Add optional compression to mariabackup

As database backups can grow substantially in size, compressing backups
helps to preserve disk space.
While the mariabackup utility offers no compression by itself, we can
stream the backup into a compression tool to create an archive [1].
The xtrabackup_checkpoints file, which contains metadata on a backup,
gets stored alongside the archive, allowing to create incremental
backups from non-compressed backups and vice-versa [2].
One thing to note, is that compressed backups cannot be prepared in
advance, this step must be manually carried out by the user.
Backup compression is disabled by default and different compressors
can be chosen (zstd, xz, ...), with gzip being the default.

[1] https://mariadb.com/kb/en/using-encryption-and-compression-tools-with-mariabackup/
[2] https://mariadb.com/kb/en/incremental-backup-and-restore-with-mariabackup/#combining-with-stream-output

Depends-On: https://review.opendev.org/c/openstack/openstack-ansible/+/888437

Change-Id: I28c6a0e0b41d4d29c3e79e601de45ea373dee4fb
Signed-off-by: Simon Hensel <simon.hensel@inovex.de>
(cherry picked from commit 60009ed7cebe9c082592fd564b1577068ef94b6c)
(cherry picked from commit 41801ab04d3c64d61b881d410691e05e0312114d)

defaults/main.yml

@@ -319,6 +319,8 @@ galera_mariadb_backups_user: galera_mariadb_backup
 galera_mariadb_backups_suffix: "{{ inventory_hostname }}"
 galera_mariadb_backups_cnf_file: "/etc/mysql/mariabackup.cnf"
 galera_mariadb_backups_nodes: ["{{ galera_cluster_members[0] }}"]
+galera_mariadb_backups_compress: False
+galera_mariadb_backups_compressor: gzip
 
 galera_mariadb_encryption_enabled: false
 galera_mariadb_encryption_plugin: "file_key_management"

releasenotes/notes/mariabackup-compression-337b04c68f370c1d.yaml

@@ -0,0 +1,28 @@
+---
+features:
+  - |
+    Adds optional compression for backups created with mariabackup. Adds two
+    new CLI parameters to the mariabackup script that are used to enable
+    compression and to choose a compression tool.
+
+    * ``--compress=True|False``
+    * ``--compressor=<compressor>``
+
+    Also introduces new Ansible variables that control the above mentioned
+    parameters.
+
+    * ``galera_mariadb_backups_compress``
+    * ``galera_mariadb_backups_compressor``
+
+    Each backup archive is stored in a dedicated directory, alongside the
+    backup metadata.
+upgrade:
+  - |
+    Backup compression is disabled by default, so no changes need to be made
+    for existing deployments. Should compression be desired, set
+    ``galera_mariadb_backups_compress`` to ``True``. Choose a compression tool
+    with ``galera_mariadb_backups_compressor``, default is ``gzip``.
+others:
+  - |
+    Compressed backups cannot be prepared in advance, this step must be
+    manually carried out by the user before importing it into MariaDB.

tasks/galera_server_backups.yml

@@ -39,6 +39,7 @@
           - /usr/bin/python3 {{ galera_mariadb_backups_path }}/mariabackup_script.py {{ galera_mariadb_backups_path }}
             --full-backup --copies={{ galera_mariadb_backups_full_copies }} --suffix={{ galera_mariadb_backups_suffix }}
             --defaults-file={{ galera_mariadb_backups_cnf_file }}
+            --compress={{ galera_mariadb_backups_compress }} --compressor={{ galera_mariadb_backups_compressor }}
         environment:
           UMASK: '0640'
           UMASK_DIR: '0750'
@@ -66,6 +67,7 @@
           - /usr/bin/python3 {{ galera_mariadb_backups_path }}/mariabackup_script.py {{ galera_mariadb_backups_path }}
             --increment --copies={{ galera_mariadb_backups_full_copies }} --suffix={{ galera_mariadb_backups_suffix }}
             --defaults-file={{ galera_mariadb_backups_cnf_file }}
+            --compress={{ galera_mariadb_backups_compress }} --compressor={{ galera_mariadb_backups_compressor }}
         environment:
           UMASK: '0640'
           UMASK_DIR: '0750'

templates/mariabackup_script.py.j2

@@ -1,11 +1,10 @@
 #!/usr/bin/python3
 # {{ ansible_managed }}
-from subprocess import Popen, PIPE
+from subprocess import Popen, PIPE, check_output, run
 from argparse import ArgumentParser
 from shutil import rmtree
 from time import strftime, mktime, sleep
 from datetime import datetime, timedelta
-import socket
 import os
 
 def get_opts():
@@ -35,6 +34,21 @@ def get_opts():
         default=False,
         help="Flag to make incremental backup, based on the latest backup",
         )
+    parser.add_argument(
+        "--compress",
+        dest="compress_flag",
+        default=False,
+        type=eval,
+        choices=[True, False],
+        help="Flag to compress created backups",
+        )
+    parser.add_argument(
+        "--compressor",
+        dest="compressor",
+        default="gzip",
+        type=str,
+        help="The compressor to use when compressing backups (default: gzip)",
+        )
     parser.add_argument(
         "-c",
         "--copies",
@@ -102,12 +116,26 @@ def check_backups(dest, warning, critical, full_backup_filename):
         raise SystemExit(0)
 
