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.
Odd - I've got 5 and all are well. 1 Intel, 2 Samsung and 1 Critical. I guess I'm lucky and you are not.
Place nail here >+
I've had 150 of them, and all of them are half dead.
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
"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.
Rejoice then, you still have 75 SSDs!
Get free satoshi (Bitcoin) and Dogecoins
hey thanks for sharing your anecdotal experience as if it carries any weight whatsoever compared to actual controlled experiments and statistics.
for comparison, I've owned 8 and no failures yet. I have a raid0 array of SSDs upstairs that has been working flawlessly since 2008. an aberration maybe. anecdotal evidence works like that.
i could live a little longer in this prison
that reminds me ... I should do a backup ....
i could live a little longer in this prison
100TB a day? Roughly 1.2GB per second? No. No you won't.
Good luck with that. This experiment has been running since Aug 20, 2013 and running almost continuously at that. Even the heaviest consumer/prosumer work load would have trouble reaching the amount of data written in this experiment.
Stop storing them in the oven...
Learn to love Alaska
By the way, 700TB isn't all that much these days. Betcha I could do it in a week's worth of video editing.
I'll take that bet. Most SSDs have physical bandwidths of less than 1GB/sec. So even if you were writing continuously, without sleep or bathroom breaks, and reading nothing back, you would still need more than a week to write that much data.
You might want to do a bit of math before making such a statement. 700TB is a very large amount of data. And in order to do that in a week, would require quite a bit of data transfer bandwidth. To wit:
700,000,000,000,000 / 7 days = 100,000,000,000,000 / 24 hours = 4,166,666,666,666 / 3600 seconds = 1,157,407,407 bytes per second.
Do you really write 1.157GB/second every second for a week? And if so, what data interface are you using? I'd really like to know since SATA 3.0 can only handle 600MB/second. Perhaps you're using SATA 3.2 which does have the required speed?
Now in an environment using multiple drives, you can get to the 700TB mark much more rapidly with much lower per drive bandwidth. But then again, that's not the test criteria. They are testing how much endurance individual SSDs have.
"I've got 5 and all are well. 1 Intel, 2 Samsung and 1 Critical. "
That apparently doesn't prevent you from dropping bits, though. 1+2+1=4.
"National Security is the chief cause of national insecurity." - Celine's First Law
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.
hey thanks for sharing your anecdotal experience as if it carries any weight whatsoever compared to actual controlled experiments and statistics.
A controlled experiment with statistics. Too bad this article is not that.
Let me guess, every single SSD you bought was a low capacity sand force controlled one.
See for yourself. Sure, that's high end now, but in the future? Anyway, there you go, ten days (so sue me) will eat a little more than a petabyte. So now I would have to stripe 10 or 20 of these SSDs to hold it all. Now what will my failure rate be?
On the other hand I still prefer SSDs over all the monkey motion going on in a hard drive. I'm just pointing out that a petabyte doesn't mean much anymore. And I still remember having a 20 meg drive and thinking I'll never use it all.
“He’s not deformed, he’s just drunk!”
100TB a day? Roughly 1.2GB per second? No. No you won't.
Yes. Yes I will! Any other questions?
“He’s not deformed, he’s just drunk!”
He's using OooA interface.
Yes, they are sooo reliable, every single SDD I've bought has been dead within 3 months.
A happy OCZ customer, I take it?
not to mention a write error: "Critical" instead of "Crucial"
not to mention a write error: "Critical" instead of "Crucial"
Hee hee. That's a "loose nut behind the keyboard" error - not an SSD error.
Place nail here >+
Protip: A computer is capable of performing actions without a person sitting in front of it 24/7.
I don't recall the brand of the fourth, got distracted and forgot to edit. But I knew someone would have fun pointing it out, so it would be rude for me to deny you the pleasure. So - yeah - I dropped a bit. :D
Place nail here >+
I have to reply anonymously to avoid the trolls mod bombing the account, but read the links in the other replies I made. A video house will chew these things up. And yes, you would have to stripe at least ten of these things to a very fast interface.
I just bought that same drive a week ago. It has very good reviews and very few failures.
I've been using a 256GB G.Skill Sniper SSD for years now, and it has served me well. I figure it was time to upgrade as SSDs have proven themselves to be very reliable; often more reliable than their platter counterparts. Still, it doesn't seem to stop this spew of "lol but ssds sux n fail alot!" nonsense from the fools that can't actually be bothered to do any research on the subject.
In short, no worries. Your drive will almost certainly be fine. And if it isn't, then contact Samsung for a replacement. You should *always* backup sensitive data no matter what storage medium you are using.
100TB a day? Roughly 1.2GB per second? No. No you won't.
Yes. Yes I will! Any other questions?
Um, sir? Yes, um, I have a question...what sort of device can I stick in my computer that will write data at 1.2 GB/sec?
They are now half dead, half something else. Wait for them to replenish the chips, violently.
You need to read the replies I already made. There's a link to shows how fast you can wreck an SSD, and if you have that kind of money, you probably wouldn't care.
And here's a big fuck you! to the idiot moderator(s).
You couldn't sustain that bit rate on a SATA interface. No normal workflow would sustain that volume of writes or encoding, especially prosumer or lower.
There may be broadcast or industrial uses but they would be writing to industrial strength storage via 16 gig fc to SAS SLC arrays.
Good luck with that.
The Intel 335 has a sequential write speed of about 350MB/s (the rest are around the same speed). Writing 700TB at that speed would take 24 days and change, with no breaks to do things like read any of that data.
Which will also spread around the writes. If you're writing a 4TB video across 10 disks, that's only 410GB to each, so you only get that much endurance used up.
SATA 3.2 isn't out yet for consumer drives, so no you won't.
1.2GB/s twice the bandwidth of SATA 3.0
.
You failed at math.
You won't be writing 1.2GB/s to any SSD currently available. They all max out at SATA 3.0 - 600MB/s.
Since you'd need at least 3 striped drives to even try to sustain 1.2GB/s, your endurance has now tripled from 700TB to 2.1PB.
Amen to this, I STUPIDLY bought a REFURBISHED OCZ drive which, coincidentally failed shortly after OCZ announced bankrupcy. The other drive I bought was a Corsair that, like it's OCZ bretheren died three weeks after put into service. The speed is wonderful but the life is pathetic. Despite this, I have a Kingston and a Samsung which are both going strong so I can confidently state that HALF OF ALL SSDs FAIL AFTER THREE WEEKS, THE OTHER RUN FOREVER!
Perhaps I need to work on my sample set and my over-use of capital letters.
Protip: less than 1GB/sec is much less than 700TB/week.
Protip 2: SATA 3.0 is only 600MB/sec, the peak interface bandwidth is only 346GB/week.
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.
Since you'd need at least 3 striped drives...
That's just multiplies the possible failure rate by three, regardless of the reason for such failures.
Stop defragmenting them.
I have two different Crucial mSATA drives - one runs VMware in one workstation (well, "server"), and the other runs virtualbox in another. Each is a different generation SSD - and no problems. I've also shipped many to customers in servers (real servers on RAID controllers, not workstations posing as servers). Not one failure.
The Christian Right is Neither (Christian nor right). See: Matthew 23, Matthew 25, Ezekiel 16:48-50
"I don't recall the brand of the fourth"
:-)
There you go again.
"National Security is the chief cause of national insecurity." - Celine's First Law
I think your math is off a bit by a factor of 1000:
600 MB/s and 604,800 sec/wk = 362,880,000 MB/wk = ~362,880 GB/w = ~ 362 TB/w
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.
Off by a letter.
s/G/T
Who says he's using SATA? There are PCIe 4x SSDs out there you know.
Not everyone - I work in broadcast. We're cheap. Not just cheap, fucking ultra cheap. Our sister station get whatever they want whenever they ask for it, but we get nothing. We use outdated consumer grade IT gear. Our network is much slower than 100 megabit should be. Our top editing computers are a couple of years old. We have single terabyte drives in them, and use those as our capture and export drives.
