Add Kafka 0.9+ consumer support (#2487)
This commit is contained in:
Seuf
Daniel Nelson
39
plugins/inputs/kafka_consumer_legacy/README.md
Normal file
39
plugins/inputs/kafka_consumer_legacy/README.md
Normal file
@@ -0,0 +1,39 @@
|
||||
# Kafka Consumer Input Plugin
|
||||
|
||||
The [Kafka](http://kafka.apache.org/) consumer plugin polls a specified Kafka
|
||||
topic and adds messages to InfluxDB. The plugin assumes messages follow the
|
||||
line protocol. [Consumer Group](http://godoc.org/github.com/wvanbergen/kafka/consumergroup)
|
||||
is used to talk to the Kafka cluster so multiple instances of telegraf can read
|
||||
from the same topic in parallel.
|
||||
|
||||
## Configuration
|
||||
|
||||
```toml
|
||||
# Read metrics from Kafka topic(s)
|
||||
[[inputs.kafka_consumer]]
|
||||
## topic(s) to consume
|
||||
topics = ["telegraf"]
|
||||
## an array of Zookeeper connection strings
|
||||
zookeeper_peers = ["localhost:2181"]
|
||||
## Zookeeper Chroot
|
||||
zookeeper_chroot = ""
|
||||
## the name of the consumer group
|
||||
consumer_group = "telegraf_metrics_consumers"
|
||||
## Offset (must be either "oldest" or "newest")
|
||||
offset = "oldest"
|
||||
|
||||
## Data format to consume.
|
||||
## Each data format has its own unique set of configuration options, read
|
||||
## more about them here:
|
||||
## https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md
|
||||
data_format = "influx"
|
||||
|
||||
## Maximum length of a message to consume, in bytes (default 0/unlimited);
|
||||
## larger messages are dropped
|
||||
max_message_len = 65536
|
||||
```
|
||||
|
||||
## Testing
|
||||
|
||||
Running integration tests requires running Zookeeper & Kafka. See Makefile
|
||||
for kafka container command.
|
||||
183
plugins/inputs/kafka_consumer_legacy/kafka_consumer_legacy.go
Normal file
183
plugins/inputs/kafka_consumer_legacy/kafka_consumer_legacy.go
Normal file
@@ -0,0 +1,183 @@
|
||||
package kafka_consumer_legacy
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"log"
|
||||
"strings"
|
||||
"sync"
|
||||
|
||||
"github.com/influxdata/telegraf"
|
||||
"github.com/influxdata/telegraf/plugins/inputs"
|
||||
"github.com/influxdata/telegraf/plugins/parsers"
|
||||
|
||||
"github.com/Shopify/sarama"
|
||||
"github.com/wvanbergen/kafka/consumergroup"
|
||||
)
|
||||
|
||||
type Kafka struct {
|
||||
ConsumerGroup string
|
||||
Topics []string
|
||||
MaxMessageLen int
|
||||
ZookeeperPeers []string
|
||||
ZookeeperChroot string
|
||||
Consumer *consumergroup.ConsumerGroup
|
||||
|
||||
// Legacy metric buffer support
|
||||
MetricBuffer int
|
||||
// TODO remove PointBuffer, legacy support
|
||||
PointBuffer int
|
||||
|
||||
Offset string
|
||||
parser parsers.Parser
|
||||
|
||||
sync.Mutex
|
||||
|
||||
// channel for all incoming kafka messages
|
||||
in <-chan *sarama.ConsumerMessage
|
||||
// channel for all kafka consumer errors
|
||||
errs <-chan error
|
||||
done chan struct{}
|
||||
|
||||
// keep the accumulator internally:
|
||||
acc telegraf.Accumulator
|
||||
|
||||
// doNotCommitMsgs tells the parser not to call CommitUpTo on the consumer
|
||||
// this is mostly for test purposes, but there may be a use-case for it later.
