Sidebar Sidebar
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.

What do your hard disks score on xbench?

6 x 1TB WD Blacks. Hightpoint 4322 controller, RAID 0

Results 617.08
System Info
Xbench Version 1.3
System Version 10.4.11 (8S2167)
Physical RAM 8192 MB
Model MacPro1,1
Drive Type HPT DISK 0_0
Disk Test 617.08
Sequential 383.30
Uncached Write 212.63 130.55 MB/sec [4K blocks]
Uncached Write 1261.81 713.93 MB/sec [256K blocks]
Uncached Read 228.65 66.91 MB/sec [4K blocks]
Uncached Read 1764.48 886.81 MB/sec [256K blocks]
Random 1581.94
Uncached Write 571.29 60.48 MB/sec [4K blocks]
Uncached Write 2206.56 706.40 MB/sec [256K blocks]
Uncached Read 8474.08 60.05 MB/sec [4K blocks]
Uncached Read 4832.41 896.69 MB/sec [256K blocks]
 
hyram said:
Code: 
Results	617.08	
	System Info		
		Xbench Version		1.3
		System Version		10.4.11 (8S2167)
		Physical RAM		8192 MB
		Model			MacPro1,1
		Drive Type		HPT DISK 0_0
	Disk Test	617.08	
		Sequential	383.30	
			Uncached Write	212.63	130.55 MB/sec [4K blocks]
			Uncached Write	1261.81	713.93 MB/sec [256K blocks]
			Uncached Read	228.65	66.91 MB/sec [4K blocks]
			Uncached Read	1764.48	886.81 MB/sec [256K blocks]
		Random	1581.94	
			Uncached Write	571.29	60.48 MB/sec [4K blocks]
			Uncached Write	2206.56	706.40 MB/sec [256K blocks]
			Uncached Read	8474.08	60.05 MB/sec [4K blocks]
			Uncached Read	4832.41	896.69 MB/sec [256K blocks]
Click to expand...

Wow! What a difference a controller makes! Sweet!
 
Tesselator said:
Here's my RAMDisk:
Code: 
Results	906.19	
	System Info		
		Xbench Version		1.3
		System Version		10.5.7 (9J61)
		Physical RAM		12288 MB
		Model			MacPro1,1
[U]		Drive Type		Apple read/write RAM-Drive[/U]

	[U]Disk Test	[B]906.19[/B]	[/U]
		Sequential	553.47	
			Uncached Write	415.27	254.97 MB/sec [4K blocks]
			Uncached Write	1242.03	702.74 MB/sec [256K blocks]
			Uncached Read	282.08	82.55 MB/sec [4K blocks]
			Uncached Read	2132.99	1072.02 MB/sec [256K blocks]
		Random	2498.42	
			Uncached Write	1195.78	126.59 MB/sec [4K blocks]
			Uncached Write	2303.16	737.33 MB/sec [256K blocks]
			Uncached Read	8109.22	57.46 MB/sec [4K blocks]
			Uncached Read	4825.48	895.40 MB/sec [256K blocks]
Click to expand...

what are using to make this RAM disk. Terminal or an app like Make RAM Disk?

Also how are you using the RAM disk

I posted a thread a while back about the benefits of using a RAM disk, but most people seemed to think it was a waste of time as OSX utilises unused RAM effieciently
 
hyram said:
Results 617.08
System Info
Xbench Version 1.3
System Version 10.4.11 (8S2167)
Physical RAM 8192 MB
Model MacPro1,1
Drive Type HPT DISK 0_0
Disk Test 617.08
Sequential 383.30
Uncached Write 212.63 130.55 MB/sec [4K blocks]
Uncached Write 1261.81 713.93 MB/sec [256K blocks]
Uncached Read 228.65 66.91 MB/sec [4K blocks]
Uncached Read 1764.48 886.81 MB/sec [256K blocks]
Random 1581.94
Uncached Write 571.29 60.48 MB/sec [4K blocks]
Uncached Write 2206.56 706.40 MB/sec [256K blocks]
Uncached Read 8474.08 60.05 MB/sec [4K blocks]
Uncached Read 4832.41 896.69 MB/sec [256K blocks]
Click to expand...


That is SICK. TOTALLY SiCK!

Give us more!!

However you're failure rate is exponential :eek:
 
sparkie7 said:
what are using to make this RAM disk. Terminal or an app like Make RAM Disk?

Also how are you using the RAM disk

I posted a thread a while back about the benefits of using a RAM disk, but most people seemed to think it was a waste of time as OSX utilises unused RAM effieciently
Click to expand...

