Benchmarks of Debian GNU/kFreeBSD vs. GNU/Linux

An anonymous reader writes "The Debian Squeeze release is going to be accompanied by a first-rate kFreeBSD port and now early benchmarks of this port have started coming out using daily install images. The Debian GNU/kFreeBSD project is marrying the FreeBSD kernel with a GNU userland and glibc while making most of the Debian repository packages available for kfreebsd-i386 and kfreebsd-amd64. The first Debian GNU/kFreeBSD benchmarks compare the performance of it to Debian GNU/Linux with the 2.6.30 kernel while the rest of the packages are the same. Results are shown for both i386 and x86_64 flavors. Debian GNU/kFreeBSD may be running well, but it has a lot of catching up to do in terms of speed against Linux."

Comments

Holy moley !

[ls671]

From the Linux only perspective, I am still running everything (servers, desktop, laptop) on Linux 32 bits even on 64 bits machine because I figured that running 64 bits wasn't really worth yet.

Now, I am really surprised to see that Debian Linux 32 bits is actually faster than Debian Linux 64 bits in many tests !

Re:Holy moley !

[MBGMorden]

32-bit was faster in a few tests, but it seems like overall the 64-bit still came ahead in more tests than it fell behind in.

Re:Holy moley !

[ls671]

Before seeing this benchmark I took for granted that 64 bits would be faster or at least come to par in all tests. How do you explain that 32 bits is faster in some tests ?

The only way I can explain it is that some piece of code is not optimized yet to run on 64 bits. This kind of prove my impression right; I can still wait for a while before upgrading to 64 bits OSes. The overall performance
gain might or might not be there depending on your use cases.

Of course, I will upgrade to 64 bits some day. Stability is also so a major concern and often, newer equals less stable or at least a new set of problems to troubleshoot.

Re:Holy moley !

[nedlohs]

Where many is ~20% of them.

And why would that be surprising? 64 bit lets you address more memory and they did the tests in a machine with memory that 32 bits could address all of. 64 bit pointers are obviously larger too, so the 32 bit version has effectively more memory and better cache usage.

Some programs aren't going to take advantage of 64 bit registers and so on, but are going to suffer from worse cache performance.

Stick 8 or 12 GB of RAM in and things might be different

Re:Holy moley !

[DAldredge]

64-bit data structures can take up more space in the L1/L2/L3 caches which may cause code to run somewhat slower.

Re:Holy moley !

[ls671]

> 64 bit pointers are obviously larger too, so the 32 bit version has effectively more memory and better cache usage.

Very good point ;-))

Re:Holy moley !

[Erikderzweite]

I'm sorry, what?!
What are "many tests" you speak of?
32-bit Debian Linux was notably better only on compilation (which isto be expected) and POVRay. A couple of tests have shown very small advantage towards 32-bit system, but 64-bit has won MOST of 27 test hands down.

Re:Holy moley !

[Bert64]

64bit code uses more memory, which can in some cases result in decreased performance..
Also, i believe on some intel cpus some performance features are not available in 64bit mode (i forget the exact details)...

Re:Holy moley !

[MBGMorden]

As others have said, 64-bit programs take more memory to run. There's nothing inherently faster about 64-bit registers and operations unless you're dealing with integers that get that big (which in most everyday programs, they don't). What makes 64-bit faster isn't just "more bits", but optimizations. 32-bit code is typically compiled for the lowest common denominator: i386. However, x86-64 CPU's are guaranteed to be at least i686 compatible (you're also guaranteed up to a certain level of SSE compatibility and such). In that regard, it's the code optimization that we can rely on and not "more bits" (which due to extra memory usage, will typically make things SLOWER, not faster) to make things faster.

However, not every app or test really benefits that much from i686 optimizations. For those that don't, and don't deal in larger numbers (AND that don't use so much memory that a 64-bit chip is needed to address it), 32-bit processors will typically be faster.

As to stability, x86-64 is well past the "new" stage. The specification is 10 years old and processors based on it 7 years old - Linux support was almost immediate. Just how long does it take for you to consider it not bleeding edge anymore? :)

Re:Holy moley !

[TheRaven64]

On most architectures, 64-bit code is slower. Pointers are bigger, which means you need more memory bandwidth to load them and you use more cache holding them. On x86-64, the situation is confused by the fact that 64-bit means 'using Long mode,' as well as 'using 64-bit pointers'.

Long mode gives you 64-bit registers (so you can store 64-bit values in a single register, rather than spread across two, doubling the number of 64-bit values you can store in registers), more registers, and a few other benefits like removing the 'must use EAX as the target' restriction on a lot of instructions (reducing the number of register-register moves, and decreasing instruction cache usage as a side effect). 64-bit pointers use more memory bandwidth and data cache.

For best performance on x86-64, you want pointers to remain 32 bits, but still run in Long mode. The OS should make sure that everything is mapped below the 4GB line for the process. As far as I am aware, no operating systems actually support this mode of operation. Without that, for any process using less than 4GB of address space, you have some advantages and some disadvantages when running in 64-bit mode. Whether the advantages outweigh the disadvantages, or vice versa, depends on the code.

Re:Holy moley !

[gmack]

You missed out on the fact that there are more registers on 64 bit than the famously register starved 32 bit x86. More places to put things can't hurt even if your not dealing in 64 bit values.

The problem with 64 bit is that a lot of code is still hand tuned to the maximum possible performance on 32 bit arches and in at least a couple of the cases listed in the benchmarks I wouldn't be shocked if there was some hand done assembler involved. I have also noticed GCC has some performance tweaks that work around the lack of registers on 32 bit that also tend to get enabled in 64 bit..

Re:Holy moley !

[cyberthanasis12]

I have been using SuSE Linux 64 since 2005 with no problems.

Re:Holy moley !

[ls671]

> Whether the advantages outweigh the disadvantages, or vice versa, depends on the code.

That is exactly what I had figured out by intuition I guess ;-))

I have learned (or got refreshed on?) some logical explanations to this fact here today, thanks to you and some others.

I have to admit that I don't remember taking the time to evaluate 32 bits vs 64 bits advantages, just postponing that analysis and an eventual upgrade to later. I though I was past due on that matter but with what I have read today, I will postpone my upgrade for another 2 or 3 years. Ah, problems quickly solved, I like this.

Yet, I think some people might be under the impression that 64 bits performs way better than it actually does, like say, up to twice as fast ;-) This was almost the case when we went from 8 bits to 16 bits for obvious reasons like a few applications used only bytes (8 bits) in their code. Most of them were using types that typically require more than 8 bits, almost doubling the time to store/compute on 16 bits types on a 8 bit machine.

This brings an interesting point: Will 64 bits architectures be "enough for everybody" ?
Will there ever be a point where we might want to go 128 bits or above ?

Thanks for your reply,

Re:Holy moley !

[ls671]

> I have been using SuSE Linux 64 since 2005 with no problems.

Patrick Volkerding has just released the first version of Slackware 64 bits about 5 months ago and it doesn't seem to have had any impacts on the perception Slackware users have ;-))

Granted, there was unofficial ports before that ;-))

Thanks for letting me know it is stable on your side although ;-)

Re:Holy moley !

[thePowerOfGrayskull]

Now, I am really surprised to see that Debian Linux 32 bits is actually faster than Debian Linux 64 bits in many tests !

I'm not so surprised to see that somebody didn't read the graphs very well. 32 bit was faster in only 4 out of 25 tests (16%). Further, 2 of those were only marginally faster to the point where they barely count as a clear lead. Conversely in the majority of cases, 64 bit was not only faster but significantly faster. To the point where I wonder if there were other configuration differences -- for example I don't understand why you'd see a much higher hard drive TPS rate under 64 bit (something like 4x) -- unless they're using a different IO scheduler...

All that said, is it really so unreasonable to ask for results to be laid out in a simple grid for all tests? Raw data is what we like here... (To answer my own question - of course it is. That would mean fewer page hits...)

