Merge remote-tracking branch 'upstream/main' into issue_14909

Author: zhuqi-lucas

Cargo.lock

@@ -80,12 +80,12 @@ version = "45.0.0"
 ahash = { version = "0.8", default-features = false, features = [
     "runtime-rng",
 ] }
-arrow = { version = "54.2.0", features = [
+arrow = { version = "54.2.1", features = [
     "prettyprint",
     "chrono-tz",
 ] }
 arrow-buffer = { version = "54.1.0", default-features = false }
-arrow-flight = { version = "54.2.0", features = [
+arrow-flight = { version = "54.2.1", features = [
     "flight-sql-experimental",
 ] }
 arrow-ipc = { version = "54.2.0", default-features = false, features = [
@@ -137,7 +137,7 @@ itertools = "0.14"
 log = "^0.4"
 object_store = { version = "0.11.0", default-features = false }
 parking_lot = "0.12"
-parquet = { version = "54.2.0", default-features = false, features = [
+parquet = { version = "54.2.1", default-features = false, features = [
     "arrow",
     "async",
     "object_store",

Cargo.toml

@@ -513,5 +513,49 @@ For example, to run query 1 with the small data generated above:
 cargo run --release --bin dfbench -- h2o --path ./benchmarks/data/h2o/G1_1e7_1e7_100_0.csv  --query 1
 ```
 
+## h2o benchmarks for join
+
+### Generate data for h2o benchmarks
+There are three options for generating data for h2o benchmarks: `small`, `medium`, and `big`. The data is generated in the `data` directory.
+
+1. Generate small data (4 table files, the largest is 1e7 rows)
+```bash
+./bench.sh data h2o_small_join
+```
+
+
+2. Generate medium data (4 table files, the largest is 1e8 rows)
+```bash
+./bench.sh data h2o_medium_join
+```
+
+3. Generate large data (4 table files, the largest is 1e9 rows)
+```bash
+./bench.sh data h2o_big_join
+```
+
+### Run h2o benchmarks
+There are three options for running h2o benchmarks: `small`, `medium`, and `big`.
+1. Run small data benchmark
+```bash
+./bench.sh run h2o_small_join
+```
+
+2. Run medium data benchmark
+```bash
+./bench.sh run h2o_medium_join
+```
+
+3. Run large data benchmark
+```bash
+./bench.sh run h2o_big_join
+```
+
+4. Run a specific query with a specific join data paths, the data paths are including 4 table files.
+
+For example, to run query 1 with the small data generated above:
+```bash
+cargo run --release --bin dfbench -- h2o --join-paths ./benchmarks/data/h2o/J1_1e7_NA_0.csv,./benchmarks/data/h2o/J1_1e7_1e1_0.csv,./benchmarks/data/h2o/J1_1e7_1e4_0.csv,./benchmarks/data/h2o/J1_1e7_1e7_NA.csv --queries-path ./benchmarks/queries/h2o/join.sql --query 1
+```
 [1]: http://www.tpc.org/tpch/
 [2]: https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page