feat: switch logging framework (#10220)
This updates our logging framework from legacy freetext strings using the `log` package to structured log entries using `log/slog`. I have updated all INFO or higher level entries, but not yet DEBUG (😓)... So, at a high level: There is a slight change in log levels, effectively adding a new warning level: - DEBUG is still debug (ideally not for users but developers, though this is something we need to work on) - INFO is still info, though I've added more data here, effectively making Syncthing more verbose by default (more on this below) - WARNING is a new log level that is different from the _old_ WARNING (more below) - ERROR is what was WARNING before -- problems that must be dealt with, and also bubbled as a popup in the GUI. A new feature is that the logging level can be set per package to something other than just debug or info, and hence I feel that we can add a bit more things into INFO while moving some (in fact, most) current INFO level warnings into WARNING. For example, I think it's justified to get a log of synced files in INFO and sync failures in WARNING. These are things that have historically been tricky to debug properly, and having more information by default will be useful to many, while still making it possible get close to told level of inscrutability by setting the log level to WARNING. I'd like to get to a stage where DEBUG is never necessary to just figure out what's going on, as opposed to trying to narrow down a likely bug. Code wise: - Our logging object, generally known as `l` in each package, is now a new adapter object that provides the old API on top of the newer one. (This should go away once all old log entries are migrated.) This is only for `l.Debugln` and `l.Debugf`. - There is a new level tracker that keeps the log level for each package. - There is a nested setup of handlers, since the structure mandated by `log/slog` is slightly convoluted (imho). We do this because we need to do formatting at a "medium" level internally so we can buffer log lines in text format but with separate timestamp and log level for the API/GUI to consume. - The `debug` API call becomes a `loglevels` API call, which can set the log level to `DEBUG`, `INFO`, `WARNING` or `ERROR` per package. The GUI is updated to handle this. - Our custom `sync` package provided some debugging of mutexes quite strongly integrated into the old logging framework, only turned on when `STTRACE` was set to certain values at startup, etc. It's been a long time since this has been useful; I removed it. - The `STTRACE` env var remains and can be used the same way as before, while additionally permitting specific log levels to be specified, `STTRACE=model:WARN,scanner:DEBUG`. - There is a new command line option `--log-level=INFO` to set the default log level. - The command line options `--log-flags` and `--verbose` go away, but are currently retained as hidden & ignored options since we set them by default in some of our startup examples and Syncthing would otherwise fail to start. Sample format messages: ``` 2009-02-13 23:31:30 INF A basic info line (attr1="val with spaces" attr2=2 attr3="val\"quote" a=a log.pkg=slogutil) 2009-02-13 23:31:30 INF An info line with grouped values (attr1=val1 foo.attr2=2 foo.bar.attr3=3 a=a log.pkg=slogutil) 2009-02-13 23:31:30 INF An info line with grouped values via logger (foo.attr1=val1 foo.attr2=2 a=a log.pkg=slogutil) 2009-02-13 23:31:30 INF An info line with nested grouped values via logger (bar.foo.attr1=val1 bar.foo.attr2=2 a=a log.pkg=slogutil) 2009-02-13 23:31:30 WRN A warning entry (a=a log.pkg=slogutil) 2009-02-13 23:31:30 ERR An error (a=a log.pkg=slogutil) ``` --------- Co-authored-by: Ross Smith II <ross@smithii.com>
