summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMarin Jankovski <marin@gitlab.com>2019-04-23 10:05:29 +0000
committerMarin Jankovski <marin@gitlab.com>2019-04-23 10:05:29 +0000
commit834688b131f49b7bcd26d129904b99d7a514c49f (patch)
treed2ee0d4e86e598d030c90900e53ec4e0af0e1ef9
parent7b7b5090bc6734a5e894fb2f52aa65dc216dcfcc (diff)
parent3c9655955c6c744bdde995a2da2c6f3918131535 (diff)
downloadgitlab-ce-834688b131f49b7bcd26d129904b99d7a514c49f.tar.gz
Merge branch '11-7-rugged-stable-backport' into '11-7-stable'
[11.7] Backport Rugged implementations for Git access See merge request gitlab-org/gitlab-ce!27537
-rw-r--r--app/helpers/tree_helper.rb11
-rw-r--r--changelogs/unreleased/sh-backport-list-commits-by-oid-rugged.yml5
-rw-r--r--changelogs/unreleased/sh-fix-rugged-tree-entries.yml5
-rw-r--r--changelogs/unreleased/sh-rugged-commit-is-ancestor.yml5
-rw-r--r--changelogs/unreleased/sh-rugged-commit-tree-entry.yml5
-rw-r--r--changelogs/unreleased/sh-rugged-find-commit.yml5
-rw-r--r--changelogs/unreleased/sh-rugged-get-tree-entry.yml5
-rw-r--r--changelogs/unreleased/sh-rugged-tree-entries.yml5
-rw-r--r--doc/administration/high_availability/nfs.md22
-rw-r--r--doc/development/gitaly.md40
-rw-r--r--lib/gitlab/git/blob.rb6
-rw-r--r--lib/gitlab/git/commit.rb22
-rw-r--r--lib/gitlab/git/ref.rb1
-rw-r--r--lib/gitlab/git/repository.rb1
-rw-r--r--lib/gitlab/git/rugged_impl/blob.rb106
-rw-r--r--lib/gitlab/git/rugged_impl/commit.rb109
-rw-r--r--lib/gitlab/git/rugged_impl/ref.rb20
-rw-r--r--lib/gitlab/git/rugged_impl/repository.rb78
-rw-r--r--lib/gitlab/git/rugged_impl/tree.rb109
-rw-r--r--lib/gitlab/git/tree.rb6
-rw-r--r--lib/gitlab/gitaly_client/storage_settings.rb8
-rw-r--r--lib/tasks/gitlab/features.rake24
-rwxr-xr-xscripts/lint-rugged8
-rw-r--r--spec/lib/gitlab/git/blob_spec.rb16
-rw-r--r--spec/lib/gitlab/git/commit_spec.rb53
-rw-r--r--spec/lib/gitlab/git/tree_spec.rb74
-rw-r--r--spec/lib/gitlab/gitaly_client/storage_settings_spec.rb10
-rw-r--r--spec/models/commit_spec.rb16
-rw-r--r--spec/models/repository_spec.rb16
-rw-r--r--spec/spec_helper.rb9
30 files changed, 775 insertions, 25 deletions
diff --git a/app/helpers/tree_helper.rb b/app/helpers/tree_helper.rb
index e2879bfdcf1..c5bab877c00 100644
--- a/app/helpers/tree_helper.rb
+++ b/app/helpers/tree_helper.rb
@@ -136,18 +136,9 @@ module TreeHelper
end
# returns the relative path of the first subdir that doesn't have only one directory descendant
- # rubocop: disable CodeReuse/ActiveRecord
def flatten_tree(root_path, tree)
- return tree.flat_path.sub(%r{\A#{Regexp.escape(root_path)}/}, '') if tree.flat_path.present?
-
- subtree = Gitlab::Git::Tree.where(@repository, @commit.id, tree.path)
- if subtree.count == 1 && subtree.first.dir?
- return tree_join(tree.name, flatten_tree(root_path, subtree.first))
- else
- return tree.name
- end
+ tree.flat_path.sub(%r{\A#{Regexp.escape(root_path)}/}, '')
end
- # rubocop: enable CodeReuse/ActiveRecord
def selected_branch
@branch_name || tree_edit_branch
diff --git a/changelogs/unreleased/sh-backport-list-commits-by-oid-rugged.yml b/changelogs/unreleased/sh-backport-list-commits-by-oid-rugged.yml
new file mode 100644
index 00000000000..eb8774d652f
--- /dev/null
+++ b/changelogs/unreleased/sh-backport-list-commits-by-oid-rugged.yml
@@ -0,0 +1,5 @@
+---
+title: Bring back Rugged implementation of ListCommitsByOid
+merge_request: 27441
+author:
+type: performance
diff --git a/changelogs/unreleased/sh-fix-rugged-tree-entries.yml b/changelogs/unreleased/sh-fix-rugged-tree-entries.yml
new file mode 100644
index 00000000000..97b27678905
--- /dev/null
+++ b/changelogs/unreleased/sh-fix-rugged-tree-entries.yml
@@ -0,0 +1,5 @@
+---
+title: Avoid excessive recursive calls with Rugged TreeEntries
+merge_request: 26813
+author:
+type: fixed
diff --git a/changelogs/unreleased/sh-rugged-commit-is-ancestor.yml b/changelogs/unreleased/sh-rugged-commit-is-ancestor.yml
new file mode 100644
index 00000000000..0f62176b4a5
--- /dev/null
+++ b/changelogs/unreleased/sh-rugged-commit-is-ancestor.yml
@@ -0,0 +1,5 @@
+---
+title: Bring back Rugged implementation of CommitIsAncestor
+merge_request: 25702
+author:
+type: other
diff --git a/changelogs/unreleased/sh-rugged-commit-tree-entry.yml b/changelogs/unreleased/sh-rugged-commit-tree-entry.yml
new file mode 100644
index 00000000000..bcefa2c7112
--- /dev/null
+++ b/changelogs/unreleased/sh-rugged-commit-tree-entry.yml
@@ -0,0 +1,5 @@
+---
+title: Bring back Rugged implementation of commit_tree_entry
+merge_request: 25896
