1
0
mirror of https://github.com/garraflavatra/docker-volume-s3-backup.git synced 2025-05-17 13:14:38 +00:00

script cleanup, misc changes

- --blobs by default
- always drop and recreate schemas, specified by DROP_SCHEMAS
This commit is contained in:
Elliott Shugerman 2019-11-29 22:17:47 -07:00
parent 1ba61ed95a
commit e8ad6ceba4
11 changed files with 188 additions and 135 deletions

View File

@ -1,5 +1,5 @@
# Overview
This project provides Docker containers to backup/restore a PostgreSQL database to/from AWS S3 (or a compatible service like DigitalOcean Spaces). Both one-off and periodic/scheduled backups are supported.
# Introduction
This project provides Docker images to periodically backup a PostgreSQL database to AWS S3, and to restore from the backup as needed.
# Credit where due
This repository is a fork and re-structuring of schickling's [postgres-backup-s3](https://github.com/schickling/dockerfiles/tree/master/postgres-backup-s3) and [postgres-restore-s3](https://github.com/schickling/dockerfiles/tree/master/postgres-restore-s3).
@ -8,8 +8,16 @@ Fork goals:
- [x] dedicated repository
- [x] automated builds
- [x] support multiple PostgreSQL versions
- [ ] support encrypted (password-protected) backups
- [x] merge backup and restore images?
- [x] support encrypted (password-protected) backups
- [x] option to restore from specific backup by timestamp
Other changes:
- uses `pg_dump`'s `custom` format (see [docs](https://www.postgresql.org/docs/10/app-pgdump.html))
- backup blobs and all schemas by default
- recreate all database objects on restore
- some env vars renamed
- only scheduled backups supported, not ad-hoc
-------
@ -17,15 +25,16 @@ Fork goals:
## Backup
```yaml
postgres:
image: postgres
image: postgres:11
environment:
POSTGRES_USER: user
POSTGRES_PASSWORD: password
pgbackups3:
image: eeshugerman/postgres-backup-s3
image: eeshugerman/postgres-backup-s3:11
environment:
SCHEDULE: '@daily'
PASSPHRASE: passphrase
S3_REGION: region
S3_ACCESS_KEY_ID: key
S3_SECRET_ACCESS_KEY: secret
@ -34,17 +43,27 @@ pgbackups3:
POSTGRES_DATABASE: dbname
POSTGRES_USER: user
POSTGRES_PASSWORD: password
POSTGRES_EXTRA_OPTS: '--schema=public --blobs'
```
### Notes
#### Periodic backups
The `SCHEDULE` variable is determines backup frequency. It is optional -- without it, the backup will run once at start up. More information about the scheduling can be found [here](http://godoc.org/github.com/robfig/cron#hdr-Predefined_schedules).
#### Docker
Docker Compose is by no means required, you can use plain ol' Docker too -- just set the required env vars with the `-e` flag.
#### PostgreSQL version
Images are tagged by the major PostgreSQL version they support: `9`, `10`, `11`, or `12`.
#### Scheduling
The `SCHEDULE` variable is determines backup frequency. See go-cron schedules documentation [here](http://godoc.org/github.com/robfig/cron#hdr-Predefined_schedules).
#### Encrypted backups
If `PASSPHRASE` is provided, the backup will be encrypted using GPG.
## Restore
With the container running,
> WARNING: DATA LOSS! All database objects will be dropped and recreated.
### From latest backup (based on unix sort)
```sh
docker exec <container name> sh restore.sh
```
#### Notes
- If your bucket has more than a 1000 files the latest may not be restored, only one S3 `ls` command is used
- Your S3 prefix should only contain backups which you wish to restore - 'latest' is determined based on unix sort with no filtering
### From specific backup
```sh
docker exec <container name> sh restore.sh <timestamp>
```

