mirror of
https://github.com/GreptimeTeam/greptimedb.git
synced 2026-10-12 06:52:34 +00:00
test: compare raw and preaggregated join SQL on controlled layouts
Signed-off-by: discord9 <55937128+discord9@users.noreply.github.com>
This commit is contained in:
discord9
@@ -0,0 +1,203 @@
|
||||
# WeightedAVG raw join versus host/area factorization; fixed direct-SST layout.
|
||||
# Each measurement is timed separately. The query list deliberately puts raw
|
||||
# first; compare with that ordering limitation in mind.
|
||||
|
||||
[case]
|
||||
name = "paper_ffx_balanced"
|
||||
description = "Raw versus factorized weightedAVG at a balanced join cardinality"
|
||||
|
||||
[scenario]
|
||||
kind = "direct_readable_sst"
|
||||
seed = 5204
|
||||
|
||||
[[scenario.tables]]
|
||||
database = "public"
|
||||
name = "paper_ffx_balanced_fact"
|
||||
engine = "mito"
|
||||
append_mode = true
|
||||
sst_format = "flat"
|
||||
primary_key = ["host", "instance"]
|
||||
time_index = "ts"
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "host"
|
||||
type = "STRING"
|
||||
semantic = "tag"
|
||||
distribution = { kind = "cardinality", values = 16, prefix = "h" }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "instance"
|
||||
type = "STRING"
|
||||
semantic = "tag"
|
||||
distribution = { kind = "cardinality", values = 80, prefix = "i" }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "metric_value"
|
||||
type = "DOUBLE"
|
||||
semantic = "field"
|
||||
distribution = { kind = "deterministic_wave", min = 1.0, max = 500.0 }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "ts"
|
||||
type = "TIMESTAMP(9)"
|
||||
semantic = "timestamp"
|
||||
|
||||
[[scenario.tables]]
|
||||
database = "public"
|
||||
name = "paper_ffx_balanced_dim"
|
||||
engine = "mito"
|
||||
append_mode = true
|
||||
sst_format = "flat"
|
||||
primary_key = ["host", "area"]
|
||||
time_index = "ts"
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "host"
|
||||
type = "STRING"
|
||||
semantic = "tag"
|
||||
distribution = { kind = "cardinality", values = 16, prefix = "h" }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "area"
|
||||
type = "STRING"
|
||||
semantic = "tag"
|
||||
distribution = { kind = "cardinality", values = 5, prefix = "a" }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "weight"
|
||||
type = "DOUBLE"
|
||||
semantic = "field"
|
||||
distribution = { kind = "deterministic_wave", min = 0.1, max = 10.0 }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "ts"
|
||||
type = "TIMESTAMP(9)"
|
||||
semantic = "timestamp"
|
||||
|
||||
[scenario.layout]
|
||||
regions = 1
|
||||
sst_count = 4
|
||||
rows_per_sst = 1280
|
||||
row_group_size = 128
|
||||
series_count = 80
|
||||
start_unix_nanos = 1704067200000000000
|
||||
step_nanos = 1000000000
|
||||
time_range_layout = "non_overlapping_per_sst"
|
||||
series_layout = "round_robin"
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "raw_wide"
|
||||
kind = "sql"
|
||||
query = "SELECT f.host, d.area, AVG(f.metric_value * d.weight) AS score FROM paper_ffx_balanced_fact f JOIN paper_ffx_balanced_dim d ON f.host = d.host WHERE f.ts >= TIMESTAMP '2024-01-01 00:00:00' AND f.ts < TIMESTAMP '2024-01-01 01:25:20' AND d.ts >= TIMESTAMP '2024-01-01 00:00:00' AND d.ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY f.host, d.area ORDER BY score DESC NULLS LAST, f.host, d.area LIMIT 10"
