Skip to content

Instantly share code, notes, and snippets.

@mulbc

mulbc/Deployment.yml Secret

Created December 16, 2019 10:23
Star
Embed
What would you like to do?
Learn more about clone URLs
Download ZIP
Prometheus benchmark with different backing stores
Raw
Deployment.yml
---
apiVersion: v1
kind: ConfigMap
metadata:
name: prometheus-config
namespace: default
data:
prometheus.yml: |-
global:
scrape_interval: 15s # Set the scrape interval to every 15 seconds. Default is every 1 minute.
evaluation_interval: 15s # Evaluate rules every 15 seconds. The default is every 1 minute.
scrape_configs:
- job_name: 'prometheus'
static_configs:
- targets: ['localhost:9090']
- job_name: 'node'
static_configs:
- targets: [192.168.1.1:9100]
labels:
instance: router
- targets: [192.168.1.157:9100]
labels:
instance: macpro
- targets: [10.10.10.5:9100]
labels:
instance: DorfMaster
- targets: [10.10.10.10:9100]
labels:
instance: storchris
- targets: [10.10.10.20:9100]
labels:
instance: vchris
- targets: [10.10.10.30:9100]
labels:
instance: vchris2
- targets: [10.10.10.50:9100]
labels:
instance: opn1
- targets: [10.10.10.60:9100]
labels:
instance: opn2
- job_name: 'speedtest'
scrape_timeout: 1m
scrape_interval: 15m
static_configs:
- targets: [192.168.1.101:9112]
---
kind: PersistentVolumeClaim
apiVersion: v1
metadata:
name: prometheus-pvc
namespace: default
spec:
storageClassName: ocs-storagecluster-ceph-rbd
accessModes:
- ReadWriteOnce
resources:
requests:
storage: 10Gi
---
apiVersion: route.openshift.io/v1
kind: Route
metadata:
labels:
app: prometheus
deploy: persistent
name: prometheus-persistent
namespace: default
spec:
port:
targetPort: 9090
to:
kind: Service
name: prometheus-persistent
weight: 100
---
apiVersion: v1
kind: Service
metadata:
labels:
app: prometheus
deploy: persistent
name: prometheus-persistent
namespace: default
spec:
ports:
- port: 9090
protocol: TCP
targetPort: 9090
selector:
app: prometheus
deploy: persistent
type: ClusterIP
---
apiVersion: route.openshift.io/v1
kind: Route
metadata:
labels:
app: prometheus
deploy: ephemeral
name: prometheus-ephemeral
namespace: default
spec:
port:
targetPort: 9090
to:
kind: Service
name: prometheus-ephemeral
weight: 100
---
apiVersion: route.openshift.io/v1
kind: Route
metadata:
labels:
app: prometheus
deploy: ephemeral
name: prometheus-ephemeral-ram
namespace: default
spec:
port:
targetPort: 9090
to:
kind: Service
name: prometheus-ephemeral-ram
weight: 100
---
apiVersion: v1
kind: Service
metadata:
labels:
app: prometheus
deploy: ephemeral
name: prometheus-ephemeral
namespace: default
spec:
ports:
- port: 9090
protocol: TCP
targetPort: 9090
selector:
app: prometheus
deploy: ephemeral
type: ClusterIP
---
apiVersion: v1
kind: Service
metadata:
labels:
app: prometheus
deploy: ephemeral-ram
name: prometheus-ephemeral-ram
namespace: default
spec:
ports:
- port: 9090
protocol: TCP
targetPort: 9090
selector:
app: prometheus
deploy: ephemeral-ram
type: ClusterIP
---
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: prometheus-ephemeral
namespace: default
labels:
app: prometheus
deploy: ephemeral
spec:
replicas: 1
template:
metadata:
name: prometheus-ephemeral
labels:
app: prometheus
deploy: ephemeral
spec:
containers:
- name: prometheus-ephemeral
image: prom/prometheus:latest
args:
- '--config.file=/etc/prometheus/prometheus.yml'
- '--storage.tsdb.path=/prometheus'
- '--storage.tsdb.retention.time=30d'
- '--web.enable-admin-api'
ports:
- name: webui
containerPort: 9090
