pg_easy_replicate 0.2.2 → 0.2.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: efcbf369a4410abd783ea1dba49ead97fa471705842df4a35d28864349b1c70c
-  data.tar.gz: 676d97aa0c551dd0f9d58c3bccb229951bcb2dfc34653995375c359718bc1d7f
+  metadata.gz: fa012c1a56df04d2aad4d61e901a7affb409c24480d8b93d1b2806a08963c93e
+  data.tar.gz: 04ac8a97564f1d179f46f83f16e1bac495b19c6c10fa3af6a8f94ec6252dec3b
 SHA512:
-  metadata.gz: 774ef530f4be4b409fdf2d4956a44deb09aebf59c8ef480074d426ca4c72006673c7a6915d860e61846fb00df8e14fa9534e920f5802873ed727e37564197b25
-  data.tar.gz: 50055941c3a83351b22ceaeb539b807a7cec5e3130732944c63e8a5440a7707a273a546681b1d581d4f79d9fba616998fc48cffc009e401bfc570e76e27064f0
+  metadata.gz: f3accba4733b9eaeb5d1acde1f299a967f487f5b6dee20a9bab0ecc31f0a8f4622cbfef5d449fd05bcf1d0a4c9b396796ad3b2663bb078162bfd7f878fd1054a
+  data.tar.gz: 16961c9f095ca3491e1231fbd5b2b934362141bbddca12b13988b84656f5e89d5fc72a759085a9d5105722e413869eb12c0d12feaacd1c8938149012d2548363

data/CHANGELOG.md

@@ -1,4 +1,20 @@
-## [0.2.1] - 2023-12-29
+## [0.2.3] - 2024-01-21
+
+- Fix tables check in config_check - #93
+- add option to skip vacuum analyzing on switchover - #92
+- Disable statement timeout and reset it before/after vacuum+analyze - #94
+- Add spec for skip_vacuum_analyze - #95
+
+Highlights
+
+- You can now skip vacuum and analyze by passing `--skip-vacuum-analyze` to `switchover`. Thanks to @honzasterba
+- Vacuum and Analyze won't run into timeouts. Thanks to the report from @TrueCarry
+
+## [0.2.2] - 2024-01-21
+
+- Extend config check to assert for REPLICA IDENTITY on tables and drop index bug - #88
+
+## [0.2.1] - 2024-01-20
 
 - Don't attempt to drop and recreate unique indices - #88
 - Dependency updates

data/Gemfile.lock

@@ -1,19 +1,19 @@
 PATH
   remote: .
   specs:
-    pg_easy_replicate (0.2.2)
+    pg_easy_replicate (0.2.4)
       ougai (~> 2.0.0)
       pg (~> 1.5.3)
-      sequel (>= 5.69, < 5.77)
+      sequel (>= 5.69, < 5.78)
       thor (>= 1.2.2, < 1.4.0)
 
 GEM
   remote: https://rubygems.org/
   specs:
     ast (2.4.2)
-    bigdecimal (3.1.5)
+    bigdecimal (3.1.6)
     coderay (1.1.3)
-    diff-lcs (1.5.0)
+    diff-lcs (1.5.1)
     haml (6.1.1)
       temple (>= 0.8.2)
       thor
@@ -39,19 +39,19 @@ GEM
     rbs (3.1.0)
     regexp_parser (2.9.0)
     rexml (3.2.6)
-    rspec (3.12.0)
-      rspec-core (~> 3.12.0)
-      rspec-expectations (~> 3.12.0)
-      rspec-mocks (~> 3.12.0)
-    rspec-core (3.12.2)
-      rspec-support (~> 3.12.0)
-    rspec-expectations (3.12.3)
+    rspec (3.13.0)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.0)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.0)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.12.0)
-    rspec-mocks (3.12.5)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.0)
       diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.12.0)
-    rspec-support (3.12.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.0)
     rubocop (1.60.1)
       json (~> 2.3)
       language_server-protocol (>= 3.17.0)
@@ -81,7 +81,7 @@ GEM
       rubocop-capybara (~> 2.17)
       rubocop-factory_bot (~> 2.22)
     ruby-progressbar (1.13.0)
-    sequel (5.76.0)
+    sequel (5.77.0)
       bigdecimal
     syntax_tree (6.2.0)
       prettier_print (>= 1.2.0)

data/README.md

@@ -4,7 +4,7 @@
 [![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?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 replicated, `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.
+`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 replicated, `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 a Blue/Green PostgreSQL database setup, load testing and other similar use cases.
 
