feat: add database resource limit fault

sre/playbooks/roles

@@ -0,0 +1 @@
+../roles

sre/roles/faults/tasks/inject_custom.yaml

@@ -1,4 +1,13 @@
 ---
+- name: Low Mem CPU Constraints
+  ansible.builtin.import_tasks:
+    file: inject_low_mem_cpu_constraints.yaml
+  vars:
+    spec: "{{ fault.custom.misconfigured_service_port }}"
+  when:
+    - fault.custom.name == 'low-mem-cpu-constraints'
+    - fault.custom.low_mem_cpu_constraints is defined
+
 - name: Import invalid command injection tasks
   ansible.builtin.import_tasks:
     file: inject_custom_invalid_command.yaml

sre/roles/faults/tasks/inject_low_mem_cpu_constraints.yaml

@@ -0,0 +1,68 @@
+---
+- name: Create ResourceQuota with hard memory limits
+  kubernetes.core.k8s:
+    kubeconfig: "{{ faults_cluster.kubeconfig }}"
+    resource_definition:
+      apiVersion: v1
+      kind: ResourceQuota
+      metadata:
+        name: "{{ spec.namespace.name }}-memory"
+        namespace: "{{ spec.namespace.name }}"
+      spec:
+        hard:
+          requests.memory: 1Gi
+          limits.memory: 2Gi
+          requests.cpu: "1"
+          limits.cpu: "2"
+          pods: "10"
+    state: present
+
+- name: Retrieve workload replica information
+  kubernetes.core.k8s_info:
+    api_version: apps/v1
+    kind: "{{ workload.kind }}"
+    kubeconfig: "{{ faults_cluster.kubeconfig }}"
+    name: "{{ workload.name }}"
+    namespace: "{{ spec.namespace.name }}"
+  register: faults_workloads_info
+  loop: "{{ spec.workloads }}"
+  loop_control:
+    label: "{{ workload.kind | lower }}/{{ workload.name }}"
+    loop_var: workload
+  when:
+    - workload.name != 'otel-collector'
+
+- name: Scale down workloads to 0 replicas
+  kubernetes.core.k8s_scale:
+    api_version: "{{ result.resources[0].apiVersion }}"
+    kind: "{{ result.resources[0].kind }}"
+    kubeconfig: "{{ faults_cluster.kubeconfig }}"
+    name: "{{ result.resources[0].metadata.name }}"
+    namespace: "{{ result.resources[0].metadata.namespace }}"
+    replicas: 0
+    wait: true
+    wait_timeout: 60
+  loop: "{{ faults_workloads_info.results }}"
+  loop_control:
+    label: "{{ result.resources[0].kind | lower }}/{{ result.resources[0].metadata.name }}"
+    loop_var: result
+  when:
+    - faults_workloads_info is defined
+    - result.resources | length == 1
+
+- name: Scale up workloads to original replica count
+  kubernetes.core.k8s_scale:
+    api_version: "{{ result.resources[0].apiVersion }}"
+    kind: "{{ result.resources[0].kind }}"
+    kubeconfig: "{{ faults_cluster.kubeconfig }}"
+    name: "{{ result.resources[0].metadata.name }}"
+    namespace: "{{ result.resources[0].metadata.namespace }}"
+    replicas: "{{ result.resources[0].spec.replicas }}"
+    wait: false
+  loop: "{{ faults_workloads_info.results }}"
+  loop_control:
+    label: "{{ result.resources[0].kind | lower }}/{{ result.resources[0].metadata.name }}"
+    loop_var: result
+  when:
+    - faults_workloads_info is defined
+    - result.resources | length == 1

sre/roles/incidents/files/ground_truths/incident_32.yaml

@@ -0,0 +1,26 @@
+---
+fault: []
+alerts:
+  - id: CPUSpend
+    group_id: otel-demo-namespace-1
+    metadata:
+      description: CPU spend increased by 20 percent
+  - id: MemorySpend
+    group_id: otel-demo-namespace-1
+    metadata:
+      description: Memory spend has increased by 20 percent
+groups:
+  - id: otel-demo-namespace-1
+    kind: Namespace
+    name: otel-demo
+    namespace: otel-demo
+    root_cause: true
+aliases:
+  - - otel-demo-namespace-1
+propagations: []
+recommended_actions:
+  - solution:
+      id: "no_action"
+      actions:
+        - no changes is needed in application
+        - update opencost alert to prevent false alerts

sre/roles/incidents/files/specs/incident_32.yaml

@@ -0,0 +1,23 @@
+---
+metadata:
+  complexity: Low
+  id: 32
+  name: Low Mem CPU Constraints
+  platform: kubernetes
+spec:
+  environment:
+    applications:
+      otel_demo:
+        enabled: true
+    tools:
+      category: sre
+      selected:
+        - kubernetes-topology-monitor
+  faults:
+    - custom: 
+        name: misconfigured-resource-quota
+        misconfigured_network_policy:
+          workload:
+            kind: Deployment
+            name: frontend
+            namespace: "{{ applications_helm_releases.otel_demo.namespace }}"