pg_easy_replicate 0.1.7 → 0.1.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8b855bf14bd72bcf4ace60b2f746139d76408d6a00e0ae7ec3fd2d0c276cf22b
-  data.tar.gz: 1eff23811d7e9d8608c241bcc7a67367c8de8271ea53d6960f57859aa5c186fd
+  metadata.gz: 73d97a0f8505fef3ac73849e6964d1204c72545eb52fb4059d2c1119ea62228d
+  data.tar.gz: 8ad93a08e70da1945e091110064a9b4be569c2a77328f9960cd7ce52c6becefa
 SHA512:
-  metadata.gz: a7de21167ee2027115972442b9aa859fba7954bdc2e04b8e27e92d6fbadd2e7c9eb92c700d01f69ba9fecd5b40fe5593b5d0467ba4b2766106a7951311401842
-  data.tar.gz: c38c45df66c9a4433b558a41f120f8c3304b5cbd9ea1072348df61397b7e51b38d1709b83c160917d69fbcf460e18dc9f9355ea7c96ae3d109ba40b4430ff06c
+  metadata.gz: 895ca04cdabbf15a082b1623890d55e650398f07eb144b2a0c8cf2877557a857926e24bfc336046afdd5097dbd5042d43d344e095338d6ffdb8f259797536c10
+  data.tar.gz: 41dd6428dd0f8c54de4d4b97931d573a0b2ae5fd4f5d61e2908d2e88e7fff0a97ed13c841a8fa2b924bacda0e8ae4c496d3f533d1398be7b15ffe0aa0ba6304a

data/CHANGELOG.md

@@ -1,13 +1,23 @@
-## [0.1.6] - 2023-06-22
+## [0.1.8] - 2023-07-23
+
+- Introduce --copy_schema via pg_dump - #35
+
+## [0.1.7] - 2023-06-26
+
+- Perform smoke test with retries in CI - #26
+- Default schema to `public` #29
+- Perform vacuum and analyze before and after switchover - #30
+
+## [0.1.6] - 2023-06-24
 
 - Bug fix: Support custom schema name
 - New smoke spec in CI
 
-## [0.1.5] - 2023-06-22
+## [0.1.5] - 2023-06-24
 
 - Fix bug in `stop_sync`
 
-## [0.1.4] - 2023-06-22
+## [0.1.4] - 2023-06-24
 
 - Drop lockbox dependency
 - Support password with special chars and test for url encoded URI

data/Dockerfile

@@ -2,4 +2,6 @@ FROM ruby:3.1.4
 
 ARG VERSION
 
+RUN apt-get update && apt-get install postgresql-client -y
+RUN pg_dump --version
 RUN gem install pg_easy_replicate -v $VERSION

data/Gemfile.lock

@@ -1,10 +1,10 @@
 PATH
   remote: .
   specs:
-    pg_easy_replicate (0.1.7)
+    pg_easy_replicate (0.1.8)
       ougai (~> 2.0.0)
       pg (~> 1.5.3)
-      sequel (~> 5.69.0)
+      sequel (>= 5.69, < 5.71)
       thor (~> 1.2.2)
 
 GEM
@@ -18,6 +18,7 @@ GEM
       thor
       tilt
     json (2.6.3)
+    language_server-protocol (3.17.0.3)
     method_source (1.0.0)
     oj (3.14.3)
     ougai (2.0.0)
@@ -50,8 +51,9 @@ GEM
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.12.0)
     rspec-support (3.12.0)
-    rubocop (1.52.1)
+    rubocop (1.54.2)
       json (~> 2.3)
+      language_server-protocol (>= 3.17.0)
       parallel (~> 1.10)
       parser (>= 3.2.2.3)
       rainbow (>= 2.2.2, < 4.0)
@@ -78,7 +80,7 @@ GEM
       rubocop-capybara (~> 2.17)
       rubocop-factory_bot (~> 2.22)
     ruby-progressbar (1.13.0)
-    sequel (5.69.0)
+    sequel (5.70.0)
     syntax_tree (6.1.1)
       prettier_print (>= 1.2.0)
     syntax_tree-haml (4.0.3)

data/README.md

@@ -2,7 +2,7 @@
 
 [![CI](https://github.com/shayonj/pg_easy_replicate/actions/workflows/ci.yaml/badge.svg?branch=main)](https://github.com/shayonj/pg_easy_replicate/actions/workflows/ci.yaml)
 [![Smoke spec](https://github.com/shayonj/pg_easy_replicate/actions/workflows/smoke.yaml/badge.svg?branch=main)](https://github.com/shayonj/pg_easy_replicate/actions/workflows/ci.yaml)
-[![Gem Version](https://badge.fury.io/rb/pg_easy_replicate.svg?1)](https://badge.fury.io/rb/pg_easy_replicate)
+[![Gem Version](https://badge.fury.io/rb/pg_easy_replicate.svg?2)](https://badge.fury.io/rb/pg_easy_replicate)
 
