[py-lmdb] Re: Multiple environments to avoid write lock?

  • From: David Wilson <dw@xxxxxxxx>
  • To: py-lmdb@xxxxxxxxxxxxx
  • Date: Thu, 5 Feb 2015 20:46:42 +0000

On Thu, Feb 05, 2015 at 08:13:13PM +0000, David Wilson wrote:

> So you're doing about 32kb of data (tiny) in 121 random reads. Depending
> on your DB size, this should be good for somewhere north of 4,000 read
> requests/sec/core with 2.4ghz Xeon, give or take a factor of 2.

Whoops, it's worth noting these numbers were based on dirtybench.py
output, which by default uses a DB of 1.87 million size-13 string keys.
I forgot that MDB_INTEGERDUP uses an optimized comparison function
(read: likely much faster random IO) in addition to being a storage
optimization, so it's entirely possible there is value in implementing
it in the binding.


Other related posts: