Jump to content
Search In
  • More options...
Find results that contain...
Find results in...

Optimal temps for Harddisk and SSD

Go to solution Solved by alpenwasser,

Google did a large scale study (pdf) on this (published 2007), in which they conclude that:

We first look at the correlation between average tem-

perature during the observation period and failure. Fig-

ure 4 shows the distribution of drives with average tem-

perature in increments of one degree and the correspond-

ing annualized failure rates. The figure 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.

(Chap. 3.4, "Temperature", p.5)

And again in the conclusion:

One of our key findings has been the lack of a con-

sistent pattern of higher failure rates for higher temper-

ature drives or for those drives at higher utilization lev-

els. 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 reliabil-

ity in the context of a professionally managed data center

deployment.

(Chap. 5, "Conclusions", p12)

If you look at Figure 4 you can see that the optimal temperature is somewhere between

37 and 46 degrees celsius. Also, Figure 5 shows that it's mostly not temperatures but

age which make drives fail.

Note that the study was conducted with consumer grade drives:

In this study we report on the failure characteristics of

consumer-grade disk drives.

(Chap. 5, "Conclusions", p12)

Here's a condensed version if you don't want to read the whole thing.

I highly recommend either looking at Google's study or some condensed version of it,

there's quite a few important results in there. Personally I was actually most surprised

about the fact that higher utilization does apparently not affect drive failure rates.

The temperature thing I kind of expected because HDDs these days use fluid dynamic

bearings which actually work better when temperatures are not too low. Personally I

try to keep my disks around between 38 and 45 C.

Some people says that it's important to keep HDD and SSD cool (in temps).

I'm curious what is the best temps for Hard disk and SSD in general?

 

My temp are 38 degrees(HDD) and 47 degrees (SSD) in my laptop.

 

And also I found it weird that my SSD's temp is higher than my HDD's temp.

I'm using crystaldisk info.

MB :MSI Z77a G45 | Proc: I5 3570K (Stock) | HSF : CM 212X turbo | RAM : Corsair Vengeance 8GB (2X4GB) | VGA : MSI GTX 660 Twin Frozr | PSU : Corsair GS600 | Case : CM Storm Enforcer | Storage :  OCZ Vector 128GB, WD Blue 500GB , Samsung 840 Evo 120GB, WD Blue 1TB

Link to post
Share on other sites

Google did a large scale study (pdf) on this (published 2007), in which they conclude that:

We first look at the correlation between average tem-

perature during the observation period and failure. Fig-

ure 4 shows the distribution of drives with average tem-

perature in increments of one degree and the correspond-

ing annualized failure rates. The figure 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.

(Chap. 3.4, "Temperature", p.5)

And again in the conclusion:

One of our key findings has been the lack of a con-

sistent pattern of higher failure rates for higher temper-

ature drives or for those drives at higher utilization lev-

els. 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 reliabil-

ity in the context of a professionally managed data center

deployment.

(Chap. 5, "Conclusions", p12)

If you look at Figure 4 you can see that the optimal temperature is somewhere between

37 and 46 degrees celsius. Also, Figure 5 shows that it's mostly not temperatures but

age which make drives fail.

Note that the study was conducted with consumer grade drives:

In this study we report on the failure characteristics of

consumer-grade disk drives.

(Chap. 5, "Conclusions", p12)

Here's a condensed version if you don't want to read the whole thing.

I highly recommend either looking at Google's study or some condensed version of it,

there's quite a few important results in there. Personally I was actually most surprised

about the fact that higher utilization does apparently not affect drive failure rates.

The temperature thing I kind of expected because HDDs these days use fluid dynamic

bearings which actually work better when temperatures are not too low. Personally I

try to keep my disks around between 38 and 45 C.

BUILD LOGS: HELIOS - Latest Update: 2015-SEP-06 ::: ZEUS - BOTW 2013-JUN-28 ::: APOLLO - Complete: 2014-MAY-10
OTHER STUFF: Cable Lacing Tutorial ::: What Is ZFS? ::: mincss Primer ::: LSI RAID Card Flashing Tutorial
FORUM INFO: Community Standards ::: The Moderating Team ::: 10TB+ Storage Showoff Topic

Link to post
Share on other sites

ah so my gut-feeling of 40 was correct-ish :P

Haha, it would appear to be the case, yes. :D

Unfortunately I haven't been able to find anything remotely similar about SSDs.

Lots of hear-say, lots of conjecture, but extremely little hard data.

I suppose it's because they just haven't been deployed in large enough numbers

for long enough yet to actually get that data.

BUILD LOGS: HELIOS - Latest Update: 2015-SEP-06 ::: ZEUS - BOTW 2013-JUN-28 ::: APOLLO - Complete: 2014-MAY-10
OTHER STUFF: Cable Lacing Tutorial ::: What Is ZFS? ::: mincss Primer ::: LSI RAID Card Flashing Tutorial
FORUM INFO: Community Standards ::: The Moderating Team ::: 10TB+ Storage Showoff Topic

Link to post
Share on other sites

I also cringe when I see my drives go above 40°C. For some reason, I am not as worried about the SSDs, although my Intel 520 does not report temperatures.

