Skip to content

minor(test): cover partially ordered aggregate spilling #23947

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
buraksenn wants to merge 2 commits into
base: main
Choose a base branch
from
+52 −0
Open

minor(test): cover partially ordered aggregate spilling #23947

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d7a29d9
test: cover partially ordered aggregate spilling
buraksenn Jul 28, 2026
5f5470e
refactor to slt test instead of rust
buraksenn Jul 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
52 changes: 52 additions & 0 deletions datafusion/sqllogictest/test_files/ordered_aggregate_spill.slt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,6 +176,58 @@ Plan with Metrics
03)----AggregateExec: mode=Partial,<slt:ignore>aggr=[sum(t1.v1 * Int64(2)), min(t1.v1 % Int64(2))], ordering_mode=PartiallySorted([0]), metrics=[<slt:ignore>spill_count=0,<slt:ignore>]
<slt:ignore>

# ==================================================================================
# Single mode: with one partition the whole aggregation runs in a `Single` mode
# AggregateExec. min() keeps one intermediate state and avg() keeps two (sum +
# count), so both single- and multi-state accumulators are spilled and merged.
# ==================================================================================

statement ok
SET datafusion.execution.target_partitions = 1

# Reference round: enough memory to aggregate without spilling.
statement ok
SET datafusion.runtime.memory_limit = '10M'

query TT
EXPLAIN ANALYZE
SELECT round(v1, -4), v1 % 5000, min(v1 * 2), avg(v1)
FROM generate_series(20000) AS t1(v1)
GROUP BY round(v1, -4), v1 % 5000
----
Plan with Metrics
01)AggregateExec: mode=Single,<slt:ignore>aggr=[min(t1.v1 * Int64(2)), avg(t1.v1)], ordering_mode=PartiallySorted([0]), metrics=[<slt:ignore>spill_count=0,<slt:ignore>]
<slt:ignore>

query IIIR rowsort
SELECT round(v1, -4), v1 % 5000, min(v1 * 2), avg(v1)
FROM generate_series(20000) AS t1(v1)
GROUP BY round(v1, -4), v1 % 5000
----
60000 values hashing to 872df6cefd51f81820fc5c6e5d7480df

# Spilling round: the same query under a 600 KB limit must spill.
statement ok
SET datafusion.runtime.memory_limit = '600K'

query TT
EXPLAIN ANALYZE
SELECT round(v1, -4), v1 % 5000, min(v1 * 2), avg(v1)
FROM generate_series(20000) AS t1(v1)
GROUP BY round(v1, -4), v1 % 5000
----
Plan with Metrics
01)AggregateExec: mode=Single,<slt:ignore>aggr=[min(t1.v1 * Int64(2)), avg(t1.v1)], ordering_mode=PartiallySorted([0]), metrics=[<slt:ignore>spilled_bytes=<slt:ignore> KB,<slt:ignore>]
<slt:ignore>

# Same result hash as the no-spill round above
query IIIR rowsort
SELECT round(v1, -4), v1 % 5000, min(v1 * 2), avg(v1)
FROM generate_series(20000) AS t1(v1)
GROUP BY round(v1, -4), v1 % 5000
----
60000 values hashing to 872df6cefd51f81820fc5c6e5d7480df

statement ok
RESET datafusion.runtime.memory_limit

Expand Down
Loading