resources:
requests:
cpu: 500m
memory: 500M
limits:
cpu: 5000m
memory: 5000M
volumeMounts:
- name: config-volume
mountPath: /etc/prometheus
- name: tsdb-volume
mountPath: /prometheus
initContainers:
- name: download-snapshot
image: busybox
command: ["wget","https://promtest.s3.eu-central-1.amazonaws.com/promBack.tgz", "--output-document=/download/promBack.tgz"]
volumeMounts:
- name: download-volume
mountPath: /download
- name: extract-snapshot
image: busybox
command: ["tar","xzvf", "/download/promBack.tgz", "--directory=/prometheus"]
volumeMounts:
- name: download-volume
mountPath: /download
- name: tsdb-volume
mountPath: /prometheus
volumes:
- name: config-volume
configMap:
name: prometheus-config
- name: download-volume
emptyDir: {}
- name: tsdb-volume
emptyDir: {}
---
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: prometheus-ephemeral-ram
namespace: default
labels:
app: prometheus
deploy: ephemeral-ram
spec:
replicas: 1
template:
metadata:
name: prometheus-ephemeral-ram
labels:
app: prometheus
deploy: ephemeral-ram
spec:
containers:
- name: prometheus-ephemeral-ram
image: prom/prometheus:latest
args:
- '--config.file=/etc/prometheus/prometheus.yml'
- '--storage.tsdb.path=/prometheus'
- '--storage.tsdb.retention.time=30d'
- '--web.enable-admin-api'
ports:
- name: webui
containerPort: 9090
resources:
requests:
cpu: 500m
memory: 500M
limits:
cpu: 5000m
memory: 5000M
volumeMounts:
- name: config-volume
mountPath: /etc/prometheus
- name: tsdb-volume
mountPath: /prometheus
initContainers:
- name: download-snapshot
image: busybox
command: ["wget","https://promtest.s3.eu-central-1.amazonaws.com/promBack.tgz", "--output-document=/download/promBack.tgz"]
volumeMounts:
- name: download-volume
mountPath: /download
- name: extract-snapshot
image: busybox
command: ["tar","xzvf", "/download/promBack.tgz", "--directory=/prometheus"]
volumeMounts:
- name: download-volume
mountPath: /download
- name: tsdb-volume
mountPath: /prometheus
volumes:
- name: config-volume
configMap:
name: prometheus-config
- name: download-volume
emptyDir: {}
- name: tsdb-volume
emptyDir:
medium: Memory
---
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
name: prometheus-persistent
namespace: default
labels:
app: prometheus
deploy: persistent
spec:
replicas: 1
template:
metadata:
name: prometheus--persistent
labels:
app: prometheus
deploy: persistent
spec:
containers:
- name: prometheus-persistent
image: prom/prometheus:latest
args:
- '--config.file=/etc/prometheus/prometheus.yml'
- '--storage.tsdb.path=/prometheus'
- '--storage.tsdb.retention.time=30d'
- '--web.enable-admin-api'
ports:
- name: webui
containerPort: 9090
resources:
requests:
cpu: 500m
memory: 500M
limits:
cpu: 5000m
memory: 5000M
volumeMounts:
- name: config-volume
mountPath: /etc/prometheus
- name: tsdb-volume
mountPath: /prometheus
initContainers:
- name: download-snapshot
image: busybox
command: ["wget","https://promtest.s3.eu-central-1.amazonaws.com/promBack.tgz", "--output-document=/download/promBack.tgz"]
volumeMounts:
- name: download-volume
mountPath: /download
- name: extract-snapshot
image: busybox
command: ["tar","xzvf", "/download/promBack.tgz", "--directory=/prometheus"]
volumeMounts:
- name: download-volume
mountPath: /download
- name: tsdb-volume
mountPath: /prometheus
volumes:
- name: config-volume
configMap:
name: prometheus-config
- name: download-volume
emptyDir: {}
- name: tsdb-volume
persistentVolumeClaim:
claimName: prometheus-pvc
...
