FEATURE: Direct S3 multipart uploads for backups (#14736)

This PR introduces a new `enable_experimental_backup_uploads` site setting (default false and hidden), which when enabled alongside `enable_direct_s3_uploads` will allow for direct S3 multipart uploads of backup .tar.gz files.

To make multipart external uploads work with both the S3BackupStore and the S3Store, I've had to move several methods out of S3Store and into S3Helper, including:

* presigned_url
* create_multipart
* abort_multipart
* complete_multipart
* presign_multipart_part
* list_multipart_parts

Then, S3Store and S3BackupStore either delegate directly to S3Helper or have their own special methods to call S3Helper for these methods. FileStore.temporary_upload_path has also removed its dependence on upload_path, and can now be used interchangeably between the stores. A similar change was made in the frontend as well, moving the multipart related JS code out of ComposerUppyUpload and into a mixin of its own, so it can also be used by UppyUploadMixin.

Some changes to ExternalUploadManager had to be made here as well. The backup direct uploads do not need an Upload record made for them in the database, so they can be moved to their final S3 resting place when completing the multipart upload.

This changeset is not perfect; it introduces some special cases in UploadController to handle backups that was previously in BackupController, because UploadController is where the multipart routes are located. A subsequent pull request will pull these routes into a module or some other sharing pattern, along with hooks, so the backup controller and the upload controller (and any future controllers that may need them) can include these routes in a nicer way.
This commit is contained in:
Martin Brennan
2021-11-11 08:25:31 +10:00
committed by GitHub
parent d4e35f50c2
commit e4350bb966
22 changed files with 725 additions and 356 deletions

View File

@@ -2,12 +2,18 @@
module BackupRestore
class S3BackupStore < BackupStore
UPLOAD_URL_EXPIRES_AFTER_SECONDS ||= 21_600 # 6 hours
UPLOAD_URL_EXPIRES_AFTER_SECONDS ||= 6.hours.to_i
delegate :abort_multipart, :presign_multipart_part, :list_multipart_parts,
:complete_multipart, to: :s3_helper
def initialize(opts = {})
@s3_options = S3Helper.s3_options(SiteSetting)
@s3_options.merge!(opts[:s3_options]) if opts[:s3_options]
@s3_helper = S3Helper.new(s3_bucket_name_with_prefix, '', @s3_options.clone)
end
def s3_helper
@s3_helper ||= S3Helper.new(s3_bucket_name_with_prefix, '', @s3_options.clone)
end
def remote?
@@ -15,12 +21,12 @@ module BackupRestore
end
def file(filename, include_download_source: false)
obj = @s3_helper.object(filename)
obj = s3_helper.object(filename)
create_file_from_object(obj, include_download_source) if obj.exists?
end
def delete_file(filename)
obj = @s3_helper.object(filename)
obj = s3_helper.object(filename)
if obj.exists?
obj.delete
@@ -29,11 +35,11 @@ module BackupRestore
end
def download_file(filename, destination_path, failure_message = nil)
@s3_helper.download_file(filename, destination_path, failure_message)
s3_helper.download_file(filename, destination_path, failure_message)
end
def upload_file(filename, source_path, content_type)
obj = @s3_helper.object(filename)
obj = s3_helper.object(filename)
raise BackupFileExists.new if obj.exists?
obj.upload_file(source_path, content_type: content_type)
@@ -41,7 +47,7 @@ module BackupRestore
end
def generate_upload_url(filename)
obj = @s3_helper.object(filename)
obj = s3_helper.object(filename)
raise BackupFileExists.new if obj.exists?
# TODO (martin) We can remove this at a later date when we move this
@@ -55,12 +61,65 @@ module BackupRestore
raise StorageError.new(e.message.presence || e.class.name)
end
def signed_url_for_temporary_upload(file_name, expires_in: S3Helper::UPLOAD_URL_EXPIRES_AFTER_SECONDS, metadata: {})
obj = object_from_path(file_name)
raise BackupFileExists.new if obj.exists?
key = temporary_upload_path(file_name)
s3_helper.presigned_url(
key,
method: :put_object,
expires_in: expires_in,
opts: {
metadata: metadata,
acl: "private"
}
)
end
def temporary_upload_path(file_name)
FileStore::BaseStore.temporary_upload_path(file_name, folder_prefix: temporary_folder_prefix)
end
def temporary_folder_prefix
folder_prefix = s3_helper.s3_bucket_folder_path.nil? ? "" : s3_helper.s3_bucket_folder_path
if Rails.env.test?
folder_prefix = File.join(folder_prefix, "test_#{ENV['TEST_ENV_NUMBER'].presence || '0'}")
end
folder_prefix
end
def create_multipart(file_name, content_type, metadata: {})
obj = object_from_path(file_name)
raise BackupFileExists.new if obj.exists?
key = temporary_upload_path(file_name)
s3_helper.create_multipart(key, content_type, metadata: metadata)
end
def move_existing_stored_upload(
existing_external_upload_key:,
original_filename: nil,
content_type: nil
)
s3_helper.copy(
existing_external_upload_key,
File.join(s3_helper.s3_bucket_folder_path, original_filename),
options: { acl: "private", apply_metadata_to_destination: true }
)
s3_helper.delete_object(existing_external_upload_key)
end
def object_from_path(path)
s3_helper.object(path)
end
private
def unsorted_files
objects = []
@s3_helper.list.each do |obj|
s3_helper.list.each do |obj|
if obj.key.match?(file_regex)
objects << create_file_from_object(obj)
end
@@ -96,7 +155,7 @@ module BackupRestore
def file_regex
@file_regex ||= begin
path = @s3_helper.s3_bucket_folder_path || ""
path = s3_helper.s3_bucket_folder_path || ""
if path.present?
path = "#{path}/" unless path.end_with?("/")