Hi,
See below.
Roy
> -Original Message-
> From: Thomas Bezdicek [mailto:[EMAIL PROTECTED]]
> Sent: 02 March 2001 09:50
> To: [EMAIL PROTECTED]
> Subject: Just another Benchmark
> Hi,
> we tried the apachebench on our solaris system, to check out
> differences between architecture
lem, this is a part of 20 man/years
commercial
project.
---
Roy
Roy Wilson
(E-mail) [EMAIL PROTECTED]
(Business) JLWIP_Services
(Affiliate) HotDispatch
>>>>>>>>>>>>>>>> Original Message <<<<<<<<<<<<<<<<
I forgot to mention in my earlier post that in his concurrency book Doug
Lea also endorse the use of the JCSP library (although the licensing
issues with may indeed be murky).
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
>>>>>>>>>>>>>>>>>&g
ugly/dysfunctional/etc for another.
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
>>>>>>>>>>>>>>>>>> Original Message <<<<<<<<<<<<<<<<<<
On 12/22/00, 3:42:13 PM, "Stein M. Eliassen&qu
annot invoke a server method unless the
server accepts the request. Info about the library is at
http://www.cs.ukc.ac.uk/projects/ofa/jcsp/
Happy Holidays
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
>>>>>>>>>>>>>>>>>> Original M
Title: How do you spell relief?
Jon,
Thanks (and thank God) for comic relief (which is nevertheless not
off-topic).
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
>>>>>>>>>>>>>>>>>> Original Message <<<<<<<<<&l
n then find out whether I can do what I want. But,
whatever's easiest for you (assuming you hear no complaints from the
community).
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
>>>>>>>>>>>>>>>>>> Original Message <<<<<<
putting things. The phrase, "it's
deja vu all over again" basically says the same thing twice. No criticism
of any sort was intended, nor was the attempt at humor directed at
anyone.
I usually keep in mind that the world is not the U.S., but slipped up
this time.
Adios, Roy
--
Ro
to the list and see if anyone has any heartburn. Does anyone?
If I don't hear anything for a week, I'll assume it's a non-issue.
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
>>>>>>>>>>>>>>>>>> Original Message <<<&
#x27;s an excelent catch, and a stupid mistake ( mea culpa ).
> ( and yet another proof for the importance of code review.)
I know what code review means in a more-or-less standard setting, but
what does/should it mean for open source development? Is or isn't it
happening with TC?
> Costin
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
s
vary by machine configuration and software configuration, not request
type.
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
tuff (along with Costin's) might be a key part of a
> great guide to TCx performance and tuning ala Dean Gaudet's stuff on
> (Apache?) performance.
That sounds like a much needed guide. Maybe a HOWTO?
>> Jason Brittain
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
he next round of measurement (and, in my case, modeling).
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
>>>>>>>>>>>>>>>>>> Original Message <<<<<<<<<<<<<<<<<<
On 12/5/00, 1:47:46 PM, J
>> Original Message <<
On 12/5/00, 1:42:41 AM, [EMAIL PROTECTED] wrote regarding Re:
Benchmarks / Performance Tuning:
> It is very important to use "ab -c 20 " ( or more ) to get real
> information about how the server works under load - "ab -c 1 " is of no
>
Thanks, Jon
Roy
>>>>>>>>>>>>>>>>>> Original Message <<<<<<<<<<<<<<<<<<
On 11/14/00, 4:21:49 PM, Jon Stevens <[EMAIL PROTECTED]> wrote regarding Re:
*.apache.org traffic, configur
11/13/00, 6:31:13 PM, Nick Bauman <[EMAIL PROTECTED]> wrote regarding
Re: Thanks for the make links and a rant:
> On Mon, 13 Nov 2000, Roy Wilson wrote:
> > Nick,
> >
> > I agree that your example is simple. Even I can understand and create
> > such "toy"
e package version
> VERSION=3_2
> # where the maketools be
> MAKE_CONF=./maketools
> include $(MAKE_CONF)/config.mk
> include $(MAKE_CONF)/rules.mk
> -8<------
> Can it be any simpler?
> Now I know that there is a lot of magic in the MAKE_CONF, but then you
> don'
Nick,
I have a copy of the FSF make manual: As our president used to say "I
recur to my former statement [about make documentation]." :-) I'll have
to check out the O'Reilly reference. See my rant below.
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
>>>>
ical papers, I'd like to think
the problem is more than brain-death on my part. :-)
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
-
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
Jon Stevens,
You mentioned that you thought *.apache.org gets 2M hits per day. Is
there a (good?) source of info re: hardware/software/traffic information?
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
-
To unsubscribe, e
>>>>>>>>>>>>>>>>>> Original Message <<<<<<<<<<<<<<<<<<
On 11/11/00, 5:26:54 PM, Roy Wilson <[EMAIL PROTECTED]> wrote
regarding Assessing the performance impact of the propos
.
I enjoyed this. I hope you did too. It might even be useful in the
future.
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
>>>>>>>>>>>>>>>>>> Original Message <<<<<<<<<<<<<<<<<<
On 11/11/00
nd
> watchdog. ( few enhancements are needed ). Then you can do your
> "scripts" in xml.