Raw
result-hard.log
➜ work
QUERYCMD="%28%28%28count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29%29%20-%20avg%28sum%20by%20%28mode%29%28irate%28node_cpu_seconds_total%7Bmode%3D%27idle%27%7D%5B5m%5D%29%29%29%29%20%2A%20100%29%20%2F%20count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29"
TESTPATH="api/v1/query_range?query=${QUERYCMD}&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m"
oc run --rm=true -i -t bench-ephemeral --image=jordi/ab --restart=Never -- -k -c 100 -n 10000 "http://prometheus-ephemeral:9090/${TESTPATH}"
oc run --rm=true -i -t bench-ephemeral-ram --image=jordi/ab --restart=Never -- -k -c 100 -n 10000 "http://prometheus-ephemeral-ram:9090/${TESTPATH}"
oc run --rm=true -i -t bench-persistent --image=jordi/ab --restart=Never -- -k -c 100 -n 10000 "http://prometheus-persistent:9090/${TESTPATH}"
If you don't see a command prompt, try pressing enter.
^C
Server Software:
Server Hostname: prometheus-ephemeral
Server Port: 9090
Document Path: /api/v1/query_range?query=%28%28%28count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29%29%20-%20avg%28sum%20by%20%28mode%29%28irate%28node_cpu_seconds_total%7Bmode%3D%27idle%27%7D%5B5m%5D%29%29%29%29%20%2A%20100%29%20%2F%20count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m
Document Length: 47128 bytes
Concurrency Level: 100
Time taken for tests: 488.789 seconds
Complete requests: 402
Failed requests: 0
Keep-Alive requests: 0
Total transferred: 18980832 bytes
HTML transferred: 18945456 bytes
Requests per second: 0.82 [#/sec] (mean)
Time per request: 121589.413 [ms] (mean)
Time per request: 1215.894 [ms] (mean, across all concurrent requests)
Transfer rate: 37.92 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 2 2.7 0 18
Processing: 4937 104707 26285.2 116197 119582
Waiting: 4925 104706 26284.9 116197 119582
Total: 4937 104709 26283.3 116197 119582
Percentage of the requests served within a certain time (ms)
50% 116197
66% 116700
75% 116994
80% 117186
90% 117779
95% 117983
98% 118300
99% 118706
100% 119582 (longest request)
^C^C
➜ work
➜ work
➜ work
➜ work
➜ work oc delete po bench-ephemeral
pod "bench-ephemeral" deleted
➜ work
QUERYCMD="%28%28%28count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29%29%20-%20avg%28sum%20by%20%28mode%29%28irate%28node_cpu_seconds_total%7Bmode%3D%27idle%27%7D%5B5m%5D%29%29%29%29%20%2A%20100%29%20%2F%20count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29"
TESTPATH="api/v1/query_range?query=${QUERYCMD}&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m"
oc run --rm=true -i -t bench-ephemeral --image=jordi/ab --restart=Never -- -k -c 100 -n 10000 "http://prometheus-ephemeral:9090/${TESTPATH}"
oc run --rm=true -i -t bench-ephemeral-ram --image=jordi/ab --restart=Never -- -k -c 100 -n 10000 "http://prometheus-ephemeral-ram:9090/${TESTPATH}"
oc run --rm=true -i -t bench-persistent --image=jordi/ab --restart=Never -- -k -c 100 -n 10000 "http://prometheus-persistent:9090/${TESTPATH}"
➜ work
QUERYCMD="%28%28%28count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29%29%20-%20avg%28sum%20by%20%28mode%29%28irate%28node_cpu_seconds_total%7Bmode%3D%27idle%27%7D%5B5m%5D%29%29%29%29%20%2A%20100%29%20%2F%20count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29"
TESTPATH="api/v1/query_range?query=${QUERYCMD}&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m"
oc run --rm=true -i -t bench-ephemeral --image=jordi/ab --restart=Never -- -k -c 100 -n 600 "http://prometheus-ephemeral:9090/${TESTPATH}"
oc run --rm=true -i -t bench-ephemeral-ram --image=jordi/ab --restart=Never -- -k -c 100 -n 600 "http://prometheus-ephemeral-ram:9090/${TESTPATH}"
oc run --rm=true -i -t bench-persistent --image=jordi/ab --restart=Never -- -k -c 100 -n 600 "http://prometheus-persistent:9090/${TESTPATH}"
If you don't see a command prompt, try pressing enter.
Completed 100 requests
Completed 200 requests
Completed 300 requests
Completed 400 requests
Completed 500 requests
Completed 600 requests
Finished 600 requests
Server Software:
Server Hostname: prometheus-ephemeral
Server Port: 9090
Document Path: /api/v1/query_range?query=%28%28%28count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29%29%20-%20avg%28sum%20by%20%28mode%29%28irate%28node_cpu_seconds_total%7Bmode%3D%27idle%27%7D%5B5m%5D%29%29%29%29%20%2A%20100%29%20%2F%20count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m
Document Length: 47128 bytes
Concurrency Level: 100
Time taken for tests: 699.177 seconds
Complete requests: 600
Failed requests: 0
Keep-Alive requests: 0
Total transferred: 28329600 bytes
HTML transferred: 28276800 bytes
Requests per second: 0.86 [#/sec] (mean)
Time per request: 116529.551 [ms] (mean)
Time per request: 1165.296 [ms] (mean, across all concurrent requests)
Transfer rate: 39.57 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 1 1.5 0 6
Processing: 4954 107903 22108.1 115490 119212
Waiting: 4945 107894 22109.5 115489 119212
Total: 4956 107903 22106.9 115490 119212
Percentage of the requests served within a certain time (ms)
50% 115490
66% 116207
75% 116621
80% 116905
90% 117488
95% 117903
98% 118293
99% 118594
100% 119212 (longest request)
pod "bench-ephemeral" deleted
If you don't see a command prompt, try pressing enter.
Completed 100 requests
Completed 200 requests
Completed 300 requests
Completed 400 requests
Completed 500 requests
Completed 600 requests
Finished 600 requests
Server Software:
Server Hostname: prometheus-ephemeral-ram
Server Port: 9090
Document Path: /api/v1/query_range?query=%28%28%28count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29%29%20-%20avg%28sum%20by%20%28mode%29%28irate%28node_cpu_seconds_total%7Bmode%3D%27idle%27%7D%5B5m%5D%29%29%29%29%20%2A%20100%29%20%2F%20count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m
Document Length: 47128 bytes
Concurrency Level: 100
Time taken for tests: 725.612 seconds
Complete requests: 600
Failed requests: 0
Keep-Alive requests: 0
Total transferred: 28329600 bytes
HTML transferred: 28276800 bytes
Requests per second: 0.83 [#/sec] (mean)
Time per request: 120935.289 [ms] (mean)
Time per request: 1209.353 [ms] (mean, across all concurrent requests)
Transfer rate: 38.13 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 1 1.5 0 6
Processing: 5007 112023 22781.7 119908 124783
Waiting: 4998 112013 22784.4 119906 124782
Total: 5009 112024 22780.5 119908 124787
Percentage of the requests served within a certain time (ms)
50% 119908
66% 120504
75% 120832
80% 121074
90% 121675
95% 122082
98% 122703
99% 123287
100% 124787 (longest request)
pod "bench-ephemeral-ram" deleted
If you don't see a command prompt, try pressing enter.
