Skip to content

SeaweedFS is a distributed storage system for object storage (S3), file systems, Iceberg table buckets, and Lance vector buckets, designed to handle billions of files with O(1) disk access and effortless horizontal scaling.

3.2 KB
Raw Blame
# A sample TOML config file for replicating SeaweedFS filer
# Used with "weed filer.backup"
# Using with "weed filer.replicate" is deprecated.
# Put this file to one of the location, with descending priority
#    ./replication.toml
#    $HOME/.seaweedfs/replication.toml
#    /etc/seaweedfs/replication.toml

[source.filer]  # deprecated. Only useful with "weed filer.replicate"
enabled = true
grpcAddress = "localhost:18888"
# all files under this directory tree are replicated.
# this is not a directory on your hard drive, but on your filer.
# i.e., all files with this "prefix" are sent to notification message queue.
directory = "/buckets"
# files from the directory separated by space are excluded from sending notifications
excludeDirectories = "/buckets/tmp"

[sink.local]
enabled = false
directory = "/data"
# all replicated files are under modified time as yyyy-mm-dd directories
# so each date directory contains all new and updated files.
is_incremental = false

[sink.filer]
enabled = false
grpcAddress = "localhost:18888"
# all replicated files are under this directory tree
# this is not a directory on your hard drive, but on your filer.
# i.e., all received files will be "prefixed" to this directory.
directory = "/backup"
replication = ""
collection = ""
ttlSec = 0
is_incremental = false

[sink.s3]
# read credentials doc at https://docs.aws.amazon.com/sdk-for-go/v1/developer-guide/sessions.html
# default loads credentials from the shared credentials file (~/.aws/credentials).
enabled = false
aws_access_key_id = ""         # if empty, loads from the shared credentials file (~/.aws/credentials).
aws_secret_access_key = ""     # if empty, loads from the shared credentials file (~/.aws/credentials).
region = "us-east-2"
bucket = "your_bucket_name"    # an existing bucket
directory = "/"                # destination directory
endpoint = ""
is_incremental = false

[sink.google_cloud_storage]
# read credentials doc at https://cloud.google.com/docs/authentication/getting-started
enabled = false
google_application_credentials = "/path/to/x.json" # path to json credential file
bucket = "your_bucket_seaweedfs"    # an existing bucket
directory = "/"                     # destination directory
is_incremental = false

[sink.azure]
# experimental, let me know if it works
enabled = false
account_name = ""
# leave account_key empty to authenticate with Entra ID instead of a shared key,
# picking up a workload identity or managed identity from the environment. The
# identity needs a data-plane role such as Storage Blob Data Contributor.
account_key = ""
# optional user-assigned identity, when account_key is empty. Workload identity
# takes its tenant and token from AZURE_TENANT_ID and AZURE_FEDERATED_TOKEN_FILE,
# which the Azure workload identity webhook projects into the pod.
client_id = ""
# blob service url, for accounts outside the public cloud. Empty resolves to
# https://<account_name>.blob.core.windows.net/
endpoint = ""
container = "mycontainer"      # an existing container
directory = "/"                # destination directory
is_incremental = false

[sink.backblaze]
enabled = false
b2_account_id = ""
b2_master_application_key = ""
b2_region = ""
bucket = "mybucket"            # an existing bucket
directory = "/"                # destination directory
is_incremental = false