perfmon question

We have a SAN solution. it used to be that you could use the average disk
queue length as a metric for how busy the disk is. I've read that that
counter is not longer the one that you should use. Instead that you should
use the Disk sec/Transfer and the like.

Does microsoft have a position on this. I've heard some say that if you are
stll using a SCSI driver to access teh disk, that the queue length is still
appropriate.

I'm asking because from what I'm seeing, the queue length doesn't appear to
be a good indicator.

any feed back would be great... i'm hoping there is a micrsoft person who
can answer this for me.

thanks


.

Relevant Pages

  • Re: Apparent strange disk behaviour in 6.0
    ... > Will get twice as much done and still keep the disk 100% busy. ... > how quickly the queue drains or fills. ... I'm trying to work out why teh read and write queues are empty for so ...
    (freebsd-current)
  • Re: [GIT PULL] Ext3 latency fixes
    ... which unplugged the write queue after every page write. ... In guarded mode the on disk i_size is not updated until after the data ... The end_io handler puts the buffer onto the per-sb list of guarded ... One big gotcha is that we starting a transaction while a page is ...
    (Linux-Kernel)
  • Re: [GIT PULL] Ext3 latency fixes
    ... which unplugged the write queue after every page write. ... In guarded mode the on disk i_size is not updated until after the data ... The end_io handler puts the buffer onto the per-sb list of guarded ...
    (Linux-Kernel)
  • Re: Higher than expected disk write(2) latency
    ... The disk is a Seagate ST380817AS SATA connected to an Intel ICH7 ... "You write sector n and n+1, it takes some amount of time for that first ... Crosses are operations enqueue times (when write requests were ... AIO queue are slowing down the retrieval from the queue and thus we miss ...
    (Linux-Kernel)
  • Re: Exchange 2007 get-mailboxstatistics hangs
    ... I have found 3-4 users with item counts in their mailboxes exceeding 5000. ... My logical disk counter avg. ... Is there not a way to just simply restart the queue (suspending ... RPC Averaged Latency (been running high in the 15-60 ...
    (microsoft.public.exchange.setup)