|
||||
warmup = 3
|
||||
iterations = 9
|
||||
|
||||
[scenario.queries.thresholds]
|
||||
max_candidate_latency_regression_pct = 50
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "factor_wide"
|
||||
kind = "sql"
|
||||
query = "WITH ff AS (SELECT host, SUM(metric_value) AS fm, COUNT(metric_value) AS fn FROM paper_ffx_balanced_fact WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY host), dd AS (SELECT host, area, SUM(weight) AS dw, COUNT(weight) AS dn FROM paper_ffx_balanced_dim WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY host, area) SELECT ff.host, dd.area, CASE WHEN ff.fn = 0 OR dd.dn = 0 THEN NULL ELSE (ff.fm * dd.dw) / (CAST(ff.fn AS DOUBLE) * CAST(dd.dn AS DOUBLE)) END AS score FROM ff JOIN dd ON ff.host = dd.host ORDER BY score DESC NULLS LAST, ff.host, dd.area LIMIT 10"
|
||||
warmup = 3
|
||||
iterations = 9
|
||||
|
||||
[scenario.queries.thresholds]
|
||||
max_candidate_latency_regression_pct = 50
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "raw_narrow"
|
||||
kind = "sql"
|
||||
query = "SELECT f.host, d.area, AVG(f.metric_value * d.weight) AS score FROM paper_ffx_balanced_fact f JOIN paper_ffx_balanced_dim d ON f.host = d.host WHERE f.ts >= TIMESTAMP '2024-01-01 01:25:04' AND f.ts < TIMESTAMP '2024-01-01 01:25:20' AND d.ts >= TIMESTAMP '2024-01-01 00:00:00' AND d.ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY f.host, d.area ORDER BY score DESC NULLS LAST, f.host, d.area LIMIT 10"
|
||||
warmup = 3
|
||||
iterations = 9
|
||||
|
||||
[scenario.queries.thresholds]
|
||||
max_candidate_latency_regression_pct = 50
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "factor_narrow"
|
||||
kind = "sql"
|
||||
query = "WITH ff AS (SELECT host, SUM(metric_value) AS fm, COUNT(metric_value) AS fn FROM paper_ffx_balanced_fact WHERE ts >= TIMESTAMP '2024-01-01 01:25:04' AND ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY host), dd AS (SELECT host, area, SUM(weight) AS dw, COUNT(weight) AS dn FROM paper_ffx_balanced_dim WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY host, area) SELECT ff.host, dd.area, CASE WHEN ff.fn = 0 OR dd.dn = 0 THEN NULL ELSE (ff.fm * dd.dw) / (CAST(ff.fn AS DOUBLE) * CAST(dd.dn AS DOUBLE)) END AS score FROM ff JOIN dd ON ff.host = dd.host ORDER BY score DESC NULLS LAST, ff.host, dd.area LIMIT 10"
|
||||
warmup = 3
|
||||
iterations = 9
|
||||
|
||||
[scenario.queries.thresholds]
|
||||
max_candidate_latency_regression_pct = 50
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "raw_rare"
|
||||
kind = "sql"
|
||||
query = "SELECT f.host, d.area, AVG(f.metric_value * d.weight) AS score FROM paper_ffx_balanced_fact f JOIN paper_ffx_balanced_dim d ON f.host = d.host WHERE f.ts >= TIMESTAMP '2024-01-01 00:00:00' AND f.ts < TIMESTAMP '2024-01-01 01:25:20' AND d.ts >= TIMESTAMP '2024-01-01 00:00:00' AND d.ts < TIMESTAMP '2024-01-01 01:25:20' AND d.area = 'a0' GROUP BY f.host, d.area ORDER BY score DESC NULLS LAST, f.host, d.area LIMIT 10"
|
||||
warmup = 3
|
||||
iterations = 9
|
||||
|
||||
[scenario.queries.thresholds]
