Add grpc prometheus metrics

This provideds generic grpc metrics via prometheus

Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
This commit is contained in:
Michael Crosby 2017-03-14 16:16:49 -07:00
parent a85c28d248
commit f9212348e4
11 changed files with 921 additions and 2 deletions

View file

@ -6,6 +6,7 @@ import (
_ "github.com/docker/containerd/services/content"
_ "github.com/docker/containerd/services/execution"
_ "github.com/docker/containerd/services/healthcheck"
_ "github.com/docker/containerd/services/metrics"
_ "github.com/docker/containerd/snapshot/btrfs"
_ "github.com/docker/containerd/snapshot/overlay"
)

View file

@ -11,6 +11,7 @@ import (
"syscall"
"time"
grpc_prometheus "github.com/grpc-ecosystem/go-grpc-prometheus"
gocontext "golang.org/x/net/context"
"google.golang.org/grpc"
@ -296,7 +297,10 @@ func loadSnapshotter(store *content.Store) (snapshot.Snapshotter, error) {
}
func newGRPCServer() *grpc.Server {
s := grpc.NewServer(grpc.UnaryInterceptor(interceptor))
s := grpc.NewServer(
grpc.UnaryInterceptor(interceptor),
grpc.StreamInterceptor(grpc_prometheus.StreamServerInterceptor),
)
return s
}
@ -365,7 +369,7 @@ func interceptor(ctx gocontext.Context,
default:
fmt.Printf("unknown GRPC server type: %#v\n", info.Server)
}
return handler(ctx, req)
return grpc_prometheus.UnaryServerInterceptor(ctx, req, info, handler)
}
func handleSignals(signals chan os.Signal, server *grpc.Server) error {

View file

@ -0,0 +1,26 @@
package metrics
import (
"github.com/docker/containerd/plugin"
grpc_prometheus "github.com/grpc-ecosystem/go-grpc-prometheus"
"google.golang.org/grpc"
)
func init() {
plugin.Register("metrics-grpc", &plugin.Registration{
Type: plugin.GRPCPlugin,
Init: New,
})
}
func New(_ *plugin.InitContext) (interface{}, error) {
return &Service{}, nil
}
type Service struct {
}
func (s *Service) Register(server *grpc.Server) error {
grpc_prometheus.Register(server)
return nil
}

View file

@ -30,3 +30,4 @@ github.com/opencontainers/image-spec a431dbcf6a74fca2e0e040b819a836dbe3fb23ca
github.com/stevvooe/continuity 1530f13d23b34e2ccaf33881fefecc7e28e3577b
golang.org/x/sync 450f422ab23cf9881c94e2db30cac0eb1b7cf80c
github.com/BurntSushi/toml v0.2.0-21-g9906417
github.com/grpc-ecosystem/go-grpc-prometheus 6b7015e65d366bf3f19b2b2a000a831940f0f7e0

View file

@ -0,0 +1,201 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
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.

