It sounds ... wrong.
Can you not setup a test harness for your production software, to mimic
what they'll be used for in real-life ? If it was a database, for instance,
record the last 100,000 select queries that were run, populate the new
server with a copy of the database, and replay the 100,000 queries with
concurrencies of 5, 20 and 100. See how the times change. You might notice
that because the new machine has more RAM, it'll do better at higher
concurrency rates.
Write performance is harder, but it's worth doing. All bonnie++ benchmarks
will tell you is how fast bonnie++ runs on the new platform.
BTW, it's also really good to guess how well your app's benchmarks will run
in advance, before you try run it. If your guess is off, it's a good sign
you don't understand completely how it works. You might even find
performance bugs you don't understand.
But, if you don't have time, and you are just curious about how bonnie++
works, yeah, work away. It's an interesting datapoint.
John
Maintained by the ILUG website team. The aim of Linux.ie is to
support and help commercial and private users of Linux in Ireland. You can
display ILUG news in your own webpages, read backend
information to find out how. Networking services kindly provided by HEAnet, server kindly donated by
Dell. Linux is a trademark of Linus Torvalds,
used with permission. No penguins were harmed in the production or maintenance
of this highly praised website. Looking for the
Indian Linux Users' Group? Try here. If you've read all this and aren't a lawyer: you should be!
