perfmon logical disk VS physical disk

  • I have perfmon running with avg disk sec read/write. I see big difference in the actual values between logical and physical r/W...what could be issue? Is it bad drivers?

  • How close are you to the drives? Are they a raid hanging directly off the machine in question? Are you working through a SAN? Are you on a VM?

    I/OPs counters from the instance once you get enough layers between you and your hardware are useful as health benchmarks when your system is running well to know that something has gone awry. I find them nearly useless once there are too many layers for any other purpose.

    If your RAID is directly connected to a hard machine without virtual, then you can directly work against those counters.

    As to what those counters actually are, this is from technet:

    http://blogs.technet.com/b/askcore/archive/2012/03/16/windows-performance-monitor-disk-counters-explained.aspx

    The Physical Disk performance object monitors disk drives on the computer. It identifies the instances representing the physical hardware, and the counters are the sum of the access to all partitions on the physical instance.

    The Logical Disk Performance object monitors logical partitions. Performance monitor identifies logical disks by their drive letter or mount point. If a physical disk contains multiple partitions, this counter will report the values just for the partition selected and not for the entire disk. On the other hand, when using Dynamic Disks the logical volumes may span more than one physical disk, in this scenario the counter values will include the access to the logical disk in all the physical disks it spans.

    So, it really depends on your setup as to which should have more volume, because it's very rare to have one volume = one disk anymore. Now, when you get to SAN results and LUNs which are sharing physical drives with other LUNs not available to a particular instance, it gets even zanier.

    So, you'll have to share a lot of information with us about your physical setup and actual values before we can attempt to help you nail down why things seem off.


    - Craig Farrell

    Never stop learning, even if it hurts. Ego bruises are practically mandatory as you learn unless you've never risked enough to make a mistake.

    For better assistance in answering your questions[/url] | Forum Netiquette
    For index/tuning help, follow these directions.[/url] |Tally Tables[/url]

    Twitter: @AnyWayDBA

  • Evil Kraig F (6/6/2013)


    How close are you to the drives? Are they a raid hanging directly off the machine in question? Are you working through a SAN? Are you on a VM?

    I/OPs counters from the instance once you get enough layers between you and your hardware are useful as health benchmarks when your system is running well to know that something has gone awry. I find them nearly useless once there are too many layers for any other purpose.

    If your RAID is directly connected to a hard machine without virtual, then you can directly work against those counters.

    As to what those counters actually are, this is from technet:

    http://blogs.technet.com/b/askcore/archive/2012/03/16/windows-performance-monitor-disk-counters-explained.aspx

    The Physical Disk performance object monitors disk drives on the computer. It identifies the instances representing the physical hardware, and the counters are the sum of the access to all partitions on the physical instance.

    The Logical Disk Performance object monitors logical partitions. Performance monitor identifies logical disks by their drive letter or mount point. If a physical disk contains multiple partitions, this counter will report the values just for the partition selected and not for the entire disk. On the other hand, when using Dynamic Disks the logical volumes may span more than one physical disk, in this scenario the counter values will include the access to the logical disk in all the physical disks it spans.

    So, it really depends on your setup as to which should have more volume, because it's very rare to have one volume = one disk anymore. Now, when you get to SAN results and LUNs which are sharing physical drives with other LUNs not available to a particular instance, it gets even zanier.

    So, you'll have to share a lot of information with us about your physical setup and actual values before we can attempt to help you nail down why things seem off.

    Stand alone server with SAN. Actually this is weird, because when i have the perfmon running in background physical and logical readings are similar but if i have it just running , the numbers look very different.

  • curious_sqldba (6/6/2013)


    Stand alone server with SAN. Actually this is weird, because when i have the perfmon running in background physical and logical readings are similar but if i have it just running , the numbers look very different.

    Your first task before you try to associate these data points in a meaningful way is to get in touch with the SAN admins and find out the LUN layout and if you're sharing physical spindles with other LUNs.


    - Craig Farrell

    Never stop learning, even if it hurts. Ego bruises are practically mandatory as you learn unless you've never risked enough to make a mistake.

    For better assistance in answering your questions[/url] | Forum Netiquette
    For index/tuning help, follow these directions.[/url] |Tally Tables[/url]

    Twitter: @AnyWayDBA

Viewing 4 posts - 1 through 3 (of 3 total)

You must be logged in to reply to this topic. Login to reply