Has SMART ever successfully predicted failure for anybody here?

[Will Dormann]

SMART monitoring sounds like a great idea to me. Who better to predict
a drive's failure than the drive itself, right? I mean, the drive knows
what it's doing internally, such as silently remapping bad sectors,
keeping track of how long it takes to spin up, error counts and all that
fun stuff.

SMART is there, comforting me.
Calling out "I'm good. I'll never let you down"

And then another drive begins to show symptoms of impending failure. In
my particular case, it's a Seagate Barracuda V. Just a couple months
past the expiration of the 1-year warranty.

And I start to realize that I can't recall a single case where SMART has
predicted a failure before I actually see the symptoms of the failing
drive. Not in any of the machines I own, or in machines of other people
I know. I've used HDD Health, DTemp, Promise Fastcheck, smartmontools
and ide-smart (on linux), and various manufacturer's utilities for
checking smart.

I've been able to monitor temperatures (it's at 37C right now, which
seems to be the norm for it), and I can look at statistics on the drive.
But not once has SMART actually predicted problems with a drive
before I actually see the symptoms (such as a repeated "thunk" sound, a
frozen mouse in Win2k with the HDD light on solid, or event log entries
indicating a drive error). Doing a full surface scan in all such cases
has indicated bad sectors on the drive.

Is SMART not predictive enough? Is this a fault of the various SMART
monitoring utilities? If SMART doesn't "kick in" until later on in the
dying process, then what good is it? (If I can see the symptoms well in
advance of it giving me a warning) What are your experiences with SMART
and its (in)ability to predict failure?

Thanks.
-WD

 

[Rod Speed]

SMART monitoring sounds like a great idea to me. Who
better to predict a drive's failure than the drive itself, right?
I mean, the drive knows what it's doing internally, such as
silently remapping bad sectors, keeping track of how long
it takes to spin up, error counts and all that fun stuff.

SMART is there, comforting me.
Calling out "I'm good. I'll never let you down"

It doesnt say that, just that its better than nothing.

And then another drive begins to show symptoms of impending
failure. In my particular case, it's a Seagate Barracuda V.
Just a couple months past the expiration of the 1-year warranty.

And I start to realize that I can't recall a single case where
SMART has predicted a failure before I actually see the
symptoms of the failing drive. Not in any of the machines
I own, or in machines of other people I know.

There have been some examples reported in here.

And should have helped with the most common
75GXP failures if it had been implemented properly.

And its obviously never going to help with
sudden semiconductor failure for example.
Or lots of other causes of hard drive failure
like the power supply dying and killing the drive.

I've used HDD Health, DTemp, Promise Fastcheck,
smartmontools and ide-smart (on linux), and various
manufacturer's utilities for checking smart.

I've been able to monitor temperatures

And that alone is quite handy, being a very convenient
way to keep track of what the drive temp is doing in the
worst conditions of high room temp and drive activity.

That does show that Dell laptops generally run their
hard drives at higher temps than I would do voluntarily.
Even tho they are technically within the allowed temp.

It also allows you to run something like MBM to
bring up alarms on temperature excursions that
are due to fan failure or just fur clogging etc.

(it's at 37C right now, which seems to be the norm
for it), and I can look at statistics on the drive.

But not once has SMART actually predicted problems
with a drive before I actually see the symptoms (such
as a repeated "thunk" sound, a frozen mouse in Win2k
with the HDD light on solid, or event log entries
indicating a drive error).

Sure, but with drive failure so rare, thats hardly
surprising given that SMART was never ever
claimed to be able to anticipate all hard drive failures.

I havent actually had a drive failure in any system
I own or look after since SMART showed up with
the exception of a single Fujitsu MPA drive that
has some dry joint or cracked trace problem that
can see it not spin up unless you deliberately apply
pressure one way to the molex power connector.

I dont need SMART to tell me that its not spinning up.

Doing a full surface scan in all such cases
has indicated bad sectors on the drive.

Then that particular SMART implementation is
inadequate because it would be better if you
were warned that new bads have appeared.

Is SMART not predictive enough?

Clearly in that particular example its not implemented
well enough if you did actually have the bios SMART
check enabled and the SMART was just incapable
of reporting the problem it had observed.

Is this a fault of the various SMART monitoring utilities?

It certainly can be.

If SMART doesn't "kick in" until later on
in the dying process, then what good is it?

Sure, but thats not cast in stone.

(If I can see the symptoms well in advance of it giving me a warning)
What are your experiences with SMART and its (in)ability to predict failure?

I basically havent had any failures since SMART showed up where
even if it was perfectly implemented, it would have helped.

Thats not to say that others havent had hard drive failures
that should have produced a SMART warning tho.

 

[Joep]

SMART monitoring sounds like a great idea to me. Who better to predict
a drive's failure than the drive itself, right? I mean, the drive knows
what it's doing internally, such as silently remapping bad sectors,
keeping track of how long it takes to spin up, error counts and all that
fun stuff.

