bench-forgejo/models/repo_indexer.go

407 lines
11 KiB
Go
Raw Normal View History

// Copyright 2017 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 models
import (
"fmt"
"strconv"
"strings"
"time"
"code.gitea.io/gitea/modules/base"
"code.gitea.io/gitea/modules/charset"
"code.gitea.io/gitea/modules/git"
"code.gitea.io/gitea/modules/graceful"
"code.gitea.io/gitea/modules/indexer"
"code.gitea.io/gitea/modules/log"
"code.gitea.io/gitea/modules/setting"
2018-02-05 23:59:17 +05:30
"github.com/ethantkoenig/rupture"
)
// RepoIndexerStatus status of a repo's entry in the repo indexer
// For now, implicitly refers to default branch
type RepoIndexerStatus struct {
ID int64 `xorm:"pk autoincr"`
RepoID int64 `xorm:"INDEX"`
CommitSha string `xorm:"VARCHAR(40)"`
}
func (repo *Repository) getIndexerStatus() error {
if repo.IndexerStatus != nil {
return nil
}
status := &RepoIndexerStatus{RepoID: repo.ID}
has, err := x.Get(status)
if err != nil {
return err
} else if !has {
status.CommitSha = ""
}
repo.IndexerStatus = status
return nil
}
func (repo *Repository) updateIndexerStatus(sha string) error {
if err := repo.getIndexerStatus(); err != nil {
return err
}
if len(repo.IndexerStatus.CommitSha) == 0 {
repo.IndexerStatus.CommitSha = sha
_, err := x.Insert(repo.IndexerStatus)
return err
}
repo.IndexerStatus.CommitSha = sha
_, err := x.ID(repo.IndexerStatus.ID).Cols("commit_sha").
Update(repo.IndexerStatus)
return err
}
type repoIndexerOperation struct {
2019-11-23 20:33:35 +05:30
repoID int64
deleted bool
watchers []chan<- error
}
var repoIndexerOperationQueue chan repoIndexerOperation
// InitRepoIndexer initialize the repo indexer
func InitRepoIndexer() {
if !setting.Indexer.RepoIndexerEnabled {
return
}
waitChannel := make(chan time.Duration)
repoIndexerOperationQueue = make(chan repoIndexerOperation, setting.Indexer.UpdateQueueLength)
go func() {
start := time.Now()
log.Info("Initializing Repository Indexer")
indexer.InitRepoIndexer(populateRepoIndexerAsynchronously)
go processRepoIndexerOperationQueue()
waitChannel <- time.Since(start)
}()
if setting.Indexer.StartupTimeout > 0 {
go func() {
timeout := setting.Indexer.StartupTimeout
if graceful.Manager.IsChild() && setting.GracefulHammerTime > 0 {
timeout += setting.GracefulHammerTime
}
select {
case duration := <-waitChannel:
log.Info("Repository Indexer Initialization took %v", duration)
case <-time.After(timeout):
log.Fatal("Repository Indexer Initialization Timed-Out after: %v", timeout)
}
}()
}
}
// populateRepoIndexerAsynchronously asynchronously populates the repo indexer
// with pre-existing data. This should only be run when the indexer is created
// for the first time.
func populateRepoIndexerAsynchronously() error {
exist, err := x.Table("repository").Exist()
if err != nil {
return err
} else if !exist {
return nil
}
// if there is any existing repo indexer metadata in the DB, delete it
// since we are starting afresh. Also, xorm requires deletes to have a
// condition, and we want to delete everything, thus 1=1.
if _, err := x.Where("1=1").Delete(new(RepoIndexerStatus)); err != nil {
return err
}
var maxRepoID int64
if _, err = x.Select("MAX(id)").Table("repository").Get(&maxRepoID); err != nil {
return err
}
go populateRepoIndexer(maxRepoID)
return nil
}
// populateRepoIndexer populate the repo indexer with pre-existing data. This
// should only be run when the indexer is created for the first time.
func populateRepoIndexer(maxRepoID int64) {
log.Info("Populating the repo indexer with existing repositories")
// start with the maximum existing repo ID and work backwards, so that we
// don't include repos that are created after gitea starts; such repos will
// already be added to the indexer, and we don't need to add them again.
for maxRepoID > 0 {
repos := make([]*Repository, 0, RepositoryListDefaultPageSize)
err := x.Where("id <= ?", maxRepoID).