View file

@ -0,0 +1,245 @@
# Go gRPC Interceptors for Prometheus monitoring
[![Travis Build](https://travis-ci.org/grpc-ecosystem/go-grpc-prometheus.svg)](https://travis-ci.org/grpc-ecosystem/go-grpc-prometheus)
[![Go Report Card](https://goreportcard.com/badge/github.com/grpc-ecosystem/go-grpc-prometheus)](http://goreportcard.com/report/grpc-ecosystem/go-grpc-prometheus)
[![GoDoc](http://img.shields.io/badge/GoDoc-Reference-blue.svg)](https://godoc.org/github.com/grpc-ecosystem/go-grpc-prometheus)
[![Apache 2.0 License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE)
[Prometheus](https://prometheus.io/) monitoring for your [gRPC Go](https://github.com/grpc/grpc-go) servers and clients.
A sister implementation for [gRPC Java](https://github.com/grpc/grpc-java) (same metrics, same semantics) is in [grpc-ecosystem/java-grpc-prometheus](https://github.com/grpc-ecosystem/java-grpc-prometheus).
## Interceptors
[gRPC Go](https://github.com/grpc/grpc-go) recently acquired support for Interceptors, i.e. middleware that is executed
by a gRPC Server before the request is passed onto the user's application logic. It is a perfect way to implement
common patterns: auth, logging and... monitoring.
To use Interceptors in chains, please see [`go-grpc-middleware`](https://github.com/mwitkow/go-grpc-middleware).
## Usage
There are two types of interceptors: client-side and server-side. This package provides monitoring Interceptors for both.
### Server-side
```go
import "github.com/grpc-ecosystem/go-grpc-prometheus"
...
// Initialize your gRPC server's interceptor.
myServer := grpc.NewServer(
grpc.StreamInterceptor(grpc_prometheus.StreamServerInterceptor),
grpc.UnaryInterceptor(grpc_prometheus.UnaryServerInterceptor),
)
// Register your gRPC service implementations.
myservice.RegisterMyServiceServer(s.server, &myServiceImpl{})
// After all your registrations, make sure all of the Prometheus metrics are initialized.
grpc_prometheus.Register(myServer)
// Register Prometheus metrics handler.
http.Handle("/metrics", prometheus.Handler())
...
```
### Client-side
```go
import "github.com/grpc-ecosystem/go-grpc-prometheus"
...
clientConn, err = grpc.Dial(
address,
grpc.WithUnaryInterceptor(UnaryClientInterceptor),
grpc.WithStreamInterceptor(StreamClientInterceptor)
)
client = pb_testproto.NewTestServiceClient(clientConn)
resp, err := client.PingEmpty(s.ctx, &myservice.Request{Msg: "hello"})
...
```
# Metrics
## Labels
All server-side metrics start with `grpc_server` as Prometheus subsystem name. All client-side metrics start with `grpc_client`. Both of them have mirror-concepts. Similarly all methods
contain the same rich labels:
* `grpc_service` - the [gRPC service](http://www.grpc.io/docs/#defining-a-service) name, which is the combination of protobuf `package` and
the `grpc_service` section name. E.g. for `package = mwitkow.testproto` and
`service TestService` the label will be `grpc_service="mwitkow.testproto.TestService"`
* `grpc_method` - the name of the method called on the gRPC service. E.g.
`grpc_method="Ping"`
* `grpc_type` - the gRPC [type of request](http://www.grpc.io/docs/guides/concepts.html#rpc-life-cycle).
Differentiating between the two is important especially for latency measurements.
- `unary` is single request, single response RPC
- `client_stream` is a multi-request, single response RPC
- `server_stream` is a single request, multi-response RPC
- `bidi_stream` is a multi-request, multi-response RPC
Additionally for completed RPCs, the following labels are used:
* `grpc_code` - the human-readable [gRPC status code](https://github.com/grpc/grpc-go/blob/master/codes/codes.go).
The list of all statuses is to long, but here are some common ones:
- `OK` - means the RPC was successful
- `IllegalArgument` - RPC contained bad values
- `Internal` - server-side error not disclosed to the clients
## Counters
The counters and their up to date documentation is in [server_reporter.go](server_reporter.go) and [client_reporter.go](client_reporter.go)
the respective Prometheus handler (usually `/metrics`).
For the purpose of this documentation we will only discuss `grpc_server` metrics. The `grpc_client` ones contain mirror concepts.
For simplicity, let's assume we're tracking a single server-side RPC call of [`mwitkow.testproto.TestService`](examples/testproto/test.proto),
calling the method `PingList`. The call succeeds and returns 20 messages in the stream.
First, immediately after the server receives the call it will increment the
`grpc_server_started_total` and start the handling time clock (if histograms are enabled).
```jsoniq
grpc_server_started_total{grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream"} 1
```
Then the user logic gets invoked. It receives one message from the client containing the request
(it's a `server_stream`):
```jsoniq
grpc_server_msg_received_total{grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream"} 1
```
The user logic may return an error, or send multiple messages back to the client. In this case, on
each of the 20 messages sent back, a counter will be incremented:
```jsoniq
grpc_server_msg_sent_total{grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream"} 20
```
After the call completes, it's status (`OK` or other [gRPC status code](https://github.com/grpc/grpc-go/blob/master/codes/codes.go))
and the relevant call labels increment the `grpc_server_handled_total` counter.
```jsoniq
grpc_server_handled_total{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream"} 1
```
## Histograms
[Prometheus histograms](https://prometheus.io/docs/concepts/metric_types/#histogram) are a great way
to measure latency distributions of your RPCs. However since it is bad practice to have metrics
of [high cardinality](https://prometheus.io/docs/practices/instrumentation/#do-not-overuse-labels))
the latency monitoring metrics are disabled by default. To enable them please call the following
in your server initialization code:
```jsoniq
grpc_prometheus.EnableHandlingTimeHistogram()
```