Completed 100 requests
Completed 200 requests
Completed 300 requests
Completed 400 requests
Completed 500 requests
Completed 600 requests
Finished 600 requests
Server Software:
Server Hostname: prometheus-persistent
Server Port: 9090
Document Path: /api/v1/query_range?query=%28%28%28count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29%29%20-%20avg%28sum%20by%20%28mode%29%28irate%28node_cpu_seconds_total%7Bmode%3D%27idle%27%7D%5B5m%5D%29%29%29%29%20%2A%20100%29%20%2F%20count%28count%28node_cpu_seconds_total%29%20by%20%28cpu%29%29&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m
Document Length: 47128 bytes
Concurrency Level: 100
Time taken for tests: 776.480 seconds
Complete requests: 600
Failed requests: 0
Keep-Alive requests: 0
Total transferred: 28329600 bytes
HTML transferred: 28276800 bytes
Requests per second: 0.77 [#/sec] (mean)
Time per request: 129413.378 [ms] (mean)
Time per request: 1294.134 [ms] (mean, across all concurrent requests)
Transfer rate: 35.63 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 1 1.8 0 11
Processing: 5052 119938 24058.2 128003 134295
Waiting: 5043 119930 24062.6 128003 134295
Total: 5054 119939 24056.9 128004 134295
Percentage of the requests served within a certain time (ms)
50% 128004
66% 128905
75% 129408
80% 129795
90% 130712
95% 131423
98% 132024
99% 132605
100% 134295 (longest request)
pod "bench-persistent" deleted
➜ work
Raw
result-medium.log
QUERYCMD="sum%20by%20%28mode%29%28irate%28node_cpu_seconds_total%5B5m%5D%29%29%20%2A%20100"
TESTPATH="api/v1/query_range?query=${QUERYCMD}&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m"
oc run --rm=true -i -t bench-ephemeral --image=jordi/ab --restart=Never -- -k -c 10 -n 100 "http://prometheus-ephemeral:9090/${TESTPATH}"
oc run --rm=true -i -t bench-ephemeral-ram --image=jordi/ab --restart=Never -- -k -c 10 -n 100 "http://prometheus-ephemeral-ram:9090/${TESTPATH}"
oc run --rm=true -i -t bench-persistent --image=jordi/ab --restart=Never -- -k -c 10 -n 100 "http://prometheus-persistent:9090/${TESTPATH}"
If you don't see a command prompt, try pressing enter.
Error attaching, falling back to logs: unable to upgrade connection: container bench-ephemeral not found in pod bench-ephemeral_default
This is ApacheBench, Version 2.3 <$Revision: 1826891 $>
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Licensed to The Apache Software Foundation, http://www.apache.org/
Benchmarking prometheus-ephemeral (be patient).....done
Server Software:
Server Hostname: prometheus-ephemeral
Server Port: 9090
Document Path: /api/v1/query_range?query=sum%20by%20%28mode%29%28irate%28node_cpu_seconds_total%5B5m%5D%29%29%20%2A%20100&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m
Document Length: 422665 bytes
Concurrency Level: 10
Time taken for tests: 56.956 seconds
Complete requests: 100
Failed requests: 0
Keep-Alive requests: 0
Total transferred: 42275300 bytes
HTML transferred: 42266500 bytes
Requests per second: 1.76 [#/sec] (mean)
Time per request: 5695.644 [ms] (mean)
Time per request: 569.564 [ms] (mean, across all concurrent requests)
Transfer rate: 724.84 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 0 1.0 0 10
Processing: 2432 5417 375.7 5484 5737
Waiting: 2427 5415 375.7 5481 5736
Total: 2432 5417 375.7 5484 5737
Percentage of the requests served within a certain time (ms)
50% 5484
66% 5517
75% 5605
80% 5612
90% 5686
95% 5705
98% 5723
99% 5737
100% 5737 (longest request)
pod "bench-ephemeral" deleted
If you don't see a command prompt, try pressing enter.