|
||||
max_candidate_latency_regression_pct = 50
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "factor_rare"
|
||||
kind = "sql"
|
||||
query = "WITH ff AS (SELECT host, SUM(metric_value) AS fm, COUNT(metric_value) AS fn FROM paper_ffx_balanced_fact WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY host), dd AS (SELECT host, area, SUM(weight) AS dw, COUNT(weight) AS dn FROM paper_ffx_balanced_dim WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 01:25:20' AND area = 'a0' GROUP BY host, area) SELECT ff.host, dd.area, CASE WHEN ff.fn = 0 OR dd.dn = 0 THEN NULL ELSE (ff.fm * dd.dw) / (CAST(ff.fn AS DOUBLE) * CAST(dd.dn AS DOUBLE)) END AS score FROM ff JOIN dd ON ff.host = dd.host ORDER BY score DESC NULLS LAST, ff.host, dd.area LIMIT 10"
|
||||
warmup = 3
|
||||
iterations = 9
|
||||
|
||||
[scenario.queries.thresholds]
|
||||
max_candidate_latency_regression_pct = 50
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "raw_full_wide"
|
||||
kind = "sql"
|
||||
query = "SELECT f.host, d.area, COUNT(*) AS pairs, COUNT(f.metric_value * d.weight) AS valid, SUM(f.metric_value * d.weight) AS total, AVG(f.metric_value * d.weight) AS score FROM paper_ffx_balanced_fact f JOIN paper_ffx_balanced_dim d ON f.host = d.host WHERE f.ts >= TIMESTAMP '2024-01-01 00:00:00' AND f.ts < TIMESTAMP '2024-01-01 01:25:20' AND d.ts >= TIMESTAMP '2024-01-01 00:00:00' AND d.ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY f.host, d.area ORDER BY f.host NULLS LAST, d.area NULLS LAST"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "factor_full_wide"
|
||||
kind = "sql"
|
||||
query = "WITH ff AS (SELECT host, SUM(metric_value) AS fm, COUNT(metric_value) AS fn, COUNT(*) AS fc FROM paper_ffx_balanced_fact WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY host), dd AS (SELECT host, area, SUM(weight) AS dw, COUNT(weight) AS dn, COUNT(*) AS dc FROM paper_ffx_balanced_dim WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY host, area) SELECT ff.host, dd.area, ff.fc * dd.dc AS pairs, ff.fn * dd.dn AS valid, ff.fm * dd.dw AS total, CASE WHEN ff.fn = 0 OR dd.dn = 0 THEN NULL ELSE (ff.fm * dd.dw) / (CAST(ff.fn AS DOUBLE) * CAST(dd.dn AS DOUBLE)) END AS score FROM ff JOIN dd ON ff.host = dd.host ORDER BY ff.host NULLS LAST, dd.area NULLS LAST"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "raw_full_narrow"
|
||||
kind = "sql"
|
||||
query = "SELECT f.host, d.area, COUNT(*) AS pairs, COUNT(f.metric_value * d.weight) AS valid, SUM(f.metric_value * d.weight) AS total, AVG(f.metric_value * d.weight) AS score FROM paper_ffx_balanced_fact f JOIN paper_ffx_balanced_dim d ON f.host = d.host WHERE f.ts >= TIMESTAMP '2024-01-01 01:25:04' AND f.ts < TIMESTAMP '2024-01-01 01:25:20' AND d.ts >= TIMESTAMP '2024-01-01 00:00:00' AND d.ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY f.host, d.area ORDER BY f.host NULLS LAST, d.area NULLS LAST"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "factor_full_narrow"
|
||||
kind = "sql"
|
||||
