Merge pull request #35073 from eileencodes/db-selection

Part 8: Multi db improvements, Adds basic automatic database switching to Rails

9 files changed, 353 insertions, 0 deletions

diff --git a/activerecord/CHANGELOG.md b/activerecord/CHANGELOG.md
index 67cf5881d3..654caafc92 100644
--- a/activerecord/CHANGELOG.md
+++ b/activerecord/CHANGELOG.md
@@ -1,3 +1,36 @@
+*   Allow applications to automatically switch connections.
+
+    Adds a middleware and configuration options that can be used in your
+    application to automatically switch between the writing and reading
+    database connections.
+
+    `GET` and `HEAD` requests will read from the replica unless there was
+    a write in the last 2 seconds, otherwise they will read from the primary.
+    Non-get requests will always write to the primary. The middleware accepts
+    an argument for a Resolver class and a Operations class where you are able
+    to change how the auto-switcher works to be most beneficial for your
+    application.
+
+    To use the middleware in your application you can use the following
+    configuration options:
+
+    ```
+    config.active_record.database_selector = { delay: 2.seconds }
+    config.active_record.database_resolver = ActiveRecord::Middleware::DatabaseSelector::Resolver
+    config.active_record.database_operations = ActiveRecord::Middleware::DatabaseSelector::Resolver::Session
+    ```
+
+    To change the database selection strategy, pass a custom class to the
+    configuration options:
+
+    ```
+    config.active_record.database_selector = { delay: 10.seconds }
+    config.active_record.database_resolver = MyResolver
+    config.active_record.database_operations = MyResolver::MyCookies
+    ```
+
+    *Eileen M. Uchitelle*
+
 *   MySQL: Support `:size` option to change text and blob size.
 
     *Ryuta Kamizono*
diff --git a/activerecord/lib/active_record.rb b/activerecord/lib/active_record.rb
index de94f9693f..7d66158f47 100644
--- a/activerecord/lib/active_record.rb
+++ b/activerecord/lib/active_record.rb
@@ -74,6 +74,7 @@ module ActiveRecord
   autoload :Translation
   autoload :Validations
   autoload :SecureToken
+  autoload :DatabaseSelector, "active_record/middleware/database_selector"
 
   eager_autoload do
     autoload :ActiveRecordError, "active_record/errors"
@@ -153,6 +154,12 @@ module ActiveRecord
     end
   end
 
+  module Middleware
+    extend ActiveSupport::Autoload
+
+    autoload :DatabaseSelector, "active_record/middleware/database_selector"
+  end
+
   module Tasks
     extend ActiveSupport::Autoload
 
diff --git a/activerecord/lib/active_record/core.rb b/activerecord/lib/active_record/core.rb
index 369d63e40a..519acd7605 100644
--- a/activerecord/lib/active_record/core.rb
+++ b/activerecord/lib/active_record/core.rb
@@ -101,6 +101,7 @@ module ActiveRecord
       # environment where dumping schema is rarely needed.
       mattr_accessor :dump_schema_after_migration, instance_writer: false, default: true
 
+      mattr_accessor :database_selector, instance_writer: false
       ##
       # :singleton-method:
       # Specifies which database schemas to dump when calling db:structure:dump.
diff --git a/activerecord/lib/active_record/middleware/database_selector.rb b/activerecord/lib/active_record/middleware/database_selector.rb
new file mode 100644
index 0000000000..06529bc1c9
--- /dev/null
+++ b/activerecord/lib/active_record/middleware/database_selector.rb
@@ -0,0 +1,74 @@
+# frozen_string_literal: true
+
+require "active_record/middleware/database_selector/resolver"
+
+module ActiveRecord
+  module Middleware
+    # The DatabaseSelector Middleware provides a framework for automatically
+    # swapping from the primary to the replica database connection. Rails
+    # provides a basic framework to determine when to swap and allows for
+    # applications to write custom strategy classes to override the default
+    # behavior.
+    #
+    # The resolver class defines when the application should switch (i.e. read
+    # from the primary if a write occurred less than 2 seconds ago) and an
+    # operations class that sets a value that helps the resolver class decide
+    # when to switch.
+    #
+    # Rails default middleware uses the request's session to set a timestamp
+    # that informs the application when to read from a primary or read from a
+    # replica.
+    #
+    # To use the DatabaseSelector in your application with default settings add
+    # the following options to your environment config:
+    #
+    #   config.active_record.database_selector = { delay: 2.seconds }
+    #   config.active_record.database_resolver = ActiveRecord::Middleware::DatabaseSelector::Resolver
+    #   config.active_record.database_operations = ActiveRecord::Middleware::DatabaseSelector::Resolver::Session
+    #
+    # New applications will include these lines commented out in the production.rb.
+    #
+    # The default behavior can be changed by setting the config options to a
+    # custom class:
+    #
+    #   config.active_record.database_selector = { delay: 2.seconds }
+    #   config.active_record.database_resolver = MyResolver
+    #   config.active_record.database_operations = MyResolver::MySession
+    class DatabaseSelector
+      def initialize(app, resolver_klass = Resolver, operations_klass = Resolver::Session)
+        @app = app
+        @resolver_klass = resolver_klass
+        @operations_klass = operations_klass
+      end
+
+      attr_reader :resolver_klass, :operations_klass
+
+      # Middleware that determines which database connection to use in a mutliple
+      # database application.
+      def call(env)
+        request = ActionDispatch::Request.new(env)
+
+        select_database(request) do
+          @app.call(env)
+        end
+      end
+
+      private
+
+        def select_database(request, &blk)
+          operations = operations_klass.build(request)
+          database_resolver = resolver_klass.call(operations)
+
+          if reading_request?(request)
+            database_resolver.read(&blk)
+          else
+            database_resolver.write(&blk)
+          end
+        end
+
+        def reading_request?(request)
+          request.get? || request.head?
+        end
+    end
+  end
+end
diff --git a/activerecord/lib/active_record/middleware/database_selector/resolver.rb b/activerecord/lib/active_record/middleware/database_selector/resolver.rb
new file mode 100644
index 0000000000..1c056e2156
--- /dev/null
+++ b/activerecord/lib/active_record/middleware/database_selector/resolver.rb
@@ -0,0 +1,88 @@
+# frozen_string_literal: true
+
+require "active_record/middleware/database_selector/resolver/session"
+
+module ActiveRecord
+  module Middleware
+    class DatabaseSelector
+      # The Resolver class is used by the DatabaseSelector middleware to
+      # determine which database the request should use.
+      #
+      # To change the behavior of the Resolver class in your application,
+      # create a custom resolver class that inherts from
+      # DatabaseSelector::Resolver and implements the methods that need to
+      # be changed.
+      #
+      # By default the Resolver class will send read traffic to the replica
