Google cloud platform 如何在使用Google Cloud Dataflow清除云Memorystore中的缓存后插入数据?
如果数据流要处理的输入文件有数据,我正在执行一项清除memorystore缓存的任务。这意味着,如果输入文件没有记录,则不会刷新memorystore,但输入文件甚至有一条记录,则应刷新memorystore,然后处理输入文件 我的数据流应用程序是一个多管道应用程序,它读取、处理数据,然后将数据存储在memorystore中。管道正在成功执行。但是,内存存储的刷新正在工作,但在刷新之后,插入没有发生 我编写了一个函数,在检查输入文件是否有记录后刷新memorystore FlushingMemorystore.javaGoogle cloud platform 如何在使用Google Cloud Dataflow清除云Memorystore中的缓存后插入数据?,google-cloud-platform,redis,google-cloud-dataflow,apache-beam,google-cloud-memorystore,Google Cloud Platform,Redis,Google Cloud Dataflow,Apache Beam,Google Cloud Memorystore,如果数据流要处理的输入文件有数据,我正在执行一项清除memorystore缓存的任务。这意味着,如果输入文件没有记录,则不会刷新memorystore,但输入文件甚至有一条记录,则应刷新memorystore,然后处理输入文件 我的数据流应用程序是一个多管道应用程序,它读取、处理数据,然后将数据存储在memorystore中。管道正在成功执行。但是,内存存储的刷新正在工作,但在刷新之后,插入没有发生 我编写了一个函数,在检查输入文件是否有记录后刷新memorystore FlushingMemo
package com.click.example.functions;
import afu.org.checkerframework.checker.nullness.qual.Nullable;
import com.google.auto.value.AutoValue;
import org.apache.beam.sdk.io.redis.RedisConnectionConfiguration;
import org.apache.beam.sdk.transforms.DoFn;
import org.apache.beam.sdk.transforms.PTransform;
import org.apache.beam.sdk.transforms.ParDo;
import org.apache.beam.sdk.values.PCollection;
import org.apache.beam.sdk.values.PDone;
import org.apache.beam.vendor.grpc.v1p26p0.com.google.common.base.Preconditions;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import redis.clients.jedis.Jedis;
import redis.clients.jedis.Pipeline;
public class FlushingMemorystore {
private static final Logger LOGGER = LoggerFactory.getLogger(FlushingMemorystore.class);
public static FlushingMemorystore.Read read() {
return (new AutoValue_FlushingMemorystore_Read.Builder())
.setConnectionConfiguration(RedisConnectionConfiguration.create()).build();
}
@AutoValue
public abstract static class Read extends PTransform<PCollection<Long>, PDone> {
public Read() {
}
@Nullable
abstract RedisConnectionConfiguration connectionConfiguration();
@Nullable
abstract Long expireTime();
abstract FlushingMemorystore.Read.Builder toBuilder();
public FlushingMemorystore.Read withEndpoint(String host, int port) {
Preconditions.checkArgument(host != null, "host cannot be null");
Preconditions.checkArgument(port > 0, "port cannot be negative or 0");
return this.toBuilder().setConnectionConfiguration(this.connectionConfiguration().withHost(host).withPort(port)).build();
}
public FlushingMemorystore.Read withAuth(String auth) {
Preconditions.checkArgument(auth != null, "auth cannot be null");
return this.toBuilder().setConnectionConfiguration(this.connectionConfiguration().withAuth(auth)).build();
}
public FlushingMemorystore.Read withTimeout(int timeout) {
Preconditions.checkArgument(timeout >= 0, "timeout cannot be negative");
return this.toBuilder().setConnectionConfiguration(this.connectionConfiguration().withTimeout(timeout)).build();
}
public FlushingMemorystore.Read withConnectionConfiguration(RedisConnectionConfiguration connectionConfiguration) {
Preconditions.checkArgument(connectionConfiguration != null, "connection cannot be null");
return this.toBuilder().setConnectionConfiguration(connectionConfiguration).build();
}
public FlushingMemorystore.Read withExpireTime(Long expireTimeMillis) {
Preconditions.checkArgument(expireTimeMillis != null, "expireTimeMillis cannot be null");
