From: Arno on
calypso(a)fly.srk.fer.hr.invalid wrote:
> Arno <me(a)privacy.net> kenjka:
>> > Why are you referring to SSD drive and sequential writes? The main reason
>> > why SSD are used are their high IOPS values! OK, I am talking from the
>> > storage vendor perspective, and not from the home-user perspective...

>> I am talking sustained maximum write speed. Does not need to be
>> sequential, but it is the worst-case for the lifetime. Of course a lower
>> rate with small writes that still result in an effective write rate
>> (because of larger internal block size) of 200MB/s also hits this worst
>> case.

> But SSD's in any serious enviroments are never used for sequential writes...
> OLTP and similar enviroments need high IOPS, not MB/s... If you want MB/s,
> go with a big bunch of SATA drives, and you'll get very cheap MB/s
> performance...

You may have a combination of mostly sequential writes and under
some circumstances a lot of random reads. And yes, this can happen
in a serious environment as well although it requires a bit more
of a specual scenario.

>> So while your 150 years figure is certainly good to boost sales, it is
>> unusable to evaluate practical endurance. For that you need to look at the
>> particular worst case.

> 200MB/s is sequential read performance, and who knows what block size were
> used... I stay with the 150 years, cause it's my calculation for STEC
> ZeusIOPS drive used in EMC storage systems... So, here's the calculation:

> 400 * 10^9 * 100000 / 4000 / 2000 / 365 / 24 / 3600

> 400GB drive (400 * 10^9 Bytes)
> SLC technology (100.000 E/W cycles)
> 4000 (block size is 4kBytes)
> 2000 (average write IOPS)
> 365 (days per year)
> 24 (hours per day)
> 3600 (seconds per hour)

> The result is 158 years...

Ah, you assume writes fall into one block of 4kB and the disk
block size is 4kB. Then you have a write speed of 8MB/s and yes,
your number fits. I expect these are a bit more expensive ;-)

However mass-market SSDs have 128kB blocks or even larger
(not exposed to the OS). There you get much lower numbers.
An affordable SSD with 4kB block size would be nice in fact,
due to much better small write performance.

>> And there is a second problem. On power-fail a SSD can corrupt areas not
>> written to because of large internal block sizes. That means in
>> high-reliability applications you actually can only write it in a
>> sequential fashion and without filesystem as everything else is dangerous
>> to your data.

> Nope... At least not with drives I was working with... They all have 64MB
> cache that has battery backup... This can be a problem for SMB drives, but
> not for enterprise...

Well, if you have RAM fronted SSD, you are in a different class anyways.
I remember that some Linux Filesystem people are starting to worry
about this, because it can kill journalling. There are some ways
around the problem, but only if the SSD exposes the block size.
Or if you have enough money for the expensive stuff ;-)

> Sorry, but I am all into enterprise, and have totally lost touch with
> reality in the normal SMB market... :(

No problem. When you can really throw money at the problem, the
solutions look a bit different. Mass market can give you similar
performance and reliability a lot cheaper, but you have to go
some extra steps and really need to know what you are doing.

Arno
--
Arno Wagner, Dr. sc. techn., Dipl. Inform., CISSP -- Email: arno(a)wagner.name
GnuPG: ID: 1E25338F FP: 0C30 5782 9D93 F785 E79C 0296 797F 6B50 1E25 338F
----
Cuddly UI's are the manifestation of wishful thinking. -- Dylan Evans
From: Arno on
calypso(a)fly.srk.fer.hr.invalid wrote:
> Arno <me(a)privacy.net> kenjka:
[...]
>> No problem. When you can really throw money at the problem, the solutions
>> look a bit different. Mass market can give you similar performance and
>> reliability a lot cheaper, but you have to go some extra steps and really
>> need to know what you are doing.

> Well, my clients are buying, and are very affraid of SSD drives because of
> the problems visible in mass market... So I need to explain them that these
> SSD drives used in high-end equipment haven't got anything similar to mass
> market SSD drives... :)

Ah, I see your problem. And it explains your stance, which I
think is justified on the equipment you are selling. If anybody
ever asks you about consumer-grade SSDs, give them my figures ;-)

Well, as I do understand the technology, I typically go for
mass-market, but my main application for large disk storage
so far was research data which was backed up on an enterprise
class tape library as well, so not really critical.

Arno
--
Arno Wagner, Dr. sc. techn., Dipl. Inform., CISSP -- Email: arno(a)wagner.name
GnuPG: ID: 1E25338F FP: 0C30 5782 9D93 F785 E79C 0296 797F 6B50 1E25 338F
----
Cuddly UI's are the manifestation of wishful thinking. -- Dylan Evans
From: Lynn McGuire on
> Does anyone yet make a TB Flash memory in a 3.5" drive physical format. If
> so, could you pass on a reference? The interface would need to support
> about at a 400MB/s sustained rate. I can work with any interface such as
> Fiber Channel or whatever .

$3,799 at newegg for SATA (claimed 260 MB/s read and write):
http://www.newegg.com/Product/Product.aspx?Item=N82E16820227502

$3,799 at newegg for PCI express (claimed 600 MB/s write and
870 MB/s read ):
http://www.newegg.com/Product/Product.aspx?Item=N82E16820227500

Lynn
From: Ian D on

"David Brown" <david.brown(a)hesbynett.removethisbit.no> wrote in message
news:SfidnbOlH-Xzm-3WnZ2dnUVZ7tRi4p2d(a)lyse.net...
> Arno wrote:
>> trs80 <trs80(a)yahoo.com> wrote:
>>> Does anyone yet make a TB Flash memory in a 3.5" drive physical format.
>>> If so, could you pass on a reference? The interface would need to
>>> support about at a 400MB/s sustained rate. I can work with any
>>> interface such as Fiber Channel or whatever .
>>> thanks for any tips
>>
>> Nobody does and nobody gets that rate, not even for large accesses.
>> Although some manufacturers have SATA3 drives
>> planned with internal excessive multi channel architectures.
>> For small accesses FLASH can be significantly slower than
>> disks. For what you want, you may want to look at a traditional RAM
>> fronted disk. Will be expensive though and definitely
>> not available in 3.5". Alternatively you could build a RAID0 with a
>> really fast controller and FLASH disks. Arno
>>
>
> There are a number of very fast drives available, but the cost is
> significant - a raid would be much more cost-effective. The biggest
> single drive I found in a quick check was:
>
> <http://www.plianttechnology.com/lightning_ls.php>
>
> That's 300 GB in 3.5" SAS, rated at 525/340 MB/s.
>
> Of course, for the fastest devices you use a PCI Express card with RAM
> rather than flash...

The fastest and largest I have seen is the 1TB OCZ PCIe
SSD with read and write rates of 870MB/s and 780MB/s.
The part number is OCZSSDPCIE-ZDM841T, and the
price is a mere $4k approx.