Heat doesn't kill hard drives. Here's what does

[Brink]

"Free-cooled" datacenters use ambient outside air instead of air conditioning. That lets us see how environment affects system components. Biggest surprise: temperature is not the disk drive killing monster we thought. Here's what is.

At last months Usenix FAST 16 conference, in the Best Paper award winner Environmental Conditions and Disk Reliability in Free-cooled Datacenters, researchers Ioannis Manousakis and Thu D. Nguyen, of Rutgers, Sriram Sankar of GoDaddy, and Gregg McKnight and Ricardo Bianchini of Microsoft, studied how the higher and more variable temperatures and humidity of free-cooling affect hardware components. They reached three key conclusions:

• Relative humidity, not higher or more variable temperatures, has a dominant impact on disk failures.
• High relative humidity causes disk failures largely due to controller/adapter malfunction.
• Despite the higher failure rates, software to mask failures and enable free-cooling is a huge money-saver.

Background

Datacenters are energy hogs. A web-scale datacenter can use more than 30 megawatts and collectively they are estimated to use 2 percent of US electricity production.

Moreover, the chillers for water cooling and the backup power required to keep them running in a blackout are costly too. As the use of cloud services has grown, the cost of hyperscale datacenters has led to more experimentation such as free-cooling and higher operating temperatures.

But to fully optimize these techniques, operators also need to understand their impact on the equipment. If lower energy costs are offset by higher hardware costs and downtime, it isn't a win.

The study

The researchers looked at 9 Microsoft datacenters around the world for periods ranging from 1.5 to 4 years, covering over 1 million drives. They gathered environmental data including temperature and relative humidity and the variation of each.

Being good scientists, they took the data and built a model to analyze the results. They quantified the trade-offs between energy, environment, reliability, and cost. Finally, they have some suggestions for datacenter design...

Read more: Heat doesn't kill hard drives. Here's what does | ZDNet

 

[ThrashZone]

Being in Texas I can relate to humidity and dehumidifiers
The weird thing is it took them this long to figure out humidity is a bad thing for hdd's
Next someone will say it's bad for all electronics

 

[Indianatone]

Here you go Thrashzone. Humidity is very bad for electronics especially if it condenses into water....It is not as bad as it used to be with CRT displays. The focus voltage was between 4K volts and 8K volts and the final anode 20K volts to 30K volts for colour CRT's. Humidity played havoc with the final anode with flash over (a loud crack that scared the s**t out of people) and a constant corona sizzle which you could smell with ozone. Oh yeah we are all better off with LCD displays......Humidity is bad for all electronics.

 

[ThrashZone]

Took a really silly person to use outside air and no dehumidifier system in it
Wonder how much they paid for someone to connect the dots

 

[Layback Bear]

High humidity can also play hell with all connectors to electronics.
When you are dealing with such small amounts of volts and amps it doesn't take much corrosion on a connector to cause problems.

The corrosion will not be visible to the human eye. It's a bacteria in some cases. Bacteria just love high humidity to bath in.

Air conditioners are also dehumidifiers. That is why you see the water run out the back or bottom of them.

 

[fireberd]

The large Federal government agency where I worked (until retirement) had regional data centers, regional LAN/WAN Network gateway systems and hardware help desk (where I worked) and the main headquarters computer center. Most of the equipment in these centers were "big iron" (IBM Mainframe and comm processors) and required lots of air conditioning. Outside air wouldn't do it for those types of systems. If we had an commercial electrical power outage we would last about 30 minutes without Air Condition, just on air circulating in the computer room, before we either manual shutdown equipment or it shut itself down (We had UPS that had about 1 hour of backup AC power) . Our field offices were in varying environments (buildings) and we had a lot of equipment failures related to heat/humidity/AC power. The environmental conditions (e.g. heat) would not show up immediately but some point later there would be failures that were traced back to environment conditions at some previous point. When the agency offices were upgraded from "dumb" terminals (IBM 3270 series) to Client Server LAN's the agency wide requirement for the file server, communications (modem, bridge, IBM token ring CAU's and LAM's) UPS to be in a controlled environment room. (AC power for the LAN systems and workstations (PC's) also required Hubbell IG5262 (Orange) Isolated ground AC Receptacles and third wire ground tied directly from the receptacle to the AC power panel's ground).

 

[themorus]

We don't have to worry about that over here in Ireland, I suppose it's one of the reasons that Google, Facebook and Twitter have their European headquarters over here.

 

[ThrashZone]

It doesn't rain in Ireland

 

[Lady Fitzgerald]

It doesn't rain in Ireland

True. Some days just aren't as soft as some others.

 

[ThrashZone]

Possibly they have a dry rain like in Arizona it evaporates when it hits 1000ft

 

[georgeks]

If anyone is interested in facts, here's the Failure Trends in a Large Disk Drive Population report published by Google back in 2007.
http://static.googleusercontent.com/media/research.google.com/en//archive/disk_failures.pdf
Additional link I have found useful:S.M.A.R.T. - Wikipedia, the free encyclopedia

Just the fact that Google's server infrastructure is estimated in excess of 450.000 systems, and used consumer-grade Hard Disks ranging between 80 to 400 GB capacities, makes the report -at least -interesting.

More than 100,000 drives were covered, manufactured from 2001 on-wards. Rotational speeds ranged from 5400 to 72000rpm, and were various (9) models from different well-known and established manufacturers.

Google claims that collection and storage of “vital information" about all of its systems occurs every few minutes.

 

[mjf]

Interesting but the negative impact of humidity and electronics isn't a surprise. In Asia/Pacific regions of high relative humidity are common. Where I live it tends to be a dry heat but evaporative air conditioners are common resulting in cool air but higher humidity.
I think the solution is fans and good ventilation for your HDDs and your PC in general.

 

[themorus]

It doesn't rain in Ireland

I should have clarified, we have low humidity even though it rains most days of the year, we have a temperate climate, it's never too cold or warm.

 

[tinmar49]

Helium filled drives have been available for years, they have to be hermetically sealed so they are proof against humidity changes. Their price must have come down by now.

 

[mjf]

The study stated:
"High relative humidity causes disk failures largely due to controller/adapter malfunction."
Not platter failure.
On standard drives this electronics is open to the environment. Maybe there is for it to be sealed to some extent as well.