query = "WITH ff AS (SELECT host, SUM(metric_value) AS fm, COUNT(metric_value) AS fn, COUNT(*) AS fc FROM paper_ffx_balanced_fact WHERE ts >= TIMESTAMP '2024-01-01 01:25:04' AND ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY host), dd AS (SELECT host, area, SUM(weight) AS dw, COUNT(weight) AS dn, COUNT(*) AS dc FROM paper_ffx_balanced_dim WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY host, area) SELECT ff.host, dd.area, ff.fc * dd.dc AS pairs, ff.fn * dd.dn AS valid, ff.fm * dd.dw AS total, CASE WHEN ff.fn = 0 OR dd.dn = 0 THEN NULL ELSE (ff.fm * dd.dw) / (CAST(ff.fn AS DOUBLE) * CAST(dd.dn AS DOUBLE)) END AS score FROM ff JOIN dd ON ff.host = dd.host ORDER BY ff.host NULLS LAST, dd.area NULLS LAST"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "raw_full_rare"
|
||||
kind = "sql"
|
||||
query = "SELECT f.host, d.area, COUNT(*) AS pairs, COUNT(f.metric_value * d.weight) AS valid, SUM(f.metric_value * d.weight) AS total, AVG(f.metric_value * d.weight) AS score FROM paper_ffx_balanced_fact f JOIN paper_ffx_balanced_dim d ON f.host = d.host WHERE f.ts >= TIMESTAMP '2024-01-01 00:00:00' AND f.ts < TIMESTAMP '2024-01-01 01:25:20' AND d.ts >= TIMESTAMP '2024-01-01 00:00:00' AND d.ts < TIMESTAMP '2024-01-01 01:25:20' AND d.area = 'a0' GROUP BY f.host, d.area ORDER BY f.host NULLS LAST, d.area NULLS LAST"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "factor_full_rare"
|
||||
kind = "sql"
|
||||
query = "WITH ff AS (SELECT host, SUM(metric_value) AS fm, COUNT(metric_value) AS fn, COUNT(*) AS fc FROM paper_ffx_balanced_fact WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY host), dd AS (SELECT host, area, SUM(weight) AS dw, COUNT(weight) AS dn, COUNT(*) AS dc FROM paper_ffx_balanced_dim WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 01:25:20' AND area = 'a0' GROUP BY host, area) SELECT ff.host, dd.area, ff.fc * dd.dc AS pairs, ff.fn * dd.dn AS valid, ff.fm * dd.dw AS total, CASE WHEN ff.fn = 0 OR dd.dn = 0 THEN NULL ELSE (ff.fm * dd.dw) / (CAST(ff.fn AS DOUBLE) * CAST(dd.dn AS DOUBLE)) END AS score FROM ff JOIN dd ON ff.host = dd.host ORDER BY ff.host NULLS LAST, dd.area NULLS LAST"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
|
||||
# Diagnostic single executions are excluded from benchmark comparison.
|
||||
[[scenario.queries]]
|
||||
name = "diagnostic_explain_raw_wide"
|
||||
kind = "sql"
|
||||
query = "EXPLAIN ANALYZE VERBOSE SELECT f.host, d.area, AVG(f.metric_value * d.weight) AS score FROM paper_ffx_balanced_fact f JOIN paper_ffx_balanced_dim d ON f.host = d.host WHERE f.ts >= TIMESTAMP '2024-01-01 00:00:00' AND f.ts < TIMESTAMP '2024-01-01 01:25:20' AND d.ts >= TIMESTAMP '2024-01-01 00:00:00' AND d.ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY f.host, d.area"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "diagnostic_explain_factor_wide"
|
||||
kind = "sql"
|
||||
query = "EXPLAIN ANALYZE VERBOSE WITH ff AS (SELECT host, SUM(metric_value) AS fm, COUNT(metric_value) AS fn FROM paper_ffx_balanced_fact WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY host), dd AS (SELECT host, area, SUM(weight) AS dw, COUNT(weight) AS dn FROM paper_ffx_balanced_dim WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 01:25:20' GROUP BY host, area) SELECT ff.host, dd.area, (ff.fm * dd.dw) / (CAST(ff.fn AS DOUBLE) * CAST(dd.dn AS DOUBLE)) AS score FROM ff JOIN dd ON ff.host = dd.host"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
