org.apache.hudi.org.apache.hadoop.hbase.tool.WriteSinkCoprocessor Maven / Gradle / Ivy
/**
*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you 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 org.apache.hadoop.hbase.tool;
import java.io.IOException;
import java.util.Optional;
import java.util.concurrent.atomic.AtomicLong;
import org.apache.hadoop.hbase.HConstants;
import org.apache.hadoop.hbase.client.Mutation;
import org.apache.hadoop.hbase.coprocessor.ObserverContext;
import org.apache.hadoop.hbase.coprocessor.RegionCoprocessor;
import org.apache.hadoop.hbase.coprocessor.RegionCoprocessorEnvironment;
import org.apache.hadoop.hbase.coprocessor.RegionObserver;
import org.apache.hadoop.hbase.regionserver.MiniBatchOperationInProgress;
import org.apache.hadoop.hbase.regionserver.OperationStatus;
import org.apache.yetus.audience.InterfaceAudience;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
*
* This coprocessor 'shallows' all the writes. It allows to test a pure
* write workload, going through all the communication layers.
* The reads will work as well, but they as we never write, they will always always
* return an empty structure. The WAL is also skipped.
* Obviously, the region will never be split automatically. It's up to the user
* to split and move it.
*
*
* For a table created like this:
* create 'usertable', {NAME => 'f1', VERSIONS => 1}
*
*
* You can then add the coprocessor with this command:
* alter 'usertable', 'coprocessor' => '|org.apache.hadoop.hbase.tool.WriteSinkCoprocessor|'
*
*
* And then
* put 'usertable', 'f1', 'f1', 'f1'
*
*
* scan 'usertable'
* Will return:
* 0 row(s) in 0.0050 seconds
*
* TODO: It needs tests
*/
@InterfaceAudience.Private
public class WriteSinkCoprocessor implements RegionCoprocessor, RegionObserver {
private static final Logger LOG = LoggerFactory.getLogger(WriteSinkCoprocessor.class);
private final AtomicLong ops = new AtomicLong();
@Override
public Optional getRegionObserver() {
return Optional.of(this);
}
private String regionName;
@Override
public void preOpen(ObserverContext e) throws IOException {
regionName = e.getEnvironment().getRegion().getRegionInfo().getRegionNameAsString();
}
@Override
public void preBatchMutate(final ObserverContext c,
final MiniBatchOperationInProgress miniBatchOp)
throws IOException {
if (ops.incrementAndGet() % 20000 == 0) {
LOG.info("Wrote " + ops.get() + " times in region " + regionName);
}
for (int i = 0; i < miniBatchOp.size(); i++) {
miniBatchOp.setOperationStatus(i,
new OperationStatus(HConstants.OperationStatusCode.SUCCESS));
}
c.bypass();
}
}