diff --git a/docs/Example-CockroachDB.md b/docs/Example-CockroachDB.md index 2fe5742c..70428ec7 100644 --- a/docs/Example-CockroachDB.md +++ b/docs/Example-CockroachDB.md @@ -280,6 +280,7 @@ In this example, this means that used memory, CPU time, etc. are summed across a ## Use Persistent Storage +To be described: Persistent storage is per experiment here ## YCSB Example Explained @@ -326,6 +327,9 @@ If data should be loaded, bexhoma at first creates a schema according to: https: ## Benchbase's TPC-C +TPC-C is performed at 16 warehouses. +The 16 threads of the client are split into a cascading sequence of 1 and 2 pods. + ```bash nohup python benchbase.py -ms 1 -tr \ -sf 16 \ @@ -339,7 +343,7 @@ nohup python benchbase.py -ms 1 -tr \ run $LOG_DIR/doc_benchbase_cockroachdb_1.log & ``` -yields +### Evaluate Results ```bash ## Show Summary @@ -408,6 +412,9 @@ TEST passed: Workflow as planned ### Benchbase More Complex +TPC-C is performed at 128 warehouses. +The 64 threads of the client are split into a cascading sequence of 1,2,4 and 8 pods. + ```bash nohup python benchbase.py -ms 1 -tr \ -sf 128 \ @@ -421,7 +428,7 @@ nohup python benchbase.py -ms 1 -tr \ run $LOG_DIR/doc_benchbase_cockroachdb_2.log & ``` -yields +### Evaluate Results ```bash ## Show Summary diff --git a/docs/Example-Result-TPC-H-MonetDB.md b/docs/Example-Result-TPC-H-MonetDB.md index fba6e8c3..9e63b8e8 100644 --- a/docs/Example-Result-TPC-H-MonetDB.md +++ b/docs/Example-Result-TPC-H-MonetDB.md @@ -1,4 +1,4 @@ -## Example: TPC-H SF=100 MonetDB +# Example: MonetDB TPC-H@100 @@ -15,7 +15,7 @@ The purpose of this example is to illustrate the usage of bexhoma and to show ho -### Generate and Load Data +## Generate and Load Data At first we generate TPC-H data at SF=100 (`-sf`) with 8 parallel generators (`-nlp`). The generated data is stored at the shared disk `data`. @@ -49,7 +49,7 @@ nohup python tpch.py -ms 1 \ run &>$LOG_DIR/doc_tpch_monetdb_1.log & ``` -### Status Data Disk +## Status Data Disk You can watch the status of the data disk via `bexperiments data`. @@ -70,7 +70,7 @@ In total the data set has a size of 106G. 106G /data/tpch/SF100 ``` -### Status Database and Benchmark +## Status Database and Benchmark You can watch the status of experiments via `bexperiments status`. @@ -93,7 +93,7 @@ Cluster Prometheus: Running +------------------------------------+-----------------+--------------+--------------+-------------------+------------+----------------------+-----------+----------+--------+--------+ ``` -### Summary of Results +## Summary of Results At the end of a benchmark you will see a summary like @@ -214,7 +214,7 @@ TEST passed: Workflow as planned To see the summary again you can simply call `bexperiments summary -e 1708411664` with the experiment code. -### List local results +## List local results You can inspect a preview list of results via `bexperiments localresults`. diff --git a/docs/Example-TPC-DS.md b/docs/Example-TPC-DS.md index 47cd30d5..eeb16c85 100644 --- a/docs/Example-TPC-DS.md +++ b/docs/Example-TPC-DS.md @@ -28,7 +28,7 @@ For performing the experiment we can run the [tpcds file](https://github.com/Beu Example: ```bash -nohup python tpcds.py -ms 1 -dt -tr \ +nohup python tpcds.py -ms 4 -dt -tr \ -nlp 8 \ -nlt 8 \ -sf 1 \ @@ -38,7 +38,7 @@ nohup python tpcds.py -ms 1 -dt -tr \ ``` This -* starts a clean instance of PostgreSQL, MonetDB, MySQL