[HIVE-4486] FetchOperator slows down SMB map joins by 50% when there are many partitions

• Type: Bug
• Status: Closed
• Priority: Minor
• Resolution: Fixed
• Affects Version/s: 0.12.0
• Fix Version/s: 0.12.0, 0.11.1
• Component/s: Query Processor

Environment

Ubuntu LXC 12.10

• Release Note: Avoid creating new HiveConf() within the FetchOperator loop
• Assignee: Gopal Vijayaraghavan
• Reporter: Gopal Vijayaraghavan
• Created: 03/May/13 13:55
• Updated: 15/Oct/13 23:30
• Resolved: 17/May/13 15:45

Description

While looking at log files for SMB joins in hive, it was noticed that the actual join op didn't show up as a significant fraction of the time spent. Most of the time was spent parsing configuration files.

To confirm, I put log lines in the HiveConf constructor and eventually made the following edit to the code

--- ql/src/java/org/apache/hadoop/hive/ql/exec/FetchOperator.java
+++ ql/src/java/org/apache/hadoop/hive/ql/exec/FetchOperator.java
@@ -648,8 +648,7 @@ public ObjectInspector getOutputObjectInspector() throws HiveException {
    * @return list of file status entries
    */
   private FileStatus[] listStatusUnderPath(FileSystem fs, Path p) throws IOException {
-    HiveConf hiveConf = new HiveConf(job, FetchOperator.class);
-    boolean recursive = hiveConf.getBoolVar(HiveConf.ConfVars.HADOOPMAPREDINPUTDIRRECURSIVE);
+    boolean recursive = false;
     if (!recursive) {
       return fs.listStatus(p);
     }

And re-ran my query to compare timings.

	Before	After
Cumulative CPU	731.07 sec	386.0 sec
Total time	347.66 seconds	218.855 seconds

The query used was

INSERT OVERWRITE LOCAL DIRECTORY
'/grid/0/smb/'
select inv_item_sk
from
     inventory inv
     join store_sales ss on (ss.ss_item_sk = inv.inv_item_sk)
limit 100000
;

On a scale=2 tpcds data-set, where both store_sales & inventory are bucketed into 4 buckets, with store_sales split into 7 partitions and inventory into 261 partitions.

78% of all CPU time was spent within new HiveConf(). The yourkit profiler runs are attached.

Issue Links

• relates to: HADOOP-9570 Configuration.addResource() should only parse the new resource