OrderBy("id DESC").
Limit(RepositoryListDefaultPageSize).
Find(&repos)
if err != nil {
Better logging (#6038) (#6095) * Panic don't fatal on create new logger Fixes #5854 Signed-off-by: Andrew Thornton <art27@cantab.net> * partial broken * Update the logging infrastrcture Signed-off-by: Andrew Thornton <art27@cantab.net> * Reset the skip levels for Fatal and Error Signed-off-by: Andrew Thornton <art27@cantab.net> * broken ncsa * More log.Error fixes Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove nal * set log-levels to lowercase * Make console_test test all levels * switch to lowercased levels * OK now working * Fix vetting issues * Fix lint * Fix tests * change default logging to match current gitea * Improve log testing Signed-off-by: Andrew Thornton <art27@cantab.net> * reset error skip levels to 0 * Update documentation and access logger configuration * Redirect the router log back to gitea if redirect macaron log but also allow setting the log level - i.e. TRACE * Fix broken level caching * Refactor the router log * Add Router logger * Add colorizing options * Adjust router colors * Only create logger if they will be used * update app.ini.sample * rename Attribute ColorAttribute * Change from white to green for function * Set fatal/error levels * Restore initial trace logger * Fix Trace arguments in modules/auth/auth.go * Properly handle XORMLogger * Improve admin/config page * fix fmt * Add auto-compression of old logs * Update error log levels * Remove the unnecessary skip argument from Error, Fatal and Critical * Add stacktrace support * Fix tests * Remove x/sync from vendors? * Add stderr option to console logger * Use filepath.ToSlash to protect against Windows in tests * Remove prefixed underscores from names in colors.go * Remove not implemented database logger This was removed from Gogs on 4 Mar 2016 but left in the configuration since then. * Ensure that log paths are relative to ROOT_PATH * use path.Join * rename jsonConfig to logConfig * Rename "config" to "jsonConfig" to make it clearer * Requested changes * Requested changes: XormLogger * Try to color the windows terminal If successful default to colorizing the console logs * fixup * Colorize initially too * update vendor * Colorize logs on default and remove if this is not a colorizing logger * Fix documentation * fix test * Use go-isatty to detect if on windows we are on msys or cygwin * Fix spelling mistake * Add missing vendors * More changes * Rationalise the ANSI writer protection * Adjust colors on advice from @0x5c * Make Flags a comma separated list * Move to use the windows constant for ENABLE_VIRTUAL_TERMINAL_PROCESSING * Ensure matching is done on the non-colored message - to simpify EXPRESSION
2019-04-02 13:18:31 +05:30
log.Error("populateRepoIndexer: %v", err)
return
} else if len(repos) == 0 {
break
}
for _, repo := range repos {
repoIndexerOperationQueue <- repoIndexerOperation{
2019-11-23 20:33:35 +05:30
repoID: repo.ID,
deleted: false,
}
maxRepoID = repo.ID - 1
}
}
log.Info("Done populating the repo indexer with existing repositories")
}
2019-11-23 20:33:35 +05:30
func updateRepoIndexer(repoID int64) error {
repo, err := getRepositoryByID(x, repoID)
if err != nil {
return err
}
sha, err := getDefaultBranchSha(repo)
if err != nil {
return err
}
changes, err := getRepoChanges(repo, sha)
if err != nil {
return err
} else if changes == nil {
return nil
}
batch := indexer.RepoIndexerBatch()
for _, update := range changes.Updates {
if err := addUpdate(update, repo, batch); err != nil {
return err
}
}
for _, filename := range changes.RemovedFilenames {
if err := addDelete(filename, repo, batch); err != nil {
return err
}
}
if err = batch.Flush(); err != nil {
return err
}
return repo.updateIndexerStatus(sha)
}
// repoChanges changes (file additions/updates/removals) to a repo
type repoChanges struct {
Updates []fileUpdate
RemovedFilenames []string
}
type fileUpdate struct {
Filename string
BlobSha string
}
func getDefaultBranchSha(repo *Repository) (string, error) {
stdout, err := git.NewCommand("show-ref", "-s", repo.DefaultBranch).RunInDir(repo.RepoPath())
if err != nil {
return "", err
}
return strings.TrimSpace(stdout), nil
}
// getRepoChanges returns changes to repo since last indexer update
func getRepoChanges(repo *Repository, revision string) (*repoChanges, error) {
if err := repo.getIndexerStatus(); err != nil {
return nil, err
}
if len(repo.IndexerStatus.CommitSha) == 0 {
return genesisChanges(repo, revision)
}
return nonGenesisChanges(repo, revision)
}
2018-02-05 23:59:17 +05:30
func addUpdate(update fileUpdate, repo *Repository, batch rupture.FlushingBatch) error {
stdout, err := git.NewCommand("cat-file", "-s", update.BlobSha).
