[Impala-ASF-CR] IMPALA-5483: Automatically disable codegen for small queries

["Tim Armstrong (Code Review)" <ge...@cloudera.org>]

Tim Armstrong has uploaded a new patch set (#3).

Change subject: IMPALA-5483: Automatically disable codegen for small queries
......................................................................

IMPALA-5483: Automatically disable codegen for small queries

This is similar to the single-node execution optimisation, but applies
to slightly larger queries that should run in a distributed manner but
won't benefit from codegen.

This adds a new query option disable_codegen_rows_threshold that
defaults to 50,000. If fewer than this number of rows are processed
by a plan node per impalad, the cost of codegen almost certainly
outweighs the benefit.

Using rows processed as a threshold is justified by a simple
model that assumes the cost of codegen and execution per row for
the same operation are proportional. E.g. if x is the complexity
of the operation, n is the number of rows processed, C is a
constant factor giving the cost of codegen and Ec/Ei are constant
factor giving the cost of codegen'd and interpreted execution and
d, then the cost of the codegen'd operator is C * x + Ec * x * n
and the cost of the interpreted operator is Ei * x * n. Rearranging
means that interpretation is cheaper if n < C / (Ei - Ec), i.e. that
(at least with the simplified model) it makes sense to choose
interpretation or codegen based on a constant threshold. The
model also implies that it is somewhat safer to choose codegen
because the additional cost of codegen is O(1) but the additional
cost of interpretation is O(n).

I ran some experiments with TPC-H Q1, varying the input table size, to
determine what the cut-over point where codegen was beneficial was.
The cutover was around 150k rows per node for both text and parquet.
At 50k rows per node disabling codegen was very beneficial - around
0.12s versus 0.24s.  To be somewhat conservative I set the default
threshold to 50k rows. On more complex queries, e.g. TPC-H Q10, the
cutover tends to be higher because there are plan nodes that process
many fewer than the max rows.

Fix a couple of minor issues in the frontend - the numNodes_
calculation could return 0 for Kudu, and the single node optimization
didn't handle the case where for a scan node with conjuncts, a limit
and missing stats correctly (it considered the estimate still valid.)

Testing:
Updated e2e tests that set disable_codegen to set
disable_codegen_rows_threshold to 0, so that those tests run both
with and without codegen still.

Added an e2e test to make sure that the optimisation is applied in
the backend.

Perf:
Added a targeted perf test for a join+agg over a small input, which
benefits from this change.

Change-Id: I273bcee58641f5b97de52c0b2caab043c914b32e
---
M be/src/exprs/expr-test.cc
M be/src/service/query-options.cc
M be/src/service/query-options.h
M common/thrift/ImpalaInternalService.thrift
M common/thrift/ImpalaService.thrift
M fe/src/main/java/org/apache/impala/planner/HBaseScanNode.java
M fe/src/main/java/org/apache/impala/planner/KuduScanNode.java
M fe/src/main/java/org/apache/impala/planner/Planner.java
M fe/src/main/java/org/apache/impala/util/MaxRowsProcessedVisitor.java
A testdata/workloads/functional-query/queries/QueryTest/codegen.test
A testdata/workloads/targeted-perf/queries/primitive_small_join_1.test
M tests/common/impala_test_suite.py
M tests/common/test_dimensions.py
A tests/query_test/test_codegen.py
M tests/query_test/test_decimal_queries.py
M tests/query_test/test_scanners_fuzz.py
M tests/query_test/test_udfs.py
17 files changed, 198 insertions(+), 41 deletions(-)


  git pull ssh://gerrit.cloudera.org:29418/Impala-ASF refs/changes/53/7153/3
-- 
To view, visit http://gerrit.cloudera.org:8080/7153
To unsubscribe, visit http://gerrit.cloudera.org:8080/settings

Gerrit-MessageType: newpatchset
Gerrit-Change-Id: I273bcee58641f5b97de52c0b2caab043c914b32e
Gerrit-PatchSet: 3
Gerrit-Project: Impala-ASF
Gerrit-Branch: master
Gerrit-Owner: Tim Armstrong <ta...@cloudera.com>