mirror of
https://github.com/apache/impala.git
synced 2025-12-25 02:03:09 -05:00
04edc8f534
This change updates the run-benchmark script to enable it to target one or more workloads. Now benchmarks can be run like: ./run-benchmark --workloads=hive-benchmark,tpch We lookup the workload in the workloads directory, then read the associated query .test files and start executing them. To ensure the queries are not duplicated between benchmark and query tests, I moved all existing queries (under fe/src/test/resources/* to the workloads directory. You do NOT need to look through all the .test files, I've just moved them. The one new file is the 'hive-benchmark.test' which contains the hive benchmark queries. Also added support for generating schema for different scale factors as well as executing against these scale factors. For example, let's say we have a dataset with a scale factor called "SF1". We would first generate the schema using: ./generate_schema_statements --workload=<workload> --scale_factor="SF3" This will create tables with a unique names from the other scale factors. Run the generated .sql file to load the data. Alternatively, the data can loaded by running a new python script: ./bin/load-data.py -w <workload1>,<workload2> -e <exploration strategy> -s [scale factor] For example: load-data.sh -w tpch -e core -s SF3 Then run against this: ./run-benchmark --workloads=<workload> --scale_factor=SF3 This changeset also includes a few other minor tweaks to some of the test scripts. Change-Id: Ife8a8d91567d75c9612be37bec96c1e7780f50d6
105 lines
1.5 KiB
Plaintext
105 lines
1.5 KiB
Plaintext
# predicate on row key col is applied to scan if row key is mapped as string col
|
|
select count(*)
|
|
from hbasestringids
|
|
where id = '5'
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
1
|
|
====
|
|
# predicate on row key col is not applied to scan if row key is mapped as non-string col
|
|
# but the result is still correct
|
|
select count(*)
|
|
from hbasealltypesagg
|
|
where id = 5
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
1
|
|
====
|
|
# ids are stored in ascii and ordered lexicographically
|
|
# exclusive upper bound
|
|
select count(*)
|
|
from hbasestringids
|
|
where id < '5'
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
4445
|
|
====
|
|
# inclusive upper bound
|
|
select count(*)
|
|
from hbasestringids
|
|
where id <= '5'
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
4446
|
|
====
|
|
# inclusive lower bound
|
|
select count(*)
|
|
from hbasestringids
|
|
where id >= '6'
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
4444
|
|
====
|
|
# exclusive lower bound
|
|
select count(*)
|
|
from hbasestringids
|
|
where id > '6'
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
4443
|
|
====
|
|
# combinations
|
|
select count(*)
|
|
from hbasestringids
|
|
where id > '5'
|
|
and id < '6'
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
1110
|
|
====
|
|
select count(*)
|
|
from hbasestringids
|
|
where id >= '5'
|
|
and id < '6'
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
1111
|
|
====
|
|
select count(*)
|
|
from hbasestringids
|
|
where id > '5'
|
|
and id <= '6'
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
1111
|
|
====
|
|
select count(*)
|
|
from hbasestringids
|
|
where id >= '5'
|
|
and id <= '6'
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
1112
|
|
====
|
|
# predicates on non-key cols are evaluated in the executor
|
|
# and non-string comparisons work
|
|
select count(*)
|
|
from hbasestringids
|
|
where id < '5'
|
|
and smallint_col < 5
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
180
|
|
====
|