 `pg_easy_replicate` is a CLI orchestrator tool that simplifies the process of setting up [logical replication](https://www.postgresql.org/docs/current/logical-replication.html) between two PostgreSQL databases. `pg_easy_replicate` also supports switchover. After the source (primary database) is fully replicating, `pg_easy_replicate` puts it into read-only mode and via logical replication flushes all data to the new target database. This ensures zero data loss and minimal downtime for the application. This method can be useful for performing minimal downtime (up to <1min, depending) major version upgrades between two PostgreSQL databases, load testing with blue/green database setup and other similar use cases.
 
@@ -26,6 +26,8 @@ Battle tested in production at [Tines](https://www.tines.com/) 🚀
 - [Switchover strategies with minimal downtime](#switchover-strategies-with-minimal-downtime)
   - [Rolling restart strategy](#rolling-restart-strategy)
   - [DNS Failover strategy](#dns-failover-strategy)
+- [FAQ](#faq)
+  - [Adding internal user to pgBouncer `userlist`](#adding-internal-user-to-pgbouncer-userlist)
 - [Contributing](#contributing)
 
 ## Installation
@@ -57,7 +59,6 @@ https://hub.docker.com/r/shayonj/pg_easy_replicate
 - PostgreSQL 10 and later
 - Ruby 2.7 and later
 - Database user should have permissions for `SUPERUSER` or pass in the special user role that has the privileges to create role, schema, publication and subscription on both databases. More on `--special-user-role` section below.
-- Both databases should have the same schema
 
 ## Limits
 
@@ -115,7 +116,7 @@ $ pg_easy_replicate config_check
 Every sync will need to be bootstrapped before you can set up the sync between two databases. Bootstrap creates a new super user to perform the orchestration required during the rest of the process. It also creates some internal metadata tables for record keeping.
 
 ```bash
-$ pg_easy_replicate bootstrap --group-name database-cluster-1
+$ pg_easy_replicate bootstrap --group-name database-cluster-1 --copy-schema
 
 {"name":"pg_easy_replicate","hostname":"PKHXQVK6DW","pid":21485,"level":30,"time":"2023-06-19T15:51:11.015-04:00","v":0,"msg":"Setting up schema","version":"0.1.0"}
 ...
@@ -132,7 +133,7 @@ For AWS the special user role is `rds_superuser`, and for GCP it is `cloudsqlsup
 #### Config Check
 
 ```bash
-$ pg_easy_replicate config_check --special-user-role="rds_superuser"
+$ pg_easy_replicate config_check --special-user-role="rds_superuser" --copy-schema
 
 ✅ Config is looking good.
 ```
@@ -140,7 +141,7 @@ $ pg_easy_replicate config_check --special-user-role="rds_superuser"
 #### Bootstrap
 
 ```bash
-$ pg_easy_replicate bootstrap --group-name database-cluster-1 --special-user-role="rds_superuser"
+$ pg_easy_replicate bootstrap --group-name database-cluster-1 --special-user-role="rds_superuser" --copy-schema
 
