Hi HN, we’re Joe and JD from Hydra (<a href="https://hydra.so/" rel="nofollow">https://hydra.so/</a>). We're excited to announce our team has added parallel query execution and vectorization to columnar storage on Postgres. In our blog you can review the clickbench benchmarks and the method of how we built Hydra.<p>Hydra open source (<a href="https://github.com/HydrasDB/hydra" rel="nofollow">https://github.com/HydrasDB/hydra</a>)<p>Starting today, we are now offering 14-day free trials of our cloud managed Hydra databases. Click the 'Get Started for Free" button on (<a href="https://hydra.so/" rel="nofollow">https://hydra.so/</a>) to get one.<p>Power to the Postgres people!
I'm a deep Postgres person and I'm very interested in the project. Congratulations and welcome as a new open source project to the ecosystem.<p>One important recommendation: please do not run benchmarks on variable-performance storage (gp2 in this case), as it obviously may yield different performance depending on the credit situation, potentially delivering more or less performance to different benchmark runs / scenarios.<p>Specifically, for 500GB you get the max throughput (250MB/s, which BTW is pretty low for an OLAP-style bench, in my opinion) but only 1.5K IOPS. See [1] for more information.<p>An easy alternative would have been gp3 volumes, which do not burst performance, and can be set to provide 16K IOPS and 1Gbps.<p>[1] <a href="https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/general-purpose.html#gp2-performance" rel="nofollow">https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/general-...</a>
Just checked out the site:
I really like the fact that you guys are addressing some of the core capabilities in the data stack (ie ETL).<p>The fact that you guys are supporting DBT natively is a HUGE plus for a data professional like myself.<p>Will definitely be kicking the tires soon & testing against my own workloads.
Congrats for the launch!<p>As I’ve anticipated, clickbench will become the defacto analytics benchmark, which is great.<p>Something to improve IMHO it’s documentation regarding Cloud and Open Source. Is somehow mixed (the same happen in ClickHouse docs)<p>As a Postgres user I would like to see: how can I install this extension in my current Database? How to migrate to new tables.<p>Timescale makes a really great job in this case.<p>Anyway, as I’ve said. Congrats and good luck!
Few questions:<p>How does it work for writing, I saw somewhere that the columnar tables are append-only? Are there any plans on storage which can be merge or updated into?<p>It is transactional, right? That part of Postgres doesn't change with the plugin.<p>Would you support a business model "install in customer cloud and we provide support" or is your own cloud the only option?
Why benchmark against AWS Aurora rather than Redshift, which would seem a closer/more relevant comparison to me?<p>Also omits ClickHouse, despite using <i>its</i> benchmarking tooling?<p>Edit: Oh, because for some reason Redshift isn't considered postgres compatible in ClickBench. Still, 'the fastest' is 'greenplum' according the full thing: <a href="https://benchmark.clickhouse.com/#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" rel="nofollow">https://benchmark.clickhouse.com/#eyJzeXN0ZW0iOnsiQXRoZW5hIC...</a>