Re:Holy moley !

[GooberToo]

Before seeing this benchmark I took for granted that 64 bits would be faster or at least come to par in all tests. How do you explain that 32 bits is faster in some tests?

For most, its generally considered a wash. Larger data structures require more cache and more memory and more memory to be accessed. On the other hand, you also get more registers in 64-bit mode. As a result, some things run slower and some things run faster, depending on the nature of the application. On average its likely to be a wash.

The big exception are those that use the PAE 32-bit extensions. Generally speaking, 64-bit is going to be a lot faster. Even still, there are some odd exceptions which will hopefully fuel the imagination of possibilities.

One such exception comes from the PostgreSQL guys. For example, on Windows, they strongly recommend running 32-bit PostgreSQL on 64-bit Windows. This seems really non-obvious at first but there is a good reason for it. If you use 64-bit OS, that means you get large pointers which can access large quantities of memory without using PAE tricks. But, since PostgreSQL spawns processes for each back-end, that means you can run more heavy hitting (very large data sets, heavy queries, etc), concurrent back-ends without taking a performance hit. Additionally, PostgreSQL relies heavily on the OS to cache files. With a 64-bit OS cache, large data sets can be readily cached by the OS and quickly return results to the 32-bit PostgreSQL. This means PostgreSQL directly benefits from 64-bit size file caches; despite running as a 32-bit application. And best of all, a 32-bit PostgreSQL means smaller data structures and more efficient cache use, with twice the available cache a 64-bit application would require. Its almost the best of both worlds.

As the above example illustrates, sometimes a mix can provide ideal results, but on average, consider it a break even unless you plan on having 4GB or more in your box. And even then... ;)

Re:Holy moley !

[Sillygates]

But on x86, you are only guaranteed 4 *real* general purpose registers. x86_64 increases this number. With a good compiler, the register allocator would use all of these, and you would have much fewer loads from main memory, which can take on the order of 75+ cpu cycles on a cache miss, or 5+ cycles on a cache hit.

Re:Holy moley !

[VGPowerlord]

For best performance on x86-64, you want pointers to remain 32 bits, but still run in Long mode. The OS should make sure that everything is mapped below the 4GB line for the process. As far as I am aware, no operating systems actually support this mode of operation. Without that, for any process using less than 4GB of address space, you have some advantages and some disadvantages when running in 64-bit mode. Whether the advantages outweigh the disadvantages, or vice versa, depends on the code.

Whoa, wait just a second. Before asking if the operating system support this, shouldn't we first ask "does the hardware support this?" or more specifically "does Intel's implementation support this?" because as far as I can tell from Wikipedia, it doesn't.

Re:Holy moley !

[Carewolf]

The architecture doesn't have to support it. It is a chastity vow from the program, that while it may use 64bit, it simply opts to only use 32bit while still running in 64bit mode. Sounds confusing but is really simple.

The register is still 64bit (because CPU is in 64bit mode).
The memory slot used to store pointers is 32bit (because no more is needed).
The 64bit instruction set still has "load 32bit from memory" which may be used to load 32bit pointers into 64bit registers.

Now: The reason no one is doing it is becaue the C api states that the pointers should be 64bit when in 64bit mode. If you use a trick like this, your application will no longer be following standards, making it unable to use standard libraries.

Re:Holy moley !

[ls671]

Hehe, sorry, my fault. I used "many" to mean "more than one" and that was a mistake. After reviewing the English dictionary, it seems that in English, "more than one" is expressed by "several". I used to think that they were almost synonyms but "many" means more "a lot" than "several".

My God, how many times must I have sounded like bullshitting before ;-))

Again, my mistake, I even learned the real signification of the word "many" today !! ;-)) /. teaches me all kind of stuff, including getting better in English ;-)

Cheers,

Re:Holy moley !

[TheRaven64]

Of course we shouldn't ask that, because it would be a stupid thing to ask. The hardware doesn't care. If you use 32-bit pointers then you zero-extend them when you load them into 64-bit registers. From the hardware's perspective, you're using 64-bit pointers, but the top 32 bits are always 0. It's up to the OS (and compiler) and has absolutely nothing to do with the hardware. It is the responsibility of the OS to define the memory layout for the application and if the OS refuses to map anything above the 4GB line then the app can safely use 32-bit pointers everywhere.

Re:Holy moley !

[TheRaven64]

There are some neat things you can do with a 128-bit architecture. For example, you can assign an IPv6 subnet to your machine and pointers and IPv6 addresses interchangeably. That's more or less what SGI does with their high-end machines; each node stores a 48-bit local address space and a 16-bit node ID in each pointer. The kernel can then access memory on other machines transparently via a cache coherency protocol. For at least the next decade or so, however, the overhead of doing this on a global scale is going to outweigh the advantages. Probably even then, because if you need to access remote resources you want to use something a bit higher level than pointers.

By the way, when we went from 8-bit to 16-bit architectures, we got 16-bit integer registers. When we went to 32-bit, we got 32-bit registers. We already have 128-bit vector registers on most architectures, and most vector units can treat these as single 128-bit integer or floating point values already, so the only advantage of a 128-bit architecture would be for

Re:Holy moley !

[Anonymous Coward]

Could you site some benchmarks? Specifically some memory bound application that can run maybe 20-50% faster on a 32bit system than the same 64bit system... Could you also point to a non-SIMD case where have 64bit data values is useful but is pointer bound such that 32bit pointers are more efficient?

On most systems that are 64bit, and I can really only think of one exception off the top of my head (the first 21064 had terrible cache and memory performance) the caching is optimized with 64bit values in mind. And it's really "values" the processor doesn't care if they are memory addresses or just numbers until they are operated upon. They typically have caches with longer lines and memory buses that are capable of filling the whole cache lines. Likewise compilers line code up to help with the rest of the system that is optimized that way, your 32bit code on a 64bit chip might still be 8byte alined in memory for best performance. Now it's theoretically possible that if you hand optimized it all and memory access and cache thrashing are your slow points you could make a 32bit version much faster on a 64bit chip by craming more "pointers" into a line of cache but I don't know that it's been done, generally.

I don't believe there is an x86_64 chip that behaves as you want.

There are, however, certain SIMD problems that benefit from what you're describing and the MMX/SSE extensions to the x86 family have supported that for years and years (64bit registers, 32bit memory access, maybe even 128bit registers with SSE, I'm not an expert at it) the thing is there aren't that many problems that benefit from it.
 

Re:Holy moley !

[mirix]

Are they able to store double the words in 32 bit mode though? Or does it just stick a 32bit word in a 64bit register, and waste half of it?
If that's the case, it shouldn't give x64 a performance hit...

Re:Holy moley !

[loonicks]

as far as I can tell from Wikipedia, it doesn't.

nah, it does. i edited the wikipedia article to screw with you.

Re:Holy moley !

[Anonymous Coward]

The extra registers do help, but x86 has register renaming going on in microcode, and it's pretty good at it. It's only some very specific kinds of code that see dramatic benefit from the extra visible registers.

Mind you any app that uses 64-bit ints, like databases, usually sees dramatic improvements.

Re:Holy moley !

[exomondo]

But you'll see - and the numbers in the article back this up - that the real performance impact of this is minimal and the performance benefits outweight the defecits in the majority of cases.

Re:Holy moley !

[ls671]

> so the only advantage of a 128-bit architecture would be for

supporting the full length of a message on /. ?? ;-))

Thanks for your reply anyway,

Cheers,

Re:Holy moley !

[TheRaven64]

The reason no one is doing it is becaue the C api states that the pointers should be 64bit when in 64bit mode. If you use a trick like this, your application will no longer be following standards, making it unable to use standard libraries.

Correction: The C ABI says that, and the C ABI is defined on a per-platform basis (for example, FreeBSD and Linux use slightly different calling conventions on IA32). It's up to the operating system to define the ABI or ABIs that it supports. Solaris, IRIX, and most other commercial UNIX variants have been happily supporting 32-bit and 64-bit ABIs on 64-bit platforms for a couple of decades.