2
render.py Normal file → Executable file
View File

@ -1,4 +1,4 @@
#!/bin/python3
#!/usr/bin/python3
VERSIONS = (
('9', '3.6'),

View File

@ -6,21 +6,21 @@ FROM alpine:3.8
ADD install.sh install.sh
RUN sh install.sh && rm install.sh
ENV POSTGRES_DATABASE **None**
ENV POSTGRES_HOST **None**
ENV POSTGRES_DATABASE ''
ENV POSTGRES_HOST ''
ENV POSTGRES_PORT 5432
ENV POSTGRES_USER **None**
ENV POSTGRES_PASSWORD **None**
ENV POSTGRES_EXTRA_OPTS ''
ENV S3_ACCESS_KEY_ID **None**
ENV S3_SECRET_ACCESS_KEY **None**
ENV S3_BUCKET **None**
ENV S3_REGION us-west-1
ENV POSTGRES_USER ''
ENV POSTGRES_PASSWORD ''
ENV PGDUMP_EXTRA_OPTS ''
ENV S3_ACCESS_KEY_ID ''
ENV S3_SECRET_ACCESS_KEY ''
ENV S3_BUCKET ''
ENV S3_REGION 'us-west-1'
ENV S3_PATH 'backup'
ENV S3_ENDPOINT **None**
ENV S3_S3V4 no
ENV SCHEDULE **None**
ENV DROP_PUBLIC no
ENV S3_ENDPOINT ''
ENV S3_S3V4 'no'
ENV SCHEDULE ''
ENV PASSPHRASE ''
ADD run.sh run.sh
ADD backup.sh backup.sh

View File

@ -6,21 +6,21 @@ FROM alpine:3.10
ADD install.sh install.sh
RUN sh install.sh && rm install.sh
ENV POSTGRES_DATABASE **None**
ENV POSTGRES_HOST **None**
ENV POSTGRES_DATABASE ''
ENV POSTGRES_HOST ''
ENV POSTGRES_PORT 5432
ENV POSTGRES_USER **None**
ENV POSTGRES_PASSWORD **None**
ENV POSTGRES_EXTRA_OPTS ''
ENV S3_ACCESS_KEY_ID **None**
ENV S3_SECRET_ACCESS_KEY **None**
ENV S3_BUCKET **None**
ENV S3_REGION us-west-1
ENV POSTGRES_USER ''
ENV POSTGRES_PASSWORD ''
ENV PGDUMP_EXTRA_OPTS ''
ENV S3_ACCESS_KEY_ID ''
ENV S3_SECRET_ACCESS_KEY ''
ENV S3_BUCKET ''
ENV S3_REGION 'us-west-1'
ENV S3_PATH 'backup'
ENV S3_ENDPOINT **None**
ENV S3_S3V4 no
ENV SCHEDULE **None**
ENV DROP_PUBLIC no
ENV S3_ENDPOINT ''
ENV S3_S3V4 'no'
ENV SCHEDULE ''
ENV PASSPHRASE ''
ADD run.sh run.sh
ADD backup.sh backup.sh

View File

@ -6,21 +6,21 @@ FROM alpine:edge
ADD install.sh install.sh
RUN sh install.sh && rm install.sh
ENV POSTGRES_DATABASE **None**
ENV POSTGRES_HOST **None**
ENV POSTGRES_DATABASE ''
ENV POSTGRES_HOST ''
ENV POSTGRES_PORT 5432
ENV POSTGRES_USER **None**
ENV POSTGRES_PASSWORD **None**
ENV POSTGRES_EXTRA_OPTS ''
ENV S3_ACCESS_KEY_ID **None**
ENV S3_SECRET_ACCESS_KEY **None**
ENV S3_BUCKET **None**
ENV S3_REGION us-west-1
ENV POSTGRES_USER ''
ENV POSTGRES_PASSWORD ''
ENV PGDUMP_EXTRA_OPTS ''
ENV S3_ACCESS_KEY_ID ''
ENV S3_SECRET_ACCESS_KEY ''
ENV S3_BUCKET ''
ENV S3_REGION 'us-west-1'
ENV S3_PATH 'backup'
ENV S3_ENDPOINT **None**
ENV S3_S3V4 no
ENV SCHEDULE **None**
ENV DROP_PUBLIC no
ENV S3_ENDPOINT ''
ENV S3_S3V4 'no'
ENV SCHEDULE ''
ENV PASSPHRASE ''
ADD run.sh run.sh
ADD backup.sh backup.sh

