[Zope] Zope performance too low ?

Alexander Staubo alex@mop.no
Thu, 17 Jun 1999 17:38:08 +0200


>-----Original Message-----
>From: Michel Pelletier [mailto:michel@digicool.com]
>Sent: 17. juni 1999 16:48
>To: 'Alexander Staubo'; Zope Mailing List (E-mail)
>Subject: RE: [Zope] Zope performance too low ?
>
>
>> -----Original Message-----
>> From: Alexander Staubo [mailto:alex@mop.no]
>> Sent: Thursday, June 17, 1999 10:36 AM
>> To: Zope Mailing List (E-mail)
>> Subject: RE: [Zope] Zope performance too low ?
>>
>>
>> >-----Original Message-----
>> >From: zope-admin@zope.org [mailto:zope-admin@zope.org]On Behalf Of
>> >Michel Pelletier
>>
>> Ouch. These extremely low transfer rates bother me. The theoretical
>> bandwidth on a local machine transfer should be way, way
>higher. Otoh,
>> your document was very small, so the stop/start, connect/teardown
>> margins would be relatively high. I'd like to see benchmarks
>> with longer
>> (>3KB) documents.
>>
>
>I think these numbers are low because the trasfer was so fast
>and small,
>the mathmatical precision of the calculation was effected.  I
>don't know
>how 'ab' calculates time, but it probably uses some less than high
>resolution system call.

I'm not familiar enough to Linux to say this for sure, but my guess is
that it _would_ be using a high-resolution system timer.

Otoh, if transfers really were fast (that is, faster than 10-11KB/sec),
and the time taken to complete a request was low, the transfer time
should explode exponentially. (Eg., 10K transferred in 10ms should yield
a transfer rate 1MB/sec.)

I'd be very interested to hear about what the CPU load was during the
test run. If it's anything above 5-8% (average), that's not promising at
all. The fact that adding more concurrent sessions did not regrade
performance seems to indicate that CPU load was not too bad.

I'm planning on putting together a simple httplib-built benchmark test
just to get some raw numbers, although I'd like to try putting the
timing logic inside Zope.

>> Yep, but ASP, PHP, Cold Fusion, etc. have proven to be very,
>> very fast.
>>
>
>I can see PHP being convincingly 'proven' to be fast, but I have doubts
>about the validity *any* comercial company says about their closed
>source program.  Have there been independant benchmarks?

Yes, at least for ASP, but I forget where. Perchance Byte Magazine,
which used to lots of very interesting tests and benchmarks before they
were gobbled up by CMP Media and folded into an online mag. :-/

--
Alexander Staubo             http://www.mop.no/~alex/
"`Ford, you're turning into a penguin. Stop it.'"
--Douglas Adams, _The Hitchhiker's Guide to the Galaxy_