public Map<String, Long> getRegionSizes(String tableName) {
Map<String, Long> regions = new HashMap<>();
try {
final Table table = connection.getTable(TableName.valueOf(tableName));
RegionLocator regionLocator = connection.getRegionLocator(table.getName());
List<HRegionLocation> tableRegionInfos = regionLocator.getAllRegionLocations();
Set<byte[]> tableRegions = new TreeSet<byte[]>(Bytes.BYTES_COMPARATOR);
for (HRegionLocation regionInfo : tableRegionInfos) {
tableRegions.add(regionInfo.getRegionInfo().getRegionName());
}
ClusterStatus clusterStatus = connection.getAdmin().getClusterStatus();
Collection<ServerName> servers = clusterStatus.getServers();
final long megaByte = 1024L * 1024L;
for (ServerName serverName : servers) {
ServerLoad serverLoad = clusterStatus.getLoad(serverName);
for (RegionLoad regionLoad : serverLoad.getRegionsLoad().values()) {
byte[] regionId = regionLoad.getName();
if (tableRegions.contains(regionId)) {
long regionSizeBytes = regionLoad.getStorefileSizeMB() * megaByte;
regions.put(regionLoad.getNameAsString(), regionSizeBytes);
}
}
}
} catch (IOException e) {
e.printStackTrace();
}
return regions;
}
public void printStats() throws IOException {
Admin admin = connection.getAdmin();
ClusterStatus status =
admin.getClusterStatus(); // co ClusterStatusExample-1-GetStatus Get the cluster status.
System.out.println("Cluster Status:\n--------------");
System.out.println("HBase Version: " + status.getHBaseVersion());
System.out.println("Version: " + status.getVersion());
System.out.println("Cluster ID: " + status.getClusterId());
System.out.println("Master: " + status.getMaster());
System.out.println("No. Backup Masters: " + status.getBackupMastersSize());
System.out.println("Backup Masters: " + status.getBackupMasters());
System.out.println("No. Live Servers: " + status.getServersSize());
System.out.println("Servers: " + status.getServers());
System.out.println("No. Dead Servers: " + status.getDeadServers());
System.out.println("Dead Servers: " + status.getDeadServerNames());
System.out.println("No. Regions: " + status.getRegionsCount());
System.out.println("Regions in Transition: " + status.getRegionsInTransition());
System.out.println("No. Requests: " + status.getRequestsCount());
System.out.println("Avg Load: " + status.getAverageLoad());
System.out.println("Balancer On: " + status.getBalancerOn());
System.out.println("Is Balancer On: " + status.isBalancerOn());
System.out.println("Master Coprocessors: " + Arrays.asList(status.getMasterCoprocessors()));
System.out.println("\nServer Info:\n--------------");
for (ServerName server :
status
.getServers()) { // co ClusterStatusExample-2-ServerInfo Iterate over the included
// server instances.
System.out.println("Hostname: " + server.getHostname());
System.out.println("Host and Port: " + server.getHostAndPort());
System.out.println("Server Name: " + server.getServerName());
System.out.println("RPC Port: " + server.getPort());
System.out.println("Start Code: " + server.getStartcode());
ServerLoad load =
status.getLoad(
server); // co ClusterStatusExample-3-ServerLoad Retrieve the load details for the
// current server.
System.out.println("\nServer Load:\n--------------");
System.out.println("Info Port: " + load.getInfoServerPort());
System.out.println("Load: " + load.getLoad());
System.out.println("Max Heap (MB): " + load.getMaxHeapMB());
System.out.println("Used Heap (MB): " + load.getUsedHeapMB());
System.out.println("Memstore Size (MB): " + load.getMemstoreSizeInMB());
System.out.println("No. Regions: " + load.getNumberOfRegions());
System.out.println("No. Requests: " + load.getNumberOfRequests());
System.out.println("Total No. Requests: " + load.getTotalNumberOfRequests());
System.out.println("No. Requests per Sec: " + load.getRequestsPerSecond());
System.out.println("No. Read Requests: " + load.getReadRequestsCount());
System.out.println("No. Write Requests: " + load.getWriteRequestsCount());
System.out.println("No. Stores: " + load.getStores());
System.out.println("Store Size Uncompressed (MB): " + load.getStoreUncompressedSizeMB());
System.out.println("No. Storefiles: " + load.getStorefiles());
System.out.println("Storefile Size (MB): " + load.getStorefileSizeInMB());
System.out.println("Storefile Index Size (MB): " + load.getStorefileIndexSizeInMB());
System.out.println("Root Index Size: " + load.getRootIndexSizeKB());
System.out.println("Total Bloom Size: " + load.getTotalStaticBloomSizeKB());
System.out.println("Total Index Size: " + load.getTotalStaticIndexSizeKB());
System.out.println("Current Compacted Cells: " + load.getCurrentCompactedKVs());
System.out.println("Total Compacting Cells: " + load.getTotalCompactingKVs());
System.out.println("Coprocessors1: " + Arrays.asList(load.getRegionServerCoprocessors()));
System.out.println("Coprocessors2: " + Arrays.asList(load.getRsCoprocessors()));
System.out.println("Replication Load Sink: " + load.getReplicationLoadSink());
System.out.println("Replication Load Source: " + load.getReplicationLoadSourceList());
System.out.println("\nRegion Load:\n--------------");
for (Map.Entry<byte[], RegionLoad>
entry : // co ClusterStatusExample-4-Regions Iterate over the region details of the
// current server.
