In my presentations in Australia and New Zealand, I mentioned that people were re-discovering the benefits of removable media. While floppy diskettes were convenient way of passing information from one person to another, they unfortunately did not have enough capacity. In today's world, you may need Gigabytes or Terabytes of re-writeable storage with a file system interface that can easily be passed from one person to another. In this post, I explore three options.

Cirago CDD2000 Docking Station

The good folks over at [Cirago International Ltd.] sent me a cute little [CDD2000 docking station] for evalution.

(FCC Disclaimer: I work for IBM, and IBM has no business relationship with Cirago at the time of this writing. Cirago has not paid me to mention their product, but instead provided me a free loaner that I promised to return to them after my evaluation is completed. This post should not be considered an endorsement for Cirago's products. List prices for Cirago and IBM products were determined from publicly available sources for the United States, and may vary in different countries. The views expressed herein may not necessarily reflect the views and opinions of either IBM or Cirago.)

I took a few photos so you can see what exactly this device looks like. Basically, it is a plastic box that holds a single naked disk drive. It has four little rubber feet so that it does not slip on your desk surface.

The inside is quite simple. The power and SATA connections match those of either a standard 3.5 inch drive, or the smaller form factor (SFF) 2.5 inch drive. However, to my dismay, it does not handle EIDE drives which I have a ton of. After taking apart six different computer systems, I found only one had SATA drives for me to try this unit out with.

The unit comes with a USB cable and AC/DC power adapter. In my case, I found the USB 3.0 cable too short for my liking. My tower systems are under my desk, but I like keeping docking stations like this on the top of the desk, within easy reach, but that wasn't going to happen because the USB cable was not long enough.

Instead, I ended up putting it half-way in between, behind my desk, sitting on another spare system. Not ideal, but in theory there are USB-extension cables that probably could fix this. Here it is with the drive inside. I had a 3.5 inch Western Digital [1600AAJS drive] 160 GB, SATA 3 Gbps, 8 MB Cache, 7200 RPM.

To compare the performance, I used a dual-core AMD [Athlon X2] system that I had built for my 2008 [One Laptop Per Child] project. To compare the performance, I ran with the drive externally in the Cirago docking station, then ran the same tests with the same drive internally on the native SATA controller. Although the Cirago documentation indicated that Windows was required, I used Ubuntu Linux 10.04 LTS just fine, using the flexible I/O [fio] benchmarking tool against an ext3 file system.

• Sequential Write - a common use for external disk drive is backup.
• Random read - randomly read files ranging from 5KB to 10MB in size.
• Random mixed - randomly read/write files (50/50 mix) ranging from 5KB to 10MB in size.

Workload	Metric	Internal	External
Sequential Write	Throughput IOPS	1119	1044
	Latency (msec)	0.866 ms	0.948 ms
	Bandwidth (KB/s)	16900	14400
Random Read	Throughput (IOPS)	164	119
	Latency (msec)	6.06 ms	8.36 ms
	Bandwidth (KB/s)	658	477
Random Mixed (50/50)	Throughput (IOPS)	112	81
	Latency (msec) read	8.78 ms	12.1 ms
	Latency (msec) write	0.0983 ms	0.120 ms
	Bandwidth (KB/s) read	557	328
	Bandwidth (KB/s) write	556	337

For sequential write, the Cirago performed well, only about 15 percent slower than native SATA. For random workloads, however, it was 30-40 percent slower. If you are wondering why I did not get USB 3.0 speeds, there are several factors involved here. First, with overheads, 5 Gbps USB 3.0 is expected to get only about 400 MB/sec. My SATA 2.0 controller maxes out at 375 MB/sec, and my USB 2.0 ports on my system are rated for 57 MB/sec, but with overheads will only get 20-25 MB/sec. Most spinning drives only get 75 to 110 MB/sec. Even solid-state drives top out at 250 MB/sec for sustained activity. Despite all that, my internal SATA drive only got 16 MB/sec, and externally with the Cirago 14 MB/sec in sustained write activity.

