|
>Well what do benchmarks show? In Java, how long does it take a 270 to loop >a million times, to create, fill and then destroy a large number of string >performance numbers compare to a pc running the same java code? .And if the performance is inferior, maybe Buell Duncan can join this list, >hear about the performance problems and get them solved. ( as TJ Watson >would have done already. He and Tom Watson Jr believed foremost in listening >and responding to the customer. ) >Steve Richter ----- Forwarded by John P Carr/FilmRich/Tredegar on 11/16/2002 02:06 PM ----- There are several public web sites you might want to look at to "get the facts". Ideas International is at: http://www.ideasinternational.com ... They posts multiple public benchmark results for lots of different BM Consortiums. IdeasInternational posts there findings in various "Top-10" results for each of the BMs they track. And from there you can get to the orginal SPEC consortium web site which has the detail BM submission reports by each of the vendors. Our SPECWeb99SSL submission is posted on their site at: http://www.spec.org/osg/web99ssl/results/res2002q3/web99ssl-20020819-00025.html I would also encourge the writer to consider the "Powered by Apache" vs Zeus web server discussion. Whereas HP has recently exceed our result .... they continue to use a "benchmarketing special" web server, i.e. Zeus. And when one reviews the Netcraft Survey on: http://www.netcraft.com/survey he would see that Apache Server is used 64% of the time in production web sites, and Zeus is <2%. There are many reason why Apache is preferred. Bottom line is that the iSeries Benchmark measurement team uses what we SELL/INSTALL to do our benchmarks. We do not use benchmark specials and then install some other tool or web server....just to try to get good BM results. Active Sites * Sept'02 * Percent * Oct'02 * Percent * Change Apache *10449418 *64.85 *10470848 *65.39 *0.54 Microsoft *4071863 *25.27 *4013397 *25.06 *-0.21 iPlanet *237802 *1.48 *227424 *1.42 *-0.06 Zeus *220729 *1.37 *215957 *1.35 *-0.02 I would also encourage the reader to remember that not all applications scale well on some platforms and that not all applications lend themselves to be parsed out across multiple systems (multiple 4 ways) to beat a 16 way SMP. It is well recognized in the tech trade press and consulting community that multiple systems are significantly more expensive to own/operate (Total Cost of Ownership) than a single system offers. For refer, I would suggest IDC, Gartner and Giga Group consulting reports. Richard Odell - iSeries Performance Marketing Dept HP4, Rochester Lab http://ca-web.rchland.ibm.com/perform/perfmenu.htm rjodell@us.ibm.com 8-553-6526, (507) 253-6526 ______________________________________________ This message is intended only for the person or entity to which it is addressed and may contain confidential material. If you are not the intended recipient, any use, distribution or other action taken in reliance on this message is prohibited. If you received this message in error, please contact the sender and delete the material from any computer. _______________________________________________ This is the Midrange Systems Technical Discussion (MIDRANGE-L) mailing list To post a message email: MIDRANGE-L@midrange.com To subscribe, unsubscribe, or change list options, visit: http://lists.midrange.com/cgi-bin/listinfo/midrange-l or email: MIDRANGE-L-request@midrange.com Before posting, please take a moment to review the archives at http://archive.midrange.com/midrange-l. ______________________________________________ This message is intended only for the person or entity to which it is addressed and may contain confidential material. If you are not the intended recipient, any use, distribution or other action taken in reliance on this message is prohibited. If you received this message in error, please contact the sender and delete the material from any computer.
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
