• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

My new raid setup, benchmarks

T

Teecee

Gawd
2FA
Joined
May 31, 2005
Messages
948
I just wanted to post the results of my new raid setup. I purchased two WD raptor 150GB 10k rpm drives and two Seagate 320GB 7200.10 drives. The raptors I have running raid 0 and the seagates are running raid 1. I can tell a HUGE difference running from my Diamond Max to my raptors.

Here are the raptors.
wd.jpg


and the seagates.
seagate.jpg
 
Wow, that's quite the difference over my non-raided 150GB Raptor and 320GB 7200.10:

WD Raptor 150GB on SATA150
HDTach_Raptor_150GB_S150.png


Seagate 7200.10 320GB on SATA300
HDTach_7200.10_320GB_S300.png


I'll post pics of my 4*320GB 7200.10 RAID5 Array once my vid card for the server gets here in the mail.
 
Would love to see those results of the RAID5. I am thinking about hooking up one full of 320gb 7200.10. I also disabled NCQ on both raids. That did give me a boost in performance.

Shame the raptors are not SATA2.
 
Teecee said:
Would love to see those results of the RAID5. I am thinking about hooking up one full of 320gb 7200.10. I also disabled NCQ on both raids. That did give me a boost in performance.

Shame the raptors are not SATA2.
Click to expand...

why? the sata1 bus cant even be saturated
 
protias said:
why? the sata1 bus cant even be saturated
Click to expand...
Yes, it can, but not by a single modern drive ;)

Teecee: you're pretty severely limited in STR by your pci-bus-based raid controller. This is probably a big deal for you, since you did the research and decided that slightly higher seek times and approximately doubled STRs were worth it. Find a different controller (you may have two onboard - try the other one, or check a block diagram) using a faster bus for an instant performance boost in your video editing stuff. Which is, of course, what you're doing with the system?

 
silvermk3: you are my hero for posting pngs. It appears that few people understand when to use which compression algorithm :) Thanks.

to Teecee:
How did you manage to get a 900MB/s burst rate?
 
System is still working great and really fast. I am glad I moved to raptor raid 0. Will do it with my next system as well. To answer your question, This is a gaming pc. I just use it for gaming mainly. My next system I am going to redo the hard drives will be my "server" that I use for video editing and things like that.
 
drizzt81 said:
silvermk3: you are my hero for posting pngs. It appears that few people understand when to use which compression algorithm :) Thanks.
Click to expand...
Hehe, lossless compression for teh win!1

Hmmm. Comparing the Average Read speed on my Raptor compared to everyone else's makes me cry a little inside :(
 
SilverMK3 said:
Hehe, lossless compression for teh win!1

Hmmm. Comparing the Average Read speed on my Raptor compared to everyone else's makes me cry a little inside :(
Click to expand...


I didnt expect there to be a big difference either but I was wrong.
 
EQTakeOffense said:
I'm confused by that as well :confused:
Click to expand...


Not sure. I will run it again and see if I get the same results. This was after a brand new install with none of the dialy computer junk installed yet and a fresh defrag.
 
drizzt81 said:
How did you manage to get a 900MB/s burst rate?
Click to expand...

Seems to be a bug/quirk in HDTach -- it shows up erratically. Considering that the OP's interface limited at PCI bus speed, it's nonsense here.

Edit: On second thought, it just looks like a PCI bus limitation; being an nVIDIA stripe, it shouldn't be PCI. Not sure why it's capping like that.
 
how do you get so high? mine is at 100 average, and the burst is on the bottom? I have raid 0, 2 raptors 36gig, SATA. updadted.Slicon drivers at 32k stripe
 
Dethman said:
how do you get so high? mine is at 100 average, and the burst is on the bottom? I have raid 0, 2 raptors 36gig, SATA. updadted.Slicon drivers at 32k stripe
Click to expand...
if you're asking me

Highpoint 2320
5 x 7200.10 RAID5
 
teecee said:
Would love to see those results of the RAID5.
Click to expand...

Here's my 3 x 7200.10 in RAID5 on a Highpoint 1740:

HDTach_3x7200.10_RAID5_HPT1740.png


I'll see how much of an effect adding another drive has soon. I have to move everything over then use OCE to merge the fourth disk into the array.
 
Looking at the other screenshots in this thread, does a flat response up until the very end indicate that performance is being capped by another subsystem (PCI bus, I would assume)?

Because I also see ~90-95% CPU & Kernal usage when I'm writing to the array... Am I CPU limited as well? Memory usage is minimal
 
Looking at the other screenshots in this thread, does a flat response up until the very end indicate that performance is being capped by another subsystem (PCI bus, I would assume)? Because I also see ~90-95% CPU & Kernal usage when I'm writing to the array... Am I CPU limited as well?
Click to expand...
Exactly.
 
You must log in or register to reply here.
Back
Top