load.getRegionsLoad().entrySet()) {
System.out.println("Region: " + Bytes.toStringBinary(entry.getKey()));
RegionLoad regionLoad =
entry
.getValue(); // co ClusterStatusExample-5-RegionLoad Get the load details for the
// current region.
System.out.println("Name: " + Bytes.toStringBinary(regionLoad.getName()));
System.out.println("Name (as String): " + regionLoad.getNameAsString());
System.out.println("No. Requests: " + regionLoad.getRequestsCount());
System.out.println("No. Read Requests: " + regionLoad.getReadRequestsCount());
System.out.println("No. Write Requests: " + regionLoad.getWriteRequestsCount());
System.out.println("No. Stores: " + regionLoad.getStores());
System.out.println("No. Storefiles: " + regionLoad.getStorefiles());
System.out.println("Data Locality: " + regionLoad.getDataLocality());
System.out.println("Storefile Size (MB): " + regionLoad.getStorefileSizeMB());
System.out.println("Storefile Index Size (MB): " + regionLoad.getStorefileIndexSizeMB());
System.out.println("Memstore Size (MB): " + regionLoad.getMemStoreSizeMB());
System.out.println("Root Index Size: " + regionLoad.getRootIndexSizeKB());
System.out.println("Total Bloom Size: " + regionLoad.getTotalStaticBloomSizeKB());
System.out.println("Total Index Size: " + regionLoad.getTotalStaticIndexSizeKB());
System.out.println("Current Compacted Cells: " + regionLoad.getCurrentCompactedKVs());
System.out.println("Total Compacting Cells: " + regionLoad.getTotalCompactingKVs());
System.out.println();
}
}
}
public void _jspService(HttpServletRequest request, HttpServletResponse response)
throws java.io.IOException, ServletException {
PageContext pageContext = null;
HttpSession session = null;
ServletContext application = null;
ServletConfig config = null;
JspWriter out = null;
Object page = this;
JspWriter _jspx_out = null;
PageContext _jspx_page_context = null;
try {
response.setContentType("text/html; charset=UTF-8");
pageContext = _jspxFactory.getPageContext(this, request, response, null, true, 8192, true);
_jspx_page_context = pageContext;
application = pageContext.getServletContext();
config = pageContext.getServletConfig();
session = pageContext.getSession();
out = pageContext.getOut();
_jspx_out = out;
_jspx_resourceInjector =
(org.apache.jasper.runtime.ResourceInjector)
application.getAttribute("com.sun.appserv.jsp.resource.injector");
out.write('\n');
JobTracker tracker = (JobTracker) application.getAttribute("job.tracker");
ClusterStatus status = tracker.getClusterStatus();
String trackerName = StringUtils.simpleHostname(tracker.getJobTrackerMachine());
out.write("\n<html>\n<head>\n<title>");
out.print(trackerName);
out.write(
" Hadoop Locality Statistics</title>\n<link rel=\"stylesheet\" type=\"text/css\" href=\"/static/hadoop.css\">\n</head>\n<body>\n<h1>");
out.print(trackerName);
out.write(" Hadoop Locality Statistics</h1>\n\n<b>State:</b> ");
out.print(status.getJobTrackerState());
out.write("<br>\n<b>Started:</b> ");
out.print(new Date(tracker.getStartTime()));
out.write("<br>\n<b>Version:</b> ");
out.print(VersionInfo.getVersion());
out.write(",\n r");
out.print(VersionInfo.getRevision());
out.write("<br>\n<b>Compiled:</b> ");
out.print(VersionInfo.getDate());
out.write(" by\n ");
out.print(VersionInfo.getUser());
out.write("<br>\n<b>Identifier:</b> ");
out.print(tracker.getTrackerIdentifier());
out.write("<br>\n\n<hr>\n\n");
Collection<JobInProgress> jobs = new ArrayList<JobInProgress>();
jobs.addAll(tracker.completedJobs());
jobs.addAll(tracker.runningJobs());
jobs.addAll(tracker.failedJobs());
int dataLocalMaps = 0;
int rackLocalMaps = 0;
int totalMaps = 0;
int totalReduces = 0;
