|
Andrew, I just ran the test. Now in fairness I'm on the far side of a 384K DSL and I don't know what your connection speed is, but these are the results: In all these tests I retrieved the HTML from www.as400net.com but I didn't get the CSS or the images. We're not testing pipe sizes, but rather logic speed. In all cases the test was: Get www.as400nut.com Sleep(500) '500 milliseconds Repeat 1 User over 1 minute: 49 Requests made Avg time to first byte: 644.53 ms Avg time to last byte: 649.63 ms 2 Users over 1 minute: 67 Requests made Avg time to first: 1,154.64 ms Avg time to last: 1,154.79 ms 3 Users over 1 minute: 102 Requests made Avg time to first: 1,054.46 Avg time to last: 1,056.79 10 Users over 1 minute: 132 requests made Avg time to first: 3,098.83 Avg time to last: 3,141.24 The conclusion I come to based on these results is that your site doesn't scale well. HOWEVER, I can't say if that lack of scaling is in the web server, the Net.Data macro or simply saturation of the IP connection between us. -Walden ------------ Walden H Leverich III President Tech Software (516) 627-3800 x11 (208) 692-3308 eFax WaldenL@TechSoftInc.com http://www.TechSoftInc.com Quiquid latine dictum sit altum viditur. (Whatever is said in Latin seems profound.) -----Original Message----- From: Andrew Borts [mailto:Andrewb@SETACORPORATION.com] Sent: Friday, August 02, 2002 16:22 To: web400@midrange.com Subject: RE: [WEB400] What happened to rpgenerationx.com? OK - do dat (this stress thingy) with www.as400nut.com It's running a Net.Data macro for the counter below... Andrew Borts / Webmaster Seta Corporation 6400 East Rogers Circle Boca Raton, FL 33499 E-mail: Andrewb@setacorporation.com Corporate web site http://www.setacorporation.com E-Commerce web site http://www.palmbeachjewelry.com http://www.myfreeitems.com Voice: 561-994-2660 Ext. 2211 / Fax: 561-997-0774 -----Original Message----- From: Walden H. Leverich [mailto:WaldenL@TechSoftInc.com] Sent: Friday, August 02, 2002 3:38 PM To: 'web400@midrange.com' Subject: RE: [WEB400] What happened to rpgenerationx.com? >From: Nathan M. Andelin [mailto:nandelin@RELATIONAL-DATA.COM] >By adding another 72 records to your copy... OK, actually I had removed the additional rows to make life simpler, but I put them back (78 in all now) and reran the tests. I had to lower the number of simultaneous connections to 20 because of W2K workstation problems, I'm trying to find a server I can play with. New numbers, same test (except for 20 users instead of 50) Requests processed: 8,339 (only 20 users now) Avg rqs/sec: 13.89 Avg time to last byte: 436.8ms Total bytes sent: 158M Page size: 158M/8339 = 19K >Another factor to consider is the CPU speed of your model... Not really. In the last test the database jobs were <0.1% used. This time they were <0.5%. I'll lay money I'm IO bound, not CPU bound, as should any good iSeries be. >What is the processor feature on your server? 2248 w/1517 interactive (not that interactive should matter). -Walden ------------ Walden H Leverich III President Tech Software (516) 627-3800 x11 (208) 692-3308 eFax WaldenL@TechSoftInc.com http://www.TechSoftInc.com Quiquid latine dictum sit altum viditur. (Whatever is said in Latin seems profound.) -----Original Message----- From: Nathan M. Andelin [mailto:nandelin@RELATIONAL-DATA.COM] Sent: Thursday, August 01, 2002 19:38 To: web400@midrange.com Subject: Re: [WEB400] What happened to rpgenerationx.com? Walden, Nice numbers on your stress test! It would be quite interesting to stress test the Relational-Web boat report on your model 270, and compare it to your ASP equivalent. Just let me know if you'd like a copy to test. I agree that testing a full application would be much more relevant than testing a single program or script. That would be a scenario in which Relational-Web would really shine, exceptionally. My program generated 24K of HTML while your ASP script generated 2K of HTML. By adding another 72 records to your copy of the BOAT table, the HTML streams would be comparable. Another factor to consider is the CPU speed of your model 270 vs. my 170. What is the processor feature on your server? We ran a CPU bound RPG benchmark on a model 270-2250 and found it to be 17.5 times faster than my model 170, for example. Nathan M. Andelin www.relational-data.com ----- Original Message ----- From: "Walden H. Leverich" <WaldenL@TechSoftInc.com> To: <web400@midrange.com> Sent: Thursday, August 01, 2002 8:56 AM Subject: RE: [WEB400] What happened to rpgenerationx.com? > >From: Nathan M. Andelin [mailto:nandelin@RELATIONAL-DATA.COM] > >measures the time between the