I'm using Esperance DV 2.3.2 that I got from here: http://www.macupdate.com/info.php/id/16518

Someone told me that PS CS4 Extended loaded in 1 second from an SSD and I didn't believe it. So I downloaded this app, created a 2GB drive, installed CS4 on it and gave it a try with something that is 4 times faster than an SSD and is the more's law equivalent. Needless to say loading a properly configured PS CS4 in anything close to 1sec. is an impossibility but that's why I have it and what I'm currently using it for. PS is still installed on it after several reboots and I was even able to shrink it's size down closer to PS's needs - which for me is 800MB. :)

As for the naysayers saying RAM Disks such as this aren't fast just look no further than the benchmark. How useful it is depends on you of course. This particular one only supports sizes up to 2GB I think so that's a little limited. There may be other warez or methods to make larger sizes I dunno. Have you tried the shell script method? How's that? And lastly they may be right about the efficiency. The way that OS X handles the system cache it will at first anyway essentially be in ram twice. And maybe three times (depending how you look at it) at least temporarily.

Anyway, it's your system. Do what you want and don't let others talk you out of it. You'll know soon enough if it's something good for you. If it's not just remove it. :)

sparkie7 said:
However you're failure rate is exponential :eek:
Click to expand...

That's a bit of a myth. You know?

.
 
sparkie7 said:
That is SICK. TOTALLY SiCK!

Give us more!!

However you're failure rate is exponential :eek:
Click to expand...


I know... it's only temporary. I'll pick up 2 more drives this week and convert it to RAID 5. I'll post those results when I have them

hyram
 
hyram said:
Results 617.08
System Info
Xbench Version 1.3
System Version 10.4.11 (8S2167)
Physical RAM 8192 MB
Model MacPro1,1
Drive Type HPT DISK 0_0
Disk Test 617.08
Sequential 383.30
Uncached Write 212.63 130.55 MB/sec [4K blocks]
Uncached Write 1261.81 713.93 MB/sec [256K blocks]
Uncached Read 228.65 66.91 MB/sec [4K blocks]
Uncached Read 1764.48 886.81 MB/sec [256K blocks]
Random 1581.94
Uncached Write 571.29 60.48 MB/sec [4K blocks]
Uncached Write 2206.56 706.40 MB/sec [256K blocks]
Uncached Read 8474.08 60.05 MB/sec [4K blocks]
Uncached Read 4832.41 896.69 MB/sec [256K blocks]
Click to expand...

There must be some cache effect at work here... for example, a single WD Black will score under 1MB/s on random 4k reads, but here the array is scoring 60MB/s which is not just 6 times a single drive but 60 times! :confused:

There are some cases where Xbench seems to fall short of being an accurate benchmarking tool and this is perhaps one. At any rate, I expect 6 WD Blacks in HW RAID0 would rock just as this suggests! :eek:
 
VirtualRain said:
There must be some cache effect at work here... for example, a single WD Black will score under 1MB/s on random 4k reads, but here the array is scoring 60MB/s which is not just 6 times a single drive but 60 times! :confused:
Click to expand...

That's classical RAID0. As the number of volumes increase access times decrease and at the same time throughput is increased, The affects compound and scores like this are achieved. You can see this more clearly if you look at detailed samplings from 1, 2, 3, 4, 5, and then 6 drive RAID's benchmarks and compare them. I've been up to 4 on the MP. He's got a card so he can go to 6 (or 8?) if he wants. :) There's documents on-line that take it up to 8. Very informative. The effects this has on the user's experience are immediately apparent.
 
Tesselator said:
That's classical RAID0. As the number of volumes increase access times decrease and at the same time throughput is increased, The affects compound and scores like this are achieved. You can see this more clearly if you look at detailed samplings from 1, 2, 3, 4, 5, and then 6 drive RAID's benchmarks and compare them. I've been up to 4 on the MP. He's got a card so he can go to 6 (or 8?) if he wants. :) There's documents on-line that take it up to 8. Very informative. The effects this has on the user's experience are immediately apparent.
Click to expand...
Yup. And once a user figures out the best stripe size for their specific usage, it gets better. ;)
 
It's a option setting in Apple's Software Raid Scheme:

blocksize.jpg


I believe it's the chunk size. :)
 
WD Velociraptor:

Wish I knew more about setting up RAIDs, but it's quickie enough for me. :)
 

Attachments

  • Picture 1.png
    Picture 1.png
    78.8 KB · Views: 415
How much can I gain if I put my two 500GB seagates into Raid0 ? (both score 85).

I can then get a 1GB drive for time machine :D
 
Thanks, that looks great! Is that with a raid card? If so which one?

Also, can you notice any difference in everyday use?
 
msmth928 said:
Thanks, that looks great! Is that with a raid card? If so which one?

Also, can you notice any difference in everyday use?
Click to expand...

You don't need a RAID card for RAID0. OSX has great software RAID support that scales well.