 Battle tested in production at [Tines](https://www.tines.com/) 🚀
 
@@ -19,7 +19,7 @@ Battle tested in production at [Tines](https://www.tines.com/) 🚀
   - [Config check](#config-check)
   - [Bootstrap](#bootstrap)
   - [Bootstrap and Config Check with special user role in AWS or GCP](#bootstrap-and-config-check-with-special-user-role-in-aws-or-gcp)
-    - [Config Check](#config-check)
+    - [Config Check](#config-check-1)
     - [Bootstrap](#bootstrap-1)
   - [Start sync](#start-sync)
   - [Stats](#stats)
@@ -29,7 +29,7 @@ Battle tested in production at [Tines](https://www.tines.com/) 🚀
   - [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)
+  - [Adding internal user to `pg_hba` or pgBouncer `userlist`](#adding-internal-user-to-pg_hba-or-pgbouncer-userlist)
 - [Contributing](#contributing)
 
 ## Installation
@@ -61,6 +61,7 @@ https://hub.docker.com/r/shayonj/pg_easy_replicate
 - PostgreSQL 10 and later
 - Ruby 3.0 and later
 - Database users should have `SUPERUSER` permissions, or pass in a special user with privileges to create the needed role, schema, publication and subscription on both databases. More on `--special-user-role` section below.
+- See more on [FAQ](#faq) below
 
 ## Limits
 
@@ -75,6 +76,14 @@ $ export SOURCE_DB_URL="postgres://USERNAME:PASSWORD@localhost:5432/DATABASE_NAM
 $ export TARGET_DB_URL="postgres://USERNAME:PASSWORD@localhost:5433/DATABASE_NAME"
 ```
 
+**Optional**
+
+You can extend the default timeout by setting the following environment variable
+
+```bash
+$ export PG_EASY_REPLICATE_STATEMENT_TIMEOUT="10s" # default 5s
+```
+
 Any `pg_easy_replicate` command can be run the same way with the docker image as well. As long the container is running in an environment where it has access to both the databases. Example
 
 ```bash
@@ -256,9 +265,9 @@ Next, you can set up a program that watches the `stats` and waits until `switcho
 
 ## FAQ
 
-### Adding internal user to pgBouncer `userlist`
+### Adding internal user to `pg_hba` or pgBouncer `userlist`
 
-`pg_easy_replicate` creates a special user to orchestrate the replication. If you use pgBouncer, you may need to allow `pger_su_h1a4fb` as a user that can perform login by adding it to the `userlist`.
+`pg_easy_replicate` sets up a designated user for managing the replication process. In case you handle user permissions through `pg_hba`, it's necessary to modify this list to permit sessions from `pger_su_h1a4fb`. Similarly, with pgBouncer, you'll need to authorize `pger_su_h1a4fb` for login access by including it in the `userlist`.
 
 ## Contributing
 

data/lib/pg_easy_replicate/cli.rb

@@ -18,6 +18,7 @@ module PgEasyReplicate
                   desc: "Copy schema to the new database"
     method_option :tables,
                   aliases: "-t",
+                  default: "",
                   desc:
                     "Comma separated list of table names. Default: All tables"
     method_option :schema_name,
@@ -87,6 +88,7 @@ module PgEasyReplicate
                     "Name of the schema tables are in, only required if passing list of tables"
     method_option :tables,
                   aliases: "-t",
+                  default: "",
                   desc:
                     "Comma separated list of table names. Default: All tables"
     method_option :recreate_indices_post_copy,
@@ -117,8 +119,12 @@ module PgEasyReplicate
                   desc: "Name of the group previously provisioned"
     method_option :lag_delta_size,
                   aliases: "-l",
-                  desc:
-                    "The size of the lag to watch for before switchover. Default 200KB."
+                  desc: "The size of the lag to watch for before switchover. Default 200KB."
+    method_option :skip_vacuum_analyze,
+                  type: :boolean,
+                  default: false,
+                  aliases: "-s",
+                  desc: "Skip vacuum analyzing tables before switchover."
     # method_option :bi_directional,
     #               aliases: "-b",
     #               desc:
@@ -127,6 +133,7 @@ module PgEasyReplicate
       PgEasyReplicate::Orchestrate.switchover(
         group_name: options[:group_name],
         lag_delta_size: options[:lag_delta_size],
+        skip_vacuum_analyze: options[:skip_vacuum_analyze]
       )
     end
 

data/lib/pg_easy_replicate/orchestrate.rb

@@ -204,16 +204,19 @@ module PgEasyReplicate
         group_name:,
         source_conn_string: source_db_url,
         target_conn_string: target_db_url,
-        lag_delta_size: nil
+        lag_delta_size: nil,
+        skip_vacuum_analyze: false
       )
         group = Group.find(group_name)
         tables_list = group[:table_names].split(",")
 
