[
https://issues.apache.org/jira/browse/HIVE-23880?focusedWorklogId=461959&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-461959
]
ASF GitHub Bot logged work on HIVE-23880:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 22/Jul/20 10:16
Start Date: 22/Jul/20 10:16
Worklog Time Spent: 10m
Work Description: abstractdog commented on a change in pull request #1280:
URL: https://github.com/apache/hive/pull/1280#discussion_r458688040
##########
File path: storage-api/src/java/org/apache/hive/common/util/BloomKFilter.java
##########
@@ -527,20 +527,19 @@ public void add(ElementWrapper wrapper) {
@Override
public void run() {
while (!executor.isTerminated() && !queue.isEmpty()) {
Review comment:
thanks, your comment regarding isTerminated check seems valid, let me
think that over
queue.isEmpty() check is needed I think, please a take a look at the
implementation above, every thread uses its own queue (which is filled in
advance), there is no concurrency between them, so queue.isEmpty() is a simple
check for every thread that "whether I have further things to do, or I can
quit", this way every thread will quit once they're ready, so
executor.awaitTermination will return and we're done
----------------------------------------------------------------
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:
us...@infra.apache.org
Issue Time Tracking
-------------------
Worklog Id: (was: 461959)
Time Spent: 1h 20m (was: 1h 10m)
> Bloom filters can be merged in a parallel way in VectorUDAFBloomFilterMerge
> ---------------------------------------------------------------------------
>
> Key: HIVE-23880
> URL: https://issues.apache.org/jira/browse/HIVE-23880
> Project: Hive
> Issue Type: Improvement
> Reporter: László Bodor
> Assignee: László Bodor
> Priority: Major
> Labels: pull-request-available
> Attachments: lipwig-output3605036885489193068.svg
>
> Time Spent: 1h 20m
> Remaining Estimate: 0h
>
> Merging bloom filters in semijoin reduction can become the main bottleneck in
> case of large number of source mapper tasks (~1000, Map 1 in below example)
> and a large amount of expected entries (50M) in bloom filters.
> For example in TPCDS Q93:
> {code}
> select /*+ semi(store_returns, sr_item_sk, store_sales, 70000000)*/
> ss_customer_sk
> ,sum(act_sales) sumsales
> from (select ss_item_sk
> ,ss_ticket_number
> ,ss_customer_sk
> ,case when sr_return_quantity is not null then
> (ss_quantity-sr_return_quantity)*ss_sales_price
> else
> (ss_quantity*ss_sales_price) end act_sales
> from store_sales left outer join store_returns on (sr_item_sk =
> ss_item_sk
> and
> sr_ticket_number = ss_ticket_number)
> ,reason
> where sr_reason_sk = r_reason_sk
> and r_reason_desc = 'reason 66') t
> group by ss_customer_sk
> order by sumsales, ss_customer_sk
> limit 100;
> {code}
> On 10TB-30TB scale there is a chance that from 3-4 mins of query runtime 1-2
> mins are spent with merging bloom filters (Reducer 2), as in:
> [^lipwig-output3605036885489193068.svg]
> {code}
> ----------------------------------------------------------------------------------------------
> VERTICES MODE STATUS TOTAL COMPLETED RUNNING PENDING
> FAILED KILLED
> ----------------------------------------------------------------------------------------------
> Map 3 .......... llap SUCCEEDED 1 1 0 0
> 0 0
> Map 1 .......... llap SUCCEEDED 1263 1263 0 0
> 0 0
> Reducer 2 llap RUNNING 1 0 1 0
> 0 0
> Map 4 llap RUNNING 6154 0 207 5947
> 0 0
> Reducer 5 llap INITED 43 0 0 43
> 0 0
> Reducer 6 llap INITED 1 0 0 1
> 0 0
> ----------------------------------------------------------------------------------------------
> VERTICES: 02/06 [====>>----------------------] 16% ELAPSED TIME: 149.98 s
> ----------------------------------------------------------------------------------------------
> {code}
> For example, 70M entries in bloom filter leads to a 436 465 696 bits, so
> merging 1263 bloom filters means running ~ 1263 * 436 465 696 bitwise OR
> operation, which is very hot codepath, but can be parallelized.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
