William L. Maltby wrote:
On Fri, 2006-10-13 at 11:44 -0400, Bowie Bailey wrote:
Kirk Bocek wrote:
<snip>
Right now, I am not looking for maximum performance. I am just trying to determine why there is a 3x difference in write performance between two identical machines.
60 vs. 40 conductor cables on UDMA? have you wiggled/reseated them?
These are SATA drives, but I have checked the cable connections.
PS sizes similar and simailar load?
Identical PS. Load should be similar. Tests have been done at runlevel 5 with nobody using the system.
/var/log/messages BogoMips the same?
I'm not familiar with this.
Mem config same?
Yep. They've both got 16GB of RAM (6GB allocated to Huge Pages and about 9GB free).
Same "load". Does top in a "long" screen show any diference in number of loads or total load being imposed? Keep an eye out for excessive wait channels in top (have to change defaults of fields displayed and order) or in ps?
I haven't seen that. I'll keep an eye on it next time.
Are you using the sar reports, which can be helpful in the case of large unknowns.
I haven't used the sar reports. Sar tends to be a bit cryptic. If you can give me a useful command line, I'll check it out.
Thanks!
On Mon, 2006-10-16 at 16:24 -0400, Bowie Bailey wrote:
William L. Maltby wrote:
On Fri, 2006-10-13 at 11:44 -0400, Bowie Bailey wrote:
Kirk Bocek wrote:
<snip>
WOW! Do I have a typo bug or what?
Right now, I am not looking for maximum performance. I am just trying to determine why there is a 3x difference in write performance between two identical machines.
60 vs. 40 conductor cables on UDMA? have you wiggled/reseated them?
s/60/80/
These are SATA drives, but I have checked the cable connections.
<snip>
/var/log/messages BogoMips the same?
I'm not familiar with this.
In /var/log/messages (and dmesg too, IIRC) is a "rating" of performance for the CPU. "BogoMIPS" is the name. Also in there is "Detected xxxx.x MHz processor". I was thinking if there is any substantial difference, maybe that is a clue.
E.g. if PS is weak, one of the processors may run slow. I just finished chasing some junk caused by a weak PS. AMD 2200+, s/b 1.8GHz, was running 1.38GHz.
Popped in a 575 watt (425 continuous) PS and all is good again.
Mem config same?
Yep. They've both got 16GB of RAM (6GB allocated to Huge Pages and about 9GB free).
In BIOS, same timings on memory (CAS, etc.)?
Same "load". Does top in a "long" screen show any diference in number of loads or total load being imposed? Keep an eye out for excessive wait channels in top (have to change defaults of fields displayed and order) or in ps?
I haven't seen that. I'll keep an eye on it next time.
Are you using the sar reports, which can be helpful in the case of large unknowns.
I haven't used the sar reports. Sar tends to be a bit cryptic. If you can give me a useful command line, I'll check it out.
It has been so long since I did admin jobs for real, I can't help you. But there's lots of strong admins here.
Guys/gals, help the man out here?
Thanks!
Sorry I can't be more help. I just acquired my first two SATA drives and have yet to install and start using them.
I just ran bonnie on a Dual-Core 3.4ghz machine w 2GB RAM and 2x120GB Seagate SATA HDD on 3Ware 8006 set as RAID 1 mirror. Ext3 FS. Second Machine is Intel 2.6ghz HT w/2GB RAM and 2X120GB Seagate SATA HDD - no 3Ware, no RAID. EXT 3.
/usr/local/bonnie/sbin/bonnie++ -d /bk1/iotest -s 10g -n 0 -b -f -u mail
output.txt
Version 1.03 ------Output------ --Input- --Block-- --Rewrite-- --Block-- --Seeks- Machine Size K/sec %CP K/sec %CP K/sec %CP K/sec %CP 3wRAID1 10G 35903 12 22456 5 58840 5 175.5 0 SATA 10G 30154 16 14094 5 42492 5 96.0 0
neither machine has any notable load 0.00 to 0.01 as they are both idle at the moment.
This doesn't seem stellar by what I'm seeing on the 9550 thread, but overall, without any tweaking, does this look reasonable?
Mike
-
Bowie Bailey -
Feizhou -
Mike -
William L. Maltby