The Intel Optane Memory M10 (64GB) Review: Optane Caching Refreshed
by Billy Tallis on May 15, 2018 10:45 AM EST- Posted in
- SSDs
- Storage
- Intel
- PCIe SSD
- SSD Caching
- M.2
- NVMe
- Optane
- Optane Memory
AnandTech Storage Bench - Light
Our Light storage test has relatively more sequential accesses and lower queue depths than The Destroyer or the Heavy test, and it's by far the shortest test overall. It's based largely on applications that aren't highly dependent on storage performance, so this is a test more of application launch times and file load times. This test can be seen as the sum of all the little delays in daily usage, but with the idle times trimmed to 25ms it takes less than half an hour to run. Details of the Light test can be found here. As with the ATSB Heavy test, this test is run with the drive both freshly erased and empty, and after filling the drive with sequential writes.
The data rates on the Light test show clear signs of a cold cache on the first run, with substantially improved performance for the second and third runs. The 32GB cache module is still a bit small for this test and it can only bring the data rates up to about the level of a SATA SSD, but the 64GB and 118GB modules allow for performance that almost matches low-end NVMe SSDs like the MyDigitalSSD SBX (and without the capacity limitations or steep performance drop when full).
With a warmed-up cache, the Optane Memory M10 64GB and the larger Optane SSD 800P offer better average and 99th percentile latency than SATA SSDs. The 118GB cache beats the SATA drives even with a cold cache. The 32GB Optane Memory is well behind the SATA SSD even with a warm cache, especially for 99th percentile latency. But even so, all of these cache configurations easily beat running on just a hard drive.
The effects of a cold vs. warm cache show up quite clearly on the average read latency chart, but naturally have minimal effect on the average write latencies. It is clear that the 32GB Optane Memory's overall latency fell behind that of the SATA SSD almost entirely because of poor write performance: with a warm cache, the read latency of the 32GB module is slower than that of its larger siblings but is still an improvement over the SATA SSD.
The 99th percentile read latency scores emphasize the impact of a cold cache more than the average latency, especially for the 64GB cache module. Even the 118GB cache lags behind the SATA SSD on the first run. The 99th percentile write latencies are larger in absolute terms than the average write latencies, but the relative differences are almost all the same except that the hard drive stands out even more.
Facebook
Twitter
RSS
96 Comments
View All Comments
TrackSmart - Tuesday, May 15, 2018 - link
People seem to be talking around each other in these threads, without actually reading the substance of each person's reply.Dr. Swag didn't mention ONLY using a 500GB SSD. Just the opposite. He/she was suggesting that you could use a 500GB SSD for both a boot drive AND a 64GB cache drive. So you end up with ~440GB of normal SSD space (enough for most programs) AND a ~60GB cache drive to speed up your HDD accesses. All for the same price as adding a 64GB optane drive.
Addressing Dr. Swag's actual comment: I partially agree. One downside to the arrangement you suggested is that most affordable SSDs have lower write endurance than cache drives. They are also likely to be slower than an optane drive (but still fast compared to HDDs). And if your SSD boot/cache all-in-one drive dies, you might lose data on both the SSD and the HDD.
Regarding WithoutWeakness: Your comment makes sense if you are accessing the same subset of data over-and-over again. But if you are accessing a block of data ONCE to run an analysis and then moving onto a new block of data, then you will experience HDD speeds. Same goes for the first access to the data in cases where you will be using it multiple times. Slow the first time, faster in future times. So the downsides of a small cache will remain in a number of scenarios.
I personally think that Intel missed the boat with Optane. These solutions would have been a lot more convincing when SSD storage was a lot more expensive (i.e. 5+ years ago) and before other caching options existed for making use of 'normal' SSDs.
ಬುಲ್ವಿಂಕಲ್ ಜೆ ಮೂಸ್ - Tuesday, May 15, 2018 - link
Power loss protection ?From what I know so far, the MX500 (500GB) cache contains unique data that has not yet been written to normal nand and Crucial does not recommend using an SLC cache unless you have battery backup protection
An Optane cache drive is a "copy" of data already on the hard drive (or SSD) and I don't see a problem with power loss resulting in data loss once you clear the cache
SkipPpe - Friday, May 18, 2018 - link
Something like an Intel 3510 would be a better drive to use for this.ಬುಲ್ವಿಂಕಲ್ ಜೆ ಮೂಸ್ - Tuesday, May 15, 2018 - link
DOH......Nevermind!
sharath.naik - Tuesday, May 15, 2018 - link
I was wondering if the lifespan of these are no better than SSD. wont this burn out much faster than the drives lifespan if used as a cache for it?MajGenRelativity - Tuesday, May 15, 2018 - link
Optane drives are more durable than the average SSDCheapSushi - Wednesday, May 16, 2018 - link
Even more so than MLC NAND, which seems to be getting harder and harder to find (aside from Samsung's PRO line).Drumsticks - Tuesday, May 15, 2018 - link
Is anybody else interested in the performance of the 800p as a cache drive? The difference between an Optane SSD 800p and a 1TB HDD versus a 1TB SATA drive nowadays is less than $15, so it's pretty comparable for effectively the same capacity of storage. On the other hand, in the 25 or so graphs presented in this review, the 118GB caching solution outperforms a SATA drive, sometimes handily, in 24 of them. The 25th is power consumption, and one of them has a single loss in run 1 of the latency measurement for the heavy test.Hell, sometimes that solution outperforms the 900p. Why would you pick a comparably priced 1TB SATA SSD over something like that? If you need less storage, a 500GB will perform even worse than a 1TB, and a 250GB would be even worse still. Going down in capacity on the Optane drive would still probably keep you in the range of the SATA drive, while leaving you with double or quadruple the capacity.
Giroro - Tuesday, May 15, 2018 - link
"58GB 800P is functionally identical to the 64GB M10 and both have the exact same usable capacity of 58,977,157,120 bytes."Hold on, either something is wrong or that is straight-up false advertisement, a new low that is far beyond how storage manufacturers usually inflate their capacity specs. Don't just breeze past the part where Intel may be illegally marketing this thing. As far as I know Optane doesn't use over-provisioning, and it definitely isn't the normal GiB/GB conversion issue or the typical "formatting" excuse that doesn't actually apply to solid state media, so what gives?
It has to be a mistake, right?
The_Assimilator - Wednesday, May 16, 2018 - link
> it definitely isn't the normal GiB/GB conversion issueActually, it is.