Dual Core Linux Performance: Two Penguins are Better than One
by Kristopher Kubicki on July 1, 2005 5:55 AM EST- Posted in
- Linux
Multitasking Scenario 4: DVD Burning
Thanks to NeroLINUX, we can now run the first benchmark we did in reverse. We will be paying particular attention to the buffer for NeroLINUX. If the burn continually empties the buffer, then the system is playing catch-up to the burner. We will count the number of times the buffer dies and graph this separately. We used a NEC 3520A burner and a 4.5GB ISO image for the burn.
- Open FireFox 1.0.4 and load all 5 web pages.
- Open XMMS and start playing a Nine Inch Nails CD ripped to Ogg
- Open Thunderbird for news
- Login to our news server and start downloading headers for our subscribed news groups
- Begin an ISO burn with NeroLINUX and start timing
There seems to be a very linear correlation between the number of buffer dumps and the speed at which the discs burned. We really only saw the buffer even come in danger of decreasing at the beginning of the burn and when Thunderbird took a little too long to process something coming in from the news server.
Even though the processors we used in this analysis are more than capable, the additional tasks of FireFox and Thunderbird proved just a tad too much for the chips to handle at all once. This benchmark is a great illustration of where dual core (or dual socket) goes so wonderfully well on the desktop. The additional overhead to run XMMS, FireFox and the other applications is not very substantial, but when FireFox decides to chew up resources while the only CPU is managing the write buffer on a DVD burn, the results can be quite dramatic.
Facebook
Twitter
RSS
69 Comments
View All Comments
juhl - Friday, July 1, 2005 - link
I see that "Norton AntiVirus 2004" is listed with "No Suggestions yet" in the "Linux Application" column. I'd like to make a suggestion : ClamAV - ClamAV is a very capable free virus scanner that runs on Linux - check it out at http://www.clamav.net/Hacp - Friday, July 1, 2005 - link
He clearly stated that this test was based on the best bang for the buck. For all of you who wanted to see tests with higher end processors, you should have stopped reading the article and waited for one that met your needs. Don't complain and ask for stuff that the article was not designed to inform us about.fishbits - Friday, July 1, 2005 - link
Why bother to test the 840 D and draw no conclusions about it? And can you at least fix the price you quote in the one-sided swipe at the X2? I've given up on your explaining why the price of the 840 isn't also "paying through the nose," but at least fix the obvious error either in the text or the price list above it."we have left a lot of not-so-subtle hints as to our feelings concerning performance between the two"
Ah, you were talking about Windows and Linux there. Fits for CPUs too in this case.
semo - Friday, July 1, 2005 - link
listen upeveryone who needs the anandtech next gen console articles just email me. i printed them out to read in the bus/train and i can make some scans.
semo.pz@gmail.com
Avalon - Friday, July 1, 2005 - link
You guys need to remember that this is Linux, so for everyone out there hollering that this article contradicts all the others out there that you read, all the others out there that you did read were most likely Windows based.DrMrLordX - Friday, July 1, 2005 - link
I agree that including only the X2 4200+ is a mistake. For ages, we saw benchmarks of new AMD cpus vs every Intel proc in the field, regardless of price. Kubicki shows up and insists on culling all AMD cpus from the lineup except one priced similarly(or even priced lower than) the Intel offerings in the test. I remember his initial, and rather controversial, article in which he did Linux benchmarks with a 3.6 ghz P4 vs a A64 3500+ Newcastle. Stupid! Where's the 4400+ and 4800+? If you don't have the hardware, DON'T DO THE REVIEW. If AMD has superior processors out at a much higher price, that's because AMD has better chips right now, and they damn well ought to be included in the review as well. Throw in an 840EE if you're so inclined.FURTHERMORE, where are the single-app tests and dual-app tests? All we have are contrived multitasking tests. This is about 1/3rd of the entire content of Anandtech's initial X2 review in a Windows environment. The Pentium Ds don't look so great when you put them into a scenario in which it's running one or two apps alone. Funny how Kubicki neglected to run any such tests in this article.
This article has too little hardware, and too few tests. Thumbs down.
KristopherKubicki - Friday, July 1, 2005 - link
Where do you see that? It should be 3.3.4Kristopher
allanw - Friday, July 1, 2005 - link
gcc3.4.5? That doesn't even exist! :)xtknight - Friday, July 1, 2005 - link
#39 - I meant why?KristopherKubicki - Friday, July 1, 2005 - link
xtknight: Yes.Kristopher