jcamachor commented on a change in pull request #794: HIVE-21884
URL: https://github.com/apache/hive/pull/794#discussion_r332272923
##########
File path:
ql/src/java/org/apache/hadoop/hive/ql/schq/ScheduledQueryExecutionService.java
##########
@@ -0,0 +1,159 @@
+package org.apache.hadoop.hive.ql.schq;
+
+import java.io.Closeable;
+import java.io.IOException;
+import java.util.concurrent.ExecutorService;
+import java.util.concurrent.Executors;
+import java.util.concurrent.TimeUnit;
+
+import org.apache.hadoop.hive.conf.HiveConf;
+import org.apache.hadoop.hive.metastore.api.QueryState;
+import org.apache.hadoop.hive.metastore.api.ScheduledQueryPollResponse;
+import org.apache.hadoop.hive.metastore.api.ScheduledQueryProgressInfo;
+import org.apache.hadoop.hive.ql.DriverFactory;
+import org.apache.hadoop.hive.ql.IDriver;
+import org.apache.hadoop.hive.ql.processors.CommandProcessorResponse;
+import org.apache.hadoop.hive.ql.session.SessionState;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+
+import com.google.common.annotations.VisibleForTesting;
+import com.google.common.util.concurrent.ThreadFactoryBuilder;
+
+public class ScheduledQueryExecutionService implements Closeable {
+
+ private static final Logger LOG =
LoggerFactory.getLogger(ScheduledQueryExecutionService.class);
+
+ private ScheduledQueryExecutionContext context;
+ private ScheduledQueryExecutor worker;
+
+ public static ScheduledQueryExecutionService
startScheduledQueryExecutorService(HiveConf conf) {
+ MetastoreBasedScheduledQueryService qService = new
MetastoreBasedScheduledQueryService(conf);
+ ExecutorService executor =
+ Executors.newCachedThreadPool(
+ new
ThreadFactoryBuilder().setDaemon(true).setNameFormat("Scheduled Query Thread
%d").build());
+ ScheduledQueryExecutionContext ctx = new
ScheduledQueryExecutionContext(executor, conf, qService);
+ return new ScheduledQueryExecutionService(ctx);
+ }
+
+ public ScheduledQueryExecutionService(ScheduledQueryExecutionContext ctx) {
+ context = ctx;
+ ctx.executor.submit(worker = new ScheduledQueryExecutor());
+ ctx.executor.submit(new ProgressReporter());
+ }
+
+ class ScheduledQueryExecutor implements Runnable {
+
+ private ScheduledQueryProgressInfo info;
+
+ @Override
+ public void run() {
+ while (true) {
+ ScheduledQueryPollResponse q =
context.schedulerService.scheduledQueryPoll();
+ if (q.isSetExecutionId()) {
+ try{
+ processQuery(q);
+ } catch (Throwable t) {
+ LOG.error("Unexpected exception during scheduled query
processing", t);
+ }
+ } else {
+ try {
+ Thread.sleep(context.getIdleSleepTime());
+ } catch (InterruptedException e) {
+ Thread.currentThread().interrupt();
+ LOG.info("interrupted");
+ break;
+ }
+ }
+ }
+ }
+
+ QueryState lastState;
+ public synchronized void reportQueryProgress() {
Review comment:
Are we synchronizing this in case two requests asked for status after each
other and the first one did not return? Should we do something for the check
interval here so we do not end up with a lot of requests block here, e.g.,
exponential backoff or simply skipping query progress (and reporting it)?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