+author:
+type: other
diff --git a/changelogs/unreleased/sh-rugged-find-commit.yml b/changelogs/unreleased/sh-rugged-find-commit.yml
new file mode 100644
index 00000000000..85b5936c9ba
--- /dev/null
+++ b/changelogs/unreleased/sh-rugged-find-commit.yml
@@ -0,0 +1,5 @@
+---
+title: Bring back Rugged implementation of find_commit
+merge_request: 25477
+author:
+type: fixed
diff --git a/changelogs/unreleased/sh-rugged-get-tree-entry.yml b/changelogs/unreleased/sh-rugged-get-tree-entry.yml
new file mode 100644
index 00000000000..4d46b764022
--- /dev/null
+++ b/changelogs/unreleased/sh-rugged-get-tree-entry.yml
@@ -0,0 +1,5 @@
+---
+title: Bring back Rugged implementation of TreeEntry
+merge_request: 25706
+author:
+type: other
diff --git a/changelogs/unreleased/sh-rugged-tree-entries.yml b/changelogs/unreleased/sh-rugged-tree-entries.yml
new file mode 100644
index 00000000000..fca1f204b9b
--- /dev/null
+++ b/changelogs/unreleased/sh-rugged-tree-entries.yml
@@ -0,0 +1,5 @@
+---
+title: Bring back Rugged implementation of GetTreeEntries
+merge_request: 25674
+author:
+type: other
diff --git a/doc/administration/high_availability/nfs.md b/doc/administration/high_availability/nfs.md
index 74b0e2c8184..78ebf8a083b 100644
--- a/doc/administration/high_availability/nfs.md
+++ b/doc/administration/high_availability/nfs.md
@@ -37,6 +37,28 @@ options:
circumstances it could lead to data loss if a failure occurs before data has
synced.
+### Improving NFS performance with GitLab
+
+If you are using NFS to share Git data, we recommend that you enable a
+number of feature flags that will allow GitLab application processes to
+access Git data directly instead of going through the [Gitaly
+service](../gitaly/index.md). Depending on your workload and disk
+performance, these flags may help improve performance. See [the
+issue](https://gitlab.com/gitlab-org/gitlab-ce/issues/57317) for more
+details.
+
+To do this, run the Rake task:
+
+```sh
+gitlab-rake gitlab:features:enable_rugged
+```
+
+If you need to undo this setting for some reason, run:
+
+```sh
+gitlab-rake gitlab:features:disable_rugged
+```
+
### Known issues
On some customer systems, we have seen NFS clients slow precipitously due to
diff --git a/doc/development/gitaly.md b/doc/development/gitaly.md
index fdae69bddd7..906585f6f21 100644
--- a/doc/development/gitaly.md
+++ b/doc/development/gitaly.md
@@ -56,6 +56,46 @@ If your test-suite is failing with Gitaly issues, as a first step, try running:
rm -rf tmp/tests/gitaly
```
+## Legacy Rugged code
+
+While Gitaly can handle all Git access, many of GitLab customers still
+run Gitaly atop NFS. The legacy Rugged implementation for Git calls may
+be faster than the Gitaly RPC due to N+1 Gitaly calls and other
+reasons. See [the
+issue](https://gitlab.com/gitlab-org/gitlab-ce/issues/57317) for more
+details.
+
+Until GitLab has eliminated most of these inefficiencies or the use of
+NFS is discontinued for Git data, Rugged implementations of some of the
+most commonly-used RPCs can be enabled via feature flags:
+
+* `rugged_find_commit`
+* `rugged_get_tree_entries`
+* `rugged_tree_entry`
+* `rugged_commit_is_ancestor`
+* `rugged_commit_tree_entry`
+* `rugged_list_commits_by_oid`
+
+A convenience Rake task can be used to enable or disable these flags
+all together. To enable:
+
+```sh
+bundle exec rake gitlab:features:enable_rugged
+```
+
+To disable:
+
+```sh
+bundle exec rake gitlab:features:disable_rugged
+```
+
+Most of this code exists in the `lib/gitlab/git/rugged_impl` directory.
+
+NOTE: **Note:** You should NOT need to add or modify code related to
+Rugged unless explicitly discussed with the [Gitaly
+Team](https://gitlab.com/groups/gl-gitaly/group_members). This code will
+NOT work on GitLab.com or other GitLab instances that do not use NFS.
+
## `TooManyInvocationsError` errors
During development and testing, you may experience `Gitlab::GitalyClient::TooManyInvocationsError` failures.
diff --git a/lib/gitlab/git/blob.rb b/lib/gitlab/git/blob.rb
index 259a2b7911a..10df4ed72d9 100644
--- a/lib/gitlab/git/blob.rb
+++ b/lib/gitlab/git/blob.rb
@@ -23,6 +23,10 @@ module Gitlab
class << self
def find(repository, sha, path, limit: MAX_DATA_DISPLAY_SIZE)
+ tree_entry(repository, sha, path, limit)
+ end
+
+ def tree_entry(repository, sha, path, limit)
return unless path
path = path.sub(%r{\A/*}, '')
@@ -179,3 +183,5 @@ module Gitlab
end
end
end
+
+Gitlab::Git::Blob.singleton_class.prepend Gitlab::Git::RuggedImpl::Blob::ClassMethods
