githaven/modules/setting/actions.go
Jason Song 33cc5837a6
Support compression for Actions logs (#31761)
Support compression for Actions logs to save storage space and
bandwidth. Inspired by
https://github.com/go-gitea/gitea/issues/24256#issuecomment-1521153015

The biggest challenge is that the compression format should support
[seekable](https://github.com/facebook/zstd/blob/dev/contrib/seekable_format/zstd_seekable_compression_format.md).
So when users are viewing a part of the log lines, Gitea doesn't need to
download the whole compressed file and decompress it.

That means gzip cannot help here. And I did research, there aren't too
many choices, like bgzip and xz, but I think zstd is the most popular
one. It has an implementation in Golang with
[zstd](https://github.com/klauspost/compress/tree/master/zstd) and
[zstd-seekable-format-go](https://github.com/SaveTheRbtz/zstd-seekable-format-go),
and what is better is that it has good compatibility: a seekable format
zstd file can be read by a regular zstd reader.

This PR introduces a new package `zstd` to combine and wrap the two
packages, to provide a unified and easy-to-use API.

And a new setting `LOG_COMPRESSION` is added to the config, although I
don't see any reason why not to use compression, I think's it's a good
idea to keep the default with `none` to be consistent with old versions.

`LOG_COMPRESSION` takes effect for only new log files, it adds `.zst` as
an extension to the file name, so Gitea can determine if it needs
decompression according to the file name when reading. Old files will
keep the format since it's not worth converting them, as they will be
cleared after #31735.

<img width="541" alt="image"
src="https://github.com/user-attachments/assets/e9598764-a4e0-4b68-8c2b-f769265183c9">
2024-08-09 10:10:30 +08:00

124 lines
4.0 KiB
Go

// Copyright 2022 The Gitea Authors. All rights reserved.
// SPDX-License-Identifier: MIT
package setting
import (
"fmt"
"strings"
"time"
"code.gitea.io/gitea/modules/log"
)
// Actions settings
var (
Actions = struct {
Enabled bool
LogStorage *Storage // how the created logs should be stored
LogRetentionDays int64 `ini:"LOG_RETENTION_DAYS"`
LogCompression logCompression `ini:"LOG_COMPRESSION"`
ArtifactStorage *Storage // how the created artifacts should be stored
ArtifactRetentionDays int64 `ini:"ARTIFACT_RETENTION_DAYS"`
DefaultActionsURL defaultActionsURL `ini:"DEFAULT_ACTIONS_URL"`
ZombieTaskTimeout time.Duration `ini:"ZOMBIE_TASK_TIMEOUT"`
EndlessTaskTimeout time.Duration `ini:"ENDLESS_TASK_TIMEOUT"`
AbandonedJobTimeout time.Duration `ini:"ABANDONED_JOB_TIMEOUT"`
SkipWorkflowStrings []string `ìni:"SKIP_WORKFLOW_STRINGS"`
}{
Enabled: true,
DefaultActionsURL: defaultActionsURLGitHub,
SkipWorkflowStrings: []string{"[skip ci]", "[ci skip]", "[no ci]", "[skip actions]", "[actions skip]"},
}
)
type defaultActionsURL string
func (url defaultActionsURL) URL() string {
switch url {
case defaultActionsURLGitHub:
return "https://github.com"
case defaultActionsURLSelf:
return strings.TrimSuffix(AppURL, "/")
default:
// This should never happen, but just in case, use GitHub as fallback
return "https://github.com"
}
}
const (
defaultActionsURLGitHub = "github" // https://github.com
defaultActionsURLSelf = "self" // the root URL of the self-hosted Gitea instance
// DefaultActionsURL only supports GitHub and the self-hosted Gitea.
// It's intentionally not supported more, so please be cautious before adding more like "gitea" or "gitlab".
// If you get some trouble with `uses: username/action_name@version` in your workflow,
// please consider to use `uses: https://the_url_you_want_to_use/username/action_name@version` instead.
)
type logCompression string
func (c logCompression) IsValid() bool {
return c.IsNone() || c.IsZstd()
}
func (c logCompression) IsNone() bool {
return c == "" || strings.ToLower(string(c)) == "none"
}
func (c logCompression) IsZstd() bool {
return strings.ToLower(string(c)) == "zstd"
}
func loadActionsFrom(rootCfg ConfigProvider) error {
sec := rootCfg.Section("actions")
err := sec.MapTo(&Actions)
if err != nil {
return fmt.Errorf("failed to map Actions settings: %v", err)
}
if urls := string(Actions.DefaultActionsURL); urls != defaultActionsURLGitHub && urls != defaultActionsURLSelf {
url := strings.Split(urls, ",")[0]
if strings.HasPrefix(url, "https://") || strings.HasPrefix(url, "http://") {
log.Error("[actions] DEFAULT_ACTIONS_URL does not support %q as custom URL any longer, fallback to %q",
urls,
defaultActionsURLGitHub,
)
Actions.DefaultActionsURL = defaultActionsURLGitHub
} else {
return fmt.Errorf("unsupported [actions] DEFAULT_ACTIONS_URL: %q", urls)
}
}
// don't support to read configuration from [actions]
Actions.LogStorage, err = getStorage(rootCfg, "actions_log", "", nil)
if err != nil {
return err
}
// default to 1 year
if Actions.LogRetentionDays <= 0 {
Actions.LogRetentionDays = 365
}
actionsSec, _ := rootCfg.GetSection("actions.artifacts")
Actions.ArtifactStorage, err = getStorage(rootCfg, "actions_artifacts", "", actionsSec)
if err != nil {
return err
}
// default to 90 days in Github Actions
if Actions.ArtifactRetentionDays <= 0 {
Actions.ArtifactRetentionDays = 90
}
Actions.ZombieTaskTimeout = sec.Key("ZOMBIE_TASK_TIMEOUT").MustDuration(10 * time.Minute)
Actions.EndlessTaskTimeout = sec.Key("ENDLESS_TASK_TIMEOUT").MustDuration(3 * time.Hour)
Actions.AbandonedJobTimeout = sec.Key("ABANDONED_JOB_TIMEOUT").MustDuration(24 * time.Hour)
if !Actions.LogCompression.IsValid() {
return fmt.Errorf("invalid [actions] LOG_COMPRESSION: %q", Actions.LogCompression)
}
return nil
}