Performance Benchmarks for WL

Does anyone know what the definition of a "Transaction" is in the performance benchmarks published by Bea?
How many session bean calls, entity beans calls, etc.
THanks

If you want to stick with Sun jdk, and don't want to see the error
messages, set weblogic.system.nativeIO.enable=false in
weblogic.properties. I wouldn't go to NT, because if you can afford it
Solaris on SPARC will be your fastest most reliable platform. We have
Solaris SPARC for production, and do our development on Lintel. For us
staying in a POSIX environment overall keeps things like startup,
environment setting, and make type scripts all on the same page.
Ian
Alexander Sommer wrote:
>
I'm currently evaluating WL 5.1 and installed it on linux.
I have installed the SUN JDK 1.2.2 for linux which should use
native threads.
When I start WL 5.1 I get the following message:
LD_LIBRARY_PATH=/usr/local/weblogic/weblogic/lib/linux:/usr/local/weblog
ic/weblogic/lib/linux
Warning: native threads are not supported in this release
What does this mean?
Also I get the following messages:
Fri Apr 07 08:59:38 CEST 2000:<A> <Posix Performance Pack> Could not
initialize POSIX Performance Pack.
Fri Apr 07 08:59:38 CEST 2000:<E> <Performance Pack> Unable to load
performance pack, using Java I/O.
How much does this impact the performance? Is it better to use NT instead
of linux?
thanks,
Alex--
Ian R. Brandt
Software Engineer
Genomics Collaborative, Inc.
99 Erie Street
Cambridge, MA 02139
(617)661-2400 Ext.244
(617)661-8899 FAX
[email protected]

Similar Messages

(268625273) Q WSI-29 Can you give any performance benchmarks for WLS web services?

Q<WSI-29> Can you give any performance benchmarks for WLS web services?
A<WSI-29>: It is very difficult to quantify performance aspects of web services
since they depend on so many variables including but not limited to: backend system
processing by stateless session beans and message driven beans, size of XML SOAP
message sent, system hardware (CPU speed, parallel processing, RAM speed) and
system software (JVM type and version of WebLogic server). However, let me point
out that the EJB backend processing of requests both have the best possible scalability
within the EJB2.0 specification (both stateless session and message driven beans
can be pooled) and servlets have a proven scalable track record. Thus it should
be possible to scale your web service deployment to meet demand. The overhead
in processing XML within the servlet can be significant depending on the size
of XML data (either as a parameter or a return type). While WLS6.1 does not have
any features to address this performance concern, WLS7.0 will feature Serializer
and Deserializer classes which can be dedicated to the XML to Java and Java to
XML translation (they can also be automatically be generated from a DTD, XML Schema
or regular JavaBean).
It is true that web services are not the fastest way to process client requests
but BEA is committed to making WebLogic server the fastest possible service provider.
Adam

see http://www.oracle.com/support/products/oas/sparc30/html/ows08811.html

Cost and performance benchmarks for security

Looking for cost and performance benchmarks on the
Cryptograhic toolkit - 8i supplied package,
Oracle Label Security (OLS)
Virtual Private Database (VPD)
Please send any suggestions to my email address - thanks

Looking for cost and performance benchmarks on the
Cryptograhic toolkit - 8i supplied package,
Oracle Label Security (OLS)
Virtual Private Database (VPD)
Please send any suggestions to my email address - thanks

Performance, Benchmark for Oracle XE

My buisness would like to use Oracle XE as a starter base installation for customers, so that they can easly upgrade to an full Oracle SE or EE later. However I fail to find benchmark tests (like tpc.org) which give an image of the performance of the Oracle XE and how it compares to other databases such as PostgreSQL or MySQL in the smaller application market segment that XE is targeting.
We have been running som tests in house, but the currently I must say they are not in the Oracle XE favour. This is disapointing, as we would want to avoid for our customers to start of with a DB other than Oracle, then do an transistion to Oracle SE or EE when the need is there.
We are working on tuning/optimizing the database to perform better. Nevertheless it would be really interesting to see some benchmarks / comparison of the performance between Oracle XE an other DBMS in this segment of the DB market. Beeing well aware that their is not necessarely one database that fits each application/segment best, such a test would be informative. And also great input for my company when choosing which DB to use. Does anyone have any experience on this subject any feedback is highly appreciated. If anyone is interested I would be glad to post details regarding our tesing in house.
Cheers