As for noticing a difference... this is a subject of great debate. In my opinion, it will make a subtle difference... more obvious with reading/writing large files. However, the greatest benefit is gaining a larger effective volume from smaller disks translating into less juggling of storage tasks between drives.
 
msmth928 said:
Thanks, that looks great! Is that with a raid card? If so which one?
Click to expand...

No. It's using Apple's disk utility. As an FYI, you can use SoftRAID and many seem to like it very much. For more info, you can refer to Lloyd's guide http://www.macperformanceguide.com/Storage-RAID.html

msmth928 said:
can you notice any difference in everyday use?
Click to expand...

I'm not a Graphics/Video person (plain business user), but for me I do see the difference moving/opening large files back and forth and running certain apps (hosting VM image files and running my VM's off the RAID 0 drive).

The different would be much more significant if you were rendering and/or dealing with massive PSD files and etc.
 
Just be aware.

Setting up your system with a RAID0 (whether Soft or Hard RAID) doubles the chances of data loss. Simply because there's twice as many things which can go wrong, double the chances of something failing. Remember, if one of the HD's fail, you'll automatically lose the data on BOTH hard drives.

Therefore, RAID0 in my opinion is best used as a fast scratch disk, where the data isn't so important, as the actual file is stored on another drive.

For safety I would strongly advise you to make backups of everything, regularly. At least once a week.
 
Thanks for the info all. :apple:

I'd only do it after getting another HD for time machine back ups. At the mo one of the 500GB drives is being used for time machine, but with HDs so cheap these days I might just get a 1TB drive and put these two in Raid0 as they are a pair.
 
msmth928 said:
Also, can you notice any difference in everyday use?
Click to expand...

Yes, you will immediately notice the difference. Your mac will over all feel as tho it got a speed injection. No one can not notice the difference unless they're asleep at the helm. At 3-Drive RAID0 the difference is in the OMG category. At 4 and above you will be picking up your jaw until you get used to it and start taking it for granted.
 
More RAID tests

You guys caught me at the right time as I'm in process of building and testing my RAID. Heres another test, but this time with 8x1TB TD Blacks in RAID0. As expected, a 25% improvement over my 6 disk configuration.

Results 782.31
System Info
Xbench Version 1.3
System Version 10.4.11 (8S2167)
Physical RAM 8192 MB
Model MacPro1,1
Drive Type HPT DISK 0_0
Disk Test 782.31
Sequential 556.89
Uncached Write 523.52 321.43 MB/sec [4K blocks]
Uncached Write 1351.34 764.59 MB/sec [256K blocks]
Uncached Read 250.32 73.26 MB/sec [4K blocks]
Uncached Read 1859.92 934.78 MB/sec [256K blocks]
Random 1314.34
Uncached Write 462.74 48.99 MB/sec [4K blocks]
Uncached Write 1830.93 586.15 MB/sec [256K blocks]
Uncached Read 8434.01 59.77 MB/sec [4K blocks]
Uncached Read 4596.27 852.87 MB/sec [256K blocks]

I ran the same test again, but this time with the cache turned off:

Results 237.62
System Info
Xbench Version 1.3
System Version 10.4.11 (8S2167)
Physical RAM 8192 MB
Model MacPro1,1
Drive Type HPT DISK 0_0
Disk Test 237.62
Sequential 164.49
Uncached Write 606.62 372.45 MB/sec [4K blocks]
Uncached Write 322.96 182.73 MB/sec [256K blocks]
Uncached Read 57.56 16.85 MB/sec [4K blocks]
Uncached Read 454.58 228.47 MB/sec [256K blocks]
Random 427.82
Uncached Write 321.00 33.98 MB/sec [4K blocks]
Uncached Write 560.49 179.43 MB/sec [256K blocks]
Uncached Read 455.11 3.23 MB/sec [4K blocks]
Uncached Read 443.85 82.36 MB/sec [256K blocks]

The affect of caching is significant.

Below is how it looks to Black Magic Speed test. As I don't really intend to run as RAID0 It's currently building RAID5. It'll take about a day, I'll post results when I have them.

hyram
 

Attachments

  • wd_test_raid0_cache_on.jpg
    wd_test_raid0_cache_on.jpg
    121.9 KB · Views: 114
  • wd_test_raid0_cache_off.jpg
    wd_test_raid0_cache_off.jpg
    118.3 KB · Views: 96
hyram said:
Random 427.82
Uncached Write 321.00 33.98 MB/sec [4K blocks]
Uncached Write 560.49 179.43 MB/sec [256K blocks]
Uncached Read 455.11 3.23 MB/sec [4K blocks]
Uncached Read 443.85 82.36 MB/sec [256K blocks]

The affect of caching is significant.
Click to expand...

Yes, this is more consistent with what I would expect from a multi-drive stripe of magnetic disks on this benchmark.
 
You must log in or register to reply here.
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.
Top Bottom
Back