and MariaDB +* starts a clean instance of PostgreSQL, MonetDB, MySQL and MariaDB (at the same time, `-ms`) * data directory inside a Docker container * with a maximum of 1 DBMS per time (`-ms`) * creates TPC-DS schema in each database @@ -56,6 +56,9 @@ This * data transfer is also measured (`-dt`) * shows a summary +Make sure your cluster can handle 4 DBMS at the same time. +Otherwise adjust die parameter `-ms`. + ### Status You can watch the status while benchmark is running via `bexperiments status` @@ -927,9 +930,9 @@ TEST passed: Workflow as planned The loading times for both instances of loading are the same, since both relate to the same process of ingesting into the database. Note the added section about `volume_size` and `volume_used` in the connections section. -## TPC-DS SF=100 MonetDB +# Example: MonetDB TPC-DS@100 -### First Test Run +## First Test Run This also sets up the database: @@ -947,7 +950,7 @@ nohup python tpcds.py -ms 1 \ run &>$LOG_DIR/doc_tpcds_monetdb_1.log & ``` -### Perform Benchmark - Power Test +## Perform Benchmark - Power Test We now start a new instance of MonetDB and mount the existing database: we use the prepared database on the shared disk. We then run two power tests, one after the other (`-ne 1,1`), and shut down the DBMS. @@ -967,7 +970,7 @@ nohup python tpcds.py -ms 1 \ run &>$LOG_DIR/doc_tpcds_monetdb_2.log & ``` -### Perform Benchmark - Throughput Test +## Perform Benchmark - Throughput Test We now start a new instance of MonetDB and mount the existing database: we use the prepared database on the shared disk. We then run two power tests, one after the other, and then a throughput test with 3 parallel driver (`-ne 1,1,3`). and shut down the DBMS. diff --git a/docs/Example-TPC-H.md b/docs/Example-TPC-H.md index b0ba4e1e..71474127 100644 --- a/docs/Example-TPC-H.md +++ b/docs/Example-TPC-H.md @@ -28,7 +28,7 @@ For performing the experiment we can run the [tpch file](https://github.com/Beut Example: ```bash -nohup python tpch.py -ms 1 -dt -tr \ +nohup python tpch.py -ms 4 -dt -tr \ -nlp 8 \ -nlt 8 \ -sf 1 \ @@ -38,7 +38,7 @@ nohup python tpch.py -ms 1 -dt -tr \ ``` This -* starts a clean instance of PostgreSQL, MonetDB, MySQL and MariaDB +* starts a clean instance of PostgreSQL, MonetDB, MySQL and MariaDB (at the same time, `-ms`) * data directory inside a Docker container * with a maximum of 1 DBMS per time (`-ms`) * creates TPC-H schema in each database @@ -56,6 +56,9 @@ This * data transfer is also measured (`-dt`) * shows a summary +Make sure your cluster can handle 4 DBMS at the same time. +Otherwise adjust die parameter `-ms`. + ### Status You can watch the status while benchmark is running via `bexperiments status` diff --git a/docs/index.rst b/docs/index.rst index 2a0144a8..aadee9a4 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -16,8 +16,8 @@ ./Example-HammerDB.md ./Example-Benchbase.md ./Example-TPC-H.md - ./Example-Result-TPC-H-MonetDB.md ./Example-TPC-DS.md + ./Example-Result-TPC-H-MonetDB.md ./Example-YugaByteDB.md ./Example-CockroachDB.md ./Example-custom.md diff --git a/test-docs.sh b/test-docs.sh index db806d54..3b3fe141 100644 --- a/test-docs.sh +++ b/test-docs.sh @@ -303,7 +303,7 @@ wait_process "benchbase" #### TCP-H Compare (Example-TPC-H.md) -nohup python tpch.py -ms 1 -dt -tr \ +nohup python tpch.py -ms 4 -dt -tr \ -nlp 8 \ -nlt 8 \ -sf 1 \