Hitachi 7k1000.c 4x500gb raid 0 performance

[SinShiva]

thought this might make a good reference.

ICH10R chipset on the msi x58m mobo, i7 920@3.5ghz with 12gb of ddr3 1600

was hoping somebody with a similar setup using samsung f3's could post to compare?

the raid volume is 200gb with 64kb stripe size. write cache enabled

http://www.newegg.com/Product/Product.aspx?Item=N82E16822145299

those are the hdds i bought. the pricing is comparable to the 500gb samsung f3s, but the availability is much nicer

i took a chance, but knowing the 7k1000.c used 500gb platters was enough for me. i am rather pleased with this investment.

this is me in another forum, but the point stands. these hdds kick ass and more people need to know that the somewhat difficult to obtain samsung f3s are not the only option

 

[cjl]

Not bad, though that's short stroked as well (it's partitioned so that only the first 200GB is usable).

 

[SinShiva]

yep, i know.

i just can't get over the value/performance these hdds have. love em.

 

[SinShiva]

bump post, but i'm looking to find some sort of CCTL (TLER) utility for this here hitachi raid. running ich10r and matrix. somebody inquired as to whether or not i could mess with it and now i'd like to know myself.

 

[Pointertovoid]

Hitachi's doc is there
http://www.hitachigst.com/tech/techlib.nsf/techdocs/33586ADC145D59A086257603007B022E/$file/DS7K1000.C_DS_final.pdf
and this is nothing of a serious datasheet I was accustomed to from Hitachi.
No access time, no sustained throughput, nothing. Not even a number of heads. Datash*t.

From the platter density, it's clear that they hold 330GB at most, so I wouldn't choose a 500GB disk unless I'm sure it has 3 heads, not 4.

The random access measurement on the first 200GB can only be compared with 200GB on another disk or group. And anyway, as Hd Tach asks for a single sector, this figure is meaningless for a Raid. Raid increases access times for files split across several disks, making 7200rpm Raid slower than a single disk for OS and applications loading.

Only IOMeter, and to some extent Atto, are meaningful for Raid arrays. But you'll get nicer curves than Hd Tach with WinBench:
http://www.benchmarkhq.ru/english.html?/be_common.html
and possibly h2benchw:
http://www.heise.de/ct/ftp/ctsi.shtml
but h2benchw doesn't seem to access big disks fully, showing them deceivingly agile.

 

[Pointertovoid]

And I wrote a big nonsense just above, please forget.

Platter density is 500GB for the 7k1000c series. This explains the good contiguous read. And 500GB disk was well chosen, as would be multiples of 250GB.

Such mistakes wouldn't happen if Hitachi were still able of writing a datasheet. But at least, it seems that they can still build hard disks.

I found very few speed measurements; one in Japanese, and that doesn't hugely help me:
http://skyline798.blog118.fc2.com/blog-entry-1996.html
they find the 7k1000c a little bit less agile than the Seagate 7200.12 though in the same category.

But then, their measurement by HdTach and HdTune tells 19ms random access! Max stroke and minimum delay are just as bad. They probably had the AAM on, but then, was it active during CrystalDiskMark measures as well?

 

[watchforice]

http://www.hitachigst.com/tech/techlib.nsf/techdocs/39C078C9FA890225862576740063F8D1/$file/7K1000C_USA7K2000_1TB_OEMspec_1.0.pdf

261 page PDF has been there since 11/20/09.

Lists access time, throughput, # of heads, # of platters, and just about everything else.

Just bought 2 of these drives from Newegg for $39.99 ea. (Shellshocker) I'm installing them in RAID 0. Can't wait to see how they perform!