From f059dd8b3db199254bc3c03d1039ba61a7d6536b Mon Sep 17 00:00:00 2001 From: ncordon Date: Thu, 2 Oct 2025 11:38:58 +0200 Subject: [PATCH 1/3] Adds better challenges for comparing inlinestats --- nyc_taxis/challenges/default.json | 21 +++++++++++++++++++++ nyc_taxis/operations/default.json | 15 +++++++++++++++ 2 files changed, 36 insertions(+) diff --git a/nyc_taxis/challenges/default.json b/nyc_taxis/challenges/default.json index 7511e297c..125378d60 100644 --- a/nyc_taxis/challenges/default.json +++ b/nyc_taxis/challenges/default.json @@ -961,6 +961,27 @@ "iterations": 50, "tags": ["inlinestats"] }, + { + "operation": "one_chained_inlinestats_esql", + "clients": 1, + "warmup-iterations": 5, + "iterations": 20, + "tags": ["inlinestats"] + }, + { + "operation": "two_chained_inlinestats_esql", + "clients": 1, + "warmup-iterations": 5, + "iterations": 20, + "tags": ["inlinestats"] + }, + { + "operation": "three_chained_inlinestats_esql", + "clients": 1, + "warmup-iterations": 5, + "iterations": 20, + "tags": ["inlinestats"] + }, {%- endif -%}{# non-serverless-inlinestats-marker-end #} {# non-serverless-doc-partitioning-marker-start #}{%- if build_flavor != "serverless" -%} { diff --git a/nyc_taxis/operations/default.json b/nyc_taxis/operations/default.json index b5a265593..36defea58 100644 --- a/nyc_taxis/operations/default.json +++ b/nyc_taxis/operations/default.json @@ -1091,6 +1091,21 @@ "operation-type": "esql", "query" : "FROM nyc_taxis | LIMIT 1000 | inlinestats s1 = sum(passenger_count) | inlinestats s2 = sum(s1) | inlinestats s3 = sum(s2)" }, + { + "name": "one_chained_inlinestats_esql", + "operation-type": "esql", + "query" : "FROM nyc_taxis | inlinestats s1 = sum(passenger_count) | LIMIT 1000" + }, + { + "name": "two_chained_inlinestats_esql", + "operation-type": "esql", + "query" : "FROM nyc_taxis | inlinestats s1 = sum(passenger_count) | inlinestats s2 = sum(trip_distance) | LIMIT 1000" + }, + { + "name": "three_chained_inlinestats_esql", + "operation-type": "esql", + "query" : "FROM nyc_taxis | inlinestats s1 = sum(passenger_count) | inlinestats s2 = sum(trip_distance) | inlinestats s3 = sum(total_amount) | LIMIT 1000" + }, { "name": "multiple_stats_esql", "operation-type": "esql", From ac654c186f6eb26fce438daa54c1940f5456211e Mon Sep 17 00:00:00 2001 From: ncordon Date: Thu, 2 Oct 2025 11:56:57 +0200 Subject: [PATCH 2/3] Changes inlinestats by inline stats --- nyc_taxis/operations/default.json | 60 +++++++++++++++---------------- 1 file changed, 30 insertions(+), 30 deletions(-) diff --git a/nyc_taxis/operations/default.json b/nyc_taxis/operations/default.json index 36defea58..f4608e095 100644 --- a/nyc_taxis/operations/default.json +++ b/nyc_taxis/operations/default.json @@ -964,32 +964,32 @@ { "name": "inlinestats_avg_esql_segment_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats avg(passenger_count)" + "query" : "FROM nyc_taxis | inline stats avg(passenger_count)" }, { "name": "inlinestats_count_esql_segment_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats count(passenger_count)" + "query" : "FROM nyc_taxis | inline stats count(passenger_count)" }, { "name": "inlinestats_median_esql_segment_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats median(passenger_count)" + "query" : "FROM nyc_taxis | inline stats median(passenger_count)" }, { "name": "inlinestats_max_esql_segment_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats max(passenger_count)" + "query" : "FROM nyc_taxis | inline stats max(passenger_count)" }, { "name": "inlinestats_sum_esql_segment_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats sum(passenger_count)" + "query" : "FROM nyc_taxis | inline stats sum(passenger_count)" }, { "name": "inlinestats_top_esql_segment_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats top(passenger_count, 3, \"desc\")" + "query" : "FROM nyc_taxis | inline stats top(passenger_count, 3, \"desc\")" }, { "name": "stats_count_esql_segment_partitioning", @@ -1024,7 +1024,7 @@ { "name": "inlinestats_count_comparison_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis METADATA _id | LIMIT 1000 | inlinestats count(passenger_count) by _id" + "query" : "FROM nyc_taxis METADATA _id | LIMIT 1000 | inline stats count(passenger_count) by _id" }, { "name": "stats_avg_comparison_esql", @@ -1034,7 +1034,7 @@ { "name": "inlinestats_avg_comparison_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis METADATA _id | LIMIT 1000 | inlinestats avg(passenger_count) by _id" + "query" : "FROM nyc_taxis METADATA _id | LIMIT 1000 | inline stats avg(passenger_count) by _id" }, { "name": "stats_max_comparison_esql", @@ -1044,67 +1044,67 @@ { "name": "inlinestats_max_comparison_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis METADATA _id | LIMIT 1000 | inlinestats max(passenger_count) by _id" + "query" : "FROM nyc_taxis METADATA _id | LIMIT 1000 | inline stats max(passenger_count) by _id" }, { "name": "inlinestats_then_stats_count_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats c = count(passenger_count) | stats count(c)" + "query" : "FROM nyc_taxis | inline stats c = count(passenger_count) | stats count(c)" }, { "name": "stats_then_inlinestats_count_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | stats c = count(passenger_count) | inlinestats count(c)" + "query" : "FROM nyc_taxis | stats c = count(passenger_count) | inline stats count(c)" }, { "name": "inlinestats_then_stats_sum_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats s = sum(passenger_count) | stats sum(s)" + "query" : "FROM nyc_taxis | inline stats s = sum(passenger_count) | stats sum(s)" }, { "name": "stats_then_inlinestats_sum_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | stats s = sum(passenger_count) | inlinestats sum(s)" + "query" : "FROM nyc_taxis | stats s = sum(passenger_count) | inline stats sum(s)" }, { "name": "inlinestats_then_stats_avg_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats a = avg(passenger_count) | stats avg(a)" + "query" : "FROM nyc_taxis | inline stats a = avg(passenger_count) | stats avg(a)" }, { "name": "stats_then_inlinestats_avg_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | stats a = avg(passenger_count) | inlinestats avg(a)" + "query" : "FROM nyc_taxis | stats a = avg(passenger_count) | inline stats avg(a)" }, { "name": "one_inlinestats_sum_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | LIMIT 1000 | inlinestats s1 = sum(passenger_count)" + "query" : "FROM nyc_taxis | LIMIT 1000 | inline stats s1 = sum(passenger_count)" }, { "name": "two_inlinestats_sum_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | LIMIT 1000 | inlinestats s1 = sum(passenger_count) | inlinestats s2 = sum(s1)" + "query" : "FROM nyc_taxis | LIMIT 1000 | inline stats s1 = sum(passenger_count) | inline stats s2 = sum(s1)" }, { "name": "three_inlinestats_sum_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | LIMIT 1000 | inlinestats s1 = sum(passenger_count) | inlinestats s2 = sum(s1) | inlinestats s3 = sum(s2)" + "query" : "FROM nyc_taxis | LIMIT 1000 | inline stats s1 = sum(passenger_count) | inline stats s2 = sum(s1) | inline stats s3 = sum(s2)" }, { "name": "one_chained_inlinestats_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats s1 = sum(passenger_count) | LIMIT 1000" + "query" : "FROM nyc_taxis | inline stats s1 = sum(passenger_count) | LIMIT 1000" }, { "name": "two_chained_inlinestats_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats s1 = sum(passenger_count) | inlinestats s2 = sum(trip_distance) | LIMIT 1000" + "query" : "FROM nyc_taxis | inline stats s1 = sum(passenger_count) | inline stats s2 = sum(trip_distance) | LIMIT 1000" }, { "name": "three_chained_inlinestats_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats s1 = sum(passenger_count) | inlinestats s2 = sum(trip_distance) | inlinestats s3 = sum(total_amount) | LIMIT 1000" + "query" : "FROM nyc_taxis | inline stats s1 = sum(passenger_count) | inline stats s2 = sum(trip_distance) | inline stats s3 = sum(total_amount) | LIMIT 1000" }, { "name": "multiple_stats_esql", @@ -1114,13 +1114,13 @@ { "name": "multiple_inlinestats_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | LIMIT 1000 | inlinestats sum = sum(passenger_count), count = count(*), avg = avg(passenger_count)" + "query" : "FROM nyc_taxis | LIMIT 1000 | inline stats sum = sum(passenger_count), count = count(*), avg = avg(passenger_count)" }, {# non-serverless-doc-partitioning-marker-start #}{%- if build_flavor != "serverless" -%} { "name": "inlinestats_avg_esql_doc_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats avg(passenger_count)", + "query" : "FROM nyc_taxis | inline stats avg(passenger_count)", "body": { "accept_pragma_risks": true, "pragma": { "data_partitioning": "doc" } @@ -1129,7 +1129,7 @@ { "name": "inlinestats_count_esql_doc_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats count(passenger_count)", + "query" : "FROM nyc_taxis | inline stats count(passenger_count)", "body": { "accept_pragma_risks": true, "pragma": { "data_partitioning": "doc" } @@ -1138,7 +1138,7 @@ { "name": "inlinestats_median_esql_doc_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats median(passenger_count)", + "query" : "FROM nyc_taxis | inline stats median(passenger_count)", "body": { "accept_pragma_risks": true, "pragma": { "data_partitioning": "doc" } @@ -1147,7 +1147,7 @@ { "name": "inlinestats_max_esql_doc_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats max(passenger_count)", + "query" : "FROM nyc_taxis | inline stats max(passenger_count)", "body": { "accept_pragma_risks": true, "pragma": { "data_partitioning": "doc" } @@ -1156,7 +1156,7 @@ { "name": "inlinestats_sum_esql_doc_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats sum(passenger_count)", + "query" : "FROM nyc_taxis | inline stats sum(passenger_count)", "body": { "accept_pragma_risks": true, "pragma": { "data_partitioning": "doc" } @@ -1165,7 +1165,7 @@ { "name": "inlinestats_top_esql_doc_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | inlinestats top(passenger_count, 3, \"desc\")", + "query" : "FROM nyc_taxis | inline stats top(passenger_count, 3, \"desc\")", "body": { "accept_pragma_risks": true, "pragma": { "data_partitioning": "doc" } @@ -1430,13 +1430,13 @@ { "name": "inlinestats_avg_passenger_count_filtered_esql_segment_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | where total_amount > 60 and rate_code_id==\"2\"| inlinestats avg(passenger_count)" + "query" : "FROM nyc_taxis | where total_amount > 60 and rate_code_id==\"2\"| inline stats avg(passenger_count)" }, {# non-serverless-doc-partitioning-marker-start #}{%- if build_flavor != "serverless" -%} { "name": "inlinestats_avg_passenger_count_filtered_esql_doc_partitioning", "operation-type": "esql", - "query" : "FROM nyc_taxis | where total_amount > 60 and rate_code_id==\"2\"| inlinestats avg(passenger_count)", + "query" : "FROM nyc_taxis | where total_amount > 60 and rate_code_id==\"2\"| inline stats avg(passenger_count)", "body": { "accept_pragma_risks": true, "pragma": { "data_partitioning": "doc" } From 44dfd3702bf959ae81a3f2828bcb24d9d25d0f25 Mon Sep 17 00:00:00 2001 From: ncordon Date: Fri, 3 Oct 2025 09:56:38 +0200 Subject: [PATCH 3/3] Changes benchmarks to have the limit afterwards --- nyc_taxis/challenges/default.json | 45 +++++++++---------------------- nyc_taxis/operations/default.json | 43 ++++++++++------------------- 2 files changed, 26 insertions(+), 62 deletions(-) diff --git a/nyc_taxis/challenges/default.json b/nyc_taxis/challenges/default.json index 125378d60..386ff7a13 100644 --- a/nyc_taxis/challenges/default.json +++ b/nyc_taxis/challenges/default.json @@ -940,27 +940,6 @@ "tags": ["inlinestats"] }, {# non-serverless-inlinestats-marker-start #}{%- if build_flavor != "serverless" -%} - { - "operation": "one_inlinestats_sum_esql", - "clients": 1, - "warmup-iterations": 10, - "iterations": 50, - "tags": ["inlinestats"] - }, - { - "operation": "two_inlinestats_sum_esql", - "clients": 1, - "warmup-iterations": 10, - "iterations": 50, - "tags": ["inlinestats"] - }, - { - "operation": "three_inlinestats_sum_esql", - "clients": 1, - "warmup-iterations": 10, - "iterations": 50, - "tags": ["inlinestats"] - }, { "operation": "one_chained_inlinestats_esql", "clients": 1, @@ -1381,45 +1360,45 @@ "tags": ["inlinestats"] }, { - "operation": "stats_count_comparison_esql", + "operation": "stats_count_group_by_esql", "clients": 1, "warmup-iterations": 10, - "iterations": 50, + "iterations": 20, "tags": ["inlinestats"] }, { - "operation": "inlinestats_count_comparison_esql", + "operation": "inlinestats_count_group_by_esql", "clients": 1, "warmup-iterations": 10, - "iterations": 50, + "iterations": 20, "tags": ["inlinestats"] }, { - "operation": "stats_avg_comparison_esql", + "operation": "stats_avg_group_by_esql", "clients": 1, "warmup-iterations": 10, - "iterations": 