Merge branch 'improve-chaos-controller' into 'master'

Add `db_spin` and refactor ChaosController

Closes #64425

See merge request gitlab-org/gitlab-ce!30559

app/controllers/chaos_controller.rb

 # frozen_string_literal: true
 
 class ChaosController < ActionController::Base
-  before_action :validate_request
+  before_action :validate_chaos_secret, unless: :development?
+  before_action :request_start_time
 
   def leakmem
-    memory_mb = (params[:memory_mb]&.to_i || 100)
-    duration_s = (params[:duration_s]&.to_i || 30).seconds
-
-    start = Time.now
     retainer = []
     # Add `n` 1mb chunks of memory to the retainer array
     memory_mb.times { retainer << "x" * 1.megabyte }
 
-    duration_taken = (Time.now - start).seconds
-    Kernel.sleep duration_s - duration_taken if duration_s > duration_taken
+    Kernel.sleep(duration_left)
 
     render plain: "OK"
   end
 
-  def cpuspin
-    duration_s = (params[:duration_s]&.to_i || 30).seconds
-    end_time = Time.now + duration_s.seconds
-
-    rand while Time.now < end_time
+  def cpu_spin
+    rand while Time.now < expected_end_time
 
     render plain: "OK"
   end
 
+  def db_spin
+    while Time.now < expected_end_time
+      ActiveRecord::Base.connection.execute("SELECT 1")
+
+      end_interval_time = Time.now + [duration_s, interval_s].min
+      rand while Time.now < end_interval_time
+    end
+  end
+
   def sleep
-    duration_s = (params[:duration_s]&.to_i || 30).seconds
-    Kernel.sleep duration_s
+    Kernel.sleep(duration_left)
 
     render plain: "OK"
   end
@@ -40,17 +41,57 @@ class ChaosController < ActionController::Base
 
   private
 
-  def validate_request
-    secret = ENV['GITLAB_CHAOS_SECRET']
-    # GITLAB_CHAOS_SECRET is required unless you're running in Development mode
-    if !secret && !Rails.env.development?
-      render plain: "chaos misconfigured: please configure GITLAB_CHAOS_SECRET when using GITLAB_ENABLE_CHAOS_ENDPOINTS outside of a development environment", status: :internal_server_error
-    end
+  def request_start_time
+    @start_time ||= Time.now
+  end
+
+  def expected_end_time
+    request_start_time + duration_s
+  end
 
-    return unless secret
+  def duration_left
+    # returns 0 if over time
+    [expected_end_time - Time.now, 0].max
+  end
+
+  def validate_chaos_secret
+    unless chaos_secret_configured
+      render plain: "chaos misconfigured: please configure GITLAB_CHAOS_SECRET",
+             status: :internal_server_error
+      return
+    end
 
-    unless request.headers["HTTP_X_CHAOS_SECRET"] == secret
-      render plain: "To experience chaos, please set X-Chaos-Secret header", status: :unauthorized
+    unless Devise.secure_compare(chaos_secret_configured, chaos_secret_request)
+      render plain: "To experience chaos, please set a valid `X-Chaos-Secret` header or `token` param",
+             status: :unauthorized
+      return
     end
   end
+
+  def chaos_secret_configured
+    ENV['GITLAB_CHAOS_SECRET']
+  end
+
+  def chaos_secret_request
+    request.headers["HTTP_X_CHAOS_SECRET"] || params[:token]
+  end
+
+  def interval_s
+    interval_s = params[:interval_s] || 1
+    interval_s.to_f.seconds
+  end
+
+  def duration_s
+    duration_s = params[:duration_s] || 30
+    duration_s.to_i.seconds
+  end
+
+  def memory_mb
+    memory_mb = params[:memory_mb] || 100
+    memory_mb.to_i
+  end
+
+  def development?
+    Rails.env.development?
+  end
 end

config/routes.rb

@@ -110,11 +110,14 @@ Rails.application.routes.draw do
       draw :jira_connect
     end
 
-    if ENV['GITLAB_ENABLE_CHAOS_ENDPOINTS']
-      get '/chaos/leakmem' => 'chaos#leakmem'
-      get '/chaos/cpuspin' => 'chaos#cpuspin'
-      get '/chaos/sleep' => 'chaos#sleep'
-      get '/chaos/kill' => 'chaos#kill'
+    if ENV['GITLAB_CHAOS_SECRET'] || Rails.env.development?
+      resource :chaos, only: [] do
+        get :leakmem
+        get :cpu_spin
+        get :db_spin
+        get :sleep
+        get :kill
+      end
     end
   end
 

doc/development/chaos_endpoints.md

@@ -15,23 +15,19 @@ Currently, there are four endpoints for simulating the following conditions:
 
 ## Enabling chaos endpoints
 
-For obvious reasons, these endpoints are not enabled by default. They can be enabled by setting the `GITLAB_ENABLE_CHAOS_ENDPOINTS` environment variable to `1`.
-
-For example, if you're using the [GDK](https://gitlab.com/gitlab-org/gitlab-development-kit) this can be done with the following command:
-
-```bash
-GITLAB_ENABLE_CHAOS_ENDPOINTS=1 gdk run
-```
-
-## Securing the chaos endpoints
+For obvious reasons, these endpoints are not enabled by default on `production`.
+They are enabled by default on **development** environments.
 