for (JobInProgress job : jobs) {
Counters counters = job.getCounters();
dataLocalMaps += counters.getCounter(JobInProgress.Counter.DATA_LOCAL_MAPS);
rackLocalMaps += counters.getCounter(JobInProgress.Counter.RACK_LOCAL_MAPS);
totalMaps += counters.getCounter(JobInProgress.Counter.TOTAL_LAUNCHED_MAPS);
totalReduces += counters.getCounter(JobInProgress.Counter.TOTAL_LAUNCHED_REDUCES);
}
int dataLocalMapPct = totalMaps == 0 ? 0 : (100 * dataLocalMaps) / totalMaps;
int rackLocalMapPct = totalMaps == 0 ? 0 : (100 * rackLocalMaps) / totalMaps;
int dataRackLocalMapPct =
totalMaps == 0 ? 0 : (100 * (dataLocalMaps + rackLocalMaps)) / totalMaps;
out.write("\n<p>\n<b>Data Local Maps:</b> ");
out.print(dataLocalMaps);
out.write(' ');
out.write('(');
out.print(dataLocalMapPct);
out.write("%) <br>\n<b>Rack Local Maps:</b> ");
out.print(rackLocalMaps);
out.write(' ');
out.write('(');
out.print(rackLocalMapPct);
out.write("%) <br>\n<b>Data or Rack Local:</b> ");
out.print(dataLocalMaps + rackLocalMaps);
out.write(' ');
out.write('(');
out.print(dataRackLocalMapPct);
out.write("%) <br>\n<b>Total Maps:</b> ");
out.print(totalMaps);
out.write(" <br>\n<b>Total Reduces:</b> ");
out.print(totalReduces);
out.write(" <br>\n</p>\n\n");
out.println(ServletUtil.htmlFooter());
out.write('\n');
} catch (Throwable t) {
if (!(t instanceof SkipPageException)) {
out = _jspx_out;
if (out != null && out.getBufferSize() != 0) out.clearBuffer();
if (_jspx_page_context != null) _jspx_page_context.handlePageException(t);
}
} finally {
_jspxFactory.releasePageContext(_jspx_page_context);
}
}
static void checkRecords(
Configuration defaults, int noMaps, int noReduces, Path sortInput, Path sortOutput)
throws IOException {
JobConf jobConf = new JobConf(defaults, RecordChecker.class);
jobConf.setJobName("sortvalidate-record-checker");
jobConf.setInputFormat(SequenceFileInputFormat.class);
jobConf.setOutputFormat(SequenceFileOutputFormat.class);
jobConf.setOutputKeyClass(BytesWritable.class);
jobConf.setOutputValueClass(IntWritable.class);
jobConf.setMapperClass(Map.class);
jobConf.setReducerClass(Reduce.class);
JobClient client = new JobClient(jobConf);
ClusterStatus cluster = client.getClusterStatus();
if (noMaps == -1) {
noMaps = cluster.getTaskTrackers() * jobConf.getInt("test.sortvalidate.maps_per_host", 10);
}
if (noReduces == -1) {
noReduces = (int) (cluster.getMaxReduceTasks() * 0.9);
String sortReduces = jobConf.get("test.sortvalidate.reduces_per_host");
if (sortReduces != null) {
noReduces = cluster.getTaskTrackers() * Integer.parseInt(sortReduces);
}
}
jobConf.setNumMapTasks(noMaps);
jobConf.setNumReduceTasks(noReduces);
FileInputFormat.setInputPaths(jobConf, sortInput);
FileInputFormat.addInputPath(jobConf, sortOutput);
Path outputPath = new Path("/tmp/sortvalidate/recordchecker");
FileSystem fs = FileSystem.get(defaults);
if (fs.exists(outputPath)) {
fs.delete(outputPath, true);
}
FileOutputFormat.setOutputPath(jobConf, outputPath);
// Uncomment to run locally in a single process
// job_conf.set("mapred.job.tracker", "local");
Path[] inputPaths = FileInputFormat.getInputPaths(jobConf);
System.out.println(
"\nSortValidator.RecordChecker: Running on "
+ cluster.getTaskTrackers()
+ " nodes to validate sort from "
+ inputPaths[0]
+ ", "
+ inputPaths[1]
+ " into "
+ FileOutputFormat.getOutputPath(jobConf)
+ " with "
+ noReduces
+ " reduces.");
Date startTime = new Date();
System.out.println("Job started: " + startTime);
JobClient.runJob(jobConf);
Date end_time = new Date();
System.out.println("Job ended: " + end_time);
System.out.println(
"The job took " + (end_time.getTime() - startTime.getTime()) / 1000 + " seconds.");
}