|
||||
doNotCommitMsgs bool
|
||||
}
|
||||
|
||||
var sampleConfig = `
|
||||
## topic(s) to consume
|
||||
topics = ["telegraf"]
|
||||
## an array of Zookeeper connection strings
|
||||
zookeeper_peers = ["localhost:2181"]
|
||||
## Zookeeper Chroot
|
||||
zookeeper_chroot = ""
|
||||
## the name of the consumer group
|
||||
consumer_group = "telegraf_metrics_consumers"
|
||||
## Offset (must be either "oldest" or "newest")
|
||||
offset = "oldest"
|
||||
|
||||
## Data format to consume.
|
||||
## Each data format has its own unique set of configuration options, read
|
||||
## more about them here:
|
||||
## https://github.com/influxdata/telegraf/blob/master/docs/DATA_FORMATS_INPUT.md
|
||||
data_format = "influx"
|
||||
|
||||
## Maximum length of a message to consume, in bytes (default 0/unlimited);
|
||||
## larger messages are dropped
|
||||
max_message_len = 65536
|
||||
`
|
||||
|
||||
func (k *Kafka) SampleConfig() string {
|
||||
return sampleConfig
|
||||
}
|
||||
|
||||
func (k *Kafka) Description() string {
|
||||
return "Read metrics from Kafka topic(s)"
|
||||
}
|
||||
|
||||
func (k *Kafka) SetParser(parser parsers.Parser) {
|
||||
k.parser = parser
|
||||
}
|
||||
|
||||
func (k *Kafka) Start(acc telegraf.Accumulator) error {
|
||||
k.Lock()
|
||||
defer k.Unlock()
|
||||
var consumerErr error
|
||||
|
||||
k.acc = acc
|
||||
|
||||
config := consumergroup.NewConfig()
|
||||
config.Zookeeper.Chroot = k.ZookeeperChroot
|
||||
switch strings.ToLower(k.Offset) {
|
||||
case "oldest", "":
|
||||
config.Offsets.Initial = sarama.OffsetOldest
|
||||
case "newest":
|
||||
config.Offsets.Initial = sarama.OffsetNewest
|
||||
default:
|
||||
log.Printf("I! WARNING: Kafka consumer invalid offset '%s', using 'oldest'\n",
|
||||
k.Offset)
|
||||
config.Offsets.Initial = sarama.OffsetOldest
|
||||
}
|
||||
|
||||
if k.Consumer == nil || k.Consumer.Closed() {
|
||||
k.Consumer, consumerErr = consumergroup.JoinConsumerGroup(
|
||||
k.ConsumerGroup,
|
||||
k.Topics,
|
||||
k.ZookeeperPeers,
|
||||
config,
|
||||
)
|
||||
if consumerErr != nil {
|
||||
return consumerErr
|
||||
}
|
||||
|
||||
// Setup message and error channels
|
||||
k.in = k.Consumer.Messages()
|
||||
k.errs = k.Consumer.Errors()
|
||||
}
|
||||
|
||||
k.done = make(chan struct{})
|
||||
|
||||
// Start the kafka message reader
|
||||
go k.receiver()
|
||||
log.Printf("I! Started the kafka consumer service, peers: %v, topics: %v\n",
|
||||
k.ZookeeperPeers, k.Topics)
|
||||
return nil
|
||||
}
|
||||
|
||||
// receiver() reads all incoming messages from the consumer, and parses them into
|
||||
// influxdb metric points.
