How smart is S.M.A.R.T.?

Wayne Davis waydavis at centurylink.net
Sat Oct 18 22:19:24 MST 2014 

Excellent info and exactly what (I)/we needed to know.

After writing my bit, I realized that WD was what I prefer. Maxtor has 
gone downhill in my opinion.

Interesting that your company uses consumer grade goodies with a fail 
rate nearly the same.

I may just go THAT route on my next replacement  cycle.


THANKS!





On 10/18/2014 12:30 PM, Joseph Sinclair wrote:
> Wayne,
>    I don't work in a datacenter, but I do (occasionally) do hardware selection for a variety of machines specifying anywhere from 1 to around 2,000 machines at a time.
> These are my thoughts on the topic:
> 1) Google did a fleet analysis a few years back tracking over 100,000 "consumer" drives [1] which shows that they're pretty reliable in large fleets.
>     The Google machine fleet is all "consumer" drives, because an earlier (unpublished) analysis showed insufficient real-world difference in failure rates to justify the much higher cost.
>     Enterprise drives often perform better, use less power, or have better interaction with RAID cards, but I wouldn't buy them just for reliability unless my storage design and data criticality justified the cost increment.
>     Backblaze publishes continuing data on reliability for their entire drive fleet; it's not an ideal sample set, but it is still useful to see failure rates in a real (albeit extremely cost-conscious) environment [2].
> 2) While many corporate datacenters still run things like RAID and enterprise drives, the largest machine fleets are using distributed computing solutions that deliberately pick the least expensive drives and tolerate higher failure rates.
> 3) I've been working with primarily large distributed computing systems for some years.  I generally pick drives in two different ways:
>    a) For desktops, I select medium reliability consumer drives; WD works well for those at the moment, but it changes year-to-year.
>    b) For "Enterprise" servers, where the platform stack cannot recover from failure (e.g. SQL databases, or NFS file servers) I pick the high-end "enterprise" drives, run frequent *verified* backups, and use RAID (10 if possible, 5 or 6 otherwise).
>    c) For laptops, assume the drive will fail at or near 3 years (18 months if running consumer Windows versions).  The laptop environment is just a bit harsh on spinning platters, and rewrite rate tends to be high for consumer SSD.
>    d) For really large fleets in distributed systems (OpenStack, Hadoop, Riak, Ceph, Cassandra, Mesos, etc...) where single cluster purchases are in the thousands of machines (at 12-48 drives each), I pick the cheapest large-volume purchase contract the company can get.
>       Drives will fail frequently, if they fail in less than 3 months they get returned defective; after that they almost always last about 3 years, at which point the entire machine is usually depreciated out and replaced.
>
> Hopefully that's helpful, Wayne.
>
> [1] : http://research.google.com/archive/disk_failures.pdf
> [2] : https://www.backblaze.com/blog/hard-drive-reliability-update-september-2014/
>
> On 10/18/2014 08:19 AM, Wayne Davis wrote:
>> It has been my experience that Seagate, and ONLY Seagate drives eventually suffer from "Sticktion".   BBS runners from back in the day are WELL aware of this phenomenon.
>> Further, PERSONALLY, I've had VERY bad luck with Seagate.   They didn't fail gracefully, with warning.  Boot today, Tits Up tomorrow.
>>
>> Unfortunately maybe, (I) just replaced MY primary data drive with a high-end Hitachi 4 TB.  I replace this drive every 4 Years MAX, even if it appears to work fine.
>> The Hitachi was purchased because I have them in a some laptops and they have performed quite well.
>>
>> MY _favorite_ _has_ long been Maxtor but I'm SURE someone will say they suck too. Them, and nearly every other too.   You know the saying: "Opinions are like....  Everyone has one" The topic, is quite subjective.   Like everything, the top dog never remains static so for ME it may be time to re-evaluate also. Look at HP printers and Brother.  HP was top, NOW I think Brother is WAYYY better.
>>
>> If anyone here on the list works in a data center.  They would know first person about drive deaths, but being a data center, they'll more than likely use only enterprise class drives, which as we all know are levels above the stuff in a typical home system.  Like everything, cars, blenders, etc,  there are certain models from each manufacturer that are garbage. *(I) would tend to take advise from someone who uses NON-enterprise drives over years **_and_**en-mass. **If anyone here on the list qualifies, I TOO would like to hear what **_you_**have to say since you are literally on the front-lines.**
>> *
>>
>>
>>
>>
>>
>> On 10/18/2014 07:30 AM, Keith Smith wrote:
>>> Sorry to hear Seagate is not as good as Hitachi.  As I recall, there was a discussion on this list about who was the best and I think Hitachi took a lot of hits.  I think Dell puts Seagate drives in their boxes.
>>>
>>> What manufacture makes the best today?
>>>
>>>
>>>
>>>
>>> On 2014-10-17 22:05, Brian Cluff wrote:
>>>> Seagate has been cranking out such bad drives lately, I think I would
>>>> rather have a used hitachi than a new seagate.
>>>>
>>>> Brian Cluff
>>>>
>>>> On 10/17/2014 08:43 AM, techlists at phpcoderusa.com wrote:
>>>>> If you have credible evidence that Seagate is selling used Hitachi
>>>>> drives as new and under their label I'm sure your State Attorney General
>>>>> would like to hear from you.
>>>>>
>>>>>
>>>>>
>>>>>
>>>>> On 2014-10-17 10:08, George Toft wrote:
>>>>>> How many [thousand] hours on the drive?  I think you're gambling if
>>>>>> you have more than 26,000 hours (3 years) and ESPECIALLY if it's
>>>>>> really a Hitachi drive.  Seagate bought Hitachi recently, and from
>>>>>> what I've seen, are selling used Hitachi drives as "new" Seagate
>>>>>> drives - check the model number and the run hours!
>>>>>>
>>>>>> Hard drives are killing me this year - I've spent over 80 hours in
>>>>>> rework because of failed drives - especially with Seatachi drives (see
>>>>>> above).  80 hours of rework at no pay is a painful lesson.
>>>>>>
>>>>>> Regards,
>>>>>>
>>>>>> George Toft
>>>>>>
>>>>>> On 9/11/2014 4:06 PM, parabellum7 at yahoo.com wrote:
>>>>>>> Greetings!
>>>>>>>
>>>>>>>
>>>>>>> I have a 500GB Seagate ST3500312CS SATA drive salvaged from a
>>>>>>> decommissioned DVR. The DVR's OS said SMART status OK. The latest
>>>>>>> Seatools disk utility from the Seagate website says the drive is A-OK
>>>>>>> (short test, long test, full erase, re-test) no errors found.
>>>>>>>
>>>>>>> However, the Gnome disk utility in Mint 17 says 'Threshold not
>>>>>>> exceeded' and 'Disk is OK, 178 bad sectors'.
>>>>>>>
>>>>>>> Some other SMART attributes displayed:
>>>>>>>
>>>>>>> ID1        Read Error Rate: 152141757
>>>>>>> ID5      Reallocated Sector Count: 178 sectors
>>>>>>> ID187     Reported Uncorrectable Errors: 0 sectors
>>>>>>> ID198    Uncorrectable Sector Count: 0 sectors
>>>>>>> ID199    UDMA CRC Error Rate: 0
>>>>>>>
>>>>>>>
>>>>>>> GSmart Control 0.8.7 is reading the same thing, 178 sectors, but also
>>>>>>> says it's OK.
>>>>>>>
>>>>>>> running an e2fsck from gparted reports 0 bad blocks.
>>>>>>>
>>>>>>> I've also retested in another machine with different cables to
>>>>>>> minimize the possibility of bogus hardware or BIOS issues, but the
>>>>>>> results remain the same.
>>>>>>>
>>>>>>> Seagate's website has a FAQ that says their tools should be the final
>>>>>>> say as they're designed to work correctly with their drives.
>>>>>>>
>>>>>>> Normally a bad sector or two wouldn't bother me, I have drives that
>>>>>>> have been running for years like that. I just keep backups fresh and
>>>>>>> check for bad sector growth. A few bad sectors is within spec and
>>>>>>> that's why HDD's have a reserved area. Yet somehow 178 sectors seems
>>>>>>> like a lot.
>>>>>>>
>>>>>>> Should I trust this drive for anything more than a paperweight?
>>>>>>>
>>>>>>> Should I trust anything with the words 'smart', 'affordable', or
>>>>>>> 'free' in the name?  ;]
>>>>>>>
>>>>>>>
>>>>>>> Thanks!
>>>>>>>
>>>>>>>
>>>>>>> --Kenn
>>>>>>> ---------------------------------------------------
>>>>>>> PLUG-discuss mailing list - PLUG-discuss at lists.phxlinux.org
>>>>>>> To subscribe, unsubscribe, or to change your mail settings:
>>>>>>> http://lists.phxlinux.org/mailman/listinfo/plug-discuss
>>>>>>>
>>>>>> ---------------------------------------------------
>>>>>> PLUG-discuss mailing list - PLUG-discuss at lists.phxlinux.org
>>>>>> To subscribe, unsubscribe, or to change your mail settings:
>>>>>> http://lists.phxlinux.org/mailman/listinfo/plug-discuss
>>>>> ---------------------------------------------------
>>>>> PLUG-discuss mailing list - PLUG-discuss at lists.phxlinux.org
>>>>> To subscribe, unsubscribe, or to change your mail settings:
>>>>> http://lists.phxlinux.org/mailman/listinfo/plug-discuss
>>>>>
>>>> ---------------------------------------------------
>>>> PLUG-discuss mailing list - PLUG-discuss at lists.phxlinux.org
>>>> To subscribe, unsubscribe, or to change your mail settings:
>>>> http://lists.phxlinux.org/mailman/listinfo/plug-discuss
>>
>>
>>
>> ---------------------------------------------------
>> PLUG-discuss mailing list - PLUG-discuss at lists.phxlinux.org
>> To subscribe, unsubscribe, or to change your mail settings:
>> http://lists.phxlinux.org/mailman/listinfo/plug-discuss
>>
>
>
> ---------------------------------------------------
> PLUG-discuss mailing list - PLUG-discuss at lists.phxlinux.org
> To subscribe, unsubscribe, or to change your mail settings:
> http://lists.phxlinux.org/mailman/listinfo/plug-discuss

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.phxlinux.org/pipermail/plug-discuss/attachments/20141018/77a2097d/attachment.html>

More information about the PLUG-discuss mailing list