Re:Holy moley !

[drinkypoo]

Because Postgres is really a Unix-type program and not an NT-type program, you mean; NT has cheap thread creation and expensive process creation, while Unix generally features the reverse situation. If Postgres were NT-ized and used multiple threads instead of multiple processes... perhaps things would be different. The bit-width of the system makes no difference to the amount of RAM used for file caches; are you talking about how fast you can shovel data with a 64-bit processor? Data shoveling is the only thing that actually does get dramatically faster.

Re:Holy moley !

[drinkypoo]

After reviewing the English dictionary, it seems that in English, "more than one" is expressed by "several".

Nope. "More than one" means "more than one", and it is a common figure of speech. "Several" means "enough to be worth mentioning."

Re:Holy moley !

[thePowerOfGrayskull]

Several would have been the better choice, but perhaps "in any tests" would have been more what you meant -- that is "more than 0"?

That said - I still wish they'd just give us the numbers in a usable format instead of spreading it across 10 pages with three charts each.

PS: and it's just like you furriners, claiming the language is too hard iffn yer not unnerstood! Why can't yous just talk good English like us reglar folk! ;)

Re:Holy moley !

[snemarch]

The bit-width of the system makes no difference to the amount of RAM used for file caches;

With the exception, of course, that non-server 32bit editions of Windows won't let you use above 4GB of RAM, even though it's supported with PAE (and PAE is enabled for hardware DEP support). Heck, it isn't even a "4GB of RAM" limitation, but "you can only use lower 4GB PhysicalAddresses", which is different... BIOS remapping and all.

Capping to 4GB was a marketing decision, which kinda sucks but is sorta fair enough. Capping to 32bit PhysicalAddresses sucks because you can lose a lot of memory that way, but was done for compatibility reasons; really sucky driver developers thinking they only need to use addr.LowPart instead of addr.QuadPart when dealing with PhysicalAddresses, because they're on a 32bit system...

Re:Holy moley !

[deek]

Glad to hear you're improving your English. Keep up the effort.

"many" implies a significant percentage of the whole. That's obviously not the case here.

"several" would be close, but I wouldn't use it for this situation. It indicates a moderate amount. My instinct is that this is a tad greater than what you want to describe.

I would use "few". It represents more than one, but also signifies a minority.

Ironically, the phrase "quite a few" actually means a large amount, and would be synonymous with "many". English can sometimes behave this way, just to make sure you're alert and paying attention, of course.

"some" may also be a good choice, but it is more indicative of an unspecified amount. It is not as accurate as "few".

Re:Holy moley !

[ls671]

> Nope. "More than one" means "more than one", and it is a common figure of speech. "Several" means "enough to be worth mentioning."

OK, about "a few" then instead of "more than one" ? ;-))

Re:Holy moley !

[ls671]

> PS: and it's just like you furriners

Hey I am not a furriners ! ;-)

My ancestors were in North America probably long before yours or at least before the ones of most Americans were! ;-)

Granted, English ain't my first language although. This doesn't constitute a valid excuse although and I don't try to use that fact as an excuse ;-))

I was merely admitting that I still do mistakes that seem obvious to the rest of the /. community and I actually enjoy being corrected ;-))

Thanks a lot or many thanks or several thanks which ever is the best ;-)

Re:Holy moley !

[ls671]

Thanks ;-)

Re:Holy moley !

[GooberToo]

Unix-type program and not an NT-type program

Yes, process model vs threaded model. For NT, a threaded application would be limited to its maximum addressable space per process, of one process, for all back-ends. Since PostgreSQL is a process model, that means each back-end is limited to the maximum addressable process space. Thus on a Windows 64-bit box, you can load it up with memory and EACH back-end can manipulate up to its 2GB-4GB of address space, depending on configuration.

The bit-width of the system makes no difference to the amount of RAM used for file caches

Absolutely it does. I have no idea why you would believe otherwise. Cache is a function of address space available to the OS. A 64bit OS has a vastly larger address space. This means while a 32bit OS is pragmatically limited to no more than perhaps 1BG of cache after you account for OS+PostgreSQL+Backends. Whereas a 64bit OS is pragmatically limited to how much memory you can afford to place into your box; meaning tens of GB or more; depending on the hardware. That's a HUGE difference.

Re:Holy moley !

[drinkypoo]

Yes, a "few" would probably work. It often is used to mean three, however; a "couple" being two. After that it gets hazy, but "handful" is probably next :)

Re:Holy moley !

[TheLink]

Like the other poster said there's register renaming - this allows pipelined stuff to be executed in parallel even though they happen to be using the same registers.

For example, if you have a pipeline of 8 instructions, the first four instructions might be using R1, and the second set of four instructions might be using R1 too - but for different _independent_ reasons. Now you can't store the same R1 values to two different locations since the second four instructions would generate a different "R1" value. So the CPU figures out that there are no dependencies and so the second set of four instructions actually use R1' to do stuff.

Register renaming can still help when you have 32 registers, but you just have less pressure to do it :).

Also while you are right that the x86 processor has to store and load from main memory more often, the CPU doesn't always have to wait for it to happen. When conditions are right it writes and reads from the cache and runs merrily along at higher speeds. Only later is the final value committed to main memory. This is not as fast as pure register access, but I'm sure there are other tricks the x86 CPU designers do for performance.

Re:Holy moley !

[drinkypoo]

Absolutely it does. I have no idea why you would believe otherwise.

It only makes a difference, as you say, over 4GB. Or on castrated platforms, 3GB. But since you can't actually use more than 4GB without ugly, performance-killing hacks, anyone using more than 4GB is going to need to use 64 bit just to use all their memory. But that's not just the file cache, that's everything.

Re:Holy moley !

[GooberToo]

I think somewhere I lost you and I'm not really sure how since the conclusion is extremely obvious. You're even making exceptions which were already clearly spelled out or flat out obvious.

Which is faster? 1GB of DB files cached? 10GB of DB files cached? The later is only possible on a 64Bit OS. Thusly, even 32bit applications can benefit in this environment, despite the fact they are 32bit and are not directly accessing all of that data within its own 32bit address space. That's entirely the point of everything I said. Yet despite being extremely obvious, it stills seems to go over your head - I think - I'm really not sure based on your comments.

In other words, it gets 32bit cache benefits, non-shared back-end providing access to its full 32-bit address space, and speedy access to 64bit cached files. Remember, the application doesn't need to be 64.bit for the OS to be 64bit. Thusly, a 64bit OS is directly benefiting a 32bit application; whereby the 32bit application is likely to be faster than its 64bit equivalent.

Considering everything I've stated is correct, and now its been stated multiple times, I'm very confused about what it is you're trying to clarify or even what you're point is? Do you have a point? If so, can you state it so I can understand?

sigh

[grub]

Debian GNU/kFreeBSD may be running well, but it has a lot of catching up to do in terms of speed against Linux."

Yep, because we ALL KNOW speed is EVERYTHING when running a computer.

groan.

Re:sigh

[MBGMorden]

Yep, because we ALL KNOW speed is EVERYTHING when running a computer.

Of course it's not everything - but it IS a major part. Cost is another. We're at a tie there.

So what's left? User friendliness? These systems use the same apps - tie there too.

We're basically left with security and stability. If you want to write and article on those feel free - I'm sure Linux won't fare too bad there, but I'd like to see the results.

Still though, to dismiss speed as a criteria is just being naive.

Re:sigh

[clarkn0va]

I think speed is everything when you're writing an article for a benchmark site. Note that I'm not disagreeing with your ironic implication that there are other things to look at, but obviously it's a lot easier to churn out some graphs than to try to compare two OSes/suites/whatever on other important metrics, such as security or usability. Leave that to the media troll sites--there's no shortage of them.