Hi,
Thanks for the reply. Being well aware of the complexity of optimizing application performance I am simply trying to find as many inputs as possible to make a decision. A benchmark test would for me not yield "the truth" in any way, but simply be another parameter to consider. I am also aware that Oracle DB has several features that other DBs don't have.
You hit the nail on you assumption:
2) use only the very basic features of both DBsThis is correct. We are using a EJB3.0 (Hibernate) environment togheter with JBOSS 4.0.5 application server, using no specific DB implementation. I realize that at some point, to acheive max performance, one should would have to implement code optimized for a specific DB. But right now I am interested in maximizing the performance with no specific DB code. We started out using Oracle XE, and it was doing well. We than switched to Mysql mainly for curiousity, and the performance was much better "out-of-the-box". ( x 2,5!) using less CPU -20%) an memory than Oracle XE. This was a suprising result for me, and now I would like to know why.
If the reason is that Oracle uses more resource for background processes like gathering statistics etc. this is a feasable explanation. Also in a larger system, if these processes take more or less the same resources, they would make out a smaller part of the total available resources. Right now I can't explain the performance gap, I simply observe the test results but cannot explain them.
As my demands to the DB features are limited (basic ER datatypes, incremental backup), is there perhaps a way to "disable advanced features" of Oracle XE, so that more CPU power is available to the application?
Also, how well does the JBOSS app. server integrate with the Oracle DB? Would the Oracle XE perform better with an Oracle App.server?
My application has a typical web-app, having mainly read queries with a high peak load (burst). I have tried tuning the connection pool etc. but no improvment. It is quite possible that I have reached the limit of performance of the Oracle XE, perhaps I am trying to use it for something it was not intended for? Having said this I would prefer to continue using Oracle XE, but it would be nice to know the reasons for the difference in performance.
Any feedback is highly appreciated.

Performance Benchmarking for XMLDB

Can anybody share any benchmarking figures on XML DB with respect to performance.
regards,
rizzy

Oracle policy does not allow us to publish benchmarking numbers unless that are for an industry recognized independantly audited benchmarks such as TPC/C. Unfortunately there no industry standard benchmarks relating to XML data at this time. I can share with you that we believe for some classes of documents 9.2.0.3.0 will be much faster the 9.2.0.2.0. so if you are doing any performance evaluations of your own please make sure you have installed the 9.2.0.3.0 patch.

IOMeter or NAS Perf Tester (network performance benchmarks) for Mac?

When I was on a PC-only home network, there were many network monitoring/testing tools like IOMeter And Intel NAS Perf tester. But I've been unable to find a network testing tool for the Mac. I'm interested in testing file creation/read/write speeds to/from my NAS.
Does anyone know of something for the Mac?
Also, I'm not afraid of using terminal, so if there's any built-in UNIX tools, or ones that are open source and can be compiled on OS X 10.6, I'm ok with that too.
Thanks.

I found something called HELIOS Lan Test. It seems to do the kinds of create/read/write testing I can use to benchmark my ReadyNAS NV+ file share protocols (CIFS, AFP, NETBIOS) to see which one is faster in my setup.
I already have iStat Menus, and I can monitor performance with it in a rough sense (ie. watch the display when I'm copying a large file), but the HELIOS Lan Test is a much better repeaatble test for ongoing analysis.

Are there any performance benchmark tools for Flash?

I am looking to benchmark Flash on various computers that I use. I was surprised that the performance of Adobe Flash on my Intel i5 computer running Windows 7 Pro 64-bit OS and IE 10 was MUCH WORSE than running on a Windows 7 Pro 32-bit on an Intel i3 computer running the same browser.
I have tried running both 32-bit IE and 64-bit IE and get the same general bad performance on the 64-bit Windows OS. I would like to find a tool to benchmark these various computers so that I can establish baseline performance while I explore finding a fix Adobe Flash on a 64-bit OS.
Can someone suggest some tools for Flash performance benchmarking? Thank you.

The best advise we can really give you is that both companies offer free trials and you should download them both and see which works best for you. I own Parallels Desktop v6, and VMWare Fusion v3. For me, VMWare s better for some things, but Parallels is better for most. Depending on what you do and how you use your applications your milage may vary.
One other note to keep in mind. Since Apple is looking to release a new OS version in the very near future, you might want to hold-off a bit on our vitualization choice just yet. I would exect that both companies will be working on a new release for support/compatibilty of the new MacOS, so you might want to wait to see if there are any other changes that make you want to lean towards one or the other...