After the call completes, it's handling time will be recorded in a [Prometheus histogram](https://prometheus.io/docs/concepts/metric_types/#histogram)
variable `grpc_server_handling_seconds`. It contains three sub-metrics:
* `grpc_server_handling_seconds_count` - the count of all completed RPCs by status and method
* `grpc_server_handling_seconds_sum` - cumulative time of RPCs by status and method, useful for
calculating average handling times
* `grpc_server_handling_seconds_bucket` - contains the counts of RPCs by status and method in respective
handling-time buckets. These buckets can be used by Prometheus to estimate SLAs (see [here](https://prometheus.io/docs/practices/histograms/))
The counter values will look as follows:
```jsoniq
grpc_server_handling_seconds_bucket{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream",le="0.005"} 1
grpc_server_handling_seconds_bucket{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream",le="0.01"} 1
grpc_server_handling_seconds_bucket{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream",le="0.025"} 1
grpc_server_handling_seconds_bucket{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream",le="0.05"} 1
grpc_server_handling_seconds_bucket{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream",le="0.1"} 1
grpc_server_handling_seconds_bucket{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream",le="0.25"} 1
grpc_server_handling_seconds_bucket{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream",le="0.5"} 1
grpc_server_handling_seconds_bucket{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream",le="1"} 1
grpc_server_handling_seconds_bucket{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream",le="2.5"} 1
grpc_server_handling_seconds_bucket{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream",le="5"} 1
grpc_server_handling_seconds_bucket{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream",le="10"} 1
grpc_server_handling_seconds_bucket{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream",le="+Inf"} 1
grpc_server_handling_seconds_sum{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream"} 0.0003866430000000001
grpc_server_handling_seconds_count{grpc_code="OK",grpc_method="PingList",grpc_service="mwitkow.testproto.TestService",grpc_type="server_stream"} 1
```
## Useful query examples
Prometheus philosophy is to provide the most detailed metrics possible to the monitoring system, and
let the aggregations be handled there. The verbosity of above metrics make it possible to have that
flexibility. Here's a couple of useful monitoring queries:
### request inbound rate
```jsoniq
sum(rate(grpc_server_started_total{job="foo"}[1m])) by (grpc_service)
```
For `job="foo"` (common label to differentiate between Prometheus monitoring targets), calculate the
rate of requests per second (1 minute window) for each gRPC `grpc_service` that the job has. Please note
how the `grpc_method` is being omitted here: all methods of a given gRPC service will be summed together.
### unary request error rate
```jsoniq
sum(rate(grpc_server_handled_total{job="foo",grpc_type="unary",grpc_code!="OK"}[1m])) by (grpc_service)
```
For `job="foo"`, calculate the per-`grpc_service` rate of `unary` (1:1) RPCs that failed, i.e. the
ones that didn't finish with `OK` code.
### unary request error percentage
```jsoniq
sum(rate(grpc_server_handled_total{job="foo",grpc_type="unary",grpc_code!="OK"}[1m])) by (grpc_service)
/
sum(rate(grpc_server_started_total{job="foo",grpc_type="unary"}[1m])) by (grpc_service)
* 100.0
```
For `job="foo"`, calculate the percentage of failed requests by service. It's easy to notice that
this is a combination of the two above examples. This is an example of a query you would like to
[alert on](https://prometheus.io/docs/alerting/rules/) in your system for SLA violations, e.g.
"no more than 1% requests should fail".
### average response stream size
```jsoniq
sum(rate(grpc_server_msg_sent_total{job="foo",grpc_type="server_stream"}[10m])) by (grpc_service)
/
sum(rate(grpc_server_started_total{job="foo",grpc_type="server_stream"}[10m])) by (grpc_service)
```
For `job="foo"` what is the `grpc_service`-wide `10m` average of messages returned for all `
server_stream` RPCs. This allows you to track the stream sizes returned by your system, e.g. allows
you to track when clients started to send "wide" queries that ret
Note the divisor is the number of started RPCs, in order to account for in-flight requests.
### 99%-tile latency of unary requests
```jsoniq
histogram_quantile(0.99,
sum(rate(grpc_server_handling_seconds_bucket{job="foo",grpc_type="unary"}[5m])) by (grpc_service,le)
)
```
For `job="foo"`, returns an 99%-tile [quantile estimation](https://prometheus.io/docs/practices/histograms/#quantiles)
of the handling time of RPCs per service. Please note the `5m` rate, this means that the quantile
estimation will take samples in a rolling `5m` window. When combined with other quantiles
(e.g. 50%, 90%), this query gives you tremendous insight into the responsiveness of your system
(e.g. impact of caching).
### percentage of slow unary queries (>250ms)
```jsoniq
100.0 - (
sum(rate(grpc_server_handling_seconds_bucket{job="foo",grpc_type="unary",le="0.25"}[5m])) by (grpc_service)
/
sum(rate(grpc_server_handling_seconds_count{job="foo",grpc_type="unary"}[5m])) by (grpc_service)
) * 100.0
```
For `job="foo"` calculate the by-`grpc_service` fraction of slow requests that took longer than `0.25`
seconds. This query is relatively complex, since the Prometheus aggregations use `le` (less or equal)
buckets, meaning that counting "fast" requests fractions is easier. However, simple maths helps.
This is an example of a query you would like to alert on in your system for SLA violations,
e.g. "less than 1% of requests are slower than 250ms".
## Status
This code has been used since August 2015 as the basis for monitoring of *production* gRPC micro services at [Improbable](https://improbable.io).
## License
`go-grpc-prometheus` is released under the Apache 2.0 license. See the [LICENSE](LICENSE) file for details.

View file

@ -0,0 +1,72 @@
// Copyright 2016 Michal Witkowski. All Rights Reserved.
// See LICENSE for licensing terms.
// gRPC Prometheus monitoring interceptors for client-side gRPC.
package grpc_prometheus
import (
"io"
"golang.org/x/net/context"
"google.golang.org/grpc"
"google.golang.org/grpc/codes"
)
// UnaryClientInterceptor is a gRPC client-side interceptor that provides Prometheus monitoring for Unary RPCs.
func UnaryClientInterceptor(ctx context.Context, method string, req, reply interface{}, cc *grpc.ClientConn, invoker grpc.UnaryInvoker, opts ...grpc.CallOption) error {
monitor := newClientReporter(Unary, method)
monitor.SentMessage()
err := invoker(ctx, method, req, reply, cc, opts...)
if err != nil {
monitor.ReceivedMessage()
}
monitor.Handled(grpc.Code(err))
return err
}
// StreamServerInterceptor is a gRPC client-side interceptor that provides Prometheus monitoring for Streaming RPCs.
func StreamClientInterceptor(ctx context.Context, desc *grpc.StreamDesc, cc *grpc.ClientConn, method string, streamer grpc.Streamer, opts ...grpc.CallOption) (grpc.ClientStream, error) {
monitor := newClientReporter(clientStreamType(desc), method)
clientStream, err := streamer(ctx, desc, cc, method, opts...)
if err != nil {
monitor.Handled(grpc.Code(err))
return nil, err
}
return &monitoredClientStream{clientStream, monitor}, nil
}
func clientStreamType(desc *grpc.StreamDesc) grpcType {
if desc.ClientStreams && !desc.ServerStreams {
return ClientStream
} else if !desc.ClientStreams && desc.ServerStreams {
return ServerStream
}
return BidiStream
}
// monitoredClientStream wraps grpc.ClientStream allowing each Sent/Recv of message to increment counters.
type monitoredClientStream struct {
grpc.ClientStream
monitor *clientReporter
}
func (s *monitoredClientStream) SendMsg(m interface{}) error {
err := s.ClientStream.SendMsg(m)
if err == nil {
s.monitor.SentMessage()
}
return err
}
func (s *monitoredClientStream) RecvMsg(m interface{}) error {
err := s.ClientStream.RecvMsg(m)
if err == nil {
s.monitor.ReceivedMessage()
} else if err == io.EOF {
s.monitor.Handled(codes.OK)
} else {
s.monitor.Handled(grpc.Code(err))
}
return err
}

