Originally posted by frantaylor
View Post
-
Sure, but I wasn't talking about full disks as in "no space left on device". I was talking about 80-90% full disks that lead to an I/O speed dropping to a few kilobytes per second. Not a very good thing to happen with hundreds of users doing stuff simultaniously on that disk. -
In all my years of computing I have never seen a system that exhibited robust behavior with full disks. Even with systems that are otherwise quite bulletproof, all bets are off when the disks fill. It's like expecting robust behavior from an airplane when it runs out of fuel in the middle of the sky.Leave a comment:
-
I'm really too lazy to read the whole thread so excuse me if I just don't know what you're flaming about. But it seems to me as if an example of someone switching from Solaris to Linux was searched for. Well, our department is currently doing this. Solaris had major issues with performance on very full disks, unbootable servers due to a zfs partition corrupted by Solaris, the Sun hardware itself also corrupted many files and the Sun support was more than lousy as far as I heard (of course Sun themselves called it "Platinum", not "lousy"). Maybe Sun isn't what it used to be.Leave a comment:
-
"Still, I already said everything about what you're babbling here :>"
Still Ive asked you to show one link, and you can not. Then please stop spreading FUD about Solaris or you are a liar. You do not consider yourself as a liar, I hope. So please stop FUDing about Solaris.Leave a comment:
-
You're still amazing me XD It seems you don't believe such bug exists:Originally posted by frantaylor View Post
because it ruins your entire theory :>Did you read the comments in the bug report?
"this bug has long past the point where it is useful.
There are far too many people posting with different issues.
There is too much noise to filter through to find a single bug.
There aren't any interested kernel developers following the bug."
It is not even a bug report, it is just a random flame fest
About this bug. Only some system configurations are affected (probably not so many, because I saw only one report at lkml about this issue). There's also workaround and some tuning helps some people.
@Kebbabert
Still, I already said everything about what you're babbling here :>
@Frantaylor
Will you be so kind to not quote his text next time please?Leave a comment:
-
If you look at his other posts you can see where he links to a devastating kernel bug that causes terrible performance issues. He knows full well that Linux has major issues and he just ignores them when he wants to make his argument. He is even worse than all the things you accuse him of.Originally posted by kebabbert View PostLeave a comment:
-
kraftman,
If you can not show any links about Solaris becomes unstable on large systems under large load, then you are a liar and FUDer just like that Matt Bryant thingie. You are just spreading FUD about Solaris. You dont know shit, and still you claim various things and "proves" them with irrelevant links.
You want to prove that Solaris becomes unstable on large systems under high load, and shows a link on a guy has problems installing ancient Solaris 8 on a desktop? What? Are you just weird or strange or a liar? Whenever I state something about Linux on large loads, I have shown several links. In fact there are many links on Linux not coping large load, including the one you posted. I dont make things up, nor do I FUD or lie. There are numerous testimonies about Linux having problems. I have showed several links where Linux kernel devs complain about the low Linux code quality - and you just refuse to consider those links. What? Are the Linux kernel devs lying?
Until you can prove any claim you have made, I will call you a FUDer and liar. You are spreading FUD about Solaris. There is no proof backing your claims up. There are no links showing that Solaris becomes unstable on large systems under high load - just as you claim.
kraftman, you are spreading FUD. And spreading lies, too.
But of course, if you can show ONE link, then you are not lying. Then you are telling the truth. Then I will apologize. But until then, you are a FUDer and liar.Leave a comment:
-
I've never ever seen an uptime percentage so low. The guys I know at the UPS datacenter (they use IBM mainframes) claim 99.9999% uptime.Originally posted by kebabbert View Post
The IT people at the NYSE lose their entire yearly bonus if their uptime drops to less than 99.99%. They use Linux, but it took a 15 year migration project to get off of HPUX. Even so they use way too much hardware and alarms go off if any machines have a load average of more than 0.1. They do not believe in putting any kind of a load on their machines, they are afraid of performance slowdowns. They know full well that Linux does not behave well under load.Leave a comment:
-
kraftman,
"Nope, difference is Linux doesn't becomes unstable, when Solaris does."
Ok, I challenge you to show at least ONE link that backs up your statement. Just one. Not two. But one. Go ahead. You will not find any such links.
Meanwhile you search, here are some links showing that Linux just doesnt cut it on large systems (not desktop, but large systems):
Here is a Linux company forced to switch to Solaris.
"The company's CEO, Joshua Rand, started the company with the free Fedora Linux distribution. That worked well enough for a small startup, but as business scaled, Fedora's effectiveness declined. So in 2005, Sapotek moved to a commercial version of Linux: Red Hat Enterprise Linux (RHEL).
After two years of trying to make RHEL work, Rand had to move on. He looked closely at Solaris 10 and, after speaking with Sun engineers about a possible migration, decided to give Sun's Startup Essentials program a try.
"Being Linux people, we were hesitant to switch," he said. "We didn't even consider [Microsoft] Windows, because we are open source," said Rand. "Sun set up some virtual servers for us to run tests, and we ported all of our apps onto those virtual servers. We did load testing, saw that it worked well and decided to go ahead with the migration."
Sapotek now runs Solaris 10 OS on Sun 4200 servers with 64-bit Advanced Micro Devices Inc. Opteron quad-core processors, along with Sun's x4500 storage unit.
The improvement is significant; with four compute nodes instead of five, Rand has more computing power and 99.99% uptime, compared with 97% uptime with RHEL, he said.
"With this switch, we've gone from playing in the sandbox to getting our doctoral degree. You can't even compare Red Hat GFS to Solaris ZFS," Rand said. "We no longer need to do all those chores we had to do with Linux. I can't even quantify the number of man-hours we freed by moving to Solaris. We have so much more time to develop our software now."
Another one:
You want more links? Just ask. Now, can you find ONE LINK showing Linux is more stable than Solaris on large systems? No you can not. Why can you not find such links? Is it because such links doesnt exist?
You claim lots of things but prove none. When you "prove" something, your links are just weird. One guy can not install ancient Solaris 8 on a PC - which shows that he had a missing device driver or something. That link doesnt show Solaris performance on large systems. Another link of yours showed a shitty 32 CPU machine with an artificial BENCHMARK. Not real work.
Come on, mr big mouth. Prove your claims. Show ONE link about Solaris on large systems. Do not show links on installation ancient Solaris 8. I really really wonder how you reason. Your arguments are flawed and your logic just strange. Not correct logic. Your links are strange, and doesnt prove any one of your points. You dont know how to prove things. "My cycle is stolen and I want to prove it by eating dinner up side down" - really really strange logic and reasoning.Leave a comment:
-
The TPC-C benchmark results touted in the linked article were run on Itanium, a very different architecture from the Intel architecture that the vast majority of Linux applications run on. Itanium was designed from the ground up for server performance, the results you get on it will not translate well to Intel or AMD systems.
The vast majority of the Itanium systems sold are HP boxes running HPUX or VMS or Tru64. Dell was selling Itanium Linux and Windows systems but they only sold a very few, so they gave up. SGI was selling them too, and we all know what happened to them.
Again, if these benchmark numbers meant anything, everyone would have rushed out and bought a nifty new Itanium machine. The only ones I ever see are in our lab.Leave a comment:
Leave a comment: