bandwidth limiting: fix crash with SnapJob

zrepl daemon panics when the snap job triggers

fixup for f5f269bfd5 (bandwidth limiting)
fixes #521

Oct 01 16:14:56 cstp zrepl[56563]: panic: invalid config`BandwidthLimit` field invalid: BucketCapacity must not be zero
Oct 01 16:14:56 cstp zrepl[56563]:         panic: end span: span still has active child spans
Oct 01 16:14:56 cstp zrepl[56563]: goroutine 38 [running]:
Oct 01 16:14:56 cstp zrepl[56563]: github.com/zrepl/zrepl/daemon/logging/trace.WithSpan.func2()
Oct 01 16:14:56 cstp zrepl[56563]:         /home/cs/zrepl/zrepl/daemon/logging/trace/trace.go:341 +0x2ea
Oct 01 16:14:56 cstp zrepl[56563]: github.com/zrepl/zrepl/daemon/logging/trace.WithTaskAndSpan.func1()
Oct 01 16:14:56 cstp zrepl[56563]:         /home/cs/zrepl/zrepl/daemon/logging/trace/trace_convenience.go:40 +0x2e
Oct 01 16:14:56 cstp zrepl[56563]: panic(0xcee9c0, 0xc000676730)
Oct 01 16:14:56 cstp zrepl[56563]:         /home/cs/go1.16.6/src/runtime/panic.go:965 +0x1b9
Oct 01 16:14:56 cstp zrepl[56563]: github.com/zrepl/zrepl/endpoint.NewSender(0xf5bbc0, 0xc0003840c0, 0xc0000b2c90, 0x4, 0xc0002c5958, 0x0, 0x0, 0x0, 0xc000068cf8)
Oct 01 16:14:56 cstp zrepl[56563]:         /home/cs/zrepl/zrepl/endpoint/endpoint.go:68 +0x1ec
Oct 01 16:14:56 cstp zrepl[56563]: github.com/zrepl/zrepl/daemon/job.(*SnapJob).doPrune(0xc00039e000, 0xf6e3b8, 0xc0006541b0)
Oct 01 16:14:56 cstp zrepl[56563]:         /home/cs/zrepl/zrepl/daemon/job/snapjob.go:179 +0x198
Oct 01 16:14:56 cstp zrepl[56563]: github.com/zrepl/zrepl/daemon/job.(*SnapJob).Run(0xc00039e000, 0xf6e3b8, 0xc0001d83c0)
Oct 01 16:14:56 cstp zrepl[56563]:         /home/cs/zrepl/zrepl/daemon/job/snapjob.go:127 +0x329
Oct 01 16:14:56 cstp zrepl[56563]: github.com/zrepl/zrepl/daemon.(*jobs).start.func1(0xc0006a4100, 0xf6e3b8, 0xc00022a0f0, 0xf72d18, 0xc00039e000)
Oct 01 16:14:56 cstp zrepl[56563]:         /home/cs/zrepl/zrepl/daemon/daemon.go:255 +0x15b
Oct 01 16:14:56 cstp zrepl[56563]: created by github.com/zrepl/zrepl/daemon.(*jobs).start
Oct 01 16:14:56 cstp zrepl[56563]:         /home/cs/zrepl/zrepl/daemon/daemon.go:251 +0x425
Oct 01 16:14:56 cstp systemd[1]: zrepl.service: Main process exited, code=exited, status=2/INVALIDARGUMENT
Oct 01 16:14:56 cstp systemd[1]: zrepl.service: Failed with result 'exit-code'.
This commit is contained in:
Christian Schwarz 2021-10-04 08:05:05 +02:00
parent 2c9fcd7c14
commit 845195b7ed

View File

@ -10,6 +10,7 @@ import (
"github.com/prometheus/client_golang/prometheus"
"github.com/zrepl/zrepl/daemon/logging/trace"
"github.com/zrepl/zrepl/util/bandwidthlimit"
"github.com/zrepl/zrepl/util/nodefault"
"github.com/zrepl/zrepl/config"
@ -179,8 +180,11 @@ func (j *SnapJob) doPrune(ctx context.Context) {
sender := endpoint.NewSender(endpoint.SenderConfig{
JobID: j.name,
FSF: j.fsfilter,
// FIXME encryption setting is irrelevant for SnapJob because the endpoint is only used as pruner.Target
// FIXME the following config fields are irrelevant for SnapJob
// because the endpoint is only used as pruner.Target.
// However, the implementation requires them to be set.
Encrypt: &nodefault.Bool{B: true},
BandwidthLimit: bandwidthlimit.NoLimitConfig(),
})
j.prunerMtx.Lock()
j.pruner = j.prunerFactory.BuildLocalPruner(ctx, sender, alwaysUpToDateReplicationCursorHistory{sender})