 
-def create_full_backup(dest, curtime, full_backup_filename, extra_mariabackup_args):
+def create_full_backup(dest, curtime, full_backup_filename, extra_mariabackup_args, compress, compressor):
     check_lock_file()
     get_lock_file()
     try:
-        #Creating full backup
         err = open(os.path.normpath(dest+"/backup.log"), "w")
+        if compress:
+            #Creating compressed full backup
+            os.makedirs(dest+"/"+full_backup_filename+curtime, exist_ok=True)
+            mariabackup_run = Popen(
+            ["/usr/bin/mariabackup"] + extra_mariabackup_args + ["--backup", "--stream=xbstream", "--extra-lsndir="+os.path.normpath(dest+"/"+full_backup_filename+curtime)], stdout=PIPE, stderr=err
+            )
+            compressed_backup = open(os.path.normpath(dest+"/"+full_backup_filename+curtime+"/"+full_backup_filename+curtime), "wb")
+            run([compressor], stdin=mariabackup_run.stdout, stdout=compressed_backup)
+            mariabackup_run.wait()
+            mariabackup_res = mariabackup_run.communicate()
+            if mariabackup_run.returncode:
+                print(mariabackup_res[1])
+            compressed_backup.close()
+        else:
+            #Creating full backup
             mariabackup_run = Popen(
             ["/usr/bin/mariabackup"] + extra_mariabackup_args + ["--backup", "--target-dir="+os.path.normpath(dest+"/"+full_backup_filename+curtime)], stdout=None, stderr=err
             )
@@ -115,7 +143,6 @@ def create_full_backup(dest, curtime, full_backup_filename, extra_mariabackup_ar
             mariabackup_res = mariabackup_run.communicate()
             if mariabackup_run.returncode:
                 print(mariabackup_res[1])
-        err.close()
             #Preparing full backup
             err_p = open(os.path.normpath(dest+"/prepare.log"), "w")
             mariabackup_prep = Popen(
@@ -126,6 +153,7 @@ def create_full_backup(dest, curtime, full_backup_filename, extra_mariabackup_ar
             if mariabackup_prep.returncode:
                 print(mariabackup_prep_res[1])
             err_p.close()
+        err.close()
     except OSError:
         print("Please, check that Mariabackup is installed")
     except Exception as e:
@@ -134,7 +162,7 @@ def create_full_backup(dest, curtime, full_backup_filename, extra_mariabackup_ar
         os.unlink("/var/run/mariabackup-galera/db_backup.pid")
 
 
-def create_increment_backup(dest, curtime, increment_backup_filename, extra_mariabackup_args):
+def create_increment_backup(dest, curtime, increment_backup_filename, extra_mariabackup_args, compress, compressor):
     check_lock_file()
     get_lock_file()
     try:
@@ -145,6 +173,20 @@ def create_increment_backup(dest, curtime, increment_backup_filename, extra_mari
         raise SystemExit(1)
     try:
         err = open(os.path.normpath(dest+"/increment.err"), "w")
+        if compress:
+            #Creating compressed incremental backup
+            os.makedirs(dest+"/"+increment_backup_filename+curtime, exist_ok=True)
+            mariabackup_run = Popen(
+            ["/usr/bin/mariabackup"] + extra_mariabackup_args + ["--backup", "--stream=xbstream", "--incremental-basedir="+basedir, "--extra-lsndir="+os.path.normpath(dest+"/"+increment_backup_filename+curtime)], stdout=PIPE, stderr=err
+            )
+            compressed_backup = open(os.path.normpath(dest+"/"+increment_backup_filename+curtime+"/"+increment_backup_filename+curtime), "wb")
+            run([compressor], stdin=mariabackup_run.stdout, stdout=compressed_backup)
+            mariabackup_run.wait()
+            mariabackup_res = mariabackup_run.communicate()
+            if mariabackup_run.returncode:
+                print(mariabackup_res[1])
+            compressed_backup.close()
+        else:
             #Creating incremental backup
             mariabackup_run = Popen(
             ["/usr/bin/mariabackup"] + extra_mariabackup_args + ["--backup", "--target-dir="+os.path.normpath(dest+"/"+increment_backup_filename+curtime), "--incremental-basedir="+basedir], stdout=None, stderr=err
@@ -227,11 +269,11 @@ def main():
     if opts.fullbackup_flag and opts.increment_flag:
         raise NameError("Only one flag can be specified per operation")
     elif opts.fullbackup_flag:
-        create_full_backup(opts.destdir, curtime, full_backup_filename, extra_mariabackup_args)
+        create_full_backup(opts.destdir, curtime, full_backup_filename, extra_mariabackup_args, opts.compress_flag, opts.compressor)
         rotate_backups(opts.destdir, opts.copies_flag, full_backup_filename, increment_backup_filename)
         raise SystemExit()
     elif opts.increment_flag:
-        create_increment_backup(opts.destdir, curtime, increment_backup_filename, extra_mariabackup_args)
+        create_increment_backup(opts.destdir, curtime, increment_backup_filename, extra_mariabackup_args, opts.compress_flag, opts.compressor)
         raise SystemExit()
     elif opts.check_flag:
         pass