You're editing 4k video 24/7? Thats quite impressive, but not terribly believable.
Its all irrelevant, because theres no SSD out there that could handle that write rate, and theres no way hes generating that much data 24/7.
Hes full of crap and doesnt want to admit it.
Protip: A PCIe 4x SSD can reach 930MB/s write speed
Protip 2: When you make sweeping assumptions, you look like an idiot.
Thats not really how it works. The wear is leveled across cells, so increasing the number of drives in a RAID0 really does increase the amount of data till a predictable failure (ie, the "write limit").
Not true... SSDs with direct PCI connections, such as those from FusionIO, Intel, and in current Macs can reach those speeds.
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.
I did some calculations on it as well, I think Tera is actually correct here. That also makes more sense to me, as I've certainly moved a few hundred GB from HD to HD with in a day before.
We seem to have the beginning of a trend here - AC's don't have very good luck with SSD's.
Try logging in and see if that changes your outlook.
Faster! Faster! Faster would be better!
Single board Computers and Sata Express...
Um... a good PCI-E drive, such as a Fusion-IO board will certainly handle that write rate. That *he* is generating enough content to fill that pipe for a week strait is unlikely though as it would require multiple 10Gbase connections to do so. Since he is talking about video editing, let's say this is a surveillance system taking uncompressed HD streams that are being written natively to disk without transcoding prior to editing; we are still talking about 188 cameras coming to this one server.
That the likes of Facebook would be generating sufficient content to saturate these cards, again possible in terms of server to server replication to keep their cluster in sync and maintain live backups and hot standbys, however unlikely that they would want to fully saturate their bandwidth to single nodes as opposed to just adding some more servers to ensure that capacity exists so their users can connect.
Thirty four characters live here.
why does flash memory have limited endurance? Too bad companies can't use regular DDR3 memory in SSDs.
See for yourself.
Why didn't you just refer to the LHC web page and imply that you are writing at that same data rate to a single SSD...it would have exactly the same value as an argument.
I seem to have the exception. I have almost 2 years on an OCZ drive I purchased from NewEgg. It's seen daily use for those two years.
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.
I think you're wrong about the week part, but otherwise correct. When we attempted to swap-out the drives on a MySQL server that had a pair of five year-old 15k drives quit, it was less than ninety days before we had the first failure and four days later the second drive quit. They were Samsung 840 250GB drives. I was able to swap them out quickly because I had bought several extra for desktops. I think at the end of five months before we finally replaced them with new 300 GB 15k SAS drives, we had replaced nine drives. The RAID array was only eight drives! Fortunately we were using RAID 6 so we didn't lose any data, but it was scary. I hated to pay more for slower drives, but for a server you must have reliable drives. There's a reason Dell's cheapest (well, the last time I looked) server SSD is $1,500.
Samsung would only replace four of the drives. Those four have been in heavy use in developer machines since then without a failure, but they just didn't work for a write-heavy DB server. I would be weary buying another Samsung product because of their horrible support, but the drives do work for their intended purpose.
Which reminds me, my VISA extended warranty claim on 1 of my terrible OCZ drives came back last week. VISA actually paid for the original price of the drive + tax + registered mail cost.
I had to do this because OCZ refuses to honor my 'intermittent' disconnect-prone ssd harddrives.
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."
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.
How large is your backup filesystem(s)? This was 700TB written to a 250gb drive. If you're copying "near a TB of data from Backups ... almost daily", then I'm betting you have many many TB of storage in the backup pool... so divide that by 250gb and multiple that by 700TB and that's the endurance the SSD's would have. However, even then it doesn't really apply... your backups are not likely to be rewriting a lot of sectors (ex. deduplication, if used, means few files are actually written). You also said you copied FROM backups, so those are just reads (I'm presuming those are going out to multiple clients).
In any case, the 700TB "endurance" figure is still acurate, even if you consider that fragile - it's a level of endurance under a specific use case.