Re:sigh

[TheRaven64]

The speed difference is a few percent. For most people, that's not noticeable. My kernel CPU usage stays well below 10% most of the time, even when the CPU is busy, so even a 50% difference in kernel performance wouldn't be particularly important. Much less important, for example, than things like ZFS, DTrace, a decent kernel sound system, and so on.

Re:sigh

[gclef]

It's not noticeable for most people...but for those of us in situations where it is noticeable that sort of difference is interesting. For example, my office has a debian box that runs at a continuous load average of around 5. Shave 10% off that & we'd notice.

Re:sigh

[ShieldW0lf]

It would be interesting if this ends up being forked into a GPLv3 project and forms the basis for the first ever pure GPLv3 distribution.

Re:sigh

[smash]

Maybe - maybe not. In my experience, latency under severe load is a win to FreeBSD. So although your throughput might not increase under FreeBSD, your responsiveness probably will.

Whether raw throughput or responsiveness is important depends on your application.

Bad time for a holy war

[stokessd]

We can't start a holy war now! My armor is at the cleaners.

Cue nerd rage

Sheldon

Re:Bad time for a holy war

[Anonymous Coward]

Come now, this is supposed to be a happy occasion. Let's not bicker about who killed who...

Mod Article Flamebait

[TheRaven64]

Okay, so I only read the first couple of pages because it's Phoronix who have a history of inflamatory and misleading benchmarks, but from what I saw:

• Sometimes Linux is faster.
• Sometimes FreeBSD is faster.
• Usually the difference between the two is smaller than the difference between IA32 and x86-64.
• The tests were mostly either CPU- or I/O-bound, so there are lots of factors beyond the kernel that would affect the results.
• Debian kFreeBSD uses an old FreeBSD kernel, not sure how old the Linux kernel is but it's probably not representative of the speed of recent releases of either kernel.

Re:Mod Article Flamebait

[Henk Poley]

Linux 2.6.30 is from Jun 9 2009. The latest patchset 2.6.30.10 though is from December 3rd.

Re:Mod Article Flamebait

[bark]

It's NOT testing freebsd. the article tests the Debian world running with FreeBSD

Re:Mod Article Flamebait

[DiegoBravo]

> # Sometimes Linux is faster, # Sometimes FreeBSD is faster. # Usually the difference between the two is smaller than the difference between IA32 and x86-64..,

That's what I would expect! A big difference would be something weird.

> The tests were mostly either CPU- or I/O-bound, so there are lots of factors beyond the kernel that would affect the results.

The benchmarks must be CPU or I/O bound... why should they benchmark sleeping apps?

>Debian kFreeBSD uses an old FreeBSD kernel, not sure how old the Linux kernel is but it's probably not representative of the speed of recent releases of either kernel

I really don't hope the last minute changes to the kernel, to do a big improve the system performance.

Re:Mod Article Flamebait

[TheRaven64]

The benchmarks must be CPU or I/O bound... why should they benchmark sleeping apps?

If they're I/O bound, userspace and kernelspace are both waiting for the drive. The layout of the files on disk will have more of an impact than the kernel. You are right that things should be CPU-bound, I should clarify that I meant userspace CPU bound. You want to benchmark things that are systemcall-heavy, like concurrent apps that use lots of synchronisation primitives.

I really don't hope the last minute changes to the kernel, to do a big improve the system performance.

FreeBSD development follows three branches. -CURRENT is where all of the latest stuff is. -STABLE is where stuff that has been tested a bit in -CURRENT goes. -RELEASE branches are where only bug fixes (no new features) go. The 8.x series began development as 8-CURRENT shortly after 7.0 was released (about two years ago). Some features were then back-ported to the 7-STABLE branch, but only those that could be moved without invasive changes that might affect system stability.

8-RELEASE is the latest stable release and has had two years worth of new features on top of the one shipped with Debian, including, among other things:

• Improvements to processor affinity and scalability in the scheduler.
• A completely new USB stack.
• A newer version of ZFS.
• Improvements to the sound subsystem (now contains a full OSS 4 implementation, per-vchan volume control, a massively improved mixing algorithm, and other improvements)
• A new NFS implementation, including NFSv4 support.
• Network stack virtualisation for jails.

It's not a matter of last minute changes, it's a matter of not getting the last two years of improvements. I know that Debian likes the stable-and-tested versions of things, but they don't seem to apply that policy to the Linux kernel.

Re:Mod Article Flamebait

[Anonymous Coward]

Debian kFreeBSD uses an old FreeBSD kernel, not sure how old the Linux kernel is but it's probably not representative of the speed of recent releases of either kernel.

According to kernel.org and freebsd.org :
Linux stable: 2.6.30.10 2009-12-04
FreeBSD stable: 7 2008-02-27
FreeBSD stable: 8 2009-11-26

The comparison should have been done with FreeBSD 8 or an older version of debian using a kernel of the same vintage.

Re:Mod Article Flamebait

[DiegoBravo]

> If they're I/O bound, userspace and kernelspace are both waiting for the drive

Filesystem strategies can impact severely the time the CPU is waiting for data. This is very important to people who runs databases.

> You want to benchmark things that are systemcall-heavy, like concurrent apps that use lots of synchronisation primitives.

Well, yes, for a pure kernel bench, and I accept it that seems to be the main purpose of TFA; but for me it's more interesting and useful a test of the system as a whole. For example, a GZIP test at 100%-userspace or the ImageMagick compilation can give me a hint about the whole set of wiseness and/or optimizations that the memory management (with help from the compiler) code could make in that platform.

Re:Mod Article Flamebait

[snemarch]

IMHO a GZIP or ImageMagick benchmark suite wouldn't be very relevant here, since you'll almost exclusively be testing usermode code unrelated to the OS. Yes, there's of course going to be some time spent in the I/O subsystem, and of course scheduler and kernel locking granularity has something to say as well... but you'll mostly be testing 3rd party code and the quality of your compiler's optimizations, not the OS kernel.

That said, it would be very interesting if such a benchmark turned up noticeable differences :)

Re:Mod Article Flamebait

[ThePhilips]

... you'll almost exclusively be testing usermode code unrelated to the OS.

Nobody cares about what OS itself does.

All people want from an OS is that their application run and run best.

... but you'll mostly be testing 3rd party code and the quality of your compiler's optimizations, not the OS kernel.

The statement is valid for e.g. MS-DOS. But it never was valid for OSs supporting virtual memory and I/O abstraction: the way kernel does things impact application performance quite noticeably. I/O optimization (read-ahead, delayed write back) and virtual memory management (application memory allocation, stack, context switching) all have direct influence on user space performance. And that is what important and is subject of the Phoronix tests.

P.S. My personal gripe with the tests is that they do not attempt to measure latencies. For some I/O-bound applications and also video playback latencies are more important compared to throughput or CPU usage.

Re:Mod Article Flamebait

[Hurricane78]

And we’re already at 2.6.33. What’s the point?

Re:Mod Article Flamebait

[Anonymous Coward]

Don't blame debian stable for the kernel tested. Blame phoronix. Debian stable is back at 2.6.26. Phoronix used debian testing...

Also, there's a lot more people working on having debian working on the linux kernel than on the freebsd kernel. Be appreciative that these people are putting in the effort because they clearly like Freebsd. They just aren't a big enough team to closely track the latest release. They got it to work on an older one and probably moving to the latest freebsd kernel is one of their priorities once they have the one they're playing with ironed out.

Plus, noone I know takes phoronix benchmarks seriously... you test your own applications, and frequently, using freebsd is more about wanting things like zfs, not worrying about how fast MAFFT runs.

Phoronix

[OverlordQ]

While they're really the only group that does a lot of linux benchmarking, I'd put a *large* grain of salt in their results.

They have no problem blindly accepting something like this without investigating why it is so much faster and seeing if there's a problem with their testing.

Re:Phoronix

[machine321]

Perhaps because it was in line with their other, unrelated benchmarks? I note you don't identify any problems with their testing, you just imply there must be a problem and they didn't look for it.