Performance benchmarks Win XP

Does anyone know if there are any performance benchmarks available for Windows XP (via Boot Camp) running on various different Mac Pro, MacBook Pro, and iMac machines?
I assume the more RAM, the greater BUS speed, the faster and more numerous the processors the better performance but I was looking for objective numbers to help me decide what system to buy.. I know that one of the PC site rated Windows on a Mac laptop very fast.

Well, I don't know that anyone has run such benchmarks, but it's logical to assume that the faster the machine the faster XP will run on a Boot Camp installation since Windows is running natively on the hardware as though it were a normal PC. What's important to you - speed or mobility? If speed then get a Mac Pro. If mobility then get a MacBook Pro.

Third party benchmarks for WLS

Does anyone have a reference for third party benchmarks for
WLS 5.1 or 6.0 vs other J2EE app servers?
Also performance of built-in WLS web server vs Apache or NES?
Thanks,
Eric Chiu

ed2345 wrote:
Easily done. See iTunes: How to set the play order of songs on an MP3 CD. Basically, if you sort the playlist by album, iTunes will burn the MP3 CD with album folders.
Thanks, that solves the second problem, which was the more pressing anyway.
Do you maybe also have an idea how to get rid of the number in front of the album title in the directory name?
Cheers, Robert

PPBM7 Benchmark for Premiere CC

It has been a long time coming but Harm (even though he is not active on the forums) and I finally have a Benchmark for Premiere CC (actually properly today's version is Premiere 7.2.1.4). Harm is the webmaster for us on ppbm7.com. Without his continuing support I would not be able proceed with a CC version and we would not have his wonderful Tweakers Page.
We have used the exact same timeline that we have used for CS6. All exports are direct exports from Premiere hence the DE to distinguish from the preceding generation where we used AME. This eliminates dynamic linking overhead and give truer Premiere benchmarks.
Since the GUI has changed in CC we need to have a new project that reflects those changes. So in the current version of CC our benchmark works fine, but as CC evolves we cannot necessarily guarantee compatibility. One thing we added was a additional script item that retrieves the current Premiere version number so we can understand future changes.
This new benchmark (called PPBM6 or 7-DE.zip) is dual purpose in that it has a project file for both versions so after downloading and unzipping the file you have to chose which project file you need and also there are two Statistics files one for each version.
As with the second version of of PPBM6 it is self instructing in that the first frames of each timeline tell you the instructions for proper setup. Before you run the benchmark you download Speccy and run the program and save a snapshot for later submission. You start the project with the Disk I/O timeline and export it, the instrutions then tell you to activate the MPEG2-DVD timeline and perform two exports on it and finally you activate the 7-layer H.264 timeline for the last of the four tests. Next you go to the project file and run the appropriate Statistics script. Then you go to Submisson and send the two files to us. When you close the project file do not save it so that if you want to run it again it will open exactly as the original file.
Unfortunately there are still a few references to PPBM6 which you have to read as PPBM6 or 7.
Here are two conclusions I have drawn after 15 CS6 runs on two different computer and 17 Premiere 7 runs
1. Premiere 7 is appreciably faster than Premiere 6 on the CPU intensive with PPBM MPEG2-DVD exporting without GPU assistance.
2. Premiere 7 is slightly faster than Premiere 6 with a single GPU on GPU assisted with PPBM MPEG2-DVD timeline exporting

Thanks for the compliments. It is a continuing labor of love!
Jim on my unpublished data that I used for my conclusions, I actually have a 3, 4 and 5
3. Premiere 7 is able to use multiple GPU's to be somewhat faster than Premiere 6 on MPE accelerated effects and features.
4. Using two GPU's in a 20-lane CPU system is feasible but it does not achieve as good results as a 40-lane system because it slows the PCIe x16 slot speed to x8
5. A simple boost in the GPU memory speed can provide a noticeable increase in performance with the GPU assisted MPEG2-DVD test (faster encoding).
Jim, if you go into Premiere in the Help and About Premiere it does show you Premiere, Version 7.2.1.4 (today at least) and this is the info we extract when you run the script. So if they make a major change that requires changes on our end we can detect why or changes in performance that we can alert the users.
Thanks again