RunInDir(repo.RepoPath())
if err != nil {
return err
}
if size, err := strconv.Atoi(strings.TrimSpace(stdout)); err != nil {
return fmt.Errorf("Misformatted git cat-file output: %v", err)
} else if int64(size) > setting.Indexer.MaxIndexerFileSize {
return addDelete(update.Filename, repo, batch)
}
fileContents, err := git.NewCommand("cat-file", "blob", update.BlobSha).
RunInDirBytes(repo.RepoPath())
if err != nil {
return err
} else if !base.IsTextFile(fileContents) {
// FIXME: UTF-16 files will probably fail here
return nil
}
2018-02-05 23:59:17 +05:30
indexerUpdate := indexer.RepoIndexerUpdate{
Filepath: update.Filename,
Op: indexer.RepoIndexerOpUpdate,
Data: &indexer.RepoIndexerData{
RepoID: repo.ID,
Content: string(charset.ToUTF8DropErrors(fileContents)),
},
2018-02-05 23:59:17 +05:30
}
return indexerUpdate.AddToFlushingBatch(batch)
}
2018-02-05 23:59:17 +05:30
func addDelete(filename string, repo *Repository, batch rupture.FlushingBatch) error {
indexerUpdate := indexer.RepoIndexerUpdate{
Filepath: filename,
Op: indexer.RepoIndexerOpDelete,
Data: &indexer.RepoIndexerData{
RepoID: repo.ID,
},
2018-02-05 23:59:17 +05:30
}
return indexerUpdate.AddToFlushingBatch(batch)
}
func isIndexable(entry *git.TreeEntry) bool {
if !entry.IsRegular() && !entry.IsExecutable() {
return false
}
name := strings.ToLower(entry.Name())
for _, g := range setting.Indexer.ExcludePatterns {
if g.Match(name) {
return false
}
}
for _, g := range setting.Indexer.IncludePatterns {
if g.Match(name) {
return true
}
}
return len(setting.Indexer.IncludePatterns) == 0
}
// parseGitLsTreeOutput parses the output of a `git ls-tree -r --full-name` command
2018-02-10 23:49:26 +05:30
func parseGitLsTreeOutput(stdout []byte) ([]fileUpdate, error) {
entries, err := git.ParseTreeEntries(stdout)
if err != nil {
return nil, err
}
var idxCount = 0
2018-02-10 23:49:26 +05:30
updates := make([]fileUpdate, len(entries))
for _, entry := range entries {
if isIndexable(entry) {
updates[idxCount] = fileUpdate{
Filename: entry.Name(),
BlobSha: entry.ID.String(),
}
idxCount++
}
}
return updates[:idxCount], nil
}
// genesisChanges get changes to add repo to the indexer for the first time
func genesisChanges(repo *Repository, revision string) (*repoChanges, error) {
var changes repoChanges
stdout, err := git.NewCommand("ls-tree", "--full-tree", "-r", revision).
