The documentation set for this product strives to use bias-free language. For the purposes of this documentation set, bias-free is defined as language that does not imply discrimination based on age, disability, gender, racial identity, ethnic identity, sexual orientation, socioeconomic status, and intersectionality. Exceptions may be present in the documentation due to language that is hardcoded in the user interfaces of the product software, language used based on RFP documentation, or language that is used by a referenced third-party product. Learn more about how Cisco is using Inclusive Language.
This appendix provides RAID controller information, and it includes the following sections:
This server supports the RAID controller options and cable requirements shown in Table C-1 .
For instructions on installing a RAID controller card, see Replacing a RAID Controller Card Inside the Server Node.
The controller can be used in JBOD mode (non-RAID) or in RAID mode with a choice of RAID levels 0,1,5,6,10, 50, or 60.
Firmware on the RAID controller must be verified for compatibility with the current Cisco IMC and BIOS versions that are installed on the server. If not compatible, upgrade or downgrade the RAID controller firmware accordingly using the Host Upgrade Utility (HUU) for your firmware release to bring it to a compatible level.
See the HUU guide for your Cisco IMC release for instructions on downloading and using the utility to bring server components to compatible levels: HUU Guides
The Cisco UCS C3X60 12G SAS RAID controller supports JBOD mode (non-RAID) on physical drives that are in pass-through mode and directly exposed to the OS. We recommended that you use JBOD mode instead of individual RAID 0 volumes when possible.
The Cisco UCS C3X60 12G SAS RAID controller allows you to create of large RAID 5 or 6 volume by including all the drives in the system with a spanned array configuration (RAID 50/RAID 60). Where possible, we recommended you create multiple, smaller RAID 5/6 volumes with fewer drives per RAID array. This provides redundancy and reduces the operations time for initialization, RAID rebuilds, and other operations.
The I/O policy applies to reads on a specific virtual drive. It does not affect the read-ahead cache. RAID volumes can be configured in two types of I/O policies. These are:
Although Cached I/O provides faster processing, it is useful only when the RAID volume has a small number of slower drives. With the C3X60 4-TB SAS drives, Cached I/O has not shown any significant advantage over Direct I/O. Instead, Direct I/O has shown better results over Cached I/O in a majority of I/O patterns. We recommended you use Direct I/O (the default) in all cases and to use Cached I/O cautiously.
The Cisco UCS 12G SAS RAID controller conducts different background operations like Consistency Check (CC), Background Initialization (BGI), Rebuild (RBLD), Volume Expansion & Reconstruction (RLM), and Patrol Real (PR).
While these BGOPS are expected to limit their impact to I/O operations, there have been cases of higher impact during some of the operations like Format or similar I/O operations. In these cases, both the I/O operation and the BGOPS may take more time to complete. In such cases, we recommend you limit concurrent BGOPS and other intensive I/O operations where possible.
BGOPS on large volumes can take an extended period of time to complete, presenting a situation where operations complete and begin with limited time between operations. Since BGOPS are intended to have a very low impact in most I/O operations, the system should function without any issues. If there are any issues that arise while running concurrent BGOPS and I/O operations, we recommend you to stop either activity to let the other complete before reusing and/or schedule the BGOPS at a later time when the I/O operations are low.
This server supports installation of one supercap power module (SCPM) backup unit. The unit mounts directly to the Cisco modular RAID controller card inside the server node. The unit comes already attached to the card and is not sold as a separate component.
The SCPM provides approximately 3 years of backup for the disk write-back cache DRAM in the case of sudden power loss by offloading the cache to the NAND flash.
When you replace a RAID controller, the RAID configuration that is stored in the controller is lost.
To restore your RAID configuration to your new RAID controller, follow these steps.
Step 1 Replace your RAID controller. See Replacing a RAID Controller Card Inside the Server Node.
Step 2 If this was a full chassis swap, replace all drives into the drive bays, in the same order that they were installed in the old chassis.
Step 3 Reboot the server node.
Step 4 Press any key (other than C) to continue when you see the following onscreen prompt:
Step 5 Watch the subsequent screens for confirmation that your RAID configuration was imported correctly:
The LSI utilities have help documentation for more information about using the utilities.
For basic information about RAID and for using the utilities for the RAID controller cards, see the
Cisco UCS Servers RAID Guide.
Full Avago Technologies/LSI documentation is also available:
Avago Technologies/LSI 12 Gb/s MegaRAID SAS Software User’s Guide, Rev. F