View file

@ -0,0 +1,111 @@
// Copyright 2016 Michal Witkowski. All Rights Reserved.
// See LICENSE for licensing terms.
package grpc_prometheus
import (
"time"
"google.golang.org/grpc/codes"
prom "github.com/prometheus/client_golang/prometheus"
)
var (
clientStartedCounter = prom.NewCounterVec(
prom.CounterOpts{
Namespace: "grpc",
Subsystem: "client",
Name: "started_total",
Help: "Total number of RPCs started on the client.",
}, []string{"grpc_type", "grpc_service", "grpc_method"})
clientHandledCounter = prom.NewCounterVec(
prom.CounterOpts{
Namespace: "grpc",
Subsystem: "client",
Name: "handled_total",
Help: "Total number of RPCs completed by the client, regardless of success or failure.",
}, []string{"grpc_type", "grpc_service", "grpc_method", "grpc_code"})
clientStreamMsgReceived = prom.NewCounterVec(
prom.CounterOpts{
Namespace: "grpc",
Subsystem: "client",
Name: "msg_received_total",
Help: "Total number of RPC stream messages received by the client.",
}, []string{"grpc_type", "grpc_service", "grpc_method"})
clientStreamMsgSent = prom.NewCounterVec(
prom.CounterOpts{
Namespace: "grpc",
Subsystem: "client",
Name: "msg_sent_total",
Help: "Total number of gRPC stream messages sent by the client.",
}, []string{"grpc_type", "grpc_service", "grpc_method"})
clientHandledHistogramEnabled = false
clientHandledHistogramOpts = prom.HistogramOpts{
Namespace: "grpc",
Subsystem: "client",
Name: "handling_seconds",
Help: "Histogram of response latency (seconds) of the gRPC until it is finished by the application.",
Buckets: prom.DefBuckets,
}
clientHandledHistogram *prom.HistogramVec
)
func init() {
prom.MustRegister(clientStartedCounter)
prom.MustRegister(clientHandledCounter)
prom.MustRegister(clientStreamMsgReceived)
prom.MustRegister(clientStreamMsgSent)
}
// EnableClientHandlingTimeHistogram turns on recording of handling time of RPCs.
// Histogram metrics can be very expensive for Prometheus to retain and query.
func EnableClientHandlingTimeHistogram(opts ...HistogramOption) {
for _, o := range opts {
o(&clientHandledHistogramOpts)
}
if !clientHandledHistogramEnabled {
clientHandledHistogram = prom.NewHistogramVec(
clientHandledHistogramOpts,
[]string{"grpc_type", "grpc_service", "grpc_method"},
)
prom.Register(clientHandledHistogram)
}
clientHandledHistogramEnabled = true
}
type clientReporter struct {
rpcType grpcType
serviceName string
methodName string
startTime time.Time
}
func newClientReporter(rpcType grpcType, fullMethod string) *clientReporter {
r := &clientReporter{rpcType: rpcType}
if clientHandledHistogramEnabled {
r.startTime = time.Now()
}
r.serviceName, r.methodName = splitMethodName(fullMethod)
clientStartedCounter.WithLabelValues(string(r.rpcType), r.serviceName, r.methodName).Inc()
return r
}
func (r *clientReporter) ReceivedMessage() {
clientStreamMsgReceived.WithLabelValues(string(r.rpcType), r.serviceName, r.methodName).Inc()
}
func (r *clientReporter) SentMessage() {
clientStreamMsgSent.WithLabelValues(string(r.rpcType), r.serviceName, r.methodName).Inc()
}
func (r *clientReporter) Handled(code codes.Code) {
clientHandledCounter.WithLabelValues(string(r.rpcType), r.serviceName, r.methodName, code.String()).Inc()
if clientHandledHistogramEnabled {
clientHandledHistogram.WithLabelValues(string(r.rpcType), r.serviceName, r.methodName).Observe(time.Since(r.startTime).Seconds())
}
}

