[#307] add package trace, integrate it with logging, and adopt it throughout zrepl

package trace:

- introduce the concept of tasks and spans, tracked as linked list within ctx
    - see package-level docs for an overview of the concepts
    - **main feature 1**: unique stack of task and span IDs
        - makes it easy to follow a series of log entries in concurrent code
    - **main feature 2**: ability to produce a chrome://tracing-compatible trace file
        - either via an env variable or a `zrepl pprof` subcommand
        - this is not a CPU profile, we already have go pprof for that
        - but it is very useful to visually inspect where the
          replication / snapshotter / pruner spends its time
          ( fixes #307 )

usage in package daemon/logging:

- goal: every log entry should have a trace field with the ID stack from package trace

- make `logging.GetLogger(ctx, Subsys)` the authoritative `logger.Logger` factory function
    - the context carries a linked list of injected fields which
      `logging.GetLogger` adds to the logger it returns
    - `logging.GetLogger` also uses package `trace` to get the
      task-and-span-stack and injects it into the returned logger's fields
This commit is contained in:
Christian Schwarz
2020-04-11 15:49:41 +02:00
parent bcb5965617
commit 10a14a8c50
75 changed files with 1934 additions and 462 deletions
+9 -12
View File
@@ -12,6 +12,7 @@ import (
"github.com/prometheus/client_golang/prometheus"
"github.com/zrepl/zrepl/config"
"github.com/zrepl/zrepl/daemon/logging"
"github.com/zrepl/zrepl/logger"
"github.com/zrepl/zrepl/pruning"
"github.com/zrepl/zrepl/replication/logic/pdu"
@@ -35,17 +36,13 @@ type Logger = logger.Logger
type contextKey int
const contextKeyLogger contextKey = 0
func WithLogger(ctx context.Context, log Logger) context.Context {
return context.WithValue(ctx, contextKeyLogger, log)
}
const (
contextKeyPruneSide contextKey = 1 + iota
)
func GetLogger(ctx context.Context) Logger {
if l, ok := ctx.Value(contextKeyLogger).(Logger); ok {
return l
}
return logger.NewNullLogger()
pruneSide := ctx.Value(contextKeyPruneSide).(string)
return logging.GetLogger(ctx, logging.SubsysPruning).WithField("prune_side", pruneSide)
}
type args struct {
@@ -138,7 +135,7 @@ func NewPrunerFactory(in config.PruningSenderReceiver, promPruneSecs *prometheus
func (f *PrunerFactory) BuildSenderPruner(ctx context.Context, target Target, receiver History) *Pruner {
p := &Pruner{
args: args{
WithLogger(ctx, GetLogger(ctx).WithField("prune_side", "sender")),
context.WithValue(ctx, contextKeyPruneSide, "sender"),
target,
receiver,
f.senderRules,
@@ -154,7 +151,7 @@ func (f *PrunerFactory) BuildSenderPruner(ctx context.Context, target Target, re
func (f *PrunerFactory) BuildReceiverPruner(ctx context.Context, target Target, receiver History) *Pruner {
p := &Pruner{
args: args{
WithLogger(ctx, GetLogger(ctx).WithField("prune_side", "receiver")),
context.WithValue(ctx, contextKeyPruneSide, "receiver"),
target,
receiver,
f.receiverRules,
@@ -170,7 +167,7 @@ func (f *PrunerFactory) BuildReceiverPruner(ctx context.Context, target Target,
func (f *LocalPrunerFactory) BuildLocalPruner(ctx context.Context, target Target, receiver History) *Pruner {
p := &Pruner{
args: args{
ctx,
context.WithValue(ctx, contextKeyPruneSide, "local"),
target,
receiver,
f.keepRules,