Add support to run baremetal node disruptions (#202)

This commit enables users to run disrupt baremetal using IPMI to be able to understand the impact on OpenShift as well as applications running on it. Signed-off-by: Naga Ravi Chaitanya Elluri <[email protected]>
krkn-chaos · Aug 20, 2024 · 2687314 · 2687314
1 parent cc1304b
commit 2687314
Show file tree

Hide file tree

Showing 5 changed files with 39 additions and 7 deletions.
diff --git a/docs/node-scenarios.md b/docs/node-scenarios.md
@@ -36,11 +36,14 @@ LABEL_SELECTOR          | Node label to target
 NODE_NAME               | Node name to inject faults in case of targeting a specific node; Can set multiple node names separated by a comma      | ""                                   |
 INSTANCE_COUNT          | Targeted instance count matching the label selector                   | 1                                    |
 RUNS                    | Iterations to perform action on a single node                         | 1                                    |
-CLOUD_TYPE              | Cloud platform on top of which cluster is running, supported platforms - aws or vmware                     | aws |
+CLOUD_TYPE              | Cloud platform on top of which cluster is running, supported platforms - aws, vmware, ibmcloud, bm           | aws |
 TIMEOUT                 | Duration to wait for completion of node scenario injection             | 180                                |
 DURATION                | Duration to stop the node before running the start action - not supported for vmware and ibm cloud type             | 120                                |
 VERIFY_SESSION          | Only needed for vmware - Set to True if you want to verify the vSphere client session using certificates    | False                               |
 SKIP_OPENSHIFT_CHECKS   | Only needed for vmware - Set to True if you don't want to wait for the status of the nodes to change on OpenShift before passing the scenario  | False |
+BMC_USER                 | Only needed for Baremetal ( bm ) - IPMI/bmc username | "" | 
+BMC_PASSWORD             | Only needed for Baremetal ( bm ) - IPMI/bmc password | "" |
+BMC_ADDR                 | Only needed for Baremetal ( bm ) - IPMI/bmc username | "" |
 
 #### Demo
 You can find a link to a demo of the scenario [here](https://asciinema.org/a/ANZY7HhPdWTNaWt4xMFanF6Q5)
@@ -74,6 +77,13 @@ $ export IBMC_APIKEY=<ibmcloud_api_key>
 
 ```
 
+Baremetal
+```
+$ export BMC_USER=<bmc/IPMI user>
+$ export BMC_PASSWORD=<bmc/IPMI password>
+$ export BMC_ADDR=<bmc address>
+```
+
 Google Cloud Platform
 ```
 TBD
@@ -93,11 +103,6 @@ OpenStack
 TBD
 ```
 
-Baremetal
-```
-TBD
-```
-
 **NOTE** In case of using custom metrics profile or alerts profile when `CAPTURE_METRICS` or `ENABLE_ALERTS` is enabled, mount the metrics profile from the host on which the container is run using podman/docker under `/home/krkn/kraken/config/metrics-aggregated.yaml` and `/home/krkn/kraken/config/alerts`. For example:
 ```
 $ podman run --name=<container_name> --net=host --env-host=true -v <path-to-custom-metrics-profile>:/home/krkn/kraken/config/metrics-aggregated.yaml -v <path-to-custom-alerts-profile>:/home/krkn/kraken/config/alerts -v <path-to-kube-config>:/home/krkn/.kube/config:Z -d quay.io/krkn-chaos/krkn-hub:container-scenarios
diff --git a/node-scenarios/Dockerfile b/node-scenarios/Dockerfile
@@ -4,6 +4,10 @@ FROM quay.io/krkn-chaos/krkn:latest
 