Besides, you should have shown the PostMark benchmark, where it was a 10:1 improvement with 64-bit.

Re:Phoronix

[david.given]

Their FreeBSD filesystem-heavy benchmarks look extremely dubious --- UFS and ext3 aren't that different. I find myself wondering whether they actually remembered to turn SoftUpdates on.

Re:Phoronix

[Anonymous Coward]

I find your dishonessty unsettling. Phoronix does look into serious regressions when resources allow, and even has an automated tool that works with the Phoronix Test Suite and (currently Git) repositories of software to isolate the cause of regressions. I say kudos to the Phoronix team for making the effort.

Here is the link to the tool:

http://www.phoronix.com/scan.php?page=article&item=linux_perf_regressions&num=1

Wait a minute... glibc?

[Tinctorius]

Didn't Debian switch to eglibc because Drepper was being an asshole?

Article over 9 pages.....

[Anonymous Coward]

.....fuck that! Tab got closed, comments get whinge added, going elsewhere.

I just wanted to see if ...

[sharkette66]

I don't use BSD, I just wanted to see if the "BSD is dying" troll still posted. It has been years, eh?

It does also seem to me that the FreeBSDk thing is meant to make certain features available to developers, maybe be more reliable, and "faster, faster" isn't being sold as part of the bill of goods. Yet, the talk returns to speed, speed, speed.

But what do I know... I work as a nurse. Although... I DO love a fast computer.

Re:I just wanted to see if ...

[brackishboy]

That meme died ages ago. Netcraft confirmed it.

Re:I just wanted to see if ...

[Anonymous Coward]

Yet, the talk returns to speed, speed, speed.

An article about benchmarks encourages discussions of speed? Who'd of thunk it?

Please educate me a bit.

[santax]

As a long time debian user who also has to work with freebsd sometimes I don't get it. Why use freebsd with GNU apps, when you can just run freebsd? And why freebsd and not lets say, openbsd or netbsd? What is the advantage in using the freebsd-kernel instead of the linux-kernel? I have access to every linux app when I use freebsd and to be honest, if I knew my way around bsd as I do under debian I would probably switch. But I am missing the improvement for Debian here. Can someone please clear this up for me a bit?

Re:Please educate me a bit.

[Erikderzweite]

Well, why not? I don't feel I'm going to use it, but it's nice to have a choice.

Re:Please educate me a bit.

[BitZtream]

'Because we can' is the answer you are looking for I think.

Considering what they've done (most of it anyway) can be accomplished with a few flags to make.conf anyway, its not exactly impressive. Tell the system to use glibc instead of its native libc, then rebuild world (to rebuild the built in GNU tools with glibc) and build the ports for other GNU tools you want and you've got what they made.

You could probably write a fairly trivial sh script to do this on a generic FBSD install.

This is just a typical 'We did it because we can and we wanted to' type of thing the way I see it.

You use the FBSD kernel because its going to have the largest driver base compared to the other two for hardware that people care about, although NetBSD can't be far behind it. OpenBSD is just a bitch thats not worth the effort to deal with for any reason since it has no real advantage over a FBSD 'Minimal' install, possibly with some config tweaks but it won't be many.

The one shining thing you can get, is a native ZFS implementation, though by using an old kernel they've kinda killed that idea since the version in that kernel is not really production ready. You get jails, which are nice for some purposes, but with paravirtualized linux on linux and enough ram its really not that big of a deal. They also claim that you get the advantage of the debian package system, but other than a gui I see no outstanding advantage over the FBSD package system, with the exception that I think they still don't make a screen package due to some kernel interface issues that break it when used with a kernel compiled with slightly different options, its never been a problem for me, I build and distribute screen internally to our BSD boxes without 'noticing' a problem.

TFA has more reasons why you might want to do it, but they all seem pretty weak to me, but I'm a FBSD person, and don't care for Linux that much, so my bias is probably not helping.

Re:Please educate me a bit.

[0racle]

Off the top of my head, and pretty much pulled out of my ass:

The FreeBSD kernel can be faster the Linux, but there are a lot of poorly written apps that think they absolutely must run on Linux or were written expecting GNUisms. Now you can do that.

FreeBSD is generally the more generic and performance driven of the BSD's with a larger developer base then the othe BSD's. The odds for very good performance and good hardware support are in FreeBSD's favor over Open or Net.

Porting apps to different platforms can have the advantage of opening or exaggerating new or difficult bugs in software, the end result being that everyone gets a better final product out of it.

Finally, of course, why not?

Re:Please educate me a bit.

[Bill, Shooter of Bul]

I prefer Gnu Userland. As for the kernel, its another option. Even though I prefer KDE, I wouldn't say that Gnome devs are wasting their time, or debian shouldn't allow users to install it. FreeBSD's kernel seems to be more performance tuned than Open BSD or Net BSD. Makes sense to me.

Re:Please educate me a bit.

[eqisow]

Why use freebsd with GNU apps, when you can just run freebsd? And why freebsd and not lets say, openbsd or netbsd?

They actually have a NetBSD port as well as a Hurd port. They also have a nifty why NetBSD section. There doesn't seem to be a similar page for kFreeBSD, but I assume the reasons are similar.

Re:Please educate me a bit.

[Enleth]

When George Mallory, the guy who attempted to climb Mount Everest several times (and almost succeeded, though the most successful attempt was also fatal in the end), was asked why exactly would he try to climb it, as it was extremely dangerous and he wasn't even a scientist or a cartographer, he said one simple thing.

"Because it's there."

Sure, there probably are some practical purposes for a version of Debian running the FreeBSD kernel, but whatever those might be, I think it's not a matter of "what for" but of "why", and this in turn is answered by the aforementioned quote.

Someone wanted to do that, probably just for the heck of it, someone else thought that it might be fun, they joined their efforts and did it. A good part of the whole FLOSS and academic research worlds works like that. Nothing wrong with that, IMHO.

Re:Please educate me a bit.

[santax]

Thank you and the other people for giving your views. Because we can sounds like a perfect legitimate reason and I did my part of 'well, because I want to see if I can' myself. ZFS is indeed a value-improvement of debian I think and that is cool. (well I think that is cool). Still I am not really satisfied with the answers (sorry, please don't take this personal cause it isn't) I just hope the devs have some sort of great masterplan that totally makes sense.

Re:Please educate me a bit.

[vlm]

Why use freebsd with GNU apps, when you can just run freebsd?

Then you'd be stuck with freebsd apps instead of GNU apps.

If you have a mighty herd of servers, desktops, and kiosks, all sharing various automation scripts, supporting both freebsd and GNU command line apps could be a pain, due to subtle differences in command line options, etc. Its possible to create a blizzard of "if then" to work around, but why bother.

But I am missing the improvement for Debian here.

Overall, none really. The way ports work on Debian, is if enough people volunteer to maintain a port, and they are successful, then we have a new port. Heck, that is the way everything works in the Debian project, if something meets a certain standard of excellence, its in, no matter if its a package, docs, artwork, shared VCS, human language translation, a network service, a mirror, or in this case, a port. Debian is thankfully not a deletionist stronghold like that dumpy embarrassment known as wikipedia.

This link provides a one page summary of each attempted Debian port, successful and ... not so successful :

http://www.debian.org/ports/

Re:Please educate me a bit.

[santax]

Thank you for the link to the why-page. It does explains things for me.

Re:Please educate me a bit.

[mrsteveman1]

As someone who is just now stepping into FreeBSD and who has managed Debian/Ubuntu systems for quite some time, i do find the front end tools for package management on Debian to be a bit nicer than pkg_add/pkg_delete on FreeBSD, but i know there are many other tools on FreeBSD for this purpose that i haven't found yet :)

Re:Please educate me a bit.

