Slashdot Mirror
Google Releases Paper on Disk Reliability
oski4410 writes "The Google engineers just published a paper on Failure Trends in a Large Disk Drive Population. Based on a study of 100,000 disk drives over 5 years they find some interesting stuff. To quote from the abstract: 'Our analysis identifies several parameters from the drive's self monitoring facility (SMART) that correlate highly with failures. Despite this high correlation, we conclude that models based on SMART parameters alone are unlikely to be useful for predicting individual drive failures. Surprisingly, we found that temperature and activity levels were much less correlated with drive failures than previously reported.'"
Excellent, i have been looking forward to thi *%)%*# DISK FAILURE
So if the article summary is correct does it even matter if the consumer desktop pc has SMART enabled or not?
They stated at one point in the document that some brands did have higher failure rates than others - yet I somehow missed any mention or ranking of brands. Did anyone else find that data?
"There is more worth loving than we have strength to love." - Brian Jay Stanley
But the disk it was on failed.
This is awesome, but the conclusion of such an interesting study leaves a lot to be desired. FTA...
"In this study we report on the failure characteristics of consumer-grade disk drives. To our knowledge, the study is unprecedented in that it uses a much larger population size than has been previously reported and presents a comprehensive analysis of the correlation between failures and several parameters that are believed to affect disk lifetime. Such analysis is made possible by a new highly parallel health data collection and analysis infrastructure, and by the sheer size of our computing deployment.
One of our key findings has been the lack of a consistent pattern of higher failure rates for higher temperature drives or for those drives at higher utilization levels. Such correlations have been repeatedly highlighted by previous studies, but we are unable to confirm them by observing our population. Although our data do not allow us to conclude that there is no such correlation, it provides strong evidence to suggest that other effects may be more prominent in affecting disk drive reliability in the context of a professionally managed data center deployment.
Our results confirm the findings of previous smaller population studies that suggest that some of the SMART parameters are well-correlated with higher failure probabilities. We find, for example, that after their first scan error, drives are 39 times more likely to fail within 60 days than drives with no such errors. First errors in reallocations, offline reallocations, and probational counts are also strongly correlated to higher failure probabilities. Despite those strong correlations, we find that failure prediction models based on SMART parameters alone are likely to be severely limited in their prediction accuracy, given that a large fraction of our failed drives have shown no SMART error signals whatsoever. This result suggests that SMART models are more useful in predicting trends for large aggregate populations than for individual components. It also suggests that powerful predictive models need to make use of signals beyond those provided by SMART."
I noticed this too. If a Google-sanctioned report had charts of which brands were more reliable, this would do serious damage to the brands that didn't perform so well. No wonder they sidestepped the whole issue!
I was at the talk, and it was very interesting. CMU also had a paper (PDF) about disk failures in the same conference (in fact, they presented one after the other).
C'mon, slashdot. There were about twenty other papers presented at FAST this year. Let's not focus only on the one with Google authors...
Am I part of the core demographic for Swedish Fish?
Ideally, they would have formatted the text to spell out the names of the brands if you take the first letter of every Nth word, or some specific column of text. (Or maybe they have...)
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
Their statistics on temperature seem very unusual. I'm surprised they didn't explore this more. For example, is the high failure rate associated with low temperatures because the drives were more likely to be inactive due to failure?
"No one likes working in a hamster wheel, and your shop smells of cedar shavings from here." - TaleSpinner
To my mind the most significant piece of info: "The gure shows that fail- ures do not increase when the average temperature in- creases. In fact, there is a clear trend showing that lower temperatures are associated with higher failure rates. Only at very high temperatures is there a slight reversal of this trend."
Excuse me, but please get off my Pennisetum Clandestinum, eh!
"...we do not show a breakdown of drives per manufacturer, model, or vintage due to the proprietary nature of these data."
t =firefox-a&rls=com.ubuntu%3Aen-US%3Aofficial&hs=tq y&q=hard+drive+reliability+research+brands++manufa cturers+models&btnG=Search
Litigation avoidance may be a consideration here but why not take Google at their word? Google is a search company that buys lots of hard drives. Based on their own internal research, they have developed information about which hard disk models and/or manufacturers are shite.
