You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@impala.apache.org by ta...@apache.org on 2019/05/14 22:43:04 UTC

[impala] 04/06: IMPALA-7228: Add tpcds-unmodified to single-node-perf-run

This is an automated email from the ASF dual-hosted git repository.

tarmstrong pushed a commit to branch 2.x
in repository https://gitbox.apache.org/repos/asf/impala.git

commit 43e54501cece5e4d4a2f8c483465dd81d8b6a115
Author: njanarthanan <nj...@cloudera.com>
AuthorDate: Thu Jul 12 14:18:10 2018 -0700

    IMPALA-7228: Add tpcds-unmodified to single-node-perf-run
    
    Description:
    tpcds-unmodified workload was added as a part of IMPALA-6819.
    This change allows tpcds-unmodified workload to be available
    for the single node perf run.
    
    Testing:
    Ran single node perf run using the following parameters and the
    test run was successful
    
    --iterations 2 --scale 2 --table_formats "parquet/none" \
    --num_impalads 1 --workload "tpcds-unmodified" \
    --load --query_names "TPCDS-Q17.*" --start_minicluster
    
    Change-Id: I511661c586cd55e3240ccbea9c499b9c3fc98440
    Reviewed-on: http://gerrit.cloudera.org:8080/10931
    Reviewed-by: Impala Public Jenkins <im...@cloudera.com>
    Reviewed-by: Jim Apple <jb...@apache.org>
    Tested-by: Impala Public Jenkins <im...@cloudera.com>
---
 bin/single_node_perf_run.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/bin/single_node_perf_run.py b/bin/single_node_perf_run.py
index c49e8e0..c931266 100755
--- a/bin/single_node_perf_run.py
+++ b/bin/single_node_perf_run.py
@@ -227,7 +227,8 @@ def perf_ab_test(options, args):
   workloads = set(options.workloads.split(","))
 
   if options.load:
-    WORKLOAD_TO_DATASET = {"tpch": "tpch", "tpcds": "tpcds", "targeted-perf": "tpch"}
+    WORKLOAD_TO_DATASET = {"tpch": "tpch", "tpcds": "tpcds", "targeted-perf": "tpch",
+                           "tpcds-unmodified": "tpcds-unmodified"}
     datasets = set([WORKLOAD_TO_DATASET[workload] for workload in workloads])
     for dataset in datasets:
       load_data(dataset, options.table_formats, options.scale)