[vlm]

but other than a gui I see no outstanding advantage over the FBSD package system

As a gauge of relative activity level in each package system:

The weekly list of UPDATED (and possibly NEW) BSD packages at

http://www.freshports.org/ports-new.php?interval=week

is roughly equal in size to the weekly list of NEW Debian packages at

http://packages.debian.org/unstable/main/newpkg

So, each week, there is about as much new stuff added to Debian as there is updated preexisting stuff in BSD.

Re:Please educate me a bit.

[TheRaven64]

The FreeBSD kernel gives you a few nice things. ZFS, DTrace, and a high-performance in-kernel sound system that eliminates the need to mess about with things like PulseAudio just to get half a dozen applications going 'bing' at the same time while another one plays music (although this got a lot of improvements in the FreeBSD 8 kernel, which isn't in Debian yet, as did ZFS). It also gives you the ULE scheduler, which has had several years of testing and refinement (unlike Linux's scheduler-of-the-week) and performs very well (was outperforming Linux by a large margin on 8+ cores, now they're pretty similar). It includes Jails, which are like chroot but with a complete environment inside so you can have a different IP, different users, and so on in a jail (and you can create them with a complete clone of a skeleton system almost instantly with ZFS clones).

As to why you'd use Debian rather than FreeBSD, the big difference is glibc rather than BSD libc. When people talk about Linuxisms in code, they most often really mean GNUisms and the code depends on something weird in glibc, rather than on anything specific to the kernel. It will therefore work with glibc on kFreeBSD just as it would with glibc on Linux. You may also prefer the GNU userland utilities. Some people install these on FreeBSD anyway, but with Debian they are the default ones. This means that a few other common GNUisms (e.g. assuming that /bin/sh is bash and that POSIX utilities accept GNU arguments in shell scripts) will work.

This means that it's easier to port crappy code (and there is a lot of it about) from GNU/Linux to GNU/kFreeBSD than to FreeBSD. I've written a bit about which bits are GNU and which bits are Linux before: most of what the user or developer interacts with is GNU.

Re:Please educate me a bit.

[morgan_greywolf]

They also claim that you get the advantage of the debian package system, but other than a gui I see no outstanding advantage over the FBSD package system, with the exception that I think they still don't make a screen package due to some kernel interface issues that break it when used with a kernel compiled with slightly different options

What are you talking about? I have screen installed on FreeBSD 8, all I had to do to install it was 'pkg_add -r screen'.

Re:Please educate me a bit.

[idiotnot]

Not only that, they're cleanly managed with apt and dpkg. Ports has grown so unwieldy that when I do use FreeBSD these days (admittedly, it's pretty rare), I don't build anything from ports, and use pkgsrc. On the rare occasion that pkgsrc doesn't have something I need, I'll just build it from source manually. But, but, but, but portsupgrade!!!1! It sucks compared to apt/dpkg and pkgsrc. 8, 10 years ago, maybe it was great. But notsomuch anymore.

I also use pkgsrc on Slackware, OpenBSD, and OS X.

Re:Please educate me a bit.

[ChipMonk]

Along the same line, I'm reminded of JFK's challenge to put a man on the moon before 1970. After the Sputnik shock and the subsequent re-grouping, we were ready to push our limits, doing things "not because they are easy, but because they are hard." And by the time Apollo 11 returned, with everybody safe and sound, the benefits of the space program was reaching society at large.

With such a large challenge, overcoming the hurdles on the way produces benefits that often can't be quantified beforehand. And we are all better off for it.

Re:Please educate me a bit.

[machine321]

In other words, in FreeBSD they fix the shit that's there, in Debian they just keep shoveling in more shit.

Re:Please educate me a bit.

[machine321]

You mean GNU/NetBSD and GNU/Hurd, right?

Re:Please educate me a bit.

[Anonymous Coward]

Debian kFreeBSD leverages much more than the APT *tool*.
The huge chunk of work that Debian is doing is in the packaging process (validation, QA, security updates).

From a more practical POV, I would be happy if I could manage only Fbsd/Linux Debian systems instead of a tenth of OpenBSD and hundreds of Linux Debian.

Re:Please educate me a bit.

[Anonymous Coward]

Debian is thankfully not a deletionist stronghold like that dumpy embarrassment known as wikipedia.

Calling Wikipedia a deletionist stronghold is like accusing Fox News of having a liberal bias. It says a lot about your prejudices, and nothing about reality.

In the real world, deletionists are (and always have been) a rather unsuccessful minority on Wikipedia. About the only victory they ever won was when they managed to get a bunch of webcomic articles deleted, and that was years ago. Schools? Inclusionists won. Pokemon? Inclusionists won. Pop songs? Inclusionists won. Etc.

Re:Please educate me a bit.

[Anonymous Coward]

Why use freebsd with GNU apps, when you can just run freebsd?

Because fBSD has a terrible BSD-like userland stuffed full of all the BSD quirks, and most people strongly prefer GNU userland? Because fBSD has some great stuff in the kernel, but a Debian userland on top of it would make it suck less? Because Debian isn't Linux? Because the Linux kernel is starting to suffer from decades of driver bloat and the 2.6 series' declining stability is undermining the desire of the user base to stick with Linux?

Personally, I'd be much more interested in FreeBSD or one of the other BSDs if it weren't slathered with all those commands that kinda-sorta work sometimes except for not recognizing half the options I pass them. Slapping a GNU userland on it makes it more appealing.

Pick a reason, any reason. Make up your own if you like.

Re:Please educate me a bit.

[Anonymous Coward]

Actually, yes, that's what they call them, but the 'GNU' wasn't necessary or proper in that context.

Re:Please educate me a bit.

[david.given]

This link provides a one page summary of each attempted Debian port...

Don't forget the unofficial Debian ports; one really interesting one is Debian Interix, which is a Debian userland on top of Microsoft's Unix layer for Windows. It hasn't had a lot of activity recently because it's mainly run by one guy, and Interix doesn't get a lot of bugfix love from Microsoft (surprise surprise), but compared to the abomination that is Cygwin it's already light-years ahead. All it needs is a decent community...

Re:Please educate me a bit.

[Anonymous Coward]

Don't forget about being able to use pf. Way better than iptables with amuch cleaner config file.

Re:Please educate me a bit.

[deek]

FreeBSD has some cool features in the kernel, like ZFS support, Jails, and a 10Gb optimised network stack. I've found that the FreeBSD kernel responds better when the system is under heavy load. That's a godsend when you're trying to fix an issue. It's a high quality kernel, and is extremely stable.

Software management in Debian is much nicer than FreeBSD. The configuration files are more consistent, and keeping your system clean and tidy is an easy process. Doing updates, and even major upgrades, is often trivial in Debian.

I imagine that the idea behind the kFreeBSD project is to marry the best of both systems. It's a neat idea, I think.

Re:Please educate me a bit.

[NemoinSpace]

When George Mallory, the guy who attempted to climb Mount Everest several times (and almost succeeded, though the most successful attempt was also fatal in the end)

Nothing wrong with that, IMHO.

What about the dying part?

Re:Please educate me a bit.

[Anonymous Coward]

Because there's people wiliing to waste their time into that... I find it stupid, to join the worst of both worlds: FreeBSD kernel (with less features than Linux, and specially with less hardware support) + bloated and ever complex GNU/Linux utils/userland. The best part of FreeBSD is the strive for simplicity and Doing Things Right, not the kernel.

Re:Please educate me a bit.

[TheRaven64]

Yes, that's true, and on the networking side netgraph is amazingly useful if you want to simulate unusual network conditions (I used it during my PhD to simulate running my code on a high-latency link with lots of jitter and 5% packet loss, for example). There's something similar for Linux, but netgraph is amazingly easy to use.

Re:Please educate me a bit.

[ancientt]

I think that sums up for me why I'd be interested in the project. I'm not interested in running Linux with a BSD kernel for work because I like things that are reliable and well tested and documented by a large userbase. I'm not running it personally because I don't want to spend the time on something without a strong obvious benefit, but I appreciate that someone is.

The goal of doing something like this isn't to produce a product that is better than anything else, it is to see what you can do and see what happens when you do something novel and complex. Think of it as a great experiment, and one that anyone who wants to invest the time can do. Even if nothing grand is the end product, the process and the lessons learned from trying new things are pretty cool on their own.

Re:Please educate me a bit.

[smash]

Because for some inexplicable reason (read: unwillingness to learn), many Linux users seem inextricably bound to the shitty GNU userland tools.

Re:Please educate me a bit.

[santax]

That is just plain trolling mate. No matter what cool uid you have.

Re:Please educate me a bit.

[smash]

No, its based on having used both Linux since 1996, and FreeBSD since 1999...

Re:Please educate me a bit.

[santax]

Yeah, whatever you say. Good to see you made a real good case for you point... Lol.

Re:Please educate me a bit.

[smash]

Well seriously, there is zero other reason to bastardize a FreeBSD system with GNU toolchain.

The BSD userland works and is tested with the BSD kernel. The GNU userland isn't, really.

The debian package manager is not really any better in real world use, so that leaves the GNU userland as being the only reason for its existence.

2c, but IMHO Debian/BSD is wasted effort that would be better spent on either Debian/Linux or FreeBSD proper...

Though, i guess if you're set on running a Debian system with a decent kernel...

Re:Please educate me a bit.

[smash]

oh btw... I ran Debian as linux of choice between 1999 and 2007 (as mail/proxy/firewalls for various business clients).... so I'm not just a linux user who has no fucking clue on BSD, or a BSD user who has no clue on linux... :)

Only reason i have RHEL at the moment here is due to it being an officially supported platform for our ERP solution.

This benchmark is useless without ZFS

[Anonymous Coward]

This benchmark is useless without ZFS.

Comparison with original FreeBSD?

[maxwell demon]

What about a performance comparison with original FreeBSD?

Re:Comparison with original FreeBSD?

[Anonymous Coward]

There are FreeBSD 7.2/8.0 benchmarks being added to the comparison next week at Phoronix.

Re:Comparison with original FreeBSD?

[vlm]

What about a performance comparison with original FreeBSD?

The "original"? Just for laughs, get the results for version 1.0 from 1993 along with 8.0-RELEASE and 9.0-CURRENT

http://en.wikipedia.org/wiki/FreeBSD#Version_history

Flash?

[xoundmind]

So can I run Flash-enabled browser on this port?

Re:Flash?

[hhw]

You've been able to use the linux adobe flash plugin with a native browser for quite some time now. Works just as well as it does in Linux (not necessarily saying much). The FreeBSD handbook is your friend:

http://www.freebsd.org/doc/handbook/desktop-browsers.html

Re:Flash?

[Anonymous Coward]

I don't see why not. Flash works on Debian and Flash works on FreeBSD. I'd assume it works on the hybrid.

glibc

[argent]

glibc is a much more complex libc than the one FreeBSD uses. FreeBSD doesn't use libc as the "glue layer" nearly as much as Linux, so the extra overhead of glibc is wasted.

FreeBSD ports can't be relied upon

[r00t]

The other day, I was installing an old FreeBSD system for compatibility with some stuff I had. I figure it's like installing an old Linux, right?

Wrong. When I install an old Linux, I can install all the old software. The *.rpm or *.deb files exist. FreeBSD doesn't work like that. It has ports. If your system is old, you're screwed. The ports system is only 100% available for the latest release. For older releases, there is a sort of weak idea that maybe it kind of sort of ought to be maintained when somebody bothers, but probably it'll just FAIL.

Really, that's crap. An OS shouldn't become unavailable as it ages. I might need it!

Slackware from 1994 still works as well as it did back then, 16 years ago. What's FreeBSD's problem?

Re:FreeBSD ports can't be relied upon

[bark]

This is wrong. the Ports system is based on CVS, so in essence, you can go back version by version, back to the beginning, and select version numbers of the software to install at will, without having to depend on precompile binaries. You use the supfile to select the port version you need http://www.freebsd.org/doc/en_US.ISO8859-1/books/handbook/cvs-tags.html Gives you all the branch tags that you can check out via historical cvs. But Alter Relationship obviously didn't read the handbook, and started complaining without even reading the man pages.

Re:FreeBSD ports can't be relied upon

[r00t]

In theory, perhaps.

On that web page I see this: "The ports and doc trees use tags whose names begin with RELEASE tags." Excuse me, WTF? You're only going to tell me how the name begins and leave me to guess the end?

Can I go back 15 years? Can I do this for versions 1, 2, or 3?

What about all the stuff it drags in? Is the old source code actually there, or just the build system?

I sure hope that a CVS checkout isn't going to drag a bunch of old history with it. Gigabytes would be unfriendly.

I can go to Red Hat or Debian's site and just download the packages I want, either binary or source. Why does FreeBSD makes things so unusable?

Re:FreeBSD ports can't be relied upon

[Anonymous Coward]

I'm sorry, FreeBSD doesn't make allowances for idiots. It's not their fault that you can't understand the docs.

Re:FreeBSD ports can't be relied upon

[Bluesman]

I wish Alter Relationship would stop replying to himself.

He's almost as bad as that other troll, Friend of a Friend.

Re:FreeBSD ports can't be relied upon

[Anonymous Coward]

Yes, your slackware from 1994 is full of security holes. The FAIL here is you trying to install an unsupported version of the OS and then complaining about it when it doesn't work.

Re:FreeBSD ports can't be relied upon

[r00t]

Yes, your slackware from 1994 is full of security holes. The FAIL here is you trying to install an unsupported version of the OS and then complaining about it when it doesn't work.

Never did I suggest that I was running a random server exposed to the Internet. The box could be running some lab equipment that costs millions of dollars to replace, using a proprietary control program that won't run on a more modern OS. The box could be running a legacy app, with a modern system controlling things over a serial line. Shit happens.

The fact that an unsupported OS suffers bit rot is disgusting. The bits should just sit there forever, as they do for every Linux distribution except Gentoo.

I will never voluntarily put myself or my future successor in such a terrible position. Software needs to be available forever.

No excuses!!!

Re:FreeBSD ports can't be relied upon

[Anonymous Coward]

andy zebrowitz

I've heard this...Unlikley.

[gbutler69]

Why? Because every 64-Bit CPU I've ever used always had more than twice as much L2 cache as 32-bit Systems. In other words, the hardware manufacturers/designers have already accounted for that.

Re:I've heard this...Unlikley.

[ls671]

> Because every 64-Bit CPU I've ever used always had more than twice as much L2 cache as 32-bit Systems.

I am glad I am using 64 bits CPUs to run my 32 bits OSes then ;-)

Well unless somehow, the "twice as much" doesn't get used with 32 bits OSes running...

What do you think ?

Re:I've heard this...Unlikley.

[barrkel]

If you're talking about x64, the primary 64-bit consumer desktop / laptop CPU architecture, has it occurred to you that code running in the CPU's 32-bit mode also benefits from the doubled cache? It's not like the 32-bit code only uses half the cache, with 64-bit code using the full cache.

Re:I've heard this...Unlikley.

[obarthelemy]

the tricky part is to NOT use half the caches when running 32 bit apps :-p

Re:I've heard this...Unlikley.

[Anonymous Coward]

32-bit 64-bit

not 32-bits, 64-bits, god.

A marriage made in...

[Anonymous Coward]

The unpolished GNU userland and GlibC (no offense, just compared to BSD's userland/libc or Solaris, they just tend to be weirder imo) combined with FreeBSD's stable but mostly unsupported kernel (Oh? You wanted ALSA? Sorry. You wanted Linux kernel modules? Oh, sorry. You need Linux hardware support? Oh sorry).

So I guess you get the worst of both worlds? Awesome.

And it's slow.

Great job guys :D

Question?

[Murdoch5]

Why even swap the kernel out? The Linux kernel supports more hardware and has better stock performance then the FreeBSD kernel. In fact most friends I have that use FreeBSD are snotty to Linux users anyway. I say give them there OS and it's sorry performance (at least I've never seen anything comparable) and I'll stick with my stage 1 Gentoo which is fast, optimized and ready to go.

Sorry if this offends any FreeBSD user as that's not my point but I've installed it a ton of times to try it out and I'm still waiting for an install that lets me say "Woah" from the get go. Sure you can optimize after the fact but that's not the point, fast out of the box, faster after the tweak! that's what I want and FreeBSD has never given that to me .

If your a FreeBSD user great and if you a Linux user great, but lets not mix the two please!

Re:Question?

[RAMMS EIN]

``Why even swap the kernel out?''

It's good to have choices. Even if Linux is the best choice for you today, you can never know that it will be the best choice for you forever. Providing Debian GNU/kFreeBSD not only offers Debian users the option of using the FreeBSD kernel instead of Linux, but also offers FreeBSD users a way to use the GNU userland instead of FreeBSD's.

Moreover, in making different kernels and userlands work together, areas where this is problematic are identified and improved, so that other projects besides Debian can benefit, too.

The end result is that you gain more options to mix and match parts to build the system exactly the way you want it.

``I'll stick with my stage 1 Gentoo which is fast, optimized and ready to go.''

And you still have that option, too, of course.

Re:Question?

[IMightB]

I'm a Linux fan, but there's a first. A linux user complaining that he needs to tweak the OS to get the most out of it!

Here's a tip, ALL OS's require tweaking to get the most out of them.

Re:Question?

[Murdoch5]

I'm not complaining I need to tweak the OS in fact, I like to tweak and tune the system. My point was that every time I've ever used FreeBSD and this is a complete personal opinion I just find it to be sluggish and slow.

Tweaking is a good time if it's done properly and effectively and it can produce a big performance boost. My only point is that I've never seen performance from FreeBSD, even my FreeBSD friends who know there system in and out still have a slower system.

If someone wants to correct me I'll stand to be corrected but just from a personal view point I've never seen FreeBSD produce performance.

So I'm not complaining I have to tweak, after all I run Gentoo lol it's tweak city and flags up the butt.

Why so ?!?

[DrYak]

No, not necessary.

It's not because your CPU is running a 64bits OS that suddenly every data format has to be replaced with one using 64bit integers.
It's not because your CPU is running a 32bits OS that you aren't allowed to manipulate anything bigger 32bits.

The OS bittage has almost no impact on what data format can be used. Only how fast those format will be processed, and how many memory can easily be addressed in a straight-forward way.

A 256 x 256 bitmap, RGBA, with 8bits per channel, will always take the same amount of memory wherever the OS is running 32bits or 64bits code. Only with a 64bits OS it will be much more easy to store more than 3GiB worth of textures.
And even a 32bits OS can manipulate 1024bit data structures like crypto key (only a little bit slower, because the CPU internally won't be able to do 64bit operations).

Also most OSes are LLP64 or LP64, meaning that the default "int" still is 32bits. Thus code recompiled in 64bits will tend to approximately use the same amount of data as original code in 32bits.

Re:Why so ?!?

[Lupu]

Also most OSes are LLP64 or LP64, meaning that the default "int" still is 32bits. Thus code recompiled in 64bits will tend to approximately use the same amount of data as original code in 32bits.

True, but the instruction set architecture doubles by size, resulting in larger binaries and more executable code to fetch from memory. As an example, the ARM instruction set is 32-bit by default, but ARM processors support a 16-bit Thumb mode. The programs typically execute slower in Thumb mode but often completion speed results in a net gain when the program is being loaded from slow flash/ROM. This is a typical set-up in many embedded systems.

Re:Why so ?!?

[ChipMonk]

It's not because your CPU is running a 32bits OS that you aren't allowed to manipulate anything bigger 32bits.

I can't speak for other OS's, but in the case of Linux, a 32-bit OS does mean there is a 32-bit limit on general registers (EAX, EBX, ECX, EDX, ESP, EBP, EIP, ESI, EDI). During a task switch, only the lower 32 bits of the general registers will be saved into the process state, even on a 64-bit CPU. When the kernel switches back to the process, only the lower 32 bits will be restored.

This is a good thing

[PhrstBrn]

I can see a really good usage case for this.

You're a sysadmin, and you're running Debian almost exclusively. You have a large number of automation scripts that you use to do your job (security updates, auditing, provisioning, general maintenance, etc). All of them are expecting to run on Debian, because all you run is Debian. So you, as a sysadmin, decide you want to use ZFS somewhere.

You have a few options:

1) Run Solaris
2) Run some derivative of BSD (FreeBSD, OpenBSD, NetBSD, etc)
3) Run Debian w/ ZFS in Fuse
4) Run Debian kFreeBSD

Options 1 and 2 will most likely require you to tweak or rewrite a lot of your scripts. I shouldn't need to explain why option 3 is a bad idea. Since you're working with Debian userland, going with option 4 seems like it would be the path of least resistance. Seems pretty useful.

Re:This is a good thing

[Anonymous Coward]

ah, but you forget about nexenta

Other Interesting Benchmarks

[RAMMS EIN]

It would also be interesting to see benchmarks of functionality actually provided by the respective kernels. E.g. performance of fork, fork+exec, socket, accept, reads and writes on IPC, multiprocessor/multicore/hyperthreading performance, etc. Past benchmarks have shown that there can be dramatic differences between operating systems especially when large numbers of something (processes, filehandles, CPUs, etc.) are being used simultaneously.

Also, I am missing a description of exactly how they measured. Did they recompile the benchmark suite from scratch on each platform? Which compiler was used, and with which settings? Are they running the same binaries on both? How exactly did they arrive at the presented values? Is each bar the result of a single run, or did they run each benchmark multiple times and account for any variation in observed scores somehow?

As others have already mentioned, it would also be interesting to see how a regular FreeBSD system would fare.

All in all, interesting benchmarks. My conclusion: there isn't that much of a difference between the tested versions of Linux and kFreeBSD in there benchmarks. The difference between 32-bit and 64-bit is usually more pronounced. If you need the highest performance for your application, you'll still have to run your own tests.

Data vs. Code

[DrYak]

The parent poster mentioned problems with *data* structures, not with code.

And the code it self is less likely to increase. First there isn't a big different in length between x86_64 and stock x86 op codes. The whole x86 family has been using opcodes of varying length since day 1.
There's nothing as dramatic as the differences between ARM native 32bits and Thumb 16bit modes.

Second, in 64bits the number of available registers increases dramatically, as said elsewhere in this thread.
As such, the net result is more compact code (less instructions are lost copying values around between the few registers - and the microcode doesn't have a hard time keeping track of this for its register renaming) and is one of the reason why 64bits code tends to sometimes even run faster as 32bit code on x86 platforms.

The only thing which is going to take more place are the memory pointer tables (they'll be using 48 and 64bits pointers).
But even they won't matter much as - as big as they are - these tables represent only a tiny fraction of all the data going through a CPU and occupy not that much cache-space. And the preferred memory model for 64bit code is flat, to begin with.

XWindows

[Gothmolly]

Does FreeBSD boot you into X by default yet? I installed the latest and told it "everything" and booted to a command shell. 'startx' returned an error. What gives?

Not a big difference

[DrYak]

in the case of Linux, a 32-bit OS does mean there is a 32-bit limit on general registers (EAX, EBX, ECX, EDX, ESP, EBP, EIP, ESI, EDI).

Well that's still 8regs * 4bytes = 32bytes per task, vs. 16regs * 8bytes = 128bytes per task.
You'll need quite a lot of task switching in order to fill the cache.

And even then, switching tasks is a rather rare event on the scale of other computations (Linux can switch task at 1000Hz when the low-latency desktop option is compiled into the kernel), so it is less dramatic if the switch does force a reload from RAM.