@@ -0,0 +1,135 @@
|
||||
# WeightedAVG raw join versus host/area factorization; fixed direct-SST layout.
|
||||
# Each measurement is timed separately. The query list deliberately puts raw
|
||||
# first; compare with that ordering limitation in mind.
|
||||
|
||||
[case]
|
||||
name = "paper_ffx_hot"
|
||||
description = "Raw versus factorized weightedAVG at a hot join cardinality"
|
||||
|
||||
[scenario]
|
||||
kind = "direct_readable_sst"
|
||||
seed = 5204
|
||||
|
||||
[[scenario.tables]]
|
||||
database = "public"
|
||||
name = "paper_ffx_hot_fact"
|
||||
engine = "mito"
|
||||
append_mode = true
|
||||
sst_format = "flat"
|
||||
primary_key = ["host", "instance"]
|
||||
time_index = "ts"
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "host"
|
||||
type = "STRING"
|
||||
semantic = "tag"
|
||||
distribution = { kind = "cardinality", values = 1, prefix = "h" }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "instance"
|
||||
type = "STRING"
|
||||
semantic = "tag"
|
||||
distribution = { kind = "cardinality", values = 64, prefix = "i" }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "metric_value"
|
||||
type = "DOUBLE"
|
||||
semantic = "field"
|
||||
distribution = { kind = "deterministic_wave", min = 1.0, max = 500.0 }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "ts"
|
||||
type = "TIMESTAMP(9)"
|
||||
semantic = "timestamp"
|
||||
|
||||
[[scenario.tables]]
|
||||
database = "public"
|
||||
name = "paper_ffx_hot_dim"
|
||||
engine = "mito"
|
||||
append_mode = true
|
||||
sst_format = "flat"
|
||||
primary_key = ["host", "area"]
|
||||
time_index = "ts"
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "host"
|
||||
type = "STRING"
|
||||
semantic = "tag"
|
||||
distribution = { kind = "cardinality", values = 1, prefix = "h" }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "area"
|
||||
type = "STRING"
|
||||
semantic = "tag"
|
||||
distribution = { kind = "cardinality", values = 4, prefix = "a" }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "weight"
|
||||
type = "DOUBLE"
|
||||
semantic = "field"
|
||||
distribution = { kind = "deterministic_wave", min = 0.1, max = 10.0 }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "ts"
|
||||
type = "TIMESTAMP(9)"
|
||||
semantic = "timestamp"
|
||||
|
||||
[scenario.layout]
|
||||
regions = 1
|
||||
sst_count = 4
|
||||
rows_per_sst = 512
|
||||
row_group_size = 128
|
||||
series_count = 64
|
||||
start_unix_nanos = 1704067200000000000
|
||||
step_nanos = 1000000000
|
||||
time_range_layout = "non_overlapping_per_sst"
|
||||
series_layout = "round_robin"
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "raw_wide"
|
||||
kind = "sql"
|
||||
query = "SELECT f.host, d.area, AVG(f.metric_value * d.weight) AS score FROM paper_ffx_hot_fact f JOIN paper_ffx_hot_dim d ON f.host = d.host WHERE f.ts >= TIMESTAMP '2024-01-01 00:00:00' AND f.ts < TIMESTAMP '2024-01-01 00:34:08' AND d.ts >= TIMESTAMP '2024-01-01 00:00:00' AND d.ts < TIMESTAMP '2024-01-01 00:34:08' GROUP BY f.host, d.area ORDER BY score DESC NULLS LAST, f.host, d.area LIMIT 10"
|
||||
warmup = 3
|
||||
iterations = 9
|
||||
|
||||
[scenario.queries.thresholds]
|
||||
max_candidate_latency_regression_pct = 50
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "factor_wide"
|
||||
kind = "sql"
|
||||