diff --git a/lib/gitlab/git/commit.rb b/lib/gitlab/git/commit.rb
index 5863815ca85..7be8539f380 100644
--- a/lib/gitlab/git/commit.rb
+++ b/lib/gitlab/git/commit.rb
@@ -5,6 +5,7 @@ module Gitlab
module Git
class Commit
include Gitlab::EncodingHelper
+ prepend Gitlab::Git::RuggedImpl::Commit
extend Gitlab::Git::WrapsGitalyErrors
attr_accessor :raw_commit, :head
@@ -62,15 +63,19 @@ module Gitlab
# This saves us an RPC round trip.
return nil if commit_id.include?(':')
- commit = wrapped_gitaly_errors do
- repo.gitaly_commit_client.find_commit(commit_id)
- end
+ commit = find_commit(repo, commit_id)
decorate(repo, commit) if commit
rescue Gitlab::Git::CommandError, Gitlab::Git::Repository::NoRepository, ArgumentError
nil
end
+ def find_commit(repo, commit_id)
+ wrapped_gitaly_errors do
+ repo.gitaly_commit_client.find_commit(commit_id)
+ end
+ end
+
# Get last commit for HEAD
#
# Ex.
@@ -185,6 +190,10 @@ module Gitlab
@repository = repository
@head = head
+ init_commit(raw_commit)
+ end
+
+ def init_commit(raw_commit)
case raw_commit
when Hash
init_from_hash(raw_commit)
@@ -305,11 +314,16 @@ module Gitlab
def tree_entry(path)
return unless path.present?
+ commit_tree_entry(path)
+ end
+
+ def commit_tree_entry(path)
# We're only interested in metadata, so limit actual data to 1 byte
# since Gitaly doesn't support "send no data" option.
entry = @repository.gitaly_commit_client.tree_entry(id, path, 1)
return unless entry
+ # To be compatible with the rugged format
entry = entry.to_h
entry.delete(:data)
entry[:name] = File.basename(path)
@@ -400,3 +414,5 @@ module Gitlab
end
end
end
+
+Gitlab::Git::Commit.singleton_class.prepend Gitlab::Git::RuggedImpl::Commit::ClassMethods
diff --git a/lib/gitlab/git/ref.rb b/lib/gitlab/git/ref.rb
index eec91194949..47cfb483509 100644
--- a/lib/gitlab/git/ref.rb
+++ b/lib/gitlab/git/ref.rb
@@ -4,6 +4,7 @@ module Gitlab
module Git
class Ref
include Gitlab::EncodingHelper
+ include Gitlab::Git::RuggedImpl::Ref
# Branch or tag name
# without "refs/tags|heads" prefix
diff --git a/lib/gitlab/git/repository.rb b/lib/gitlab/git/repository.rb
index 786c90f9272..72ab0ee6f0e 100644
--- a/lib/gitlab/git/repository.rb
+++ b/lib/gitlab/git/repository.rb
@@ -11,6 +11,7 @@ module Gitlab
include Gitlab::Git::WrapsGitalyErrors
include Gitlab::EncodingHelper
include Gitlab::Utils::StrongMemoize
+ prepend Gitlab::Git::RuggedImpl::Repository
SEARCH_CONTEXT_LINES = 3
REV_LIST_COMMIT_LIMIT = 2_000
diff --git a/lib/gitlab/git/rugged_impl/blob.rb b/lib/gitlab/git/rugged_impl/blob.rb
new file mode 100644
index 00000000000..11ee4ebda4b
--- /dev/null
+++ b/lib/gitlab/git/rugged_impl/blob.rb
@@ -0,0 +1,106 @@
+# frozen_string_literal: true
+
+# NOTE: This code is legacy. Do not add/modify code here unless you have
+# discussed with the Gitaly team. See
+# https://docs.gitlab.com/ee/development/gitaly.html#legacy-rugged-code
+# for more details.
+
+module Gitlab
+ module Git
+ module RuggedImpl
+ module Blob
+ module ClassMethods
+ extend ::Gitlab::Utils::Override
+
+ override :tree_entry
+ def tree_entry(repository, sha, path, limit)
+ if Feature.enabled?(:rugged_tree_entry)
+ rugged_tree_entry(repository, sha, path, limit)
+ else
+ super
+ end
+ end
+
+ private
+
+ def rugged_tree_entry(repository, sha, path, limit)
+ return unless path
+
+ # Strip any leading / characters from the path
+ path = path.sub(%r{\A/*}, '')
+
+ rugged_commit = repository.lookup(sha)
+ root_tree = rugged_commit.tree
+
+ blob_entry = find_entry_by_path(repository, root_tree.oid, *path.split('/'))
+
+ return unless blob_entry
+
+ if blob_entry[:type] == :commit
+ submodule_blob(blob_entry, path, sha)
+ else
+ blob = repository.lookup(blob_entry[:oid])
+
+ if blob
+ new(
+ id: blob.oid,
+ name: blob_entry[:name],
+ size: blob.size,
+ # Rugged::Blob#content is expensive; don't call it if we don't have to.
+ data: limit.zero? ? '' : blob.content(limit),
+ mode: blob_entry[:filemode].to_s(8),
+ path: path,
+ commit_id: sha,
+ binary: blob.binary?
+ )
+ end
+ end
+ rescue Rugged::ReferenceError
+ nil
+ end
+
+ # Recursive search of blob id by path
+ #
+ # Ex.
+ # blog/ # oid: 1a
+ # app/ # oid: 2a
+ # models/ # oid: 3a
+ # file.rb # oid: 4a
+ #
+ #
+ # Blob.find_entry_by_path(repo, '1a', 'blog', 'app', 'file.rb') # => '4a'
+ #
+ def find_entry_by_path(repository, root_id, *path_parts)
+ root_tree = repository.lookup(root_id)
+
+ entry = root_tree.find do |entry|
+ entry[:name] == path_parts[0]
+ end
+
+ return unless entry
+
+ if path_parts.size > 1
+ return unless entry[:type] == :tree
+
+ path_parts.shift
+ find_entry_by_path(repository, entry[:oid], *path_parts)
+ else
+ [:blob, :commit].include?(entry[:type]) ? entry : nil
+ end
+ end
+
+ def submodule_blob(blob_entry, path, sha)
+ new(
+ id: blob_entry[:oid],
+ name: blob_entry[:name],
+ size: 0,
+ data: '',
+ path: path,
+ commit_id: sha
+ )
+ end
+ end
+ end
+ end
+ end
+end
diff --git a/lib/gitlab/git/rugged_impl/commit.rb b/lib/gitlab/git/rugged_impl/commit.rb
new file mode 100644
index 00000000000..bce4fa14fb4
--- /dev/null
+++ b/lib/gitlab/git/rugged_impl/commit.rb
@@ -0,0 +1,109 @@
+# frozen_string_literal: true
+
+# NOTE: This code is legacy. Do not add/modify code here unless you have
+# discussed with the Gitaly team. See
+# https://docs.gitlab.com/ee/development/gitaly.html#legacy-rugged-code
+# for more details.
+
+# rubocop:disable Gitlab/ModuleWithInstanceVariables
+module Gitlab
+ module Git
+ module RuggedImpl
+ module Commit
+ module ClassMethods
+ extend ::Gitlab::Utils::Override
+
+ def rugged_find(repo, commit_id)
+ obj = repo.rev_parse_target(commit_id)
+
+ obj.is_a?(::Rugged::Commit) ? obj : nil
+ rescue ::Rugged::Error
+ nil
+ end
+
+ # This needs to return an array of Gitlab::Git:Commit objects
+ # instead of Rugged::Commit objects to ensure upstream models
+ # operate on a consistent interface. Unlike
+ # Gitlab::Git::Commit.find, Gitlab::Git::Commit.batch_by_oid
+ # doesn't attempt to decorate the result.
+ def rugged_batch_by_oid(repo, oids)
+ oids.map { |oid| rugged_find(repo, oid) }
+ .compact
+ .map { |commit| decorate(repo, commit) }
+ end
+
+ override :find_commit
+ def find_commit(repo, commit_id)
+ if Feature.enabled?(:rugged_find_commit)
+ rugged_find(repo, commit_id)
+ else
+ super
+ end
+ end
+
+ override :batch_by_oid
+ def batch_by_oid(repo, oids)
+ if Feature.enabled?(:rugged_list_commits_by_oid)
+ rugged_batch_by_oid(repo, oids)
+ else
+ super
+ end
+ end
+ end
+
+ extend ::Gitlab::Utils::Override
+
+ override :init_commit
+ def init_commit(raw_commit)
+ case raw_commit
+ when ::Rugged::Commit
+ init_from_rugged(raw_commit)
+ else
+ super
+ end
+ end
+
+ override :commit_tree_entry
+ def commit_tree_entry(path)
+ if Feature.enabled?(:rugged_commit_tree_entry)
+ rugged_tree_entry(path)
+ else
+ super
+ end
+ end
+
+ # Is this the same as Blob.find_entry_by_path ?
+ def rugged_tree_entry(path)
+ rugged_commit.tree.path(path)
+ rescue Rugged::TreeError
+ nil
+ end
+
+ def rugged_commit
+ @rugged_commit ||= if raw_commit.is_a?(Rugged::Commit)
+ raw_commit
+ else
+ @repository.rev_parse_target(id)
+ end
+ end
+
+ def init_from_rugged(commit)
+ author = commit.author
+ committer = commit.committer
+
+ @raw_commit = commit
+ @id = commit.oid
+ @message = commit.message
+ @authored_date = author[:time]
+ @committed_date = committer[:time]
+ @author_name = author[:name]
+ @author_email = author[:email]
+ @committer_name = committer[:name]
+ @committer_email = committer[:email]
+ @parent_ids = commit.parents.map(&:oid)
+ end
+ end
+ end
+ end
+end
+# rubocop:enable Gitlab/ModuleWithInstanceVariables
diff --git a/lib/gitlab/git/rugged_impl/ref.rb b/lib/gitlab/git/rugged_impl/ref.rb
new file mode 100644
index 00000000000..b553e82dc47
--- /dev/null
+++ b/lib/gitlab/git/rugged_impl/ref.rb
@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+
+# NOTE: This code is legacy. Do not add/modify code here unless you have
+# discussed with the Gitaly team. See
+# https://docs.gitlab.com/ee/development/gitaly.html#legacy-rugged-code
+# for more details.
+
+module Gitlab
+ module Git
+ module RuggedImpl
+ module Ref
+ def self.dereference_object(object)
+ object = object.target while object.is_a?(::Rugged::Tag::Annotation)
+
+ object
+ end
+ end
+ end
+ end
+end
diff --git a/lib/gitlab/git/rugged_impl/repository.rb b/lib/gitlab/git/rugged_impl/repository.rb
new file mode 100644
index 00000000000..e91b0ddcd31
--- /dev/null
+++ b/lib/gitlab/git/rugged_impl/repository.rb
@@ -0,0 +1,78 @@
+# frozen_string_literal: true
+
+# NOTE: This code is legacy. Do not add/modify code here unless you have
+# discussed with the Gitaly team. See
+# https://docs.gitlab.com/ee/development/gitaly.html#legacy-rugged-code
+# for more details.