Preconditions.checkArgument(expireTimeMillis > 0L, "expireTimeMillis cannot be negative or 0");
return this.toBuilder().setExpireTime(expireTimeMillis).build();
}
public PDone expand(PCollection<Long> input) {
Preconditions.checkArgument(this.connectionConfiguration() != null, "withConnectionConfiguration() is required");
input.apply(ParDo.of(new FlushingMemorystore.Read.ReadFn(this)));
return PDone.in(input.getPipeline());
}
private static class ReadFn extends DoFn<Long, String> {
private static final int DEFAULT_BATCH_SIZE = 1000;
private final FlushingMemorystore.Read spec;
private transient Jedis jedis;
private transient Pipeline pipeline;
private int batchCount;
public ReadFn(FlushingMemorystore.Read spec) {
this.spec = spec;
}
@Setup
public void setup() {
this.jedis = this.spec.connectionConfiguration().connect();
}
@StartBundle
public void startBundle() {
this.pipeline = this.jedis.pipelined();
this.pipeline.multi();
this.batchCount = 0;
}
@ProcessElement
public void processElement(DoFn<Long, String>.ProcessContext c) {
Long count = c.element();
batchCount++;
if(count==null && count < 0) {
LOGGER.info("No Records are there in the input file");
} else {
if (pipeline.isInMulti()) {
pipeline.exec();
pipeline.sync();
jedis.flushDB();
}
LOGGER.info("*****The memorystore is flushed*****");
}
}
@FinishBundle
public void finishBundle() {
if (this.pipeline.isInMulti()) {
this.pipeline.exec();
this.pipeline.sync();
}
this.batchCount=0;
}
@Teardown
public void teardown() {
this.jedis.close();
}
}
@AutoValue.Builder
abstract static class Builder {
Builder() {
}
abstract FlushingMemorystore.Read.Builder setExpireTime(Long expireTimeMillis);
abstract FlushingMemorystore.Read build();
abstract FlushingMemorystore.Read.Builder setConnectionConfiguration(RedisConnectionConfiguration connectionConfiguration);
}
}
}
数据流执行得很好,它也会刷新memorystore,但在此之后插入就不起作用了。你能指出我错在哪里吗?
任何解决问题的办法都是值得赞赏的。提前谢谢
编辑:
StorageToRedisOptions options = PipelineOptionsFactory.fromArgs(args)
.withValidation()
.as(StorageToRedisOptions.class);
Pipeline p = Pipeline.create(options);
PCollection<String> lines = p.apply(
"ReadLines", TextIO.read().from(options.getInputFile()));
/**
* Flushing the Memorystore if there are records in the input file
*/
lines.apply("Checking Data in input file", Count.globally())
.apply("Flushing the data store", FlushingMemorystore.read()
.withConnectionConfiguration(RedisConnectionConfiguration
.create(options.getRedisHost(), options.getRedisPort())));
dataset.apply(SOME_DATASET_TRANSFORMATION, RedisIO.write()
.withMethod(RedisIO.Write.Method.SADD)
.withConnectionConfiguration(RedisConnectionConfiguration
.create(options.getRedisHost(), options.getRedisPort())));
提供评论中要求的其他信息
使用的运行时是Java11,它使用ApacheBeamSDK for 2.24.0
如果输入文件有记录,它将用一些逻辑处理数据。例如,如果输入文件包含以下数据:
abcabc|Bruce|Wayne|2000
abbabb|Tony|Stark|3423
数据流将统计记录的数量,在本例中为2,并根据逻辑处理id、名字等,然后存储在memorystore中。此输入文件每天都会出现,因此,如果输入文件有记录,则应清除(或刷新)memorystore
虽然管道没有中断,但我认为我遗漏了一些东西。我怀疑这里的问题是,您需要确保在RedisIO.write步骤发生之前运行(并完成)“刷新”步骤。Beam具有可用于此操作的变换 为了实现这一点,我们可以使用flushing pttransform的输出作为我们已经刷新了数据库的信号,并且我们只在完成刷新后才向数据库写入数据。刷新DoFn的
过程调用如下所示:
@ProcessElement
public void processElement(DoFn.ProcessContext c){
长计数=c.元素();
if(count==null&&count<0){
info(“输入文件中没有记录”);
}否则{
if(pipeline.isInMulti()){