FWIW, for a backup system, I'd also stick with spinning disks (or tape) for now and well into the foreseeable future. Throughput and IOPs are not very important to backup storage, and you'll get way more GB/dollar from HDD's.
Might be luck, might be an exception, but my Agility 2 is still kicking after 3 years, half of that was under XP (no TRIM).
I've had 4 spinning drives (Seagate) die or get bad sectors in the same time frame.
I've got better things to do tonight than die.
Automation, baby! It's the next big thing.
Posting AC because the asshole moderators are trolling my account
-F
SAS 12gbps exists.... 1.5GB/s
I have a loverly LSI megaraid controller that does 1.5GB/s read/write(to bbu cache)
You're acting like a smug little bitch, it's no wonder people want to mod you down.
you underestimate the porn overlords of our time.
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?
And... that's it? What did SMART say? Did you actually wear the SSDs out as-per the wear indicator? Or did you hit a bug in the samsung controller before the wear-indicator maxed out?
To be fair, the precise situation you describe, particularly if you did not retune the RAID-6 setup or the mysql server, and if the server was fsync()ing on every transaction (instead of e.g. syncing on a fixed time-frame as postgres can be programmed to do)... that could result in el-cheapo samsungs not being able to do any write-combining and cause a 256:1 write-amplication of the data.
With proper tuning the write-amplication could easily be reduced to 4:1 and you would probably be able to run the server with SSDs. Maybe use Intel or Crucial though, and not Samsung. It isn't just the controller that matters... just using stock firmware doesn't really net you a good, robust SSD and there aren't too many real vendors who work on the firmware vs just OEM whatever was supplied with the controller. Intel is probably one of the better ones. They actually fix bugs, as does Crucial. Samsung... I dunno.
-Matt
How do you know he wasn't listing them chronologically? "1 Intel, 2 Samsung[, 1 don't recall] and 1 Critical. "
09F91102 no, 455FE104 nope, F190A1E8 uh-uh, 7A5F8A09 that's not it, C87294CE no. Ah! 452F6E403CDF10714E41DFAA257D313F.
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.
All you had to do was check at Amazon to see the star ratings people are giving them. The Samsung's were/are at about 4.8/5 for hundreds of reviews, while the OCZ was closer to 3/5 (again for loads of reviews). I'm still amazed how few actually bother doing this simple step.
Why OpalCalc is the best Windows calc
No, with 1920x1080 24bit per pixel and 30fps I'm getting 178MB/s so six cameras almost saturate the SSD. Of course it would be a great deal more reasonable to acquire the data compressed in H264 frame by frame, or H265 if it comes out and is better for that.
Though, we might get mad and use uncompressed 1080p at 60fps. Then you can have a realistic "zoom in and ehnance" sequence as in the dumb movies and TV shows, with an algorithm able to combine data from multiple pictures and see a face more clearly esp. if the subject was reasonably stationary for a short while.
But the SSD controllers aren't fully aware of what is going on and the free or reserved space for wear leveling is splitted as many times as you have drives. A n times bigger SSD are still better than n SSD in a RAID 0.
Then we're limited by interface for speed, but we have good incremental progress on the horizon. PCIe storage is already standardized in the form of M2 and SATA Express, the latter works in PCIe 2.0 2x or 4x, the latter is 2x : that gives a theoretical 1GB/s and 2GB/s. Upgrade to PCIe 3.0 doubles that.
SAS 12Gb/s is also an option.
As far as I know SAS 12Gb gives you 1.2GB/s theoretical.
Also Samsung 840 (non pro) is TLC chips, three bits stored per flash cell. They'd be the drives that suffer the most from that write amplification, with 840 EVO that is similar and is very aggressive in working with very few overprovisioning.
840 Pro would have taken a lot longer to die, while still being a consumer drive. Still that was an interesting experiment.
I've got 3 SSDs. One is a Toshiba that was stock with an Apple laptop used constantly. Fine for 3 years of use until I replaced it for a larger-capacity Corsair SSD (i.e. no problems, just too small). The other is an OCZ as the boot drive in a very heavily used Windows 7 desktop machine for ~3 years. These aren't top-of-the-line drives and OCZ is particularly notorious for reliability problems (I bought that drive before their problems became so well-known). People are probably laughing at the brand choices. I'm practically asking for problems by using cheap drives rather than, say Intel ones. And yet the drives have all been fine.
