In Which Redis Guy is Unfair To Sys Toilet Guy

I’m a big fan of Antirez. I’ve been subscribed to his blog for a while.

I’m also a big fan of shoddy benchmarks. Maybe that makes me biased.

So, the sys/toilet guy writes a post benchmarking Redis vs Memcached and concludes that Memcached is faster and Redis doesn’t do so well at setup and teardown.

Antirez responds: (emphasis mine)

Unfortunately I also think that our dude is part of the problem, since running crappy benchmarks is not going to help our pop culture.

Okay, fine. Sys/Toilet guy used some robust language in his post. Antirez has every right to respond in kind.

But the thing is…

Still this benchmark captured my interest. Even with all this problems, why on the earth Redis was showing so low numbers in multi-get (MGET) operations?

I checked the implementation better and found a problem in the query parsing code that resulted in a quadratic algorithm due to a wrong positioned strchr() call.

Hmmm… sounds like the “crappy” benchmark helped. And what’s more, there is already a (presumably decent) Redis benchmark that didn’t pick up the issue.

In Redis land we already have redis-benchmark that assisted us in the course of the latest one and half years, and worked as a great advertising tool: we were able to show that our system was performing well.

So, sys/toilet guy, thanks for making Redis better. I appreciate it.

Advertisements