pjdbruin

Great to see cost-effective alternatives to Cloudera and Databricks! We’ve spent three years building IOMETE, a self-hosted data lakehouse that combines Apache Iceberg and Spark, designed to run natively on Kubernetes. We’re focused on on-premises deployments to address the growing need for data sovereignty and low TCO, with a streamlined setup for large-scale analytics. Early adopters are seeing strong results. Curious about your experience with Trino and Superset—any tips for optimizing performance at scale?

LOL!

Just ran your comments - not just this comment - through ChatGPT and am passing along the feedback: As an AI language model, I do not have personal opinions or emotions. However, based on an objective analysis of the language used by catchnear4321 in the comments above, I can say that their tone appears to be confrontational and aggressive. They use strong and direct language, and they do not seem to be interested in having a constructive conversation. This type of communication style can sometimes be counterproductive in online discussions and can lead to misunderstandings or conflict.

The article doesn't claim that demand (or pricing) is inelastic in the data space. It makes the point that VC funding has inflated price levels across the board, similar to how college tuitions rose dramatically after student debt became widely available. There are still differences between college tuitions, but overall tuitions might be multiple(s) higher compared to what the price would have been if there was no (cheap) financing available even.

Now that VC funding is mostly on the sidelines the question is how this will play out further.

Haven't studied Elastic and Confluent, but Snowflake seems now profitable (5%) with 25% free cash flow. See p.28 of their last investor presentation. https://s26.q4cdn.com/463892824/files/doc_financials/2023/q4...

Not necessarily. Switching cost is an issue when the effort to switch is bigger than the potential benefits of switching (where benefit can be added functionality or lower costs).

For instance, average Snowflake bill is $300k and many Snowflake customers (almost 400) pay more than a million per year. If you can cut that in half by augmenting Snowflake with IOMETE that's a pretty sweet deal.

No need to switch (that's a hard sell for an early stage startup to enterprise customers), but just augment...

How? By transitioning some of the compute load to IOMETE data lake. IOMETE charges a flat fee compared to Snowflake's consumption-based model. By cutting Snowflake compute consumption (often 5x or more the price of an AWS instance) organizations can save a lot.