pipeline.exec();
sync();
绝地武士;
}
LOGGER.info(“******内存存储已刷新******”);
}
c、 输出(“就绪”);
}
一旦有信号指示数据库已刷新,我们可以使用它等待,然后再将新数据写入其中:
Pipeline p=Pipeline.create(选项);
p收集线=p应用(
“ReadLines”,TextIO.read().from(options.getInputFile());
/**
*如果输入文件中有记录,则刷新Memorystore
*/
PCollection flushedSignal=线路
.apply(“检查输入文件中的数据”,Count.globally())
.apply(“刷新数据存储”,FlushingMemorystore.read())
.带连接配置(重新连接配置
.create(options.getRedisHost(),options.getRedisPort());
//然后,我们使用刷新信号开始写入Redis:
数据集
.apply(等待打开(flushedSignal))
.apply(一些数据集转换,RedisIO.write()
.withMethod(RedisIO.Write.Method.SADD)
.带连接配置(重新连接配置
.create(options.getRedisHost(),options.getRedisPort());
在我申请Wait.on转换后,问题得到了解决,Pablo的回答已经解释了这一点。但是,我不得不将FlushingMemorystore.java稍微重写为flushSignal标志的PCollection
下面是函数:
package com.click.example.functions;
import afu.org.checkerframework.checker.nullness.qual.Nullable;
import com.google.auto.value.AutoValue;
import org.apache.beam.sdk.io.redis.RedisConnectionConfiguration;
import org.apache.beam.sdk.transforms.DoFn;
import org.apache.beam.sdk.transforms.PTransform;
import org.apache.beam.sdk.transforms.ParDo;
import org.apache.beam.sdk.values.PCollection;
import org.apache.beam.vendor.grpc.v1p26p0.com.google.common.base.Preconditions;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import redis.clients.jedis.Jedis;
import redis.clients.jedis.Pipeline;
public class FlushingMemorystore extends DoFn<Long, String> {
private static final Logger LOGGER = LoggerFactory.getLogger(FlushingMemorystore.class);
public static FlushingMemorystore.Read read() {
return (new AutoValue_FlushingMemorystore_Read.Builder())
.setConnectionConfiguration(RedisConnectionConfiguration.create()).build();
}
@AutoValue
public abstract static class Read extends PTransform<PCollection<Long>, PCollection<String>> {
public Read() {
}
@Nullable
abstract RedisConnectionConfiguration connectionConfiguration();
@Nullable
abstract Long expireTime();
abstract FlushingMemorystore.Read.Builder toBuilder();
public FlushingMemorystore.Read withEndpoint(String host, int port) {
Preconditions.checkArgument(host != null, "host cannot be null");
Preconditions.checkArgument(port > 0, "port cannot be negative or 0");
return this.toBuilder().setConnectionConfiguration(this.connectionConfiguration().withHost(host).withPort(port)).build();
}
public FlushingMemorystore.Read withAuth(String auth) {
Preconditions.checkArgument(auth != null, "auth cannot be null");
return this.toBuilder().setConnectionConfiguration(this.connectionConfiguration().withAuth(auth)).build();
}
public FlushingMemorystore.Read withTimeout(int timeout) {
Preconditions.checkArgument(timeout >= 0, "timeout cannot be negative");
return this.toBuilder().setConnectionConfiguration(this.connectionConfiguration().withTimeout(timeout)).build();
}
public FlushingMemorystore.Read withConnectionConfiguration(RedisConnectionConfiguration connectionConfiguration) {
Preconditions.checkArgument(connectionConfiguration != null, "connection cannot be null");
return this.toBuilder().setConnectionConfiguration(connectionConfiguration).build();
}
public FlushingMemorystore.Read withExpireTime(Long expireTimeMillis) {
Preconditions.checkArgument(expireTimeMillis != null, "expireTimeMillis cannot be null");
Preconditions.checkArgument(expireTimeMillis > 0L, "expireTimeMillis cannot be negative or 0");
