iDRAC 8/7 v2.30.30.30 User’s Guide

Editing virtual disk cache policies

You can change the read, write, or disk cache policy of a virtual disk.

NOTE: Some of the controllers do not support all read or write policies. Therefore, when a policy is applied, an error message is displayed.

The read policies indicate whether the controller must read sequential sectors of the virtual disk searching for data:

Adaptive Read Ahead — The controller initiates read ahead only if the two most recent reads requests accessed sequential sectors of the disk. If subsequent read requests access random sectors of the disk, the controller reverts to no read ahead policy. The controller continues to evaluate whether read requests are accessing sequential sectors of the disk, and initiates read ahead if necessary.
- NOTE: Previous generations of PERC controllers support read policy settings of No Read Ahead , Read Ahead, and Adaptive Read Ahead. With PERC 8 and PERC 9, the Read Ahead and Adaptive Read Ahead settings are functionally equivalent at the controller level. For backward compatibility purposes, some systems management interfaces and PERC 8 and 9 controllers still allow setting the read policy to Adaptive Read Ahead. While it is possible to set Read Ahead or Adaptive Read Ahead on PERC 8 or PERC 9, there is no functional difference.
Read Ahead — The controller reads sequential sectors of the virtual disk when seeking data. Read ahead policy may improve system performance if the data is written to the sequential sectors of the virtual disk.
No Read Ahead — Selecting no read ahead policy indicates that the controller should not use read ahead policy.

The write policies specify if the controller sends a write-request completion signal when the data is in the cache or after it has been written to the disk.

Write Through — The controller sends a write-request completion signal only after the data is written to the disk. Write-through caching provides better data security than write-back caching, since the system assumes that the data is available only after it has been safely written to the disk.
Write Back — The controller sends a write-request completion signal as soon as the data is in the controller cache but has not yet been written to disk. Write back caching may provide improved performance since subsequent read requests can retrieve data quickly from the cache then from the disk. However, data loss may occur in the event of a system failure which prevents that data from being written on a disk. Other applications may also experience problems when actions assume that the data is available on the disk.
Force Write Back — The write cache is enabled regardless of whether the controller has a battery. If the controller does not have a battery and force write-back caching is used, data loss may occur in the event of a power failure.

The Disk Cache policy applies to readings on a specific virtual disk. These settings do not affect the read-ahead policy.

NOTE:
- Controller non-volatile cache and battery backup of controller cache affects the read-policy or the write policy that a controller can support. All PERCs do not have battery and cache.
- Read ahead and write back requires cache. Therefore, if the controller does not have cache, it does not allow you to set the policy value.
  
  Similarly, if the PERC has cache but not battery and the policy is set that requires accessing cache, then data loss may occur if base of power off. So few PERCs may not allow that policy.
  
  Therefore, depending upon the PERC, the policy value is set.