Yes. thanks for correction Jeremie ;)
Jeremie Le Hen wrote:
Hi, Gustavo,
In my first post in this thread, there are some numbers for connections
from localhost, but using TCP instead of socket.
For the sake of accuracy, sockets are either TCP or Unix (and maybe
other kinds). Thus you mean
Hi, Gustavo,
> In my first post in this thread, there are some numbers for connections
> from localhost, but using TCP instead of socket.
For the sake of accuracy, sockets are either TCP or Unix (and maybe
other kinds). Thus you meant "..., but using TCP socket instead
of Unix socket".
Regards
On Friday, 9 December 2005 at 8:23:26 +0800, David Xu wrote:
> Greg 'groggy' Lehey wrote:
>
>> I've heard this claim again and again, and I intend to look at it when
>> I have time. I find it difficult to believe that this alone could
>> explain the sometimes horrendous performance differences (
Greg 'groggy' Lehey wrote:
I've heard this claim again and again, and I intend to look at it when
I have time. I find it difficult to believe that this alone could
explain the sometimes horrendous performance differences (3 to 1) that
have been reported.
Can somebody tell me:
1. How many cal
On Friday, 2 December 2005 at 13:23:50 +1100, Michael Vince wrote:
> It would be good to actually see the Linux performance on the exact same
> hardware, all we ever see is how it is on FreeBSD.
>
> MySQL has very frequent use of queries of the system time and is
> well known in FreeBSD to be slow
It would be good to actually see the Linux performance on the exact same
hardware, all we ever see is how it is on FreeBSD.
MySQL has very frequent use of queries of the system time and is well
known in FreeBSD to be slower because its more expensive to call
compared to Linux, which has less p
OTECTED]>
Cc:
Sent: Thursday, December 01, 2005 11:09 AM
Subject: Re: new benchmarks. WAS: FreeBSD MySQL still WAY slower than Linux
On Thu, 1 Dec 2005 10:58:43 -0800
"Gustavo A. Baratto" <[EMAIL PROTECTED]> wrote:
The numbers are roughly the same with HTT disabled. For example for
> ---
>
>
> For linuxthreads and libpthread, the numbers are all within the same margin
> as the other post as well.
>
> Cheers
>
>
> - Original Message -
> From: "Xin LI" <[EMAIL PROTECTED]>
> To: "Gustavo A. Bara
o A. Baratto" <[EMAIL PROTECTED]>
Cc:
Sent: Wednesday, November 30, 2005 9:24 PM
Subject: Re: new benchmarks. WAS: FreeBSD MySQL still WAY slower than Linux
Hi,
On 12/1/05, Gustavo A. Baratto <[EMAIL PROTECTED]> wrote:
[snip]
DMESG:
--
Features2=0x4400>
Hyperthreadi
Hi,
On 12/1/05, Gustavo A. Baratto <[EMAIL PROTECTED]> wrote:
[snip]
> DMESG:
> --
> Features2=0x4400>
> Hyperthreading: 2 logical CPUs
Would you have a try of disabling HTT? It harms performance for
certain applications.
Cheers,
--
Xin LI <[EMAIL PROTECTED]> http://www.delphij.n
I would just like to finish my own thoughts on the thread I created here
for the sakes of other people who may be googling up this mailing list
thread in the future and judging performance on this particular
benchmark method.
I just wanted to point out that this benchmark test is using 50
sim
Update:
Switched threading libraries from libpthread to libthr and now I'm getting
27,500 selects/sec at 45% idle. This is with version 4.1.12 of mysql using
myISAM tables compiled with the following options
WITHOUT_INNODB
BUILD_OPTIMIZED
relevant parts of my.cnf:
# The MySQL server
[mysqld]
po
On Wed, 29 Jun 2005, Jeremie Le Hen wrote:
Could you try mounting the filesystem where the database lives with
the noatime option, and re-run your tests ? IIRC from previous threads
on this subject, Linux doesn't really honor this while FreeBSD does,
which pulls down the performances.
I think
I just tried this on my dual opteron test rig and didn't notice a difference
in performance with noatime set. What did make a difference was moving from
fxp to bge network cards. bge supports checksum offloading where fxp only
supports interrupt bundling. Freed up another 20% idle during my test ru
At 01:33 PM 29/06/2005 +0100, Robert Watson wrote this to All:
On Thu, 23 Jun 2005, Steve Roome wrote:
The different threading libraries are more for completeness. In my last
test I saw <10% difference between them on amd64.
Well, I finally got some tests out for FreeBSD/i386 with -current,
On Thu, 23 Jun 2005, Steve Roome wrote:
The different threading libraries are more for completeness. In my
last test I saw <10% difference between them on amd64.
Well, I finally got some tests out for FreeBSD/i386 with -current, Here
we go with a bunch of results of FreeBSD 6 with mysql and
Hi Michael, hi Steve,
> For me this is as fast as I need my database to be but I can understand
> there is a difference here between FreeBSD and Linux that would make you
> prefer it as the db OS choice.
Could you try mounting the filesystem where the database lives with
the noatime option, and
I tried some benchmark testing on a Dell 1850 5.4-Release-P2 with
generic kernel.
From what I have seen from your postings I was able to get a higher
supersmack result, 23626.76 .
