Intel X25-E Extreme SSD Benchmarks On Linux
Phoronix: Intel X25-E Extreme SSD Benchmarks On Linux
In early January we had delivered Linux Solid-State Drive Benchmarks of an OCZ Core Series V2 SSD, which was a low-cost low-capacity single-cell drive. The increased performance and decreased power consumption compared to a 5400RPM Serial ATA 2.0 hard drive was nice for a netbook, but how are the higher-end solid-state drives performing? In this article, we have a high-performance Intel X25-E Extreme SSD on a System76 notebook running Ubuntu Linux.
Too expensive for normal people who need big storage capacity. I wonder in how many years SSDs will drop to the price of today's HDs and totally replace them. Probably too many :P
It didn't occur to you that the encoding benchmarks might be CPU-limited, as opposed to disk limited?
More to the point, you made no mention of the common issues surrounding SLC Flash SSDs: re-write speed. The performance of single-level cell flash, when re-writing, is hideous.
Actually in a shoot out between the current NEBS certifiable (Telecom grade...needs to be about as abusable as the mil-spec stuff...) drives from Samsung, Intel, and the magnetic drives we have in hand- the rewrite performance wasn't anywhere near as hideous as everyone'd been led to believe. I can't share the details (Tektronix confidential info...sigh...) but we'd almost had upper management and product management sold on this generation. Still just a bit too expensive yet because they don't believe in the reliability story- they're still hung on the "disk" being in the name and that means the same thing as the magnetics in their mind.
Originally Posted by tomm3h
Not as many as one would think if Micron's actually pulling together their line like the word going around would indicate. We won't know until a couple of months from now whether that's the case or not, but it is worth noting that the drive Michael Larabel reviewed here is an SLC drive and as such is going to be smaller and much, much more expensive. $550 is the rough price for a slightly slower SLC NEBS Level 3 certifiable 64Gb drive from Samsung right at the moment- we priced them out and I almost got product management to sign off on them this go round for our replacement for magnetic disks.
Originally Posted by RealNC
Uhhm... I'm pretty sure there's no way you were able to read from the drive with ~370 MB/s when Intel themselves advertises the read speed with 250 MB/s (that's almost the half! ). (refering to the IOzone 4GB Read Performance).
You are probably just writing to cache (at least partialy). I think you should look into possibilities to disable the cache if you want to accurately measure the SSD-performance.
Bad SSD benchmark
Too many non-ssd related tests and thereby uninteresting graphs! What about running tests designed to expose some of the problems with today's ssd? I'm talking about OCZ's sucky IOPS and things like that..
The cache on SSDs is minimal and irrelevant. A typical cache size is something like 64KB. When it comes to SSDs, data is typically written directly to the drive itself. It's entirely possible to reach the numbers quoted under ideal circumstances.
Originally Posted by Zhick
My main concern with the article is that the benchmarks are a bunch of compression and encryption tasks, followed by some synthetic tests. Hardly representative of "real world" stuff. Also, there was no mention of the proper things that need to be done to get maximum performance out of the drive, like aligning partitions and setting proper block sizes, among other things. Sure, the Intel drives don't suffer from the same "hesitation" as most of the lower-cost drives on the market, but that doesn't mean it wouldn't improve performance to set the drive up properly.
Another interesting thing would've been a discussion of filesystems that are geared directly to SSDs, but that was never mentioned either.
This Intel SSD's supposedly do not suffer from the random writes problem most other SSD's seem to have; it would have been interesting to see some tests with this SSD vs HDD vs the other SSD that was tested some time ago to confirm/disprove that this SSD doesn't suffer from latency troubles.
Any chance of seeing boot times in the next test? Please