Slashdot Mirror
Endurance Experiment Writes One Petabyte To Six Consumer SSDs
crookedvulture (1866146) writes "Last year, we kicked off an SSD endurance experiment to see how much data could be written to six consumer drives. One petabyte later, half of them are still going. Their performance hasn't really suffered, either. The casualties slowed down a little toward the very end, and they died in different ways. The Intel 335 Series and Kingston HyperX 3K provided plenty of warning of their imminent demise, though both still ended up completely unresponsive at the very end. The Samsung 840 Series, which uses more fragile TLC NAND, perished unexpectedly. It also suffered a rash of cell failures and multiple bouts of uncorrectable errors during its life. While the sample size is far too small to draw any definitive conclusions, all six SSDs exceeded their rated lifespans by hundreds of terabytes. The fact that all of them wrote over 700TB is a testament to the endurance of modern SSDs."
Yes, they are sooo reliable, every single SDD I've bought has been dead within 3 months.
has anyone tried this with platter drives? would it simply take too long?
it's hard for me to judge whether this is more or less data than a platter drive will typically write in its lifespan. I feel like it's probably a lot more than the average drive processing in its lifetime. and anyway, platter drive failure might be more a function of total time spent spinning or seeking or simply time spent existing for all I know.
i could live a little longer in this prison
Oh wait, I have to read the article? Homey don't do that.
By the way, 700TB isn't all that much these days. Betcha I could do it in a week's worth of video editing.
“He’s not deformed, he’s just drunk!”
"all six SSDs exceeded their rated lifespans by hundreds of terabytes" - Interesting and probably relevant data, but doesn't the "rated lifespan" include retaining the data for at least one year after the last write is performed?
*blink*
Nice that the MWI provided advanced warning, but the actual behavior when it ran out seems to be the opposite of what's supposed to happen: the drive should be readable but not writable.
I had an X-25M that failed in similar fashion; although it had an MWI of 100% when it died and had barely seen its first couple of terabytes of writing, it was in a situation where there would have been heavy write amplification on whatever space it had left. When it died, applications fell over, and it showed up as an 8MB drive on powerup. 100% data loss. I should probably pull the chips off it and dump them - it was one of the pre-encryption drives - just to see if I can get anything back.
but with Ne4tcraft core te4m. They of BSD/OS. A
I have around 30 ranging from 40G to 512G, all of them are still intact including the original Intel 40G SSDs I bought way at the beginning of the SSD era. Nominal linux/bsd use cases, workstation-level paging, some modest-but-well-managed SSD-as-a-HDD-cache use cases. So far wearout rate is far lower than originally anticipated.
I'm not surprised that some people complain about wear-out problems, it depends heavily on the environment and use cases and people who are heavy users who are not cognizant of how they are using their SSDs could easily get into trouble.
For the typical consumer however, the SSD will easily outlast the machine. Even for a pro-sumer doing heavy video editing. Which, strangely enough, means that fewer PCs get sold because many consumers use failed or failing HDDs as an excuse to buy a new machine, and that is no longer the case if a SSD has been stuffed into it.
A more pertinent question is what the unpowered shelf-life for typical SSDs is. I don't know anyone who's done good tests (storing a SSD in a hot area unpowered to simulate a longer shelf time). Flash has historically been rated for 10-years data retention but as the technology gets better it should presumably be possible to retrieve the data after a long period on a freshly written (only a few erase cycles) SSD. HDDs which have been operational for a time have horrible unpowered shelf lives... a bit unclear why, but any HDD I've ever put on the shelf (for 6-12 months) that I try to put back into a machine will typically spin-up, but then fail within a few months after that.
-Matt
Considering 90% of my storage is write once, read many (email, mp3, dvds, programs, etc), this is good for me as long as the drive has a good, errr, brain fart, scheme so when I write a byte it chooses one I haven't written to in a while. My SSD should last forever, or until the electron holes break free of their silicon bonds.
I just purchased an EVO 840 and put my entire life on it. Now I find it's fragile. OH NOES!
