Question

2. If assume collection of modules have exponentially distributed lifetimes (age of component doesn't matter in failure probability) and modules fail independently, overall failure rate of collection is sum of failure rates of modules. Calculate MTTF of a disk subsystem with • 10 disks, each rated at 1,000,000 hour MTTF • 1 SCSI controller, 500,000 hour MTTF • 1 power supply, 200,000 hour MTTF • 1 fan, 200,000 MTTF • 1 SCSI cable, 1,000,000 hour MTTF 1) Failure Rate? 2) MTTF? 3) What if 1000,000 MTTF > 100 years, Make an example for this condition.

Answer 1

Answer: ! + failure rate To'x 1,000,000 500,000 1 ( t t + 200,000 2007000 1,000,000 23 = C1042+5+571) 1,000,000 ,000,000 MTTF 1,000,000 failure rate 23 = 43,500 hours what if 1000,000 MTTF >100 years ? in a room a тг calculate Let 2000 failures in 6o days, then rate is calculated as long as <=30 failures => 4000/000 hy MTTF Suppose it is people, 1998 deaths per year . in u.s (failure rate) death s 5 to 14 years old = 20/100,000

- MTTF (Human) 100,000 =5000.XY3 20 Deathe' >85years olds - 20,000/100,000 MTTF Chumain) ) = 100.000 /20.000 = 5 years 1,000,000 M TTF > 100 years but disk life time is 5 years if we replace a disk every 5 years it won't until 21st replacement fail over lifelite if had 1000 disks for 5 years (1000 disks * 3655 * 24) 1,000,000 hrs Ifailures : 43,800,000/1,000,000 544 failures 4.4% fail with 1,000,000 MTTF detail d disk specfication lists failures million/spondant 300 failures , Month / Milliondisks at 1,000,000 MTTF g about it per year for 5 year disk life time

Hardware M7 rf is often 100,000 to 1,000,000 hrs 8 MITF is often I tolo * hours there is good chances that it one component fails it can be repalced be for and fails Therefore, design systems with sufficient redundancies that is NO single point of failure