"For a typical 1-KB item, Cosmos DB guarantees end-to-end latency of reads under 10 ms and indexed writes under 15 ms at the 99th percentile, within the same Azure region."

i.e. 1 KB item; Same Azure region;

This now seems more plausible.

One thing I'm curious about is if they tested load on a single partition, or if they only tested latencies for random access.

It is interesting that given their scale it essentially says that you can implement twitter on one of these and be done with a chunk of the infrastructure.

Cosmos DB guarantees both low latency and that you can achieve your provisioned throughput with SLAs. Latency is guaranteed at p99 regardless of storage size or number of partitions.

Sorry, I'm not talking about "number of partitions" but if I "forcibly"[0] hit the same partition, will the SLA hold?

[0] i.e. If I somehow pick keys which are on the same partition.

Agreed - seems like a rebranding in response to Google Cloud Spanner DB announcement a couple of months back. Microsoft's marketing seems to be pushing some of the same outcomes in the ad copy.

We just did a benchmarking for a PoC on DocumentDB side-by-side Cassandra. It does the job, I have not yet seen anything revolutionary. Cassandra benchmarks seemed better.

One key difference is the cost difference between running Cosmos DB and Cassandra. We have a TCO paper (https://aka.ms/documentdb-tco-paper) that shows that for a 1M operations/second workload, Cosmos DB is significantly 3x-10x cheaper than other systems.

And white papers are full of it. Has random things like s Cassandra cluster needs 1 full time engineer per 100 nodes. Where do you come up with this stuff?

In my experience of Cassandra (working on an application client, not managing it), one FTE per hundred nodes is extremely generous.

Do you mean that you typically need more engineers, or less?

The former. One FTE per dozen nodes is more in line with what I've seen in practice.

Given that this makes bolder claims that Cassandra, near-parity is pretty impressive, no?

(I don't know a ton about either technology, please correct me if I'm wrong)

this is a little bit hard to believe. Inter region Ping can even take longer than 15ms... I guess this SLA is for eventual consistency model not strong consistency model

The latency SLAs are within the same Azure region. You can distribute your data across any of the 30+ regions that Azure is available in. Your apps always read from the local/closest region with the homing APIs.

That didn't answer the question: will all regions be always consistent?

We would invite you to explore the consistency levels available in Cosmos DB. As a developer you can choose what makes most sense in distributed scenario. https://docs.microsoft.com/en-us/azure/documentdb/documentdb... Eventual is one end of the consistency. But then consistent prefix, session (if you can control) and bounded staleness all can play a role.

Tunable consistency. Very cool.