Hog scenario porting from arcaflow to native (#748)

* added new native hog scenario * removed arcaflow dependency + legacy hog scenarios * config update * changed hog configuration structure + added average samples * fix on cpu count * removes tripledes warning * changed selector format * changed selector syntax * number of nodes option * documentation * functional tests * exception handling on hog deployment thread Signed-off-by: Paige Patton <[email protected]>
krkn-chaos · Jan 31, 2025 · 82b4cea · 82b4cea
1 parent 64cfd2c
commit 82b4cea
Show file tree

Hide file tree

Showing 52 changed files with 588 additions and 1,313 deletions.
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
@@ -84,9 +84,9 @@ jobs:
             echo "test_namespace"      >> ./CI/tests/functional_tests
             echo "test_net_chaos"      >> ./CI/tests/functional_tests
             echo "test_time"           >> ./CI/tests/functional_tests
-            echo "test_arca_cpu_hog" >> ./CI/tests/functional_tests
-            echo "test_arca_memory_hog" >> ./CI/tests/functional_tests
-            echo "test_arca_io_hog" >> ./CI/tests/functional_tests
+            echo "test_cpu_hog" >> ./CI/tests/functional_tests
+            echo "test_memory_hog" >> ./CI/tests/functional_tests
+            echo "test_io_hog" >> ./CI/tests/functional_tests
 
 
       # Push on main only steps + all other functional to collect coverage
@@ -113,9 +113,9 @@ jobs:
           echo "test_namespace"      >> ./CI/tests/functional_tests
           echo "test_net_chaos"      >> ./CI/tests/functional_tests
           echo "test_time"           >> ./CI/tests/functional_tests
-          echo "test_arca_cpu_hog" >> ./CI/tests/functional_tests
-          echo "test_arca_memory_hog" >> ./CI/tests/functional_tests
-          echo "test_arca_io_hog" >> ./CI/tests/functional_tests
+          echo "test_cpu_hog" >> ./CI/tests/functional_tests
+          echo "test_memory_hog" >> ./CI/tests/functional_tests
+          echo "test_io_hog" >> ./CI/tests/functional_tests
 
       # Final common steps
       - name: Run Functional tests

diff --git a/CI/tests/test_arca_cpu_hog.sh b/CI/tests/test_arca_cpu_hog.sh
diff --git a/CI/tests/test_arca_io_hog.sh b/CI/tests/test_arca_io_hog.sh
diff --git a/CI/tests/test_arca_memory_hog.sh b/CI/tests/test_arca_memory_hog.sh
diff --git a/CI/tests/test_cpu_hog.sh b/CI/tests/test_cpu_hog.sh
@@ -0,0 +1,20 @@
+set -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+
+function functional_test_cpu_hog {
+  yq -i '.node_selector="kubernetes.io/hostname=kind-worker2"' scenarios/kube/cpu-hog.yml
+
+  export scenario_type="hog_scenarios"
+  export scenario_file="scenarios/kube/cpu-hog.yml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/cpu_hog.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/cpu_hog.yaml
+  echo "CPU Hog: Success"
+}
+
+functional_test_cpu_hog
diff --git a/CI/tests/test_io_hog.sh b/CI/tests/test_io_hog.sh
@@ -0,0 +1,19 @@
+set -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+
+function functional_test_io_hog {
+  yq -i '.node_selector="kubernetes.io/hostname=kind-worker2"' scenarios/kube/io-hog.yml
+  export scenario_type="hog_scenarios"
+  export scenario_file="scenarios/kube/io-hog.yml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/io_hog.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/io_hog.yaml
+  echo "IO Hog: Success"
+}
+
+functional_test_io_hog
diff --git a/CI/tests/test_memory_hog.sh b/CI/tests/test_memory_hog.sh
@@ -0,0 +1,19 @@
+set -xeEo pipefail
+
+source CI/tests/common.sh
+
+trap error ERR
+trap finish EXIT
+
+
+function functional_test_memory_hog {
+  yq -i '.node_selector="kubernetes.io/hostname=kind-worker2"' scenarios/kube/memory-hog.yml
+  export scenario_type="hog_scenarios"
+  export scenario_file="scenarios/kube/memory-hog.yml"
+  export post_config=""
+  envsubst < CI/config/common_test_config.yaml > CI/config/memory_hog.yaml
+  python3 -m coverage run -a run_kraken.py -c CI/config/memory_hog.yaml
+  echo "Memory Hog: Success"
+}
+
+functional_test_memory_hog
diff --git a/README.md b/README.md
@@ -55,7 +55,7 @@ Scenario type               | Kubernetes
 [Container Scenarios](docs/container_scenarios.md) | :heavy_check_mark: |
 [Node Scenarios](docs/node_scenarios.md) | :heavy_check_mark: |
 [Time Scenarios](docs/time_scenarios.md) | :heavy_check_mark: |
-[Hog Scenarios: CPU, Memory](docs/arcaflow_scenarios.md) | :heavy_check_mark: |
+[Hog Scenarios: CPU, Memory](docs/hog_scenarios.md) | :heavy_check_mark: |
 [Cluster Shut Down Scenarios](docs/cluster_shut_down_scenarios.md) | :heavy_check_mark: |
 [Service Disruption Scenarios](docs/service_disruption_scenarios.md.md) | :heavy_check_mark: |
 [Zone Outage Scenarios](docs/zone_outage.md) | :heavy_check_mark: |

diff --git a/config/config.yaml b/config/config.yaml
@@ -9,10 +9,9 @@ kraken:
     chaos_scenarios:
         # List of policies/chaos scenarios to load
         - hog_scenarios:
-            - scenarios/kube/cpu-hog/input.yaml
-            - scenarios/kube/memory-hog/input.yaml
-            - scenarios/kube/io-hog/input.yaml
-            - scenarios/kube/io-hog/input.yaml
+            - scenarios/kube/cpu-hog.yml
+            - scenarios/kube/memory-hog.yml
+            - scenarios/kube/io-hog.yml
         - application_outages_scenarios:
             - scenarios/openshift/app_outage.yaml
         - container_scenarios:                             # List of chaos pod scenarios to load

diff --git a/docs/arcaflow_scenarios.md b/docs/arcaflow_scenarios.md
diff --git a/docs/arcaflow_scenarios/cpu_hog.md b/docs/arcaflow_scenarios/cpu_hog.md
diff --git a/docs/arcaflow_scenarios/io_hog.md b/docs/arcaflow_scenarios/io_hog.md
diff --git a/docs/arcaflow_scenarios/memory_hog.md b/docs/arcaflow_scenarios/memory_hog.md