Wow, I thought the difference would be much greater than that, like 1:10.
I'll do my own tests as well to see for myself.

But this makes parsing all cached pages as ADPs looking for tags to
include other content a real possibility.

Cheers,
Bas.

Olaf Mersmann said:
> Hi Bas,
>
> Bas Scheffers wrote:
>> Has anyone ever done any test on how much of a performance hit an ADP
>> page is (asuming minimal processing, of course!) over fastpath
>> returning a static page?
>
> I did some testing that goes in this direction concering cached /
> noncached ADPs and static files. Here are the numbers that are relevant
> to your question (all this was done on an aging Sun Ultra 2, so the abs.
> numbers are pretty low).
>
> The tests where run with Apaches 'ab' utility with 10000 requests and 4
> concurrent threads (ab -n 10000 -c 4 $url) and the document length was
> 3053 bytes.
>
> Static html file:
> -----------------------------------------------------------------
>    Requests per second:    446.21 [#/sec] (mean)
>    Time per request:       8.964 [ms] (mean)
>    Time per request:       2.241 [ms] (mean, across all concurrent
>                                        requests)
>    Connection Times (ms)
>                  min  mean[+/-sd] median   max
>    Connect:        0    0   0.6      0      37
>    Processing:     2    7   2.7      7      94
>    Waiting:        0    4   2.7      5      93
>    Total:          2    7   2.8      7      94
>
>
> Same file wrapped in an ADP (<% ns_adp_puts {....} %>):
> -----------------------------------------------------------------
>    Requests per second:    290.69 [#/sec] (mean)
>    Time per request:       13.760 [ms] (mean)
>    Time per request:       3.440 [ms] (mean, across all concurrent
>                                        requests)
>    Connection Times (ms)
>                  min  mean[+/-sd] median   max
>    Connect:        0    0   0.2      0       7
>    Processing:     2   12   6.8     13     246
>    Waiting:        0    6   6.7      5     244
>    Total:          2   12   6.8     13     246
>
> Doubeling the file size changes little.
>
> Static html file:
> -----------------------------------------------------------------
>    Requests per second:    464.74 [#/sec] (mean)
>    Time per request:       8.607 [ms] (mean)
>    Time per request:       2.152 [ms] (mean, across all concurrent
>                                        requests)
>    Connection Times (ms)
>                  min  mean[+/-sd] median   max
>    Connect:        0    0   0.3      0       7
>    Processing:     2    7   3.0      7     115
>    Waiting:        0    4   2.9      5     115
>    Total:          3    7   3.1      7     115
>
> Same file wrapped in an ADP (<% ns_adp_puts {....} %>):
> -----------------------------------------------------------------
>    Requests per second:    273.17 [#/sec] (mean)
>    Time per request:       14.643 [ms] (mean)
>    Time per request:       3.661 [ms] (mean, across all concurrent
>                                        requests)
>    Connection Times (ms)
>                  min  mean[+/-sd] median   max
>    Connect:        0    0   0.2      0       9
>    Processing:     2   13  11.9     13     409
>    Waiting:        0    6  11.0      5     353
>    Total:          2   13  11.9     13     409
>
> HTH
>
> -- Olaf
>
>
> --
> AOLserver - http://www.aolserver.com/
>
> To Remove yourself from this list, simply send an email to
> <[EMAIL PROTECTED]> with the
> body of "SIGNOFF AOLSERVER" in the email message. You can leave the
> Subject: field of your email blank.
>


--
AOLserver - http://www.aolserver.com/

To Remove yourself from this list, simply send an email to <[EMAIL PROTECTED]> 
with the
body of "SIGNOFF AOLSERVER" in the email message. You can leave the Subject: 
field of your email blank.

Reply via email to