Github user davisp commented on the pull request:
https://github.com/apache/couchdb-couch/pull/71#issuecomment-121134365
I'm working on getting the actual dataset used and benchmark code. The
general outline of the test though is that they loaded something like 35K
records into a Q=128 database from the XML music set and then had a view that
emitted a row for the artist. The test was then to just run a view query
getting 10 artists starting with a random letter between A-O (I assume there
were less than 10 after O or something).
This test was then run with a number of different concurrent clients. IIRC
somewhere around 100 clients maxed out throughput for both.
The exact numbers we were seeing were about 50-55 req/s with the current
NIF implementation and about 340-350 req/s with this TLS version.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