query = "WITH ff AS (SELECT host, SUM(metric_value) AS fm, COUNT(metric_value) AS fn FROM paper_ffx_hot_fact WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 00:34:08' GROUP BY host), dd AS (SELECT host, area, SUM(weight) AS dw, COUNT(weight) AS dn FROM paper_ffx_hot_dim WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 00:34:08' GROUP BY host, area) SELECT ff.host, dd.area, CASE WHEN ff.fn = 0 OR dd.dn = 0 THEN NULL ELSE (ff.fm * dd.dw) / (CAST(ff.fn AS DOUBLE) * CAST(dd.dn AS DOUBLE)) END AS score FROM ff JOIN dd ON ff.host = dd.host ORDER BY score DESC NULLS LAST, ff.host, dd.area LIMIT 10"
|
||||
warmup = 3
|
||||
iterations = 9
|
||||
|
||||
[scenario.queries.thresholds]
|
||||
max_candidate_latency_regression_pct = 50
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "raw_full_wide"
|
||||
kind = "sql"
|
||||
query = "SELECT f.host, d.area, COUNT(*) AS pairs, COUNT(f.metric_value * d.weight) AS valid, SUM(f.metric_value * d.weight) AS total, AVG(f.metric_value * d.weight) AS score FROM paper_ffx_hot_fact f JOIN paper_ffx_hot_dim d ON f.host = d.host WHERE f.ts >= TIMESTAMP '2024-01-01 00:00:00' AND f.ts < TIMESTAMP '2024-01-01 00:34:08' AND d.ts >= TIMESTAMP '2024-01-01 00:00:00' AND d.ts < TIMESTAMP '2024-01-01 00:34:08' GROUP BY f.host, d.area ORDER BY f.host NULLS LAST, d.area NULLS LAST"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "factor_full_wide"
|
||||
kind = "sql"
|
||||
query = "WITH ff AS (SELECT host, SUM(metric_value) AS fm, COUNT(metric_value) AS fn, COUNT(*) AS fc FROM paper_ffx_hot_fact WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 00:34:08' GROUP BY host), dd AS (SELECT host, area, SUM(weight) AS dw, COUNT(weight) AS dn, COUNT(*) AS dc FROM paper_ffx_hot_dim WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 00:34:08' GROUP BY host, area) SELECT ff.host, dd.area, ff.fc * dd.dc AS pairs, ff.fn * dd.dn AS valid, ff.fm * dd.dw AS total, CASE WHEN ff.fn = 0 OR dd.dn = 0 THEN NULL ELSE (ff.fm * dd.dw) / (CAST(ff.fn AS DOUBLE) * CAST(dd.dn AS DOUBLE)) END AS score FROM ff JOIN dd ON ff.host = dd.host ORDER BY ff.host NULLS LAST, dd.area NULLS LAST"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
|
||||
# Diagnostic single executions are excluded from benchmark comparison.
|
||||
[[scenario.queries]]
|
||||
name = "diagnostic_explain_raw_wide"
|
||||
kind = "sql"
|
||||
query = "EXPLAIN ANALYZE VERBOSE SELECT f.host, d.area, AVG(f.metric_value * d.weight) AS score FROM paper_ffx_hot_fact f JOIN paper_ffx_hot_dim d ON f.host = d.host WHERE f.ts >= TIMESTAMP '2024-01-01 00:00:00' AND f.ts < TIMESTAMP '2024-01-01 00:34:08' AND d.ts >= TIMESTAMP '2024-01-01 00:00:00' AND d.ts < TIMESTAMP '2024-01-01 00:34:08' GROUP BY f.host, d.area"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "diagnostic_explain_factor_wide"
|
||||
kind = "sql"
|
||||
query = "EXPLAIN ANALYZE VERBOSE WITH ff AS (SELECT host, SUM(metric_value) AS fm, COUNT(metric_value) AS fn FROM paper_ffx_hot_fact WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 00:34:08' GROUP BY host), dd AS (SELECT host, area, SUM(weight) AS dw, COUNT(weight) AS dn FROM paper_ffx_hot_dim WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 00:34:08' GROUP BY host, area) SELECT ff.host, dd.area, (ff.fm * dd.dw) / (CAST(ff.fn AS DOUBLE) * CAST(dd.dn AS DOUBLE)) AS score FROM ff JOIN dd ON ff.host = dd.host"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
