Workstation I/O Efficiency
In this benchmark, we measure workstation I/O performance while tracking power consumption during the workload. Finally, we calculate performance by watt, dividing I/O operations per second by the average power used.
As expected, the workstation I/O performance of Intel’s new X25-E flash SSD dominates all of the competition. It is nine times as fast as an Mtron Pro 7500, which also is a professional product that was intended for servers and workstations. While the 15,000 RPM hard drives still did well when compared to the Samsung and Mtron SSDs, the X25-E outclasses them.
The 15,000 RPM hard drives required 17.1 W and 18.5 W of average power during the workstation I/O benchmark; Intel’s X25-E was at only 1.1 W on average. Let’s look at performance per Watt now.
Low power combined with maximum performance results in mind-boggling efficiency figures for the new X25-E server SSD by Intel. Whether you like the product or not, the X25-E provides the workstation performance of fifteen 15,000 RPM hard drives at 1/16 of their power requirement. We don’t dare to think of the total power requirements of 15 hard drives!
Related Stories :
- OCZ Says Its New Vertex SSD Beats Intel's X25-E
- Intel’s X25-E SSD Walks All Over The Competition
- Intel Adds 80GB Model to SSD 335 Series
- Intel SSD 525 Review: Five mSATA Drives, From 30 To 240 GB
- Report: Intel's Ivy Bridge-E CPUs Will Launch Sept. 2013
- Intel Adds New Capacity, Case Design to SSD 335 Series
- Intel SSD DC S3700 Review: Benchmarking Consistency
- Intel Pushing 550 MB/s mSATA Speeds with SSD 525 Series
- Unofficial Benchmarks Show Intel Core i7-4960X Ivy Bridge-E Performing 10% Faster Than i7-3970X
- Intel Launches the Atom Z2420 E-20 Smartphone in Egypt
Recently, I've seen an article about performance degradation in the X25-M due to internal fragmentation, have you looked into if this also applies to the X25-E?
hard drive makers will be scratching their heads on this one. i've read some social networking and dating sites that uses around 200 to 600GB only of data.
Your previous review was of another flash-based product, the ioDrive from Fusion-io. If only you had included it's benchmarks in this article's figures, it would have been a most interesting shootoff. Any chance of updating the charts? Or do I just have to flip back and forth between the two articles?
Your previous review was of another flash-based product, the ioDrive from Fusion-io. If only you had included it's benchmarks in this article's figures, it would have been a most interesting shootoff. Any chance of updating the charts? Or do I just have to flip back and forth between the two articles?
I agree right after I clicked on this article the first thing I thought is I wonder how this compairs to the IODrive form IOFusion.
.... and a costs/performance chart with maybe total yearly costs with drive price, watt etc.. maybe even say something about the raid hardware you'll be able to save.
nice article though, good to see that for (rich) consumers the X25-M is the right choice.
So when can we expect Tom's to upgrade their servers with Intel X-25E's so that we can truly experience this amazing drive in real time???
I have one of these going into my new server I'm building actually. We'll eventually raid 4 of them. Should be a nice addition to the 4x Quad-core Shanghai's.
Your previous review was of another flash-based product, the ioDrive from Fusion-io. If only you had included it's benchmarks in this article's figures, it would have been a most interesting shootoff. Any chance of updating the charts? Or do I just have to flip back and forth between the two articles?
That's coming, probably next week, in a head-to-head between the two!
omg walks over the competition?
fusion-IO has over 100000 IO operations in the same benchmark as where this intel reaches ~6000...
don't believe me? read the IOdrive review. it utterly crushes the intel, the Mtron and all other SSD's, not to mention normal hard drives
I think you may have another bottleneck in your configuration. I have been able to get 250MB sustain read from both my MLC and SLC drives.
Could it be that the Nocona platform's chipset is limited on bandwith with its SATA connections? By the way I was refering to the Intel MLC and SLC.
That's coming, probably next week, in a head-to-head between the two!
Can you please include cost compassion? I am trying to figure out that for the same $$ which gives me a better value. So if I had $10,000 which would be a better buy.
Besides theoretical numbers, I haven't read anything about the real-world life-expectancy of these drives in workstations and/or high-volumn servers.
Can you please include cost compassion? I am trying to figure out that for the same $$ which gives me a better value. So if I had $10,000 which would be a better buy.
Area, the piece is already written, but I'll check to see if there's a discussion on cost.
Usually I'd say who cares about power consumption, but it actually makes sense in this article! An extra couple watts for a desktop becomes much much more in a server full of drives.
One thing I'd like to see is some sort of mainstream desktop hard drive in there purely for sake of comparison. Throw a Caviar blue in the mix or something - with just these benchmarks, I find it difficult to get a sense of the performance gap between these drives and the one in my desktop.
But good article guys, lots of data.
TEST THE PERFORMANCE OF THE DRIVES AT CERTAIN % POINTS - EMPTY, 20% 50% 70% AND 99% - the performance changes from what i hear - would love to know the results
Intel SSD's - making your porn load quicker!
When looking at power efficiency one should compare equal setups and I see power usage of storage of 32GB compared against up to 450GB here. One will need 14 of the smaller SSDs to hold the same data as one HD. Where does this comparo account for this?
When looking at power efficiency one should compare equal setups and I see power usage of storage of 32GB compared against up to 450GB here. One will need 14 of the smaller SSDs to hold the same data as one HD. Where does this comparo account for this?
When looking at power efficiency one should compare equal setups and I see power usage of storage of 32GB compared against up to 450GB here. One will need 14 of the smaller SSDs to hold the same data as one HD. Where does this comparo account for this?