Hacker News Reader

Comment by eloff | Hacker News Reader

So what's special about this database? What properties does it have that are superior to the currently available alternatives? This article is all hype and no substance.

EDIT: GitHub has more information. It's a scalable ordered key-value store (think a distributed version of Berkeley db.) Storage is based on RocksDB (a variant of LevelDB) and consensus is achieved using Raft. The database is written in Go. It's meant to "tolerate disk, machine, rack, and even datacenter failures with minimal latency disruption and no manual intervention."

What's not clear at all is where it sits CAP wise. It says it's available and strongly consistent. Which would be CA, which is not an option (especially for something claiming to be failure tolerant.) It must either sacrifice write availability or consistency in the event of a partition. No idea which way it leans.

View on HN

> Cockroach provides snapshot isolation (SI) and serializable snapshot isolation (SSI) semantics, allowing externally consistent, lock-free reads and writes--both from an historical snapshot timestamp and from the current wall clock time. SI provides lock-free reads and writes but still allows write skew. SSI eliminates write skew, but introduces a performance hit in the case of a contentious system. SSI is the default isolation; clients must consciously decide to trade correctness for performance. Cockroach implements a limited form of linearalizability, providing ordering for any observer or chain of observers.

Either you use a strongly consistent mode that can have poor performance under contention, or a strongly consistent mode that will have good performance under contention but lots of failed transactions. So you get to decide on performance vs availability.

To answer your question, it sacrifices availability, not consistency. It's an MVCC, after all.

I think they're trying to create open source Spanner. Here is Google scientific paper about Spanner. http://static.googleusercontent.com/media/research.google.co...

In my opinion, one of the most profound ideas in Spanner is the introduction of TrueTime API and the guarantee provided in the implementation. I wonder if this project is going to have something similar?

From the description, it sounds like they're not at the moment. Instead, they seem to be aiming for the globally replicated, consistent, SQL-supporting features. Nothing wrong with that -- the world could use more geographically-aware database implementations. Seems like they'd be able to make use of the time sync for more efficient replication/failover/transactions in the future when the hardware is more widely available.

Why are they using RocksDB rather than LMDB?

If it's based on Raft, then it sacrifices availability if there aren't a quorum of nodes online.

Probably because 1. LMDB is limited to logical address space, 2. it has one big global lock, 3. It's a B-Tree, and both of those contribute to the fact that 4. LMDB is a read-oriented database [performance wise]. I would conjecture that Rocks could also be 'more easily embeddable', but i'm talking out my ass there :)

And yeah, you kind of have to sacrifice availability if you want to stay consistent in the face of write skew...

One big global write lock in LMDB maps pretty well to one single stream of replicated log entries in Raft, IMO.

And logical address space is still far in excess of what most disks or arrays can fit, right? 40 bits or so on linux?

EDIT: 47 bits, for 128TB -- http://stackoverflow.com/questions/2159456/whats-the-max-fil...

I don't see how? One global write lock means a single instance can't update multiple ranges at a time, so determining consensus and writing from multiple peers would just take a long time for no reason. The whole point of an SSI MVCC is to get around difficult locks....

If Moore's law holds, a single SSD will outgrow the address space in around 7 years. In four years, an array of eight disks would outgrow the address space. This is just for a single server. If you want a linearly-scaling, robust solution for future requirements (like multi-petabyte and exabyte distributed datastores), there's no reason to lock yourself into technology that'll be obsolete in half a decade.

(edit: SanDisk says it may release 8TB SSDs next year, also adding "We see reaching the 4TB mark as really just the beginning and expect to continue doubling the capacity every year or two, far outpacing the growth for traditional HDDs")

I'm not on the inside of cockroachDB's raft implementation, but typically you've got a single thread processing AppendEntries requests in a defined order, exactly one at a time, to guarantee the same order of execution on every node. There might be some small savings from doing a couple of updates concurrently here and there but your overall flow should be single threaded.

As far as the address space and big SSDs thing.. I'd be willing to gamble on linux supporting mmap up to the biggest devices on the market, one way or another. Heck, there's only 16 more bits after that 47 before every FS under VFS has to be rewritten, right?

IIRC, current x86-64 chips are limited to 48bits virtual address to simplify the address translation logic (cheaper to manufacture).

This makes sense for the current generation of storage sub-systems, though it would be misleading to say using memory map technology will be "obsolete in half a decade". The 48 bit limit is arbitrary. Manufacturers have 56 bit designs on the table right now, and there is nothing stopping them from implementing full 64 bit virtual address support.

I benchmarked lmdb vs. leveldb once and on a write-heavy workload leveldb destroys lmdb (think 10x better perf).

The author of LMDB makes pretty bold performance claims and people are too eager to believe them.

You shouldn't propagate those claims unless you've done benchmarking to verify them.

I would be interested in seeing your benchmarks.

The author of LMDB doesn't really make bold claims, he actually just included LMDB (and the venerable Berkeley DB) in LevelDB's published benchmarks. The benchmarks were developed by the LevelDB team.

http://symas.com/mdb/microbench/

http://symas.com/mdb/inmem/

Reply on news.ycombinator.com