说明
- 本博客每周五更新一次。
- 本博客主要介绍java代码实现kafka数据入库的代码实现，并包含kerberos认证实现。kafka版本为2.3.0
讲解
maven导包
<dependency>
<groupId>org.apache.kafka</groupId>
<artifactId>kafka-clients</artifactId>
<version>2.3.0</version>
</dependency>
连接kafka
Properties props = new Properties();
props.put("acks", "all");
props.put("bootstrap.servers", Config.ipList);
props.put("key.serializer", "org.apache.kafka.common.serialization.ByteArraySerializer");
props.put("value.serializer", "org.apache.kafka.common.serialization.ByteArraySerializer");
props.put("retries", "2");
KafkaProducer<byte[], byte[]> produce= new KafkaProducer<byte[], byte[]>(props);
kerberos认证
- kerberos是大数据平台的安全认证策略，可在项目启动时先一步完成。这里介绍两种实现方式。
方式一
System.setProperty("java.security.krb5.conf", "/etc/krb5.conf");
System.setProperty("java.security.auth.login.config", "/etc/kafka/conf/kafka_jaas.conf");
方式二
- 某些时候，考虑到用户切换，不同机器，有不同的用户信息，每个都要通过配置文件设置，比较麻烦，考虑使用java的启动的临时文件功能（主要是炫技——微笑）。
System.setProperty("java.security.krb5.conf", "/etc/krb5.conf");
KafkaUtil.configureJAAS(Config.tabFile, Config.principal);
public static void configureJAAS(String keyTab, String principal) {
String JAAS_TEMPLATE =
"KafkaClient {\n"
+ "com.sun.security.auth.module.Krb5LoginModule required\n" +
"useKeyTab=true\n" +
"keyTab=\"%1$s\"\n" +
"principal=\"%2$s\";\n"
+ "};";
String content = String.format(JAAS_TEMPLATE, keyTab, principal);
File jaasConf = null;
PrintWriter writer = null;
try {
jaasConf = File.createTempFile("jaas", ".conf");
writer = new PrintWriter(jaasConf);
writer.println(content);
} catch (IOException e) {
e.printStackTrace();
} finally {
if (writer != null) {
writer.close();
}
jaasConf.deleteOnExit();
}
System.setProperty("java.security.auth.login.config", jaasConf.getAbsolutePath());
}
应用
- 实际线上使用时，考虑到数据传输效率和稳定性，要做以下优化。
- 传输类为线程类，线程池管理，增加传输效率。
- 批量上传数据。
- 添加Callback处理机制，避免数据丢失。
- 上传线程类如下。
public class Performance extends Thread{
private final static Logger log = LoggerFactory.getLogger(Performance.class);
private List<ProducerRecord<byte[], byte[]>> recordList;
public Performance(List<ProducerRecord<byte[], byte[]>> recordList) {
this.recordList=recordList;
}
public static void test() {
log.info("Kafka Tool Test");
try {
String topicName ="test40";
long numRecords = 10000000000L;
int recordSize = 1500;
int throughput = 10000000;
Properties props = new Properties();
props.put("acks", "1");
props.put("bootstrap.servers","ip:6667,ip:6667");
props.put("sasl.kerberos.service.name", "kafka");
props.put("security.protocol", "SASL_PLAINTEXT");
props.put(ProducerConfig.KEY_SERIALIZER_CLASS_CONFIG, "org.apache.kafka.common.serialization.ByteArraySerializer");
props.put(ProducerConfig.VALUE_SERIALIZER_CLASS_CONFIG, "org.apache.kafka.common.serialization.ByteArraySerializer");
KafkaProducer<byte[], byte[]> producer = new KafkaProducer<byte[], byte[]>(props);
byte[] payload = new byte[recordSize];
Random random = new Random(0);
for (int i = 0; i < payload.length; ++i)
payload[i] = (byte) (random.nextInt(26) + 65);
ProducerRecord<byte[], byte[]> record = new ProducerRecord<byte[], byte[]>(topicName, payload);
Stats stats = new Stats(numRecords, 5000);
long startMs = System.currentTimeMillis();
ThroughputThrottler throttler = new ThroughputThrottler(throughput, startMs);
for (int i = 0; i < numRecords; i++) {
long sendStartMs = System.currentTimeMillis();
Callback cb = stats.nextCompletion(sendStartMs, payload.length, stats,record.topic(),record.value());
