mirror of
https://codeberg.org/forgejo/forgejo.git
synced 2024-12-21 05:42:28 +03:00
e28cc79c92
This addresses https://github.com/go-gitea/gitea/issues/18352 It aims to improve performance (and resource use) of the `SyncReleasesWithTags` operation for pull-mirrors. For large repositories with many tags, `SyncReleasesWithTags` can be a costly operation (taking several minutes to complete). The reason is two-fold: 1. on sync, every upstream repo tag is compared (for changes) against existing local entries in the release table to ensure that they are up-to-date. 2. the procedure for getting _each tag_ involves a series of git operations ```bash git show-ref --tags -- v8.2.4477 git cat-file -t 29ab6ce9f36660cffaad3c8789e71162e5db5d2f git cat-file -p 29ab6ce9f36660cffaad3c8789e71162e5db5d2f git rev-list --count 29ab6ce9f36660cffaad3c8789e71162e5db5d2f ``` of which the `git rev-list --count` can be particularly heavy. This PR optimizes performance for pull-mirrors. We utilize the fact that a pull-mirror is always identical to its upstream and rebuild the entire release table on every sync and use a batch `git for-each-ref .. refs/tags` call to retrieve all tags in one go. For large mirror repos, with hundreds of annotated tags, this brings down the duration of the sync operation from several minutes to a few seconds. A few unscientific examples run on my local machine: - https://github.com/spring-projects/spring-boot (223 tags) - before: `0m28,673s` - after: `0m2,244s` - https://github.com/kubernetes/kubernetes (890 tags) - before: `8m00s` - after: `0m8,520s` - https://github.com/vim/vim (13954 tags) - before: `14m20,383s` - after: `0m35,467s` I added a `foreachref` package which contains a flexible way of specifying which reference fields are of interest (`git-for-each-ref(1)`) and to produce a parser for the expected output. These could be reused in other places where `for-each-ref` is used. I'll add unit tests for those if the overall PR looks promising.
67 lines
1.6 KiB
Go
67 lines
1.6 KiB
Go
// Copyright 2022 The Gitea Authors. All rights reserved.
|
|
// Use of this source code is governed by a MIT-style
|
|
// license that can be found in the LICENSE file.
|
|
|
|
package foreachref_test
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"code.gitea.io/gitea/modules/git/foreachref"
|
|
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
func TestFormat_Flag(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
|
|
givenFormat foreachref.Format
|
|
|
|
wantFlag string
|
|
}{
|
|
{
|
|
name: "references are delimited by dual null chars",
|
|
|
|
// no reference fields requested
|
|
givenFormat: foreachref.NewFormat(),
|
|
|
|
// only a reference delimiter field in --format
|
|
wantFlag: "%00%00",
|
|
},
|
|
|
|
{
|
|
name: "a field is a space-separated key-value pair",
|
|
|
|
givenFormat: foreachref.NewFormat("refname:short"),
|
|
|
|
// only a reference delimiter field
|
|
wantFlag: "refname:short %(refname:short)%00%00",
|
|
},
|
|
|
|
{
|
|
name: "fields are separated by a null char field-delimiter",
|
|
|
|
givenFormat: foreachref.NewFormat("refname:short", "author"),
|
|
|
|
wantFlag: "refname:short %(refname:short)%00author %(author)%00%00",
|
|
},
|
|
|
|
{
|
|
name: "multiple fields",
|
|
|
|
givenFormat: foreachref.NewFormat("refname:short", "objecttype", "objectname"),
|
|
|
|
wantFlag: "refname:short %(refname:short)%00objecttype %(objecttype)%00objectname %(objectname)%00%00",
|
|
},
|
|
}
|
|
|
|
for _, test := range tests {
|
|
tc := test // don't close over loop variable
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
gotFlag := tc.givenFormat.Flag()
|
|
|
|
require.Equal(t, tc.wantFlag, gotFlag, "unexpected for-each-ref --format string. wanted: '%s', got: '%s'", tc.wantFlag, gotFlag)
|
|
})
|
|
}
|
|
}
|