@@ -0,0 +1,135 @@
|
||||
# WeightedAVG raw join versus host/area factorization; fixed direct-SST layout.
|
||||
# Each measurement is timed separately. The query list deliberately puts raw
|
||||
# first; compare with that ordering limitation in mind.
|
||||
|
||||
[case]
|
||||
name = "paper_ffx_low"
|
||||
description = "Raw versus factorized weightedAVG at a low join cardinality"
|
||||
|
||||
[scenario]
|
||||
kind = "direct_readable_sst"
|
||||
seed = 5201
|
||||
|
||||
[[scenario.tables]]
|
||||
database = "public"
|
||||
name = "paper_ffx_low_fact"
|
||||
engine = "mito"
|
||||
append_mode = true
|
||||
sst_format = "flat"
|
||||
primary_key = ["host", "instance"]
|
||||
time_index = "ts"
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "host"
|
||||
type = "STRING"
|
||||
semantic = "tag"
|
||||
distribution = { kind = "cardinality", values = 512, prefix = "h" }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "instance"
|
||||
type = "STRING"
|
||||
semantic = "tag"
|
||||
distribution = { kind = "cardinality", values = 512, prefix = "i" }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "metric_value"
|
||||
type = "DOUBLE"
|
||||
semantic = "field"
|
||||
distribution = { kind = "deterministic_wave", min = 1.0, max = 500.0 }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "ts"
|
||||
type = "TIMESTAMP(9)"
|
||||
semantic = "timestamp"
|
||||
|
||||
[[scenario.tables]]
|
||||
database = "public"
|
||||
name = "paper_ffx_low_dim"
|
||||
engine = "mito"
|
||||
append_mode = true
|
||||
sst_format = "flat"
|
||||
primary_key = ["host", "area"]
|
||||
time_index = "ts"
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "host"
|
||||
type = "STRING"
|
||||
semantic = "tag"
|
||||
distribution = { kind = "cardinality", values = 512, prefix = "h" }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "area"
|
||||
type = "STRING"
|
||||
semantic = "tag"
|
||||
distribution = { kind = "cardinality", values = 4, prefix = "a" }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "weight"
|
||||
type = "DOUBLE"
|
||||
semantic = "field"
|
||||
distribution = { kind = "deterministic_wave", min = 0.1, max = 10.0 }
|
||||
|
||||
[[scenario.tables.columns]]
|
||||
name = "ts"
|
||||
type = "TIMESTAMP(9)"
|
||||
semantic = "timestamp"
|
||||
|
||||
[scenario.layout]
|
||||
regions = 1
|
||||
sst_count = 1
|
||||
rows_per_sst = 512
|
||||
row_group_size = 128
|
||||
series_count = 512
|
||||
start_unix_nanos = 1704067200000000000
|
||||
step_nanos = 1000000000
|
||||
time_range_layout = "non_overlapping_per_sst"
|
||||
series_layout = "round_robin"
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "raw_wide"
|
||||
kind = "sql"
|
||||
query = "SELECT f.host, d.area, AVG(f.metric_value * d.weight) AS score FROM paper_ffx_low_fact f JOIN paper_ffx_low_dim d ON f.host = d.host WHERE f.ts >= TIMESTAMP '2024-01-01 00:00:00' AND f.ts < TIMESTAMP '2024-01-01 00:08:32' AND d.ts >= TIMESTAMP '2024-01-01 00:00:00' AND d.ts < TIMESTAMP '2024-01-01 00:08:32' GROUP BY f.host, d.area ORDER BY score DESC NULLS LAST, f.host, d.area LIMIT 10"
|
||||
warmup = 3
|
||||
iterations = 9
|
||||
|
||||
[scenario.queries.thresholds]
|
||||
max_candidate_latency_regression_pct = 50
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "factor_wide"
|
||||
kind = "sql"
|
||||
