Slashdot Mirror
2.4 vs 2.6 Linux Kernel Shootout
FyRE666 writes "Infoworld are currently running an interesting comparison of the 2.4 series kernel against the new 2.6 release on Xeon, Opteron and Itanium CPUs with some surprising benchmark results for common server-related tasks. Basically the new scheduler helps the 2.6 kernel to cream the old 2.4: Samba tests showing up to 73% speed increases, MySQL showing up to 29% and Apache serving dynamic content up to 47% faster!"
But how much of an improvement does it get on older hardware and/or software packages?
Sorry, my karma just ran over your dogma.
I was wondering about upgrading to 2.6 from 2.4 with XFS on my box, with the improvements to SCSI support and the CPU speed ups it sounds promising :D
Then again BSD is very nice on the same hardware. Wonder how 2.6 linux & (free)BSD compare for those tasks.
These are impressive improvements.
Its actuallly hard to believe that there is that much more improvement to be gained - it will leave the microsoft servers even further behind as I don't think that they are improving their kernel that fast.
One question:
Does this mean that we can see improvements in low end systems for desktop use, or is the benefit only for servers. Because if this helps low end machines, it extends further the number of machines that can move from (say) win 98 to a real OS, whose hardware has long been abandoned by microsoft.
Michael
There is no cryptographic solution to the problem where the intended receiver and the attacker are the same entity.
What I'd like to see is Linux that could run entirely within cache on the higher end chips. Even dated UltraSparcII chips can have up to 8M/cache. That's 64M in an 8-way box, allowing for some truly awe-inspiring performance on mathematical problems if RAM is ignored.
I haven't looked into sparc assembly enough to know if this is possible.
You can't judge a book by the way it wears its hair.
Slackware with Dropline, btw. I do notice that Java tends to take up 250MB of RAM every once in a while while running Firebird. I didn't have that problem with 2.x.x.
The chart on the first page says that 2.6 supports read and write for NTFS. Is this really the case? Does anyone trust NTFS writing if it's in the kernel?
Computers are useless. They can only give you answers.
-- Pablo Picasso
..is the parformance of the Opteron. Looks like Linux 2.6.x and Opteron are a great combo. Okay, I admit, I was a bit skeptical regarding Linux 2.6, but it seems it might actually deliver.
I'm looking forward for Solaris + Opteron servers. Should be another interesting combo, performance wise. For one, Solaris 9 has some fantastic scheduling for multiprocessor machines. Additionally, it has been implemented in 64 bit for many years.
Sigged!
OS X is far better than either "kernel". With OS X you get a better GUI, more apps, and an OS that is backed up by a fantastic corporation, rather than a bunch of hackers who have dubious backgrounds and sketchy credentials.
You aren't comparing like with like. I have windows, linux and OSX running on different laptops at home (ok, I have a problem with needing toys, but at least I have insight).
OSX is very nice - but you don't buy it for speed. In fact, the sort of people who buy it often gloat at how you don't need to worry about that sort of thing with a Mac. I don't doubt that for many windows users, they would be much better off with a mac, as they are pretty clueless, and Mac's are a very nice implementation of the BSD core.
However, this isn't what this post is about. It could be argued that any server that runs a GUI is wasting resources. It depends on what you are asking your server to do.
There are clear improvements in the 2.6 kernel, especially with regard to Disk access from what I can see in the article.
This is totally different to which OS provides the better GUI. In any case, OSX doesn't run on a vast amount of hardware out there, and your attitude is that all that intel stuff is only good for landfill. If you accept that there is alot of hardware out there that will NEVER run OSX, then you should also accept that for those people, its very useful to know if 2.6 is a better performer.
Michael
There is no cryptographic solution to the problem where the intended receiver and the attacker are the same entity.
Maybe one of them, maybe both...
1) The new kernel is really very good.
2) The old kernel is really very bad.
Really, if such huge increase was possible, there must have been a lot of room for it. If you face a really well written program, you have a hard time to speed it up by 5%. If you can speed it up by 50% without loss in other domains, it must have been seriously flawed.
Yeah, mod me flamebait. But first think if I'm really wrong.
45 5F E1 04 22 CA 29 C4 93 3F 95 05 2B 79 2A B2
Yesterday I started a new Gentoo install with the 2.6.1 kernel. I used GCC 3.3.2 and glibc 2.3.2 with NPTL support. I have to admit, the naked eye can see a major diferance with the new kernel. With my XP computer and the new gentoo install (exact same computers .. P4 512MB) I ran a simple boot up and lanch a web browser test. And supprise supprise, Gnome is screamming fast. I had already booted and opened up mozilla 1.6 befor xp was even done booting! Also, simple stuff like opening up email, browsing, etc. is all noticable faster than XP. Soo... before I get slammed by the XP folks.. my XP box was also a clean install. (yes, I have no life!) I am happy to say I am one step closer to completely weening myself off of windows XP.
I just compiled 2.6.1 for my 200mhz laptop (Debian unstable) and the speed increase - especially at boot and for Fluxbox - was very, very noticeable, particularly for cpu intensive apps.