Error attaching, falling back to logs: unable to upgrade connection: container bench-ephemeral-ram not found in pod bench-ephemeral-ram_default
This is ApacheBench, Version 2.3 <$Revision: 1826891 $>
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Licensed to The Apache Software Foundation, http://www.apache.org/
Benchmarking prometheus-ephemeral-ram (be patient).....done
Server Software:
Server Hostname: prometheus-ephemeral-ram
Server Port: 9090
Document Path: /api/v1/query_range?query=sum%20by%20%28mode%29%28irate%28node_cpu_seconds_total%5B5m%5D%29%29%20%2A%20100&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m
Document Length: 422665 bytes
Concurrency Level: 10
Time taken for tests: 59.002 seconds
Complete requests: 100
Failed requests: 0
Keep-Alive requests: 0
Total transferred: 42275300 bytes
HTML transferred: 42266500 bytes
Requests per second: 1.69 [#/sec] (mean)
Time per request: 5900.211 [ms] (mean)
Time per request: 590.021 [ms] (mean, across all concurrent requests)
Transfer rate: 699.71 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 0 1.7 0 17
Processing: 2445 5614 429.5 5618 6271
Waiting: 2444 5611 429.6 5617 6269
Total: 2446 5615 429.5 5618 6271
Percentage of the requests served within a certain time (ms)
50% 5618
66% 5719
75% 5803
80% 5892
90% 6045
95% 6136
98% 6161
99% 6271
100% 6271 (longest request)
pod "bench-ephemeral-ram" deleted
If you don't see a command prompt, try pressing enter.
Error attaching, falling back to logs: unable to upgrade connection: container bench-persistent not found in pod bench-persistent_default
This is ApacheBench, Version 2.3 <$Revision: 1826891 $>
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Licensed to The Apache Software Foundation, http://www.apache.org/
Benchmarking prometheus-persistent (be patient).....done
Server Software:
Server Hostname: prometheus-persistent
Server Port: 9090
Document Path: /api/v1/query_range?query=sum%20by%20%28mode%29%28irate%28node_cpu_seconds_total%5B5m%5D%29%29%20%2A%20100&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m
Document Length: 422665 bytes
Concurrency Level: 10
Time taken for tests: 60.455 seconds
Complete requests: 100
Failed requests: 0
Keep-Alive requests: 0
Total transferred: 42275300 bytes
HTML transferred: 42266500 bytes
Requests per second: 1.65 [#/sec] (mean)
Time per request: 6045.550 [ms] (mean)
Time per request: 604.555 [ms] (mean, across all concurrent requests)
Transfer rate: 682.89 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 0 0.3 0 2
Processing: 2428 5757 446.1 5823 6178
Waiting: 2426 5753 446.9 5818 6177
Total: 2429 5757 446.1 5823 6178
Percentage of the requests served within a certain time (ms)
50% 5823
66% 5914
75% 5961
80% 6020
90% 6098
95% 6131
98% 6165
99% 6178
100% 6178 (longest request)
pod "bench-persistent" deleted
Raw
result-simple.log
QUERYCMD="node_load1"
TESTPATH="api/v1/query_range?query=${QUERYCMD}&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m"
oc run --rm=true -i -t bench-ephemeral --image=jordi/ab --restart=Never -- -k -c 100 -n 1000 "http://prometheus-ephemeral:9090/${TESTPATH}"
oc run --rm=true -i -t bench-ephemeral-ram --image=jordi/ab --restart=Never -- -k -c 100 -n 1000 "http://prometheus-ephemeral-ram:9090/${TESTPATH}"
oc run --rm=true -i -t bench-persistent --image=jordi/ab --restart=Never -- -k -c 100 -n 1000 "http://prometheus-persistent:9090/${TESTPATH}"
If you don't see a command prompt, try pressing enter.
