5 minutes.", + "type": "BASELINE", + "url": null + }, + { + "name": "CoreDNS Panics", + "details": "This alert will trigger if the CoreDNS panic rate is above 0 at least once in 5 minutes", + "type": "STATIC", + "url": null + }, + { + "name": "CoreDNS Request Duration", + "details": "This alert will trigger if the CoreDNS request duration 95th percentile is above or below 2 standard deviations for more than 5 minutes", + "type": "BASELINE", + "url": null + }, + { + "name": "CoreDNS Request Rate", + "details": "This alert will trigger if the CoreDNS requests per second is above or below 2 standard deviations for more than 5 minutes", + "type": "BASELINE", + "url": null + } + ], + "documentation": [ + { + "name": "Prometheus installation docs", + "description": "Use Prometheus remote_write or Prometheus Agent\n", + "url": "https://docs.newrelic.com/docs/infrastructure/prometheus-integrations/install-configure-remote-write/set-your-prometheus-remote-write-integration/" + } + ], + "installPlans": [ + { + "name": "Prometheus remote write", + "id": "setup-prometheus" + }, + { + "name": "Prometheus Agent Mode", + "id": "setup-prometheus-agent-mode" + } + ] + }, { "title": "Amazon SageMaker", "name": "mlops-sagemaker", @@ -24696,11 +24705,11 @@ ] }, { - "name": "GCP Integrations Data Ingest Analysis", + "name": "Kubernetes Data Ingest Analysis", "description": null, "url": null, "screenshots": [ - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/gcp-integrations-data-ingest-analysis/gcp-integrations-data-ingest-analysis.png" + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/kubernetes-data-ingest-analysis/kubernetes-data-ingest-analysis.png" ] }, { @@ -24712,11 +24721,11 @@ ] }, { - "name": "Kubernetes Data Ingest Analysis", + "name": "GCP Integrations Data Ingest Analysis", "description": null, "url": null, "screenshots": [ - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/kubernetes-data-ingest-analysis/kubernetes-data-ingest-analysis.png" + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/gcp-integrations-data-ingest-analysis/gcp-integrations-data-ingest-analysis.png" ] } ], @@ -25600,6 +25609,12 @@ } ], "alerts": [ + { + "name": "Apdex Score", + "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", + "type": "STATIC", + "url": null + }, { "name": "High CPU Utilization", "details": "This alert is triggered when the CPU Utilization is above 90%.", @@ -25617,12 +25632,6 @@ "details": "This alert is triggered when the the transactions fail more than 10% of the time in 5 minutes.", "type": "STATIC", "url": null - }, - { - "name": "Apdex Score", - "details": "This alert is triggered when the Apdex score is below 0.5 for 5 minutes", - "type": "STATIC", - "url": null } ], "documentation": [ @@ -25680,19 +25689,19 @@ ] }, { - "name": "Browser Traffic Analysis", + "name": "Browser Pages Dashboard", "description": null, "url": null, "screenshots": [ - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/traffic-analysis/traffic_analysis.png" + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/browser-pages-dashboard/browser_pages_dashboard.png" ] }, { - "name": "Browser Pages Dashboard", + "name": "Browser Traffic Analysis", "description": null, "url": null, "screenshots": [ - "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/browser-pages-dashboard/browser_pages_dashboard.png" + "https://raw.githubusercontent.com/newrelic/newrelic-quickstarts/main/dashboards/traffic-analysis/traffic_analysis.png" ] } ],