50, + "iterations": 20, "tags": ["inlinestats"] }, { - "operation": "inlinestats_avg_comparison_esql", + "operation": "inlinestats_avg_group_by_esql", "clients": 1, "warmup-iterations": 10, - "iterations": 50, + "iterations": 20, "tags": ["inlinestats"] }, { - "operation": "stats_max_comparison_esql", + "operation": "stats_max_group_by_esql", "clients": 1, "warmup-iterations": 10, - "iterations": 50, + "iterations": 20, "tags": ["inlinestats"] }, { - "operation": "inlinestats_max_comparison_esql", + "operation": "inlinestats_max_group_by_esql", "clients": 1, "warmup-iterations": 10, - "iterations": 50, + "iterations": 20, "tags": ["inlinestats"] }, { diff --git a/nyc_taxis/operations/default.json b/nyc_taxis/operations/default.json index f4608e095..c1af7f7ba 100644 --- a/nyc_taxis/operations/default.json +++ b/nyc_taxis/operations/default.json @@ -1017,34 +1017,34 @@ "query" : "FROM nyc_taxis | stats top(passenger_count, 3, \"desc\")" }, { - "name": "stats_count_comparison_esql", + "name": "stats_count_group_by_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis METADATA _id | LIMIT 1000 | stats count(passenger_count) by _id" + "query" : "FROM nyc_taxis METADATA _id | stats count(passenger_count) by _id | LIMIT 1000" }, { - "name": "inlinestats_count_comparison_esql", + "name": "inlinestats_count_group_by_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis METADATA _id | LIMIT 1000 | inline stats count(passenger_count) by _id" + "query" : "FROM nyc_taxis METADATA _id | inline stats count(passenger_count) by _id | LIMIT 1000" }, { - "name": "stats_avg_comparison_esql", + "name": "stats_avg_group_by_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis METADATA _id | LIMIT 1000 | stats avg(passenger_count) by _id" + "query" : "FROM nyc_taxis METADATA _id | stats avg(passenger_count) by _id | LIMIT 1000" }, { - "name": "inlinestats_avg_comparison_esql", + "name": "inlinestats_avg_group_by_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis METADATA _id | LIMIT 1000 | inline stats avg(passenger_count) by _id" + "query" : "FROM nyc_taxis METADATA _id | inline stats avg(passenger_count) by _id | LIMIT 1000" }, { - "name": "stats_max_comparison_esql", + "name": "stats_max_group_by_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis METADATA _id | LIMIT 1000 | stats max(passenger_count) by _id" + "query" : "FROM nyc_taxis METADATA _id | stats max(passenger_count) by _id | LIMIT 1000" }, { - "name": "inlinestats_max_comparison_esql", + "name": "inlinestats_max_group_by_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis METADATA _id | LIMIT 1000 | inline stats max(passenger_count) by _id" + "query" : "FROM nyc_taxis METADATA _id | inline stats max(passenger_count) by _id | LIMIT 1000" }, { "name": "inlinestats_then_stats_count_esql", @@ -1076,21 +1076,6 @@ "operation-type": "esql", "query" : "FROM nyc_taxis | stats a = avg(passenger_count) | inline stats avg(a)" }, - { - "name": "one_inlinestats_sum_esql", - "operation-type": "esql", - "query" : "FROM nyc_taxis | LIMIT 1000 | inline stats s1 = sum(passenger_count)" - }, - { - "name": "two_inlinestats_sum_esql", - "operation-type": "esql", - "query" : "FROM nyc_taxis | LIMIT 1000 | inline stats s1 = sum(passenger_count) | inline stats s2 = sum(s1)" - }, - { - "name": "three_inlinestats_sum_esql", - "operation-type": "esql", - "query" : "FROM nyc_taxis | LIMIT 1000 | inline stats s1 = sum(passenger_count) | inline stats s2 = sum(s1) | inline stats s3 = sum(s2)" - }, { "name": "one_chained_inlinestats_esql", "operation-type": "esql", @@ -1109,12 +1094,12 @@ { "name": "multiple_stats_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | LIMIT 1000 | stats sum = sum(passenger_count), count = count(*), avg = avg(passenger_count)" + "query" : "FROM nyc_taxis | stats sum = sum(passenger_count), count = count(*), avg = avg(passenger_count) | LIMIT 1000" }, { "name": "multiple_inlinestats_esql", "operation-type": "esql", - "query" : "FROM nyc_taxis | LIMIT 1000 | inline stats sum = sum(passenger_count), count = count(*), avg = avg(passenger_count)" + "query" : "FROM nyc_taxis | inline stats sum = sum(passenger_count), count = count(*), avg = avg(passenger_count) | LIMIT 1000" }, {# non-serverless-doc-partitioning-marker-start #}{%- if build_flavor != "serverless" -%} {