[thelist] Performance testing: Reasonable TTLB benchmark

Paul Cowan paul at wishlist.com.au
Sun May 27 21:26:25 CDT 2001


Hi all,

I know this is the most vague possible email, and one for which it will 
be extremely hard to provide an intelligent answer, but I'm trying to 
help out a friend, and someone out there might be able to give us a
hand.

She is having problems with her web development company over the speed
of the site they have developed for her. She drew some rough figures
out of the air, and asked me if I thought they were a reasonable benchmark.

For the record, the site (without naming names or giving too much away):
	- is largely content-driven
	- provides a service that is not dissimilar to a job-
	  searching/job-matching service (but not actually that)
	- provides news and classified-type services to certain niche 
	  user groups on topics that interest them
	- does not, as far as I am aware, use SSL encryption anywhere
	  (which would slow it down a bit)
	- runs on Sun-clone Solaris hardware, running BEA 
	  WebLogic off Oracle
	- contains nothing (getting even vaguer here, I know)
	  which is particularly complicated or more whizz-bang
	  than the majority of content-based sites out there (really
	  no magic 'special features' - just hierarchical/searchable
	  blocks of text)

My friend told the dev. company that the site should cope with 3 page 
requests/sec, with a Time-To-Last-Byte (TTLB) of 1.5 secs. The 
development company scoffed at this, saying it was unreasonable and 
they couldn't meet those specs.

I, of course, in turn scoffed at them, because I am well aware that
3 pages/sec @ 1.5 sec TTLB each should be a doddle for pretty much
any straightforward app. Based on my experiences, serving HEAVILY dynamic
non-cacheable pages @ 15/sec with 500-600 millisecond TTLB is quite 
doable, on crappy old pure VBScript ASP.

Basically, my friends wants some 'ammo' to use against this company. I
realise what I've told you is almost impossibly vague, but if anyone can 
point to a site she can use as a comparison to say her benchmarks are 
not unreasonable, or even any anecdotal evidence you can provide to 
back up my belief that the company in question are a load of shonks for 
even suggesting such a thing, we will both be very grateful.

What would you say to them? What would you use to back it up? etc.

Thanks in advance for any help.

Cheers,

Paul Cowan




More information about the thelist mailing list