This commit is contained in:
co-authored by
Ross Smith II
parent
49462448d0
commit
836045ee87
+21
-22
@@ -10,14 +10,17 @@ import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"math/rand"
|
||||
"path/filepath"
|
||||
"slices"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"github.com/syncthing/syncthing/internal/db"
|
||||
"github.com/syncthing/syncthing/internal/itererr"
|
||||
"github.com/syncthing/syncthing/internal/slogutil"
|
||||
"github.com/syncthing/syncthing/lib/config"
|
||||
"github.com/syncthing/syncthing/lib/events"
|
||||
"github.com/syncthing/syncthing/lib/fs"
|
||||
@@ -30,7 +33,6 @@ import (
|
||||
"github.com/syncthing/syncthing/lib/stats"
|
||||
"github.com/syncthing/syncthing/lib/stringutil"
|
||||
"github.com/syncthing/syncthing/lib/svcutil"
|
||||
"github.com/syncthing/syncthing/lib/sync"
|
||||
"github.com/syncthing/syncthing/lib/versioner"
|
||||
"github.com/syncthing/syncthing/lib/watchaggregator"
|
||||
)
|
||||
@@ -54,6 +56,7 @@ type folder struct {
|
||||
modTimeWindow time.Duration
|
||||
ctx context.Context //nolint:containedctx // used internally, only accessible on serve lifetime
|
||||
done chan struct{} // used externally, accessible regardless of serve
|
||||
sl *slog.Logger
|
||||
|
||||
scanInterval time.Duration
|
||||
scanTimer *time.Timer
|
||||
@@ -98,7 +101,7 @@ type puller interface {
|
||||
pull() (bool, error) // true when successful and should not be retried
|
||||
}
|
||||
|
||||
func newFolder(model *model, ignores *ignore.Matcher, cfg config.FolderConfiguration, evLogger events.Logger, ioLimiter *semaphore.Semaphore, ver versioner.Versioner) folder {
|
||||
func newFolder(model *model, ignores *ignore.Matcher, cfg config.FolderConfiguration, evLogger events.Logger, ioLimiter *semaphore.Semaphore, ver versioner.Versioner) *folder {
|
||||
f := folder{
|
||||
stateTracker: newStateTracker(cfg.ID, evLogger),
|
||||
FolderConfiguration: cfg,
|
||||
@@ -112,6 +115,7 @@ func newFolder(model *model, ignores *ignore.Matcher, cfg config.FolderConfigura
|
||||
mtimefs: cfg.Filesystem(fs.NewMtimeOption(model.sdb, cfg.ID)),
|
||||
modTimeWindow: cfg.ModTimeWindow(),
|
||||
done: make(chan struct{}),
|
||||
sl: slog.Default().With(cfg.LogAttr()),
|
||||
|
||||
scanInterval: time.Duration(cfg.RescanIntervalS) * time.Second,
|
||||
scanTimer: time.NewTimer(0), // The first scan should be done immediately.
|
||||
@@ -123,17 +127,13 @@ func newFolder(model *model, ignores *ignore.Matcher, cfg config.FolderConfigura
|
||||
|
||||
pullScheduled: make(chan struct{}, 1), // This needs to be 1-buffered so that we queue a pull if we're busy when it comes.
|
||||
|
||||
errorsMut: sync.NewMutex(),
|
||||
|
||||
doInSyncChan: make(chan syncRequest),
|
||||
|
||||
forcedRescanRequested: make(chan struct{}, 1),
|
||||
forcedRescanPaths: make(map[string]struct{}),
|
||||
forcedRescanPathsMut: sync.NewMutex(),
|
||||
|
||||
watchCancel: func() {},
|
||||
restartWatchChan: make(chan struct{}, 1),
|
||||
watchMut: sync.NewMutex(),
|
||||
|
||||
versioner: ver,
|
||||
}
|
||||
@@ -143,7 +143,7 @@ func newFolder(model *model, ignores *ignore.Matcher, cfg config.FolderConfigura
|
||||
|
||||
registerFolderMetrics(f.ID)
|
||||
|
||||
return f
|
||||
return &f
|
||||
}
|
||||
|
||||
func (f *folder) Serve(ctx context.Context) error {
|
||||
@@ -440,7 +440,7 @@ func (f *folder) pull() (success bool, err error) {
|
||||
|
||||
// Pulling failed, try again later.
