This year
Experiences with Node.js: Porting a RESTful Service Written in Java - ZiggyTech
After more research and swapping out modules, the bottleneck was narrowed down to the Sequelize ORM. A direct correlation was identified between the number of records and the throughput from the resource. By increasing the number of records in a table, it exponentially decreased the throughput of data when using Sequelize.
On comprend mieux pourquoi les révolutionnaires se concentrent sur le NoSQL : c'est qu'ils ont du mal avec le SQL :-)
2010
Yoshinori Matsunobu's blog: Using MySQL as a NoSQL - A story for exceeding 750,000 qps on a commodity server
2009
