BlockSim Example RC1 - Reliability Analysis of a Storage Cluster System
Download Example
File (*.rbp)Background
This example is based on the example shown in Figure 8 of the article "Determining the Availability and Reliability of Storage Configurations" by Santosh Shetty, August 2002, as posted on Dell's Web site.
Analysis
Consider a "high-availability" cluster with a reliability block diagram (RBD) as shown in the next figure.
Furthermore (and from the referenced Web article), assume the following life distributions and parameters. (Note that this example, unlike the original article, assumes no repair of failed components.)
- Server: Exponential (Mean = 45753 hr)
- Switch: Exponential (Mean = 255,358 hr)
- HBA: Exponential (Mean = 252,550 hr)
- Controller: Exponential (Mean = 68,961 hr)
Step 1: Determine the "reliability equation" and cdf of the system....
Figure 1 illustrates BlockSim being used to determine the system reliability function.
Figure 1: BlockSim 7 screen shot with the system reliability equation.
You can also view the system reliability equation and cdf in HTML format.
Step 2: Looking at some system level plots...
Component Reliability Importance Plots
The next two charts are component reliability importance plots at t = 8544 hr (1 year). Both plots (a tableau area plot and a bar chart) illustrate the same concept. That is, the higher the importance of the component, the higher its effect on system reliability.
The next graphic shows a component reliability importance plot that varies with time.
Conclusion
The servers in this configuration are the most critical component while the hubs are the least critical.
System Reliability Plot
System Failure Rate Plot
System pdf Plot
Step 3: Determine System Results...
The MTTF of the system can be obtained from BlockSim's Analytical QCP.
