From c59ec02b76b8ece538ee74d59391c6152a7e46a9 Mon Sep 17 00:00:00 2001 From: Ryan Miller Date: Mon, 28 Oct 2019 17:36:32 -0700 Subject: [PATCH 1/4] Fix etcd_request_cache_(get|add)_latencies_summary to wildcard match Slack discussion: https://sumologic.slack.com/archives/GFJ6U4SCE/p1572046074091800 --- deploy/helm/sumologic/values.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/deploy/helm/sumologic/values.yaml b/deploy/helm/sumologic/values.yaml index 18183fcb4c..4700367095 100644 --- a/deploy/helm/sumologic/values.yaml +++ b/deploy/helm/sumologic/values.yaml @@ -319,7 +319,7 @@ prometheus-operator: - url: http://collection-sumologic.sumologic.svc.cluster.local:9888/prometheus.metrics.apiserver writeRelabelConfigs: - action: keep - regex: apiserver;(?:apiserver_request_count|apiserver_request_latencies.*|etcd_request_cache_get_latencies_summary|etcd_request_cache_add_latencies_summary|etcd_helper_cache_hit_count|etcd_helper_cache_miss_count) + regex: apiserver;(?:apiserver_request_count|apiserver_request_latencies.*|etcd_request_cache_get_latencies_summary.*|etcd_request_cache_add_latencies_summary.*|etcd_helper_cache_hit_count|etcd_helper_cache_miss_count) sourceLabels: [job, __name__] # kubelet metrics - url: http://collection-sumologic.sumologic.svc.cluster.local:9888/prometheus.metrics.kubelet From 17ae690878f25a1acb172d604ea499d37d1faa17 Mon Sep 17 00:00:00 2001 From: Travis CI Date: Tue, 29 Oct 2019 00:41:27 +0000 Subject: [PATCH 2/4] Generate new overrides yaml file(s). --- deploy/helm/prometheus-overrides.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/deploy/helm/prometheus-overrides.yaml b/deploy/helm/prometheus-overrides.yaml index 469b43f6ca..2eeabf66d4 100644 --- a/deploy/helm/prometheus-overrides.yaml +++ b/deploy/helm/prometheus-overrides.yaml @@ -67,7 +67,7 @@ prometheus: - url: http://collection-sumologic.sumologic.svc.cluster.local:9888/prometheus.metrics.apiserver writeRelabelConfigs: - action: keep - regex: apiserver;(?:apiserver_request_count|apiserver_request_latencies.*|etcd_request_cache_get_latencies_summary|etcd_request_cache_add_latencies_summary|etcd_helper_cache_hit_count|etcd_helper_cache_miss_count) + regex: apiserver;(?:apiserver_request_count|apiserver_request_latencies.*|etcd_request_cache_get_latencies_summary.*|etcd_request_cache_add_latencies_summary.*|etcd_helper_cache_hit_count|etcd_helper_cache_miss_count) sourceLabels: [job, __name__] # kubelet metrics - url: http://collection-sumologic.sumologic.svc.cluster.local:9888/prometheus.metrics.kubelet From e70add57e68e9d6a5d22680751b6a574375a8c81 Mon Sep 17 00:00:00 2001 From: Ryan Miller Date: Tue, 29 Oct 2019 09:23:06 -0700 Subject: [PATCH 3/4] Add container_spec_memory_limit_bytes explicitly --- deploy/helm/sumologic/values.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/deploy/helm/sumologic/values.yaml b/deploy/helm/sumologic/values.yaml index 4700367095..5276cd9a14 100644 --- a/deploy/helm/sumologic/values.yaml +++ b/deploy/helm/sumologic/values.yaml @@ -337,7 +337,7 @@ prometheus-operator: regex: POD sourceLabels: [container_name] - action: keep - regex: kubelet;(?:container_cpu_load_average_10s|container_cpu_system_seconds_total|container_cpu_usage_seconds_total|container_cpu_cfs_throttled_seconds_total|container_memory_usage_bytes|container_memory_swap|container_memory_working_set_bytes|container_spec_memory_swap_limit_bytes|container_spec_memory_reservation_limit_bytes|container_spec_cpu_quota|container_spec_cpu_period|container_fs_usage_bytes|container_fs_limit_bytes|container_fs_reads_bytes_total|container_fs_writes_bytes_total|container_network_receive_bytes_total|container_network_transmit_bytes_total|container_network_receive_errors_total|container_network_transmit_errors_total|container_network_receive_packets_dropped_total|container_network_transmit_packets_dropped_total|) + regex: kubelet;(?:container_cpu_load_average_10s|container_cpu_system_seconds_total|container_cpu_usage_seconds_total|container_cpu_cfs_throttled_seconds_total|container_memory_usage_bytes|container_memory_swap|container_memory_working_set_bytes|container_spec_memory_limit_bytes|container_spec_memory_swap_limit_bytes|container_spec_memory_reservation_limit_bytes|container_spec_cpu_quota|container_spec_cpu_period|container_fs_usage_bytes|container_fs_limit_bytes|container_fs_reads_bytes_total|container_fs_writes_bytes_total|container_network_receive_bytes_total|container_network_transmit_bytes_total|container_network_receive_errors_total|container_network_transmit_errors_total|container_network_receive_packets_dropped_total|container_network_transmit_packets_dropped_total|) sourceLabels: [job, __name__] # node exporter metrics - url: http://collection-sumologic.sumologic.svc.cluster.local:9888/prometheus.metrics.node From 4e4edf48367a719aec4a724f179775729492e7f7 Mon Sep 17 00:00:00 2001 From: Travis CI Date: Tue, 29 Oct 2019 16:27:55 +0000 Subject: [PATCH 4/4] Generate new overrides yaml file(s). --- deploy/helm/prometheus-overrides.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/deploy/helm/prometheus-overrides.yaml b/deploy/helm/prometheus-overrides.yaml index 2eeabf66d4..f4faf2036b 100644 --- a/deploy/helm/prometheus-overrides.yaml +++ b/deploy/helm/prometheus-overrides.yaml @@ -85,7 +85,7 @@ prometheus: regex: POD sourceLabels: [container_name] - action: keep - regex: kubelet;(?:container_cpu_load_average_10s|container_cpu_system_seconds_total|container_cpu_usage_seconds_total|container_cpu_cfs_throttled_seconds_total|container_memory_usage_bytes|container_memory_swap|container_memory_working_set_bytes|container_spec_memory_swap_limit_bytes|container_spec_memory_reservation_limit_bytes|container_spec_cpu_quota|container_spec_cpu_period|container_fs_usage_bytes|container_fs_limit_bytes|container_fs_reads_bytes_total|container_fs_writes_bytes_total|container_network_receive_bytes_total|container_network_transmit_bytes_total|container_network_receive_errors_total|container_network_transmit_errors_total|container_network_receive_packets_dropped_total|container_network_transmit_packets_dropped_total|) + regex: kubelet;(?:container_cpu_load_average_10s|container_cpu_system_seconds_total|container_cpu_usage_seconds_total|container_cpu_cfs_throttled_seconds_total|container_memory_usage_bytes|container_memory_swap|container_memory_working_set_bytes|container_spec_memory_limit_bytes|container_spec_memory_swap_limit_bytes|container_spec_memory_reservation_limit_bytes|container_spec_cpu_quota|container_spec_cpu_period|container_fs_usage_bytes|container_fs_limit_bytes|container_fs_reads_bytes_total|container_fs_writes_bytes_total|container_network_receive_bytes_total|container_network_transmit_bytes_total|container_network_receive_errors_total|container_network_transmit_errors_total|container_network_receive_packets_dropped_total|container_network_transmit_packets_dropped_total|) sourceLabels: [job, __name__] # node exporter metrics - url: http://collection-sumologic.sumologic.svc.cluster.local:9888/prometheus.metrics.node