Ability to write hundreds of terrabytes more is nice. But it's reading them back that I am really worried about. Great news for someone deploying a short term cache.
to make sure the 7or hthe state of
There was also a very interesting endurance test done on extremesystems.org. Very impressive stuff. I don't yet own an SSD, but I'll continue to consider buying one! Maybe next Black Friday. Just waiting for the right deal.
Quite an experience to live in fear, isn't it? That's what it is to be a slave.
That's a heck of a lot of data, and certainly more than most folks will write in the lifetimes of their drives.
Continued write cycling [...]
That's just ridiculous. Since when the reliability is measured in how many petabytes can be written?
Spinning disks can be forced into inefficient patterns, speeding up the wear on mechanics.
SSDs can be easily forced to do a whole erase/write cycle just by writing single bytes into the wrong sector.
There is no need to waste bus bandwidth with a petabyte of data.
The problem was never the amount of the information.
The problem was always the IO pattern which might accelerate the wear of the the media.
All hope abandon ye who enter here.
why does flash memory have limited endurance? Too bad companies can't use regular DDR3 memory in SSDs.
How is 700TB "endurance"? I copy near a TB of data from Backups at work almost daily. So 1-2 years (if that) is "endurance"? Screw that! Sounds more like modern SSD's suck hard and aren't designed to last past 1-2 years of work. I'll stick with traditional HD's until they figure out DRAM drives that don't need batteries or constant power.
Even Intel, behemoth of reliable server hardware, wasnt able to fix Sandforce problems. :DDD and not switch it to read only mode (like you promise in the documentation).
According to Intel representative Graceful Failover of SSD drive means you _kill_ the drive in software during a reboot
Kiss your perfectly readable data goodbye.
Who logs in to gdm? Not I, said the duck.
Endurance Experiment Writes One Petabyte To Three Consumer SSDs
"how much data could be written to six consumer drives. One petabyte later, half of them are still going."
Stopping and starting a drive is also a moment where you can break/wear down a drive. This can be explained by the fact that heads rest on platters (unless in parked position) when the platters are not spinning at the right speed. Also, because a drive that is being spun down will cool down and warm up again when being spun up. These temperature fluctuations will be of influence on the drive reliability. The most plausible explanation I can come up with is that temperature shifts will make parts inside the drive align differently, possibly permanently changing alignment enough for head-misalignment to occur.
I was promised a flying car. Where is my flying car?
Has anyone found a way to get this media wearout indicator (MWI) that the article claims to exist? Sounds like BS since none of the tools I have ever used including smartmontools or HD Sentinel show that value.
RAID implementations don't always support cobbling together a random mixture of disk sizes which change over time.
Linux' software RAID support this without any problem. As you finished a cycle of yearly swap over the whole pool, you can increase the RAID to the new maximum (= shared minimum accross the drives). The resize is done on-line and is gracefully restartable (in fact, you can even migrate to bigger RAIDs with more drives gracefully).
(e.g.: After 6 years, once you've upgraded a RAID6 from 6x 1TB to 6x4TB, you can easily grow the system from 4TB to 16TB).
In addition to that, modern filesystems like BTRFS and ZFS can entirely handle the random mixture of disk. Just specify the level of redundancy (i want to be able to lose 2 drives and still suffer no data loss), plug in drives, add them to the pool, and let BTRFS or ZFS handle the actual details.
(e.g.: throw watever mix you want, total size would be always sum of drives minus what's needed for the level of redundancy you asked for).
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
I think that's what I was saying: a random mixture of disk sizes is not supported by this particular RAID implementation - it will only use the same size across each disk, meaning you are constrained to the size of the smallest disk in the pool.
Okay I was thinking that you were comparing with other RAID implementation (most fake RAID cards can't even *grow* the raid, once you've cycled the drives and that the "smallest disk in pool" is now bigger).
Btrfs and ZFS sound like they handle it much better.
Yup, they would handle whatever you throw at them, as long as they can manage to fit the constrains you've asked.
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]