+
+# rubocop:disable Gitlab/ModuleWithInstanceVariables
+module Gitlab
+ module Git
+ module RuggedImpl
+ module Repository
+ extend ::Gitlab::Utils::Override
+
+ FEATURE_FLAGS = %i(rugged_find_commit rugged_tree_entries rugged_tree_entry rugged_commit_is_ancestor rugged_commit_tree_entry rugged_list_commits_by_oid).freeze
+
+ def alternate_object_directories
+ relative_object_directories.map { |d| File.join(path, d) }
+ end
+
+ ALLOWED_OBJECT_RELATIVE_DIRECTORIES_VARIABLES = %w[
+ GIT_OBJECT_DIRECTORY_RELATIVE
+ GIT_ALTERNATE_OBJECT_DIRECTORIES_RELATIVE
+ ].freeze
+
+ def relative_object_directories
+ Gitlab::Git::HookEnv.all(gl_repository).values_at(*ALLOWED_OBJECT_RELATIVE_DIRECTORIES_VARIABLES).flatten.compact
+ end
+
+ def rugged
+ @rugged ||= ::Rugged::Repository.new(path, alternates: alternate_object_directories)
+ rescue ::Rugged::RepositoryError, ::Rugged::OSError
+ raise ::Gitlab::Git::Repository::NoRepository.new('no repository for such path')
+ end
+
+ def cleanup
+ @rugged&.close
+ end
+
+ # Return the object that +revspec+ points to. If +revspec+ is an
+ # annotated tag, then return the tag's target instead.
+ def rev_parse_target(revspec)
+ obj = rugged.rev_parse(revspec)
+ Ref.dereference_object(obj)
+ end
+
+ override :ancestor?
+ def ancestor?(from, to)
+ if Feature.enabled?(:rugged_commit_is_ancestor)
+ rugged_is_ancestor?(from, to)
+ else
+ super
+ end
+ end
+
+ def rugged_is_ancestor?(ancestor_id, descendant_id)
+ return false if ancestor_id.nil? || descendant_id.nil?
+
+ rugged_merge_base(ancestor_id, descendant_id) == ancestor_id
+ rescue Rugged::OdbError
+ false
+ end
+
+ def rugged_merge_base(from, to)
+ rugged.merge_base(from, to)
+ rescue Rugged::ReferenceError
+ nil
+ end
+
+ # Lookup for rugged object by oid or ref name
+ def lookup(oid_or_ref_name)
+ rugged.rev_parse(oid_or_ref_name)
+ end
+ end
+ end
+ end
+end
+# rubocop:enable Gitlab/ModuleWithInstanceVariables
diff --git a/lib/gitlab/git/rugged_impl/tree.rb b/lib/gitlab/git/rugged_impl/tree.rb
new file mode 100644
index 00000000000..bb13d114d46
--- /dev/null
+++ b/lib/gitlab/git/rugged_impl/tree.rb
@@ -0,0 +1,109 @@
+# frozen_string_literal: true
+
+# NOTE: This code is legacy. Do not add/modify code here unless you have
+# discussed with the Gitaly team. See
+# https://docs.gitlab.com/ee/development/gitaly.html#legacy-rugged-code
+# for more details.
+
+module Gitlab
+ module Git
+ module RuggedImpl
+ module Tree
+ module ClassMethods
+ extend ::Gitlab::Utils::Override
+
+ override :tree_entries
+ def tree_entries(repository, sha, path, recursive)
+ if Feature.enabled?(:rugged_tree_entries)
+ tree_entries_with_flat_path_from_rugged(repository, sha, path, recursive)
+ else
+ super
+ end
+ end
+
+ def tree_entries_with_flat_path_from_rugged(repository, sha, path, recursive)
+ tree_entries_from_rugged(repository, sha, path, recursive).tap do |entries|
+ # This was an optimization to reduce N+1 queries for Gitaly
+ # (https://gitlab.com/gitlab-org/gitaly/issues/530). It
+ # used to be done lazily in the view via
+ # TreeHelper#flatten_tree, so it's possible there's a
+ # performance impact by loading this eagerly.
+ rugged_populate_flat_path(repository, sha, path, entries)
+ end
+ end
+
+ def tree_entries_from_rugged(repository, sha, path, recursive)
+ current_path_entries = get_tree_entries_from_rugged(repository, sha, path)
+ ordered_entries = []
+
+ current_path_entries.each do |entry|
+ ordered_entries << entry
+
+ if recursive && entry.dir?
+ ordered_entries.concat(tree_entries_from_rugged(repository, sha, entry.path, true))
+ end
+ end
+ end
+
+ def rugged_populate_flat_path(repository, sha, path, entries)
+ entries.each do |entry|
+ entry.flat_path = entry.path
+
+ next unless entry.dir?
+
+ entry.flat_path =
+ if path
+ File.join(path, rugged_flatten_tree(repository, sha, entry, path))
+ else
+ rugged_flatten_tree(repository, sha, entry, path)
+ end
+ end
+ end
+
+ # Returns the relative path of the first subdir that doesn't have only one directory descendant
+ def rugged_flatten_tree(repository, sha, tree, root_path)
+ subtree = tree_entries_from_rugged(repository, sha, tree.path, false)
+
+ if subtree.count == 1 && subtree.first.dir?
+ File.join(tree.name, rugged_flatten_tree(repository, sha, subtree.first, root_path))
+ else
+ tree.name
+ end
+ end
+
+ def get_tree_entries_from_rugged(repository, sha, path)
+ commit = repository.lookup(sha)
+ root_tree = commit.tree
+
+ tree = if path
+ id = find_id_by_path(repository, root_tree.oid, path)
+ if id
+ repository.lookup(id)
+ else
+ []
+ end
+ else
+ root_tree
+ end
+
+ tree.map do |entry|
+ current_path = path ? File.join(path, entry[:name]) : entry[:name]
+
+ new(
+ id: entry[:oid],
+ root_id: root_tree.oid,
+ name: entry[:name],
+ type: entry[:type],
+ mode: entry[:filemode].to_s(8),
+ path: current_path,
+ commit_id: sha
+ )
+ end
+ rescue Rugged::ReferenceError
+ []
+ end
+ end
+ end
+ end
+ end
+end
diff --git a/lib/gitlab/git/tree.rb b/lib/gitlab/git/tree.rb
index 51542bcaaa2..33505372eaf 100644
--- a/lib/gitlab/git/tree.rb
+++ b/lib/gitlab/git/tree.rb
@@ -18,6 +18,10 @@ module Gitlab
def where(repository, sha, path = nil, recursive = false)
path = nil if path == '' || path == '/'
+ tree_entries(repository, sha, path, recursive)
+ end
+
+ def tree_entries(repository, sha, path, recursive)
wrapped_gitaly_errors do
repository.gitaly_commit_client.tree_entries(repository, sha, path, recursive)
end
@@ -95,3 +99,5 @@ module Gitlab
end
end
end
+
+Gitlab::Git::Tree.singleton_class.prepend Gitlab::Git::RuggedImpl::Tree::ClassMethods
diff --git a/lib/gitlab/gitaly_client/storage_settings.rb b/lib/gitlab/gitaly_client/storage_settings.rb
index 754cccb6b3f..78ef6bfc0ec 100644
--- a/lib/gitlab/gitaly_client/storage_settings.rb
+++ b/lib/gitlab/gitaly_client/storage_settings.rb
@@ -32,11 +32,19 @@ module Gitlab
end
def self.disk_access_denied?
+ return false if rugged_enabled?
+
!temporarily_allowed?(ALLOW_KEY) && GitalyClient.feature_enabled?(DISK_ACCESS_DENIED_FLAG)
rescue
false # Err on the side of caution, don't break gitlab for people
end
+ def self.rugged_enabled?
+ Gitlab::Git::RuggedImpl::Repository::FEATURE_FLAGS.any? do |flag|
+ Feature.enabled?(flag)
+ end
+ end
+
def initialize(storage)
raise InvalidConfigurationError, "expected a Hash, got a #{storage.class.name}" unless storage.is_a?(Hash)
raise InvalidConfigurationError, INVALID_STORAGE_MESSAGE unless storage.has_key?('path')
diff --git a/lib/tasks/gitlab/features.rake b/lib/tasks/gitlab/features.rake
new file mode 100644
index 00000000000..d115961108e
--- /dev/null
+++ b/lib/tasks/gitlab/features.rake
@@ -0,0 +1,24 @@
+namespace :gitlab do
+ namespace :features do
+ desc 'GitLab | Features | Enable direct Git access via Rugged for NFS'
+ task enable_rugged: :environment do
+ set_rugged_feature_flags(true)
+ puts 'All Rugged feature flags were enabled.'
+ end
+
+ task disable_rugged: :environment do
+ set_rugged_feature_flags(false)
+ puts 'All Rugged feature flags were disabled.'
+ end
+ end
+
+ def set_rugged_feature_flags(status)
+ Gitlab::Git::RuggedImpl::Repository::FEATURE_FLAGS.each do |flag|
+ if status
+ Feature.enable(flag)
+ else
+ Feature.disable(flag)
+ end
+ end
+ end
+end
diff --git a/scripts/lint-rugged b/scripts/lint-rugged
index 22e3e1f1505..9466c62a415 100755
--- a/scripts/lint-rugged
+++ b/scripts/lint-rugged
@@ -5,12 +5,18 @@ ALLOWED = [
'lib/gitlab/bare_repository_import/repository.rb',
# Needed to avoid using the git binary to validate a branch name
- 'lib/gitlab/git_ref_validator.rb'
+ 'lib/gitlab/git_ref_validator.rb',
+
+ # Reverted Rugged calls due to Gitaly atop NFS performance
+ # See https://docs.gitlab.com/ee/development/gitaly.html#legacy-rugged-code.
+ 'lib/gitlab/git/rugged_impl/',
+ 'lib/gitlab/gitaly_client/storage_settings.rb'
].freeze
rugged_lines = IO.popen(%w[git grep -i -n rugged -- app config lib], &:read).lines
rugged_lines = rugged_lines.select { |l| /^[^:]*\.rb:/ =~ l }
rugged_lines = rugged_lines.reject { |l| l.start_with?(*ALLOWED) }
+rugged_lines = rugged_lines.reject { |l| /(include|prepend) Gitlab::Git::RuggedImpl/ =~ l}
rugged_lines = rugged_lines.reject do |line|
code, _comment = line.split('# ', 2)
code !~ /rugged/i
diff --git a/spec/lib/gitlab/git/blob_spec.rb b/spec/lib/gitlab/git/blob_spec.rb
index 1bcec04d28f..9c46df02062 100644
--- a/spec/lib/gitlab/git/blob_spec.rb
+++ b/spec/lib/gitlab/git/blob_spec.rb
@@ -18,7 +18,7 @@ describe Gitlab::Git::Blob, :seed_helper do
end
end
- describe '.find' do
+ shared_examples '.find' do
context 'nil path' do
let(:blob) { Gitlab::Git::Blob.find(repository, SeedRepo::Commit::ID, nil) }
@@ -128,6 +128,20 @@ describe Gitlab::Git::Blob, :seed_helper do
end
end
+ describe '.find with Gitaly enabled' do
+ it_behaves_like '.find'
+ end
+
+ describe '.find with Rugged enabled', :enable_rugged do
+ it 'calls out to the Rugged implementation' do
+ allow_any_instance_of(Rugged).to receive(:rev_parse).with(SeedRepo::Commit::ID).and_call_original
+
+ described_class.find(repository, SeedRepo::Commit::ID, 'files/images/6049019_460s.jpg')
+ end
+
+ it_behaves_like '.find'
+ end
+
describe '.raw' do
let(:raw_blob) { Gitlab::Git::Blob.raw(repository, SeedRepo::RubyBlob::ID) }
let(:bad_blob) { Gitlab::Git::Blob.raw(repository, SeedRepo::BigCommit::ID) }
diff --git a/spec/lib/gitlab/git/commit_spec.rb b/spec/lib/gitlab/git/commit_spec.rb
index db68062e433..e06131d3039 100644
--- a/spec/lib/gitlab/git/commit_spec.rb
+++ b/spec/lib/gitlab/git/commit_spec.rb
@@ -112,7 +112,7 @@ describe Gitlab::Git::Commit, :seed_helper do
end
context 'Class methods' do
- describe '.find' do
+ shared_examples '.find' do
it "should return first head commit if without params" do
expect(described_class.last(repository).id).to eq(
rugged_repo.head.target.oid
@@ -154,6 +154,20 @@ describe Gitlab::Git::Commit, :seed_helper do
end
end
+ describe '.find with Gitaly enabled' do
+ it_should_behave_like '.find'
+ end
+
+ describe '.find with Rugged enabled', :enable_rugged do
+ it 'calls out to the Rugged implementation' do
+ allow_any_instance_of(Rugged).to receive(:rev_parse).with(SeedRepo::Commit::ID).and_call_original
+
+ described_class.find(repository, SeedRepo::Commit::ID)
+ end
+
+ it_should_behave_like '.find'
