News for hackers. Stuff that matters.

A comment on Using MySQL as a NoSQL - A story for exceeding 750,000 qps on a commodity server. Parent comment

Re:Using MySQL as a NoSQL - A story for exceeding 750,000 qp... by quassnoi on Tuesday November 09, 2010 @10:58AM (#1886820)
"HDD bound" here means that not all data fits into the cache.

Given the average RAM size on even an entry-level server (some 16 or maybe even 8 GB) and the average size of a database (same 8GB on http://musicbrainz.org/, the largest online music database), I wouldn't claim that it's "most workloads".

[ Parent | on HN ]
Re:Using MySQL as a NoSQL - A story for exceeding 750,000 qp... by icey on Tuesday November 09, 2010 @11:27AM (#1886927)
If we're comparing anecdotes, the smallest database I deal with on any given day is 50GB. Enterprise applications trap lots of data. I don't know that most of our queries are HDD bound, but a significant portion of them are.
[ Parent | on HN ]
Re:Using MySQL as a NoSQL - A story for exceeding 750,000 qp... by quassnoi on Tuesday November 09, 2010 @12:11PM (#1887097)
OK, OK. Most of your workloads are HDD bound.
[ Parent | on HN ]
Re:Using MySQL as a NoSQL - A story for exceeding 750,000 qp... by icey on Tuesday November 09, 2010 @12:19PM (#1887130)
Isn't that the definition of anecdote?
[ Parent | on HN ]
Re:Using MySQL as a NoSQL - A story for exceeding 750,000 qp... by alexro on Tuesday November 09, 2010 @07:55PM (#1888707)
I think while the most performance-critical portion of your data fits in memory you should be alright with this method. The rest of the data can be consumed using normal SQL approach.
[ Parent | on HN ]