public Object invoke(Object proxy, Method method, Object[] args) throws Throwable {
final boolean logDebug = LOG.isDebugEnabled();
long startTime = 0;
if (logDebug) {
startTime = System.currentTimeMillis();
}
ObjectWritable value = null;
try {
value =
(ObjectWritable)
client.call(
new Invocation(method, args), getAddress(), protocol, ticket, rpcTimeout);
} catch (RemoteException re) {
throw re;
} catch (ConnectException ce) {
needCheckDnsUpdate = true;
throw ce;
} catch (NoRouteToHostException nrhe) {
needCheckDnsUpdate = true;
throw nrhe;
} catch (PortUnreachableException pue) {
needCheckDnsUpdate = true;
throw pue;
} catch (UnknownHostException uhe) {
needCheckDnsUpdate = true;
throw uhe;
}
if (logDebug) {
long callTime = System.currentTimeMillis() - startTime;
LOG.debug("Call: " + method.getName() + " " + callTime);
}
return value.get();
}
public void inject(Path crawlDb, Path urlDir) throws IOException {
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
long start = System.currentTimeMillis();
if (LOG.isInfoEnabled()) {
LOG.info("Injector: starting at " + sdf.format(start));
LOG.info("Injector: crawlDb: " + crawlDb);
LOG.info("Injector: urlDir: " + urlDir);
}
Path tempDir =
new Path(
getConf().get("mapred.temp.dir", ".")
+ "/inject-temp-"
+ Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));
// map text input file to a <url,CrawlDatum> file
if (LOG.isInfoEnabled()) {
LOG.info("Injector: Converting injected urls to crawl db entries.");
}
JobConf sortJob = new NutchJob(getConf());
sortJob.setJobName("inject " + urlDir);
FileInputFormat.addInputPath(sortJob, urlDir);
sortJob.setMapperClass(InjectMapper.class);
FileOutputFormat.setOutputPath(sortJob, tempDir);
sortJob.setOutputFormat(SequenceFileOutputFormat.class);
sortJob.setOutputKeyClass(Text.class);
sortJob.setOutputValueClass(CrawlDatum.class);
sortJob.setLong("injector.current.time", System.currentTimeMillis());
RunningJob mapJob = JobClient.runJob(sortJob);
long urlsInjected = mapJob.getCounters().findCounter("injector", "urls_injected").getValue();
long urlsFiltered = mapJob.getCounters().findCounter("injector", "urls_filtered").getValue();
LOG.info("Injector: total number of urls rejected by filters: " + urlsFiltered);
LOG.info(
"Injector: total number of urls injected after normalization and filtering: "
+ urlsInjected);
// merge with existing crawl db
if (LOG.isInfoEnabled()) {
LOG.info("Injector: Merging injected urls into crawl db.");
}
JobConf mergeJob = CrawlDb.createJob(getConf(), crawlDb);
FileInputFormat.addInputPath(mergeJob, tempDir);
mergeJob.setReducerClass(InjectReducer.class);
JobClient.runJob(mergeJob);
CrawlDb.install(mergeJob, crawlDb);
// clean up
FileSystem fs = FileSystem.get(getConf());
fs.delete(tempDir, true);
long end = System.currentTimeMillis();
LOG.info(
"Injector: finished at "
+ sdf.format(end)
+ ", elapsed: "
+ TimingUtil.elapsedTime(start, end));
}
public Writable call(Class<?> protocol, Writable param, long receivedTime) throws IOException {
try {
Invocation call = (Invocation) param;
if (verbose) log("Call: " + call);
Method method = protocol.getMethod(call.getMethodName(), call.getParameterClasses());
method.setAccessible(true);
int qTime = (int) (System.currentTimeMillis() - receivedTime);
long startNanoTime = System.nanoTime();
Object value = method.invoke(instance, call.getParameters());
long processingMicroTime = (System.nanoTime() - startNanoTime) / 1000;
if (LOG.isDebugEnabled()) {
LOG.debug(
"Served: "
+ call.getMethodName()