View file

@ -0,0 +1,74 @@
// Copyright 2016 Michal Witkowski. All Rights Reserved.
// See LICENSE for licensing terms.
// gRPC Prometheus monitoring interceptors for server-side gRPC.
package grpc_prometheus
import (
"golang.org/x/net/context"
"google.golang.org/grpc"
)
// PreregisterServices takes a gRPC server and pre-initializes all counters to 0.
// This allows for easier monitoring in Prometheus (no missing metrics), and should be called *after* all services have
// been registered with the server.
func Register(server *grpc.Server) {
serviceInfo := server.GetServiceInfo()
for serviceName, info := range serviceInfo {
for _, mInfo := range info.Methods {
preRegisterMethod(serviceName, &mInfo)
}
}
}
// UnaryServerInterceptor is a gRPC server-side interceptor that provides Prometheus monitoring for Unary RPCs.
func UnaryServerInterceptor(ctx context.Context, req interface{}, info *grpc.UnaryServerInfo, handler grpc.UnaryHandler) (interface{}, error) {
monitor := newServerReporter(Unary, info.FullMethod)
monitor.ReceivedMessage()
resp, err := handler(ctx, req)
monitor.Handled(grpc.Code(err))
if err == nil {
monitor.SentMessage()
}
return resp, err
}
// StreamServerInterceptor is a gRPC server-side interceptor that provides Prometheus monitoring for Streaming RPCs.
func StreamServerInterceptor(srv interface{}, ss grpc.ServerStream, info *grpc.StreamServerInfo, handler grpc.StreamHandler) error {
monitor := newServerReporter(streamRpcType(info), info.FullMethod)
err := handler(srv, &monitoredServerStream{ss, monitor})
monitor.Handled(grpc.Code(err))
return err
}
func streamRpcType(info *grpc.StreamServerInfo) grpcType {
if info.IsClientStream && !info.IsServerStream {
return ClientStream
} else if !info.IsClientStream && info.IsServerStream {
return ServerStream
}
return BidiStream
}
// monitoredStream wraps grpc.ServerStream allowing each Sent/Recv of message to increment counters.
type monitoredServerStream struct {
grpc.ServerStream
monitor *serverReporter
}
func (s *monitoredServerStream) SendMsg(m interface{}) error {
err := s.ServerStream.SendMsg(m)
if err == nil {
s.monitor.SentMessage()
}
return err
}
func (s *monitoredServerStream) RecvMsg(m interface{}) error {
err := s.ServerStream.RecvMsg(m)
if err == nil {
s.monitor.ReceivedMessage()
}
return err
}