I haven't noticed any breakage - not yet - the machine has only been up for 4 days running 2.6.1. But so far it's great
BTW I used the kernel source from debian, not the backport.
A question for anyone out there with a Digital HiNote 7xx series laptop; any idea which sound chip it uses, and how to set up sound? Google hasn't been very informative. (Not a 2.6 problem, I can't figure out which driver to use; most people seem to be using old SB compatibility, but I can't make it work
SB
It's old. The more humans I meet, the more I like my cats. At least they are honest.
I ran the -ck patches to 2.4 (they have a backported pre-empt, O(1), and low latency) before moving to 2.6. The -ck patches were noticably faster than vanilla 2.4 but 2.6 still crushes them on boot. 2.6 also seems a hair more responsive than 2.4-ck but I expected that.
And I've never used a vendor kernel beyond booting the system and downloading/compiling my own.
THIS IS NOT AN INVITATION TO A FLAME WAR.
Does anyone have factual comparisons of a reasonably-tweaked Linux (2.6 kernel) with a reasonably-tweaked [x]BSD (whatever kernel)?
--
Don't like it? Respond with words, not karma.
I have tried out 2.6 on Mandrake 9.2 and I must say that for desktop use I can't really tell any difference between 2.6 and the 2.4 version that Mandrake is shipping.
I don't know if Mandrake is patching the 2.4 series, but it seems pretty snappy as it is.
The reviewer used RHEL but compiled vanilla 2.4 and 2.6 kernels for the test, not Redhat's. I certainly understand his reasons for doing so but I wish I could have seen how Redhat's custom halfbreed kernel would have performed. Has RedHat already squeezed most of 2.6's performance enhances into 2.4? I'd love to know as I run a number of RHEL boxes, maybe I'll start testing 2.6 on them to see what kind of performance differences there are.
Therefore I assume #1 is much more likely than #2.
It would seem as though the 2.4 focussed on getting a number of feature in the kernel while the 2.6 series allowed the developers to work towards making those new feature faster. Programming a new feature from scratch while also aiming to optimize it for speed can often lead to buggy code. Optimized code is rarely as straightforward and easy to debug as a more general (but slower) algorithm. When it comes to something as important as a kernel I'd much rather have clean, clear code which can later be optimized than a confusing kludge meant to squeeze out the last little bit of processing power.
Just my humble opinion
You forgot billions of dollars lost due to code red infection... Linux=0. How many other IIS virii? Don't go spouting of the usual crap about Microsoft being the bigger target. Apache has double their market share and it's climbing while IIS is falling, and yet MS has double the vulnerabilities in their product.
Number of times my company has been shut down or had a virus replicate through my groupwise system. Zero. Number of companies I personally know people at who'se e-mail servers were shut down due to virus overload... too many to count.
I run 100% MS on the desktop. Linux isn't there yet, and doesn't pretend to be. I have both MS SQL and mysql servers in production. Novell runs my file/print/e-mail. Apache/Linux runs my web servers.
I have a couple of MS Sharepoint 2.0 sites running by special request from one group. It's actually not too bad of a product once you get over the glaring bugs it has.
The fact that you believe MIcrosoft paid for studies is pathetic. I wouldn't believe a study proving linux superior if it was paid for by Red Hat.
FYI I know dozens of MCSE's who did nothing other than study cram exams online and pass the tests. I know of 2 that did it just to say they could, and neither of them can install windows.
I've seen Novell CNE's that couldn't properly set up a Netware box if their life depended on it, and don't even get me started on the Lotus notes people...
People who try and list as many certs as they can in their sig's are about the same as people who drive flashy expensive sports cars... They are usually trying to make up for some other inadequacy.
The hardware specifications weren't very complete, but from what I can see from IBM's x335 configuration they were using the no-L3 cache Xeons. A 3.2GHz Xeon with 1MB of L3 cache could easily boost the performance 10-20% over a 3.06GHz Xeon with no L3. Of course, the Opteron could still end up leading in a lot of the tests. What's more, the Opteron seems to really come into it's own in 4-processor configurations, where the Xeon scales poorly. In short, the Opteron is a heck of a good chip.
Where this really looks bad for Intel though is with their Itanium systems. Assuming that those 1.5GHz I2 processors are of the 6MB L3 cache variety, this is Intel's top-end chips. The servers probably won't have the performance of HP or SGI's I2 servers (IBM doesn't care much for the Itanium so they don't invest nearly as much time and effort in the designs as HP or SGI do), the chip still looks pretty weak.
Intel's saving grace here may be that the Itanium line of chips are VERY dependant on a good compiler, and chances are that these applications were compiled with GCC. Using Intel's ICC instead probably would boost performance by a noticeable margin, though a number of applications still won't compile with ICC from what I understand.
I am using a P4 hyperthread processor. Back in the 2.4.x days /proc/cpuinfo showed me two processors.
Now it shows me only one!
Where is the lost one? Linus, give it me back! Maybe this is the reason his mozilla is faster now?
Anyway, the PCs seems as fast as before, that means that the 2.6.x kernel is able to gain a 100% performance with only one processor ? :)
M.