Comments on Agile Testing: Code performance vs system performance

Benjamin -- I disagree. I think slow I/O masks a l...

2012-11-30T13:08:39.380-08:00

Benjamin -- I disagree. I think slow I/O masks a lot of issues that come to the forefront once I/O is not the issue anymore. Once you eliminate your #1 problem, #2 becomes #1. And #2 for most people is poorly written queries and poorly written code that makes too much redundant use of queries.

Poorly written SQL queries are poorly written beca...

2012-11-30T12:51:33.555-08:00

Poorly written SQL queries are poorly written because they have redundant queries which hit the DB, not because they're using so much CPU to process DB results. An order of magnitude faster DBs are going to lessen this problem, not increase it.

Profiling is always the best way to see where to focus optimization efforts. SSDs don't change that.

Simon -- thanks for the kind words. I'll follo...

2012-11-30T10:40:42.700-08:00

Simon -- thanks for the kind words. I'll follow up on your question with another post soon.

Koen -- you refer to raw speeds here. I refer to p...

2012-11-30T10:35:38.295-08:00

Koen -- you refer to raw speeds here. I refer to poorly written SQL queries and poorly written code that uses those queries. That combination can tie up the CPU and potentially cause deadlocks as well no matter how fast your CPU is.

I disagree. Even if the I/O subsystem becomes an o...

2012-11-30T06:09:38.870-08:00

I disagree. Even if the I/O subsystem becomes an order of magnitude faster, this will not be enough to keep the CPU busy all the time; I/O subsystem >> RAM >> CPU cache; there's multiple orders of magnitude difference between them.

Hi Grig. Nice article. I'm interested to kno...

2012-11-29T17:02:50.413-08:00

Hi Grig. Nice article.

I'm interested to know, from a tester rather than a developer perspective - what tools do you think are useful for measuring code performance?