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; 022import org.apache.hadoop.hbase.ServerName; 023import org.apache.hadoop.hbase.chaos.monkies.PolicyBasedChaosMonkey; 024import org.slf4j.Logger; 025import org.slf4j.LoggerFactory; 026 027/** 028 * 029 * Lose network packets on a random regionserver. 030 */ 031public class LosePacketsCommandAction extends TCCommandAction { 032 private static final Logger LOG = LoggerFactory.getLogger(LosePacketsCommandAction.class); 033 private final float ratio; 034 private final long duration; 035 036 /** 037 * Lose network packets on a random regionserver. 038 * 039 * @param ratio the ratio of packets lost 040 * @param duration the time this issue persists in milliseconds 041 * @param timeout the timeout for executing required commands on the region server in milliseconds 042 * @param network network interface the regionserver uses for communication 043 */ 044 public LosePacketsCommandAction(float ratio, long duration, long timeout, String network) { 045 super(timeout, network); 046 this.ratio = ratio; 047 this.duration = duration; 048 } 049 050 @Override protected Logger getLogger() { 051 return LOG; 052 } 053 054 protected void localPerform() throws IOException { 055 getLogger().info("Starting to execute LosePacketsCommandAction"); 056 ServerName server = PolicyBasedChaosMonkey.selectRandomItem(getCurrentServers()); 057 String hostname = server.getHostname(); 058 059 try { 060 clusterManager.execSudoWithRetries(hostname, timeout, getCommand(ADD)); 061 Thread.sleep(duration); 062 } catch (InterruptedException e) { 063 getLogger().debug("Failed to run the command for the full duration", e); 064 } finally { 065 clusterManager.execSudoWithRetries(hostname, timeout, getCommand(DELETE)); 066 } 067 068 getLogger().info("Finished to execute LosePacketsCommandAction"); 069 } 070 071 private String getCommand(String operation){ 072 return String.format("tc qdisc %s dev %s root netem loss %s%%", operation, network, 073 ratio * 100); 074 } 075}