2018-02-10 23:49:26 +05:30
RunInDirBytes(repo.RepoPath())
if err != nil {
return nil, err
}
changes.Updates, err = parseGitLsTreeOutput(stdout)
return &changes, err
}
// nonGenesisChanges get changes since the previous indexer update
func nonGenesisChanges(repo *Repository, revision string) (*repoChanges, error) {
diffCmd := git.NewCommand("diff", "--name-status",
repo.IndexerStatus.CommitSha, revision)
stdout, err := diffCmd.RunInDir(repo.RepoPath())
if err != nil {
// previous commit sha may have been removed by a force push, so
// try rebuilding from scratch
log.Warn("git diff: %v", err)
if err = indexer.DeleteRepoFromIndexer(repo.ID); err != nil {
return nil, err
}
return genesisChanges(repo, revision)
}
var changes repoChanges
updatedFilenames := make([]string, 0, 10)
for _, line := range strings.Split(stdout, "\n") {
line = strings.TrimSpace(line)
if len(line) == 0 {
continue
}
filename := strings.TrimSpace(line[1:])
if len(filename) == 0 {
continue
} else if filename[0] == '"' {
filename, err = strconv.Unquote(filename)
if err != nil {
return nil, err
}
}
switch status := line[0]; status {
case 'M', 'A':
updatedFilenames = append(updatedFilenames, filename)
case 'D':
changes.RemovedFilenames = append(changes.RemovedFilenames, filename)
default:
log.Warn("Unrecognized status: %c (line=%s)", status, line)
}
}
cmd := git.NewCommand("ls-tree", "--full-tree", revision, "--")
cmd.AddArguments(updatedFilenames...)
2018-02-10 23:49:26 +05:30
lsTreeStdout, err := cmd.RunInDirBytes(repo.RepoPath())
if err != nil {
return nil, err
}
2018-02-10 23:49:26 +05:30
changes.Updates, err = parseGitLsTreeOutput(lsTreeStdout)
return &changes, err
}
func processRepoIndexerOperationQueue() {
for {
op := <-repoIndexerOperationQueue
var err error
if op.deleted {
2019-11-23 20:33:35 +05:30
if err = indexer.DeleteRepoFromIndexer(op.repoID); err != nil {
Better logging (#6038) (#6095) * Panic don't fatal on create new logger Fixes #5854 Signed-off-by: Andrew Thornton <art27@cantab.net> * partial broken * Update the logging infrastrcture Signed-off-by: Andrew Thornton <art27@cantab.net> * Reset the skip levels for Fatal and Error Signed-off-by: Andrew Thornton <art27@cantab.net> * broken ncsa * More log.Error fixes Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove nal * set log-levels to lowercase * Make console_test test all levels * switch to lowercased levels * OK now working * Fix vetting issues * Fix lint * Fix tests * change default logging to match current gitea * Improve log testing Signed-off-by: Andrew Thornton <art27@cantab.net> * reset error skip levels to 0 * Update documentation and access logger configuration * Redirect the router log back to gitea if redirect macaron log but also allow setting the log level - i.e. TRACE * Fix broken level caching * Refactor the router log * Add Router logger * Add colorizing options * Adjust router colors * Only create logger if they will be used * update app.ini.sample * rename Attribute ColorAttribute * Change from white to green for function * Set fatal/error levels * Restore initial trace logger * Fix Trace arguments in modules/auth/auth.go * Properly handle XORMLogger * Improve admin/config page * fix fmt * Add auto-compression of old logs * Update error log levels * Remove the unnecessary skip argument from Error, Fatal and Critical * Add stacktrace support * Fix tests * Remove x/sync from vendors? * Add stderr option to console logger * Use filepath.ToSlash to protect against Windows in tests * Remove prefixed underscores from names in colors.go * Remove not implemented database logger This was removed from Gogs on 4 Mar 2016 but left in the configuration since then. * Ensure that log paths are relative to ROOT_PATH * use path.Join * rename jsonConfig to logConfig * Rename "config" to "jsonConfig" to make it clearer * Requested changes * Requested changes: XormLogger * Try to color the windows terminal If successful default to colorizing the console logs * fixup * Colorize initially too * update vendor * Colorize logs on default and remove if this is not a colorizing logger * Fix documentation * fix test * Use go-isatty to detect if on windows we are on msys or cygwin * Fix spelling mistake * Add missing vendors * More changes * Rationalise the ANSI writer protection * Adjust colors on advice from @0x5c * Make Flags a comma separated list * Move to use the windows constant for ENABLE_VIRTUAL_TERMINAL_PROCESSING * Ensure matching is done on the non-colored message - to simpify EXPRESSION
