Allow for the exclusion of files from backups (#100)

* Hoist walking of files so it can be used for features other than archive creation

* Add option to ignore files from backup using glob patterns

* Use Regexp instead of glob for exclusion

* Ignore artifacts

* Add teardown to test

* Allow single Re for filtering only

* Add documentation

* Use MatchString on re, add bad input to message in case of error

.circleci/config.yml

@@ -48,6 +48,7 @@ jobs:
             if [[ "$CIRCLE_TAG" =~ ^v[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
               # prerelease tags like `v2.0.0-alpha.1` should not be released as `latest`
               tag_args="$tag_args -t offen/docker-volume-backup:latest"
+              tag_args="$tag_args -t offen/docker-volume-backup:$(echo "$CIRCLE_TAG" | cut -d. -f1)"
             fi
             docker buildx build --platform linux/amd64,linux/arm64,linux/arm/v7 \
                $tag_args . --push

Dockerfile

@@ -1,7 +1,7 @@
 # Copyright 2021 - Offen Authors <hioffen@posteo.de>
 # SPDX-License-Identifier: MPL-2.0
 
-FROM golang:1.17-alpine as builder
+FROM golang:1.18-alpine as builder
 
 WORKDIR /app
 COPY go.mod go.sum ./

README.md

@@ -27,8 +27,10 @@ It handles __recurring or one-off backups of Docker volumes__ to a __local direc
   - [Using with Docker Swarm](#using-with-docker-swarm)
   - [Manually triggering a backup](#manually-triggering-a-backup)
   - [Update deprecated email configuration](#update-deprecated-email-configuration)
+  - [Replace deprecated `BACKUP_FROM_SNAPSHOT` usage](#replace-deprecated-backup_from_snapshot-usage)
   - [Using a custom Docker host](#using-a-custom-docker-host)
   - [Run multiple backup schedules in the same container](#run-multiple-backup-schedules-in-the-same-container)
+  - [Define different retention schedules](#define-different-retention-schedules)
 - [Recipes](#recipes)
   - [Backing up to AWS S3](#backing-up-to-aws-s3)
   - [Backing up to Filebase](#backing-up-to-filebase)
@@ -107,7 +109,7 @@ docker run --rm \
   --env AWS_SECRET_ACCESS_KEY="<xxx>" \
   --env AWS_S3_BUCKET_NAME="<xxx>" \
   --entrypoint backup \
-  offen/docker-volume-backup:latest
+  offen/docker-volume-backup:v2
 ```
 
 Alternatively, pass a `--env-file` in order to use a full config as described below.
@@ -149,6 +151,11 @@ You can populate below template according to your requirements and use it as you
 
 # BACKUP_LATEST_SYMLINK="backup.latest.tar.gz"
 
+# ************************************************************************
+# The BACKUP_FROM_SNAPSHOT option has been deprecated and will be removed
+# in the next major version. Please use exec-pre and exec-post
+# as documented below instead.
+# ************************************************************************
 # Whether to copy the content of backup folder before creating the tar archive.
 # In the rare scenario where the content of the source backup volume is continously
 # updating, but we do not wish to stop the container while performing the backup,
@@ -161,6 +168,12 @@ You can populate below template according to your requirements and use it as you
 
 # BACKUP_SOURCES="/other/location"
 
+# When given, all files in BACKUP_SOURCES whose full path matches the given
+# regular expression will be excluded from the archive. Regular Expressions
+# can be used as from the Go standard library https://pkg.go.dev/regexp
+
+# BACKUP_EXCLUDE_REGEXP="\.log$"
+
 ########### BACKUP STORAGE
 
 # The name of the remote bucket that should be used for storing backups. If
@@ -201,9 +214,9 @@ You can populate below template according to your requirements and use it as you
 # AWS_ENDPOINT_PROTO="https"
 
 # Setting this variable to `true` will disable verification of
-# SSL certificates. You shouldn't use this unless you use self-signed
-# certificates for your remote storage backend. This can only be used
-# when AWS_ENDPOINT_PROTO is set to `https`.