|
||||
func (k *Kafka) receiver() {
|
||||
for {
|
||||
select {
|
||||
case <-k.done:
|
||||
return
|
||||
case err := <-k.errs:
|
||||
if err != nil {
|
||||
k.acc.AddError(fmt.Errorf("Consumer Error: %s\n", err))
|
||||
}
|
||||
case msg := <-k.in:
|
||||
if k.MaxMessageLen != 0 && len(msg.Value) > k.MaxMessageLen {
|
||||
k.acc.AddError(fmt.Errorf("Message longer than max_message_len (%d > %d)",
|
||||
len(msg.Value), k.MaxMessageLen))
|
||||
} else {
|
||||
metrics, err := k.parser.Parse(msg.Value)
|
||||
if err != nil {
|
||||
k.acc.AddError(fmt.Errorf("Message Parse Error\nmessage: %s\nerror: %s",
|
||||
string(msg.Value), err.Error()))
|
||||
}
|
||||
for _, metric := range metrics {
|
||||
k.acc.AddFields(metric.Name(), metric.Fields(), metric.Tags(), metric.Time())
|
||||
}
|
||||
}
|
||||
|
||||
if !k.doNotCommitMsgs {
|
||||
// TODO(cam) this locking can be removed if this PR gets merged:
|
||||
// https://github.com/wvanbergen/kafka/pull/84
|
||||
k.Lock()
|
||||
k.Consumer.CommitUpto(msg)
|
||||
k.Unlock()
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func (k *Kafka) Stop() {
|
||||
k.Lock()
|
||||
defer k.Unlock()
|
||||
close(k.done)
|
||||
if err := k.Consumer.Close(); err != nil {
|
||||
k.acc.AddError(fmt.Errorf("Error closing consumer: %s\n", err.Error()))
|
||||
}
|
||||
}
|
||||
|
||||
func (k *Kafka) Gather(acc telegraf.Accumulator) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
func init() {
|
||||
inputs.Add("kafka_consumer_legacy", func() telegraf.Input {
|
||||
return &Kafka{}
|
||||
})
|
||||
}
|
||||
@@ -0,0 +1,96 @@
|
||||
package kafka_consumer_legacy
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/Shopify/sarama"
|
||||
"github.com/influxdata/telegraf/testutil"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
|
||||
"github.com/influxdata/telegraf/plugins/parsers"
|
||||
)
|
||||
|
||||
func TestReadsMetricsFromKafka(t *testing.T) {
|
||||
if testing.Short() {
|
||||
t.Skip("Skipping integration test in short mode")
|
||||
}
|
||||
|
||||
brokerPeers := []string{testutil.GetLocalHost() + ":9092"}
|
||||
zkPeers := []string{testutil.GetLocalHost() + ":2181"}
|
||||
testTopic := fmt.Sprintf("telegraf_test_topic_legacy_%d", time.Now().Unix())
|
||||
|
||||
// Send a Kafka message to the kafka host
|
||||
msg := "cpu_load_short,direction=in,host=server01,region=us-west value=23422.0 1422568543702900257\n"
|
||||
producer, err := sarama.NewSyncProducer(brokerPeers, nil)
|
||||
require.NoError(t, err)
|
||||
_, _, err = producer.SendMessage(
|
||||
&sarama.ProducerMessage{
|
||||
Topic: testTopic,
|
||||
Value: sarama.StringEncoder(msg),
|
||||
})
|
||||
require.NoError(t, err)
|
||||
defer producer.Close()
|
||||
|
||||
// Start the Kafka Consumer
|
||||
k := &Kafka{
|
||||
ConsumerGroup: "telegraf_test_consumers",
|
||||
Topics: []string{testTopic},
|
||||
ZookeeperPeers: zkPeers,
|
||||
PointBuffer: 100000,
|
||||
Offset: "oldest",
|
||||
}
|
||||
p, _ := parsers.NewInfluxParser()
|
||||
k.SetParser(p)
|
||||
|
||||
