S2024 #19 - Snowflake Data Warehouse Internals (CMU Advanced Database Systems)

[@Brandon-youtube]

I don’t work with Snowflake in my current role but I think about the white paper frequently. “Cloud native” is thrown around so loosely but it wasn’t until that white paper where I had seen something that was truly cloud native from start to finish and was only possibly with the scale and flexibility of modern cloud providers.

[@prateek1317]

What funny stuff got chopped off at 40:02?

[@andrewm4894]

We need to know!

[@nosh3019]

+1

[@NickEllis-nr6ot]

Excellent explanations/lecture Prof Andy!

[@CalifornianViking]

Shouldn't Amazon offer a cached S3 service, just like you can get HDDs with cache? The cached service would have an algorithm for keeping the latest objects in memory and have an algorithm to cycle them out when all memory is used. This does not seem to be something that should be written in the application layer of a database. An external system would (should) not even know that this cache is in place. It just connects to the service and gets the cached content. This, however, likely will bring up a potential other issue with S3. I believe (and I may be wrong) that the S3 object is all or nothing. This means that either the whole object is read/written or none of it.

[@sehajpreetsingh6266]

Never knew Alex Honnold taught computer science.

[@hubstrangers3450]

These lectures should've followed HDFS....2011...instead of 2024.....with Compute/Security/Cost/etc, "Cloud should gradually depreciate", doesn't need to join the "Taxing Community..."

[@millouwmills367]

What?

[@hubstrangers3450]

@@millouwmills367 Billions of dollars down the drain...."Scumbag Intel: Shady Practices, Terrible Responses, & Failure to Act", Federal Reserve, Banking Cartel, Pharma Companies, Technologies, Educational Systems......why do everything out there feels like a "Mafia Family" .....