diff --git a/TOC.md b/TOC.md index f54f6173d3202..e35284e7a9c93 100644 --- a/TOC.md +++ b/TOC.md @@ -13,7 +13,7 @@ + Benchmarks + [v5.1 Sysbench Performance Test Report](/benchmark/benchmark-sysbench-v5.1.0-vs-v5.0.2.md) + [v5.1 TPC-C Performance Test Report](/benchmark/v5.1-performance-benchmarking-with-tpcc.md) - + [v5.1 MPP mode TPC-H 100GB Performance Test](/benchmark/v5.1-performance-benchmarking-with-tpch.md) + + [v5.2 MPP mode TPC-H 100GB Performance Test](/benchmark/v5.2-performance-benchmarking-with-tpch.md) + [MySQL Compatibility](/mysql-compatibility.md) + [TiDB Limitations](/tidb-limitations.md) + [TiDB Adopters](/adopters.md) diff --git a/benchmark/v5.1-performance-benchmarking-with-tpch.md b/benchmark/v5.2-performance-benchmarking-with-tpch.md similarity index 82% rename from benchmark/v5.1-performance-benchmarking-with-tpch.md rename to benchmark/v5.2-performance-benchmarking-with-tpch.md index 39e6ccd6be727..3cefbfe0e55a3 100644 --- a/benchmark/v5.1-performance-benchmarking-with-tpch.md +++ b/benchmark/v5.2-performance-benchmarking-with-tpch.md @@ -1,17 +1,17 @@ --- -title: TiDB TPC-H 100GB Performance Test Report -- v5.1 MPP mode vs. Greenplum 6.15.0 and Apache Spark 3.1.1 -summary: Compare the TPC-H 100GB performance of TiDB 5.1 MPP mode, Greenplum 6.15.0, and Apache Spark 3.1.1. +title: TiDB TPC-H 100GB Performance Test Report -- v5.2 MPP mode vs. Greenplum 6.15.0 and Apache Spark 3.1.1 +summary: Compare the TPC-H 100GB performance of TiDB 5.2 MPP mode, Greenplum 6.15.0, and Apache Spark 3.1.1. --- -# TiDB TPC-H 100GB Performance Test Report -- TiDB v5.1 MPP mode vs. Greenplum 6.15.0 and Apache Spark 3.1.1 +# TiDB TPC-H 100GB Performance Test Report -- TiDB v5.2 MPP mode vs. Greenplum 6.15.0 and Apache Spark 3.1.1 ## Test overview -This test aims at comparing the TPC-H 100GB performance of TiDB v5.1 in the MPP mode with that of Greenplum and Apache Spark, two mainstream analytics engines, in their latest versions. The test result shows that the performance of TiDB v5.1 in the MPP mode is two to three times faster than that of the other two solutions under TPC-H workload. +This test aims at comparing the TPC-H 100GB performance of TiDB v5.2 in the MPP mode with that of Greenplum and Apache Spark, two mainstream analytics engines, in their latest versions. The test result shows that the performance of TiDB v5.2 in the MPP mode is two to three times faster than that of the other two solutions under TPC-H workload. -In v5.0, TiDB introduces the MPP mode for [TiFlash](/tiflash/tiflash-overview.md), which significantly enhances TiDB's Hybrid Transactional and Analytical Processing (HTAP) capabilities. Test objects in this report are as follows: +In v5.0, TiDB introduces the MPP mode for [TiFlash](/tiflash/tiflash-overview.md). In v5.1 and v5.2, the MPP mode has been further improved, which significantly enhances TiDB's Hybrid Transactional and Analytical Processing (HTAP) capabilities. Test objects in this report are as follows: -+ TiDB v5.1 columnar storage in the MPP mode ++ TiDB v5.2 columnar storage in the MPP mode + Greenplum 6.15.0 + Apache Spark 3.1.1 + Parquet @@ -28,15 +28,15 @@ In v5.0, TiDB introduces the MPP mode for [TiFlash](/tiflash/tiflash-overview.md | Service type | Software version | |:----------|:-----------| -| TiDB | 5.1 | +| TiDB | 5.2 | | Greenplum | 6.15.0 | | Apache Spark | 3.1.1 | ### Parameter configuration -#### TiDB v5.1 +#### TiDB v5.2 -For the v5.1 cluster, TiDB uses the default parameter configuration except for the following configuration items. +For the v5.2 cluster, TiDB uses the default parameter configuration except for the following configuration items. In the configuration file `users.toml` of TiFlash, configure `max_memory_usage` as follows: @@ -87,7 +87,7 @@ The test of Apache Spark uses Apache Parquet as the storage format and stores th > > The following test results are the average data of three tests. All numbers are in seconds. -| Query ID | TiDB v5.1 | Greenplum 6.15.0 | Apache Spark 3.1.1 + Parquet | +| Query ID | TiDB v5.2 | Greenplum 6.15.0 | Apache Spark 3.1.1 + Parquet | | :-------- | :----------- | :------------ | :-------------- | | 1 | 8.08 | 64.1307 | 52.64 | | 2 | 2.53 | 4.76612 | 11.83 | @@ -112,11 +112,11 @@ The test of Apache Spark uses Apache Parquet as the storage format and stores th | 21 | 24.44 | 39.08594 | 34.83 | | 22 | 1.23 | 7.67476 | 4.59 | -![TPC-H](/media/tidb-v5-tpch-100-vs-gp-spark.png) +![TPC-H](/media/tidb-v5.2-tpch-100-vs-gp-spark.png) In the performance diagram above: -- Blue lines represent TiDB v5.1; +- Blue lines represent TiDB v5.2; - Red lines represent Greenplum 6.15.0; - Yellow lines represent Apache Spark 3.1.1. - The y-axis represents the execution time of the query. The less the time is, the better the performance is. diff --git a/media/tidb-v5-tpch-100-vs-gp-spark.png b/media/tidb-v5-tpch-100-vs-gp-spark.png deleted file mode 100644 index c76f4ede8c37a..0000000000000 Binary files a/media/tidb-v5-tpch-100-vs-gp-spark.png and /dev/null differ diff --git a/media/tidb-v5.2-tpch-100-vs-gp-spark.png b/media/tidb-v5.2-tpch-100-vs-gp-spark.png new file mode 100644 index 0000000000000..e743a8f7965e9 Binary files /dev/null and b/media/tidb-v5.2-tpch-100-vs-gp-spark.png differ