001/**
002 * Licensed to the Apache Software Foundation (ASF) under one
003 * or more contributor license agreements.  See the NOTICE file
004 * distributed with this work for additional information
005 * regarding copyright ownership.  The ASF licenses this file
006 * to you under the Apache License, Version 2.0 (the
007 * "License"); you may not use this file except in compliance
008 * with the License.  You may obtain a copy of the License at
009 *
010 *     http://www.apache.org/licenses/LICENSE-2.0
011 *
012 * Unless required by applicable law or agreed to in writing, software
013 * distributed under the License is distributed on an "AS IS" BASIS,
014 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
015 * See the License for the specific language governing permissions and
016 * limitations under the License.
017 */
018
019package org.apache.hadoop.hbase.chaos.actions;
020
021import java.io.IOException;
022
023import org.apache.hadoop.hbase.ServerName;
024import org.apache.hadoop.hbase.chaos.monkies.PolicyBasedChaosMonkey;
025import org.slf4j.Logger;
026import org.slf4j.LoggerFactory;
027
028/**
029 *
030 * Corrupt network packets on a random regionserver.
031 */
032public class CorruptPacketsCommandAction extends TCCommandAction {
033  private static final Logger LOG = LoggerFactory.getLogger(CorruptPacketsCommandAction.class);
034  private float ratio;
035  private long duration;
036
037  /**
038   * Corrupt network packets on a random regionserver.
039   *
040   * @param ratio the ratio of packets corrupted
041   * @param duration the time this issue persists in milliseconds
042   * @param timeout the timeout for executing required commands on the region server in milliseconds
043   * @param network network interface the regionserver uses for communication
044   */
045  public CorruptPacketsCommandAction(float ratio, long duration, long timeout, String network) {
046    super(timeout, network);
047    this.ratio = ratio;
048    this.duration = duration;
049  }
050
051  protected void localPerform() throws IOException {
052    LOG.info("Starting to execute CorruptPacketsCommandAction");
053    ServerName server = PolicyBasedChaosMonkey.selectRandomItem(getCurrentServers());
054    String hostname = server.getHostname();
055
056    try {
057      clusterManager.execSudoWithRetries(hostname, timeout, getCommand(ADD));
058      Thread.sleep(duration);
059    } catch (InterruptedException e) {
060      LOG.debug("Failed to run the command for the full duration", e);
061    } finally {
062      clusterManager.execSudoWithRetries(hostname, timeout, getCommand(DELETE));
063    }
064
065    LOG.info("Finished to execute CorruptPacketsCommandAction");
066  }
067
068  private String getCommand(String operation){
069    return String.format("tc qdisc %s dev %s root netem corrupt %s%%", operation, network,
070        ratio * 100);
071  }
072}