-        run_vacuum_analyze(
-          conn_string: target_conn_string,
-          tables: tables_list,
-          schema: group[:schema_name],
-        )
+        unless skip_vacuum_analyze
+          run_vacuum_analyze(
+            conn_string: target_conn_string,
+            tables: tables_list,
+            schema: group[:schema_name],
+          )
+        end
 
         watch_lag(group_name: group_name, lag: lag_delta_size || DEFAULT_LAG)
 
@@ -238,11 +241,13 @@ module PgEasyReplicate
         )
         mark_switchover_complete(group_name)
         # Run vacuum analyze to refresh the planner post switchover
-        run_vacuum_analyze(
-          conn_string: target_conn_string,
-          tables: tables_list,
-          schema: group[:schema_name],
-        )
+        unless skip_vacuum_analyze
+          run_vacuum_analyze(
+            conn_string: target_conn_string,
+            tables: tables_list,
+            schema: group[:schema_name],
+          )
+        end
         drop_subscription(
           group_name: group_name,
           target_conn_string: target_conn_string,
@@ -358,11 +363,13 @@ module PgEasyReplicate
             schema: schema,
             table: t,
           )
+
           Query.run(
-            query: "VACUUM VERBOSE ANALYZE #{t}",
+            query: "VACUUM VERBOSE ANALYZE #{t};",
             connection_url: conn_string,
             schema: schema,
             transaction: false,
+            using_vacuum_analyze: true,
           )
         end
       rescue => e

data/lib/pg_easy_replicate/query.rb

@@ -10,20 +10,26 @@ module PgEasyReplicate
         connection_url:,
         user: internal_user_name,
         schema: nil,
-        transaction: true
+        transaction: true,
+        using_vacuum_analyze: false
       )
         conn =
           connect(connection_url: connection_url, schema: schema, user: user)
+        timeout ||= ENV["PG_EASY_REPLICATE_STATEMENT_TIMEOUT"] || "5s"
         if transaction
           r =
             conn.transaction do
               conn.run("SET search_path to #{quote_ident(schema)}") if schema
-              conn.run("SET statement_timeout to '5s'")
+              conn.run("SET statement_timeout to '#{timeout}'")
               conn.fetch(query).to_a
             end
         else
           conn.run("SET search_path to #{quote_ident(schema)}") if schema
-          conn.run("SET statement_timeout to '5s'")
+          if using_vacuum_analyze
+            conn.run("SET statement_timeout=0")
+          else
+            conn.run("SET statement_timeout to '5s'")
+          end
           r = conn.fetch(query).to_a
         end
         conn.disconnect

data/lib/pg_easy_replicate/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module PgEasyReplicate
-  VERSION = "0.2.2"
+  VERSION = "0.2.4"
 end

data/scripts/e2e-start.sh

@@ -10,7 +10,7 @@ export SOURCE_DB_URL="postgres://james-bond:james-bond123%407%21%273aaR@localhos
 export TARGET_DB_URL="postgres://james-bond:james-bond123%407%21%273aaR@localhost:5433/postgres-db"
 export PGPASSWORD='james-bond123@7!'"'"''"'"'3aaR'
 
-# Bootstrap and cleanup
+# Config check, Bootstrap and cleanup
 echo "===== Performing Bootstrap and cleanup"
 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 --recreate-indices-post-copy

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pg_easy_replicate
 version: !ruby/object:Gem::Version
-  version: 0.2.2
+  version: 0.2.4
 platform: ruby
 authors:
 - Shayon Mukherjee
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-01-21 00:00:00.000000000 Z
+date: 2024-02-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ougai
@@ -47,7 +47,7 @@ dependencies:
         version: '5.69'
     - - "<"
       - !ruby/object:Gem::Version
-        version: '5.77'
+        version: '5.78'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -57,7 +57,7 @@ dependencies:
         version: '5.69'
     - - "<"
       - !ruby/object:Gem::Version
-        version: '5.77'
+        version: '5.78'
 - !ruby/object:Gem::Dependency
   name: thor
   requirement: !ruby/object:Gem::Requirement