51–60 of 74 posts
Other people have had trouble wringing competitive performance out of Bw-Trees despite heroic optimization efforts [0]. Why is this implementation going to beat other index structures with just a bit of tuning? [0] https://news.ycombinator.com/item?id=17041616
Earlier quoted context omitted.
Your parent didn't say that. Speaking about Rust in a thread about a Rust project seems to be very on-topic? (I would also disagree with that statement, but in a different way: Rust enables zero-cost abstractions, but nothing inherently means they have to be. I can also make quite costly ones, and they'll compile.)
> Your parent didn't say that. Yes and it's more disturbing. It says "In Rust abstractions are free" when an algorithm was discussed. Rust having "free" abstractions does not change the performance characteristics of an algorithm: this is what the grand-parent was talking about.
Other people have had trouble wringing competitive performance out of Bw-Trees despite heroic optimization efforts [0]. Why is this implementation going to beat other index structures with just a bit of tuning? [0] https://news.ycombinator.com/item?id=17041616
It might not. But the critiques of bw trees in terms of performance that I've seen have not had compelling data in terms of things that matter outside of academia or benchmarking shootouts, like write or space amplification. The bw tree is a cheap thing to abandon after I implement a persistent ART and measure it though. The bwtree is only like 1k of rust on top of the modular pagecache, which is the real heart of th…
https://db.cs.cmu.edu/papers/2018/mod342-wangA.pdf
Moving to ARTs (possibly combined with B+ trees) might be a smart choice after all.
Edit: sorry, I missed that grand-parent has cited the same paper already.
Earlier quoted context omitted.
Your parent didn't say that. Speaking about Rust in a thread about a Rust project seems to be very on-topic? (I would also disagree with that statement, but in a different way: Rust enables zero-cost abstractions, but nothing inherently means they have to be. I can also make quite costly ones, and they'll compile.)
> Your parent didn't say that. Yes and it's more disturbing. It says "In Rust abstractions are free" when an algorithm was discussed. Rust having "free" abstractions does not change the performance characteristics of an algorithm: this is what the grand-parent was talking about.
Other people have had trouble wringing competitive performance out of Bw-Trees despite heroic optimization efforts [0]. Why is this implementation going to beat other index structures with just a bit of tuning? [0] https://news.ycombinator.com/item?id=17041616
That paper is pretty good but it's comparing bw-tree with much simpler in memory data structures. I think bw-tress might work specially well for fast-disk storage.
Earlier quoted context omitted.
You can't cluster an embedded database, this comment makes not sense. Compare with SQLite, not with Orcale or Postgres.
Currently it's even more basic. The current usable parts are a pagecache following the llama approach, some great testing utility libraries, and an index (that you can use as a kv) that follows the bwtree approach. Later it will have structured access support, but it needs some more db components to get there. It is a construction kit as well as a kv.
Other people have had trouble wringing competitive performance out of Bw-Trees despite heroic optimization efforts [0]. Why is this implementation going to beat other index structures with just a bit of tuning? [0] https://news.ycombinator.com/item?id=17041616
That paper is pretty good but it's comparing bw-tree with much simpler in memory data structures. I think bw-tress might work specially well for fast-disk storage.
That's precisely the claim made in the original paper describing Bw-trees.
How does it compare relatively to dgraph's Badger library?
I see that MVCC is a planned feature. Why would you need MVCC for an embedded database? It seems like unnecessary overhead that conflicts with the performance goals.
It's not needed for the single-key atomic record store, which is the sled bwtree index that is the current highest level module. MVCC is implemented in most popular embedded DBs because it is an effective way to manage mixed workloads that seek to read snapshots of the entire database at a single point in time as well as not blocking writes as this happens. This functionality is desirable for transactions that suppor…
Does rust compile reliably to embedded targets yet? Last time I checked there were a lot of problems with armv5.