+      # if it's been 2 seconds since the last write.
+      class Resolver # :nodoc:
+        SEND_TO_REPLICA_DELAY = 2.seconds
+
+        def self.call(resolver)
+          new(resolver)
+        end
+
+        def initialize(resolver)
+          @resolver = resolver
+          @instrumenter = ActiveSupport::Notifications.instrumenter
+        end
+
+        attr_reader :resolver, :instrumenter
+
+        def read(&blk)
+          if read_from_primary?
+            read_from_primary(&blk)
+          else
+            read_from_replica(&blk)
+          end
+        end
+
+        def write(&blk)
+          write_to_primary(&blk)
+        end
+
+        private
+
+          def read_from_primary(&blk)
+            ActiveRecord::Base.connection.while_preventing_writes do
+              ActiveRecord::Base.connected_to(role: :writing) do
+                instrumenter.instrument("database_selector.active_record.read_from_primary") do
+                  yield
+                end
+              end
+            end
+          end
+
+          def read_from_replica(&blk)
+            ActiveRecord::Base.connected_to(role: :reading) do
+              instrumenter.instrument("database_selector.active_record.read_from_replica") do
+                yield
+              end
+            end
+          end
+
+          def write_to_primary(&blk)
+            ActiveRecord::Base.connected_to(role: :writing) do
+              instrumenter.instrument("database_selector.active_record.wrote_to_primary") do
+                resolver.update_last_write_timestamp
+                yield
+              end
+            end
+          end
+
+          def read_from_primary?
+            !time_since_last_write_ok?
+          end
+
+          def send_to_replica_delay
+            (ActiveRecord::Base.database_selector && ActiveRecord::Base.database_selector[:delay]) ||
+              SEND_TO_REPLICA_DELAY
+          end
+
+          def time_since_last_write_ok?
+            Time.now - resolver.last_write_timestamp >= send_to_replica_delay
+          end
+      end
+    end
+  end
+end
diff --git a/activerecord/lib/active_record/middleware/database_selector/resolver/session.rb b/activerecord/lib/active_record/middleware/database_selector/resolver/session.rb
new file mode 100644
index 0000000000..33e0af5ee4
--- /dev/null
+++ b/activerecord/lib/active_record/middleware/database_selector/resolver/session.rb
@@ -0,0 +1,45 @@
+# frozen_string_literal: true
+
+module ActiveRecord
+  module Middleware
+    class DatabaseSelector
+      class Resolver
+        # The session class is used by the DatabaseSelector::Resolver to save
+        # timestamps of the last write in the session.
+        #
+        # The last_write is used to determine whether it's safe to read
+        # from the replica or the request needs to be sent to the primary.
+        class Session # :nodoc:
+          def self.build(request)
+            new(request.session)
+          end
+
+          # Converts time to a timestamp that represents milliseconds since
+          # epoch.
+          def self.convert_time_to_timestamp(time)
+            time.to_i * 1000 + time.usec / 1000
+          end
+
+          # Converts milliseconds since epoch timestamp into a time object.
+          def self.convert_timestamp_to_time(timestamp)
+            timestamp ? Time.at(timestamp / 1000, (timestamp % 1000) * 1000) : Time.at(0)
+          end
+
+          def initialize(session)
+            @session = session
+          end
+
+          attr_reader :session
+
+          def last_write_timestamp
+            self.class.convert_timestamp_to_time(session[:last_write])
+          end
+
+          def update_last_write_timestamp
+            session[:last_write] = self.class.convert_time_to_timestamp(Time.now)
+          end
+        end
+      end
+    end
+  end
+end
diff --git a/activerecord/lib/active_record/railtie.rb b/activerecord/lib/active_record/railtie.rb
index 6346a95d57..a981fa97d9 100644
--- a/activerecord/lib/active_record/railtie.rb
+++ b/activerecord/lib/active_record/railtie.rb
@@ -88,6 +88,14 @@ module ActiveRecord
       end
     end
 