// Verify that we can now gather the sent message
|
||||
var acc testutil.Accumulator
|
||||
|
||||
// Sanity check
|
||||
assert.Equal(t, 0, len(acc.Metrics), "There should not be any points")
|
||||
if err := k.Start(&acc); err != nil {
|
||||
t.Fatal(err.Error())
|
||||
} else {
|
||||
defer k.Stop()
|
||||
}
|
||||
|
||||
waitForPoint(&acc, t)
|
||||
|
||||
// Gather points
|
||||
err = acc.GatherError(k.Gather)
|
||||
require.NoError(t, err)
|
||||
if len(acc.Metrics) == 1 {
|
||||
point := acc.Metrics[0]
|
||||
assert.Equal(t, "cpu_load_short", point.Measurement)
|
||||
assert.Equal(t, map[string]interface{}{"value": 23422.0}, point.Fields)
|
||||
assert.Equal(t, map[string]string{
|
||||
"host": "server01",
|
||||
"direction": "in",
|
||||
"region": "us-west",
|
||||
}, point.Tags)
|
||||
assert.Equal(t, time.Unix(0, 1422568543702900257).Unix(), point.Time.Unix())
|
||||
} else {
|
||||
t.Errorf("No points found in accumulator, expected 1")
|
||||
}
|
||||
}
|
||||
|
||||
// Waits for the metric that was sent to the kafka broker to arrive at the kafka
|
||||
// consumer
|
||||
func waitForPoint(acc *testutil.Accumulator, t *testing.T) {
|
||||
// Give the kafka container up to 2 seconds to get the point to the consumer
|
||||
ticker := time.NewTicker(5 * time.Millisecond)
|
||||
counter := 0
|
||||
for {
|
||||
select {
|
||||
case <-ticker.C:
|
||||
counter++
|
||||
if counter > 1000 {
|
||||
t.Fatal("Waited for 5s, point never arrived to consumer")
|
||||
} else if acc.NFields() == 1 {
|
||||
return
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,150 @@
|
||||
package kafka_consumer_legacy
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/influxdata/telegraf/plugins/parsers"
|
||||
"github.com/influxdata/telegraf/testutil"
|
||||
|
||||
"github.com/Shopify/sarama"
|
||||
"github.com/stretchr/testify/assert"
|
||||
)
|
||||
|
||||
const (
|
||||
testMsg = "cpu_load_short,host=server01 value=23422.0 1422568543702900257\n"
|
||||
testMsgGraphite = "cpu.load.short.graphite 23422 1454780029"
|
||||
testMsgJSON = "{\"a\": 5, \"b\": {\"c\": 6}}\n"
|
||||
invalidMsg = "cpu_load_short,host=server01 1422568543702900257\n"
|
||||
)
|
||||
|
||||
func newTestKafka() (*Kafka, chan *sarama.ConsumerMessage) {
|
||||
in := make(chan *sarama.ConsumerMessage, 1000)
|
||||
k := Kafka{
|
||||
ConsumerGroup: "test",
|
||||
Topics: []string{"telegraf"},
|
||||
ZookeeperPeers: []string{"localhost:2181"},
|
||||
Offset: "oldest",
|
||||
in: in,
|
||||
doNotCommitMsgs: true,
|
||||
errs: make(chan error, 1000),
|
||||
done: make(chan struct{}),
|
||||
}
|
||||
return &k, in
|
||||
}
|
||||
|
||||
// Test that the parser parses kafka messages into points
|
||||
func TestRunParser(t *testing.T) {
|
||||
k, in := newTestKafka()
|
||||
acc := testutil.Accumulator{}
|
||||
k.acc = &acc
|
||||
defer close(k.done)
|
||||
|
||||
k.parser, _ = parsers.NewInfluxParser()
|
||||
go k.receiver()
|
||||
in <- saramaMsg(testMsg)
|
||||
acc.Wait(1)
|
||||
|
||||
assert.Equal(t, acc.NFields(), 1)
