What I learned benchmarking Citus & Postgres performance with HammerDB | Citus Con 2023

Video recording of Naisila Puka’s conference talk at Citus Con: An Event for Postgres 2023-about measuring database performance of Azure Cosmos DB for PostgreSQL, the new home for Citus on Azure, by using the HammerDB benchmark. In this talk you’ll get a tour of what Naisila learned in the whole benchmarking process, including:
1. Choosing the Citus database cluster to test: size and tuning of each node
2. Configuring HammerDB based on the cluster's capacity, in order to utilize the cluster's resources as much as possible
3. Interpreting the benchmark result
4.Tweaking parameters in steps 1 and 2 based on the CPU and Disk utilization graphs
Naisila Puka is a software engineer working on the Citus database engine in the Postgres team at Microsoft. She is a fan of organizing & decluttering, algebraic objects, and foreign languages.
► Video bookmarks:
⏩ 00:00 Introducing Naisila
⏩ 01:27 Naisila’s benchmarking talk begins here
⏩ 04:00 OLTP and Citus
⏩ 04:58 HammerDB TPROC-C
⏩ 06:28 Running benchmarks on Azure Cosmos DB for PostgreSQL
⏩ 09:48 Interpreting benchmark results
⏩ 13:30 Increasing concurrent connections
⏩ 19:21 Adjusting the shard count
⏩ 26:20 What I learned about benchmarking
⏩ 28:13 Q&A
✅ Learn more:
Watch more Citus Con talks: aka.ms/cituscon-playlist
📕 Everything you need to know about Citus Con: An Event for Postgres can be found at: aka.ms/cituscon
📌 Let’s connect:  
Twitter - @CitusCon, / cituscon
⭐ Stay connected with the Citus open source project on GitHub: github.com/citusdata/citus
💡Take the Azure Cosmos DB for PostgreSQL training at aka.ms/pg-azurecosmosdb-training
🔔 Subscribe to the Citus monthly technical newsletter: aka.ms/citus-newsletter
More resources:
📣 Slides for this talk: github.com/naisila/slides/blo...
#CitusCon #PostgreSQL #Citus

[@ahmettek315]

Oh well, this could just be put as a paper or somethıng and we could read it as you did as well. You should put a note that there is no code, no demo to prevent time waste.