Here is the mess that is inside my system. The slot for drive 2 was blocked by cables, memory chips and the heat sink for my processor. It is possible to damage a system just trying to squeeze between these obstacles.

However, the point of this post is "removable media". Having to open up the case and insert the second drive and wire it up to the correct SATA port was a pain, and certainly a more difficult challenge than the average PC user wishes to tackle.

Price-wise, the Cirago lists for $49 USD, and the 160GB drive I used lists for $69, so the combination $118 is about what you would pay for a fully integrated external USB drive. However, if you had lots of loose drives, then this could be more convenient and start to save you some money.

IBM RDX disk backup system

Another problem with the Cirago approach is that the disk drives are naked, with printed circuit board (PCB) exposed. When not in the docking station, where do you put your drive? Did you keep the [anti-static ESD bag] that it came in when you bought it? And once inside the bag, now what? Do you want to just stack it up in a pile with your other pieces of equipment?

To solve this, IBM offers the RDX backup system. These are fully compatible with other RDX sytems from Dell, HP, Imation, NEC, Quantum, and Tandberg Data. The concept is to have a docking station that takes removable, rugged plastic-coated disk-enclosed cartridges. The docking station can be part of the PC itself, similar to how CD/DVD drives are installed, or as a stand-alone USB 2.0 system, capable of processing data up to 25 MB/sec.

The idea is not new, about 10 years ago we had [Iomega "zip" drives] that offered disk-enclosed cartridges with capacities of 100, 250 and 750MB in size. Iomega had its fair share of problems with the zip drive, which were ranked in 2006 as the 15th worst technology product of all time, and were eventually were bought out by EMC two years later (as if EMC has not had enough failures on its own!)

The problem with zip drives was that they did not hold as much as CD or DVD media, and were more expensive. By comparison, IBM RDX cartridges come in 160GB to 750GB in size, at list prices starting at $127 USD.

IBM LTO tape with Long-Term File System

Removable media is not just for backup. Disk cartridges, like the IBM RDX above, had the advantage of being random access, but most tape are accessed sequentially. IBM has solved this also, with the new IBM Long Term File System [LTFS], available for LTO-5 tape cartridges.

With LFTS, the LTO-5 tape cartridge now can act as a super-large USB memory stick for passing information from one person to the next. The LTO-5 cartridge can handle up to 3TB of compressed data at up to SAS speeds of 140 MB/sec. An LTO-5 tape cartridge lists for only $87 USD.

The LTO-5 drives, such as the IBM [TS2250 drive] can read LTO-3, LTO-4 and LTO-5cartridges, and can write LTO-4 and LTO-5 cartridges, in a manner that is fully compatible with LTO drives from HP or Quantum. LTO-3, LTO-4 and LTO-5 cartridges are available in WORM or rewriteable formats. LTO-4 and LTO-5 cartridges can be encrypted with 256-bit AES built-in encryption. With three drive manufacturers, and seven cartridge manufacturers, there is no threat of vendor lock-in with this approach.

These three options offer various trade-offs in price, performance, security and convenience. Not surprisingly, tape continues to be the cheapest option.

technorati tags: IBM, Cirago, CDD2000, RDX, Ubuntu, Linux, LTO, LTO-5, LTFS, SATA, USB, fio

Continuing my discussion of this week's announcements of IBM storage products, I will cover the announcements that double storage capacity per footprint.

Linear Tape Open - Generation 5

IBM announced [LTO-5 drives], the TS2250 half-height and the TS2350 full-height drives, as well as support for LTO-5 drives in its various tape libraries: TS3100, TS3200, and TS3500. The native 1.5TB capacity of the LTO-5 cartridge is nearly double the 800GB capacity of the LTO-4 predecessor. With 2:1 compression, that's 3TB of data per cartridge! Performance-wise, the data transfer rate is 140 MB/sec, about 17 percent improvement over the 120MB/sec of the LTO-4 technology. The TS2250, TS2350, TS3100 and TS3200 now all offer dual-SAS ports for higher availability.