View File

@ -6,21 +6,21 @@ FROM alpine:3.6
ADD install.sh install.sh
RUN sh install.sh && rm install.sh
ENV POSTGRES_DATABASE **None**
ENV POSTGRES_HOST **None**
ENV POSTGRES_DATABASE ''
ENV POSTGRES_HOST ''
ENV POSTGRES_PORT 5432
ENV POSTGRES_USER **None**
ENV POSTGRES_PASSWORD **None**
ENV POSTGRES_EXTRA_OPTS ''
ENV S3_ACCESS_KEY_ID **None**
ENV S3_SECRET_ACCESS_KEY **None**
ENV S3_BUCKET **None**
ENV S3_REGION us-west-1
ENV POSTGRES_USER ''
ENV POSTGRES_PASSWORD ''
ENV PGDUMP_EXTRA_OPTS ''
ENV S3_ACCESS_KEY_ID ''
ENV S3_SECRET_ACCESS_KEY ''
ENV S3_BUCKET ''
ENV S3_REGION 'us-west-1'
ENV S3_PATH 'backup'
ENV S3_ENDPOINT **None**
ENV S3_S3V4 no
ENV SCHEDULE **None**
ENV DROP_PUBLIC no
ENV S3_ENDPOINT ''
ENV S3_S3V4 'no'
ENV SCHEDULE ''
ENV PASSPHRASE ''
ADD run.sh run.sh
ADD backup.sh backup.sh

View File

@ -1,30 +1,30 @@
#! /bin/sh
set -e
set -eu
set -o pipefail
if [ "${S3_ACCESS_KEY_ID}" = "**None**" ]; then
if [ -z "$S3_ACCESS_KEY_ID" ]; then
echo "You need to set the S3_ACCESS_KEY_ID environment variable."
exit 1
fi
if [ "${S3_SECRET_ACCESS_KEY}" = "**None**" ]; then
if [ -z "$S3_SECRET_ACCESS_KEY" ]; then
echo "You need to set the S3_SECRET_ACCESS_KEY environment variable."
exit 1
fi
if [ "${S3_BUCKET}" = "**None**" ]; then
if [ -z "$S3_BUCKET" ]; then
echo "You need to set the S3_BUCKET environment variable."
exit 1
fi
if [ "${POSTGRES_DATABASE}" = "**None**" ]; then
if [ -z "$POSTGRES_DATABASE" ]; then
echo "You need to set the POSTGRES_DATABASE environment variable."
exit 1
fi
if [ "${POSTGRES_HOST}" = "**None**" ]; then
if [ -n "${POSTGRES_PORT_5432_TCP_ADDR}" ]; then
if [ -z "$POSTGRES_HOST" ]; then
if [ -n "$POSTGRES_PORT_5432_TCP_ADDR" ]; then
POSTGRES_HOST=$POSTGRES_PORT_5432_TCP_ADDR
POSTGRES_PORT=$POSTGRES_PORT_5432_TCP_PORT
else
@ -33,36 +33,53 @@ if [ "${POSTGRES_HOST}" = "**None**" ]; then
fi
fi
if [ "${POSTGRES_USER}" = "**None**" ]; then
if [ -z "$POSTGRES_USER" ]; then
echo "You need to set the POSTGRES_USER environment variable."
exit 1
fi
if [ "${POSTGRES_PASSWORD}" = "**None**" ]; then
echo "You need to set the POSTGRES_PASSWORD environment variable or link to a container named POSTGRES."
if [ -z "$POSTGRES_PASSWORD" ]; then
echo "You need to set the POSTGRES_PASSWORD environment variable."
exit 1
fi
if [ "${S3_ENDPOINT}" == "**None**" ]; then
AWS_ARGS=""
if [ -z "$S3_ENDPOINT" ]; then
aws_args=""
else
AWS_ARGS="--endpoint-url ${S3_ENDPOINT}"
aws_args="--endpoint-url $S3_ENDPOINT"
fi
# env vars needed for aws tools
export AWS_ACCESS_KEY_ID=$S3_ACCESS_KEY_ID
export AWS_SECRET_ACCESS_KEY=$S3_SECRET_ACCESS_KEY
export AWS_DEFAULT_REGION=$S3_REGION
export PGPASSWORD=$POSTGRES_PASSWORD
POSTGRES_HOST_OPTS="-h $POSTGRES_HOST -p $POSTGRES_PORT -U $POSTGRES_USER $POSTGRES_EXTRA_OPTS"
echo "Creating dump of ${POSTGRES_DATABASE} database from ${POSTGRES_HOST}..."
echo "Creating backup of $POSTGRES_DATABASE database..."
pg_dump --format=custom \
-h $POSTGRES_HOST \
-p $POSTGRES_PORT \
-U $POSTGRES_USER \
-d $POSTGRES_DATABASE \
$PGDUMP_EXTRA_OPTS \
> db.dump
pg_dump $POSTGRES_HOST_OPTS $POSTGRES_DATABASE | gzip > dump.sql.gz
timestamp=$(date +"%Y-%m-%dT%H:%M:%S")
s3_uri_base="s3://${S3_BUCKET}/${S3_PREFIX}/${POSTGRES_DATABASE}_${timestamp}.dump"
echo "Uploading dump to $S3_BUCKET"
if [ -n "$PASSPHRASE" ]; then
echo "Encrypting backup..."
gpg --symmetric --batch --passphrase "$PASSPHRASE" db.dump
rm db.dump
local_file="db.dump.gpg"
s3_uri="${s3_uri_base}.gpg"
else
local_file="db.dump"
s3_uri="$s3_uri_base"
fi
cat dump.sql.gz | aws $AWS_ARGS s3 cp - s3://$S3_BUCKET/$S3_PREFIX/${POSTGRES_DATABASE}_$(date +"%Y-%m-%dT%H:%M:%SZ").sql.gz || exit 2
echo "Uploading backup to $S3_BUCKET..."
aws $aws_args s3 cp "$local_file" "$s3_uri"
rm "$local_file"
echo "SQL backup uploaded successfully"
echo "Backup complete."

