gitlab-org--gitlab-foss/app/models/upload.rb
Toon Claes 1c481b7aac Enhance performance of counting local Uploads
Add an index to the `store` column on `uploads`. This makes counting
local uploads faster.

Also, there is no longer need to check for objects with `store = NULL`.
See https://gitlab.com/gitlab-org/gitlab-ce/merge_requests/18557

---

### Query plans

Query:

```sql
SELECT COUNT(*)
FROM "uploads"
WHERE ("uploads"."store" = ? OR "uploads"."store" IS NULL)
```

#### Without index

```
gitlabhq_production=# EXPLAIN ANALYZE SELECT uploads.* FROM uploads WHERE (uploads.store = 1 OR uploads.store IS NULL);
                                                  QUERY PLAN
---------------------------------------------------------------------------------------------------------------
 Seq Scan on uploads  (cost=0.00..601729.54 rows=578 width=272) (actual time=6.170..2308.256 rows=545 loops=1)
   Filter: ((store = 1) OR (store IS NULL))
   Rows Removed by Filter: 4411957
 Planning time: 38.652 ms
 Execution time: 2308.454 ms
(5 rows)
```

#### Add index

```
gitlabhq_production=# create index uploads_tmp1 on uploads (store);
CREATE INDEX
```

#### With index

```
gitlabhq_production=# EXPLAIN ANALYZE SELECT uploads.* FROM uploads WHERE (uploads.store = 1 OR uploads.store IS NULL);
                                                          QUERY PLAN
-------------------------------------------------------------------------------------------------------------------------------
 Bitmap Heap Scan on uploads  (cost=11.46..1238.88 rows=574 width=272) (actual time=0.155..0.577 rows=545 loops=1)
   Recheck Cond: ((store = 1) OR (store IS NULL))
   Heap Blocks: exact=217
   ->  BitmapOr  (cost=11.46..11.46 rows=574 width=0) (actual time=0.116..0.116 rows=0 loops=1)
         ->  Bitmap Index Scan on uploads_tmp1  (cost=0.00..8.74 rows=574 width=0) (actual time=0.095..0.095 rows=545 loops=1)
               Index Cond: (store = 1)
         ->  Bitmap Index Scan on uploads_tmp1  (cost=0.00..2.44 rows=1 width=0) (actual time=0.020..0.020 rows=0 loops=1)
               Index Cond: (store IS NULL)
 Planning time: 0.274 ms
 Execution time: 0.637 ms
(10 rows)
```

Closes https://gitlab.com/gitlab-org/gitlab-ee/issues/6070
2018-11-07 11:29:31 +01:00

96 lines
2.1 KiB
Ruby

# frozen_string_literal: true
class Upload < ActiveRecord::Base
# Upper limit for foreground checksum processing
CHECKSUM_THRESHOLD = 100.megabytes
belongs_to :model, polymorphic: true # rubocop:disable Cop/PolymorphicAssociations
validates :size, presence: true
validates :path, presence: true
validates :model, presence: true
validates :uploader, presence: true
scope :with_files_stored_locally, -> { where(store: ObjectStorage::Store::LOCAL) }
before_save :calculate_checksum!, if: :foreground_checksummable?
after_commit :schedule_checksum, if: :checksummable?
# as the FileUploader is not mounted, the default CarrierWave ActiveRecord
# hooks are not executed and the file will not be deleted
after_destroy :delete_file!, if: -> { uploader_class <= FileUploader }
def self.hexdigest(path)
Digest::SHA256.file(path).hexdigest
end
def absolute_path
raise ObjectStorage::RemoteStoreError, "Remote object has no absolute path." unless local?
return path unless relative_path?
uploader_class.absolute_path(self)
end
def calculate_checksum!
self.checksum = nil
return unless checksummable?
self.checksum = Digest::SHA256.file(absolute_path).hexdigest
end
def build_uploader(mounted_as = nil)
uploader_class.new(model, mounted_as || mount_point).tap do |uploader|
uploader.upload = self
uploader.retrieve_from_store!(identifier)
end
end
def exist?
File.exist?(absolute_path)
end
def uploader_context
{
identifier: identifier,
secret: secret
}.compact
end
def local?
store == ObjectStorage::Store::LOCAL
end
private
def delete_file!
build_uploader.remove!
end
def checksummable?
checksum.nil? && local? && exist?
end
def foreground_checksummable?
checksummable? && size <= CHECKSUM_THRESHOLD
end
def schedule_checksum
UploadChecksumWorker.perform_async(id)
end
def relative_path?
!path.start_with?('/')
end
def uploader_class
Object.const_get(uploader)
end
def identifier
File.basename(path)
end
def mount_point
super&.to_sym
end
end