request and the first byte received in > >order to strip network time from the equation. > > Now, if I write a page that sends back the <HTML> line, then goes off > and does all its work then returns the rest of the page JMeter will > say it performs well. You can't rely on such a test. > > Also, I don't believe you can validly test one page over and over. A > more realistic test would be to walk the application as a user would, > script that > entire "session" and then replay that. > > In another e-mail: > >From: Nathan M. Andelin [mailto:nandelin@RELATIONAL-DATA.COM] > >it would be interesting to compare with MS ASP. Could you share some > >of the scalability aspects of ASP? > > Sure, it scales GRRRRRRReat! <G> Seriously though, what do you want to know? > There are several (many) pieces of ASP and IIS from the static page serving > to VBScript to ADO to MTS to ... > > As a start I ran a test on an ASP version of your boats example. > (http://w3.techsoftwareinc.com/boats.asp) This is a simple ASP script > that retrieves the boats from a table on my iSeries and displays the > results. The > tests were run from MS's Application Center Test program from VS.NET > (however the tests are of "classic" asp, not asp.net). > > iSeries: 270 w/512 meg & 4x6717 drives in raid 5. > iSeries OS: V5R1 CUME 02036 (hmmm, maybe I should update <G>) Web > server: Dell Inspiron 8100 (my laptop) 1.2Ghz Pentium III 512 Meg > OS: Windows 2000 Workstation SP2 > > Test: > Retrieve page boats.asp and wait 1000 milliseconds Simultaneous > connections: 50 Test run time: 10 minutes > Ramp up time: 1 minute (not included in the 10 minutes) > NB: Test client running on same machine as web server so 0 network > latency > > Results: > Test iterations in 10 minutes: 28,521 > Avg rqs/second: 47.53 > Avg time to 1st byte: 50.34 ms > Avg time to last byte: 50.45 ms > Avg bytes/sec: 121K > Total bytes sent: 10M > Total bytes received: 62M > iSeries impact: several QZDASOINIT jobs, each showing <0.2% CPU at all > times. > > Response code 500: 269 (0.94%) > Response code 403: 204 (0.72%) > Response code 200: 28,047 (98.34%) > > Notes: > The 403 errors are generated when the server understands the request > but refuses to process it. This is simply due to the fact that I ran > the test on > my PC running W2K Workstation not server which has a limit to the > number of > IIS connections it's allowed to accept. > > The 500 errors are generated when there is an error in the ASP. In > each of these cases the error was the result of exceeding the maximum > number of connections allowed by my license of the OLEDB driver (not > IBM's). > > -Walden > > ------------ > Walden H Leverich III > President > Tech Software > (516) 627-3800 x11 > (208) 692-3308 eFax > WaldenL@TechSoftInc.com > http://www.TechSoftInc.com > > Quiquid latine dictum sit altum viditur. > (Whatever is said in Latin seems profound.) _______________________________________________ This is the Web Enabling the AS400 / iSeries (WEB400) mailing list To post a message email: WEB400@midrange.com To subscribe, unsubscribe, or change list options, visit: http://lists.midrange.com/cgi-bin/listinfo/web400 or email: WEB400-request@midrange.com Before posting, please take a moment to review the archives at http://archive.midrange.com/web400. _______________________________________________ This is the Web Enabling the AS400 / iSeries (WEB400) mailing list To post a message email: WEB400@midrange.com To subscribe, unsubscribe, or change list options, visit: http://lists.midrange.com/cgi-bin/listinfo/web400 or email: WEB400-request@midrange.com Before posting, please take a moment to review the archives at http://archive.midrange.com/web400. _______________________________________________ This is the Web Enabling the AS400 / iSeries (WEB400) mailing list To post a message email: WEB400@midrange.com To subscribe, unsubscribe, or change list options, visit: http://lists.midrange.com/cgi-bin/listinfo/web400 or email: WEB400-request@midrange.com Before posting, please take a moment to review the archives at http://archive.midrange.com/web400.
As an Amazon Associate we earn from qualifying purchases.
This mailing list archive is Copyright 1997-2024 by midrange.com and David Gibbs as a compilation work. Use of the archive is restricted to research of a business or technical nature. Any other uses are prohibited. Full details are available on our policy page. If you have questions about this, please contact [javascript protected email address].
Operating expenses for this site are earned using the Amazon Associate program and Google Adsense.
midrange.com
