diff --git a/definitions/infra-awsefsfilesystem/definition.yml b/definitions/infra-awsefsfilesystem/definition.yml index f854c4b8b..418f829b0 100644 --- a/definitions/infra-awsefsfilesystem/definition.yml +++ b/definitions/infra-awsefsfilesystem/definition.yml @@ -1,5 +1,11 @@ domain: INFRA type: AWSEFSFILESYSTEM +goldenTags: +- aws.accountId +- aws.awsRegion +- aws.availabilityZone compositeMetrics: + goldenMetrics: + - golden_metrics.yml summaryMetrics: - summary_metrics.yml diff --git a/definitions/infra-awsefsfilesystem/golden_metrics.yml b/definitions/infra-awsefsfilesystem/golden_metrics.yml new file mode 100644 index 000000000..9ca2f506e --- /dev/null +++ b/definitions/infra-awsefsfilesystem/golden_metrics.yml @@ -0,0 +1,32 @@ +iops: + title: Total I/O (Bytes per sec) + query: + select: rate(sum(`provider.totalIOBytes.Sum`), 1 second) + from: BlockDeviceSample + where: provider='EfsFileSystem' + facet: entityName + eventId: entityGuid +iolimit: + title: I/O limit (%) + query: + select: max(`provider.percentIOLimit.Maximum`) + from: BlockDeviceSample + where: provider='EfsFileSystem' + facet: entityName + eventId: entityGuid +clientConnections: + title: Client Connections + query: + select: max(`provider.clientConnections.Sum`) + from: BlockDeviceSample + where: provider='EfsFileSystem' + facet: entityName + eventId: entityGuid +burstCreditBalance: + title: Burst Credit Balance + query: + select: average(`provider.burstCreditBalance.Average`) + from: BlockDeviceSample + where: provider='EfsFileSystem' + facet: entityName + eventId: entityGuid diff --git a/definitions/infra-awsefsfilesystem/summary_metrics.yml b/definitions/infra-awsefsfilesystem/summary_metrics.yml index a57366772..dca9954bf 100644 --- a/definitions/infra-awsefsfilesystem/summary_metrics.yml +++ b/definitions/infra-awsefsfilesystem/summary_metrics.yml @@ -6,14 +6,14 @@ providerAccountName: iops: query: eventId: entityGuid - select: sum(`provider.totalIOBytes.Sum`) + select: rate(sum(`provider.totalIOBytes.Sum`), 1 second) from: BlockDeviceSample - unit: BYTES + unit: BYTES_PER_SECOND title: Total I/O iolimit: query: eventId: entityGuid - select: 'max(`provider.percentIOLimit.Maximum`) ' + select: 'max(`provider.percentIOLimit.Maximum`)' from: BlockDeviceSample unit: PERCENTAGE title: I/O limit diff --git a/definitions/infra-awselasticachememcachedcluster/definition.yml b/definitions/infra-awselasticachememcachedcluster/definition.yml index 82177392d..d6c26cedd 100644 --- a/definitions/infra-awselasticachememcachedcluster/definition.yml +++ b/definitions/infra-awselasticachememcachedcluster/definition.yml @@ -1,8 +1,11 @@ domain: INFRA type: AWSELASTICACHEMEMCACHEDCLUSTER goldenTags: -- aws.availabilityZone - aws.accountId +- aws.awsRegion +- aws.customerAvailabilityZone +- aws.cacheNodeType +- aws.numCacheNodes compositeMetrics: goldenMetrics: - golden_metrics.yml diff --git a/definitions/infra-awselasticachememcachedcluster/golden_metrics.yml b/definitions/infra-awselasticachememcachedcluster/golden_metrics.yml index e50b984d8..fb4cc58a0 100644 --- a/definitions/infra-awselasticachememcachedcluster/golden_metrics.yml +++ b/definitions/infra-awselasticachememcachedcluster/golden_metrics.yml @@ -1,5 +1,5 @@ -cpuUsage: - title: CPU usage (%) +cpuUtilization: + title: CPU utilization (%) query: select: average(provider.cpuUtilization.Average) from: DatastoreSample @@ -14,3 +14,27 @@ swapUsageBytes: where: provider='ElastiCacheMemcachedCluster' facet: entityName eventId: entityGuid +freeableMemory: + title: Free memory (bytes) + query: + select: average(`provider.freeableMemory.Average`) + from: DatastoreSample + where: provider='ElastiCacheMemcachedCluster' + facet: entityName + eventId: entityGuid +networkBytesIn: + title: Bytes in per sec + query: + select: rate(sum(`provider.networkBytesIn.Sum`), 1 second) + from: DatastoreSample + where: provider='ElastiCacheMemcachedCluster' + facet: entityName + eventId: entityGuid +networkBytesOut: + title: Bytes out per sec + query: + select: rate(sum(`provider.networkBytesOut.Sum`), 1 second) + from: DatastoreSample + where: provider='ElastiCacheMemcachedCluster' + facet: entityName + eventId: entityGuid diff --git a/definitions/infra-awselasticachememcachedcluster/summary_metrics.yml b/definitions/infra-awselasticachememcachedcluster/summary_metrics.yml index fbd77852e..2dd789901 100644 --- a/definitions/infra-awselasticachememcachedcluster/summary_metrics.yml +++ b/definitions/infra-awselasticachememcachedcluster/summary_metrics.yml @@ -13,11 +13,11 @@ cpuUtilization: freeableMemory: query: eventId: entityGuid - select: sum(`provider.freeableMemory.Sum`) + select: average(`provider.freeableMemory.Average`) from: DatastoreSample unit: BYTES title: Free memory -memoryUtilization: +swapUsageBytes: query: eventId: entityGuid select: average(`provider.swapUsage.Average`) diff --git a/definitions/infra-awselasticachememcachednode/definition.yml b/definitions/infra-awselasticachememcachednode/definition.yml index f51a3f785..d035c549e 100644 --- a/definitions/infra-awselasticachememcachednode/definition.yml +++ b/definitions/infra-awselasticachememcachednode/definition.yml @@ -1,8 +1,11 @@ domain: INFRA type: AWSELASTICACHEMEMCACHEDNODE goldenTags: -- aws.availabilityZone - aws.accountId +- aws.awsRegion +- aws.customerAvailabilityZone +- aws.cacheClusterId +- aws.parameterGroupStatus compositeMetrics: goldenMetrics: - golden_metrics.yml diff --git a/definitions/infra-awselasticachememcachednode/golden_metrics.yml b/definitions/infra-awselasticachememcachednode/golden_metrics.yml index ac1053bfe..df5e23dbe 100644 --- a/definitions/infra-awselasticachememcachednode/golden_metrics.yml +++ b/definitions/infra-awselasticachememcachednode/golden_metrics.yml @@ -1,23 +1,47 @@ -cpuUsage: - title: CPU usage (%) +getThroughput: + title: Gets per sec query: - select: average(provider.cpuUtilization.Average) + select: rate(sum(provider.getHits.Sum)+sum(provider.getMisses.Sum), 1 second) from: DatastoreSample where: provider='ElastiCacheMemcachedNode' facet: entityName eventId: entityGuid -currentConnections: - title: Current connections +getMisses: + title: Get hit rate (%) query: - select: average(`provider.currConnections.Average`) + select: (sum(provider.getHits.Sum)/(sum(provider.getHits.Sum)+sum(provider.getMisses.Sum)))*100 from: DatastoreSample where: provider='ElastiCacheMemcachedNode' facet: entityName eventId: entityGuid evictedItems: - title: Evicted items + title: Evicted items per sec + query: + select: rate(sum(`provider.evictions.Sum`), 1 second) + from: DatastoreSample + where: provider='ElastiCacheMemcachedNode' + facet: entityName + eventId: entityGuid +swapUsage: + title: Swap Usage query: - select: average(`provider.evictions.Average`) + select: average(`provider.swapUsage.Average`) + from: DatastoreSample + where: provider='ElastiCacheMemcachedNode' + facet: entityName + eventId: entityGuid +cpuUtilization: + title: CPU utilization (%) + query: + select: average(provider.cpuUtilization.Average) + from: DatastoreSample + where: provider='ElastiCacheMemcachedNode' + facet: entityName + eventId: entityGuid +currentConnections: + title: Current connections + query: + select: average(`provider.currConnections.Average`) from: DatastoreSample where: provider='ElastiCacheMemcachedNode' facet: entityName diff --git a/definitions/infra-awselasticachememcachednode/summary_metrics.yml b/definitions/infra-awselasticachememcachednode/summary_metrics.yml index fbd77852e..56330b1b1 100644 --- a/definitions/infra-awselasticachememcachednode/summary_metrics.yml +++ b/definitions/infra-awselasticachememcachednode/summary_metrics.yml @@ -3,24 +3,24 @@ providerAccountName: key: providerAccountName title: AWS Account unit: STRING -cpuUtilization: +getThroughput: query: eventId: entityGuid - select: average(`provider.cpuUtilization.Average`) + select: rate(sum(provider.getHits.Sum)+sum(provider.getMisses.Sum), 1 second) from: DatastoreSample - unit: PERCENTAGE - title: CPU utilization -freeableMemory: + unit: REQUESTS_PER_SECOND + title: Get throughput +getHitRatio: query: eventId: entityGuid - select: sum(`provider.freeableMemory.Sum`) + select: (sum(provider.getHits.Sum)/(sum(provider.getHits.Sum)+sum(provider.getMisses.Sum)))*100 from: DatastoreSample - unit: BYTES - title: Free memory -memoryUtilization: + unit: PERCENTAGE + title: Get Hit Rate +swapUsage: query: eventId: entityGuid select: average(`provider.swapUsage.Average`) from: DatastoreSample unit: BYTES - title: Swap usage + title: Swap Usage diff --git a/definitions/infra-awselasticacherediscluster/definition.yml b/definitions/infra-awselasticacherediscluster/definition.yml index 8bf21319f..dbb732a74 100644 --- a/definitions/infra-awselasticacherediscluster/definition.yml +++ b/definitions/infra-awselasticacherediscluster/definition.yml @@ -1,8 +1,11 @@ domain: INFRA type: AWSELASTICACHEREDISCLUSTER goldenTags: -- aws.availabilityZone - aws.accountId +- aws.awsRegion +- aws.customerAvailabilityZone +- aws.cacheNodeType +- aws.numCacheNodes compositeMetrics: goldenMetrics: - golden_metrics.yml diff --git a/definitions/infra-awselasticacherediscluster/golden_metrics.yml b/definitions/infra-awselasticacherediscluster/golden_metrics.yml index 99077f2a8..62644648f 100644 --- a/definitions/infra-awselasticacherediscluster/golden_metrics.yml +++ b/definitions/infra-awselasticacherediscluster/golden_metrics.yml @@ -1,11 +1,19 @@ -cpuUsage: - title: CPU usage (%) +cpuUtilization: + title: CPU utilizacion (%) query: select: average(provider.cpuUtilization.Average) from: DatastoreSample where: provider='ElastiCacheRedisCluster' facet: entityName eventId: entityGuid +engineCpuUtilization: + title: Egine CPU utilization (%) + query: + select: average(provider.engineCpuUtilization.Average) + from: DatastoreSample + where: provider='ElastiCacheRedisCluster' + facet: entityName + eventId: entityGuid swapUsageBytes: title: Swap usage (bytes) query: @@ -14,3 +22,27 @@ swapUsageBytes: where: provider='ElastiCacheRedisCluster' facet: entityName eventId: entityGuid +freeableMemory: + title: Free memory (bytes) + query: + select: average(`provider.freeableMemory.Average`) + from: DatastoreSample + where: provider='ElastiCacheRedisCluster' + facet: entityName + eventId: entityGuid +networkBytesIn: + title: Bytes in per sec + query: + select: rate(sum(`provider.networkBytesIn.Sum`), 1 second) + from: DatastoreSample + where: provider='ElastiCacheRedisCluster' + facet: entityName + eventId: entityGuid +networkBytesOut: + title: Bytes out per sec + query: + select: rate(sum(`provider.networkBytesOut.Sum`), 1 second) + from: DatastoreSample + where: provider='ElastiCacheRedisCluster' + facet: entityName + eventId: entityGuid diff --git a/definitions/infra-awselasticacherediscluster/summary_metrics.yml b/definitions/infra-awselasticacherediscluster/summary_metrics.yml index fbd77852e..f81e959e2 100644 --- a/definitions/infra-awselasticacherediscluster/summary_metrics.yml +++ b/definitions/infra-awselasticacherediscluster/summary_metrics.yml @@ -13,7 +13,7 @@ cpuUtilization: freeableMemory: query: eventId: entityGuid - select: sum(`provider.freeableMemory.Sum`) + select: average(`provider.freeableMemory.Average`) from: DatastoreSample unit: BYTES title: Free memory diff --git a/definitions/infra-awselasticacheredisnode/definition.yml b/definitions/infra-awselasticacheredisnode/definition.yml index 619640102..03020a0f7 100644 --- a/definitions/infra-awselasticacheredisnode/definition.yml +++ b/definitions/infra-awselasticacheredisnode/definition.yml @@ -1,8 +1,11 @@ domain: INFRA type: AWSELASTICACHEREDISNODE goldenTags: -- aws.availabilityZone - aws.accountId +- aws.awsRegion +- aws.customerAvailabilityZone +- aws.cacheClusterId +- aws.parameterGroupStatus compositeMetrics: goldenMetrics: - golden_metrics.yml diff --git a/definitions/infra-awselasticacheredisnode/golden_metrics.yml b/definitions/infra-awselasticacheredisnode/golden_metrics.yml index b7ca69ff5..7cb2e372e 100644 --- a/definitions/infra-awselasticacheredisnode/golden_metrics.yml +++ b/definitions/infra-awselasticacheredisnode/golden_metrics.yml @@ -1,23 +1,47 @@ -cpuUsage: - title: CPU usage (%) +readThroughput: + title: Reads per sec query: - select: average(provider.cpuUtilization.Average) + select: rate(sum(provider.cacheHits.Sum)+sum(provider.cacheMisses.Sum), 1 second) from: DatastoreSample where: provider='ElastiCacheRedisNode' facet: entityName eventId: entityGuid -currentConnections: - title: Current connections +cacheHitRate: + title: Cache hit rate (%) query: - select: average(`provider.currConnections.Average`) + select: (sum(provider.cacheHits.Sum)/(sum(provider.cacheHits.Sum)+sum(provider.cacheMisses.Sum)))*100 from: DatastoreSample where: provider='ElastiCacheRedisNode' facet: entityName eventId: entityGuid evictedItems: - title: Evicted items + title: Evicted items per sec + query: + select: rate(sum(`provider.evictions.Sum`), 1 second) + from: DatastoreSample + where: provider='ElastiCacheRedisNode' + facet: entityName + eventId: entityGuid +swapUsage: + title: Swap Usage query: - select: average(`provider.evictions.Average`) + select: average(`provider.swapUsage.Average`) + from: DatastoreSample + where: provider='ElastiCacheRedisNode' + facet: entityName + eventId: entityGuid +cpuUtilization: + title: CPU utilization (%) + query: + select: average(provider.cpuUtilization.Average) + from: DatastoreSample + where: provider='ElastiCacheRedisNode' + facet: entityName + eventId: entityGuid +currentConnections: + title: Current connections + query: + select: average(`provider.currConnections.Average`) from: DatastoreSample where: provider='ElastiCacheRedisNode' facet: entityName diff --git a/definitions/infra-awselasticacheredisnode/summary_metrics.yml b/definitions/infra-awselasticacheredisnode/summary_metrics.yml index fbd77852e..2f9243752 100644 --- a/definitions/infra-awselasticacheredisnode/summary_metrics.yml +++ b/definitions/infra-awselasticacheredisnode/summary_metrics.yml @@ -3,24 +3,24 @@ providerAccountName: key: providerAccountName title: AWS Account unit: STRING -cpuUtilization: +readThroughput: query: eventId: entityGuid - select: average(`provider.cpuUtilization.Average`) + select: rate(sum(provider.cacheHits.Sum)+sum(provider.cacheMisses.Sum), 1 second) from: DatastoreSample - unit: PERCENTAGE - title: CPU utilization -freeableMemory: + unit: REQUESTS_PER_SECOND + title: Read Throughput +cacheHitRate: query: eventId: entityGuid - select: sum(`provider.freeableMemory.Sum`) + select: (sum(provider.cacheHits.Sum)/(sum(provider.cacheHits.Sum)+sum(provider.cacheMisses.Sum)))*100 from: DatastoreSample - unit: BYTES - title: Free memory -memoryUtilization: + unit: PERCENTAGE + title: Cache Hit Rate +swapUsage: query: eventId: entityGuid select: average(`provider.swapUsage.Average`) from: DatastoreSample unit: BYTES - title: Swap usage + title: Swap Usage diff --git a/definitions/infra-awselasticsearchcluster/definition.yml b/definitions/infra-awselasticsearchcluster/definition.yml index 4e02e1f3e..617d6a622 100644 --- a/definitions/infra-awselasticsearchcluster/definition.yml +++ b/definitions/infra-awselasticsearchcluster/definition.yml @@ -1,8 +1,9 @@ domain: INFRA type: AWSELASTICSEARCHCLUSTER goldenTags: -- aws.availabilityZone - aws.accountId +- aws.awsRegion +- aws.vpcId compositeMetrics: goldenMetrics: - golden_metrics.yml diff --git a/definitions/infra-awselasticsearchcluster/golden_metrics.yml b/definitions/infra-awselasticsearchcluster/golden_metrics.yml index bf662db4d..4aa1d1a1c 100644 --- a/definitions/infra-awselasticsearchcluster/golden_metrics.yml +++ b/definitions/infra-awselasticsearchcluster/golden_metrics.yml @@ -1,5 +1,5 @@ searchRateOpsMin: - title: Search rate (ops/min) + title: Search rate (reqs/min) query: select: average(provider.SearchRate.Average) from: DatastoreSample @@ -30,3 +30,19 @@ indexingLatencyMs: where: provider='ElasticsearchCluster' facet: entityName eventId: entityGuid +cpuUtilization: + title: CPU Utilization (%) + query: + select: average(`provider.CPUUtilization.Average`) + from: DatastoreSample + where: provider='ElasticsearchCluster' + facet: entityName + eventId: entityGuid +jvmMemoryPressure: + title: JVM memory pressure (%) + query: + select: max(`provider.JVMMemoryPressure.Maximum`) + from: DatastoreSample + where: provider='ElasticsearchCluster' + facet: entityName + eventId: entityGuid diff --git a/definitions/infra-awselasticsearchnode/definition.yml b/definitions/infra-awselasticsearchnode/definition.yml index fda9c9d8d..6746c2c9f 100644 --- a/definitions/infra-awselasticsearchnode/definition.yml +++ b/definitions/infra-awselasticsearchnode/definition.yml @@ -1,5 +1,10 @@ domain: INFRA type: AWSELASTICSEARCHNODE +goldenTags: +- aws.accountId +- aws.awsRegion compositeMetrics: + goldenMetrics: + - golden_metrics.yml summaryMetrics: - summary_metrics.yml diff --git a/definitions/infra-awselasticsearchnode/golden_metrics.yml b/definitions/infra-awselasticsearchnode/golden_metrics.yml new file mode 100644 index 000000000..e8bd0c580 --- /dev/null +++ b/definitions/infra-awselasticsearchnode/golden_metrics.yml @@ -0,0 +1,48 @@ +searchRateOpsMin: + title: Search rate (reqs/min) + query: + select: average(provider.SearchRate.Average) + from: DatastoreSample + where: provider='ElasticsearchNode' + facet: entityName + eventId: entityGuid +indexingRateReqsMin: + title: Indexing rate (reqs/min) + query: + select: average(provider.IndexingRate.Average) + from: DatastoreSample + where: provider='ElasticsearchNode' + facet: entityName + eventId: entityGuid +searchLatencyMs: + title: Search latency (ms) + query: + select: average(provider.SearchLatency.Average) + from: DatastoreSample + where: provider='ElasticsearchNode' + facet: entityName + eventId: entityGuid +indexingLatencyMs: + title: Indexing latency (ms) + query: + select: average(provider.IndexingLatency.Average) + from: DatastoreSample + where: provider='ElasticsearchNode' + facet: entityName + eventId: entityGuid +cpuUtilization: + title: Max CPU Utilization (%) + query: + select: max(`provider.CPUUtilization.Maximum`) + from: DatastoreSample + where: provider='ElasticsearchNode' + facet: entityName + eventId: entityGuid +jvmMemoryPressure: + title: Max JVM memory pressure (%) + query: + select: max(`provider.JVMMemoryPressure.Maximum`) + from: DatastoreSample + where: provider='ElasticsearchNode' + facet: entityName + eventId: entityGuid diff --git a/definitions/infra-awselasticsearchnode/summary_metrics.yml b/definitions/infra-awselasticsearchnode/summary_metrics.yml index afb341444..5ebdd75d9 100644 --- a/definitions/infra-awselasticsearchnode/summary_metrics.yml +++ b/definitions/infra-awselasticsearchnode/summary_metrics.yml @@ -17,3 +17,10 @@ writeThroughput: from: DatastoreSample unit: REQUESTS_PER_SECOND title: Search rate +jvmMemoryPressure: + query: + eventId: entityGuid + select: (max(`provider.JVMMemoryPressure.Maximum`)) + from: DatastoreSample + unit: PERCENTAGE + title: JVM mem pressure diff --git a/definitions/infra-awselb/definition.yml b/definitions/infra-awselb/definition.yml index 13979bf3a..d30f2d346 100644 --- a/definitions/infra-awselb/definition.yml +++ b/definitions/infra-awselb/definition.yml @@ -1,8 +1,10 @@ domain: INFRA type: AWSELB goldenTags: -- aws.availabilityZone - aws.accountId +- aws.awsRegion +- aws.vpcId +- aws.dnsName compositeMetrics: goldenMetrics: - golden_metrics.yml diff --git a/definitions/infra-awselb/golden_metrics.yml b/definitions/infra-awselb/golden_metrics.yml index ee26f4135..645a7c6c5 100644 --- a/definitions/infra-awselb/golden_metrics.yml +++ b/definitions/infra-awselb/golden_metrics.yml @@ -1,12 +1,12 @@ requests: - title: Requests + title: Requests per min query: - select: sum(provider.requestCount.Sum) + select: rate(sum(provider.requestCount.Sum), 1 minute) from: LoadBalancerSample where: provider='Elb' facet: entityName eventId: entityGuid -latencyS: +latency: title: Latency (s) query: select: average(provider.latency.Average) @@ -14,10 +14,34 @@ latencyS: where: provider='Elb' facet: entityName eventId: entityGuid -backendConnectionErrors: - title: Backend connection errors +errorRate: + title: Error Rate query: - select: sum(provider.backendConnectionErrors.Sum) + select: rate(sum(provider.backendConnectionErrors.Sum), 1 minute) + from: LoadBalancerSample + where: provider='Elb' + facet: entityName + eventId: entityGuid +latencyP99: + title: P99 Latency (s) + query: + select: average(provider.latency.p99) + from: LoadBalancerSample + where: provider='Elb' + facet: entityName + eventId: entityGuid +latencyP90: + title: P90 Latency (s) + query: + select: average(provider.latency.p90) + from: LoadBalancerSample + where: provider='Elb' + facet: entityName + eventId: entityGuid +unhealthyHosts: + title: Unhealthy hosts + query: + select: average(`provider.unhealthyHostCount.Average`) from: LoadBalancerSample where: provider='Elb' facet: entityName diff --git a/definitions/infra-awselb/summary_metrics.yml b/definitions/infra-awselb/summary_metrics.yml index 244702cf3..e1c022a6d 100644 --- a/definitions/infra-awselb/summary_metrics.yml +++ b/definitions/infra-awselb/summary_metrics.yml @@ -3,24 +3,24 @@ providerAccountName: key: providerAccountName title: AWS Account unit: STRING -requests: +throughput: query: eventId: entityGuid - select: sum(`provider.requestCount.Sum`) + select: rate(sum(`provider.requestCount.Sum`), 1 second) from: LoadBalancerSample - unit: COUNT - title: Requests -healthyHosts: + unit: REQUESTS_PER_SECOND + title: Throughput +latency: query: eventId: entityGuid - select: average(`provider.healthyHostCount.Average`) + select: average(provider.latency.Average) from: LoadBalancerSample - unit: COUNT - title: Healthy hosts -unhealthyHosts: + unit: SECONDS + title: Latency (s) +surgeQueueLength: query: eventId: entityGuid - select: average(`provider.unhealthyHostCount.Average`) + select: max(provider.surgeQueueLength.Max) from: LoadBalancerSample unit: COUNT - title: Unhealthy hosts + title: Surge Queue Length diff --git a/definitions/infra-awskinesisdeliverystream/definition.yml b/definitions/infra-awskinesisdeliverystream/definition.yml index 6e36c96b1..40f935b28 100644 --- a/definitions/infra-awskinesisdeliverystream/definition.yml +++ b/definitions/infra-awskinesisdeliverystream/definition.yml @@ -1,5 +1,12 @@ domain: INFRA type: AWSKINESISDELIVERYSTREAM +goldenTags: +- aws.accountId +- aws.awsRegion +- aws.availabilityZone +- aws.status compositeMetrics: + goldenMetrics: + - golden_metrics.yml summaryMetrics: - summary_metrics.yml diff --git a/definitions/infra-awskinesisdeliverystream/golden_metrics.yml b/definitions/infra-awskinesisdeliverystream/golden_metrics.yml new file mode 100644 index 000000000..eda1277ef --- /dev/null +++ b/definitions/infra-awskinesisdeliverystream/golden_metrics.yml @@ -0,0 +1,34 @@ +putThroughput: + title: Bytes in per sec + query: + select: rate(sum(provider.incomingBytes.Sum), 1 second) + from: QueueSample + where: provider='KinesisDeliveryStream' + facet: entityName + eventId: entityGuid +getThroughput: + title: Bytes out per sec + query: + select: rate(sum(`provider.deliveryToElasticsearchBytes.Sum`) + sum(`provider.deliveryToS3Bytes.Sum`) + + sum(`provider.deliveryToRedshiftBytes.Sum`)), 1 second) + from: QueueSample + where: provider='KinesisDeliveryStream' + facet: entityName + eventId: entityGuid +putRecordThroughput: + title: Records in per sec + query: + select: rate(sum(provider.incomingRecords.Sum), 1 second) + from: QueueSample + where: provider='KinesisDeliveryStream' + facet: entityName + eventId: entityGuid +getRecordsThroughput: + title: Records out per sec + query: + select: rate(sum(`provider.deliveryToElasticsearchRecords.Sum`) + sum(`provider.deliveryToS3Records.Sum`) + + sum(`provider.deliveryToRedshiftRecords.Sum`)), 