I compiled 4.0 MySQL with some optimizations
portupgrade -RN -m 'BUILD_STATIC=yes BUILD_OPTIMIZED=yes'
/usr/ports/d
Martin Nilsson wrote:
Steve Roome wrote:
Sorry, good point, here's the my.cnf we're using. Please note however
that although the configuration may not be optimal, we have been using
the same config for benchmarking on Linux also. No matter how broken
this my.cnf is we still shouldn't find MySQ
Steve Roome wrote:
Sorry, good point, here's the my.cnf we're using. Please note however
that although the configuration may not be optimal, we have been using
the same config for benchmarking on Linux also. No matter how broken
this my.cnf is we still shouldn't find MySQL running half the speed
On Sun, Jun 26, 2005 at 12:06:41AM +1000, Michael Vince wrote:
> Your posting a lot of configuration here except the most easily
> important one for performance in MySQL, thats your my.cnf configuration file
> You will more then double your performance if you just start off by copying
> /usr/local
itchell
Cc: 'Michael Vince'; 'Steve Roome'; [EMAIL PROTECTED]
Subject: Re[2]: FreeBSD MySQL still WAY slower than Linux
Nemam dobru naladu Shawn,
Saturday, June 25, 2005, 7:26:22 PM, si odoslal:
I tested a MySQL install on a Dell 6600. It's specs were 8 GB ra
[EMAIL PROTECTED]
Subject: Re[2]: FreeBSD MySQL still WAY slower than Linux
Nemam dobru naladu Shawn,
Saturday, June 25, 2005, 7:26:22 PM, si odoslal:
> I tested a MySQL install on a Dell 6600. It's specs were 8 GB ram, 12 x
73
> 15k rpm drives (Ultra320) on a RAID5, 4 Xeon MP w/ 2 m
On Saturday 25 June 2005 11:06, Michael Vince wrote:
> configuration file You will more then double your performance if
> you just start off by copying /usr/local/share/mysql/my-large.cnf
you are very fast with your conclusions ...
I am not a system engineer but
IMO it is not as easy as you sa
Nemam dobru naladu Shawn,
Saturday, June 25, 2005, 7:26:22 PM, si odoslal:
> I tested a MySQL install on a Dell 6600. It's specs were 8 GB ram, 12 x 73
> 15k rpm drives (Ultra320) on a RAID5, 4 Xeon MP w/ 2 meg of cache, HT
> enabled so the OS saw 8 CPU's.
> Every time, a stock linux install (S
05 9:07 AM
To: Steve Roome
Cc: [EMAIL PROTECTED]
Subject: Re: FreeBSD MySQL still WAY slower than Linux
Your posting a lot of configuration here except the most easily
important one for performance in MySQL, thats your my.cnf configuration file
You will more then double your performance if you just star
Your posting a lot of configuration here except the most easily
important one for performance in MySQL, thats your my.cnf configuration file
You will more then double your performance if you just start off by copying
/usr/local/share/mysql/my-large.cnf
to
/var/db/mysql
MySQL out of the box setup
Oops, here's what I was supposed to attach to the email with test results in it.
Sorry about that,
Steve Roome
/etc/make.conf
WITHOUT_X11=yes
Oops, here's what I was supposed to "attach" to the email with test
results in it.
Sorry about that,
Steve Roome
/etc/make.conf
WITHOUT_X11=y
On Mon, Jun 20, 2005 at 10:51:30AM -0400, David Sze wrote:
> This is what I'll be trying:
>
> FreeBSD/amd64 4.11-RELEASE, linuxthreads
> FreeBSD/amd64 5.4-RELEASE, libpthread
> FreeBSD/amd64 5.4-RELEASE, libpthread, process scope
> FreeBSD/amd64 6.0-CURRENT, libpthr
On Mon, June 20, 2005 10:51 am, David Sze said:
>
> I'll be re-running super-smack against an InnoDB table. Any additional
> requests for configurations to test, or other tweaking suggestions?
Any chance you could compare performance on MySQL 4.0 and 4.1 while you're
at it?
_
On Mon, Jun 20, 2005 at 04:08:45PM +0100, Robert Watson wrote:
>
> I realize every additional variation increases the testing load, but I'd
> be interested in seeing linuxthreads performance on 5.x/6.x also. While
> we've worked hard to improve native threading, linuxthreading remains
> fully
On Mon, 20 Jun 2005, David Sze wrote:
I'll be re-running super-smack against an InnoDB table. Any additional
requests for configurations to test, or other tweaking suggestions?
This is what I'll be trying:
FreeBSD/amd64 4.11-RELEASE, linuxthreads
FreeBSD/amd64 5.4-RELEASE, lib
At 04:59 PM 19/06/2005 +0100, Robert Watson wrote this to All:
BTW, could you run 'file' on the Linux and FreeBSD MySQL binaries and
confirm that they're both either 32-bit i386 binaries, or 64-bit amd64
binaries?
I can no longer run tests on the machine because it's in production, but I
wil
On Fri, 17 Jun 2005, David Sze wrote:
FreeBSD/amd64 5.4-RELEASE (libpthread, system and process scope)
FreeBSD/amd64 6.0-CURRENT (libpthread, libthr, system and process
scope)
CentOS/amd64 4.0 (i.e. RHEL4.0)
I couldn't get libthr to work on FreeBSD/amd64 5.4-RELEASE, mys
I moved this thread to -performance as that's entirely what it's about
now and we seem not to care which version of freebsd we'll try out.
Thanks for your comments on this, rather than write you an essay (I
just deleted that) here's the results I've just got from trying this
with vmstat and iostat
36 matches
Mail list logo
