Hard disk and reliability
-
Found on http://en.wikibooks.org/wiki/Minimizing_Hard_Disk_Drive_Failure_and_Data_Loss/Stress_Control[^] "Based on professional experience of system administrators, it is believed that there is a direct relationship between the number of power cycles of a computer and the probability of failure of its drives. In other words, a computer with a high uptime may have a lower probability of drive failure than one that has its power cycled routinely." Question is, is this a cliché, or is this a verified assertion? What is your experience on this in the real life, outside the testing labs? And more generally, did you make any correlation between a human behavior and computer reliability? (punching the hardware excepted :) )
When they kick at your front door How you gonna come? With your hands on your head Or on the trigger of your gun?
Empirically, and without any real research, I think it does make sense. Think about it, most things fail when you turn them on. When was the last time a light bulb blew while you were reading? As opposed to the last time you turned it on and it went "Plink" and flashed before dying?
Ideological Purity is no substitute for being able to stick your thumb down a pipe to stop the water
-
Google did a whole lot of research on this and were surprised by their findings - they discovered the more a disk is used the longer it lasts. The wanted to know the lifespan of their disks and discovered that the least used disks had amongst the highest failure rates. You could probably find an article on this somewhere on... it's on the tip of my tongue... ah yes I remember... Yahoo...
“That which can be asserted without evidence, can be dismissed without evidence.”
― Christopher Hitchens
The website I mention talks also about the Google's study (you can find it here[^]) . I remember at the time of the release of this study being surprised by their conclusion on the thermal environment, 'Hard drives with average temperatures below 27 °C had a failure rate worse than hard drives with the highest reported average temperature of 50 °C, and a failure rate at least twice as high as the optimum temperature range of 37 °C to 46 °C'. However, in this study they could not really see the impact of power cycling, as they say,
Quote:
"In a server-class deployment, in which drives are powered continuously, we do not expect to reach high enough power cycle counts to see any effects on failure rates."
When they kick at your front door How you gonna come? With your hands on your head Or on the trigger of your gun?
-
Empirically, and without any real research, I think it does make sense. Think about it, most things fail when you turn them on. When was the last time a light bulb blew while you were reading? As opposed to the last time you turned it on and it went "Plink" and flashed before dying?
Ideological Purity is no substitute for being able to stick your thumb down a pipe to stop the water
Yes, I've got the same feeling, mechanical stress seems higher with power cycling, however since I learned that colder hard disks are less reliable than hotter ones, I'm a little bit less confident in my intuition :)
When they kick at your front door How you gonna come? With your hands on your head Or on the trigger of your gun?
-
Found on http://en.wikibooks.org/wiki/Minimizing_Hard_Disk_Drive_Failure_and_Data_Loss/Stress_Control[^] "Based on professional experience of system administrators, it is believed that there is a direct relationship between the number of power cycles of a computer and the probability of failure of its drives. In other words, a computer with a high uptime may have a lower probability of drive failure than one that has its power cycled routinely." Question is, is this a cliché, or is this a verified assertion? What is your experience on this in the real life, outside the testing labs? And more generally, did you make any correlation between a human behavior and computer reliability? (punching the hardware excepted :) )
When they kick at your front door How you gonna come? With your hands on your head Or on the trigger of your gun?
KaЯl wrote:
What is your experience on this in the real life
My PC at home runs 24/7. Since circa 1993, I have only had 2 drives die on me.
-
KaЯl wrote:
What is your experience on this in the real life
My PC at home runs 24/7. Since circa 1993, I have only had 2 drives die on me.
You've been running the same PC since 1993 ? Don't you think it's time for an upgrade ? :-D
When I was a coder, we worked on algorithms. Today, we memorize APIs for countless libraries — those libraries have the algorithms - Eric Allman
-
You've been running the same PC since 1993 ? Don't you think it's time for an upgrade ? :-D
When I was a coder, we worked on algorithms. Today, we memorize APIs for countless libraries — those libraries have the algorithms - Eric Allman
No - he has developed a technique of hot-swapping processors!
Ideological Purity is no substitute for being able to stick your thumb down a pipe to stop the water
-
No - he has developed a technique of hot-swapping processors!
Ideological Purity is no substitute for being able to stick your thumb down a pipe to stop the water
Now there's an article worth reading :laugh:
When I was a coder, we worked on algorithms. Today, we memorize APIs for countless libraries — those libraries have the algorithms - Eric Allman
-
No - he has developed a technique of hot-swapping processors!
Ideological Purity is no substitute for being able to stick your thumb down a pipe to stop the water
So he has learnt the secret art of the del Icatessen.
Panic, Chaos, Destruction. My work here is done. Drink. Get drunk. Fall over - P O'H OK, I will win to day or my name isn't Ethel Crudacre! - DD Ethel Crudacre I cannot live by bread alone. Bacon and ketchup are needed as well. - Trollslayer Have a bit more patience with newbies. Of course some of them act dumb - they're often *students*, for heaven's sake - Terry Pratchett
-
Found on http://en.wikibooks.org/wiki/Minimizing_Hard_Disk_Drive_Failure_and_Data_Loss/Stress_Control[^] "Based on professional experience of system administrators, it is believed that there is a direct relationship between the number of power cycles of a computer and the probability of failure of its drives. In other words, a computer with a high uptime may have a lower probability of drive failure than one that has its power cycled routinely." Question is, is this a cliché, or is this a verified assertion? What is your experience on this in the real life, outside the testing labs? And more generally, did you make any correlation between a human behavior and computer reliability? (punching the hardware excepted :) )
When they kick at your front door How you gonna come? With your hands on your head Or on the trigger of your gun?
I've just replaced my boot drive with an SSD and my data drive with a hybrid, and the machine goes like the proverbial off a shovel. :-D
-
So he has learnt the secret art of the del Icatessen.
Panic, Chaos, Destruction. My work here is done. Drink. Get drunk. Fall over - P O'H OK, I will win to day or my name isn't Ethel Crudacre! - DD Ethel Crudacre I cannot live by bread alone. Bacon and ketchup are needed as well. - Trollslayer Have a bit more patience with newbies. Of course some of them act dumb - they're often *students*, for heaven's sake - Terry Pratchett
Have you been reading Truckers, Diggers and Wings again?
Ideological Purity is no substitute for being able to stick your thumb down a pipe to stop the water
-
Found on http://en.wikibooks.org/wiki/Minimizing_Hard_Disk_Drive_Failure_and_Data_Loss/Stress_Control[^] "Based on professional experience of system administrators, it is believed that there is a direct relationship between the number of power cycles of a computer and the probability of failure of its drives. In other words, a computer with a high uptime may have a lower probability of drive failure than one that has its power cycled routinely." Question is, is this a cliché, or is this a verified assertion? What is your experience on this in the real life, outside the testing labs? And more generally, did you make any correlation between a human behavior and computer reliability? (punching the hardware excepted :) )
When they kick at your front door How you gonna come? With your hands on your head Or on the trigger of your gun?
Personal experience as a former system administrator confirms this. But I would even say that it's not the power cycling that it the problem, but lack of usage. In Sweden many companies basically shut down during July as most employees have their vacation then. But the servers remain on. Despite this I've noticed that we we had most server HDD failures during the first week after vacation ends, and all other failures after Christmas. For your second question: yes. Moving the computer while HDD is reading or writing is a mistake.
Light moves faster than sound. That is why some people appear bright, until you hear them speak. List of common misconceptions
-
Have you been reading Truckers, Diggers and Wings again?
Ideological Purity is no substitute for being able to stick your thumb down a pipe to stop the water
I confess. I am currently reading The Bromeliad.
Panic, Chaos, Destruction. My work here is done. Drink. Get drunk. Fall over - P O'H OK, I will win to day or my name isn't Ethel Crudacre! - DD Ethel Crudacre I cannot live by bread alone. Bacon and ketchup are needed as well. - Trollslayer Have a bit more patience with newbies. Of course some of them act dumb - they're often *students*, for heaven's sake - Terry Pratchett
-
I confess. I am currently reading The Bromeliad.
Panic, Chaos, Destruction. My work here is done. Drink. Get drunk. Fall over - P O'H OK, I will win to day or my name isn't Ethel Crudacre! - DD Ethel Crudacre I cannot live by bread alone. Bacon and ketchup are needed as well. - Trollslayer Have a bit more patience with newbies. Of course some of them act dumb - they're often *students*, for heaven's sake - Terry Pratchett
"It wasn't a thing, it was a bit of shaped sky" Oh yes - I remember that feeling when I first saw Concorde during wing reliability testing on a school trip!
Ideological Purity is no substitute for being able to stick your thumb down a pipe to stop the water
-
Found on http://en.wikibooks.org/wiki/Minimizing_Hard_Disk_Drive_Failure_and_Data_Loss/Stress_Control[^] "Based on professional experience of system administrators, it is believed that there is a direct relationship between the number of power cycles of a computer and the probability of failure of its drives. In other words, a computer with a high uptime may have a lower probability of drive failure than one that has its power cycled routinely." Question is, is this a cliché, or is this a verified assertion? What is your experience on this in the real life, outside the testing labs? And more generally, did you make any correlation between a human behavior and computer reliability? (punching the hardware excepted :) )
When they kick at your front door How you gonna come? With your hands on your head Or on the trigger of your gun?