+    initializer "active_record.database_selector" do
+      if config.active_record.database_selector
+        resolver = config.active_record.delete(:database_resolver)
+        operations = config.active_record.delete(:database_operations)
+        config.app_middleware.use ActiveRecord::Middleware::DatabaseSelector, resolver, operations
+      end
+    end
+
     initializer "Check for cache versioning support" do
       config.after_initialize do |app|
         ActiveSupport.on_load(:active_record) do
diff --git a/activerecord/test/cases/database_selector_test.rb b/activerecord/test/cases/database_selector_test.rb
new file mode 100644
index 0000000000..f961fa754b
--- /dev/null
+++ b/activerecord/test/cases/database_selector_test.rb
@@ -0,0 +1,77 @@
+# frozen_string_literal: true
+
+require "cases/helper"
+require "models/person"
+require "action_dispatch"
+
+module ActiveRecord
+  class DatabaseSelectorTest < ActiveRecord::TestCase
+    setup do
+      @session_store = {}
+      @session = ActiveRecord::Middleware::DatabaseSelector::Resolver::Session.new(@session_store)
+    end
+
+    def test_empty_session
+      assert_equal Time.at(0), @session.last_write_timestamp
+    end
+
+    def test_writing_the_session_timestamps
+      assert @session.update_last_write_timestamp
+
+      session2 = ActiveRecord::Middleware::DatabaseSelector::Resolver::Session.new(@session_store)
+      assert_equal @session.last_write_timestamp, session2.last_write_timestamp
+    end
+
+    def test_writing_session_time_changes
+      assert @session.update_last_write_timestamp
+
+      before = @session.last_write_timestamp
+      sleep(0.1)
+
+      assert @session.update_last_write_timestamp
+      assert_not_equal before, @session.last_write_timestamp
+    end
+
+    def test_read_from_replicas
+      @session_store[:last_write] = ActiveRecord::Middleware::DatabaseSelector::Resolver::Session.convert_time_to_timestamp(Time.now - 5.seconds)
+
+      resolver = ActiveRecord::Middleware::DatabaseSelector::Resolver.new(@session)
+
+      called = false
+      resolver.read do
+        called = true
+        assert ActiveRecord::Base.connected_to?(role: :reading)
+      end
+      assert called
+    end
+
+    def test_read_from_primary
+      @session_store[:last_write] = ActiveRecord::Middleware::DatabaseSelector::Resolver::Session.convert_time_to_timestamp(Time.now)
+
+      resolver = ActiveRecord::Middleware::DatabaseSelector::Resolver.new(@session)
+
+      called = false
+      resolver.read do
+        called = true
+        assert ActiveRecord::Base.connected_to?(role: :writing)
+      end
+      assert called
+    end
+
+    def test_the_middleware_chooses_writing_role_with_POST_request
+      middleware = ActiveRecord::Middleware::DatabaseSelector.new(lambda { |env|
+        assert ActiveRecord::Base.connected_to?(role: :writing)
+        [200, {}, ["body"]]
+      })
+      assert_equal [200, {}, ["body"]], middleware.call("REQUEST_METHOD" => "POST")
+    end
+
+    def test_the_middleware_chooses_reading_role_with_GET_request
+      middleware = ActiveRecord::Middleware::DatabaseSelector.new(lambda { |env|
+        assert ActiveRecord::Base.connected_to?(role: :reading)
+        [200, {}, ["body"]]
+      })
+      assert_equal [200, {}, ["body"]], middleware.call("REQUEST_METHOD" => "GET")
+    end
+  end
+end
diff --git a/railties/lib/rails/generators/rails/app/templates/config/environments/production.rb.tt b/railties/lib/rails/generators/rails/app/templates/config/environments/production.rb.tt
index 08befd9196..94f7dd0c79 100644
--- a/railties/lib/rails/generators/rails/app/templates/config/environments/production.rb.tt
+++ b/railties/lib/rails/generators/rails/app/templates/config/environments/production.rb.tt
@@ -98,4 +98,24 @@ Rails.application.configure do
   # Do not dump schema after migrations.
   config.active_record.dump_schema_after_migration = false
   <%- end -%>
+
+  # Inserts middleware to perform automatic connection switching.
+  # The `database_selector` hash is used to pass options to the DatabaseSelector
+  # middleware. The `delay` is used to determine how long to wait after a write
+  # to send a subsequent read to the primary.
+  #
+  # The `database_resolver` class is used by the middleware to determine which
+  # database is appropriate to use based on the time delay.
+  #
+  # The `database_operations` class is used by the middleware to set timestamps
+  # for the last write to the primary. The resolver uses the operations class
+  # timestamps to determine how long to wait before reading from the replica.
+  #
+  # By default Rails will store a last write timestamp in the session. The
+  # DatabaseSelector middleware is designed as such you can define your own
+  # strategy for connection switching and pass that into the middleware through
+  # these configuration options.
+  # config.active_record.database_selector = { delay: 2.seconds }
+  # config.active_record.database_resolver = ActiveRecord::Middleware::DatabaseSelector::Resolver
+  # config.active_record.database_operations = ActiveRecord::Middleware::DatabaseSelector::Resolver::Session
 end