 ENV KUBECONFIG /home/krkn/.kube/config
 
+USER root
+RUN yum install -y OpenIPMI ipmitool
+USER krkn
+
 # Copy configurations
 COPY config.yaml.template /home/krkn/kraken/config/config.yaml.template
 COPY metrics_config.yaml.template /home/krkn/kraken/config/kube_burner.yaml.template
@@ -13,4 +17,5 @@ COPY node-scenarios/run.sh /home/krkn/run.sh
 COPY common_run.sh /home/krkn/common_run.sh
 COPY node-scenarios/node_scenario.yaml.template /home/krkn/kraken/scenarios/node_scenario.yaml.template
 COPY node-scenarios/plugin_node_scenario.yaml.template /home/krkn/kraken/scenarios/plugin_node_scenario.yaml.template
+COPY node-scenarios/baremetal_node_scenario.yaml.template /home/krkn/kraken/scenarios/baremetal_node_scenario.yaml.template
 ENTRYPOINT /home/krkn/run.sh
diff --git a/node-scenarios/baremetal_node_scenario.yaml.template b/node-scenarios/baremetal_node_scenario.yaml.template
@@ -0,0 +1,14 @@
+node_scenarios:
+  - actions:                                                        # Node chaos scenarios to be injected.
+    - $ACTION
+    node_name: $NODE_NAME                                           # Node on which scenario has to be injected.
+    label_selector: $LABEL_SELECTOR                                 # When node_name is not specified, a node with matching label_selector is selected for node chaos scenario injection.
+    instance_count: $INSTANCE_COUNT                                 # Number of nodes to perform action/select that match the label selector.
+    runs: $RUNS                                                     # Number of times to inject each scenario under actions (will perform on same node each time).
+    timeout: $TIMEOUT                                               # Duration to wait for completion of node scenario injection.
+    cloud_type: $CLOUD_TYPE                                         # Cloud type on which Kubernetes/OpenShift runs.
+    bmc_user: $BMC_USER                                             # For baremetal (bm) cloud type. The default IPMI username. Optional if specified for all machines.
+    bmc_password: $BMC_PASSWORD                                     # For baremetal (bm) cloud type. The default IPMI password. Optional if specified for all machines.
+    bmc_info:                                                       # This section is here to specify baremetal per-machine info, so it is optional if there is no per-machine info.
+      $NODE_NAME:                                                   # The node name for the baremetal machine
+        bmc_addr: $BMC_ADDR                                         # Optional. For baremetal nodes with the IPMI BMC address missing from 'oc get bmh'.
diff --git a/node-scenarios/env.sh b/node-scenarios/env.sh
@@ -14,3 +14,8 @@ export SCENARIO_FILE=${SCENARIO_FILE:=scenarios/node_scenario.yaml}
 export SCENARIO_POST_ACTION=${SCENARIO_POST_ACTION:=""}
 export VERIFY_SESSION=${VERIFY_SESSION:="false"}
 export SKIP_OPENSHIFT_CHECKS=${SKIP_OPENSHIFT_CHECKS:="false"}
+
+# Baremetal vars
+export BMC_USER=${BMC_USER:=""}
+export BMC_PASSWORD=${BMC_PASSWORD:=""}
+export BMC_ADDR=${BMC_ADDR:=""}
diff --git a/node-scenarios/run.sh b/node-scenarios/run.sh
@@ -26,10 +26,13 @@ if [[ "$CLOUD_TYPE" == "vmware" || "$CLOUD_TYPE" == "ibmcloud" ]]; then
   fi
   envsubst < /home/krkn/kraken/scenarios/plugin_node_scenario.yaml.template > /home/krkn/kraken/scenarios/node_scenario.yaml
 
-
+elif [[ "$CLOUD_TYPE" == "bm" ]]; then
+    envsubst < /home/krkn/kraken/scenarios/baremetal_node_scenario.yaml.template > /home/krkn/kraken/scenarios/node_scenario.yaml  
 else
   envsubst < /home/krkn/kraken/scenarios/node_scenario.yaml.template > /home/krkn/kraken/scenarios/node_scenario.yaml
 fi
+
+# Setup config
 envsubst < /home/krkn/kraken/config/config.yaml.template > /home/krkn/kraken/config/node_scenario_config.yaml
 
 # Run Kraken