Re: How many threads impala start for handling partitioned join?

The multithreading effort is still ongoing. Joins, in particular, are not executed with multiple threads yet. Not sure if I completely followed your last two questions, please correct me if I misunderstood. The general idea of the multithreading effort is to start multiple fragment instances per

Re: performance issue on big table join

Hi, Looks like you are joining store_sales with catalog_sales on item_sk, this kind of join condition is a many to many, which means the output number of rows will be much larger then input number of rows, not sure if this is intended. Also did you run "compute stats [TABLE_NAME]" on both

Re: performance issue on big table join

The profile file is damaged. Here is a screenshot for exec summary ​ 2017-10-27 10:04 GMT+08:00 俊杰陈 : > Hi Devs > > I met a performance issue on big table join. The query takes more than 3 > hours on Impala and only 3 minutes on Spark SQL on the same 5 nodes > cluster. when

performance issue on big table join

Hi Devs I met a performance issue on big table join. The query takes more than 3 hours on Impala and only 3 minutes on Spark SQL on the same 5 nodes cluster. when running query, the left scanner and exchange node are very slow. Did I miss some key arguments? you can see profile file in

Re: Unknown clang-tidy failure in GVO

I think the actual failure was this: *16:13:18* + grep ']' /home/ubuntu/tidylog.txt*16:13:18* /home/ubuntu/Impala/be/src/rpc/thrift-server-test.cc:105:26: warning: extra ';' after member function definition [clang-diagnostic-extra-semi]*16:13:18*

Re: Unknown clang-tidy failure in GVO

At the bottom of https://jenkins.impala.io/job/clang-tidy-ub1604/78/consoleFull I see: *16:05:31* + bin/run_clang_tidy.sh*16:13:18* + grep ']' /home/ubuntu/tidylog.txt*16:13:18* /home/ubuntu/Impala/be/src/rpc/thrift-server-test.cc:105:26: warning: extra ';' after member function definition

Unknown clang-tidy failure in GVO

Does anyone know the cause for this failure in the clang-tidy run in GVO? It's something to do with hadoop-lzo. https://jenkins.impala.io/job/clang-tidy-ub1604/78/consoleFull *15:52:44* [javadoc] Generating /home/ubuntu/hadoop-lzo/build/docs/api/help-doc.html...*15:52:44* [javadoc] 1

Re: Please hold off merging new code changes

Thanks Tim, for the update. On Thu, Oct 26, 2017 at 9:53 AM, Tim Armstrong wrote: > It looks like tests are more stable for me now so I think we can continue > merging changes. Please put in as much effort as reasonable to make sure > that your changes don't add to test

Re: Parquet min/max statistics & null values

Hi Bruno, Could you provide an example of the specific predicates that aren't being used to successfully skip the row group? - Tim On Thu, Oct 26, 2017 at 7:21 AM, Jeszy wrote: > Hello Bruno, > > Thanks for bringing this up. While not apparent from the commit > comments,

Re: Please hold off merging new code changes

It looks like tests are more stable for me now so I think we can continue merging changes. Please put in as much effort as reasonable to make sure that your changes don't add to test flakiness. - Tim On Wed, Oct 25, 2017 at 2:51 PM, Tim Armstrong wrote: > A few recent

New Impala Contributors: IMPALA-941

If you'd like to contribute a patch to Impala, but aren't sure what you want to work on, you can look at Impala's newbie issues: https://issues.apache.org/jira/issues/?filter=12341668. You can find detailed instructions on submitting patches at