|
||||
}
|
||||
|
||||
// Test that the parser ignores invalid messages
|
||||
func TestRunParserInvalidMsg(t *testing.T) {
|
||||
k, in := newTestKafka()
|
||||
acc := testutil.Accumulator{}
|
||||
k.acc = &acc
|
||||
defer close(k.done)
|
||||
|
||||
k.parser, _ = parsers.NewInfluxParser()
|
||||
go k.receiver()
|
||||
in <- saramaMsg(invalidMsg)
|
||||
acc.WaitError(1)
|
||||
|
||||
assert.Equal(t, acc.NFields(), 0)
|
||||
}
|
||||
|
||||
// Test that overlong messages are dropped
|
||||
func TestDropOverlongMsg(t *testing.T) {
|
||||
const maxMessageLen = 64 * 1024
|
||||
k, in := newTestKafka()
|
||||
k.MaxMessageLen = maxMessageLen
|
||||
acc := testutil.Accumulator{}
|
||||
k.acc = &acc
|
||||
defer close(k.done)
|
||||
overlongMsg := strings.Repeat("v", maxMessageLen+1)
|
||||
|
||||
go k.receiver()
|
||||
in <- saramaMsg(overlongMsg)
|
||||
acc.WaitError(1)
|
||||
|
||||
assert.Equal(t, acc.NFields(), 0)
|
||||
}
|
||||
|
||||
// Test that the parser parses kafka messages into points
|
||||
func TestRunParserAndGather(t *testing.T) {
|
||||
k, in := newTestKafka()
|
||||
acc := testutil.Accumulator{}
|
||||
k.acc = &acc
|
||||
defer close(k.done)
|
||||
|
||||
k.parser, _ = parsers.NewInfluxParser()
|
||||
go k.receiver()
|
||||
in <- saramaMsg(testMsg)
|
||||
acc.Wait(1)
|
||||
|
||||
acc.GatherError(k.Gather)
|
||||
|
||||
assert.Equal(t, acc.NFields(), 1)
|
||||
acc.AssertContainsFields(t, "cpu_load_short",
|
||||
map[string]interface{}{"value": float64(23422)})
|
||||
}
|
||||
|
||||
// Test that the parser parses kafka messages into points
|
||||
func TestRunParserAndGatherGraphite(t *testing.T) {
|
||||
k, in := newTestKafka()
|
||||
acc := testutil.Accumulator{}
|
||||
k.acc = &acc
|
||||
defer close(k.done)
|
||||
|
||||
k.parser, _ = parsers.NewGraphiteParser("_", []string{}, nil)
|
||||
go k.receiver()
|
||||
in <- saramaMsg(testMsgGraphite)
|
||||
acc.Wait(1)
|
||||
|
||||
acc.GatherError(k.Gather)
|
||||
|
||||
assert.Equal(t, acc.NFields(), 1)
|
||||
acc.AssertContainsFields(t, "cpu_load_short_graphite",
|
||||
map[string]interface{}{"value": float64(23422)})
|
||||
}
|
||||
|
||||
// Test that the parser parses kafka messages into points
|
||||
func TestRunParserAndGatherJSON(t *testing.T) {
|
||||
k, in := newTestKafka()
|
||||
acc := testutil.Accumulator{}
|
||||
k.acc = &acc
|
||||
defer close(k.done)
|
||||
|
||||
k.parser, _ = parsers.NewJSONParser("kafka_json_test", []string{}, nil)
|
||||
go k.receiver()
|
||||
in <- saramaMsg(testMsgJSON)
|
||||
acc.Wait(1)
|
||||
|
||||
acc.GatherError(k.Gather)
|
||||
|
||||
assert.Equal(t, acc.NFields(), 2)
|
||||
acc.AssertContainsFields(t, "kafka_json_test",
|
||||
map[string]interface{}{
|
||||
"a": float64(5),
|
||||
"b_c": float64(6),
|
||||
})
|
||||
}
|
||||
|
||||
func saramaMsg(val string) *sarama.ConsumerMessage {
|
||||
return &sarama.ConsumerMessage{
|
||||
Key: nil,
|
||||
Value: []byte(val),
|
||||
Offset: 0,
|
||||
Partition: 0,
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user