Technology for Mortals

Update 7/14/2008 - Tomshardware redeems themselves with new flash versus hard drive energy efficiency tests

Lots of people are talking about Tomshardware’s latest claim that SSD (Solid State Disk) flash drives are less energy efficient than a conventional laptop hard drive.  The problem is that the analysis is fundamentally shoddy.

Tomshardware’s Patrick Schmid and Achim Roos claims that a computer with a SanDisk SSD5000 SSD drive doesn’t last as long as the same computer running a conventional Hitachi 7K200 2.5″ 7200 RPM hard drive.  We can pretty much throw this conclusion out the window because the SanDisk SSD5000 has a PEAK power consumption of 1 watt while the Hitachi 7K200 has an IDLE power consumption of 1.1 watt.  So even if we assume that the test they ran was so flawed that it forced the SanDisk to operate at PEAK and permitted the Hitachi to operate at IDLE, the computer running the SanDisk SSD should still consume less power.  But the Hitachi 7K200 actually has a PEAK power consumption of 3.2 watts so the odds are it consumed a lot more than 1.1 watt during the tests and the battery drain test run by Schmid and Roos are flawed.

It’s actually quite simple to explain how they might have botched the experiment.  The SSD drives are capable of far more performance especially when it comes to random access.  By having more storage IO performance, it’s very easy for the CPU and the rest of the system to work harder because they’re not idling as much waiting for data from the storage system.  Whenever you’re doing a batter drain test, you have to keep the variables in check.  The amount of work done by the two systems must be identical because cranking one system’s CPU to a higher utilization rate will easily cause it to consume more power and run the battery down.  The ideal test for a battery drain test is to play back a movie using popular movie formats and movie software.  This way, the computational workload on the CPU, graphics, and the storage system is identical across all the systems and you’re not unfairly stressing one system more than the other.

Schmid and Roos are so confident that they state “No, our results are definitely correct” and they have theories to explain why they’re think they’re right.  On hard drive power consumption, the Tomshardware duo explains that for sequential access, hard drives should “not require much more than the idle power” because the mechanical actuators aren’t jumping back and forth.  That’s an interesting hypothesis, too bad they never tested that theory before they exclaimed to the world that their conclusions are definitive.

Xbit Laboratories did test power consumption between idle, random access, and sequential access but they showed that this theory is wrong.  In fact, power consumption between random access and sequential access is almost identical and in some cases, sequential access actually consumed more power.  How can this be?  Well with random access, the hard drive is putting out maybe 1 Megabyte/second of data which isn’t very much work for the I/O (Input/Output) logic on the storage device.  With sequential access, the hard drive is putting out roughly 50 MB/sec which stresses the hell out of the IO logic on the hard drive.  This additional power consumption in the IO logic is enough to offset or even exceed the power consumed by the mechanical actuators.

However, Schmid and Roos proclaimed in bold subtitles that “Flash SSDs only Know Two Power States” and that SSDs are “active or idle”.  Oh really?  Is it possible they concluded this because they only tested two working states rather than testing three working states between idle, random access, and sequential access?  I’ve been looking and analyzing power consumption characteristics for a long time and I’ve never seen IO logic with only two power states.  IO logic like all microprocessors subtly increases in power consumption as you increase workloads.  Tomshardware would have you believe that an SSD would consume 0.5 watts in idle and immediately jump to 2.9 watts as soon as you throw any work at it.  So they’re claiming that an SSD pushing out data at 1 MB/sec would consume just as much power as it would at 100 MB/sec.  This is a preposterous hypothesis and it is laughable.

Tomshardware only tested “load” (whatever that means since they didn’t disclose methodology) and idle power consumption.  The problem is that they don’t factor in the fact that the SSDs are being forced to operate at above 100 MB/sec while the hard drive is only operating at around 50 MB/sec.  In fact if you divide their Megabyte/second measurements by the wattage (Joules/second) measurements, you can actually get the megabytes per joule (unit energy) number.  This is the number of megabytes transferred using a single joule of energy.  I made an assumption and used their average sequential throughput divided by load power measurements and produced the following table showing how much more efficient the flash drives are if you account for the amount of work being done.

The proper way to do this test is to run all the devices at equal throughput.  So you could simply play a DVD movie off the storage device at 1 MB/sec (8 megabits/sec) or an HDV stream at 3 MB/sec and measure the power consumption at these fixed storage workloads rather than assuming that the SSDs “only know two power states”.