 DANGER: **Danger:**
-It is highly recommended that you secure access to the chaos endpoints using a secret token. This is recommended when enabling these endpoints locally and essential when running in a staging or other shared environment. You should not enable them in production unless you absolutely know what you're doing.
+It is required that you secure access to the chaos endpoints using a secret token.
+You should not enable them in production unless you absolutely know what you're doing.
 
-A secret token can be set through the `GITLAB_CHAOS_SECRET` environment variable. For example, when using the [GDK](https://gitlab.com/gitlab-org/gitlab-development-kit) this can be done with the following command:
+A secret token can be set through the `GITLAB_CHAOS_SECRET` environment variable.
+For example, when using the [GDK](https://gitlab.com/gitlab-org/gitlab-development-kit)
+this can be done with the following command:
 
 ```bash
-GITLAB_ENABLE_CHAOS_ENDPOINTS=1 GITLAB_CHAOS_SECRET=secret gdk run
+GITLAB_CHAOS_SECRET=secret gdk run
 ```
 
 Replace `secret` with your own secret token.
@@ -56,10 +52,11 @@ GET /-/chaos/leakmem?memory_mb=1024&duration_s=50
 | Attribute    | Type    | Required | Description                                                                        |
 | ------------ | ------- | -------- | ---------------------------------------------------------------------------------- |
 | `memory_mb`  | integer | no       | How much memory, in MB, should be leaked. Defaults to 100MB.                       |
-| `duration_s` | integer | no       | Minimum duration, in seconds, that the memory should be retained. Defaults to 30s. |
+| `duration_s` | integer | no       | Minimum duration_s, in seconds, that the memory should be retained. Defaults to 30s. |
 
 ```bash
 curl http://localhost:3000/-/chaos/leakmem?memory_mb=1024&duration_s=10 --header 'X-Chaos-Secret: secret'
+curl http://localhost:3000/-/chaos/leakmem?memory_mb=1024&duration_s=10&token=secret
 ```
 
 ## CPU spin
@@ -70,23 +67,47 @@ Depending on your rack server setup, your request may timeout after a predermine
 If you're using Unicorn, this is done by killing the worker process.
 
 ```
-GET /-/chaos/cpuspin
-GET /-/chaos/cpuspin?duration_s=50
+GET /-/chaos/cpu_spin
+GET /-/chaos/cpu_spin?duration_s=50
+```
+
+| Attribute    | Type    | Required | Description                                                           |
+| ------------ | ------- | -------- | --------------------------------------------------------------------- |
+| `duration_s` | integer | no       | Duration, in seconds, that the core will be utilised. Defaults to 30s |
+
+```bash
+curl http://localhost:3000/-/chaos/cpu_spin?duration_s=60 --header 'X-Chaos-Secret: secret'
+curl http://localhost:3000/-/chaos/cpu_spin?duration_s=60&token=secret
+```
+
+## DB spin
+
+This endpoint attempts to fully utilise a single core, and interleave it with DB request, for the given period.
+This endpoint can be used to model yielding execution to another threads when running concurrently.
+
+Depending on your rack server setup, your request may timeout after a predermined period (normally 60 seconds).
+If you're using Unicorn, this is done by killing the worker process.
+
+```
+GET /-/chaos/db_spin
+GET /-/chaos/db_spin?duration_s=50
 ```
 
 | Attribute    | Type    | Required | Description                                                           |
 | ------------ | ------- | -------- | --------------------------------------------------------------------- |
+| `interval_s` | float   | no       | Interval, in seconds, for every DB request. Defaults to 1s            |
 | `duration_s` | integer | no       | Duration, in seconds, that the core will be utilised. Defaults to 30s |
 
 ```bash
-curl http://localhost:3000/-/chaos/cpuspin?duration_s=60 --header 'X-Chaos-Secret: secret'
+curl http://localhost:3000/-/chaos/db_spin?interval_s=1&duration_s=60 --header 'X-Chaos-Secret: secret'
+curl http://localhost:3000/-/chaos/db_spin?interval_s=1&duration_s=60&token=secret
 ```
 
 ## Sleep
 
-This endpoint is similar to the CPU Spin endpoint but simulates off-processor activity, such as network calls to backend services. It will sleep for a given duration.
+This endpoint is similar to the CPU Spin endpoint but simulates off-processor activity, such as network calls to backend services. It will sleep for a given duration_s.
 
-As with the CPU Spin endpoint, this may lead to your request timing out if duration exceeds the configured limit.
+As with the CPU Spin endpoint, this may lead to your request timing out if duration_s exceeds the configured limit.
 
 ```
 GET /-/chaos/sleep
@@ -99,6 +120,7 @@ GET /-/chaos/sleep?duration_s=50
 
 ```bash
 curl http://localhost:3000/-/chaos/sleep?duration_s=60 --header 'X-Chaos-Secret: secret'
+curl http://localhost:3000/-/chaos/sleep?duration_s=60&token=secret
 ```
 
 ## Kill
@@ -114,4 +136,5 @@ GET /-/chaos/kill
 
 ```bash
 curl http://localhost:3000/-/chaos/kill --header 'X-Chaos-Secret: secret'
+curl http://localhost:3000/-/chaos/kill?token=secret
 ```