 

EDIT: That's very interesting that higher temperatures do not necessarily mean higher mortality rate. In fact, my friend's HDD suffered a heat stroke (about 70°C in a (poorly-designed?) laptop). It would respond extremely slowly, "develop" bad sectors in such a way that my prognosis at the time was to replace it. However, after a secure erase and placing it in an external enclosure, and except for some minor spin up issue, it was back to normal.

CPU Intel Xeon X5650 | Motherboard ASUS Sabretooth X58 | RAM Corsair Vengeance 1.6GHz 9-9-9-24 24GB | GPU ASUS Dual Series GTX 1060 6GB | Case Fractal Design Define R5 |

Storage Samsung 860 Pro 512GB, WD Black 640GB, WD Green 4TB | PSU Corsair TX750 "v1" | Display ASUS VP247QG + Samsung SyncMaster T220 | Cooling Corsair H80i GT

Link to post
Share on other sites

EDIT: That's very interesting that higher temperatures do not necessarily mean higher mortality rate. In fact, my friend's HDD suffered a heat stroke (about 70°C in a (poorly-designed?) laptop). It would respond extremely slowly, "develop" bad sectors in such a way that my prognosis at the time was to replace it. However, after a secure erase and placing it in an external enclosure, and except for some minor spin up issue, it was back to normal.

Well, 70 C is pretty damn high :D. Most HDDs I've seen are spec'd up to 55 C, and in

the graphs of the Google study mortality rate does rise again above 46 C. Personally

I tolerate short term temps of ~50 C, but not for longer amounts of time. Of course

this can be rather tricky if you have a laptop.

It's interesting that it went back to normal though.

BUILD LOGS: HELIOS - Latest Update: 2015-SEP-06 ::: ZEUS - BOTW 2013-JUN-28 ::: APOLLO - Complete: 2014-MAY-10
OTHER STUFF: Cable Lacing Tutorial ::: What Is ZFS? ::: mincss Primer ::: LSI RAID Card Flashing Tutorial
FORUM INFO: Community Standards ::: The Moderating Team ::: 10TB+ Storage Showoff Topic

Link to post
Share on other sites

Well, 70 C is pretty damn high :D. Most HDDs I've seen are spec'd up to 55 C, and in

the graphs of the Google study mortality rate does rise again above 46 C.

Oh, darn I was reading the graph incorrectly...  :blush:

 

Personally

I tolerate short term temps of ~50 C, but not for longer amounts of time. Of course

this can be rather tricky if you have a laptop.

Most laptops' HDD compartments are closer to the bottom, so a laptop cooler will help. I also recommended my friend to buy it in order to keep the new HDD happy. If a cooler is not a viable solution for whatever reason, then I agree it is harder to manage the temperatures.

 

It's interesting that it went back to normal though.

That was a surprise for me too. However, like I said, there were some minor spin up issue. It does not want to wake up at all after about a day's worth of down time, but the second time it receives power, it will start properly. So "normal" is very subjective. However, none of the slowness remained. Even still, because of that spin up behaviour, at most, it is only suitable for large file transfers over sneaker-net anyway.

I tried this on some other failing drives too, but they were not as memorable. All I remember was one of them decided to make the SMART information become permanently unintelligible, and the other one kept the number of bad sectors.

CPU Intel Xeon X5650 | Motherboard ASUS Sabretooth X58 | RAM Corsair Vengeance 1.6GHz 9-9-9-24 24GB | GPU ASUS Dual Series GTX 1060 6GB | Case Fractal Design Define R5 |

Storage Samsung 860 Pro 512GB, WD Black 640GB, WD Green 4TB | PSU Corsair TX750 "v1" | Display ASUS VP247QG + Samsung SyncMaster T220 | Cooling Corsair H80i GT

Link to post
Share on other sites

What scares me is my SSD is 47 degrees (in a HP laptop though (Not the best cooling laptop brand) ).

 

Thanks for the rep guys.

MB :MSI Z77a G45 | Proc: I5 3570K (Stock) | HSF : CM 212X turbo | RAM : Corsair Vengeance 8GB (2X4GB) | VGA : MSI GTX 660 Twin Frozr | PSU : Corsair GS600 | Case : CM Storm Enforcer | Storage :  OCZ Vector 128GB, WD Blue 500GB , Samsung 840 Evo 120GB, WD Blue 1TB

Link to post
Share on other sites
  • 11 months later...
  • 1 year later...

I have a samsung 850 evo that will not go above 26C. does it matter that it is below google's "optimal temperature?"

The study was for hard drives. I don't think an SSD will care that much as long as it

doesn't cook as it does not have any mechanical parts (bearings, specifically) which

could suffer damage due to lower-than-optimal temperatures, at least as far as I know.

BUILD LOGS: HELIOS - Latest Update: 2015-SEP-06 ::: ZEUS - BOTW 2013-JUN-28 ::: APOLLO - Complete: 2014-MAY-10
OTHER STUFF: Cable Lacing Tutorial ::: What Is ZFS? ::: mincss Primer ::: LSI RAID Card Flashing Tutorial
FORUM INFO: Community Standards ::: The Moderating Team ::: 10TB+ Storage Showoff Topic

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

×