Posts

Showing posts from January, 2023

TPC-E vs. TPC-C: Characterizing the New TPC-E Benchmark via an I/O Comparison Study

Image
This paper is from Sigmod 2010, and compares the two standard TPC benchmarks for OLTP, TPC-C which came in 1992, and the TPC-E which dropped in 2007. TPC-E is designed to be a more realistic and sophisticated OLTP benchmark than TPC-C by incorporating realistic data skews and referential integrity constraints. However, because of its complexity, TPC-E is more difficult to implement, and hard to provide reproducability of the results by others. As a result adoption had been very slow and little. (I linked TPC-C to its TPC-C wikipedia page above, but poor TPC-E does not even have a Wikipedia page. Instead it has this 1990s style webpage .) A more cynical view on the immense popularity of TPC-C over TPC-E would be that TPC-C can be easily abused to show your database in the best possible light. TPC-C is very easily shardable on the  warehouse_id to hide any contention on concurrency control, so your database would be able to display high-scalability. We had recently reviewed the OceanSt

Is Scalable OLTP in the Cloud a Solved Problem? (CIDR 2023)

Image
This paper appeared in CIDR 2023 recently. It is a thought provoking big picture paper, coming from a great  team. The paper draws attention to the divide between conventional wisdom on building scalable OLTP databases (shared-nothing architecture) and how they are built and deployed on the cloud (shared storage architecture). There are shared nothing systems like CockroachDB, Yugabyte, and Spanner, but the overwhelming trend/volume on cloud OLTP is shared storage, and even with single writer, like AWS Aurora , Azure SQL HyperScale, PolarDB, and AlloyDB. The paper doesn't analyze this divide in detail, and jumps off to discuss shared storage with multiple writer as a more scalable way to build cloud OLTP databases. It would have been nice to go deep on this divide. I think the big benefit from shared storage is the disaggregation we get between compute and storage, which allows us to scale/optimize compute and storage resources independently based on demand. Shared storage also al

Reconfiguring Replicated Atomic Storage

Image
Reconfiguration is a rich source of faults in distributed systems. If you don't reconfigure, you lose availability when you lose additional nodes. But the reconfiguration algorithms are subtle, and it is easy to get them wrong, and lose consistency during reconfiguration. This is because a reconfiguration operation is run concurrently with the read/write operations and with potentially other reconfiguration operations, and they run when the system is already in some turmoil due to faults. Even the consensus papers/protocols do a bad job of addressing the reconfiguration problem; reconfiguration is always addressed as secondarily, incompletely, and many times incorrectly. This paper, which appeared in the Bulletin of the EATCS: The Distributed Computing 2010, is about reconfiguration protocols for atomic storage. The atomic storage problem is a simpler problem than consensus or state machine replication (SMR). The difference is atomic storage is hedonistic (lives in the moment), it

Popular posts from this blog

Hints for Distributed Systems Design

Learning about distributed systems: where to start?

Making database systems usable

Looming Liability Machines (LLMs)

Foundational distributed systems papers

Advice to the young

Linearizability: A Correctness Condition for Concurrent Objects

Scalable OLTP in the Cloud: What’s the BIG DEAL?

Understanding the Performance Implications of Storage-Disaggregated Databases

Designing Data Intensive Applications (DDIA) Book