That's not surprising. Very much like your car's engine, a hard drive operates at a certain temperature and the parts have worn in to work with the least possible amount of friction. Changes in temperature cause the material to deform and when the drive starts, it's cold and the parts do not have that perfect fit. The differences are very small, but until it has reached its operating temperature the parts will be worn out far more than during normal operation.
And from the clouds a mighty voice spoke:
"Smile and be happy, for it could come worse!"And I smiled and was happy
And it came worse. -
Found on http://en.wikibooks.org/wiki/Minimizing_Hard_Disk_Drive_Failure_and_Data_Loss/Stress_Control[^] "Based on professional experience of system administrators, it is believed that there is a direct relationship between the number of power cycles of a computer and the probability of failure of its drives. In other words, a computer with a high uptime may have a lower probability of drive failure than one that has its power cycled routinely." Question is, is this a cliché, or is this a verified assertion? What is your experience on this in the real life, outside the testing labs? And more generally, did you make any correlation between a human behavior and computer reliability? (punching the hardware excepted :) )
When they kick at your front door How you gonna come? With your hands on your head Or on the trigger of your gun?
Temperature cycling is a large part of stress testing equipment, particularly electro mechanical. Part of this is differential thermal epxansion of different materials which creates stress between them.
-
Found on http://en.wikibooks.org/wiki/Minimizing_Hard_Disk_Drive_Failure_and_Data_Loss/Stress_Control[^] "Based on professional experience of system administrators, it is believed that there is a direct relationship between the number of power cycles of a computer and the probability of failure of its drives. In other words, a computer with a high uptime may have a lower probability of drive failure than one that has its power cycled routinely." Question is, is this a cliché, or is this a verified assertion? What is your experience on this in the real life, outside the testing labs? And more generally, did you make any correlation between a human behavior and computer reliability? (punching the hardware excepted :) )
When they kick at your front door How you gonna come? With your hands on your head Or on the trigger of your gun?
In my experience hard disks are very reliable devices: the only one stopped working was a 2.5" external one that fell down from a shelf at about 1.5 m (another one survived such a shock) above the ground.
If the Lord God Almighty had consulted me before embarking upon the Creation, I would have recommended something simpler. -- Alfonso the Wise, 13th Century King of Castile.
This is going on my arrogant assumptions. You may have a superb reason why I'm completely wrong. -- Iain Clarke
[My articles] -
"It wasn't a thing, it was a bit of shaped sky" Oh yes - I remember that feeling when I first saw Concorde during wing reliability testing on a school trip!
Ideological Purity is no substitute for being able to stick your thumb down a pipe to stop the water
OriginalGriff wrote:
during wing reliability testing on a school trip!
You got to test Concorde's wing when you were at school? I got play-dough.
Panic, Chaos, Destruction. My work here is done. Drink. Get drunk. Fall over - P O'H OK, I will win to day or my name isn't Ethel Crudacre! - DD Ethel Crudacre I cannot live by bread alone. Bacon and ketchup are needed as well. - Trollslayer Have a bit more patience with newbies. Of course some of them act dumb - they're often *students*, for heaven's sake - Terry Pratchett
-
OriginalGriff wrote:
during wing reliability testing on a school trip!
You got to test Concorde's wing when you were at school? I got play-dough.
Panic, Chaos, Destruction. My work here is done. Drink. Get drunk. Fall over - P O'H OK, I will win to day or my name isn't Ethel Crudacre! - DD Ethel Crudacre I cannot live by bread alone. Bacon and ketchup are needed as well. - Trollslayer Have a bit more patience with newbies. Of course some of them act dumb - they're often *students*, for heaven's sake - Terry Pratchett
Well, if you had passed your 11-plus... :laugh:
Ideological Purity is no substitute for being able to stick your thumb down a pipe to stop the water
-
Found on http://en.wikibooks.org/wiki/Minimizing_Hard_Disk_Drive_Failure_and_Data_Loss/Stress_Control[^] "Based on professional experience of system administrators, it is believed that there is a direct relationship between the number of power cycles of a computer and the probability of failure of its drives. In other words, a computer with a high uptime may have a lower probability of drive failure than one that has its power cycled routinely." Question is, is this a cliché, or is this a verified assertion? What is your experience on this in the real life, outside the testing labs? And more generally, did you make any correlation between a human behavior and computer reliability? (punching the hardware excepted :) )
When they kick at your front door How you gonna come? With your hands on your head Or on the trigger of your gun?
Long time no see - hi KaЯl! :D How's life?
FILETIME to time_t
| FoldWithUs! | sighist | WhoIncludes - Analyzing C++ include file hierarchy -
Long time no see - hi KaЯl! :D How's life?
FILETIME to time_t
| FoldWithUs! | sighist | WhoIncludes - Analyzing C++ include file hierarchy