producer.send(record, cb);
if (throttler.shouldThrottle(i, sendStartMs)) {
throttler.throttle();
}
}
producer.close();
stats.printTotal();
} catch (Exception e) {
log.info("Test Error:"+e);
}
}
@Override
public void run() {
super.run();
KafkaUtil kafkaUtil=new KafkaUtil();
KafkaProducer<byte[], byte[]> produce=kafkaUtil.create();
long size=recordList.size();
int throughput = 900000;
Stats stats = new Stats(size, 5000);
long startMs = System.currentTimeMillis();
ThroughputThrottler throttler = new ThroughputThrottler(throughput, startMs);
int i=0;
for (ProducerRecord<byte[], byte[]> record:recordList) {
long sendStartMs = System.currentTimeMillis();
Callback cb = stats.nextCompletion(sendStartMs, record.value().length, stats,record.topic(),record.value());
produce.send(record,cb);
if (throttler.shouldThrottle(i, sendStartMs)) {
throttler.throttle();
}
i++;
}
produce.close();
log.info("Finish Data To Send");
LogModel.sendNum++;
}
private static class Stats {
private long start;
private long windowStart;
private int[] latencies;
private int sampling;
private int iteration;
private int index;
private long count;
private long bytes;
private int maxLatency;
private long totalLatency;
private long windowCount;
private int windowMaxLatency;
private long windowTotalLatency;
private long windowBytes;
private long reportingInterval;
public Stats(long numRecords, int reportingInterval) {
this.start = System.currentTimeMillis();
this.windowStart = System.currentTimeMillis();
this.index = 0;
this.iteration = 0;
this.sampling = (int) (numRecords / Math.min(numRecords, 500000));
this.latencies = new int[(int) (numRecords / this.sampling) + 1];
this.index = 0;
this.maxLatency = 0;
this.totalLatency = 0;
this.windowCount = 0;
this.windowMaxLatency = 0;
this.windowTotalLatency = 0;
this.windowBytes = 0;
this.totalLatency = 0;
this.reportingInterval = reportingInterval;
}
public void record(int iter, int latency, int bytes, long time) {
this.count++;
this.bytes += bytes;
this.totalLatency += latency;
this.maxLatency = Math.max(this.maxLatency, latency);
this.windowCount++;
this.windowBytes += bytes;
this.windowTotalLatency += latency;
this.windowMaxLatency = Math.max(windowMaxLatency, latency);
if (iter % this.sampling == 0) {
this.latencies[index] = latency;
this.index++;
}
if (time - windowStart >= reportingInterval) {
printWindow();
newWindow();
}
}
public Callback nextCompletion(long start, int bytes, Stats stats,String topic,byte[] data) {
Callback cb = new PerfCallback(this.iteration, start, bytes, stats,topic,data);
this.iteration++;
return cb;
}
public void printWindow() {
long ellapsed = System.currentTimeMillis() - windowStart;
double recsPerSec = 1000.0 * windowCount / (double) ellapsed;
double mbPerSec = 1000.0 * this.windowBytes / (double) ellapsed / (1024.0 * 1024.0);
System.out.printf("%d spend time,%d records sent, %.1f records/sec (%.2f MB/sec), %.1f ms avg latency, %.1f max latency.\n",
ellapsed,
windowCount,
recsPerSec,
mbPerSec,
windowTotalLatency / (double) windowCount,
(double) windowMaxLatency);
}
public void newWindow() {
this.windowStart = System.currentTimeMillis();
this.windowCount = 0;
this.windowMaxLatency = 0;
this.windowTotalLatency = 0;
this.windowBytes = 0;
}
public void printTotal() {
long elapsed = System.currentTimeMillis() - start;
double recsPerSec = 1000.0 * count / (double) elapsed;