+ end
+
describe '.last_for_path' do
context 'no path' do
subject { described_class.last_for_path(repository, 'master') }
@@ -366,7 +380,32 @@ describe Gitlab::Git::Commit, :seed_helper do
end
end
- describe '#batch_by_oid' do
+ shared_examples '.batch_by_oid' do
+ context 'with multiple OIDs' do
+ let(:oids) { [SeedRepo::Commit::ID, SeedRepo::FirstCommit::ID] }
+
+ it 'returns multiple commits' do
+ commits = described_class.batch_by_oid(repository, oids)
+
+ expect(commits.count).to eq(2)
+ expect(commits).to all( be_a(Gitlab::Git::Commit) )
+ expect(commits.first.sha).to eq(SeedRepo::Commit::ID)
+ expect(commits.second.sha).to eq(SeedRepo::FirstCommit::ID)
+ end
+ end
+
+ context 'when oids is empty' do
+ it 'returns empty commits' do
+ commits = described_class.batch_by_oid(repository, [])
+
+ expect(commits.count).to eq(0)
+ end
+ end
+ end
+
+ describe '.batch_by_oid with Gitaly enabled' do
+ it_should_behave_like '.batch_by_oid'
+
context 'when oids is empty' do
it 'makes no Gitaly request' do
expect(Gitlab::GitalyClient).not_to receive(:call)
@@ -376,6 +415,16 @@ describe Gitlab::Git::Commit, :seed_helper do
end
end
+ describe '.batch_by_oid with Rugged enabled', :enable_rugged do
+ it_should_behave_like '.batch_by_oid'
+
+ it 'calls out to the Rugged implementation' do
+ allow_any_instance_of(Rugged).to receive(:rev_parse).with(SeedRepo::Commit::ID).and_call_original
+
+ described_class.batch_by_oid(repository, [SeedRepo::Commit::ID])
+ end
+ end
+
shared_examples 'extracting commit signature' do
context 'when the commit is signed' do
let(:commit_id) { '0b4bc9a49b562e85de7cc9e834518ea6828729b9' }
diff --git a/spec/lib/gitlab/git/tree_spec.rb b/spec/lib/gitlab/git/tree_spec.rb
index bec875fb03d..c27c415c5ab 100644
--- a/spec/lib/gitlab/git/tree_spec.rb
+++ b/spec/lib/gitlab/git/tree_spec.rb
@@ -3,7 +3,7 @@ require "spec_helper"
describe Gitlab::Git::Tree, :seed_helper do
let(:repository) { Gitlab::Git::Repository.new('default', TEST_REPO_PATH, '') }
- context :repo do
+ shared_examples :repo do
let(:tree) { Gitlab::Git::Tree.where(repository, SeedRepo::Commit::ID) }
it { expect(tree).to be_kind_of Array }
@@ -12,6 +12,17 @@ describe Gitlab::Git::Tree, :seed_helper do
it { expect(tree.select(&:file?).size).to eq(10) }
it { expect(tree.select(&:submodule?).size).to eq(2) }
+ it 'returns an empty array when called with an invalid ref' do
+ expect(described_class.where(repository, 'foobar-does-not-exist')).to eq([])
+ end
+
+ it 'returns a list of tree objects' do
+ entries = described_class.where(repository, SeedRepo::Commit::ID, 'files', true)
+
+ expect(entries.count).to be >= 5
+ expect(entries).to all(be_a(Gitlab::Git::Tree))
+ end
+
describe '#dir?' do
let(:dir) { tree.select(&:dir?).first }
@@ -20,8 +31,8 @@ describe Gitlab::Git::Tree, :seed_helper do
it { expect(dir.commit_id).to eq(SeedRepo::Commit::ID) }
it { expect(dir.name).to eq('encoding') }
it { expect(dir.path).to eq('encoding') }
- it { expect(dir.flat_path).to eq('encoding') }
it { expect(dir.mode).to eq('40000') }
+ it { expect(dir.flat_path).to eq('encoding') }
context :subdir do
let(:subdir) { Gitlab::Git::Tree.where(repository, SeedRepo::Commit::ID, 'files').first }
@@ -44,6 +55,51 @@ describe Gitlab::Git::Tree, :seed_helper do
it { expect(subdir_file.path).to eq('files/ruby/popen.rb') }
it { expect(subdir_file.flat_path).to eq('files/ruby/popen.rb') }
end
+
+ context :flat_path do
+ let(:filename) { 'files/flat/path/correct/content.txt' }
+ let(:oid) { create_file(filename) }
+ let(:subdir_file) { Gitlab::Git::Tree.where(repository, oid, 'files/flat').first }
+ let(:repository_rugged) { Rugged::Repository.new(File.join(SEED_STORAGE_PATH, TEST_REPO_PATH)) }
+
+ it { expect(subdir_file.flat_path).to eq('files/flat/path/correct') }
+ end
+
+ def create_file(path)
+ oid = repository_rugged.write('test', :blob)
+ index = repository_rugged.index
+ index.add(path: filename, oid: oid, mode: 0100644)
+
+ options = commit_options(
+ repository_rugged,
+ index,
+ repository_rugged.head.target,
+ 'HEAD',
+ 'Add new file')
+
+ Rugged::Commit.create(repository_rugged, options)
+ end
+
+ # Build the options hash that's passed to Rugged::Commit#create
+ def commit_options(repo, index, target, ref, message)
+ options = {}
+ options[:tree] = index.write_tree(repo)
+ options[:author] = {
+ email: "test@example.com",