 {"name":"pg_easy_replicate","hostname":"PKHXQVK6DW","pid":21485,"level":30,"time":"2023-06-19T15:51:11.015-04:00","v":0,"msg":"Setting up schema","version":"0.1.0"}
 ...
@@ -217,12 +218,12 @@ By default all tables are added for replication but you can create multiple grou
 
 ```bash
 
-$ pg_easy_replicate bootstrap --group-name database-cluster-1
+$ pg_easy_replicate bootstrap --group-name database-cluster-1 --copy-schema
 $ pg_easy_replicate start_sync --group-name database-cluster-1 --schema-name public --tables "users, posts, events"
 
 ...
 
-$ pg_easy_replicate bootstrap --group-name database-cluster-2
+$ pg_easy_replicate bootstrap --group-name database-cluster-2 --copy-schema
 $ pg_easy_replicate start_sync --group-name database-cluster-2 --schema-name public --tables "comments, views"
 
 ...
@@ -247,6 +248,12 @@ In this strategy, you have a weighted based DNS system (example [AWS Route53 wei
 
 Next, you can set up a program that watches the `stats` and waits until `switchover_completed_at` is reporting as `true`. Once that happens it updates the weight in the DNS weighted group where 100% of the requests now go to the new/target database. Note: Keeping a low `ttl` is recommended.
 
+## FAQ
+
+### Adding internal user to pgBouncer `userlist`
+
+`pg_easy_replicate` creates a special user to orchestrate the replication. If you us pgBouncer, you may need to allow `pger_su_h1a4fb` as a user that can perform login by adding it to the `userlist`.
+
 ## Contributing
 
 PRs most welcome. You can get started locally by

data/lib/pg_easy_replicate/cli.rb

@@ -12,9 +12,14 @@ module PgEasyReplicate
                   aliases: "-s",
                   desc:
                     "Name of the role that has superuser permissions. Usually useful for AWS (rds_superuser) or GCP (cloudsqlsuperuser)."
+    method_option :copy_schema,
+                  aliases: "-c",
+                  boolean: true,
+                  desc: "Copy schema to the new database"
     def config_check
       PgEasyReplicate.assert_config(
         special_user_role: options[:special_user_role],
+        copy_schema: options[:copy_schema],
       )
 
       puts "✅ Config is looking good."
@@ -28,6 +33,10 @@ module PgEasyReplicate
                   aliases: "-s",
                   desc:
                     "Name of the role that has superuser permissions. Usually useful with AWS (rds_superuser) or GCP (cloudsqlsuperuser)."
+    method_option :copy_schema,
+                  aliases: "-c",
+                  boolean: true,
+                  desc: "Copy schema to the new database"
     desc "bootstrap",
          "Sets up temporary tables for information required during runtime"
     def bootstrap

data/lib/pg_easy_replicate/helper.rb

@@ -36,7 +36,7 @@ module PgEasyReplicate
 
     def underscore(str)
       str
-        .gsub(/::/, "/")
+        .gsub("::", "/")
         .gsub(/([A-Z]+)([A-Z][a-z])/, '\1_\2')
         .gsub(/([a-z\d])([A-Z])/, '\1_\2')
         .tr("-", "_")

data/lib/pg_easy_replicate/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module PgEasyReplicate
-  VERSION = "0.1.7"
+  VERSION = "0.1.8"
 end

data/lib/pg_easy_replicate.rb

@@ -4,6 +4,7 @@ require "json"
 require "ougai"
 require "pg"
 require "sequel"
+require "open3"
 
 require "pg_easy_replicate/helper"
 require "pg_easy_replicate/version"
@@ -15,16 +16,21 @@ require "pg_easy_replicate/cli"
 
 Sequel.default_timezone = :utc
 module PgEasyReplicate
+  SCHEMA_FILE_LOCATION = "/tmp/pger_schema.sql"
+
   class Error < StandardError
   end
 
   extend Helper
 
   class << self
-    def config(special_user_role: nil)
+    def config(special_user_role: nil, copy_schema: false)
       abort_with("SOURCE_DB_URL is missing") if source_db_url.nil?
       abort_with("TARGET_DB_URL is missing") if target_db_url.nil?
 
+      system("which pg_dump")
+      pg_dump_exists = $CHILD_STATUS.success?
+
       @config ||=
         begin
           q =
@@ -47,14 +53,20 @@ module PgEasyReplicate
                 connection_url: target_db_url,
                 user: db_user(target_db_url),
               ),
+            pg_dump_exists: pg_dump_exists,
           }
         rescue => e
           abort_with("Unable to check config: #{e.message}")
         end
     end
 
-    def assert_config(special_user_role: nil)
-      config_hash = config(special_user_role: special_user_role)
+    def assert_config(special_user_role: nil, copy_schema: false)
+      config_hash =
+        config(special_user_role: special_user_role, copy_schema: copy_schema)
