• Sign in to Neowin Faster!

    Create an account on Neowin to contribute and support the site.

Sign in to follow this  

Reliability of Spinning Things, Complex Levels and Types of Backups - A List of Ideas, Tips, Approaches

Recommended Posts

Peresvet    181

1.21 Gigawatts!!!

 

200TB, eh? That's a lot of porn, dude.

Share this post


Link to post
Share on other sites
DevTech    1,517
2 hours ago, Jim K said:

With respect to BackBlaze ... while their hard drive reliability stats are a fun read ... it is far from giving a real world consumer level reliability test on hard drives.  Looking at the "Annualized Hard Drive Failure Rates for Active Drives" half of those drives are consumer and the other half are enterprise.  The consumer drives are being used in an environment which they weren't really designed for. They also do not give the cause of particular hard drive failures (afaik) or how much "thrashing" a failed drive underwent.

 

...but anyway.  That is my take on BackBlaze ... interesting ... but I'm not going to use their data in deciding my next consumer hard drive. /shrug

I could probably make a list of more areas where the data is difficult...

 

But there is NOTHING ELSE so a logical thinking person of scientific disposition which describes many tech enthusiasts should be motivated to give as much weight to whatever real data that can be found over and above the plethora of random anecdotal information of ZERO statistic significance that often informs and weights people's decision making process.

 

It is a shameful that the industry or some large player like Azure or AWS or GCP or HP or Dell doesn't provide information that in addition to helping all of use would light a fire under drive manufacturers...

 

It's all we have, so I am advocating using it as much as we can.

 

"They also do not give the cause of particular hard drive failures (afaik) or how much "thrashing" a failed drive underwent."

 

They did do a fascinating analysis of SMART data

 

Share this post


Link to post
Share on other sites
DevTech    1,517
2 minutes ago, Peresvet said:

1.21 Gigawatts!!!

 

200TB, eh? That's a lot of porn, dude.

I haven't updated that but there was an error in my inventory process

 

In any case, it would be more interesting if I had some of that stuff instead of movies I'm never going to watch again and way too many backups and small variations in VM image configs...

 

And although I strongly advocated every citizen collection information that might otherwise become unavailable in some less than perfect future, I'm doing a crappy job on that because Dark Web and "underground information" etc just doesn't hold my interest...

 

Share this post


Link to post
Share on other sites
DevTech    1,517
3 hours ago, Mindovermaster said:

 

You really needed to quote me twice? :laugh:

 

But, yeah. I only had one WD Black drive, but hasn't failed me yet...And several Blues and Greens. Never touched the other stuff.

Twice, because I had a new thought that your comment triggered...

 

Your personal subjective experience in terms of reliability data is meaningless, as is mine as well. Even if you managed 100 computers for a small I.T. shop, it would barely be statistically significant.

 

We can find insights to share with people on performance and config and tweaking and process and procedures but reliability of hard drives is a numbers game over time about which we might be tempted to provide similar opinions as in our actual areas of expertise, but would then be doing a disservice to the community.

 

"All drives fail - back them up" is advice we can repeat but if it's not in the Backblaze.com data, saying Model XXX will last longer than Model YYY is simply not right. I can tell people that WD Black has better components than other drives and has great performance, but since it was never used at any time by Backblaze, it has COMPLETELY UNKNOWN RELIABILITY like pretty much ALL DISK DRIVES.

 

Do I like that? NO!

 

Is it reality? unfortunately, YES.

 

 

 

  • Sad 1

Share this post


Link to post
Share on other sites
conna    108

What kills the excitement of cloud storage is the "restore".  Most actually charge you to restore and the restore from online backup is still going to be limited in speed.   It may take you 2-3 days just to download your 200TB of data and untold charges.

Share this post


Link to post
Share on other sites
DevTech    1,517

COPY of my Backblaze Analysis from other thread so everything is in one place:

 

 

"Finally in Q4, we added 1,200 Toshiba 14 TB drives (model: MG07ACA14TA). These are helium-filled PMR (perpendicular magnetic recording) drives."

 

I would have a difficult time trusting a Helium filled drive for longevity since Helium is so small it will leak through any metal over time...

 

"Speaking of HGST drives, in Q4 we added 1,200 HGST 12 TB drives (model: HUH721212ALN604). We had previously tested these drives in Q3 with no failures, so we have filled a Backblaze Vault with 1,200 drives. After about one month we’ve only had one failure, so they are off to a good start."

 

As a group, the Hitachi drives have the lowest failure rate over time. So why doesn't Backblaze buy Hitachi drives over Seagate which have had some of the highest failure rates? The reason is that a drive failure is a monetary event to them. They have multiple copies of any data so all a drive failure means is that it needs to be replaced and another one purchased. So if Seagate drives have a higher failure rate but are a lot cheaper to buy, then they are more attractive overall. 

 

For an individual, the trade-off is different and in most cases trading extra money for more reliability is a very good deal. The problem has been that there has been no way to be certain about reliability...

 

On a quick look, the most reliable drives right now 6 TB or larger appear to be:

 

1. Hitachi HUH721212ALN604 12 TB - 0.51 %

 

2. Seagate ST10000NM0086 10 TB - 0.33 %

 

Note that if you make a purchase based on that data, the drive model number must match exactly for you to benefit from the reliability info.

 

As a consumer and not an objective mathematician, failure rates of 1/2 of 1% are bad enough that 1% is just uncomfortable to think about - 1 in a 100 in any given year is a horrible lotto for precious data...

 

Which leads me to completely rethink the WD Red 6 TB with a horrible failure of 5.5% to 2% averaged at 4% - WTF.

