High disk queue lengh ???

  • Hi,

    Iam getting the following high disk queue lengh alarams frequently from monitoring tool. We are using SQL server 2005 EE x64 with service pack SP2. what are the steps I need to take to get rid of these errors

    Physical disk #0 C: containing paging file(s) 'C:\pagefile.sys' is experiencing a high rate of I/O (83.63% busy) unrelated to paging.

    Physical disk #20 Z: containing paging file(s) 'C:\pagefile.sys' is experiencing a high rate of I/O (32.07% busy) unrelated to paging.

    Thanks

  • I'd say check what the monitoring tool means by that. And why is it saying that drive Z has a C-drive filepath on it?

    - Gus "GSquared", RSVP, OODA, MAP, NMVP, FAQ, SAT, SQL, DNA, RNA, UOI, IOU, AM, PM, AD, BC, BCE, USA, UN, CF, ROFL, LOL, ETC
    Property of The Thread

    "Nobody knows the age of the human race, but everyone agrees it's old enough to know better." - Anon

  • thanks,

    we have only backups stored on Z drive and page file located in C drive with default size of 2046 MB.

    But Iam frequently getting these ararms, So what are the things I need to consider? plz advice me

    TimeConnectionActionDetailsSeverityAlarm

    01/09/2009 9:52:13 AMABCAlarm raisedThe database WSS_Search has a high Log Flush Wait time (516 ms).LowDatabases - Log Flush Wait Time Alarm

    TimeConnectionActionDetailsSeverityAlarm

    01/09/2009 9:52:13 AMABC Alarm raisedThe database WSS_Search has a high Log Flush Wait time (516 ms).LowDatabases - Log Flush Wait Time Alarm

    TimeConnectionActionDetailsSeverityAlarm

    01/09/2009 2:08:32 AMABCAlarm raisedPhysical disk #20 Z: containing paging file(s) 'C:\pagefile.sys' is experiencing a high rate of I/O (75.72% busy) unrelated to paging.InformationPaging Disk Activity Alarm

    TimeConnectionActionDetailsSeverityAlarm

    01/09/2009 2:08:32 AMABCAlarm raisedPhysical disk #20 Z: containing paging file(s) 'C:\pagefile.sys' is experiencing a high rate of I/O (75.72% busy) unrelated to paging.InformationPaging Disk Activity Alarm

  • Madhu I would do some googling on disk counters in sysmon or perfmon if I was you. I have come across this message where the page file was heavily used but it was not due to normal paging activity, but I cannot for the life of me remember the details as to cause. I am pretty sure it is down to a disk bottleneck (the error hints at that). The cure for that could be anything from eliminating unnecessary i/o (get rid of table scans, move files around) to getting faster disks. moving your logs to a separate disks if not already looks a good bet.

    ---------------------------------------------------------------------

  • Are you using local disk, SAN or NAS? what sort of disk configuration (RAID level, how many disks) are you using? How are you connecting to your disk?

    - Local - local RAID controller. SCSI, SATA?

    - SAN - Fiber Channel, ATA, iSCSI, SCSI

    - NAS - Ethernet, iSCSI, ATA over Ethernet

    If you're using a SAN, how are your queues setup? Array queue or LUN queue (QueueTarget)? How long is your queue (QueueDepth)?

    Do you have any anti virus software running real-time scanning against your pagefile.sys files?

    --
    Andrew Hatfield

Viewing 5 posts - 1 through 4 (of 4 total)

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