2019-04-02 13:18:31 +05:30
log.Error("DeleteRepoFromIndexer: %v", err)
}
} else {
2019-11-23 20:33:35 +05:30
if err = updateRepoIndexer(op.repoID); err != nil {
Better logging (#6038) (#6095) * Panic don't fatal on create new logger Fixes #5854 Signed-off-by: Andrew Thornton <art27@cantab.net> * partial broken * Update the logging infrastrcture Signed-off-by: Andrew Thornton <art27@cantab.net> * Reset the skip levels for Fatal and Error Signed-off-by: Andrew Thornton <art27@cantab.net> * broken ncsa * More log.Error fixes Signed-off-by: Andrew Thornton <art27@cantab.net> * Remove nal * set log-levels to lowercase * Make console_test test all levels * switch to lowercased levels * OK now working * Fix vetting issues * Fix lint * Fix tests * change default logging to match current gitea * Improve log testing Signed-off-by: Andrew Thornton <art27@cantab.net> * reset error skip levels to 0 * Update documentation and access logger configuration * Redirect the router log back to gitea if redirect macaron log but also allow setting the log level - i.e. TRACE * Fix broken level caching * Refactor the router log * Add Router logger * Add colorizing options * Adjust router colors * Only create logger if they will be used * update app.ini.sample * rename Attribute ColorAttribute * Change from white to green for function * Set fatal/error levels * Restore initial trace logger * Fix Trace arguments in modules/auth/auth.go * Properly handle XORMLogger * Improve admin/config page * fix fmt * Add auto-compression of old logs * Update error log levels * Remove the unnecessary skip argument from Error, Fatal and Critical * Add stacktrace support * Fix tests * Remove x/sync from vendors? * Add stderr option to console logger * Use filepath.ToSlash to protect against Windows in tests * Remove prefixed underscores from names in colors.go * Remove not implemented database logger This was removed from Gogs on 4 Mar 2016 but left in the configuration since then. * Ensure that log paths are relative to ROOT_PATH * use path.Join * rename jsonConfig to logConfig * Rename "config" to "jsonConfig" to make it clearer * Requested changes * Requested changes: XormLogger * Try to color the windows terminal If successful default to colorizing the console logs * fixup * Colorize initially too * update vendor * Colorize logs on default and remove if this is not a colorizing logger * Fix documentation * fix test * Use go-isatty to detect if on windows we are on msys or cygwin * Fix spelling mistake * Add missing vendors * More changes * Rationalise the ANSI writer protection * Adjust colors on advice from @0x5c * Make Flags a comma separated list * Move to use the windows constant for ENABLE_VIRTUAL_TERMINAL_PROCESSING * Ensure matching is done on the non-colored message - to simpify EXPRESSION
2019-04-02 13:18:31 +05:30
log.Error("updateRepoIndexer: %v", err)
}
}
for _, watcher := range op.watchers {
watcher <- err
}
}
}
// DeleteRepoFromIndexer remove all of a repository's entries from the indexer
func DeleteRepoFromIndexer(repo *Repository, watchers ...chan<- error) {
2019-11-23 20:33:35 +05:30
addOperationToQueue(repoIndexerOperation{repoID: repo.ID, deleted: true, watchers: watchers})
}
// UpdateRepoIndexer update a repository's entries in the indexer
func UpdateRepoIndexer(repo *Repository, watchers ...chan<- error) {
2019-11-23 20:33:35 +05:30
addOperationToQueue(repoIndexerOperation{repoID: repo.ID, deleted: false, watchers: watchers})
}
func addOperationToQueue(op repoIndexerOperation) {
if !setting.Indexer.RepoIndexerEnabled {
return
}
select {
case repoIndexerOperationQueue <- op:
break
default:
go func() {
repoIndexerOperationQueue <- op
}()
}
}