|
||||
delay := f.pullPause + time.Since(startTime)
|
||||
l.Infof("Folder %v isn't making sync progress - retrying in %v.", f.Description(), stringutil.NiceDurationString(delay))
|
||||
f.sl.Info("Folder failed to sync, will be retried", slog.String("wait", stringutil.NiceDurationString(delay)))
|
||||
f.pullFailTimer.Reset(delay)
|
||||
|
||||
return false, err
|
||||
@@ -948,11 +948,11 @@ func (f *folder) scanTimerFired() error {
|
||||
select {
|
||||
case <-f.initialScanFinished:
|
||||
default:
|
||||
status := "Completed"
|
||||
if err != nil {
|
||||
status = "Failed"
|
||||
f.sl.Error("Failed initial scan", slogutil.Error(err))
|
||||
} else {
|
||||
f.sl.Info("Competed initial scan")
|
||||
}
|
||||
l.Infoln(status, "initial scan of", f.Type.String(), "folder", f.Description())
|
||||
close(f.initialScanFinished)
|
||||
}
|
||||
|
||||
@@ -973,7 +973,7 @@ func (f *folder) versionCleanupTimerFired() {
|
||||
f.setState(FolderCleaning)
|
||||
|
||||
if err := f.versioner.Clean(f.ctx); err != nil {
|
||||
l.Infoln("Failed to clean versions in %s: %v", f.Description(), err)
|
||||
f.sl.Warn("Failed to clean versions", slogutil.Error(err))
|
||||
}
|
||||
|
||||
f.versionCleanupTimer.Reset(f.versionCleanupInterval)
|
||||
@@ -1084,7 +1084,7 @@ func (f *folder) monitorWatch(ctx context.Context) {
|
||||
var errOutside *fs.WatchEventOutsideRootError
|
||||
if errors.As(err, &errOutside) {
|
||||
if !warnedOutside {
|
||||
l.Warnln(err)
|
||||
slog.WarnContext(ctx, err.Error()) //nolint:sloglint
|
||||
warnedOutside = true
|
||||
}
|
||||
f.evLogger.Log(events.Failure, "watching for changes encountered an event outside of the filesystem root")
|
||||
@@ -1099,7 +1099,7 @@ func (f *folder) monitorWatch(ctx context.Context) {
|
||||
f.warnedKqueue = true
|
||||
summarySub.Unsubscribe()
|
||||
summaryChan = nil
|
||||
l.Warnf("Filesystem watching (kqueue) is enabled on %v with a lot of files/directories, and that requires a lot of resources and might slow down your system significantly", f.Description())
|
||||
slog.WarnContext(ctx, "Filesystem watching (kqueue) is enabled with a lot of files/directories, which requires a lot of resources and might slow down your system significantly", f.LogAttr())
|
||||
}
|
||||
case <-ctx.Done():
|
||||
aggrCancel() // for good measure and keeping the linters happy
|
||||
@@ -1130,12 +1130,11 @@ func (f *folder) setWatchError(err error, nextTryIn time.Duration) {
|
||||
if err == nil {
|
||||
return
|
||||
}
|
||||
msg := fmt.Sprintf("Error while trying to start filesystem watcher for folder %s, trying again in %v: %v", f.Description(), nextTryIn, err)
|
||||
if prevErr != err { //nolint:errorlint
|
||||
l.Infof(msg)
|
||||
return
|
||||
f.sl.Warn("Failed to start filesystem watcher", slog.String("wait", nextTryIn.String()), slogutil.Error(err))
|
||||
} else {
|
||||
f.sl.Debug("Failed to start filesystem watcher", slog.String("wait", nextTryIn.String()), slogutil.Error(err))
|
||||
}
|
||||
l.Debugf(msg)
|
||||
}
|
||||
|
||||
// scanOnWatchErr schedules a full scan immediately if an error occurred while watching.
|
||||
@@ -1162,12 +1161,12 @@ func (f *folder) setError(err error) {
|
||||
|
||||
if err != nil {
|
||||
if oldErr == nil {
|
||||
l.Warnf("Error on folder %s: %v", f.Description(), err)
|
||||
f.sl.Warn("Error on folder", slogutil.Error(err))
|
||||
} else {
|
||||
l.Infof("Error on folder %s changed: %q -> %q", f.Description(), oldErr, err)
|
||||
f.sl.Info("Folder error changed", slogutil.Error(err), slog.Any("previously", oldErr))
|
||||
}
|
||||
} else {
|
||||
l.Infoln("Cleared error on folder", f.Description())
|
||||
f.sl.Info("Folder error cleared")
|
||||
f.SchedulePull()
|
||||
}
|
||||
|
||||
@@ -1195,7 +1194,7 @@ func (f *folder) String() string {
|
||||
|
||||
func (f *folder) newScanError(path string, err error) {
|
||||
f.errorsMut.Lock()
|
||||
l.Infof("Scanner (folder %s, item %q): %v", f.Description(), path, err)
|
||||
f.sl.Warn("Failed to scan", slogutil.FilePath(path), slogutil.Error(err))
|
||||
f.scanErrors = append(f.scanErrors, FileError{
|
||||
Err: err.Error(),
|
||||
Path: path,
|
||||
|
||||
Reference in New Issue
Block a user