+
+      if copy_schema && !config_hash.dig(:pg_dump_exists)
+        abort_with("pg_dump must exist if copy_schema (-c) is passed")
+      end
 
       unless assert_wal_level_logical(config_hash.dig(:source_db))
         abort_with("WAL_LEVEL should be LOGICAL on source DB")
@@ -74,7 +86,15 @@ module PgEasyReplicate
 
     def bootstrap(options)
       logger.info("Setting up schema")
-      setup_schema
+      setup_internal_schema
+
+      if options[:copy_schema]
+        logger.info("Setting up schema on targer database")
+        copy_schema(
+          source_conn_string: source_db_url,
+          target_conn_string: target_db_url,
+        )
+      end
 
       logger.info("Setting up replication user on source database")
       create_user(
@@ -103,7 +123,7 @@ module PgEasyReplicate
 
       if options[:everything]
         logger.info("Dropping schema")
-        drop_schema
+        drop_internal_schema
       end
 
       if options[:everything] || options[:sync]
@@ -130,7 +150,7 @@ module PgEasyReplicate
       abort_with("Unable to cleanup: #{e.message}")
     end
 
-    def drop_schema
+    def drop_internal_schema
       Query.run(
         query: "DROP SCHEMA IF EXISTS #{internal_schema_name} CASCADE",
         connection_url: source_db_url,
@@ -141,7 +161,7 @@ module PgEasyReplicate
       raise "Unable to drop schema: #{e.message}"
     end
 
-    def setup_schema
+    def setup_internal_schema
       sql = <<~SQL
         create schema if not exists #{internal_schema_name};
         grant usage on schema #{internal_schema_name} to #{db_user(source_db_url)};
@@ -169,7 +189,39 @@ module PgEasyReplicate
         end
     end
 
-    private
+    def copy_schema(source_conn_string:, target_conn_string:)
+      export_schema(conn_string: source_conn_string)
+      import_schema(conn_string: target_conn_string)
+    end
+
+    def export_schema(conn_string:)
+      logger.info("Exporting schema to #{SCHEMA_FILE_LOCATION}")
+      _, stderr, status =
+        Open3.capture3(
+          "pg_dump",
+          conn_string,
+          "-f",
+          SCHEMA_FILE_LOCATION,
+          "--schema-only",
+        )
+
+      success = status.success?
+      raise stderr unless success
+    rescue => e
+      raise "Unable to export schema: #{e.message}"
+    end
+
+    def import_schema(conn_string:)
+      logger.info("Importing schema from #{SCHEMA_FILE_LOCATION}")
+
+      _, stderr, status =
+        Open3.capture3("psql", "-f", SCHEMA_FILE_LOCATION, conn_string)
+
+      success = status.success?
+      raise stderr unless success
+    rescue => e
+      raise "Unable to import schema: #{e.message}"
+    end
 
     def assert_wal_level_logical(db_config)
       db_config&.find do |r|

data/scripts/e2e-bootstrap.sh

@@ -12,8 +12,4 @@ export PGPASSWORD='jamesbond123@7!'"'"'3aaR'
 
 pgbench --initialize -s 5 --foreign-keys --host localhost -U jamesbond -d postgres
 
-pg_dump --schema-only --host localhost -U jamesbond -d postgres >schema.sql
-cat schema.sql | psql --host localhost -U jamesbond -d postgres -p 5433
-rm schema.sql
-
-bundle exec bin/pg_easy_replicate config_check
+bundle exec bin/pg_easy_replicate config_check --copy-schema

data/scripts/e2e-start.sh

@@ -12,7 +12,7 @@ export PGPASSWORD='jamesbond123@7!'"'"''"'"'3aaR'
 
 # Bootstrap and cleanup
 echo "===== Performing Bootstrap and cleanup"
-bundle exec bin/pg_easy_replicate bootstrap -g cluster-1
+bundle exec bin/pg_easy_replicate bootstrap -g cluster-1 --copy-schema
 bundle exec bin/pg_easy_replicate start_sync -g cluster-1 -s public
 bundle exec bin/pg_easy_replicate stats -g cluster-1
 bundle exec bin/pg_easy_replicate switchover -g cluster-1

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pg_easy_replicate
 version: !ruby/object:Gem::Version
-  version: 0.1.7
+  version: 0.1.8
 platform: ruby
 authors:
 - Shayon Mukherjee
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-06-27 00:00:00.000000000 Z
+date: 2023-07-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ougai
@@ -42,16 +42,22 @@ dependencies:
   name: sequel
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '5.69'
+    - - "<"
       - !ruby/object:Gem::Version
-        version: 5.69.0
+        version: '5.71'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '5.69'
+    - - "<"
       - !ruby/object:Gem::Version
-        version: 5.69.0
+        version: '5.71'
 - !ruby/object:Gem::Dependency
   name: thor
   requirement: !ruby/object:Gem::Requirement