Yahoo is also a search company that buys lots of hard drives. Why should Google give that hard drive reliability information to you, me and Yahoo for free? Let Yahoo/Excite/MSN and the competitors figure it out for themselves.
Yeah, sure I'd like to have access to Google's data the next time I'm in the market for a hard drive but I won't hold a grudge against them if they don't do my consumer research for me. On the other hand, whereinafuck is the data from Tom's Hardware Guide, Anandtech, Consumer Reports and all the other reviewer and consumer sites? If someone doesn't have a handy link to their results, I'll see if I can google something up:
http://www.google.com/search?hl=en&safe=off&clien
Google releases a paper on disk reliability.
What if I do the same thing, and I do get different results?
From my experience, Western Digitals are (relatively) reliable. They unfortunately do not have the same power connector orientation as any other consumer drive on the planet, so if you want to use IDE RAID you have to get the type that either (1) fits any consumer ide drive or (2) fits a Western Digital Drive. (grr)
Had some good experiences with Maxtor. A couple of years ago (OK - maybe 6 or 8) we had batches of super reliable Maxtors - 10GB.
Some Samsungs are good, some are evil - the SP0411N was a particularly reliable model - the SP0802N sucked - out of a batch of 20, 15 of them died within a year: all reallocated sector errors beyond the threshold.
Seagates are a mixed bag too - been having a nice experience with the SATA models 160GB and 120GB - can't remember their model #'s off the top of my head. - The older Seagates, though, I spent a fair amount of time replacing.
IBM DeskStar's, as far as I know, have been quite good - for some reason didn't use too many.
Now, if you'll excuse me, I've got some idea balls to remove from a manatee tank.
Interesting.. but I disagree with your analysis.
The DeskStars were nicknamed DeathStars due to their high failure rate.
Maxtor has a terrible reputation in the channel.
Seagate has a fantastic reputation in the channel.
And as far as the WD power connectors.. I have 4 Western Digitals, a Samsung, a Maxtor, and a Seagate on my desk right now.. and they all have the same layout (left to right: 40 pin, jumpers, molex).
http://sourceforge.net/projects/smartmontools
Not exactly point & click but it'll do.
The Christian Right is Neither (Christian nor right). See: Matthew 23, Matthew 25, Ezekiel 16:48-50
that sounds like a great idea, however, flash memory has a habit of failing with no warning whatsoever as well.
They're using their grammar skills there.
You really didn't read the article, did you? On page 3 (Section 2.2 Deployment Details), the authors state: "More than one hundred thousand disk drives were used for all the results presented here. The disks are a combination of serial and parallel ATA consumer-grade hard disk drives, ranging in speed from 5400 to 7200 rpm, and in size from 80 to 400 GB. All units were put into production in or after 2001. [...] The data used for this study were collected between December 2005 and August 2006."
What are you waiting for Google to tell you? Are you really accusing them of being evil because they did a study, described their methodology, detailed their results, presented their analyses, and published it all for anyone who is interested?
You describe their conclusions as:
But there is no contradiction at all if you are smart enough to understand. They are telling you that if SMART identifies a problem with a drive then it is very likely that drive will fail within 60 days. But in a sample of 100,000 drives, many drives will also fail that have not returned errors on SMART scans. Thus SMART is a reliable indicator of impending failure but is not a silver bullet that can recognize and predict all failures before they happen.
Next time you have access to 100,000 hard drives, can analyze patterns of failure among them, can use those failures as a benchmark against which to measure analysis tools, and can come up with better recommendations for predicting failure than this study, then by all means let us know. But if you're looking for Microsoft or Western Digital or Seagate or Yahoo to perform and publish this kind of study for free, I think you may be waiting a good long while.
It is well known that google uses commodity hardware. SCSI is not commodity, although I'm sure at least some of their servers are high end.
I pretend to know more than I really do by mooching off google and wikipedia.
About a year and a half ago, a presentation by Google concerning a massive online storage service called GDrive , was leaked . It was pretty much confirmed that it is on some level operational . The study might have something to do with it , maybe even so kind of clever PR . Just my 2c.