Aperture 3: A quick benchmark for buying decision

I'm in the unlucky situation, that my workhorse machine for Aperture is still a well equipment PowerMac Quad G5. I can't use Aperture 3 on this machine as Aperture 3 is Intel only.
I've read several posts on boards discussing Aperture 3, that Apple did right in abandoning PPC code, because the G5 would simply no be powerful enough to run Aperture 3 efficiently.
So I did a small test. Installed the Aperture 3 trial on my MacBook Pro, which is officially supported by Aperture 3 and exported 34 heavy edited RAW pictures to 50% downscaled JPEGs.
Here is the result:
Quad G5 / Aperture 2: 2:14 Min
MacBook Pro 2.4 GHz early 2008 / Aperture 3: 3:14 Min
So what is the conclusion?
1.) A Quad G5 would have been more than powerful enough to run Aperture 3, if Apple had made it an universal app. Sadly they decided against and I have to live with this decision.
2.) Using the MacBook Pro with Aperture 3 is no option for me and not only due to limited display size and hard disc size/speed. According to this benchmark, it would be a serious performance downgrade in compare with the G5 Quad/Aperture 2 combo I use now.
3.) A 2,66 GHz Quad-Core Mac Pro (the cheapest Quad G5 successor) would run Aperture 3 and would cut the time for my benchmark probably by halve (given 4 cores vs. 2 on the MBP). That would mean probably 1:40 Min to complete the test. Yeah, faster than 2:14 Min. but frankly not that much.
If I spend a lot of money to replace my Quad G5 with an Aperture 3 compatible desktop Mac, I expect it to be noticeable faster than my current machine - or I stick with the G5 and Aperture 2 for another year.
So my question:
Is there someone with a fast Mac Pro and/or an i5 or i7 iMac and has still access to an Quad G5 or a 2.4 GHz MacBook Pro, who could make a similar benchmark test to compare with?
Peter

It shouldn't be a surprise that, years after switching to Intel, that Apple now develops software for Intel machines. It doesn't develop software for my old Apple //e with a 6502 chip, either. I've moved on and so has Apple.
William, no offense against your reply, but people often speak, as if the PPC in the Mac platform had been superseded by Intel CPUs almost a decade ago, and so it has to be expected now, that this architecture isn't supported any more.
The truth is:
- It wasn't before August 2006, that the crown for the "fastest Mac ever" went from the Quad G5 to the Mac Pro.
- And it wasn't before March 2007 with the release of Adobe CS3, that the Quad G5 lost the crown as the fastest machine for running Photoshop, InDesign etc.
So until March 2007 the Quad G5 was the best performing machine for creative professionals.
In August 2009 Apple dropped PPC support with the release of Snow Leopard and as we know now for all future Pro apps as well. No surprise, other major software vendors like Adobe quickly follow Apple's route and abandon PPC support too, as we see in the Lightroom 3 beta and the next version of CS.
So it is just about 2 years for the Quad G5 to move from the best performing machine for creative professionals to a machine being totally unusable to run current software for creative professionals.
While I fully understand, that Apple doesn't want to waste resources with coding for a plattform, they don't sell any more, the often praised longevity of Mac system in compare to windows system is really a joke in this special case. My 6 years old windows box is better supported by current software than my now 5 years old Quad G5.
Ok, let's stop here with the discussion (whining ) about the drop of PPC support. Apple's decision is made and it is final, so it is time to move forward.
My lesson from this story: I'll never buy legacy hardware from Apple again. They are just "too innovative" to make a good use of legacy hardware over its usual lifetime.
Peter

Performance benchmarks?

Hello,
Has anyone done any performance benchmarking on Portal Server? (Or know
where I can find such information?)
I'm curious to know:
1. Given iPlanet's recommended hardware, how many concurrent users does
this support with decent performance (SSL to gateway to non-SSL server)?
2. How does the product scale...e.g. if I wanted to have 250 concurrent
gateway users (running SSL), what hardware is recommended? 500 users?
1000 users?
3. Has anyone tried (or does the product even support) the use of SSL
accelerator cards on the gateway machine?
Any help is appreciated.
Thanks,
Murray

