Merge pull request #285 from rickettmwork/master

Make deploy check retries configurable
IBM · Jul 31, 2023 · ea4273d · ea4273d
2 parents 82ba1d1 + 9ee8102
commit ea4273d
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 3 deletions.
diff --git a/ansible/roles/fyrevm_provision/defaults/main.yml b/ansible/roles/fyrevm_provision/defaults/main.yml
@@ -8,9 +8,14 @@ clusterName: "{{ stackName|default(clusterName_prefix+'-'+ (999999|random)|strin
 ssh_public_key: "{{ lookup('file', lookup('env','HOME') + '/.ssh/id_rsa.pub') }}"
 
 # How many times to retry waiting for an ssh connection after provisioning
-fyre_sshRetries: 250
+# The check is performed every 5 seconds, so the default is 30 minutes
+fyre_sshRetries: 360
 # How many times to wait for a fyre request to complete
-fyre_requestRetries: 999
+# The check is performed every 5 seconds, so the default is 1 hour
+fyre_requestRetries: 720
+# How many times to check for deployed status after provisioning a cluster
+# The check is performed every 20 seconds, so the default equates to 2 hours
+fyre_deployCheckRetries: 360
 
 #Default Specs
 fyre_platform: "x"

diff --git a/ansible/roles/fyrevm_provision/tasks/fyrevm_provision.yml b/ansible/roles/fyrevm_provision/tasks/fyrevm_provision.yml
@@ -89,7 +89,7 @@
   changed_when: false
   register: clusterStatus
   until: (clusterStatus.status == 200) and clusterStatus.json is defined and (clusterStatus.json[clusterName][0].status  == "deployed" or clusterStatus.json[clusterName][0].status == "error")
-  retries: 600
+  retries: "{{ fyre_deployCheckRetries }}"
   delay: 20
 
 - name: check for error status after loop check