SMART is there, comforting me.
Calling out "I'm good. I'll never let you down"

Nope, that's where you're wrong. Not all faillures are predictable. No SMART
alarms by no means indicates that the drive will not let you down. Using
SMART you *may* be able to to predict failures that are predictable, that's
the best SMART can do. A drive can die without SMART *ever* predicting it.

 

[Mr. Grinch]

Have you any favourites among the SMART monitoring software?

I started trying some the other night. Most are pretty limited, and will
only show the motherboard attached drives. I've got 3 more on a Promise
Ultra133 that I'd like to examine now and then but looks like I'd have to
buy a tool to do that.

I have not checked out the most recent tools from the vendors yet. The
drives are IBM and Maxtor. I wasn't sure if they offered any windows based
SMART monitors for free.

 

[Bruce Allen]

Is SMART not predictive enough? Is this a fault of the various SMART

monitoring utilities? If SMART doesn't "kick in" until later on in the
dying process, then what good is it? (If I can see the symptoms well in
advance of it giving me a warning) What are your experiences with SMART
and its (in)ability to predict failure?

I've been monitoring about 1100 ATA disk drives (IBM and Maxtor) on
two large linux data analysis clusters for the past two years. I've
seen more than forty failures -- SMART has predicted between half and
two-thirds of those. I've also had advanced warning of *other* types
of 'non-failure' problems, particularly unreadable (uncorrectable)
disk sectors which *would* have caused unpredictable and unrepeatable
errors with the OS and data analysis.

The bottom line is that SMART can not and will not predict all
failures. But in many cases (especially if you or the monitoring
software know what to watch for) it will predict a substantial
fraction of them.

Bruce Allen

 

[Will Dormann]

Have you any favourites among the SMART monitoring software?

I started trying some the other night. Most are pretty limited, and will
only show the motherboard attached drives. I've got 3 more on a Promise
Ultra133 that I'd like to examine now and then but looks like I'd have to
buy a tool to do that.

Smartmon is junk, HDD Health is nice once you turn off the non-critical
alerts (like a change in temp of 1 degree... no need to keep popping up
alerts for that). I'm currently using DTemp, since it puts the temp
of the drive in the windows sytem tray.

I have a drive on a promise controller (MBFastTrack133) that isn't
supported by those programs, so I need to run Promise's FastCheck
utility. It just gives me a "Functional" report on the drive and
nothing else, but I guess that's better than nothing.


-WD

 

[Folkert Rienstra]

Smartmon is junk,

David Lethe will be so pleased to know.

 

[Folkert Rienstra]

Have you any favourites among the SMART monitoring software?

I started trying some the other night.

Most are pretty limited, and will only show the motherboard attached drives.
Most?

I've got 3 more on a Promise Ultra133 that I'd like to examine now and then
but looks like I'd have to buy a tool to do that.

The Promise drivers may not support S.M.A.R.T. and therefor no software
will show you S.M.A.R.T. data.

 

[Mike Tomlinson]

What are your experiences with SMART
and its (in)ability to predict failure?

I worked as a bench tech fixing Compaq machines under warranty. Saw
many dozens of machines which would produce a "SMART Predicts Imminent
Disk Failure" message on bootup when the drive was failing.

Drive replacement was covered by Compaq's 3 year warranty even if it had
not actually yet failed, allowing data to be transferred from the old
drive to the warranty replacement while it was still functional.

 

[Will Dormann]

David Lethe will be so pleased to know.

I'm sure he will be. To be fair, the software may have some technical
merits. But it's definately a candidate for the User Interface Hall Of
Shame in my book.


-WD

 

[Rod Speed]

I'm sure he will be. To be fair, the software may have some technical
merits. But it's definately a candidate for the User Interface Hall Of
Shame in my book.

Mine too.

The Author's Attitude Hall of Shame, too |-)

 

[Mr. Grinch]

Most?

All the one's I've tried so far. One claims to show the devices on other
controllers but you have to buy it first. I was hoping to find something
I'd not have to buy that would show SMART status on the installed
controller.

The Promise drivers may not support S.M.A.R.T. and therefor no
software will show you S.M.A.R.T. data.

That's correct. I know the controller supports SMART, but the driver is
anyone's guess.

It's hard to say for sure without trying out some SMART software is capable
of showing info for installed controllers. So far I've only found one that
claims to do this but you have to buy it first.

 

[Mark M]

Smartmon is junk, HDD Health is nice once you turn off the
non-critical alerts (like a change in temp of 1 degree... no
need to keep popping up alerts for that). I'm currently
using DTemp, since it puts the temp of the drive in the
windows sytem tray.

I like DTEMP too. It is simple and fulfills a straightforward
need.

