mirror of
https://github.com/coredns/coredns.git
synced 2025-11-02 02:03:13 -05:00
plugin/proxy: decrease health timeouts (#1107)
Turn down the timeouts and numbers a bit: FailTimeout 10s -> 5s Future 60s -> 12s TryDuration 60s -> 16s The timeout for decrementing the fails in a host: 10s -> 2s And the biggest change: don't set fails when the error is Timeout(), meaning we loop for a bit and may try the same server again, but we don't mark our upstream as bad, see comments in proxy.go. Testing this with "ANY isc.org" and "MX miek.nl" we see: ~~~ ::1 - [24/Sep/2017:08:06:17 +0100] "ANY IN isc.org. udp 37 false 4096" SERVFAIL qr,rd 37 10.001621221s 24/Sep/2017:08:06:17 +0100 [ERROR 0 isc.org. ANY] unreachable backend: read udp 192.168.1.148:37420->8.8.8.8:53: i/o timeout ::1 - [24/Sep/2017:08:06:17 +0100] "MX IN miek.nl. udp 37 false 4096" NOERROR qr,rd,ra,ad 170 35.957284ms 127.0.0.1 - [24/Sep/2017:08:06:18 +0100] "ANY IN isc.org. udp 37 false 4096" SERVFAIL qr,rd 37 10.002051726s 24/Sep/2017:08:06:18 +0100 [ERROR 0 isc.org. ANY] unreachable backend: read udp 192.168.1.148:54901->8.8.8.8:53: i/o timeout ::1 - [24/Sep/2017:08:06:19 +0100] "MX IN miek.nl. udp 37 false 4096" NOERROR qr,rd,ra,ad 170 56.848416ms 127.0.0.1 - [24/Sep/2017:08:06:21 +0100] "MX IN miek.nl. udp 37 false 4096" NOERROR qr,rd,ra,ad 170 48.118349ms ::1 - [24/Sep/2017:08:06:21 +0100] "MX IN miek.nl. udp 37 false 4096" NOERROR qr,rd,ra,ad 170 1.055172915s ~~~ So the ANY isc.org queries show up twice, because we retry internally - this is I think WAI. The `miek.nl MX` queries are just processed normally as no backend is marked as unreachable. May fix #1035 #486
This commit is contained in:
@@ -5,6 +5,7 @@ package proxy
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"net"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
|
||||
@@ -26,9 +27,9 @@ func NewLookupWithOption(hosts []string, opts Options) Proxy {
|
||||
upstream := &staticUpstream{
|
||||
from: ".",
|
||||
HealthCheck: healthcheck.HealthCheck{
|
||||
FailTimeout: 10 * time.Second,
|
||||
MaxFails: 3, // TODO(miek): disable error checking for simple lookups?
|
||||
Future: 60 * time.Second,
|
||||
FailTimeout: 5 * time.Second,
|
||||
MaxFails: 3,
|
||||
Future: 12 * time.Second,
|
||||
},
|
||||
ex: newDNSExWithOption(opts),
|
||||
}
|
||||
@@ -85,7 +86,7 @@ func (p Proxy) lookup(state request.Request) (*dns.Msg, error) {
|
||||
}
|
||||
|
||||
// duplicated from proxy.go, but with a twist, we don't write the
|
||||
// reply back to the client, we return it and there is no monitoring.
|
||||
// reply back to the client, we return it and there is no monitoring to update here.
|
||||
|
||||
atomic.AddInt64(&host.Conns, 1)
|
||||
|
||||
@@ -96,11 +97,20 @@ func (p Proxy) lookup(state request.Request) (*dns.Msg, error) {
|
||||
if backendErr == nil {
|
||||
return reply, nil
|
||||
}
|
||||
|
||||
if oe, ok := backendErr.(*net.OpError); ok {
|
||||
if oe.Timeout() { // see proxy.go for docs.
|
||||
continue
|
||||
}
|
||||
}
|
||||
|
||||
timeout := host.FailTimeout
|
||||
if timeout == 0 {
|
||||
timeout = 10 * time.Second
|
||||
timeout = 2 * time.Second
|
||||
}
|
||||
|
||||
atomic.AddInt32(&host.Fails, 1)
|
||||
|
||||
go func(host *healthcheck.UpstreamHost, timeout time.Duration) {
|
||||
time.Sleep(timeout)
|
||||
atomic.AddInt32(&host.Fails, -1)
|
||||
|
||||
Reference in New Issue
Block a user