query = "WITH ff AS (SELECT host, SUM(metric_value) AS fm, COUNT(metric_value) AS fn FROM paper_ffx_low_fact WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 00:08:32' GROUP BY host), dd AS (SELECT host, area, SUM(weight) AS dw, COUNT(weight) AS dn FROM paper_ffx_low_dim WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 00:08:32' GROUP BY host, area) SELECT ff.host, dd.area, CASE WHEN ff.fn = 0 OR dd.dn = 0 THEN NULL ELSE (ff.fm * dd.dw) / (CAST(ff.fn AS DOUBLE) * CAST(dd.dn AS DOUBLE)) END AS score FROM ff JOIN dd ON ff.host = dd.host ORDER BY score DESC NULLS LAST, ff.host, dd.area LIMIT 10"
|
||||
warmup = 3
|
||||
iterations = 9
|
||||
|
||||
[scenario.queries.thresholds]
|
||||
max_candidate_latency_regression_pct = 50
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "raw_full_wide"
|
||||
kind = "sql"
|
||||
query = "SELECT f.host, d.area, COUNT(*) AS pairs, COUNT(f.metric_value * d.weight) AS valid, SUM(f.metric_value * d.weight) AS total, AVG(f.metric_value * d.weight) AS score FROM paper_ffx_low_fact f JOIN paper_ffx_low_dim d ON f.host = d.host WHERE f.ts >= TIMESTAMP '2024-01-01 00:00:00' AND f.ts < TIMESTAMP '2024-01-01 00:08:32' AND d.ts >= TIMESTAMP '2024-01-01 00:00:00' AND d.ts < TIMESTAMP '2024-01-01 00:08:32' GROUP BY f.host, d.area ORDER BY f.host NULLS LAST, d.area NULLS LAST"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "factor_full_wide"
|
||||
kind = "sql"
|
||||
query = "WITH ff AS (SELECT host, SUM(metric_value) AS fm, COUNT(metric_value) AS fn, COUNT(*) AS fc FROM paper_ffx_low_fact WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 00:08:32' GROUP BY host), dd AS (SELECT host, area, SUM(weight) AS dw, COUNT(weight) AS dn, COUNT(*) AS dc FROM paper_ffx_low_dim WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 00:08:32' GROUP BY host, area) SELECT ff.host, dd.area, ff.fc * dd.dc AS pairs, ff.fn * dd.dn AS valid, ff.fm * dd.dw AS total, CASE WHEN ff.fn = 0 OR dd.dn = 0 THEN NULL ELSE (ff.fm * dd.dw) / (CAST(ff.fn AS DOUBLE) * CAST(dd.dn AS DOUBLE)) END AS score FROM ff JOIN dd ON ff.host = dd.host ORDER BY ff.host NULLS LAST, dd.area NULLS LAST"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
|
||||
# Diagnostic single executions are excluded from benchmark comparison.
|
||||
[[scenario.queries]]
|
||||
name = "diagnostic_explain_raw_wide"
|
||||
kind = "sql"
|
||||
query = "EXPLAIN ANALYZE VERBOSE SELECT f.host, d.area, AVG(f.metric_value * d.weight) AS score FROM paper_ffx_low_fact f JOIN paper_ffx_low_dim d ON f.host = d.host WHERE f.ts >= TIMESTAMP '2024-01-01 00:00:00' AND f.ts < TIMESTAMP '2024-01-01 00:08:32' AND d.ts >= TIMESTAMP '2024-01-01 00:00:00' AND d.ts < TIMESTAMP '2024-01-01 00:08:32' GROUP BY f.host, d.area"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
|
||||
[[scenario.queries]]
|
||||
name = "diagnostic_explain_factor_wide"
|
||||
kind = "sql"
|
||||
query = "EXPLAIN ANALYZE VERBOSE WITH ff AS (SELECT host, SUM(metric_value) AS fm, COUNT(metric_value) AS fn FROM paper_ffx_low_fact WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 00:08:32' GROUP BY host), dd AS (SELECT host, area, SUM(weight) AS dw, COUNT(weight) AS dn FROM paper_ffx_low_dim WHERE ts >= TIMESTAMP '2024-01-01 00:00:00' AND ts < TIMESTAMP '2024-01-01 00:08:32' GROUP BY host, area) SELECT ff.host, dd.area, (ff.fm * dd.dw) / (CAST(ff.fn AS DOUBLE) * CAST(dd.dn AS DOUBLE)) AS score FROM ff JOIN dd ON ff.host = dd.host"
|
||||
warmup = 0
|
||||
iterations = 1
|
||||
Reference in New Issue
Block a user