summaryrefslogtreecommitdiff
path: root/config/prometheus
diff options
context:
space:
mode:
authorJoshua Lambert <joshua@gitlab.com>2017-07-04 01:45:35 -0400
committerJoshua Lambert <joshua@gitlab.com>2017-07-04 01:45:35 -0400
commitfb6144298e19a632a574bfc576f5f672e08e4324 (patch)
treee40c62dff668ddfea66ee0d30190df1755e7a162 /config/prometheus
parent7424eb05d7d6ead2cce2e1045f2d00d273f7540e (diff)
downloadgitlab-ce-fb6144298e19a632a574bfc576f5f672e08e4324.tar.gz
Add NGINX metrics and other minor changes34636-update-prometheus-metrics-library
Diffstat (limited to 'config/prometheus')
-rw-r--r--config/prometheus/additional_metrics.yml90
1 files changed, 53 insertions, 37 deletions
diff --git a/config/prometheus/additional_metrics.yml b/config/prometheus/additional_metrics.yml
index 3f7e897e73a..d33fae4182d 100644
--- a/config/prometheus/additional_metrics.yml
+++ b/config/prometheus/additional_metrics.yml
@@ -1,66 +1,82 @@
- group: AWS Elastic Load Balancer
priority: 10
metrics:
- - title: "Request Rate"
- y_label: "Requests/Min"
+ - title: "Throughput"
+ y_label: "Requests / Sec"
required_metrics:
- aws_elb_request_count_sum
weight: 1
queries:
- - query_range: 'sum(aws_elb_request_count_sum{%{environment_filter}})'
- label: Requests per minute
- unit: requests
+ - query_range: 'sum(aws_elb_request_count_sum{%{environment_filter}}) * 60'
+ label: Total
+ unit: req / sec
- title: "Latency"
- y_label: "Average Latency"
+ y_label: "Latency (ms)"
required_metrics:
- - aws_elb_latency_average
+ - aws_elb_latency_average
weight: 1
queries:
- - query_range: 'avg(aws_elb_latency_average{%{environment_filter}})'
- unit: seconds
- - title: "Error Rate"
- y_label: "Percent HTTP Errors / minute"
+ - query_range: 'avg(aws_elb_latency_average{%{environment_filter}}) * 1000'
+ label: Average
+ unit: ms
+ - title: "HTTP Error Rate"
+ y_label: "Error Rate (%)"
required_metrics:
- - aws_elb_request_count_sum
- - aws_elb_httpcode_backend_5_xx_sum
+ - aws_elb_request_count_sum
+ - aws_elb_httpcode_backend_5_xx_sum
weight: 1
queries:
- query_range: 'sum(aws_elb_httpcode_backend_5_xx_sum{%{environment_filter}}) / sum(aws_elb_request_count_sum{%{environment_filter}})'
-- group: Kubernetes
- priority: 5
+ label: HTTP Errors
+ unit: "%"
+- group: NGINX
+ priority: 10
metrics:
- - title: "Memory usage"
- y_label: "Values"
+ - title: "Throughput"
+ y_label: "Requests / Sec"
required_metrics:
- - container_memory_usage_bytes
+ - nginx_requests_total
weight: 1
queries:
- - query_range: 'avg(container_memory_usage_bytes{%{environment_filter}}) / 2^20'
- label: Container memory
- unit: MiB
- - title: "Current memory usage"
+ - query_range: 'sum(rate(nginx_requests_total{server_zone!="*", server_zone!="_", %{environment_filter}}[2m]))'
+ label: Total
+ unit: req / sec
+ - title: "Latency"
+ y_label: "Latency (ms)"
required_metrics:
- - container_memory_usage_bytes
+ - nginx_upstream_response_msecs_avg
weight: 1
queries:
- - query: 'avg(container_memory_usage_bytes{%{environment_filter}}) / 2^20'
- display_empty: false
- unit: MiB
- - title: "CPU usage"
+ - query_range: 'avg(nginx_upstream_response_msecs_avg{%{environment_filter}}) * 1000'
+ label: Upstream
+ unit: ms
+ - title: "HTTP Error Rate"
+ y_label: "Error Rate (%)"
required_metrics:
- - container_cpu_usage_seconds_total
+ - nginx_responses_total
+ weight: 1
+ queries:
+ - query_range: 'sum(nginx_responses_total{status_code="5xx", %{environment_filter}}) / sum(nginx_responses_total{server_zone!="*", server_zone!="_", %{environment_filter}})'
+ label: HTTP Errors
+ unit: "%"
+- group: Kubernetes
+ priority: 5
+ metrics:
+ - title: "Memory Usage"
+ y_label: "Memory Usage (MB)"
+ required_metrics:
+ - container_memory_usage_bytes
weight: 1
queries:
- - query_range: 'avg(rate(container_cpu_usage_seconds_total{%{environment_filter}}[2m])) by (cpu) * 100'
- series:
- label: cpu
- - value: cpu00
- color: red
- - value: cpu01
- color: blue
- - title: "Current CPU usage"
+ - query_range: '(sum(container_memory_usage_bytes{container_name!="POD",%{environment_filter}}) / count(container_memory_usage_bytes{container_name!="POD",%{environment_filter}})) /1024/1024'
+ label: Average
+ unit: MB
+ - title: "CPU Utilization"
+ y_label: "CPU Utilization (%)"
required_metrics:
- container_cpu_usage_seconds_total
weight: 1
queries:
- - query: 'avg(rate(container_cpu_usage_seconds_total{%{environment_filter}}[2m])) * 100'
+ - query_range: 'sum(rate(container_cpu_usage_seconds_total{container_name!="POD",%{environment_filter}}[2m])) / count(container_cpu_usage_seconds_total{container_name!="POD",%{environment_filter}}) * 100'
+ label: Average
+ unit: "%"