1 second) + from: QueueSample + where: provider='KinesisDeliveryStream' + facet: entityName + eventId: entityGuid diff --git a/definitions/infra-awskinesisdeliverystream/summary_metrics.yml b/definitions/infra-awskinesisdeliverystream/summary_metrics.yml index 524ded66c..eaca62ad4 100644 --- a/definitions/infra-awskinesisdeliverystream/summary_metrics.yml +++ b/definitions/infra-awskinesisdeliverystream/summary_metrics.yml @@ -3,18 +3,18 @@ providerAccountName: key: providerAccountName title: AWS Account unit: STRING -incoming: +putTroughput: query: eventId: entityGuid - select: sum(`provider.incomingBytes.Sum`) + select: rate(sum(`provider.incomingBytes.Sum`), 1 second) from: QueueSample - unit: BYTES - title: Incoming + unit: BYTES_PER_SECOND + title: Throughput in delivered: query: eventId: entityGuid - select: sum(`provider.deliveryToElasticsearchBytes.Sum`) + sum(`provider.deliveryToS3Bytes.Sum`) - + sum(`provider.deliveryToRedshiftBytes.Sum`) + select: rate(sum(`provider.deliveryToElasticsearchBytes.Sum`) + sum(`provider.deliveryToS3Bytes.Sum`) + + sum(`provider.deliveryToRedshiftBytes.Sum`)), 1 second) from: QueueSample - unit: BYTES - title: Delivered + unit: BYTES_PER_SECOND + title: Throuput out diff --git a/definitions/infra-awskinesisstream/definition.yml b/definitions/infra-awskinesisstream/definition.yml index 01120cf31..7a13e3790 100644 --- a/definitions/infra-awskinesisstream/definition.yml +++ b/definitions/infra-awskinesisstream/definition.yml @@ -1,8 +1,9 @@ domain: INFRA type: AWSKINESISSTREAM goldenTags: -- aws.availabilityZone - aws.accountId +- aws.awsRegion +- aws.availabilityZone compositeMetrics: goldenMetrics: - golden_metrics.yml diff --git a/definitions/infra-awskinesisstream/golden_metrics.yml b/definitions/infra-awskinesisstream/golden_metrics.yml index 71c846da1..2556969bc 100644 --- a/definitions/infra-awskinesisstream/golden_metrics.yml +++ b/definitions/infra-awskinesisstream/golden_metrics.yml @@ -1,31 +1,47 @@ -getRecords: - title: Get Records +putThroughput: + title: Bytes in per sec query: - select: sum(provider.getRecordsRecords.Sum) + select: rate(sum(provider.incomingBytes.Sum), 1 second) from: QueueSample where: provider='KinesisStream' facet: entityName eventId: entityGuid -putRecords: - title: Put Records +getThroughput: + title: Bytes out per sec query: - select: sum(provider.putRecordsRecords.Sum) + select: rate(sum(provider.getRecordsBytes.Sum), 1 second) from: QueueSample where: provider='KinesisStream' facet: entityName eventId: entityGuid -getrecordsCallsThrottled: - title: GetRecords calls throttled +putRecordThroughput: + title: Put records per sec + query: + select: rate(sum(provider.incomingRecords.Sum), 1 second) + from: QueueSample + where: provider='KinesisStream' + facet: entityName + eventId: entityGuid +getRecordsThroughput: + title: Get records per sec query: - select: sum(provider.readProvisionedThroughputExceeded.Sum) + select: rate(sum(provider.getRecordsRecords.Sum), 1 second) from: QueueSample where: provider='KinesisStream' facet: entityName eventId: entityGuid putrecordsCallsThrottled: - title: PutRecords calls throttled + title: Puts throttled per second + query: + select: rate(sum(provider.writeProvisionedThroughputExceeded.Sum), 1 second) + from: QueueSample + where: provider='KinesisStream' + facet: entityName + eventId: entityGuid +getrecordsCallsThrottled: + title: Gets throttled per second query: - select: sum(provider.writeProvisionedThroughputExceeded.Sum) + select: rate(sum(provider.readProvisionedThroughputExceeded.Sum), 1 second) from: QueueSample where: provider='KinesisStream' facet: entityName diff --git a/definitions/infra-awskinesisstream/summary_metrics.yml b/definitions/infra-awskinesisstream/summary_metrics.yml index d7c2550b6..dfe2d9963 100644 --- a/definitions/infra-awskinesisstream/summary_metrics.yml +++ b/definitions/infra-awskinesisstream/summary_metrics.yml @@ -3,31 +3,17 @@ providerAccountName: key: providerAccountName title: AWS Account unit: STRING -getRecords: +putTroughput: query: eventId: entityGuid - select: sum(`provider.getRecordsRecords.Sum`) + select: rate(sum(`provider.incomingBytes.Sum`), 1 second) from: QueueSample - unit: COUNT - title: Get records -putRecords: + unit: BYTES_PER_SECOND + title: Throughput in +getThroughput: query: eventId: entityGuid - select: sum(`provider.incomingRecords.Sum`) + select: rate(sum(`provider.getRecordsBytes.Sum`), 1 second) from: QueueSample - unit: COUNT - title: Put records -getThrottles: - query: - eventId: entityGuid - select: sum(`provider.readProvisionedThroughputExceeded.Sum`) - from: QueueSample - unit: COUNT - title: Get throttles -putThrottles: - query: - eventId: entityGuid - select: sum(`provider.writeProvisionedThroughputExceeded.Sum`) - from: QueueSample - unit: COUNT - title: Put throttles + unit: BYTES_PER_SECOND + title: Throughput out diff --git a/definitions/infra-awskinesisstreamshard/definition.yml b/definitions/infra-awskinesisstreamshard/definition.yml index 68dd9f348..5e343f4e1 100644 --- a/definitions/infra-awskinesisstreamshard/definition.yml +++ b/definitions/infra-awskinesisstreamshard/definition.yml @@ -1,5 +1,12 @@ domain: INFRA type: AWSKINESISSTREAMSHARD +goldenTags: +- aws.accountId +- aws.awsRegion +- aws.availabilityZone +- aws.streamName compositeMetrics: + goldenMetrics: + - golden_metrics.yml summaryMetrics: - summary_metrics.yml diff --git a/definitions/infra-awskinesisstreamshard/golden_metrics.yml b/definitions/infra-awskinesisstreamshard/golden_metrics.yml new file mode 100644 index 000000000..08bd62783 --- /dev/null +++ b/definitions/infra-awskinesisstreamshard/golden_metrics.yml @@ -0,0 +1,48 @@ +putThroughput: + title: Bytes in per sec + query: + select: rate(sum(provider.incomingBytes.Sum), 1 second) + from: QueueSample + where: provider='KinesisStreamShard' + facet: entityName + eventId: entityGuid +getThroughput: + title: Bytes out per sec + query: + select: rate(sum(provider.outgoingBytes.Sum), 1 second) + from: QueueSample + where: provider='KinesisStreamShard' + facet: entityName + eventId: entityGuid +putRecordThroughput: + title: Put records per sec + query: + select: rate(sum(provider.incomingRecords.Sum), 1 second) + from: QueueSample + where: provider='KinesisStreamShard' + facet: entityName + eventId: entityGuid +getRecordsThroughput: + title: Get records per sec + query: + select: rate(sum(provider.outgoingRecords.Sum), 1 second) + from: QueueSample + where: provider='KinesisStreamShard' + facet: entityName + eventId: entityGuid +putrecordsCallsThrottled: + title: Puts throttled per sec + query: + select: rate(sum(provider.writeProvisionedThroughputExceeded.Sum), 1 second) + from: QueueSample + where: provider='KinesisStreamShard' + facet: entityName + eventId: entityGuid +getrecordsCallsThrottled: + title: Gets throttled per sec + query: + select: rate(sum(provider.readProvisionedThroughputExceeded.Sum), 1 second) + from: QueueSample + where: provider='KinesisStreamShard' + facet: entityName + eventId: entityGuid diff --git a/definitions/infra-awskinesisstreamshard/summary_metrics.yml b/definitions/infra-awskinesisstreamshard/summary_metrics.yml index 465c79546..d9fc317b5 100644 --- a/definitions/infra-awskinesisstreamshard/summary_metrics.yml +++ b/definitions/infra-awskinesisstreamshard/summary_metrics.yml @@ -3,17 +3,17 @@ providerAccountName: key: providerAccountName title: AWS Account unit: STRING -incoming: +putTroughput: query: eventId: entityGuid - select: sum(`provider.incomingBytes.Sum`) + select: rate(sum(`provider.incomingBytes.Sum`), 1 second) from: QueueSample - unit: BYTES - title: Incoming -outgoing: + unit: BYTES_PER_SECOND + title: Throughput in +getThroughput: query: eventId: entityGuid - select: sum(`provider.outgoingBytes.Sum`) + select: rate(sum(`provider.outgoingBytes.Sum`), 1 second) from: QueueSample - unit: BYTES - title: Outgoing + unit: BYTES_PER_SECOND + title: Throughput out