+# SSL certificates for AWS_ENDPOINT. You shouldn't use this unless you use
+# self-signed certificates for your remote storage backend. This can only be
+# used when AWS_ENDPOINT_PROTO is set to `https`.
 
 # AWS_ENDPOINT_INSECURE="true"
 
@@ -226,6 +239,12 @@ You can populate below template according to your requirements and use it as you
 
 # WEBDAV_PASSWORD="password"
 
+# Setting this variable to `true` will disable verification of
+# SSL certificates for WEBDAV_URL. You shouldn't use this unless you use
+# self-signed certificates for your remote storage backend.
+
+# WEBDAV_URL_INSECURE="true"
+
 # In addition to storing backups remotely, you can also keep local copies.
 # Pass a container-local path to store your backups if needed. You also need to
 # mount a local folder or Docker volume into that location (`/archive`
@@ -335,6 +354,16 @@ You can populate below template according to your requirements and use it as you
 
 # DOCKER_HOST="tcp://docker_socket_proxy:2375"
 
+########### LOCK_TIMEOUT
+
+# In the case of overlapping cron schedules run by the same container,
+# subsequent invocations will wait for previous runs to finish before starting.
+# By default, this will time out and fail in case the lock could not be acquired
+# after 60 minutes. In case you need to adjust this timeout, supply a duration
+# value as per https://pkg.go.dev/time#ParseDuration to `LOCK_TIMEOUT`
+
+# LOCK_TIMEOUT="60m"
+
 ########### EMAIL NOTIFICATIONS
 
 # ************************************************************************
@@ -391,7 +420,7 @@ services:
       - docker-volume-backup.stop-during-backup=service1
 
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
       BACKUP_STOP_CONTAINER_LABEL: service1
     volumes:
@@ -414,7 +443,7 @@ version: '3'
 services:
   # ... define other services using the `data` volume here
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
       BACKUP_FILENAME: backup-%Y-%m-%dT%H-%M-%S.tar.gz
       BACKUP_PRUNING_PREFIX: backup-
@@ -437,7 +466,7 @@ version: '3'
 
 services:
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
       # ... other configuration values go here
       NOTIFICATION_URLS=smtp://me:secret@smtp.example.com:587/?fromAddress=no-reply@example.com&toAddresses=you@example.com
@@ -515,7 +544,7 @@ services:
       - docker-volume-backup.exec-label=database
 
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
       EXEC_LABEL: database
     volumes:
@@ -592,7 +621,7 @@ version: '3'
 
 services:
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     volumes:
       - data:/backup/my-app-backup:ro
       - /etc/timezone:/etc/timezone:ro
@@ -615,7 +644,7 @@ When running in Swarm mode, it's also advised to set a hard memory limit on your
 ```yml
 services:
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     deployment:
       resources:
         limits:
@@ -650,6 +679,37 @@ After:
 NOTIFICATION_URLS=smtp://me:secret@posteo.de:587/?fromAddress=no-reply@example.com&toAddresses=you@example.com
 ```
 
+### Replace deprecated `BACKUP_FROM_SNAPSHOT` usage
+
+Starting with version 2.15.0, the `BACKUP_FROM_SNAPSHOT` feature has been deprecated.
+If you need to prepare your sources before the backup is taken, use `exec-pre`, `exec-post` and an intermediate volume:
+
+```yml
+version: '3'
+
+services:
+  my_app:
+    build: .
+    volumes:
+      - data:/var/my_app
+      - backup:/tmp/backup
+    labels:
+      - docker-volume-backup.exec-pre=cp -r /var/my_app /tmp/backup/my-app
+      - docker-volume-backup.exec-post=rm -rf /tmp/backup/my-app
+
+  backup:
+    image: offen/docker-volume-backup:latest
+    environment:
+      BACKUP_SOURCES: /tmp/backup
+    volumes:
+      - backup:/backup:ro
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+
+volumes:
+  data:
+  backup:
+```
+
 ### Using a custom Docker host
 
 If you are interfacing with Docker via TCP, set `DOCKER_HOST` to the correct URL.
