Bump telemetry archive default size to 500MB

This commit also removes litmus configs as they are not maintained.
This commit is contained in:
Naga Ravi Chaitanya Elluri
2023-10-30 12:33:57 -04:00
parent 27fabfd4af
commit 43d891afd3
2 changed files with 25 additions and 11 deletions

View File

@@ -29,13 +29,6 @@ kraken:
- scenarios/openshift/openshift-kube-apiserver.yml
- time_scenarios: # List of chaos time scenarios to load
- scenarios/openshift/time_scenarios_example.yml
- litmus_scenarios: # List of litmus scenarios to load
- - scenarios/openshift/templates/litmus-rbac.yaml
- scenarios/openshift/node_cpu_hog_engine.yaml
- - scenarios/openshift/templates/litmus-rbac.yaml
- scenarios/openshift/node_mem_engine.yaml
- - scenarios/openshift/templates/litmus-rbac.yaml
- scenarios/openshift/node_io_engine.yaml
- cluster_shut_down_scenarios:
- - scenarios/openshift/cluster_shut_down_scenario.yml
- scenarios/openshift/post_action_shut_down.py
@@ -83,7 +76,7 @@ telemetry:
archive_path: /tmp # local path where the archive files will be temporarly stored
max_retries: 0 # maximum number of upload retries (if 0 will retry forever)
run_tag: '' # if set, this will be appended to the run folder in the bucket (useful to group the runs)
archive_size: 10000 # the size of the prometheus data archive size in KB. The lower the size of archive is
archive_size: 500000 # the size of the prometheus data archive size in KB. The lower the size of archive is
# the higher the number of archive files will be produced and uploaded (and processed by backup_threads
# simultaneously).
# For unstable/slow connection is better to keep this value low

View File

@@ -21,9 +21,6 @@ kraken:
- scenarios/openshift/openshift-kube-apiserver.yml
- time_scenarios: # List of chaos time scenarios to load
- scenarios/openshift/time_scenarios_example.yml
- litmus_scenarios: # List of litmus scenarios to load
- - https://hub.litmuschaos.io/api/chaos/1.10.0?file=charts/generic/node-cpu-hog/rbac.yaml
- scenarios/openshift/node_cpu_hog_engine.yaml
- cluster_shut_down_scenarios:
- - scenarios/openshift/cluster_shut_down_scenario.yml
- scenarios/openshift/post_action_shut_down.py
@@ -61,3 +58,27 @@ tunings:
wait_duration: 60 # Duration to wait between each chaos scenario
iterations: 1 # Number of times to execute the scenarios
daemon_mode: False # Iterations are set to infinity which means that the kraken will cause chaos forever
telemetry:
enabled: False # enable/disables the telemetry collection feature
api_url: https://ulnmf9xv7j.execute-api.us-west-2.amazonaws.com/production #telemetry service endpoint
username: username # telemetry service username
password: password # telemetry service password
prometheus_backup: True # enables/disables prometheus data collection
full_prometheus_backup: False # if is set to False only the /prometheus/wal folder will be downloaded.
backup_threads: 5 # number of telemetry download/upload threads
archive_path: /tmp # local path where the archive files will be temporarly stored
max_retries: 0 # maximum number of upload retries (if 0 will retry forever)
run_tag: '' # if set, this will be appended to the run folder in the bucket (useful to group the runs)
archive_size: 500000 # the size of the prometheus data archive size in KB. The lower the size of archive is
# the higher the number of archive files will be produced and uploaded (and processed by backup_threads
# simultaneously).
# For unstable/slow connection is better to keep this value low
# increasing the number of backup_threads, in this way, on upload failure, the retry will happen only on the
# failed chunk without affecting the whole upload.
logs_backup: True
logs_filter_patterns:
- "(\\w{3}\\s\\d{1,2}\\s\\d{2}:\\d{2}:\\d{2}\\.\\d+).+" # Sep 9 11:20:36.123425532
- "kinit (\\d+/\\d+/\\d+\\s\\d{2}:\\d{2}:\\d{2})\\s+" # kinit 2023/09/15 11:20:36 log
- "(\\d{4}-\\d{2}-\\d{2}T\\d{2}:\\d{2}:\\d{2}\\.\\d+Z).+" # 2023-09-15T11:20:36.123425532Z log
oc_cli_path: /usr/bin/oc # optional, if not specified will be search in $PATH