Wednesday, April 9, 2014

Why aren't multi-object updates atomic?

Losing ACID across shards isn't an excuse for not having it within a shard. Applications control the shard key and can co-locate data that would benefit from this feature. Performance imperfections in the product, limits in the product and application data models will require this in some deployments.

No comments:

Post a Comment

RocksDB on a big server: LRU vs hyperclock

This has benchmark results for RocksDB using a big (48-core) server. I ran tests to document the impact of the the block cache type (LRU vs ...