LTO-5 carries forward many of the advancements of past generations. For example, LTO-5 continues the G-2/G-1 "backward compatibility" architecture, which means that the LTO-5 drive can read LTO-3 and LTO-4 cartridges, and can write LTO-4 cartridges. Like the LTO-3 and LTO-4, the same LTO-5 drive can read and write WORM or regular rewriteable cartridges. Like the LTO-4, the LTO-5 offers drive-level data-at-rest encryption. These use a symmetric 256-bit AES key, managed by IBM Tivoli Key Lifecycle Manager (TKLM).

One thing that is new in LTO-5 is the Long Term File System [LTFS] available on the TS2250 and TS2350, which allows you to treat the tape as a hierarchical file system, with files and folders, that you can drag and drop like any other file system.

XIV storage system

IBM [doubles the capacity of the XIV storage system] by supporting 2TB SATA drives. A full 15-module frame can hold up to 161TB of usable capacity. The smallest 6-module system with 2TB can hold up to 55TB of usable capacity. At this time, all of the drives in an XIV must be the same type, so we do not yet allow intermix of 1TB and 2TB in the same frame. The 2TB are more energy efficient, with a full 15-module frame consuming on average 6.7 kVA, compared to 7.8 kVA for the 1TB drives. The performance is roughly the same, so if, for example, your application workload got 3700 IOPS per module with 1TB drives, it will get about the same 3700 IOPS per module with 2TB drives.

TS7650 ProtecTIER Data Deduplication

IBM now supports [many-to-one virtual tape volume mirroring] on the ProtecTIER. In other words, you can have two or more locations sending data to a single ProtecTIER disaster recovery site.

N series disk system

The EXN1000 and EXN3000 can now double in capacity with 2TB SATA drives. These can be attached to the N3000 entry-level models, such as the N3400.

DS3000 disk system

The DS3200, DS3300 and DS3400, as well as their related expansion drawers, now supports 2TB SATA drives. This means that a single control unit with three expansion drawers can hold up to 96TB of raw capacity (48 drives).

DS8700 disk system

The DS8700 also now supports 2TB SATA drives, for a maximum raw capacity over 2PB, as well as new 600GB Fibre Channel drives. Now that IBM offers [Easy Tier] functionality, pairing Solid State Drives with slower, energy-efficient SATA disk makes a lot of financial sense.

That's a lot of announcements! As always, feel free to dig into each of the links to learn more about each product.

technorati tags: IBM, LTO-5, TS2250, TS2350, TS3100, TS3200, TS500, AES, TKLM, LTFS, XIV, 2TB, TS7650, TS7650G, EXN1000, EXN3000, N3400, DS3200, DS3300, DS3400, DS8700, SATA

Continuing my series of posts on the IBM Storage launch of February 9, I cover some new disk options.

IBM System Storage DCS9900

The DCS9900 uses a 4U enclosure to hold 60 (that's sixty, SIX-ZERO) drives! Normally, hot-swapable drives face the front or back surface of the rack, but these surfaces are valuable "real estate", so instead, the drives stick downward into a tray that rolls out, giving you full access to access any of the drives. The DCS9900 added support for 2TB (7200 RPM) SATA drives, and 600GB (15K RPM) SAS drives. The systems use ten-pack RAID-6 ranks, 8+2P.

(If this sounds a lot like the newly announced SONAS product, it should! The two products share "DNA", and so can be considered sister products, packing 60 drives into a 4U enclosure. By comparison, the SONAS initially only supports 1TB SATA in RAID-6 ten-packs 8+2P, and 450GB SAS in RAID-5 ten-packs 8+P+S, but now that 2TB SATA and 600GB SAS drives have been qualified for the DCS9900, we hope to qualify these for the SONAS soon as well.)