return this.toBuilder().setExpireTime(expireTimeMillis).build();
}
public PCollection<String> expand(PCollection<Long> input) {
Preconditions.checkArgument(this.connectionConfiguration() != null, "withConnectionConfiguration() is required");
return input.apply(ParDo.of(new FlushingMemorystore.Read.ReadFn(this)));
}
@Setup
public Jedis setup() {
return this.connectionConfiguration().connect();
}
private static class ReadFn extends DoFn<Long, String> {
private static final int DEFAULT_BATCH_SIZE = 1000;
private final FlushingMemorystore.Read spec;
private transient Jedis jedis;
private transient Pipeline pipeline;
private int batchCount;
public ReadFn(FlushingMemorystore.Read spec) {
this.spec = spec;
}
@Setup
public void setup() {
this.jedis = this.spec.connectionConfiguration().connect();
}
@StartBundle
public void startBundle() {
this.pipeline = this.jedis.pipelined();
this.pipeline.multi();
this.batchCount = 0;
}
@ProcessElement
public void processElement(@Element Long count, OutputReceiver<String> out) {
batchCount++;
if(count!=null && count > 0) {
if (pipeline.isInMulti()) {
pipeline.exec();
pipeline.sync();
jedis.flushDB();
LOGGER.info("*****The memorystore is flushed*****");
}
out.output("SUCCESS");
} else {
LOGGER.info("No Records are there in the input file");
out.output("FAILURE");
}
}
@FinishBundle
public void finishBundle() {
if (this.pipeline.isInMulti()) {
this.pipeline.exec();
this.pipeline.sync();
}
this.batchCount=0;
}
@Teardown
public void teardown() {
this.jedis.close();
}
}
@AutoValue.Builder
abstract static class Builder {
Builder() {
}
abstract FlushingMemorystore.Read.Builder setExpireTime(Long expireTimeMillis);
abstract FlushingMemorystore.Read build();
abstract FlushingMemorystore.Read.Builder setConnectionConfiguration(RedisConnectionConfiguration connectionConfiguration);
}
}
}
package com.click.example.functions;
导入afu.org.checkerframework.checker.nullness.qual.Nullable;
导入com.google.auto.value.AutoValue;
导入org.apache.beam.sdk.io.redis.RedisConnectionConfiguration;
导入org.apache.beam.sdk.transforms.DoFn;
导入org.apache.beam.sdk.transforms.ptTransform;
导入org.apache.beam.sdk.transforms.ParDo;
导入org.apache.beam.sdk.values.PCollection;
导入org.apache.beam.vendor.grpc.v1p26p0.com.google.common.base.premissions;
导入org.slf4j.Logger;
导入org.slf4j.LoggerFactory;
导入redis.clients.jedis.jedis;
导入redis.clients.jedis.Pipeline;
公共类FlushingMemorystore扩展了DoFn{
私有静态最终记录器Logger=LoggerFactory.getLogger(FlushingMemorystore.class);
公共静态FlushingMemorystore.Read读取(){
返回(新的自动值\u FlushingMemorystore\u Read.Builder())
.setConnectionConfiguration(重新连接配置.create()).build();
}
@自动值
公共抽象静态类读取扩展了pttransform{
公众阅读(){
}
@可空
抽象重新连接配置connectionConfiguration();
@可空
抽象长呼气时间();
抽象FlushingMemorystore.Read.Builder toBuilder();
公共FlushingMemorystore.ReadWithEndpoint(字符串主机,int端口){
前提条件.checkArgument(主机!=null,“主机不能为null”);
先决条件.checkArgument(端口>0,“端口不能为负或0”);
返回此.toBuilder().setConnectionConfiguration(this.connectionConfiguration().withHost(host).withPort(port)).build();
}
public FlushingMemorystore.ReadWithAuth(字符串身份验证){
预条件.checkArgument(auth!=null,“auth不能为null”);
返回this.toBuilder().setConnectionConfiguration(this.connectionConfiguration().withAuth(auth)).build();
}
公共FlushingMemorystore.ReadWithTimeout(int timeout){
前提条件