TurboKV: Insanely fast Rust key-value store (github.com)

43 pointsby rgbimbochamp3 hours ago12 comments

dangoodmanUT an hour ago

> DbOptions::durable()

> Appended to the WAL without a per-write sync

So… it’s not durable? Durable doesn’t mean “survives a process restart”, it means “durably saved to persistent storage”. For example, this “durable” mode wouldn’t survive power loss.

stingraycharles an hour ago

Yeah this should be benchmarked against other systems that have flush() disabled.

mmap is nice but it doesn’t support durable semantics in the way that we usually mean with databases.

if a write is acknowledged it should not be forgotten, which is not what this is.

rgbimbochamp 42 minutes ago

You're right, that mode provides process crash recovery, not power-loss durability. The benchmark compares it against fjall’s equivalent buffered-WAL mode.

a2ff6eeb0 22 minutes ago

If that's your design constraint, couldn't you speed it up by getting rid of the WAL?

boguscoder 17 minutes ago

Embedded could also mean no_std, which this is absolutely not. Still cool though

AtlasBarfed 8 minutes ago

Aphyr or gtfo

nine_k 2 hours ago

I suppose the insane speed is due to this:

> TurboKV's persisted Bloom-filter format uses hardware AES.

Also, built-in LZ4 compression.

I would expect SIMD to be used for scans.

rgbimbochamp an hour ago

Those help but the main write speed gain is the WAL, that uses preallocated mmap segments to avoid a write(2) per durable mutation while preserving crash recovery. AES hashing mainly helps Bloom filter point lookups and LZ4 mainly helps SSTable I/O. Scans benefit indirectly, but don’t yet use a custom SIMD merge loop.

dangoodmanUT an hour ago

Iirc that’s how badger handles the WAL as well

bestouff 34 minutes ago

I said elsewhere this doesn't survive a power loss.

taneq 30 minutes ago

While it’s important to make this explicit, at what point do we just assume a high-reliability UPS is table stakes?

Of course, if you need SIL2 type reliability then you need to assume any given hardware component can spontaneously combust and become a total loss, at which point the data loss caused by a power cut is a rounding error.

haberman an hour ago

I assume this is for hashing. I've seen several hashing algorithms turn to hardware AES instructions before, but I haven't seen any evidence that this technique outperforms state-of-the-art hashes like RapidHash (https://github.com/Nicoshev/rapidhash) in either quality or speed.