+ " queueTime (millisec)= "
+ qTime
+ " procesingTime (microsec)= "
+ processingMicroTime);
}
rpcMetrics.rpcQueueTime.inc(qTime);
rpcMetrics.rpcProcessingTime.inc(processingMicroTime);
MetricsTimeVaryingRate m =
(MetricsTimeVaryingRate) rpcMetrics.registry.get(call.getMethodName());
if (m == null) {
try {
m = new MetricsTimeVaryingRate(call.getMethodName(), rpcMetrics.registry);
} catch (IllegalArgumentException iae) {
// the metrics has been registered; re-fetch the handle
LOG.debug("Error register " + call.getMethodName(), iae);
m = (MetricsTimeVaryingRate) rpcMetrics.registry.get(call.getMethodName());
}
}
// record call time in microseconds
m.inc(processingMicroTime);
if (verbose) log("Return: " + value);
return new ObjectWritable(method.getReturnType(), value);
} catch (InvocationTargetException e) {
Throwable target = e.getTargetException();
if (target instanceof IOException) {
throw (IOException) target;
} else {
IOException ioe = new IOException(target.toString());
ioe.setStackTrace(target.getStackTrace());
throw ioe;
}
} catch (Throwable e) {
if (!(e instanceof IOException)) {
LOG.error("Unexpected throwable object ", e);
}
IOException ioe = new IOException(e.toString());
ioe.setStackTrace(e.getStackTrace());
throw ioe;
}
}
/**
* Get a proxy connection to a remote server
*
* @param protocol protocol class
* @param clientVersion client version
* @param addr remote address
* @param conf configuration to use
* @param rpcTimeout timeout for each RPC
* @param timeout time in milliseconds before giving up
* @return the proxy
* @throws IOException if the far end through a RemoteException
*/
static <T extends VersionedProtocol> ProtocolProxy<T> waitForProtocolProxy(
Class<T> protocol,
long clientVersion,
InetSocketAddress addr,
Configuration conf,
long timeout,
int rpcTimeout)
throws IOException {
long startTime = System.currentTimeMillis();
UserGroupInformation ugi = null;
try {
ugi = UserGroupInformation.login(conf);
} catch (LoginException le) {
throw new RuntimeException("Couldn't login!");
}
IOException ioe;
while (true) {
try {
return getProtocolProxy(
protocol,
clientVersion,
addr,
ugi,
conf,
NetUtils.getDefaultSocketFactory(conf),
rpcTimeout);
} catch (ConnectException se) { // namenode has not been started
LOG.info("Server at " + addr + " not available yet, Zzzzz...");
ioe = se;
} catch (SocketTimeoutException te) { // namenode is busy
LOG.info("Problem connecting to server: " + addr);
ioe = te;
}
// check if timed out
if (System.currentTimeMillis() - timeout >= startTime) {
throw ioe;
}
// wait for retry
try {
Thread.sleep(1000);
} catch (InterruptedException ie) {
// IGNORE
}
}
}
private synchronized InetSocketAddress getAddress() {
if (needCheckDnsUpdate
&& address != null
&& address.getHostName() != null
&& System.currentTimeMillis() - this.timeLastDnsCheck > MIN_DNS_CHECK_INTERVAL_MSEC) {
try {
InetSocketAddress newAddr = NetUtils.resolveAddress(address);
if (newAddr != null) {
LOG.info("DNS change: " + newAddr);
address = newAddr;
}
} finally {
this.timeLastDnsCheck = System.currentTimeMillis();
}
}
needCheckDnsUpdate = false;
return address;
}
public void configure(JobConf job) {
this.jobConf = job;
urlNormalizers = new URLNormalizers(job, URLNormalizers.SCOPE_INJECT);
interval = jobConf.getInt("db.fetch.interval.default", 2592000);
filters = new URLFilters(jobConf);
scfilters = new ScoringFilters(jobConf);
scoreInjected = jobConf.getFloat("db.score.injected", 1.0f);
curTime = job.getLong("injector.current.time", System.currentTimeMillis());
}