Learn more about the DCS9900 from the IBM [Press Release].

IBM System Storage DS3000 series

The DS3000 adds support for 600GB SAS drives. Here is the IBM [Press Release].

IBM System Storage N series

IBM adds support for 600GB FC and 600GB SAS drives for the entire N series from the smallest N3000 series to the largest N7000 series. Here is the IBM [Press Release].

Next week, I'll continue to chip away, bit by bit, at this huge storage launch.

technorati tags: IBM, DCS9900, RAID-6, RAID-5, SAS, SATA, FC, SONAS, DS3000, N3000, N6000, N7000

Continuing my coverage of last week's Data Center Conference 2009, my last breakout session of the week was an analyst presentation on Solid State Drive (SSD) technology. There are two different classes of SSD, consumer grade multi-level cell (MLC) running currently at $2 US dollars per GB, and Enterprise grade single-level cell (SLC) running at $4.50 US dollars per GB. Roughly 80 to 90 percent of the SSD is used in consumer use cases, such as digital cameras, cell phones, mobile devices, USB sticks, camcorders, media players, gaming devices and automotive.

While the two classes are different, the large R&D budgets spent on consumer grade MLC carry forward to help out enterprise grade SLC as well. SLC means there is a single level for each cell, so each cell can only hold a single bit of data, a one or a zero. MLC means the cell can hold multiple levels of charge, each representing a different value. Typically MLC can hold 3 to 4 bits of data per cell.

Back in 1997, SLC Enterprise Grade SSD cost roughly $7870 per GB. By 2013, Consumer Grade 4-bit MLC is expected to be only 24 cents per GB. Engineers are working on trade-offs between endurance cycles and retention periods. FLASH management software is the key differentiator, such as clever wear-leveling algorithms.

SSD is 10-15 times more expensive than spinning hard disk drives (HDD), and this price difference is expected to continue for a while. This is because of production volumes. In 4Q09, manufacturers will manufacturer 50 Exabytes of HDD, but only 2 Exabytes of SSD. The analyst thinks that SSD will only be roughly 2 percent of the total SAN storage deployed over the next few years.

How well did the audience know about SSD technology?

• 4 percent not at all
• 30 percent some awareness
• 30 percent enough to make purchase decision
• 21 percent able to quantify benefits and trade-offs
• 15 percent experts

SSD does not change the design objectives of disk systems. We want disk systems that are more scalable and have higher performance. We want to fully utilize our investment. We want intelligent self-management similar to caching algorithms. We want an extensible architecture.

What will happen to fast Fibre Channel drives? Take out your Mayan calendar. Already 84mm 10K RPM drives are end of life (EOL) in 2009. The analyst expects 67mm and 70mm 10K drives will EOL in 2010, and that 15K will EOL by 2012. A lot of this is because HDD performance has not kept up with CPU advancements, resulting in an I/O bottleneck. SSD is roughly 10x slower than DRAM, and some architectures use SSD as a cache extension. The IBM N series PAM II card and Sun 7000 series being two examples.

Let's take a look at a disk system with 120 drives, comparing 73GB HDD's versus 32GB SSD's.

There are various use cases for SSD. These include internal DAS, stand-alone Tier 0 storage, replace or complement HDD in disk arrays, and as an extension of read cache or write cache. The analyst believes there will be mixed MLC/SLC devices that will allow for mixed workloads. His recommendations:

• Use SSD to eliminate performance and throughput bottlenecks
• Consolidate workloads to maximize value
• Use SLAs to identify workload candidates
• Evaluate emerging technologies along with established vendors
• Do not expect SSD to drastically reduce power/cooling
• SSD will continue to complement HDD, primarily SATA disk
• Trust but verify, check out customer references offered by storage vendors

technorati tags: ssd, hdd, das, mlc, slc, sata, fc, disk systems