Replace Benchmark with Integration Tests

* remove benchmark. resolves #40 * add webmock/vcr based integration tests * test that api gets correct number fo request * test that api gets correct data in each request
rperryng · Oct 31, 2024 · 953c2ea · 953c2ea
1 parent b24a1bb
commit 953c2ea
Show file tree

Hide file tree

Showing 16 changed files with 550 additions and 173 deletions.
diff --git a/.ruby-version b/.ruby-version
@@ -0,0 +1 @@
+3.3.5
diff --git a/Gemfile b/Gemfile
@@ -9,7 +9,15 @@ gemspec
 
 group :development do
   gem "bundler", "~> 2"
+  gem "debug", ">= 1.0.0"
+  gem "rack-contrib", "~> 2"
+  gem "rack-test", "~> 2"
   gem "rake", "~> 13"
   gem "rspec", "~> 3"
+  gem "sinatra", "~> 2"
+  gem "sinatra-contrib"
   gem "standardrb", "~> 1"
+  gem "timecop", "~> 0.9"
+  gem "vcr", "~> 6"
+  gem "webmock", "~> 3"
 end
diff --git a/Gemfile.lock b/Gemfile.lock
@@ -7,22 +7,53 @@ PATH
 GEM
   remote: https://rubygems.org/
   specs:
+    addressable (2.8.7)
+      public_suffix (>= 2.0.2, < 7.0)
     ast (2.4.2)
     base64 (0.2.0)
+    bigdecimal (3.1.8)
+    crack (1.0.0)
+      bigdecimal
+      rexml
+    debug (1.9.2)
+      irb (~> 1.10)
+      reline (>= 0.3.8)
     diff-lcs (1.5.1)
     graphql (2.3.7)
       base64
+    hashdiff (1.1.1)
+    io-console (0.7.2)
+    irb (1.14.1)
+      rdoc (>= 4.0.0)
+      reline (>= 0.4.2)
     json (2.7.2)
     language_server-protocol (3.17.0.3)
     lint_roller (1.1.0)
+    multi_json (1.15.0)
+    mustermann (2.0.2)
+      ruby2_keywords (~> 0.0.1)
     parallel (1.26.3)
     parser (3.3.5.0)
       ast (~> 2.4.1)
       racc
+    psych (5.1.2)
+      stringio
+    public_suffix (6.0.1)
     racc (1.8.1)
+    rack (2.2.10)
+    rack-contrib (2.5.0)
+      rack (< 4)
+    rack-protection (2.2.4)
+      rack
+    rack-test (2.1.0)
+      rack (>= 1.3)
     rainbow (3.1.1)
     rake (13.2.1)
+    rdoc (6.7.0)
+      psych (>= 4.0.0)
     regexp_parser (2.9.2)
+    reline (0.5.10)
+      io-console (~> 0.5)
     rexml (3.3.8)
     rspec (3.13.0)
       rspec-core (~> 3.13.0)
@@ -54,6 +85,18 @@ GEM
       rubocop (>= 1.48.1, < 2.0)
       rubocop-ast (>= 1.31.1, < 2.0)
     ruby-progressbar (1.13.0)
+    ruby2_keywords (0.0.5)
+    sinatra (2.2.4)
+      mustermann (~> 2.0)
+      rack (~> 2.2)
+      rack-protection (= 2.2.4)
+      tilt (~> 2.0)
+    sinatra-contrib (2.2.4)
+      multi_json
+      mustermann (~> 2.0)
+      rack-protection (= 2.2.4)
+      sinatra (= 2.2.4)
+      tilt (~> 2.0)
     standard (1.40.1)
       language_server-protocol (~> 3.17.0.2)
       lint_roller (~> 1.0)
@@ -68,18 +111,35 @@ GEM
       rubocop-performance (~> 1.21.0)
     standardrb (1.0.1)
       standard
+    stringio (3.1.1)
+    tilt (2.4.0)
+    timecop (0.9.10)
     unicode-display_width (2.6.0)
+    vcr (6.3.1)
+      base64
+    webmock (3.24.0)
+      addressable (>= 2.8.0)
+      crack (>= 0.3.2)
+      hashdiff (>= 0.4.0, < 2.0.0)
 
 PLATFORMS
   arm64-darwin-23
   ruby
 
 DEPENDENCIES
   bundler (~> 2)
+  debug (>= 1.0.0)
   graphql-hive!
+  rack-contrib (~> 2)
+  rack-test (~> 2)
   rake (~> 13)
   rspec (~> 3)
+  sinatra (~> 2)
+  sinatra-contrib
   standardrb (~> 1)
+  timecop (~> 0.9)
+  vcr (~> 6)
+  webmock (~> 3)
 
 BUNDLED WITH
    2.5.15
diff --git a/README.md b/README.md
@@ -1,4 +1,4 @@
-# GraphQL Hive: `graphql-ruby` integration 
+# GraphQL Hive: `graphql-ruby` integration
 [![CI Suite](https://github.com/charlypoly/graphql-ruby-hive/actions/workflows/ci.yml/badge.svg)](https://github.com/charlypoly/graphql-ruby-hive/actions)
 [![Gem Version](https://badge.fury.io/rb/graphql-hive.svg)](https://rubygems.org/gems/graphql-hive)
 