I'll take a look at Gtest. I just started fiddling with ANT today. Like
an idiot I took a full-blown build.xml used to generate a production
system and wondered why I couldn't inst
0 128 128+316 324010.25
> >
> > So, what is a "good" max/avg ratio? And, for what machine? I'd be
> > surprised if someone saw these ratios on a Pentium 650Mhz.
> >
> > BTW, it is possible to calculate (after making
public class UpperBound extends HttpServlet {
static final String msg = "\n" +
"UpperBound\n" +
"\n" +
"UpperBound\n" +
"\n";
static final byte[] bytes = msg.getBytes();
public void service(ServletRequest req
Hi,
I couldn't locate the Ping Servlet, but did get one very close to it
called the UpperBound Servlet, which is attached. I haven't tried it.
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
Title: UpperBound
public class UpperBound extends HttpServlet {
static final
for each request, z ms for an internal dispatch, etc.
> ( of course, on average )
>From a developer perspective, I agree with the above. I don't see the
user and developer perspectives as entirely incompatible.
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
-
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
han some
value (like 10 - Z seconds, where Z represents some level of network
delay).
Roy
Roy Wilson
E-mail: [EMAIL PROTECTED]
-
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
Hi,
In addition to some of the other concerns voiced, there is the somewhat
more personal matter of color. I like yellow, but the page is TOO
yellow/butter/whatever for me. OTOH, the images are fairly crisp.
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
>>>>>>>>>
filename="text1.rtf" filename="text1.rtf"
filename="text1.rtf" filename="text1.rtf"
filename="text1.rtf"
filename="text1.rtf" filename="text1.rtf"
ch type of request, what the server response time
is likely to be, and what the CPU and disk utilizations are like (since
they might want to put TC on a system with some room for growth).
So, I propose a workload model based on servlets we already have (or
could develop for). Starements about TC pe
ts an upper bound on the avg
thruput, and a lower bound bound on the average response time, of any
more resource-intensive request on the machine where the resource
measurements were taken.
Bell Labs uses this kind of bounding approach to performance
assessment, especially in the design phase.
Ro
mance people get out of the box. If AccessLogValve
is and continues to be a hog, then maybe it shouldn't be a default?
BTW, what did you use to do the profiling? What did you see? I'm planning
to use OptimizeIt4.0 when I can get it and get it to attach.
Roy
--
Roy Wilson
E-mail: [
Ignacio/Nacho,
I am under the weather and, even if I wasn't, I'm too pressed for time
:(. The shell scripts are pretty simple, though, so I imagine other
volunteers could do the run(s). As I recall, Costin did something similar
in his recent ApacheCon Europe presentation.
Roy
Ro
filename="text1.rtf"
# Draft script by Roy Wilson used on Redhat6.1 system (bash)
# Assume ONLY HelloWorld servlet being used: better to have a set, but what?
#
# To promote comparability, run script immediately after a cold boot
echo Run script only after a cold boot to make results
ION 3: Since the scripts can be modified to run any servlet, how
about a "realistic" one as Costin suggested in his ApacheCon
presentation (unless the examples are "representative").
(Hack) Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
# Draft script by Roy Wilson used on R
I wonder if such testimonials would be worth collecting (or at least
links to the relevant web pages) on a special page so that CTOs, VCs,
etc., can
find them?
Roy
Roy Wilson
E-mail: [EMAIL PROTECTED]
> > Dear Friends,
> > We have successfully managed to host a website www.gtsuae
ess" ought to include
graceful degradation when configuration settings are less than optimal
for the OS, VM, etc. being used. I realize this is a rather simplistic
conception,but ...
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
--
eople will see similar logfile entries with
different N and C values. I'll send an updated, more flexible, version of
the bash scripts today or tomorrow as I'm feelin' poorly. :-)
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
--
testing begins ...
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
-
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
mind over time.]
Those who want to capitalize on OSS as users, might find paragraph 3
especially important, since it indicates the significance of the names
for use as well as for development activity.
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
> Let's try to explain this a little bit:
h the
summary file in ascii format to a post that describes your system
configuration (CPU, disk, memory, OS, etc.) I will process that files
post the results every TBD days.
Sorry about the length. If I knew how to make it shorter, I would. :-)
Roy
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
>>
Craig,
I have a bash shell script that (currently) drives Apache, sar, and sa on
a RedHat6.1 system. I will doctor it a bit and post it tonight to see if
there are suggestions about what to include, modify, leave out, so that
it will span most Unix/Linux systems.
Roy
--
Roy Wilson
E-mail
, not just the HelloWorld
servlet (again in keeping with Costin's pitch at ApacheCon).
Roy Wilson
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
-
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
ak can't be broadcast until there is
technical data to support it in some fashion. Otherwise, perhaps, some
CEO/CTO/etc., asks a question that ultimately gets answered by a
technically savvy person such as yourself who (in the absence of
technical performance docs) might then be forced to
on
Europe?) and see numbers. In particular, how was the load generated?
ApacheBench?
Roy Wilson
E-mail: [EMAIL PROTECTED]
-
To unsubscribe, e-mail: [EMAIL PROTECTED]
For additional commands, e-mail: [EMAIL PROTECTED]
re's any interest, I can post a link to a PowerPoint presentation
that summarizes what I've done so far (and let the barbecue begin :-)).
--
Roy Wilson
E-mail: [EMAIL PROTECTED]
>>>>>>>>>>>>>>>>>> Original Message <<&
50 matches
Mail list logo