Hi.
We did some benchmarking in january, at the SUN iforce center in holland,
using iPlanet Portal Server SP2 Hotpatch3.
We focused on measuring:
1) Average time to log in to portal(with default channels, netlet set up) as
a function of simultaneous users
2) Average time to do a "standard operation" inside portal.
Our results supported the numbers from iPlanet saying thath one could have
250 simultaneous "secure" users pr CPU in this setup. (SP2 HP3)
This "guaranteed" number of simultaneous users pr CPU for iPS 3 SP3 is said
to be increased to 1500.
We used SUN E 220 s with 2x450 MHZ CPUs and 1 G RAM.
The performance increased remarkable when we went from gateway and server on
1 machine, to separate gateway and server.
Tore
"Murray Bodor" <[email protected]> wrote in message
news:[email protected]..
Hello,
Has anyone done any performance benchmarking on Portal Server? (Or know
where I can find such information?)
I'm curious to know:
1. Given iPlanet's recommended hardware, how many concurrent users does
this support with decent performance (SSL to gateway to non-SSL server)?
2. How does the product scale...e.g. if I wanted to have 250 concurrent
gateway users (running SSL), what hardware is recommended? 500 users?
1000 users?
3. Has anyone tried (or does the product even support) the use of SSL
accelerator cards on the gateway machine?
Any help is appreciated.
Thanks,
Murray

Performance benchmarks within BPC

Has anyone ever performed any benchmarks with BPC?
I know there is such a wide spectrum of elements that go into benchmarking a BPC solution that most benchmarks can not easily be correlated to each other. (i.e., Platform, environment, dimensionality, hierarchies u2026) Any estimates would be a great benefit.
Iu2019m hoping someone has performed some serious performance benchmarks such as;
u2022 Data throughput, (time to submit data such as 1000 cells per minute).
u2022 Query time, (x row by x column expansion and query).
Thanks in advance for your input and assistance!
Fletch

Hi David,
I agree with you about your point on performance benchmarks. However I don't know if you are already aware of the performance tuining guide available at:
https://www.sdn.sap.com/irj/sdn/go/portal/prtroot/docs/library/uuid/9016a6b9-3309-2b10-2d91-8233450139c1
Also you may want to have a look at OSS note 1124332.
Regards
Pravin

Performance benckmarks for Portal/Discoverer

This is kind-of the right forum...
I'm embarking on a project to implement a warehouse/portal system that will be implemented with portal and utilising components such as the Discoverer tool.
As a warehouse the project is perhaps a little atypical in that it will have a medium sized warehouse (probably measured in 10s-100s of GB for years 1-2) but a relatively large user community (overall in the 1000s, probable average 10-50, peak (at specific times of year in the 1000s).
I've looked through "3.0.9.8.2 Architecture & Scalability" but I was wondering if anyone could give some benchmark performance indicators for similar profile sites.
John Skelton

John,
I tried sending you a response to this direct, but your email was bounced ([email protected])
what I said was
"Metrics for Portal are very hard for us to define, .
We are working on the case-study type of document you are asking for, currently we only have one for my.oracle.com (attached, hence why I am mailing you directly) - which currently has 250,000 registered users."
You will need to download the whitepaper from the documentation area of portalcenter.oracle.com
Look for "Architecting my.oracle.com"
Thx
Jason Pepper

I need some performance advice for video editing

or
I am deciding on which Mac Book Pro to purchase for video editing. My choices are:
2012 - 2.3 Ghz Quad-Core i7 w/ 500GB Serial ATA@5400 rpm 8G RAM
or
2013 - 2.0 Ghz Quad-Core i7 w/ 256 Flash Storage 8G RAM
The one is a year newer but .3 Ghz slower processor and I'm really not sure if it would matter that much for video editing. (FCPX, After Effects, etc.) I know the Flash Storage would be faster as far as opening applications etc., but for video editing, I didn't know.
Can someone more qualified than me recommend which would be best. I need a laptop for video editing, but I need the least expensive I can get so I am looking at refurbs from Apple.
Thank you!

If you look at the 2013 Retina models in the Apple store, you'll see the higher end version has both the Intel Iris and an additional Nvidia graphics module. The higher end models have this additional circuit, which is to provide faster and smoother graphics for video, games, etc.
I'd suggest looking at both model benchmarks at everymac.com. Here's the 2012:
https://www.everymac.com/systems/apple/macbook_pro/macbook-pro-unibody-faq/macbo ok-pro-13-15-mid-2012-performance-benchmark-comparison.html

Performance Benchmarks for WL

Similar Messages

Maybe you are looking for