@@ -146,38 +146,53 @@ class MySchema < GraphQL::Schema
   use(
     GraphQL::Hive,
     {
-      # mandatory
-      token: 'YOUR-TOKEN',
-
-      # optional
-      enabled: true, # enable/disable Hive Client
-      debug: false, # verbose logs
+      # token is the only required configuration value
+      token: 'YOUR-REGISTRY-TOKEN',
+      #
+      # The following are optional configuration values
+      #
+      # enable/disable Hive Client
+      enabled: true,
+      # verbose logs
+      debug: false,
+      # A custom logger
       logger: MyLogger.new,
+      # endpoint and port of the Hive API. Change this if you are using a self-hosted Hive instance
       endpoint: 'app.graphql-hive.com',
       port: 80,
-      buffer_size: 50, # how many operations can be sent to hive in a single batch (AFTER sampling)
-
-      collect_usage: true, # report usage to Hive
+      # number of operations sent to hive in a batch (AFTER sampling)
+      buffer_size: 50,
+      # size of the queue used to send operations to the buffer before sampling
+      queue_size: 1000,
+      # report usage to hive
+      collect_usage: true,
+      # Usage sampling configurations
       collect_usage_sampling: {
-        # optional members of `collect_usage_sampling`  
-        sample_rate: 0.5, # % of operations reported
-        sampler: proc { |context| context.operation_name.includes?('someQuery') 1 : 0.5 }, # assign custom sampling rates (overrides `sampling rate`)
-        at_least_once: true, # sample every distinct operation at least once
-        key_generator: proc { |context| context.operation_name } # assign custom keys to distinguish between distinct operations
+        # % of operations recorded
+        sample_rate: 0.5,
+        # custom sampler to assign custom sampling rates
+        sampler: proc { |context| context.operation_name.includes?('someQuery') 1 : 0.5 },
+        # sample every distinct operation at least once
+        at_least_once: true,
+        # assign custom keys to distinguish between distinct operations
+        key_generator: proc { |context| context.operation_name }
       },
-      report_schema: true,  # publish schema to Hive
+      # publish schema to Hive
+      report_schema: true,
       # mandatory if `report_schema: true`
-      reporting: { 
+      reporting: {
         # mandatory members of `reporting`
         author: 'Author of the latest change',
         commit: 'git sha or any identifier',
-        # optional members of `reporting  
+        # optional members of `reporting
         service_name: '',
         service_url: '',
       },
 
        # pass an optional proc to client_info to help identify the client (ex: Apollo web app) that performed the query
-      client_info: proc { |context| { name: context.client_name, version: context.client_version } }
+      client_info: proc { |context|
+        { name: context.client_name, version: context.client_version }
+      }
     }
   )
 
@@ -186,16 +201,14 @@ class MySchema < GraphQL::Schema
 end
 ```
 
-See default options for the optional parameters [here](https://github.com/charlypoly/graphql-ruby-hive/blob/01407d8fed80912a7006fee503bf2967fa20a79c/lib/graphql-hive.rb#L53).
+See default options for the optional parameters [here](https://github.com/rperryng/graphql-ruby-hive/blob/master/lib/graphql-hive.rb#L31-L41).
 
 <br/>
 
-**A note on `buffer_size` and performances**
-
-The `graphql-hive` usage reporter, responsible for sending the operations data to Hive, is running in a separate `Thread` to avoid any significant impact on your GraphQL API performances.
-
-The performance overhead (with the default `buffer_size` option) is around 1% and [is constantly evaluated for new PR](https://github.com/charlypoly/graphql-ruby-hive/actions/workflows/benchmark.yml).
-
-If your GraphQL API has a high RPM, we encourage you to increase the `buffer_size` value.
-
-However, please note that a higher `buffer_size` value will introduce some peak of increase in memory consumption.
+> [!Important]
+> `buffer_size` and `queue_size` will affect memory consumption.
+>
+> `buffer_size` is the number of operations sent to Hive in a batch after operations have been sampled.
+> `queue_size` is the size of the queue used to send operations to the buffer before sampling.
+> Adjust these values according to your application's memory constraints and throughput.
+> High throughput applications will need a larger `queue_size`.
diff --git a/examples/simple-api/Gemfile b/examples/simple-api/Gemfile
diff --git a/examples/simple-api/Gemfile.lock b/examples/simple-api/Gemfile.lock
diff --git a/examples/simple-api/app.rb b/examples/simple-api/app.rb
diff --git a/examples/simple-api/config.ru b/examples/simple-api/config.ru
diff --git a/examples/simple-api/schema.rb b/examples/simple-api/schema.rb
diff --git a/lib/graphql-hive.rb b/lib/graphql-hive.rb
@@ -10,6 +10,7 @@
 require "graphql-hive/sampler"
 require "graphql-hive/sampling/basic_sampler"
 require "graphql-hive/sampling/dynamic_sampler"
+require "graphql"
 
 module GraphQL
   # GraphQL Hive usage collector and schema reporter
@@ -36,6 +37,7 @@ class Hive < GraphQL::Tracing::PlatformTracing
       read_operations: true,
       report_schema: true,
       buffer_size: 50,
+      queue_size: 1000,
       logger: nil,
       collect_usage_sampling: 1.0
     }.freeze