The purpose of my analysis is not to say you should buy SSD drives for your laptop.  I simply abhor bad science and bad analysis especially when it gets taken seriously.  I’m actually not a big proponent of SSD drives in laptops yet because the economics aren’t there *YET* and the power consumption difference isn’t that great.

At this point in time, SSDs make sense for submarine duty in the US Navy where silence means survival.  It might also make sense in ultraportable laptops where you don’t need that much capacity and the SSD saves space and some power.  Companies like MSI are actually opting out of SSDs for their 10 inch “Wind” notebook because of the additional storage capacity and the power savings aren’t all that compelling.  SSDs also make sense for server duty where random access performance is extremely important.

The reality is that the average SSD drive doesn’t save all that much power compared to a conventional 2.5″ hard drive and it’s quite possible that some 2.5″ hard drives are more energy efficient than some SSDs.  But the analysis and conclusions drawn by Tomshardware are not to be taken seriously.

My former colleague Adrian Kingsley-Hughes pondered whether it was feasible to rip (to digitally archive) his entire DVD collection in to a computer.  Adrian estimates that he has at least 600 DVDs and that each would take 30 minutes to rip which works out to 12.5 days of non-stop ripping.  So I popped Adrian an instant message telling him that it’s actually nowhere near as bad and that it could be done 6 DVDs at a time and each batch would probably take no more than 15 minutes which works out to 25 hours of solid ripping time.  After chatting for about an hour, I think Adrian was fairly convinced that this was more than feasible and that perhaps he would even attempt it.

But how would you actually build such a machine?  A key consideration is that you never want to use PATA interface optical drives configured as master/slave because of severe performance problems for ripping or burning DVDs.  The other problem is that it’s difficult to hook up 6 PATA drives is the difficulty in wiring those thick or wide PATA cables and motherboards don’t come with 6 PATA ports.  But this is an easy problem to solve because many of the newer Intel P35-chipset motherboards have 8 SATA II ports which allows you to easily connect many hard drives and optical drives.

Adrian and I pondered some hardware options and Adrian suggested the “Sharkoon Rebel 12″ full ATX tower chassis he sourced from the UK, the ICY DOCK MB455SPF-B 5 in 3 Multi Bay, and an Adaptec 1430SA 4-port SATA II RAID controller.  I found the Sabrent SBT-SRD4 PCI 4-port SATA I controller for $60 and since SATA I is probably 10 times faster than what you need for an optical drive and we don’t need RAID, I suggested the cheaper option.

I also suggested that this DVD ripping station would be an awesome storage NAS (Network Attached Storage) box as well as an awesome HTPC (Home Theater PC) and gaming system all at the same time.  This not only saves you money because you don’t need to build multiple solutions, but it saves on energy costs since this is a low-power machine.  It also has the ability to burn 5 or 6 DVDs at a time which allows you to quickly make multiple copies of your kids school recital to hand out or hold on as backups.

I have put together two build lists.  The first is a 5-drive ripping/burning station with 3.75 TB of storage that also serves as an HTPC computer.  The second is the ultimate 5 TB NAS, HTPC, Gaming, Ripping/Burning PC that can be built at an affordable price.  Given the fact that the average DVD requires about 6 GBs of storage, the first configuration will store 625 DVDs and the second will store 833 DVDs.  The 5 TB solution can also store around 8000 CDs uncompressed.  If you want to record TV programming at 5 Mbps, the 5 TB system will let you store 2,222 hours of programming.  If you want to record over-the-air HD programming at 15 Mbps, the 5 TB system will let you store 740 hours of programming.

Note: You are free to mix and match or substitute your own preferences in hardware but if you’re not sure about something, stick with the exact build list.

To rip 6 DVDs at the same time, simply fire up 6 copies of “ DVD Decrypter “.  Since DVD Decrypter was discontinued in 2005 in response to a legal threat, it may not work on some of the latest DVD titles.  I would suggest putting those in a separate but small pile and use a commercial DVD ripper or look at the DVD backup guides on Doom9.org .  My friend Charles recommends using the AnyDVD commercial middleware that makes DVD Decrypter work for any DVD and that it’s worth the 40 Euros.

Is DVD Ripping legal?  According to Wikipedia entry on DVD Decrypter

“In the noted “321″ case, Federal District Judge Susan Illston, of the Northern District of California [6], ruled that the backup copies made with software such as DVD Decrypter are in fact legal but that distribution of the software used to make them is illegal . As of the date of this revision, neither the US Supreme Court nor the US Congress has taken definitive action on the matter.”