View File

@ -1,13 +1,16 @@
#! /bin/sh
# exit if a command fails
set -e
set -o pipefail
apk update
# install pg_dump
apk add postgresql-client
# install gpg
apk add gnupg
# install s3 tools
apk add python py-pip
pip install awscli

View File

@ -1,30 +1,30 @@
#! /bin/sh
set -e
set -eu
set -o pipefail
if [ "${S3_ACCESS_KEY_ID}" = "**None**" ]; then
if [ -z "$S3_ACCESS_KEY_ID" ]; then
echo "You need to set the S3_ACCESS_KEY_ID environment variable."
exit 1
fi
if [ "${S3_SECRET_ACCESS_KEY}" = "**None**" ]; then
if [ -z "$S3_SECRET_ACCESS_KEY" ]; then
echo "You need to set the S3_SECRET_ACCESS_KEY environment variable."
exit 1
fi
if [ "${S3_BUCKET}" = "**None**" ]; then
if [ -z "$S3_BUCKET" ]; then
echo "You need to set the S3_BUCKET environment variable."
exit 1
fi
if [ "${POSTGRES_DATABASE}" = "**None**" ]; then
if [ -z "$POSTGRES_DATABASE" ]; then
echo "You need to set the POSTGRES_DATABASE environment variable."
exit 1
fi
if [ "${POSTGRES_HOST}" = "**None**" ]; then
if [ -n "${POSTGRES_PORT_5432_TCP_ADDR}" ]; then
if [ -z "$POSTGRES_HOST" ]; then
if [ -n "$POSTGRES_PORT_5432_TCP_ADDR" ]; then
POSTGRES_HOST=$POSTGRES_PORT_5432_TCP_ADDR
POSTGRES_PORT=$POSTGRES_PORT_5432_TCP_PORT
else
@ -33,49 +33,63 @@ if [ "${POSTGRES_HOST}" = "**None**" ]; then
fi
fi
if [ "${POSTGRES_USER}" = "**None**" ]; then
if [ -z "$POSTGRES_USER" ]; then
echo "You need to set the POSTGRES_USER environment variable."
exit 1
fi
if [ "${POSTGRES_PASSWORD}" = "**None**" ]; then
echo "You need to set the POSTGRES_PASSWORD environment variable or link to a container named POSTGRES."
if [ -z "$POSTGRES_PASSWORD" ]; then
echo "You need to set the POSTGRES_PASSWORD environment variable" \
"or link to a container named POSTGRES."
exit 1
fi
if [ "${S3_ENDPOINT}" == "**None**" ]; then
AWS_ARGS=""
if [ -z "$S3_ENDPOINT" ]; then
aws_args=""
else
AWS_ARGS="--endpoint-url ${S3_ENDPOINT}"
aws_args="--endpoint-url $S3_ENDPOINT"
fi
# env vars needed for aws tools
export AWS_ACCESS_KEY_ID=$S3_ACCESS_KEY_ID
export AWS_SECRET_ACCESS_KEY=$S3_SECRET_ACCESS_KEY
export AWS_DEFAULT_REGION=$S3_REGION
export PGPASSWORD=$POSTGRES_PASSWORD
POSTGRES_HOST_OPTS="-h $POSTGRES_HOST -p $POSTGRES_PORT -U $POSTGRES_USER"
echo "Finding latest backup"
s3_uri_base="s3://${S3_BUCKET}/${S3_PREFIX}"
LATEST_BACKUP=$(aws $AWS_ARGS s3 ls s3://$S3_BUCKET/$S3_PREFIX/ | sort | tail -n 1 | awk '{ print $4 }')
echo "Fetching ${LATEST_BACKUP} from S3"
aws $AWS_ARGS s3 cp s3://$S3_BUCKET/$S3_PREFIX/${LATEST_BACKUP} dump.sql.gz
gzip -d dump.sql.gz
if [ "${DROP_PUBLIC}" == "yes" ]; then
echo "Recreating the public schema"
psql $POSTGRES_HOST_OPTS -d $POSTGRES_DATABASE -c "drop schema public cascade; create schema public;"
if [ -z "$PASSPHRASE" ]; then
file_type=".dump"
else
file_type=".dump.gpg"
fi
echo "Restoring ${LATEST_BACKUP}"
if [ $# -eq 1 ]; then
timestamp="$1"
key_suffix="${POSTGRES_DATABASE}_${timestamp}${file_type}"
else
echo "Finding latest backup..."
key_suffix=$(
aws $aws_args s3 ls "${s3_uri_base}/" \
| sort \
| tail -n 1 \
| awk '{ print $4 }'
)
fi
psql $POSTGRES_HOST_OPTS -d $POSTGRES_DATABASE < dump.sql
echo "Fetching backup from S3..."
aws $aws_args s3 cp "${s3_uri_base}/${key_suffix}" "db${file_type}"
rm dump.sql
if [ -n "$PASSPHRASE" ]; then
echo "Decrypting backup..."
gpg --decrypt --batch --passphrase "$PASSPHRASE" db.dump.gpg > db.dump
rm db.dump.gpg
fi
echo "Restore complete"
conn_opts="-h $POSTGRES_HOST -p $POSTGRES_PORT -U $POSTGRES_USER -d $POSTGRES_DATABASE"
echo "Restoring from backup..."
pg_restore $conn_opts --single-transaction --clean db.dump
rm db.dump
echo "Restore complete."