So, that AC apparently has bad luck, or I'm running on borrowed time.
I'll see your incredibly small sample size, and raise you with "the company I work for has bought hundreds of Kingston SSDs, and we haven't had even one fail in the last two years."
Slashdot still doesnâ(TM)t support Unicode after it was added to the HTML standard in 1997.
How do you know he wasn't listing them chronologically? "1 Intel, 2 Samsung[, 1 don't recall] and 1 Critical. "
Thanks, but no - I just screwed up. Yesterday was just my turn to be in the barrel.
Place nail here >+
Maybe buy SSDs meant for high transaction rates and extended write cycles next time. Throwing consumer SSDs into a SQL server is just dumb, and asking for a failure.
Kingston has drives that are far less than the price you quote that they warranty for 5 years, and they came up with that number by how many days the drive could operate at 10GB of writes per day. Also, SLC drives are far more robust than MLC, but more expensive.
I purchased two OCZ 64Gb SSDs and they both failed right around the end of the warranty. One was replaced under warranty, the other not. They replaced the 64Gb drive with a 60Gb drive which was a little upsetting, but better than nothing I suppose.
Both died suddenly, and with no warning.
1TB of writes per day to an SSD probably isn't a normal usage scenario for your average consumer. Samsung for example claims that the average consumer writes no more than 10GB/day to an SSD:
(emphasis mine)
OCZ's SSD's over-all average failure was about 2x-4x the industry average, which places them about mechanical harddrives, but there was several models in a row with failure rates over 50%. Worse than flipping a coin. No idea how their QA managed that, but their bankruptcy tells the story.
I'm using a 500GB 840 EVO as my main drive in my system. I've moved stuff like /var to a separate hard drive (because of log files and constant tiny read/writes that aren't speed-sensitive), and I do all compiles on a RAM disk, I've upgraded to 16GB to avoid swapping.
Based on reviews etc., I fully expect the 840 EVO to outlast every other component in my PC.
Eat the rich.
Actually, this *was* a controlled experiment, and it *does* have statistics. Unfortunately, the sample size is too small to extrapolate to the population at large, but studies often *start* like this, with interesting results triggering larger, more significant studies to determine if the result is typical, or atypical.
No, I logged in and I've still got Outlook 2007.
Hail Eris, full of mischief...
E pluribus sanguinem
The OCZ drive I had lasted 2.5 years, so it was replaced within the 3 year warranty. Recently I bought a Mushkin 180GB which failed after only 10 months. Again, replaced under warranty, but nobody seems to be badmouthing them. I'm sure anecdotal data is anecdotal.
I'm interested in this question because we do nightly calculations rewriting postgresql databases. I'm thinking of trying to do it on SSDs for speed, but I'm worried that I'll just kill the drives in a month or so. Still, if I could get 2 months out of a sub $200 drive, it might just be worth it - make a kickstart file to ease the reinstall, then just pop in a new one when it dies.
HAHA
Hmm... Out of the four I bought, 1 failed after a few weeks. So I can confidently state that the typical lifetime of a SSD is somewhere between 3 weeks and 3 million years.
I used to say that SSDs aren't mature yet and cost way too much. These days I find that most of the technical issues I have with them have been addressed, the sole remaining one being that HDDs tend to have kinder failure modes. SSDs have come of age and are desirable even to a relatively conservative buyer like me.
Now if I could only justify the price... (The only computer where an SSD would be relevant for me is a laptop with a 500 GB HDD that typically sees heavy load. An SSD that fits my storage requirements would put a serious dent in my finances. Oh well, perhaps next year.)
USE HOT GRITS WITH STATUE OF NATALIE PORTMAN (NAKED AND PETRIFIED)
And run the winsat formal before starting to use the new Windows installation.
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 ]