My Starcraft 2 Blog
The paper claims "more than 100 thousand drives". But the nice thing is that you can derive the actual number from the error bars, for example those in figure 4. The data should be governed by Poisson statistics, which means that the standard deviation in the counts is equal to the square root of the count. However, their error bars seem to be about a factor 2 larger than the standard deviation, because normally around 68% of the data points should lie within one standard deviation from the "smooth curve". Let's assume the error bars are 95% confidence intervals, i.e. 2 standard deviations.
Look at the data for 20 to 21 C. It tells you that it represents a fraction 0.0135 of their total drive population, with an average failure rate of 7 +- 0.5 %. Following the reasoning above, this 7% should represent 784+-28 drives. Since these represent 7% of 1.35% of the total number of drives, we can derive that the total number of drives is 784/0.07/0.0135 = 830,000 drives. Trying the same thing for 30 to 31 C gives 826,000 drives, which seems fairly consistent.
So can we assume that Google has deployed 830,000 hard disk drives since 2001? How many servers do they have now?
Avantslash: low-bandwidth mobile slashdot.
Being able to choose freely to not say something is freedom of speech.
The right to stay silent on something is just as important a freedom as the right to have your say.
Censorship has nothing whatsoever to do with it.
Advanced users are users too!
Google Labs, yet in its youth, certainly resembles me of the golden yers of the Bell Labs.
The report does say that "vintage" matters, ie. that "Past performance is not a reliable indicator of future development".
Manufacturers have good years and bad years. The writers don't want to damn a company because it had a couple of bad years during this time period.
Still, it's a bummer that the single most important factor goes unpublished. Even if it could cause a panic I'm sure there's some useful information in there (eg. a company to avoid like the plague).
No sig today...
I had a disk reporting a SMART failure once. The result was that the disk was red in the list in Disk Utility, but there were no other warnings. So you might want to check Disk Utility once in a while.
One of largest retailers in Russia (and maybe in Europe - more than 300 terminals for orders in person at ex-factory building, busy 24/7) "Pro Sunrise" released information on failure rates of major components (CPU, Videocards, motherboards, IDE/SATA, etc) of PC they sold for Q1-Q2 of 2005.
8 3 - the article (in russian, but diagrams are self-explanatory).
http://pro.sunrise.ru/articletext.asp?reg=30&id=2
http://pro.sunrise.ru/docs/30/image001.gif - IDE/SATA (3.5" formfactor)
http://pro.sunrise.ru/docs/30/image002.gif - HDD (2.5" notebook formfactor)
In short, most returns are for Maxtor brand. Lowest - IBM/Hitachi.
Toshiba is worst in 2.5", and Seagate is best.
The chance to be blown are between 1/20 (Maxtor) to 1/70 (Hitachi).
To me it's useful - if I get a SMART warning, then I'm definitely backing up my drive and will replace it before it croaks.
Sensitivity/specificity always presents a balancing act of testing, and they are usually in a push/pull relationship. If you make a test too sensitive, then you get too many false positives, and wind up over treating something (i.e. the test says it might fail so you replace the drive even though it's not going to - a false alert)
If you make the test too specific, then usually you wind up decreasing it's sensitivity, or ability to detect something. Now you get false negatives, so when the test works, you can be sure that it's accurate, but it always doesn't detect the problem.
What you want to know is the Positive Predictive Value PPV, which is determnined by the formula PPV=TP/(TP+FP). TP= true positives, FP = false positives
Also useful is the Negative Predictive Value NPV, or this formula NPV=TN/(FN+TN) where TN = true negative, FN = false negative.
What information these give are as such. If a test is positive (i.e. the drive temperature is >80 C), then it accurately will predict that the drive will fail. If the test is negative (drive temp 40 C0 then it accurately predicts that the drive is ok.
..........FULL STOP.
In summary: Your statistical analysis on a sample size of one showed a 100% failure rate, so Samsung are crap. You found some other people also had failed Samsung drives, so Samsung are crap.