 

So, I still feel the more expensive construction of the WD Black should actually result in good reliability (and fantastic performance is built in) but for new "Mass Storage" drives, the Hitachi 12 TB or Seagate 10 TB are the ones to get.

 

If the Hitachi 4 TB is still available it is 0.36% and suitable.

 

Hmm maybe that will be hard to source - $70 refurbished at Newegg:

 

Hitachi HMS5C4040BLE640 $70

 

https://www.newegg.com/Product/Product.aspx?Item=9SIA5AD8N69185&Description=HMS5C4040BLE640&cm_re=HMS5C4040BLE640-_-9SIA5AD8N69185-_-Product

 

Seagate ST10000NM0086 $400

 

https://www.newegg.com/Product/Product.aspx?Item=9SIA1K68GH1882&Description=ST10000NM0086&cm_re=ST10000NM0086-_-9SIA1K68GH1882-_-Product

 

Hitachi HUH721212ALN604 448 in pounds, (but in 37 days it might be 2,000,000 inflated May Bucks...)

 

https://www.amazon.co.uk/HGST-Ultrastar-HE12-12TB-HUH7-21212ALE604-24x7-8-9-3-5-Inch/dp/B071W4BVVT/ref=pd_lpo_sbs_107_t_2?_encoding=UTF8&psc=1&refRID=P4HY7M2K4H5H9N1V1H48

 

For reference:

 

WD Black 6 TB $230

 

https://www.newegg.com/Product/Product.aspx?Item=234-000G-000W5&Description=wd black&cm_re=wd_black-_-234-000G-000W5-_-Product

 

 

Share this post


Link to post
Share on other sites
Jim K    13,683

Gonna say it again ... while the data from BackBlaze is fairly neat ... it really shouldn't be used as a guide in determining which hard drive to purchase (consumer level).  

 

 

  • Thanks 1

Share this post


Link to post
Share on other sites
DevTech    1,517
2 hours ago, Jim K said:

Gonna say it again ... while the data from BackBlaze is fairly neat ... it really shouldn't be used as a guide in determining which hard drive to purchase (consumer level).  

 

 

Of course it should!

 

Think of it as a cold splash of water in the face.

 

There are literally just 2 drives from that data that you could buy new today and have statistical confidence if you bought enough of them!

 

The lesson for the consumer is that ALL the stupid (sometimes well meaning) anecdotal experiences that people have with different drive brands is just meaningless. Backblaze data shows that the reliability of most drives is really quite BAD and shoving literally the ONLY reliable source down people's throats  means that maybe just maybe "ALL DRIVES DIE" will seem a bit more real...

 

Share this post


Link to post
Share on other sites
Jim K    13,683

I disagree.  It shouldn't be a surprise that enterprise drives fail less than consumer drives in an enterprise environment.  Basically you're saying that consumers should purchase enterprise level equipment for a home environment.  The number of different model drives is relatively small as well .. I'm guessing WD Blues and Greens have a 0% failure rate?  How about Blacks vs. Barracuda Pros?  How do these "recommended" enterprise drives perform in the home environment?

 

Just saying the it needs to be taken with a grain of salt.

  • Like 1

Share this post


Link to post
Share on other sites
DevTech    1,517
On 6/19/2019 at 6:42 AM, Jim K said:

I disagree.  It shouldn't be a surprise that enterprise drives fail less than consumer drives in an enterprise environment.  Basically you're saying that consumers should purchase enterprise level equipment for a home environment.  The number of different model drives is relatively small as well .. I'm guessing WD Blues and Greens have a 0% failure rate?  How about Blacks vs. Barracuda Pros?  How do these "recommended" enterprise drives perform in the home environment?

 

Just saying the it needs to be taken with a grain of salt.

1. There is ONLY ONE source of hard drive reliability information.

 

2. It is not the easy prescriptive answer we wish we had.

 

3. It is completely NUTS to ignore it. Digging out useful bits is annoying and prone to misinterpretation. The alternative is VooDoo.

 

4. When described correctly, the limited usefulness SHOULD BE a giant WARNING and it should always be emphasized that no matter how useless you think it is, there is NO ALTERNATIVE.

 

5. My analysis of the Backblaze data was detailed and complete. So your points are meaningless in that context "I'm guessing WD Blues and Greens have a 0% failure rate?  How about Blacks vs. Barracuda Pros?  How do these "recommended" enterprise drives perform in the home environment?"

 

I ONLY bring up the Backblaze data when people ask which drive is most reliable, a natural human question for which the computer industry in some nasty CARTEL type thinking just has a WALL OF SILENCE outside of the wonderful folks at Backblaze.

 

6. Do I expect people to by enterprise drives? If somebody is deeply concerned about the reliability of a drive, then I point out there are ONLY TWO models which you can ACTUALLY BUY and have KNOWN STATISTICAL RELIABILITY. Enterprise or not, buy a few of those drives and rest easier if that issue gives you the heebie-jeebies.

 

Otherwise, buy any drive you like and PLAN FOR IT TO DIE SOON. We all know that backup is essential. 

 

7. What I fight against by bringing up the Backblaze data is NON-SCIENTIFIC anecdotal stories about which "brands" are most reliable. Total-BS.

 

 

 

  • Facepalm 1

Share this post


Link to post
Share on other sites
Peresvet    181
Posted (edited)
On 2/8/2019 at 10:08 AM, DevTech said:

And although I strongly advocated every citizen collection information that might otherwise become unavailable in some less than perfect future, I'm doing a crappy job on that because Dark Web and "underground information" etc just doesn't hold my interest...

So, have you already acquired the means of generating power in-house for a scenario "in some less than perfect future" in which (I presume) the Internet is permanently shut down?

 

 

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
Sign in to follow this  

  • Recently Browsing   0 members

    No registered users viewing this page.