+ name: "Test Author",
+ time: Time.gm(2014, "mar", 3, 20, 15, 1)
+ }
+ options[:committer] = {
+ email: "test@example.com",
+ name: "Test Author",
+ time: Time.gm(2014, "mar", 3, 20, 15, 1)
+ }
+ options[:message] ||= message
+ options[:parents] = repo.empty? ? [] : [target].compact
+ options[:update_ref] = ref
+
+ options
+ end
end
describe '#file?' do
@@ -79,9 +135,17 @@ describe Gitlab::Git::Tree, :seed_helper do
end
end
- describe '#where' do
- it 'returns an empty array when called with an invalid ref' do
- expect(described_class.where(repository, 'foobar-does-not-exist')).to eq([])
+ describe '.where with Gitaly enabled' do
+ it_behaves_like :repo
+ end
+
+ describe '.where with Rugged enabled', :enable_rugged do
+ it 'calls out to the Rugged implementation' do
+ allow_any_instance_of(Rugged).to receive(:lookup).with(SeedRepo::Commit::ID)
+
+ described_class.where(repository, SeedRepo::Commit::ID, 'files', false)
end
+
+ it_behaves_like :repo
end
end
diff --git a/spec/lib/gitlab/gitaly_client/storage_settings_spec.rb b/spec/lib/gitlab/gitaly_client/storage_settings_spec.rb
index c89913ec8e9..bb10be2a4dc 100644
--- a/spec/lib/gitlab/gitaly_client/storage_settings_spec.rb
+++ b/spec/lib/gitlab/gitaly_client/storage_settings_spec.rb
@@ -26,4 +26,14 @@ describe Gitlab::GitalyClient::StorageSettings do
end
end
end
+
+ describe '.disk_access_denied?' do
+ it 'return false when Rugged is enabled', :enable_rugged do
+ expect(described_class.disk_access_denied?).to be_falsey
+ end
+
+ it 'returns true' do
+ expect(described_class.disk_access_denied?).to be_truthy
+ end
+ end
end
diff --git a/spec/models/commit_spec.rb b/spec/models/commit_spec.rb
index baad8352185..9d4e18534ae 100644
--- a/spec/models/commit_spec.rb
+++ b/spec/models/commit_spec.rb
@@ -542,7 +542,7 @@ eos
end
end
- describe '#uri_type' do
+ shared_examples '#uri_type' do
it 'returns the URI type at the given path' do
expect(commit.uri_type('files/html')).to be(:tree)
expect(commit.uri_type('files/images/logo-black.png')).to be(:raw)
@@ -561,6 +561,20 @@ eos
end
end
+ describe '#uri_type with Gitaly enabled' do
+ it_behaves_like "#uri_type"
+ end
+
+ describe '#uri_type with Rugged enabled', :enable_rugged do
+ it 'calls out to the Rugged implementation' do
+ allow_any_instance_of(Rugged::Tree).to receive(:path).with('files/html').and_call_original
+
+ commit.uri_type('files/html')
+ end
+
+ it_behaves_like '#uri_type'
+ end
+
describe '.from_hash' do
let(:new_commit) { described_class.from_hash(commit.to_hash, project) }
diff --git a/spec/models/repository_spec.rb b/spec/models/repository_spec.rb
index 4978c43c9b5..c66cc99b113 100644
--- a/spec/models/repository_spec.rb
+++ b/spec/models/repository_spec.rb
@@ -2214,7 +2214,7 @@ describe Repository do
rugged.references.create("refs/remotes/#{remote_name}/#{branch_name}", target.id)
end
- describe '#ancestor?' do
+ shared_examples '#ancestor?' do
let(:commit) { repository.commit }
let(:ancestor) { commit.parents.first }
@@ -2238,6 +2238,20 @@ describe Repository do
end
end
+ describe '#ancestor? with Gitaly enabled' do
+ it_behaves_like "#ancestor?"
+ end
+
+ describe '#ancestor? with Rugged enabled', :enable_rugged do
+ it 'calls out to the Rugged implementation' do
+ allow_any_instance_of(Rugged).to receive(:merge_base).with(repository.commit.id, Gitlab::Git::BLANK_SHA).and_call_original
+
+ repository.ancestor?(repository.commit.id, Gitlab::Git::BLANK_SHA)
+ end
+
+ it_behaves_like '#ancestor?'
+ end
+
describe '#archive_metadata' do
let(:ref) { 'master' }
let(:storage_path) { '/tmp' }
diff --git a/spec/spec_helper.rb b/spec/spec_helper.rb
index 89357056c93..efd88f4605d 100644
--- a/spec/spec_helper.rb
+++ b/spec/spec_helper.rb
@@ -115,10 +115,17 @@ RSpec.configure do |config|
TestEnv.clean_test_path
end
- config.before do
+ config.before do |example|
# Enable all features by default for testing
allow(Feature).to receive(:enabled?) { true }
+ enabled = example.metadata[:enable_rugged].present?
+
+ # Disable Rugged features by default
+ Gitlab::Git::RuggedImpl::Repository::FEATURE_FLAGS.each do |flag|
+ allow(Feature).to receive(:enabled?).with(flag).and_return(enabled)
+ end
+
# The following can be removed when we remove the staged rollout strategy
# and we can just enable it using instance wide settings
# (ie. ApplicationSetting#auto_devops_enabled)