Search the net and you will find people ranting about Seagate drives failures, Western Digital drive failures, IBM drive failures, Maxtor drives failures and failures of drives made by companies neither of us have even heard of. You won't find many, if any, reports of recent failures with 8" floppy drives though, so I suggest you use one of those. They must be more reliable, right?
Chernobyl 'not a wildlife haven' - BBC News
after their first scan error, drives are 39 times more likely to fail within 60 days than drives with no such errors
This is easily the most important thing a sysadmin needs to know about hard drives. Much as I love Spinrite, when drives start to fail they continue to fail.
This story reminds me of the run around I got from Dell [India] when my one-and-only-Dell I'm-not-stupid-enough-to buy-their-crap-again started to have seek errors.
I come here for the love
The research results are VERY poorly communicated, as research results often are.
This seems to be the most relevant sentence: "What stands out are the 3 and 4- year old drives, where the trend for higher failures with higher temperature is much more constant and also more pronounced." (Page 5, Section 3.4, 4th paragraph)
Often poor communication in research pages is intended to hide the fact that the results are not very useful. The above sentence can be translated to: "If you run hard drives hot, after 3 or 4 years you will have a high failure rate."
All of our drives have their own vibration-isolated fans. Google, I recommend you do that too, based on your research results.
--
Is U.S. government violence a good in the world, or does violence just cause more violence?
They are hardly trade secrets. Google isn't in the hardware business. There are only so many patterns of disk usage on can have, and knowing what pattern Google has would hardly be useful to figure out how they did anything that they do. At least, to any level of detail useful enough to copy.
The amount of positive press they get from these types of releases easily justifies the effort to polish internal reports up to a publication standard. By releasing these types of papers, others may change their buying habits, which in turn will change the products sold. Google may believe that these types of papers would cause shame, not from individual manufacturers, but the industry in a whole, and thus cause better products to be produced.
Here's a quote from the Google paper: "Power-on hours -- Although we do not dispute that power-on hours might have an effect on drive lifetime, it happens that in our deployment the age of the drive is an excellent approximation for that parameter, given that our drives remain powered on for most of their life time." (Page 10, 4th paragraph)
Translation: The number of hours the drives are powered is the same as the age of the drives, since the drives are always powered.
When two numbers are close to equal, they are approximations for each other. LOL. Is there a social breakdown at Google? Are the people who don't like to think taking power at Google?
... is not only a breakdown by age, but by other parameters, such as size, model, series, etc. I am sure that the IBM DeathStars would have greatly biased the statistics, for example, and it would be useful to have breakouts not only for such well known disasters, but also for the sample excluding the Deathstars, etc.
It is also interesting to note the magnificent jump in failure rates once the drives get outside the three year warrenty period. No coincidence there.
"It is a greater offense to steal men's labor, than their clothes"
An interesting document, and I found the data on temperatures particularly interesting.
I have been previously led to believe that it's not so much the average temperature of a hard drive that causes failure, but temperature fluctuations. This makes sense, since repeated expansion and contraction of the disk platters is likely to cause warpage before too long. This, I guess, is where glass platters like what IBM toyed with would come in useful. In the meantime I guess we still need our HVAC units to keep a constant temperature, just not too low anymore.
This also has implications for data centers that spend a considerable amount of energy pumping heat out of the server room. If we can raise the undustry-accepted temperature ceiling from 22C to say 30C then a lot of energy can be saved over time. Perhaps not quite enough to dip below 1% of US-wide power use but every bit helps.
"Nine times out of ten, starting a fire is not the best way to solve the problem." - my wife
You might be interested in the other best paper award winner (in the shameless self-promotion department): TFS: A Transparent File System for Contributory Storage , by Jim Cipar, Mark Corner, and Emery Berger (Dept. of Computer Science, University of Massachusetts Amherst). Briefly, it describes how you can make all the empty space on your disk available for others to use, without affecting your own use of the disk (no performance impact, and you can still use the space if you need it).
Enjoy!
--
Emery Berger
Dept. of Computer Science
University of Massachusetts Amherst
The program sounds pretty amazing from their web site.
Are many companies using it for preventative maintenance to avoid data loss on their servers?