View File

@ -1,13 +1,13 @@
#! /bin/sh
set -e
set -eu
if [ "${S3_S3V4}" = "yes" ]; then
if [ "$S3_S3V4" = "yes" ]; then
aws configure set default.s3.signature_version s3v4
fi
if [ "${SCHEDULE}" = "**None**" ]; then
sh backup.sh
if [ -z "$SCHEDULE" ]; then
echo "You need to set the SCHEDULE environment variable."
else
exec go-cron "$SCHEDULE" /bin/sh backup.sh
fi

View File

@ -3,21 +3,21 @@ FROM alpine:{alpine_version}
ADD install.sh install.sh
RUN sh install.sh && rm install.sh
ENV POSTGRES_DATABASE **None**
ENV POSTGRES_HOST **None**
ENV POSTGRES_DATABASE ''
ENV POSTGRES_HOST ''
ENV POSTGRES_PORT 5432
ENV POSTGRES_USER **None**
ENV POSTGRES_PASSWORD **None**
ENV POSTGRES_EXTRA_OPTS ''
ENV S3_ACCESS_KEY_ID **None**
ENV S3_SECRET_ACCESS_KEY **None**
ENV S3_BUCKET **None**
ENV S3_REGION us-west-1
ENV POSTGRES_USER ''
ENV POSTGRES_PASSWORD ''
ENV PGDUMP_EXTRA_OPTS ''
ENV S3_ACCESS_KEY_ID ''
ENV S3_SECRET_ACCESS_KEY ''
ENV S3_BUCKET ''
ENV S3_REGION 'us-west-1'
ENV S3_PATH 'backup'
ENV S3_ENDPOINT **None**
ENV S3_S3V4 no
ENV SCHEDULE **None**
ENV DROP_PUBLIC no
ENV S3_ENDPOINT ''
ENV S3_S3V4 'no'
ENV SCHEDULE ''
ENV PASSPHRASE ''
ADD run.sh run.sh
ADD backup.sh backup.sh