The trouble is that I installed an IDE controller card and put a
coule of drive on it. Now DTEMP (and Motherboard Monitor) can't
report on the temp of those drives on the controller.

I have a drive on a promise controller (MBFastTrack133) that
isn't supported by those programs, so I need to run Promise's
FastCheck utility. It just gives me a "Functional" report on
the drive and nothing else, but I guess that's better than
nothing.

My card uses the Silicon Image chip SiL0680.
http://www.siimage.com/products/overview_sii0680.asp
(Thanks Eric - it works nicely.)

I haven't run the Medley software which comes with my card but the
documentation suggests it is like your FastCheck utility.

Is there any way around not getting temp and other SMART data from
drives attached to such cards?

 

[puss]

The Promise drivers may not support S.M.A.R.T. and therefor no software
will show you S.M.A.R.T. data.

They do as I have ued it , so get the correct SMART Program..

 

[puss]

The Promise drivers may not support S.M.A.R.T. and therefor no software
will show you S.M.A.R.T. data.

Active SMART works..

 

[puss]

All the one's I've tried so far. One claims to show the devices on other
controllers but you have to buy it first. I was hoping to find something
I'd not have to buy that would show SMART status on the installed
controller.

Try Active SMART as it works for me.

 

[Mr. Grinch]

(e-mail address removed) wrote in

Try Active SMART as it works for me.

Tried it, but no luck.

According to the FAQ in the helpfile for Active Smart 2.41 (and Active
Smart SCSI 2.41):

Quote:

Does Active SMART supports Promise Ultra 100 controller (or controllers on
HighPoint chipsets)?

Current version does not support drives on external IDE controllers, that
uses HighPoint or Promise chipsets, but we work on this and support for
HighPoint and possible Promise IDE RAID cards will be added to our
software.

 

[Terence H. Bartlett]

(e-mail address removed) wrote in


Tried it, but no luck.

According to the FAQ in the helpfile for Active Smart 2.41 (and Active
Smart SCSI 2.41):

Quote:

Does Active SMART supports Promise Ultra 100 controller (or controllers on
HighPoint chipsets)?

Current version does not support drives on external IDE controllers, that
uses HighPoint or Promise chipsets, but we work on this and support for
HighPoint and possible Promise IDE RAID cards will be added to our
software.

Active Smart works for my WD drives on both Promise Ultra 133TX (Win
XP) and Ultra 100 (Win98) controller cards. I have two Computers with
different controllers and operating systems.
It does not work on an IDE raid controller with disks configued as a
raid array, because I tried the SCSI version at work on an IDE Raid
Array and the data it gave was garbage.

Hence I think the author is trying to say his utility will not
currently work with Promise Raid controller cards where the disks
installed as a Raid Array.

regards
Terry Bartlett

 

[Mr. Grinch]

Hence I think the author is trying to say his utility will not
currently work with Promise Raid controller cards where the disks
installed as a Raid Array.

Ahh, got ya. For some reason, the product does not see my attached
Ultra133 non-raid controller. Strange. I'm running the latest firmware,
and the .42 driver. Have not upgraded to the .43 driver as I didn't want
to "break" anything but perhaps that's what I need to do.

Thanks again.

 

[David Chien]

Both WD (DLGDIAG for Windows) and IBM give away free SMART HD monitoring
tools, and there are many other freeware programs that'll read SMART
info off your HDs and display them (eg. http://www.hdtune.com/

(funny! Active Smart's screen shot of the SMART info looks almost like
the WD one!)

They both work and saved my data before. Also, most PCs with SMART
turned on in BIOS will report HD problems as well on the next bootup,
which has also saved me in the past.

Keep in mind that all these tools do is to query the HD and report the
current SMART parameters that have been saved on the HD memory -- none
of these programs can do more than just that and alerting you!

I seriously would not bother paying for a tool that's free.

As an example of some of the stored parameters they all report:
(Not all parameters are reported by all drives!)

HD Tune: WDC WD200BB-32CJA0 SMART information

ID Current Worst Treshold Data
(01) Raw Read Error Rate 200 198 51 0
(03) Spin Up Time 96 93 21 2575
(04) Start/Stop Count 100 100 40 364
(05) Reallocated Sector Count 200 200 140 0
(07) Seek Error Rate 200 200 51 0
(09) Power On Hours Count 88 88 0 9131
(0A) Spin Retry Count 100 100 51 0
(0B) Calibration Retry Count 100 100 51 0
(0C) Power Cycle Count 100 100 0 307
(C4) Reallocated Event Count 200 200 0 0
(C5) Current Pending Sector 200 173 0 0
(C6) Offline Uncorrectable 200 200 0 0
(C7) Ultra DMA CRC Error Count 200 253 0 7569
(C8) Write Error Rate 200 200 51 0

Temperature : unknown
Power On Time : 9131