@@ -669,7 +729,7 @@ version: '3'
 services:
   # ... define other services using the `data` volume here
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     volumes:
       - data:/backup/my-app-backup:ro
       - /var/run/docker.sock:/var/run/docker.sock:ro
@@ -681,10 +741,44 @@ volumes:
 
 A separate cronjob will be created for each config file.
 If a configuration value is set both in the global environment as well as in the config file, the config file will take precedence.
-The `backup` command expects to run on an exclusive lock, so it is your responsibility to make sure the invocations do not overlap.
+The `backup` command expects to run on an exclusive lock, so in case you provide the same or overlapping schedules in your cron expressions, the runs will still be executed serially, one after the other.
+The exact order of schedules that use the same cron expression is not specified.
 In case you need your schedules to overlap, you need to create a dedicated container for each schedule instead.
 When changing the configuration, you currently need to manually restart the container for the changes to take effect.
 
+### Define different retention schedules
+
+If you want to manage backup retention on different schedules, the most straight forward approach is to define a dedicated configuration for retention rule using a different prefix in the `BACKUP_FILENAME` parameter and then run them on different cron schedules.
+
+For example, if you wanted to keep daily backups for 7 days, weekly backups for a month, and retain monthly backups forever, you could create three configuration files and mount them into `/etc/dockervolumebackup.d`:
+
+```ini
+# 01daily.conf
+BACKUP_FILENAME="daily-backup-%Y-%m-%dT%H-%M-%S.tar.gz"
+# run every day at 2am
+BACKUP_CRON_EXPRESSION="0 2 * * *"
+BACKUP_PRUNING_PREFIX="daily-backup-"
+BACKUP_RETENTION_DAYS="7"
+```
+
+```ini
+# 02weekly.conf
+BACKUP_FILENAME="weekly-backup-%Y-%m-%dT%H-%M-%S.tar.gz"
+# run every monday at 3am
+BACKUP_CRON_EXPRESSION="0 3 * * 1"
+BACKUP_PRUNING_PREFIX="weekly-backup-"
+BACKUP_RETENTION_DAYS="31"
+```
+
+```ini
+# 03monthly.conf
+BACKUP_FILENAME="monthly-backup-%Y-%m-%dT%H-%M-%S.tar.gz"
+# run every 1st of a month at 4am
+BACKUP_CRON_EXPRESSION="0 4 1 * *"
+```
+
+Note that while it's possible to define colliding cron schedules for each of these configurations, you might need to adjust the value for `LOCK_TIMEOUT` in case your backups are large and might take longer than an hour.
+
 ## Recipes
 
 This section lists configuration for some real-world use cases that you can mix and match according to your needs.
@@ -697,9 +791,9 @@ version: '3'
 services:
   # ... define other services using the `data` volume here
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
-      AWS_BUCKET_NAME: backup-bucket
+      AWS_S3_BUCKET_NAME: backup-bucket
       AWS_ACCESS_KEY_ID: AKIAIOSFODNN7EXAMPLE
       AWS_SECRET_ACCESS_KEY: wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
     volumes:
@@ -718,10 +812,10 @@ version: '3'
 services:
   # ... define other services using the `data` volume here
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
       AWS_ENDPOINT: s3.filebase.com
-      AWS_BUCKET_NAME: filebase-bucket
+      AWS_S3_BUCKET_NAME: filebase-bucket
       AWS_ACCESS_KEY_ID: FILEBASE-ACCESS-KEY
       AWS_SECRET_ACCESS_KEY: FILEBASE-SECRET-KEY
     volumes:
@@ -740,10 +834,10 @@ version: '3'
 services:
   # ... define other services using the `data` volume here
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
       AWS_ENDPOINT: minio.example.com
-      AWS_BUCKET_NAME: backup-bucket
+      AWS_S3_BUCKET_NAME: backup-bucket
       AWS_ACCESS_KEY_ID: MINIOACCESSKEY
       AWS_SECRET_ACCESS_KEY: MINIOSECRETKEY
     volumes:
@@ -762,7 +856,7 @@ version: '3'
 services:
   # ... define other services using the `data` volume here
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
       WEBDAV_URL: https://webdav.mydomain.me
       WEBDAV_PATH: /my/directory/
@@ -784,7 +878,7 @@ version: '3'
 services:
   # ... define other services using the `data` volume here
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
       BACKUP_FILENAME: backup-%Y-%m-%dT%H-%M-%S.tar.gz
       BACKUP_LATEST_SYMLINK: backup-latest.tar.gz
@@ -805,9 +899,9 @@ version: '3'
 services:
   # ... define other services using the `data` volume here
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
-      AWS_BUCKET_NAME: backup-bucket
+      AWS_S3_BUCKET_NAME: backup-bucket
       AWS_ACCESS_KEY_ID: AKIAIOSFODNN7EXAMPLE
       AWS_SECRET_ACCESS_KEY: wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
     volumes:
@@ -827,11 +921,11 @@ version: '3'
 services:
   # ... define other services using the `data` volume here
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
       # take a backup on every hour
       BACKUP_CRON_EXPRESSION: "0 * * * *"
-      AWS_BUCKET_NAME: backup-bucket
+      AWS_S3_BUCKET_NAME: backup-bucket
       AWS_ACCESS_KEY_ID: AKIAIOSFODNN7EXAMPLE
       AWS_SECRET_ACCESS_KEY: wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
     volumes:
@@ -850,9 +944,9 @@ version: '3'
 services:
   # ... define other services using the `data` volume here
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
-      AWS_BUCKET_NAME: backup-bucket
+      AWS_S3_BUCKET_NAME: backup-bucket
       AWS_ACCESS_KEY_ID: AKIAIOSFODNN7EXAMPLE
       AWS_SECRET_ACCESS_KEY: wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
       BACKUP_FILENAME: backup-%Y-%m-%dT%H-%M-%S.tar.gz
@@ -874,9 +968,9 @@ version: '3'
 services:
   # ... define other services using the `data` volume here
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
-      AWS_BUCKET_NAME: backup-bucket
+      AWS_S3_BUCKET_NAME: backup-bucket
       AWS_ACCESS_KEY_ID: AKIAIOSFODNN7EXAMPLE
       AWS_SECRET_ACCESS_KEY: wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
       GPG_PASSPHRASE: somesecretstring
@@ -901,7 +995,7 @@ services:
     volumes:
       - app_data:/tmp/dumps
   backup:
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment:
       BACKUP_FILENAME: db.tar.gz
       BACKUP_CRON_EXPRESSION: "0 2 * * *"
@@ -922,10 +1016,10 @@ version: '3'
 services:
   # ... define other services using the `data_1` and `data_2` volumes here
   backup_1: &backup_service
-    image: offen/docker-volume-backup:latest
+    image: offen/docker-volume-backup:v2
     environment: &backup_environment
       BACKUP_CRON_EXPRESSION: "0 2 * * *"
-      AWS_BUCKET_NAME: backup-bucket
+      AWS_S3_BUCKET_NAME: backup-bucket
       AWS_ACCESS_KEY_ID: AKIAIOSFODNN7EXAMPLE
       AWS_SECRET_ACCESS_KEY: wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
       # Label the container using the `data_1` volume as `docker-volume-backup.stop-during-backup=service1`

cmd/backup/archive.go

@@ -11,14 +11,13 @@ import (
 	"compress/gzip"
 	"fmt"
 	"io"
-	"io/fs"
 	"os"
 	"path"
 	"path/filepath"
 	"strings"
 )
 
-func createArchive(inputFilePath, outputFilePath string) error {
+func createArchive(files []string, inputFilePath, outputFilePath string) error {
 	inputFilePath = stripTrailingSlashes(inputFilePath)
 	inputFilePath, outputFilePath, err := makeAbsolute(inputFilePath, outputFilePath)
 	if err != nil {
@@ -28,7 +27,7 @@ func createArchive(inputFilePath, outputFilePath string) error {
 		return fmt.Errorf("createArchive: error creating output file path: %w", err)
 	}
 
-	if err := compress(inputFilePath, outputFilePath, filepath.Dir(inputFilePath)); err != nil {
+	if err := compress(files, outputFilePath, filepath.Dir(inputFilePath)); err != nil {
 		return fmt.Errorf("createArchive: error creating archive: %w", err)
 	}
 
@@ -52,7 +51,7 @@ func makeAbsolute(inputFilePath, outputFilePath string) (string, string, error)
 	return inputFilePath, outputFilePath, err
 }
 
-func compress(inPath, outFilePath, subPath string) error {
+func compress(paths []string, outFilePath, subPath string) error {
 	file, err := os.Create(outFilePath)
 	if err != nil {
 		return fmt.Errorf("compress: error creating out file: %w", err)
@@ -62,14 +61,6 @@ func compress(inPath, outFilePath, subPath string) error {
 	gzipWriter := gzip.NewWriter(file)
 	tarWriter := tar.NewWriter(gzipWriter)
 
-	var paths []string
-	if err := filepath.WalkDir(inPath, func(path string, di fs.DirEntry, err error) error {
-		paths = append(paths, path)
-		return err
-	}); err != nil {
-		return fmt.Errorf("compress: error walking filesystem tree: %w", err)
-	}
-
 	for _, p := range paths {
 		if err := writeTarGz(p, tarWriter, prefix); err != nil {
 			return fmt.Errorf("compress error writing %s to archive: %w", p, err)

cmd/backup/config.go

@@ -3,7 +3,11 @@
 
 package main
 
-import "time"
+import (
+	"fmt"
+	"regexp"
+	"time"
+)
 
 // Config holds all configuration values that are expected to be set
 // by users.
@@ -18,6 +22,7 @@ type Config struct {
 	BackupPruningPrefix        string        `split_words:"true"`
 	BackupStopContainerLabel   string        `split_words:"true" default:"true"`
 	BackupFromSnapshot         bool          `split_words:"true"`
+	BackupExcludeRegexp        RegexpDecoder `split_words:"true"`
 	AwsS3BucketName            string        `split_words:"true"`
 	AwsS3Path                  string        `split_words:"true"`
 	AwsEndpoint                string        `split_words:"true" default:"s3.amazonaws.com"`
@@ -36,9 +41,27 @@ type Config struct {
 	EmailSMTPUsername          string        `envconfig:"EMAIL_SMTP_USERNAME"`
 	EmailSMTPPassword          string        `envconfig:"EMAIL_SMTP_PASSWORD"`
 	WebdavUrl                  string        `split_words:"true"`
+	WebdavUrlInsecure          bool          `split_words:"true"`
 	WebdavPath                 string        `split_words:"true" default:"/"`
 	WebdavUsername             string        `split_words:"true"`
 	WebdavPassword             string        `split_words:"true"`
 	ExecLabel                  string        `split_words:"true"`
 	ExecForwardOutput          bool          `split_words:"true"`
+	LockTimeout                time.Duration `split_words:"true" default:"60m"`
+}
+
+type RegexpDecoder struct {
+	Re *regexp.Regexp
+}
+
+func (r *RegexpDecoder) Decode(v string) error {
+	if v == "" {
+		return nil
+	}
+	re, err := regexp.Compile(v)
+	if err != nil {
+		return fmt.Errorf("config: error compiling given regexp `%s`: %w", v, err)
+	}
+	*r = RegexpDecoder{Re: re}
+	return nil
 }

cmd/backup/exec.go

@@ -13,12 +13,12 @@ import (
 	"io/ioutil"
 	"os"
 	"strings"
-	"sync"
 
 	"github.com/cosiner/argv"
 	"github.com/docker/docker/api/types"
 	"github.com/docker/docker/api/types/filters"
 	"github.com/docker/docker/pkg/stdcopy"
+	"golang.org/x/sync/errgroup"
 )
 
 func (s *script) exec(containerRef string, command string) ([]byte, []byte, error) {
@@ -97,29 +97,27 @@ func (s *script) runLabeledCommands(label string) error {
 		return nil
 	}
 
-	wg := sync.WaitGroup{}
-	wg.Add(len(containersWithCommand))
+	g := new(errgroup.Group)
 
-	var cmdErrors []error
 	for _, container := range containersWithCommand {
-		go func(c types.Container) {
+		c := container
+		g.Go(func() error {
 			cmd, _ := c.Labels[label]
 			s.logger.Infof("Running %s command %s for container %s", label, cmd, strings.TrimPrefix(c.Names[0], "/"))
 			stdout, stderr, err := s.exec(c.ID, cmd)
-			if err != nil {
-				cmdErrors = append(cmdErrors, err)
-			}
 			if s.c.ExecForwardOutput {
 				os.Stderr.Write(stderr)
 				os.Stdout.Write(stdout)
 			}
-			wg.Done()
-		}(container)
+			if err != nil {
+				return fmt.Errorf("runLabeledCommands: error executing command: %w", err)
+			}
+			return nil
+		})
 	}
 
-	wg.Wait()
-	if len(cmdErrors) != 0 {
-		return join(cmdErrors...)
+	if err := g.Wait(); err != nil {
+		return fmt.Errorf("runLabeledCommands: error from errgroup: %w", err)
 	}
 	return nil
 }

cmd/backup/lock.go

@@ -0,0 +1,58 @@
+// Copyright 2022 - Offen Authors <hioffen@posteo.de>
+// SPDX-License-Identifier: MPL-2.0
+
+package main
+
+import (
+	"errors"
+	"fmt"
+	"time"
+
+	"github.com/gofrs/flock"
+)
+
+// lock opens a lockfile at the given location, keeping it locked until the
+// caller invokes the returned release func. In case the lock is currently blocked
+// by another execution, it will repeatedly retry until the lock is available
+// or the given timeout is exceeded.
+func (s *script) lock(lockfile string) (func() error, error) {
+	start := time.Now()
+	defer func() {
+		s.stats.LockedTime = time.Now().Sub(start)
+	}()
+
+	retry := time.NewTicker(5 * time.Second)
+	defer retry.Stop()
+	deadline := time.NewTimer(s.c.LockTimeout)
+	defer deadline.Stop()
+
+	fileLock := flock.New(lockfile)
+
+	for {
+		acquired, err := fileLock.TryLock()
+		if err != nil {
+			return noop, fmt.Errorf("lock: error trying lock: %w", err)
+		}
+		if acquired {
+			if s.encounteredLock {
+				s.logger.Info("Acquired exclusive lock on subsequent attempt, ready to continue.")
+			}
+			return fileLock.Unlock, nil
+		}
+
+		if !s.encounteredLock {
+			s.logger.Infof(
+				"Exclusive lock was not available on first attempt. Will retry until it becomes available or the timeout of %s is exceeded.",
+				s.c.LockTimeout,
+			)
+			s.encounteredLock = true
+		}
+
+		select {
+		case <-retry.C:
+			continue
+		case <-deadline.C:
+			return noop, errors.New("lock: timed out waiting for lockfile to become available")
+		}
+	}
+}

cmd/backup/main.go

@@ -8,14 +8,15 @@ import (
 )
 
 func main() {
-	unlock := lock("/var/lock/dockervolumebackup.lock")
-	defer unlock()
-
 	s, err := newScript()
 	if err != nil {
 		panic(err)
 	}
 
+	unlock, err := s.lock("/var/lock/dockervolumebackup.lock")
+	defer unlock()
+	s.must(err)
+
 	defer func() {
 		if pArg := recover(); pArg != nil {
 			if err, ok := pArg.(error); ok {

cmd/backup/script.go

@@ -9,6 +9,7 @@ import (
 	"fmt"
 	"io"
 	"io/fs"
+	"net/http"
 	"os"
 	"path"
 	"path/filepath"
@@ -47,6 +48,8 @@ type script struct {
 	file  string
 	stats *Stats
 
+	encounteredLock bool
+
 	c *Config
 }
 
@@ -144,6 +147,15 @@ func newScript() (*script, error) {
 		} else {
 			webdavClient := gowebdav.NewClient(s.c.WebdavUrl, s.c.WebdavUsername, s.c.WebdavPassword)
 			s.webdavClient = webdavClient
+			if s.c.WebdavUrlInsecure {
+				defaultTransport, ok := http.DefaultTransport.(*http.Transport)
+				if !ok {
+					return nil, errors.New("newScript: unexpected error when asserting type for http.DefaultTransport")
+				}
+				webdavTransport := defaultTransport.Clone()
+				webdavTransport.TLSClientConfig.InsecureSkipVerify = s.c.WebdavUrlInsecure
+				s.webdavClient.SetTransport(webdavTransport)
+			}
 		}
 	}
 
@@ -354,6 +366,12 @@ func (s *script) takeBackup() error {
 	backupSources := s.c.BackupSources
 
 	if s.c.BackupFromSnapshot {
+		s.logger.Warn(
+			"Using BACKUP_FROM_SNAPSHOT has been deprecated and will be removed in the next major version.",
+		)
+		s.logger.Warn(
+			"Please use `exec-pre` and `exec-post` commands to prepare your backup sources. Refer to the README for an upgrade guide.",
+		)
 		backupSources = filepath.Join("/tmp", s.c.BackupSources)
 		// copy before compressing guard against a situation where backup folder's content are still growing.
 		s.registerHook(hookLevelPlumbing, func(error) error {
@@ -380,7 +398,28 @@ func (s *script) takeBackup() error {
 		s.logger.Infof("Removed tar file `%s`.", tarFile)
 		return nil
 	})
-	if err := createArchive(backupSources, tarFile); err != nil {
+
+	backupPath, err := filepath.Abs(stripTrailingSlashes(backupSources))
+	if err != nil {
+		return fmt.Errorf("takeBackup: error getting absolute path: %w", err)
+	}
+
+	var filesEligibleForBackup []string
+	if err := filepath.WalkDir(backupPath, func(path string, di fs.DirEntry, err error) error {
+		if err != nil {
+			return err
+		}
+
+		if s.c.BackupExcludeRegexp.Re != nil && s.c.BackupExcludeRegexp.Re.MatchString(path) {
+			return nil
+		}
+		filesEligibleForBackup = append(filesEligibleForBackup, path)
+		return nil
+	}); err != nil {
+		return fmt.Errorf("compress: error walking filesystem tree: %w", err)
+	}
+
+	if err := createArchive(filesEligibleForBackup, backupSources, tarFile); err != nil {
 		return fmt.Errorf("takeBackup: error compressing backup folder: %w", err)
 	}
 
@@ -528,7 +567,8 @@ func (s *script) pruneBackups() error {
 	if s.minioClient != nil {
 		candidates := s.minioClient.ListObjects(context.Background(), s.c.AwsS3BucketName, minio.ListObjectsOptions{
 			WithMetadata: true,
-			Prefix:       s.c.BackupPruningPrefix,
+			Prefix:       filepath.Join(s.c.AwsS3Path, s.c.BackupPruningPrefix),
+			Recursive:    true,
 		})
 
 		var matches []minio.ObjectInfo

cmd/backup/stats.go

@@ -42,6 +42,7 @@ type Stats struct {
 	StartTime  time.Time
 	EndTime    time.Time
 	TookTime   time.Duration
+	LockedTime time.Duration
 	LogOutput  *bytes.Buffer
 	Containers ContainersStats
 	BackupFile BackupFileStats

cmd/backup/util.go

@@ -10,27 +10,10 @@ import (
 	"io"
 	"os"
 	"strings"
-
-	"github.com/gofrs/flock"
 )
 
 var noop = func() error { return nil }
 
-// lock opens a lockfile at the given location, keeping it locked until the
-// caller invokes the returned release func. When invoked while the file is
-// still locked the function panics.
-func lock(lockfile string) func() error {
-	fileLock := flock.New(lockfile)
-	acquired, err := fileLock.TryLock()
-	if err != nil {
-		panic(err)
-	}
-	if !acquired {
-		panic("unable to acquire file lock")
-	}
-	return fileLock.Unlock
-}
-
 // copy creates a copy of the file located at `dst` at `src`.
 func copyFile(src, dst string) error {
 	in, err := os.Open(src)

docs/NOTIFICATION-TEMPLATES.md

@@ -13,6 +13,7 @@ Here is a list of all data passed to the template:
   * `StartTime`: time when the script started execution
   * `EndTime`: time when the backup has completed successfully (after pruning)
   * `TookTime`: amount of time it took for the backup to run. (equal to `EndTime - StartTime`)
+  * `LockedTime`: amount of time it took for the backup to acquire the exclusive lock
   * `LogOutput`: full log of the application
   * `Containers`: object containing stats about the docker containers
     * `All`: total number of containers

go.mod

@@ -1,6 +1,6 @@
 module github.com/offen/docker-volume-backup
 
-go 1.17
+go 1.18
 
 require (
 	github.com/containrrr/shoutrrr v0.5.2
@@ -12,8 +12,9 @@ require (
 	github.com/minio/minio-go/v7 v7.0.16
 	github.com/otiai10/copy v1.7.0
 	github.com/sirupsen/logrus v1.8.1
-	github.com/studio-b12/gowebdav v0.0.0-20211109083228-3f8721cd4b6f
+	github.com/studio-b12/gowebdav v0.0.0-20220128162035-c7b1ff8a5e62
 	golang.org/x/crypto v0.0.0-20210817164053-32db794688a5
+	golang.org/x/sync v0.0.0-20210220032951-036812b2e83c
 )
 
 require (

go.sum

@@ -430,7 +430,6 @@ github.com/klauspost/compress v1.13.5/go.mod h1:/3/Vjq9QcHkK5uEr5lBEmyoZ1iFhe47e
 github.com/klauspost/compress v1.13.6 h1:P76CopJELS0TiO2mebmnzgWaajssP/EszplttgQxcgc=
 github.com/klauspost/compress v1.13.6/go.mod h1:/3/Vjq9QcHkK5uEr5lBEmyoZ1iFhe47etQ6QUkpK6sk=
 github.com/klauspost/cpuid v1.2.3/go.mod h1:Pj4uuM528wm8OyEC2QMXAi2YiTZ96dNQPGgoMS4s3ek=
-github.com/klauspost/cpuid v1.3.1 h1:5JNjFYYQrZeKRJ0734q51WCEEn2huer72Dc7K+R/b6s=
 github.com/klauspost/cpuid v1.3.1/go.mod h1:bYW4mA6ZgKPob1/Dlai2LviZJO7KGI3uoWLd42rAQw4=
 github.com/klauspost/cpuid/v2 v2.0.1/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
 github.com/klauspost/cpuid/v2 v2.0.4/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
@@ -661,6 +660,8 @@ github.com/stretchr/testify v1.6.1 h1:hDPOHmpOpP40lSULcqw7IrRb/u7w6RpDC9399XyoNd
 github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/studio-b12/gowebdav v0.0.0-20211109083228-3f8721cd4b6f h1:L2NE7BXnSlSLoNYZ0lCwZDjdnYjCNYC71k9ClZUTFTs=
 github.com/studio-b12/gowebdav v0.0.0-20211109083228-3f8721cd4b6f/go.mod h1:bHA7t77X/QFExdeAnDzK6vKM34kEZAcE1OX4MfiwjkE=
+github.com/studio-b12/gowebdav v0.0.0-20220128162035-c7b1ff8a5e62 h1:b2nJXyPCa9HY7giGM+kYcnQ71m14JnGdQabMPmyt++8=
+github.com/studio-b12/gowebdav v0.0.0-20220128162035-c7b1ff8a5e62/go.mod h1:bHA7t77X/QFExdeAnDzK6vKM34kEZAcE1OX4MfiwjkE=
 github.com/subosito/gotenv v1.2.0/go.mod h1:N0PQaV/YGNqwC0u51sEeR/aUtSLEXKX9iv69rRypqCw=
 github.com/syndtr/gocapability v0.0.0-20170704070218-db04d3cc01c8/go.mod h1:hkRG7XYTFWNJGYcbNJQlaLq0fg1yr4J4t/NcTQtrfww=
 github.com/syndtr/gocapability v0.0.0-20180916011248-d98352740cb2/go.mod h1:hkRG7XYTFWNJGYcbNJQlaLq0fg1yr4J4t/NcTQtrfww=
@@ -806,6 +807,8 @@ golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJ
 golang.org/x/sync v0.0.0-20200625203802-6e8e738ad208/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20201207232520-09787c993a3a/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20210220032951-036812b2e83c h1:5KslGYwFpkhGh+Q16bwMP3cOontH8FOep7tGV86Y7SQ=
+golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20180909124046-d0be0721c37e/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=

test/compose/docker-compose.yml

@@ -43,6 +43,7 @@ services:
       BACKUP_PRUNING_PREFIX: test
       GPG_PASSPHRASE: 1234secret
       WEBDAV_URL: http://webdav/
+      WEBDAV_URL_INSECURE: 'true'
       WEBDAV_PATH: /my/new/path/
       WEBDAV_USERNAME: test
       WEBDAV_PASSWORD: test

test/confd/02backup.env

@@ -0,0 +1,2 @@
+BACKUP_FILENAME="other.tar.gz"
+BACKUP_CRON_EXPRESSION="*/1 * * * *"

test/confd/docker-compose.yml

@@ -7,8 +7,9 @@ services:
     volumes:
       - ./local:/archive
       - app_data:/backup/app_data:ro
-      - ./backup.env:/etc/dockervolumebackup/conf.d/00backup.env
-      - ./never.env:/etc/dockervolumebackup/conf.d/10never.env
+      - ./01backup.env:/etc/dockervolumebackup/conf.d/01backup.env
+      - ./02backup.env:/etc/dockervolumebackup/conf.d/02backup.env
+      - ./03never.env:/etc/dockervolumebackup/conf.d/03never.env
       - /var/run/docker.sock:/var/run/docker.sock
 
   offen:

test/confd/run.sh

@@ -19,6 +19,12 @@ if [ ! -f ./local/conf.tar.gz ]; then
 fi
 echo "[TEST:PASS] Config from file was used."
 
+if [ ! -f ./local/other.tar.gz ]; then
+  echo "[TEST:FAIL] Run on same schedule did not succeed."
+  exit 1
+fi
+echo "[TEST:PASS] Run on same schedule succeeded."
+
 if [ -f ./local/never.tar.gz ]; then
   echo "[TEST:FAIL] Unexpected file was found."
   exit 1

test/ignore/.gitignore

@@ -0,0 +1 @@
+local

test/ignore/docker-compose.yml

@@ -0,0 +1,15 @@
+version: '3.8'
+
+services:
+  backup:
+    image: offen/docker-volume-backup:${TEST_VERSION:-canary}
+    deploy:
+      restart_policy:
+        condition: on-failure
+    environment:
+      BACKUP_FILENAME: test.tar.gz
+      BACKUP_CRON_EXPRESSION: 0 0 5 31 2 ?
+      BACKUP_EXCLUDE_REGEXP: '\.(me|you)$$'
+    volumes:
+      - ./local:/archive
+      - ./sources:/backup/data:ro

test/ignore/run.sh

@@ -0,0 +1,27 @@
+#!/bin/sh
+
+set -e
+
+cd $(dirname $0)
+mkdir -p local
+
+docker-compose up -d
+sleep 5
+docker-compose exec backup backup
+
+docker-compose down --volumes
+
+out=$(mktemp -d)
+sudo tar --same-owner -xvf ./local/test.tar.gz -C "$out"
+
+if [ ! -f "$out/backup/data/me.txt" ]; then
+  echo "[TEST:FAIL] Expected file was not found."
+  exit 1
+fi
+echo "[TEST:PASS] Expected file was found."
+
+if [ -f "$out/backup/data/skip.me" ]; then
+  echo "[TEST:FAIL] Ignored file was found."
+  exit 1
+fi
+echo "[TEST:PASS] Ignored file was not found."

test/swarm/docker-compose.yml

@@ -43,6 +43,8 @@ services:
     image: offen/offen:latest
     labels:
       - docker-volume-backup.stop-during-backup=true
+    healthcheck:
+      disable: true
     deploy:
       replicas: 2
       restart_policy: