Re: Help with improving mysql performance on 6.2PRE

2006-10-14 Thread Eric Hodel
On Oct 13, 2006, at 1:13 PM, Kris Kennaway wrote: On Fri, Oct 13, 2006 at 11:49:04AM -0700, Chuck Swiger wrote: On Oct 13, 2006, at 11:26 AM, Eric Hodel wrote: Or did that change recently? It's only on certain systems, apparently. Is there a list of systems where it is safe to use the TSC w

Re: Performance 4.x vs. 6.x

2006-10-14 Thread NOC Meganet
On Saturday 14 October 2006 15:05, Mike Horwath wrote: > > I would say this preference is mostly set by beeing afraid of > > migration (lots of things can come up when migrating a production > > server) or by lack of money to buy some nasty HW ... > > Ah, hardware bigotry.  Your colors are showing.

Re: Performance 4.x vs. 6.x

2006-10-14 Thread NOC Meganet
On Saturday 14 October 2006 17:13, Danial Thom wrote: > The fact that a processor has 2 cores doesn't > mean you have to use them, just like a MB with 2 > sockets doesn't need both to be used. If the OS > is faster with 1 processor than 2, then you only > use one of the cores. The concept that you

Re: Help with improving mysql performance on 6.2PRE

2006-10-14 Thread Jerry Bell
I will do some testing tonight with variations in the my.cnf file and post the results tomorrow. > At 03:20 PM 10/6/2006, Jerry Bell wrote: >>I have actually made the changes to my.cnf before I ran these. I >> expanded >>them quite a bit beyond what is in my-large.cnf. I need to pull them >> bac

Re: Performance 4.x vs. 6.x

2006-10-14 Thread Mike Horwath
On Sat, Oct 14, 2006 at 01:30:02PM -0700, Danial Thom wrote: > You should try the new 10K WD drives (the ones that just came > out). They kick butt. Unfortunately, I'd have to use FreeBSD 6 to > use them, so I have to stick with SCSI on 4.x to get maximum > performance. You are so completely wron

Re: Performance 4.x vs. 6.x

2006-10-14 Thread Danial Thom
--- Mike Horwath <[EMAIL PROTECTED]> wrote: > On Sat, Oct 14, 2006 at 11:13:24AM -0300, NOC > Prowip wrote: > > Hi, I am hooking in here without any > intention to fire things up but > > isn 't this discussion certainly useless? Not > only 4.11 is gone but > > also i386 is practically marked to

Re: Performance 4.x vs. 6.x

2006-10-14 Thread Danial Thom
--- NOC Prowip <[EMAIL PROTECTED]> wrote: > > > Linux 2.6 is not suitable for uniprocessor, > nor > > is FreeBSD 6. The difference is that Linux > scales > > with MP, and FreeBSD doesn't. So the case to > keep > > 4.x as an option is an easy one to make. > > > > > Hi, I am hooking in here wit

Re: Performance 4.x vs. 6.x

2006-10-14 Thread Danial Thom
The fact that a processor has 2 cores doesn't mean you have to use them, just like a MB with 2 sockets doesn't need both to be used. If the OS is faster with 1 processor than 2, then you only use one of the cores. The concept that you have to fire up both of them just because they're there is just

Re: Performance 4.x vs. 6.x

2006-10-14 Thread Mike Horwath
On Sat, Oct 14, 2006 at 06:22:23PM +0200, Robert Joosten wrote: > Hi, > > > but I tell you that a 10K Raptor is faster then a 15K 320Mb SCSI when > > compiling world or untarring large files. > > Well, put that '10K Raptor' in a loaded fileserver and compare it > with a SCSI thing. Most scsi imp

Re: Performance 4.x vs. 6.x

2006-10-14 Thread Mike Horwath
On Sat, Oct 14, 2006 at 01:13:27PM -0300, NOC Prowip wrote: > On Saturday 14 October 2006 12:38, Mike Horwath wrote: > > On Sat, Oct 14, 2006 at 11:13:24AM -0300, NOC Prowip wrote: > > > Hi, I am hooking in here without any intention to fire things up but > > > isn 't this discussion certainly usel

Re: Performance 4.x vs. 6.x

2006-10-14 Thread Robert Joosten
Hi, > but I tell you that a 10K Raptor is faster then a 15K 320Mb SCSI when > compiling world or untarring large files. Well, put that '10K Raptor' in a loaded fileserver and compare it with a SCSI thing. Most scsi implementations I know are much more scalable when there's a realworld load suc

Re: Performance 4.x vs. 6.x

2006-10-14 Thread NOC Prowip
On Saturday 14 October 2006 12:38, Mike Horwath wrote: > On Sat, Oct 14, 2006 at 11:13:24AM -0300, NOC Prowip wrote: > > Hi, I am hooking in here without any intention to fire things up but > > isn 't this discussion certainly useless? Not only 4.11 is gone but > > also i386 is practically marked t

Re: Performance 4.x vs. 6.x

2006-10-14 Thread Mike Horwath
On Sat, Oct 14, 2006 at 11:13:24AM -0300, NOC Prowip wrote: > Hi, I am hooking in here without any intention to fire things up but > isn 't this discussion certainly useless? Not only 4.11 is gone but > also i386 is practically marked to die out as well as UP systems > are. Wow, I hope not. Unles

Re: Performance 4.x vs. 6.x

2006-10-14 Thread NOC Prowip
> Linux 2.6 is not suitable for uniprocessor, nor > is FreeBSD 6. The difference is that Linux scales > with MP, and FreeBSD doesn't. So the case to keep > 4.x as an option is an easy one to make. > Hi, I am hooking in here without any intention to fire things up but isn 't this discussion cert

Re: Performance 4.x vs. 6.x

2006-10-14 Thread Danial Thom
Unfortunately, the "certain tasks" are squid, apache and networking applications, which are the only viable reasons to use the OS commercially. I've yet to hear 1 (thats *one*) commercial vendor who built a product on 4.x claim to move to 5 or 6 because of its superior performance. The only ones I