Annualized failure rate: Difference between revisions
No edit summary Tags: Visual edit Mobile edit Mobile web edit |
m Fixed doubled up reference, extra space and reference name |
||
| Line 1: | Line 1: | ||
'''Annualized failure rate''' ('''AFR''') gives the estimated probability that a device or component will fail during a full year of use. It is a relation between the mean time between failure ([[Failure rate|MTBF]]) and the hours that a number of devices are run per year. AFR is estimated from a sample of like components—AFR and MTBF as given by vendors are [[Statistical population|population]] statistics that can not predict the behaviour of an individual unit.<ref name=" |
'''Annualized failure rate''' ('''AFR''') gives the estimated probability that a device or component will fail during a full year of use. It is a relation between the mean time between failure ([[Failure rate|MTBF]]) and the hours that a number of devices are run per year. AFR is estimated from a sample of like components—AFR and MTBF as given by vendors are [[Statistical population|population]] statistics that can not predict the behaviour of an individual unit.<ref name="Seagate">{{cite web|url=http://enterprise.media.seagate.com/2010/04/inside-it-storage/diving-into-mtbf-and-afr-storage-reliability-specs-explained/ |title=Diving into "MTBF" and "AFR": Storage Reliability Specs Explained |work=Inside IT Storage |publisher=Seagate |date=Apr 2010 |deadurl=bot: unknown |archiveurl=https://web.archive.org/web/20100501151901/http://enterprise.media.seagate.com/2010/04/inside-it-storage/diving-into-mtbf-and-afr-storage-reliability-specs-explained/ |archivedate=2010-05-01 }}</ref> |
||
==Hard disk drives== |
==Hard disk drives== |
||
For example, AFR is used to characterize the reliability of [[hard disk drive]]s. |
For example, AFR is used to characterize the reliability of [[hard disk drive]]s. |
||
The relationship between AFR and MTBF (in hours) is:<ref name=" |
The relationship between AFR and MTBF (in hours) is:<ref name="Seagate" /> |
||
:<math>AFR = 1-exp(-8766/MTBF)</math> |
:<math>AFR = 1-exp(-8766/MTBF)</math> |
||
This equation assumes that the device or component is [[Power-on hours|powered on]] for the full 8766 hours of a year, and gives the estimated fraction of an original sample of devices or components that will fail in one year, or, equivalently, 1 − AFR is the fraction of devices or components that will show no failures over a year. It is based on an exponential failure distribution (see [[Failure rate#Failure rate in the continuous sense| |
This equation assumes that the device or component is [[Power-on hours|powered on]] for the full 8766 hours of a year, and gives the estimated fraction of an original sample of devices or components that will fail in one year, or, equivalently, 1 − AFR is the fraction of devices or components that will show no failures over a year. It is based on an exponential failure distribution (see [[Failure rate#Failure rate in the continuous sense|failure rate]] for a full derivation). |
||
| ⚫ | |||
[[Failure rate#Failure rate in the continuous sense|rate]] for a full derivation). |
|||
| ⚫ | |||
This ratio can be approximated by, assuming a small AFR, |
This ratio can be approximated by, assuming a small AFR, |
||
Revision as of 22:42, 25 February 2019
Annualized failure rate (AFR) gives the estimated probability that a device or component will fail during a full year of use. It is a relation between the mean time between failure (MTBF) and the hours that a number of devices are run per year. AFR is estimated from a sample of like components—AFR and MTBF as given by vendors are population statistics that can not predict the behaviour of an individual unit.[1]
Hard disk drives
For example, AFR is used to characterize the reliability of hard disk drives.
The relationship between AFR and MTBF (in hours) is:[1]
This equation assumes that the device or component is powered on for the full 8766 hours of a year, and gives the estimated fraction of an original sample of devices or components that will fail in one year, or, equivalently, 1 − AFR is the fraction of devices or components that will show no failures over a year. It is based on an exponential failure distribution (see failure rate for a full derivation). Note: Some manufacturers count a year as 8760 hours.[2]
This ratio can be approximated by, assuming a small AFR,
For example, a common specification for PATA and SATA drives may be an MTBF of 300,000 hours, giving an approximate theoretical 2.92% annualized failure rate i.e. a 2.92% chance that a given drive will fail during a year of use.
The AFR for a drive is derived from time-to-fail data from a reliability-demonstration test (RDT).[3]
AFR will increase towards and beyond the end of the service life of a device or component. Google's 2007 study found, based on a large field sample of drives, that actual AFRs for individual drives ranged from 1.7% for first year drives to over 8.6% for three-year-old drives.[4] A CMU 2007 study showed an estimated 3% mean AFR over 1–5 years based on replacement logs for a large sample of drives.[5]
See also
References
- ^ a b "Diving into "MTBF" and "AFR": Storage Reliability Specs Explained". Inside IT Storage. Seagate. Apr 2010. Archived from the original on 2010-05-01.
{{cite web}}: Unknown parameter|deadurl=ignored (|url-status=suggested) (help) - ^ Hard disk drive reliability and MTBF / AFR
- ^ Cole, Gerry, Estimating Drive Reliability in Desktop Computers and Consumer Electronics Systems (PDF), Virginia.
- ^ "AFR broken down by age groups", Failure Trends in Large Disk Drive Population (PDF), Google, p. 4, figure 2ff.
- ^ Schroeder, Bianca; Gibson, Garth A, Disk Failures in the Real World: What Does an MTTF of 1,000,000 Hours Mean to You?.