1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
|
/*
*
* Copyright 2018 gRPC authors.
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*
*/
package health
import (
"context"
"fmt"
"io"
"time"
"google.golang.org/grpc"
"google.golang.org/grpc/codes"
"google.golang.org/grpc/connectivity"
healthpb "google.golang.org/grpc/health/grpc_health_v1"
"google.golang.org/grpc/internal"
"google.golang.org/grpc/internal/backoff"
"google.golang.org/grpc/status"
)
var (
backoffStrategy = backoff.DefaultExponential
backoffFunc = func(ctx context.Context, retries int) bool {
d := backoffStrategy.Backoff(retries)
timer := time.NewTimer(d)
select {
case <-timer.C:
return true
case <-ctx.Done():
timer.Stop()
return false
}
}
)
func init() {
internal.HealthCheckFunc = clientHealthCheck
}
const healthCheckMethod = "/grpc.health.v1.Health/Watch"
// This function implements the protocol defined at:
// https://github.com/grpc/grpc/blob/master/doc/health-checking.md
func clientHealthCheck(ctx context.Context, newStream func(string) (interface{}, error), setConnectivityState func(connectivity.State, error), service string) error {
tryCnt := 0
retryConnection:
for {
// Backs off if the connection has failed in some way without receiving a message in the previous retry.
if tryCnt > 0 && !backoffFunc(ctx, tryCnt-1) {
return nil
}
tryCnt++
if ctx.Err() != nil {
return nil
}
setConnectivityState(connectivity.Connecting, nil)
rawS, err := newStream(healthCheckMethod)
if err != nil {
continue retryConnection
}
s, ok := rawS.(grpc.ClientStream)
// Ideally, this should never happen. But if it happens, the server is marked as healthy for LBing purposes.
if !ok {
setConnectivityState(connectivity.Ready, nil)
return fmt.Errorf("newStream returned %v (type %T); want grpc.ClientStream", rawS, rawS)
}
if err = s.SendMsg(&healthpb.HealthCheckRequest{Service: service}); err != nil && err != io.EOF {
// Stream should have been closed, so we can safely continue to create a new stream.
continue retryConnection
}
s.CloseSend()
resp := new(healthpb.HealthCheckResponse)
for {
err = s.RecvMsg(resp)
// Reports healthy for the LBing purposes if health check is not implemented in the server.
if status.Code(err) == codes.Unimplemented {
setConnectivityState(connectivity.Ready, nil)
return err
}
// Reports unhealthy if server's Watch method gives an error other than UNIMPLEMENTED.
if err != nil {
setConnectivityState(connectivity.TransientFailure, fmt.Errorf("connection active but received health check RPC error: %v", err))
continue retryConnection
}
// As a message has been received, removes the need for backoff for the next retry by resetting the try count.
tryCnt = 0
if resp.Status == healthpb.HealthCheckResponse_SERVING {
setConnectivityState(connectivity.Ready, nil)
} else {
setConnectivityState(connectivity.TransientFailure, fmt.Errorf("connection active but health check failed. status=%s", resp.Status))
}
}
}
}
|