double mbPerSec = 1000.0 * this.bytes / (double) elapsed / (1024.0 * 1024.0);
int[] percs = percentiles(this.latencies, index, 0.5, 0.95, 0.99, 0.999);
System.out.printf("%d spend time,%d records sent, %f records/sec (%.2f MB/sec), %.2f ms avg latency, %.2f ms max latency, %d ms 50th, %d ms 95th, %d ms 99th, %d ms 99.9th.\n",
elapsed,
count,
recsPerSec,
mbPerSec,
totalLatency / (double) count,
(double) maxLatency,
percs[0],
percs[1],
percs[2],
percs[3]);
}
private static int[] percentiles(int[] latencies, int count, double... percentiles) {
int size = Math.min(count, latencies.length);
Arrays.sort(latencies, 0, size);
int[] values = new int[percentiles.length];
for (int i = 0; i < percentiles.length; i++) {
int index = (int) (percentiles[i] * size);
values[i] = latencies[index];
}
return values;
}
}
private static final class PerfCallback implements Callback {
private final long start;
private final int iteration;
private final int bytes;
private final Stats stats;
private final String topic;
private final byte[] data;
public PerfCallback(int iter, long start, int bytes, Stats stats,String topic,byte[] data) {
this.start = start;
this.stats = stats;
this.iteration = iter;
this.bytes = bytes;
this.topic=topic;
this.data=data;
}
public void onCompletion(RecordMetadata metadata, Exception exception) {
long now = System.currentTimeMillis();
int latency = (int) (now - start);
this.stats.record(iteration, latency, bytes, now);
if (exception != null){
ProducerRecord<byte[], byte[]> record=new ProducerRecord<byte[], byte[]>(topic,data);
ControlTask.recordList.add(record);
log.error("Send Error And Second To Send",exception);
}
}
}
}
public class KafkaUtil {
private KafkaProducer<byte[], byte[]> produce;
public KafkaProducer<byte[], byte[]> create(){
Properties props = new Properties();
props.put("acks", "all");
props.put("bootstrap.servers", Config.ipList);
props.put("key.serializer", "org.apache.kafka.common.serialization.ByteArraySerializer");
props.put("value.serializer", "org.apache.kafka.common.serialization.ByteArraySerializer");
props.put("retries", "2");
if(Config.kerberos==0){
props.put("security.protocol", "SASL_PLAINTEXT");
props.put("sasl.mechanism", "GSSAPI");
props.put("sasl.kerberos.service.name", "kafka");
}
produce = new KafkaProducer<byte[], byte[]>(props);
return produce;
}
public void send(ProducerRecord<byte[], byte[]> record,Callback cb){
produce.send(record,cb);
}
public void close(){
produce.flush();
produce.close();
}
public static void configureJAAS(String keyTab, String principal) {
String JAAS_TEMPLATE =
"KafkaClient {\n"
+ "com.sun.security.auth.module.Krb5LoginModule required\n" +
"useKeyTab=true\n" +
"keyTab=\"%1$s\"\n" +
"principal=\"%2$s\";\n"
+ "};";
String content = String.format(JAAS_TEMPLATE, keyTab, principal);
File jaasConf = null;
PrintWriter writer = null;
try {
jaasConf = File.createTempFile("jaas", ".conf");
writer = new PrintWriter(jaasConf);
writer.println(content);
} catch (IOException e) {
e.printStackTrace();
} finally {
if (writer != null) {
writer.close();
}
jaasConf.deleteOnExit();
}
System.setProperty("java.security.auth.login.config", jaasConf.getAbsolutePath());
}
}
总结
- 第一次做kafka入库时，效率很差，最后反攻官方实例才确定了传输方案，但还是不理想，测试发现是java自身消息队里太慢，无法满足现有需求，最后将队列改为Disruptor事件队列，才满足要求。
- 认真学习，好好奋斗，做自己喜欢做的事，努力活成自己喜欢的样子。
扫一扫
963
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