View file

@ -0,0 +1,157 @@
// Copyright 2016 Michal Witkowski. All Rights Reserved.
// See LICENSE for licensing terms.
package grpc_prometheus
import (
"time"
"google.golang.org/grpc/codes"
prom "github.com/prometheus/client_golang/prometheus"
"google.golang.org/grpc"
)
type grpcType string
const (
Unary grpcType = "unary"
ClientStream grpcType = "client_stream"
ServerStream grpcType = "server_stream"
BidiStream grpcType = "bidi_stream"
)
var (
serverStartedCounter = prom.NewCounterVec(
prom.CounterOpts{
Namespace: "grpc",
Subsystem: "server",
Name: "started_total",
Help: "Total number of RPCs started on the server.",
}, []string{"grpc_type", "grpc_service", "grpc_method"})
serverHandledCounter = prom.NewCounterVec(
prom.CounterOpts{
Namespace: "grpc",
Subsystem: "server",
Name: "handled_total",
Help: "Total number of RPCs completed on the server, regardless of success or failure.",
}, []string{"grpc_type", "grpc_service", "grpc_method", "grpc_code"})
serverStreamMsgReceived = prom.NewCounterVec(
prom.CounterOpts{
Namespace: "grpc",
Subsystem: "server",
Name: "msg_received_total",
Help: "Total number of RPC stream messages received on the server.",
}, []string{"grpc_type", "grpc_service", "grpc_method"})
serverStreamMsgSent = prom.NewCounterVec(
prom.CounterOpts{
Namespace: "grpc",
Subsystem: "server",
Name: "msg_sent_total",
Help: "Total number of gRPC stream messages sent by the server.",
}, []string{"grpc_type", "grpc_service", "grpc_method"})
serverHandledHistogramEnabled = false
serverHandledHistogramOpts = prom.HistogramOpts{
Namespace: "grpc",
Subsystem: "server",
Name: "handling_seconds",
Help: "Histogram of response latency (seconds) of gRPC that had been application-level handled by the server.",
Buckets: prom.DefBuckets,
}
serverHandledHistogram *prom.HistogramVec
)
func init() {
prom.MustRegister(serverStartedCounter)
prom.MustRegister(serverHandledCounter)
prom.MustRegister(serverStreamMsgReceived)
prom.MustRegister(serverStreamMsgSent)
}
type HistogramOption func(*prom.HistogramOpts)
// WithHistogramBuckets allows you to specify custom bucket ranges for histograms if EnableHandlingTimeHistogram is on.
func WithHistogramBuckets(buckets []float64) HistogramOption {
return func(o *prom.HistogramOpts) { o.Buckets = buckets }
}
// EnableHandlingTimeHistogram turns on recording of handling time of RPCs for server-side interceptors.
// Histogram metrics can be very expensive for Prometheus to retain and query.
func EnableHandlingTimeHistogram(opts ...HistogramOption) {
for _, o := range opts {
o(&serverHandledHistogramOpts)
}
if !serverHandledHistogramEnabled {
serverHandledHistogram = prom.NewHistogramVec(
serverHandledHistogramOpts,
[]string{"grpc_type", "grpc_service", "grpc_method"},
)
prom.Register(serverHandledHistogram)
}
serverHandledHistogramEnabled = true
}
type serverReporter struct {
rpcType grpcType
serviceName string
methodName string
startTime time.Time
}
func newServerReporter(rpcType grpcType, fullMethod string) *serverReporter {
r := &serverReporter{rpcType: rpcType}
if serverHandledHistogramEnabled {
r.startTime = time.Now()
}
r.serviceName, r.methodName = splitMethodName(fullMethod)
serverStartedCounter.WithLabelValues(string(r.rpcType), r.serviceName, r.methodName).Inc()
return r
}
func (r *serverReporter) ReceivedMessage() {
serverStreamMsgReceived.WithLabelValues(string(r.rpcType), r.serviceName, r.methodName).Inc()
}
func (r *serverReporter) SentMessage() {
serverStreamMsgSent.WithLabelValues(string(r.rpcType), r.serviceName, r.methodName).Inc()
}
func (r *serverReporter) Handled(code codes.Code) {
serverHandledCounter.WithLabelValues(string(r.rpcType), r.serviceName, r.methodName, code.String()).Inc()
if serverHandledHistogramEnabled {
serverHandledHistogram.WithLabelValues(string(r.rpcType), r.serviceName, r.methodName).Observe(time.Since(r.startTime).Seconds())
}
}
// preRegisterMethod is invoked on Register of a Server, allowing all gRPC services labels to be pre-populated.
func preRegisterMethod(serviceName string, mInfo *grpc.MethodInfo) {
methodName := mInfo.Name
methodType := string(typeFromMethodInfo(mInfo))
// These are just references (no increments), as just referencing will create the labels but not set values.
serverStartedCounter.GetMetricWithLabelValues(methodType, serviceName, methodName)
serverStreamMsgReceived.GetMetricWithLabelValues(methodType, serviceName, methodName)
serverStreamMsgSent.GetMetricWithLabelValues(methodType, serviceName, methodName)
if serverHandledHistogramEnabled {
serverHandledHistogram.GetMetricWithLabelValues(methodType, serviceName, methodName)
}
for _, code := range allCodes {
serverHandledCounter.GetMetricWithLabelValues(methodType, serviceName, methodName, code.String())
}
}
func typeFromMethodInfo(mInfo *grpc.MethodInfo) grpcType {
if mInfo.IsClientStream == false && mInfo.IsServerStream == false {
return Unary
}
if mInfo.IsClientStream == true && mInfo.IsServerStream == false {
return ClientStream
}
if mInfo.IsClientStream == false && mInfo.IsServerStream == true {
return ServerStream
}
return BidiStream
}

View file

@ -0,0 +1,27 @@
// Copyright 2016 Michal Witkowski. All Rights Reserved.
// See LICENSE for licensing terms.
package grpc_prometheus
import (
"strings"
"google.golang.org/grpc/codes"
)
var (
allCodes = []codes.Code{
codes.OK, codes.Canceled, codes.Unknown, codes.InvalidArgument, codes.DeadlineExceeded, codes.NotFound,
codes.AlreadyExists, codes.PermissionDenied, codes.Unauthenticated, codes.ResourceExhausted,
codes.FailedPrecondition, codes.Aborted, codes.OutOfRange, codes.Unimplemented, codes.Internal,
codes.Unavailable, codes.DataLoss,
}
)
func splitMethodName(fullMethodName string) (string, string) {
fullMethodName = strings.TrimPrefix(fullMethodName, "/") // remove leading slash
if i := strings.Index(fullMethodName, "/"); i >= 0 {
return fullMethodName[:i], fullMethodName[i+1:]
}
return "unknown", "unknown"
}