News for hackers. Stuff that matters.
Re:HSE: Heterogeneous-memory storage engine designed for SSDs by aloknnikhil on Monday April 27, 2020 @06:03PM (#23000636)
> https://github.com/hse-project/hse

Their benchmarks show significant gains compared to RocksDB.

> https://github.com/spdk/rocksdb

But what I'd really like to see is a comparison against RocksDB using SPDK

> https://dqtibwqq6s6ux.cloudfront.net/download/papers/Hitachi... Based on these results, SPDK performs significantly better than the kernel requiring only 1-2 cores to saturate IOPS on an NVMe SSD (compared to the kernel requiring 16)

Re:HSE: Heterogeneous-memory storage engine designed for SSDs by benlwalker on Monday April 27, 2020 @08:15PM (#23001850)
SPDK's RocksDB integration really hasn't gotten a lot of love. There's really two main challenges we hit and then never revisited.

First, the IO threads in RocksDB are a thread pool that assume they perform blocking operations. That doesn't jive with SPDK's async model (nor io_uring's). We're having to message pass to an async thread and block on semaphores in the IO threads.

Second, RocksDB was heavily reliant on the kernel page cache to make it fast.

Both of these things could have changed since we last worked on the integration. I haven't kept up with RocksDB development recently.

source: am SPDK maintainer

Re:HSE: Heterogeneous-memory storage engine designed for SSDs by continuations on Tuesday April 28, 2020 @09:53AM (#23006947)
The SPDK RocksDB repo (https://github.com/spdk/rocksdb) seems to have been abandoned (last commit 2017).

Is there a maintained version of SPDK RocksDB? Or SPDK any DB?

Re:HSE: Heterogeneous-memory storage engine designed for SSDs by wtallis on Monday April 27, 2020 @06:07PM (#23000675)
I'd also like to see comparison to Toshiba/Kioxia's fork TRocksDB: https://github.com/KioxiaAmerica/trocksdb
Re:HSE: Heterogeneous-memory storage engine designed for SSDs by ignoramous on Monday April 27, 2020 @07:40PM (#23001540)
SPDK has had its share of detractors here on news.yc [0], especially with io_uring around the block [1]. It'd be interesting to see the improvements to these io-centric applications once they move to io_uring [2], which, in a way, like RocksDB, is sponsored by Facebook [3].

[0] https://news.ycombinator.com/item?id=10511960

[1] https://news.ycombinator.com/item?id=22266503

[2] https://news.ycombinator.com/item?id=19843464

[3] https://lkml.org/lkml/2014/1/24/252

Re:HSE: Heterogeneous-memory storage engine designed for SSDs by benlwalker on Monday April 27, 2020 @08:10PM (#23001811)
io_uring is a fantastic development for the kernel, and I really can't praise it enough.

However, there's still lots of reasons to use SPDK. Performance is still significantly better[0], and you can directly access all the of the NVMe features on the device without going through any abstraction layers.

[0] https://spdk.io/news/2019/05/06/nvme/

Re:HSE: Heterogeneous-memory storage engine designed for SSDs by zerd on Monday April 27, 2020 @09:08PM (#23002202)
Woah, just realizing that 10.39M 4k IOPS is 42GB/s. Doing 40GB/s of sequential IO was difficult not that many years ago, let alone random IO. That's faster than my memory bandwidth. https://www.microway.com/knowledge-center-articles/performan...
Re:HSE: Heterogeneous-memory storage engine designed for SSDs by teleforce on Tuesday April 28, 2020 @02:09AM (#23003952)
For those who is wondering about what is io_uring and its significance I'd highly recommend this blog article posted at HN few days ago[1].

The potential of using io_uring with eBPF in Linux will makes any HPC enthusiast drooling :-)

https://news.ycombinator.com/item?id=22974728

Re:HSE: Heterogeneous-memory storage engine designed for SSDs by Rafuino on Monday April 27, 2020 @07:58PM (#23001707)
SPDK has made some progress since [0] was posted in 2015 (see https://spdk.io/ if you're curious). Still, I am excited about io_uring and what it brings to the table.
Re:HSE: Heterogeneous-memory storage engine designed for SSDs by AtlasBarfed on Monday April 27, 2020 @07:44PM (#23001579)
Is there an api compatibility for this thing so it can be switched easily out for things like Rocksandra?