AIX > Administrator > Performance

AIX Flash Cache

Flash Cache

Youi will see the following responses

Partition cm1part1 assigned to target hdisk106
Partition cm1part1 assigned to target hdisk107
Partition cm1part1 assigned to target hdisk108
Partition cm1part1 assigned to target hdisk109

I then checked the partition and assignments:

cache_mgt partition list -l
cache_mgt cache list

INACTIVE means cache is not started!

And I then checked the engine status:
cache_mgt engine list -l

At this point it was time to start the caching—you can start it in two ways. The first is to start it for all assigned disks, the second is to start it disk by disk. All disks

cache_mgt cache start -t all

You will see something like: All caches have been started.

Disk by disk

cache_mgt cache start -t hdisk106
cache_mgt cache start -t hdisk107
cache_mgt cache start -t hdisk108
cache_mgt cache start -t hdisk109

Similarly, you stop the caching either disk by disk or using all:

cache_mgt cache stop -t all


cache_mgt cache stop -t hdisk106

If you want to remove target disks then you need to stop caching of that target prior to the unassign of the disk. The unassign is done as follows:

cache_mgt cache stop -t hdisk106
cache_mgt partition unassign -t hdisk106

After my initial tests we moved over to using the full 88 disks that we wanted to cache and discovered something interesting. To list the status of the cached disks you use the following command:

cache_mgt cache list

This provides a list of the targets and their status (inactive or active). What I discovered is that the command is fine up to 76 target disks but as soon as you add the 77th disk the command takes a core dump. This is being worked on by IBM and an apar will be out shortly. All other commands work fine and this does not affect the caching functions.

Once caching is up and running you can get statistics using the cache_mgt monitor command. By default it seems to start, but the 3 versions of the command are:

cache_mgt monitor start
	cache_mgt monitor stop
	cache_mgt monitor get -h -s

Jaqui Lynch is an independent consultant, focusing on enterprise architecture, performance and delivery on Power Systems with AIX and Linux.

Like what you just read? To receive technical tips and articles directly in your inbox twice per month, sign up for the EXTRA e-newsletter here.

comments powered by Disqus



2019 Solutions Edition

A Comprehensive Online Buyer's Guide to Solutions, Services and Education.

Achieving a Resilient Data Center

Implement these techniques to improve data-center resiliency.


AIO: The Fast Path to Great Performance

AIX Enhancements -- Workload Partitioning

The most exciting POWER6 enhancement, live partition mobility, allows one to migrate a running LPAR to another physical box and is designed to move running partitions from one POWER6 processor-based server to another without any application downtime whatsoever.

IBM Systems Magazine Subscribe Box Read Now Link Subscribe Now Link iPad App Google Play Store
IBMi News Sign Up Today! Past News Letters