Completed 200 requests
Completed 300 requests
Completed 400 requests
Completed 500 requests
Completed 600 requests
Completed 700 requests
Completed 800 requests
Completed 900 requests
Completed 1000 requests
Finished 1000 requests
Server Software:
Server Hostname: prometheus-ephemeral
Server Port: 9090
Document Path: /api/v1/query_range?query=node_load1&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m
Document Length: 174896 bytes
Concurrency Level: 100
Time taken for tests: 14.004 seconds
Complete requests: 1000
Failed requests: 0
Keep-Alive requests: 0
Total transferred: 174984000 bytes
HTML transferred: 174896000 bytes
Requests per second: 71.41 [#/sec] (mean)
Time per request: 1400.379 [ms] (mean)
Time per request: 14.004 [ms] (mean, across all concurrent requests)
Transfer rate: 12202.61 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 1 1.8 0 8
Processing: 66 1338 239.8 1388 1730
Waiting: 54 1335 240.3 1387 1730
Total: 67 1338 238.6 1388 1730
Percentage of the requests served within a certain time (ms)
50% 1388
66% 1410
75% 1433
80% 1480
90% 1508
95% 1589
98% 1659
99% 1675
100% 1730 (longest request)
pod "bench-ephemeral" deleted
If you don't see a command prompt, try pressing enter.
Error attaching, falling back to logs: unable to upgrade connection: container bench-ephemeral-ram not found in pod bench-ephemeral-ram_default
This is ApacheBench, Version 2.3 <$Revision: 1826891 $>
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Licensed to The Apache Software Foundation, http://www.apache.org/
Benchmarking prometheus-ephemeral-ram (be patient)
Completed 100 requests
Completed 200 requests
Completed 300 requests
Completed 400 requests
Completed 500 requests
Completed 600 requests
Completed 700 requests
Completed 800 requests
Completed 900 requests
Completed 1000 requests
Finished 1000 requests
Server Software:
Server Hostname: prometheus-ephemeral-ram
Server Port: 9090
Document Path: /api/v1/query_range?query=node_load1&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m
Document Length: 174896 bytes
Concurrency Level: 100
Time taken for tests: 14.148 seconds
Complete requests: 1000
Failed requests: 0
Keep-Alive requests: 0
Total transferred: 174984000 bytes
HTML transferred: 174896000 bytes
Requests per second: 70.68 [#/sec] (mean)
Time per request: 1414.838 [ms] (mean)
Time per request: 14.148 [ms] (mean, across all concurrent requests)
Transfer rate: 12077.90 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 1 1.8 0 8
Processing: 70 1351 238.6 1396 1775
Waiting: 58 1348 238.1 1394 1768
Total: 70 1351 237.4 1396 1775
Percentage of the requests served within a certain time (ms)
50% 1396
66% 1415
75% 1477
80% 1486
90% 1512
95% 1581
98% 1606
99% 1675
100% 1775 (longest request)
pod "bench-ephemeral-ram" deleted
If you don't see a command prompt, try pressing enter.
Completed 100 requests
Completed 200 requests
Completed 300 requests
Completed 400 requests
Completed 500 requests
Completed 600 requests
Completed 700 requests
Completed 800 requests
Completed 900 requests
Completed 1000 requests
Finished 1000 requests
Server Software:
Server Hostname: prometheus-persistent
Server Port: 9090
Document Path: /api/v1/query_range?query=node_load1&start=2019-12-01T20:10:30.781Z&end=2019-12-10T20:11:00.781Z&step=10m
Document Length: 174896 bytes
Concurrency Level: 100
Time taken for tests: 15.332 seconds
Complete requests: 1000
Failed requests: 0
Keep-Alive requests: 0
Total transferred: 174984000 bytes
HTML transferred: 174896000 bytes
Requests per second: 65.22 [#/sec] (mean)
Time per request: 1533.172 [ms] (mean)
Time per request: 15.332 [ms] (mean, across all concurrent requests)
Transfer rate: 11145.71 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 1 1.7 0 8
Processing: 75 1463 244.7 1503 1898
Waiting: 64 1461 245.2 1502 1890
Total: 76 1464 243.5 1504 1898
Percentage of the requests served within a certain time (ms)
50% 1504
66% 1533
75% 1584
80% 1592
90% 1618
95% 1688
98% 1706
99% 1774
100% 1898 (longest request)
pod "bench-persistent" deleted
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment