feat: add better handler for part size (#214)

* feat: add better handler for part size


fix: use local file 


fix: try with another path


fix: use bytes 


chore: go back


go back readme


goback


goback


goback

* chore: better handling

* fix: typo readme

* chore: wrong comparaison

* fix: typo

.github/workflows/test.yml

@@ -11,10 +11,20 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - uses: actions/checkout@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
       - name: Build Docker Image
+        env:
+          DOCKER_BUILDKIT: '1'
         run: docker build . -t offen/docker-volume-backup:test
+
       - name: Run Tests
         working-directory: ./test
         run: |
+          # Stop the buildx container so the tests can make assertions
+          # about the number of running containers
+          docker rm -f $(docker ps -aq)
           export GPG_TTY=$(tty)
           ./test.sh test

Dockerfile

@@ -16,8 +16,6 @@ WORKDIR /root
 RUN apk add --no-cache ca-certificates
 
 COPY --from=builder /app/cmd/backup/backup /usr/bin/backup
-
-COPY ./entrypoint.sh /root/
-RUN chmod +x entrypoint.sh
+COPY --chmod=755 ./entrypoint.sh /root/
 
 ENTRYPOINT ["/root/entrypoint.sh"]

README.md

@@ -260,6 +260,15 @@ You can populate below template according to your requirements and use it as you
 
 # AWS_STORAGE_CLASS="GLACIER"
 
+# Setting this variable will change the S3 default part size for the copy step.
+# This value is useful when you want to upload large files.
+# NB : While using Scaleway as S3 provider, be aware that the parts counter is set to 1.000.
+# While Minio uses a hard coded value to 10.000. As a workaround, try to set a higher value.
+# Defaults to "16" (MB) if unset (from minio), you can set this value according to your needs.
+# The unit is in MB and an integer.
+
+# AWS_PART_SIZE=16
+
 # You can also backup files to any WebDAV server:
 
 # The URL of the remote WebDAV server
@@ -424,7 +433,7 @@ You can populate below template according to your requirements and use it as you
 
 # Notifications (email, Slack, etc.) can be sent out when a backup run finishes.
 # Configuration is provided as a comma-separated list of URLs as consumed
-# by `shoutrrr`: https://containrrr.dev/shoutrrr/v0.5/services/overview/
+# by `shoutrrr`: https://containrrr.dev/shoutrrr/0.7/services/overview/
 # The content of such notifications can be customized. Dedicated documentation
 # on how to do this can be found in the README. When providing multiple URLs or
 # an URL that contains a comma, the values can be URL encoded to avoid ambiguities.
@@ -568,7 +577,7 @@ services:
 Notification backends other than email are also supported.
 Refer to the documentation of [shoutrrr][shoutrrr-docs] to find out about options and configuration.
 
-[shoutrrr-docs]: https://containrrr.dev/shoutrrr/v0.5/services/overview/
+[shoutrrr-docs]: https://containrrr.dev/shoutrrr/0.7/services/overview/
 
 ### Customize notifications
 
@@ -657,7 +666,23 @@ volumes:
 The backup procedure is guaranteed to wait for all `pre` or `post` commands to finish before proceeding.
 However there are no guarantees about the order in which they are run, which could also happen concurrently.
 
-By default the backup command is executed by the root user. It is possible to specify a custom user in container labels with the format `docker-volume-backup.[step]-[pre|post]-[user]`. The option will allow you to run a specific step command by specified user. Make sure the user exists and present in `passwd` inside the target container.
+By default the backup command is executed by the user provided by the container's image.
+It is possible to specify a custom user that is used to run commands in dedicated labels with the format `docker-volume-backup.[step]-[pre|post].user`:
+
+```yml
+version: '3'
+
+services:
+  gitea:
+    image: gitea/gitea
+    volumes:
+      - backup_data:/tmp
+    labels:
+      - docker-volume-backup.archive-pre.user=git
+      - docker-volume-backup.archive-pre=/bin/bash -c 'cd /tmp; /usr/local/bin/gitea dump -c /data/gitea/conf/app.ini -R -f dump.zip'
+```
+
+Make sure the user exists and is present in `passwd` inside the target container.
 
 ### Encrypting your backup using GPG
 

cmd/backup/config.go

@@ -28,6 +28,7 @@ type Config struct {
 	AwsSecretAccessKey            string        `split_words:"true"`
 	AwsSecretAccessKeyFile        string        `split_words:"true"`
 	AwsIamRoleEndpoint            string        `split_words:"true"`
+	AwsPartSize                   int64         `split_words:"true"`
 	BackupSources                 string        `split_words:"true" default:"/backup"`
 	BackupFilename                string        `split_words:"true" default:"backup-%Y-%m-%dT%H-%M-%S.tar.gz"`
 	BackupFilenameExpand          bool          `split_words:"true"`

cmd/backup/script.go

@@ -142,6 +142,7 @@ func newScript() (*script, error) {
 			BucketName:       s.c.AwsS3BucketName,
 			StorageClass:     s.c.AwsStorageClass,
 			CACert:           s.c.AwsEndpointCACert.Cert,
+			PartSize:         s.c.AwsPartSize,
 		}
 		if s3Backend, err := s3.NewStorageBackend(s3Config, logFunc); err != nil {
 			return nil, err

go.mod

@@ -5,7 +5,7 @@ go 1.19
 require (
 	github.com/Azure/azure-sdk-for-go/sdk/azidentity v1.2.0
 	github.com/Azure/azure-sdk-for-go/sdk/storage/azblob v0.6.1
-	github.com/containrrr/shoutrrr v0.6.0
+	github.com/containrrr/shoutrrr v0.7.1
 	github.com/cosiner/argv v0.1.0
 	github.com/docker/docker v20.10.24+incompatible
 	github.com/gofrs/flock v0.8.1
@@ -17,7 +17,7 @@ require (
 	github.com/sirupsen/logrus v1.9.0
 	github.com/studio-b12/gowebdav v0.0.0-20220128162035-c7b1ff8a5e62
 	golang.org/x/crypto v0.3.0
-	golang.org/x/sync v0.0.0-20220601150217-0de741cfad7f
+	golang.org/x/sync v0.1.0
 )
 
 require (
@@ -25,24 +25,21 @@ require (
 	github.com/Azure/azure-sdk-for-go/sdk/internal v1.0.1 // indirect
 	github.com/AzureAD/microsoft-authentication-library-for-go v0.7.0 // indirect
 	github.com/Microsoft/go-winio v0.5.2 // indirect
-	github.com/docker/distribution v2.8.0+incompatible // indirect
+	github.com/docker/distribution v2.8.2+incompatible // indirect
 	github.com/docker/go-connections v0.4.0 // indirect
 	github.com/docker/go-units v0.4.0 // indirect
 	github.com/dustin/go-humanize v1.0.0 // indirect
-	github.com/fatih/color v1.10.0 // indirect
+	github.com/fatih/color v1.13.0 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/golang-jwt/jwt/v4 v4.4.2 // indirect
-	github.com/golang/protobuf v1.5.2 // indirect
-	github.com/google/go-cmp v0.5.6 // indirect
 	github.com/google/uuid v1.3.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/klauspost/compress v1.15.12 // indirect
 	github.com/klauspost/cpuid/v2 v2.2.1 // indirect
 	github.com/kr/fs v0.1.0 // indirect
-	github.com/kr/text v0.2.0 // indirect
 	github.com/kylelemons/godebug v1.1.0 // indirect
-	github.com/mattn/go-colorable v0.1.8 // indirect
-	github.com/mattn/go-isatty v0.0.12 // indirect
+	github.com/mattn/go-colorable v0.1.13 // indirect
+	github.com/mattn/go-isatty v0.0.16 // indirect
 	github.com/minio/md5-simd v1.1.2 // indirect
 	github.com/minio/sha256-simd v1.0.0 // indirect
 	github.com/moby/term v0.0.0-20200312100748-672ec06f55cd // indirect
@@ -50,7 +47,6 @@ require (
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/morikuni/aec v1.0.0 // indirect
 	github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e // indirect
-	github.com/onsi/gomega v1.10.3 // indirect
 	github.com/opencontainers/go-digest v1.0.0 // indirect
 	github.com/opencontainers/image-spec v1.0.3-0.20211202183452-c5a74bcca799 // indirect
 	github.com/pkg/browser v0.0.0-20210115035449-ce105d075bb4 // indirect
@@ -59,10 +55,7 @@ require (
 	golang.org/x/net v0.7.0 // indirect
 	golang.org/x/sys v0.7.0 // indirect
 	golang.org/x/text v0.7.0 // indirect
-	golang.org/x/time v0.0.0-20210723032227-1f47c861a9ac // indirect
-	google.golang.org/protobuf v1.28.0 // indirect
 	gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f // indirect
 	gopkg.in/ini.v1 v1.67.0 // indirect
-	gopkg.in/yaml.v3 v3.0.1 // indirect
 	gotest.tools/v3 v3.0.3 // indirect
 )

internal/storage/s3/s3.go

@@ -8,6 +8,7 @@ import (
 	"crypto/x509"
 	"errors"
 	"fmt"
+	"os"
 	"path"
 	"path/filepath"
 	"time"
@@ -22,6 +23,7 @@ type s3Storage struct {
 	client       *minio.Client
 	bucket       string
 	storageClass string
+	partSize     int64
 }
 
 // Config contains values that define the configuration of a S3 backend.
@@ -35,6 +37,7 @@ type Config struct {
 	RemotePath       string
 	BucketName       string
 	StorageClass     string
+	PartSize         int64
 	CACert           *x509.Certificate
 }
 
@@ -89,6 +92,7 @@ func NewStorageBackend(opts Config, logFunc storage.Log) (storage.Backend, error
 		client:       mc,
 		bucket:       opts.BucketName,
 		storageClass: opts.StorageClass,
+		partSize:     opts.PartSize,
 	}, nil
 }
 
@@ -100,16 +104,32 @@ func (v *s3Storage) Name() string {
 // Copy copies the given file to the S3/Minio storage backend.
 func (b *s3Storage) Copy(file string) error {
 	_, name := path.Split(file)
-
-	if _, err := b.client.FPutObject(context.Background(), b.bucket, filepath.Join(b.DestinationPath, name), file, minio.PutObjectOptions{
+	putObjectOptions := minio.PutObjectOptions{
 		ContentType:  "application/tar+gzip",
 		StorageClass: b.storageClass,
-	}); err != nil {
+	}
+
+	if b.partSize > 0 {
+		srcFileInfo, err := os.Stat(file)
+		if err != nil {
+			return fmt.Errorf("(*s3Storage).Copy: error reading the local file: %w", err)
+		}
+
+		_, partSize, _, err := minio.OptimalPartInfo(srcFileInfo.Size(), uint64(b.partSize*1024*1024))
+		if err != nil {
+			return fmt.Errorf("(*s3Storage).Copy: error computing the optimal s3 part size: %w", err)
+		}
+
+		putObjectOptions.PartSize = uint64(partSize)
+	}
+
+	if _, err := b.client.FPutObject(context.Background(), b.bucket, filepath.Join(b.DestinationPath, name), file, putObjectOptions); err != nil {
 		if errResp := minio.ToErrorResponse(err); errResp.Message != "" {
 			return fmt.Errorf("(*s3Storage).Copy: error uploading backup to remote storage: [Message]: '%s', [Code]: %s, [StatusCode]: %d", errResp.Message, errResp.Code, errResp.StatusCode)
 		}
 		return fmt.Errorf("(*s3Storage).Copy: error uploading backup to remote storage: %w", err)
 	}
+
 	b.Log(storage.LogLevelInfo, b.Name(), "Uploaded a copy of backup `%s` to bucket `%s`.", file, b.bucket)
 
 	return nil

test/azure/run.sh

@@ -17,7 +17,7 @@ sleep 5
 
 expect_running_containers "3"
 
-docker-compose run --rm az_cli \
+docker compose run --rm az_cli \
   az storage blob download -f /dump/test.tar.gz -c test-container -n path/to/backup/test.tar.gz
 tar -xvf ./local/test.tar.gz -C /tmp && test -f /tmp/backup/app_data/offen.db
 
@@ -26,7 +26,7 @@ pass "Found relevant files in untared remote backups."
 # The second part of this test checks if backups get deleted when the retention
 # is set to 0 days (which it should not as it would mean all backups get deleted)
 # TODO: find out if we can test actual deletion without having to wait for a day
-BACKUP_RETENTION_DAYS="0" docker-compose up -d
+BACKUP_RETENTION_DAYS="0" docker compose up -d
 sleep 5
 
 docker compose exec backup backup