ALM-12033 Slow Disk Fault

Alarm Description

• For HDDs, the alarm is triggered when any of the following conditions is met:
  • By default, the system collects data every 3 seconds. The svctm latency reaches 1000 ms within 30 seconds in at least seven collection periods.
  • By default, the system collects data every 3 seconds. At least 50% of detected svctm take no less than 150 ms within 300 seconds.
• For SSDs, the alarm is triggered when any of the following conditions is met:
  • By default, the system collects data every 3 seconds. The svctm latency reaches 1000 ms within 30 seconds in at least seven collection periods.
  • By default, the system collects data every 3 seconds. At least 50% of detected svctm take no less than 20 ms within 300 seconds.

The collection period is 3 seconds, and the detection period is 30 or 300 seconds. This alarm is automatically cleared when none of the preceding conditions are met for three consecutive detection periods (30 or 300 seconds).

The svctm value can be obtained as follows:

svctm = (tot_ticks_new - tot_ticks_old) / (rd_ios_new + wr_ios_new - rd_ios_old - wr_ios_old)

When the detection period is 30 seconds, if rd_ios_new + wr_ios_new - rd_ios_old - wr_ios_old = 0, then svctm = 0.

When the detection period is 300 seconds and rd_ios_new + wr_ios_new - rd_ios_old - wr_ios_old = 0, if tot_ticks_new - tot_ticks_old = 0, then svctm = 0; otherwise, the value of svctm is infinite.

The parameters can be obtained as follows:

The system runs the cat /proc/diskstats command every 3 seconds to collect data.

In the data collected for the first time, the number in the fourth column is the rd_ios_old value, the number in the eighth column is the wr_ios_old value, and the number in the thirteenth column is the tot_ticks_old value.

In the data collected for the second time, the number in the fourth column is the rd_ios_new value, the number in the eighth column is the wr_ios_new value, and the number in the thirteenth column is the tot_ticks_new value.

In this case, the value of svctm is as follows:

(19571460 - 19569526) / (1101553 + 28747977 - 1101553 - 28744856) = 0.6197

Alarm Attributes

Alarm Parameters

Impact on the System

• The system I/O performance deteriorates, which means slow response and low throughput. For example, job submission is slow, page responds slowly, interface response times out, and the system is in error or even crash.
• System fault: Customer services may be interrupted. The system may break down and the key information stored on the faulty disk may be lost.

Possible Causes

The disk is aged or has bad sectors.

Handling Procedure

Check the disk status.

1. On FusionInsight Manager, choose O&M. In the navigation pane on the left, choose Alarm > Alarms.
2. View the detailed information about the alarm. Check the values of HostName and DiskName in the location information to obtain the information about the faulty disk for which the alarm is generated.
3. Check whether the node for which the alarm is generated is in a virtualization environment.
   • If yes, go to 4.
   • If no, go to 7.

4. Check whether the storage performance provided by the virtualization environment meets the hardware requirements. Then, go to 5.
5. Log in to the alarm node as user root, run the df -h command, and check whether the command output contains the value of the DiskName field.
   • If yes, go to 7.
   • If no, go to 6.

6. Run the lsblk command to check whether the mapping between the value of DiskName and the disk has been created.
   

   • If yes, go to 7. .
   • If no, go to 25.

7. Log in to the alarm node as user root, run the lsscsi | grep "/dev/sd[x]" command to view the disk information, and check whether RAID has been set up.
   

   In the command, /dev/sd[x] indicates the disk name obtained in 2.

   Example:

   lsscsi | grep "/dev/sda"

   In the command output, if ATA, SATA, or SAS is displayed in the third line, the disk has not been organized into a RAID group. If other information is displayed, RAID has been set up.

   • If yes, go to 12.
   • If no, go to 8.

8. Run the smartctl -i /dev/sd[x] command to check whether the hardware supports the SMART tool.

   Example:

   smartctl -i /dev/sda

   In the command output, if "SMART support is: Enabled" is displayed, the hardware supports SMART. If "Device does not support SMART" or other information is displayed, the hardware does not support SMART.

   • If yes, go to 9.
   • If no, go to 16.

9. Run the smartctl -H --all /dev/sd[x] command to check basic SMART information and determine whether the disk is working properly.

   Example:

   smartctl -H --all /dev/sda

   Check the value of SMART overall-health self-assessment test result in the command output. If the value is FAILED, the disk is faulty and needs to be replaced. If the value is PASSED, check the value of Reallocated_Sector_Ct or Elements in grown defect list. If the value is greater than 100, the disk is faulty and needs to be replaced.

   • If yes, go to 10.
   • If no, go to 18.

10. Run the smartctl -l error -H /dev/sd[x] command to check the Glist of the disk and determine whether the disk is normal.

    Example:

    smartctl -l error -H /dev/sda

    Check the Command/Feature_name column in the command output. If READ SECTOR(S) or WRITE SECTOR(S) is displayed, the disk has bad sectors. If other errors occur, the disk circuit board is faulty. Both errors indicate that the disk is abnormal and needs to be replaced.

    If "No Errors Logged" is displayed, no error log exists. You can perform step 9 to trigger the disk SMART self-check.

    • If yes, go to 11.
    • If no, go to 18.

11. Run the smartctl -t long /dev/sd[x] command to trigger the disk SMART self-check. After the command is executed, the time when the self-check is to be completed is displayed. After the self-check is completed, repeat 9 and 10 to check whether the disk is working properly.

    Example:

    smartctl -t long /dev/sda

    • If yes, go to 17.
    • If no, go to 18.

12. Run the smartctl -d [sat|scsi]+megaraid,[DID] -H --all /dev/sd[x] command to check whether the hardware supports SMART.
    

    • In the command, [sat|scsi] indicates the disk type. Both types need to be used.
    • [DID] indicates the slot information. Slots 0 to 15 need to be used.

    For example, run the following commands in sequence:

    smartctl -d sat+megaraid,0 -H --all /dev/sda

    smartctl -d sat+megaraid,1 -H --all /dev/sda

    smartctl -d sat+megaraid,2 -H --all /dev/sda

    ...

    Try the command combinations of different disk types and slot information. If "SMART support is: Enabled" is displayed in the command output, the disk supports SMART. Record the parameters of the disk type and slot information when a command is successfully executed. If "SMART support is: Enabled" is not displayed in the command output, the disk does not support SMART.

    • If yes, go to 13.
    • If no, go to 16.

13. Run the smartctl -d [sat|scsi]+megaraid,[DID] -H --all /dev/sd[x] command recorded in 12 to check basic SMART information and determine whether the disk is normal.

    Example:

    smartctl -d sat+megaraid,2 -H --all /dev/sda

    Check the value of SMART overall-health self-assessment test result in the command output. If the value is FAILED, the disk is faulty and needs to be replaced. If the value is PASSED, check the value of Reallocated_Sector_Ct or Elements in grown defect list. If the value is greater than 100, the disk is faulty and needs to be replaced.

    • If yes, go to 14.
    • If no, go to 18.

14. Run the smartctl -d [sat|scsi]+megaraid,[DID] -l error -H /dev/sd[x] command to check the Glist of the disk and determine whether the hard disk is working properly.

    Example:

    smartctl -d sat+megaraid,2 -l error -H /dev/sda

    Check the Command/Feature_name column in the command output. If READ SECTOR(S) or WRITE SECTOR(S) is displayed, the disk has bad sectors. If other errors occur, the disk circuit board is faulty. Both errors indicate that the disk is abnormal and needs to be replaced.

    If "No Errors Logged" is displayed, no error log exists. You can trigger the disk SMART self-check.

    • If yes, go to 15.
    • If no, go to 18.

15. Run the smartctl -d [sat|scsi]+megaraid,[DID] -t long /dev/sd[x] command to trigger the disk SMART self-check. After the command is executed, the time when the self-check is to be completed is displayed. After the self-check is completed, repeat 13 and 14 to check whether the disk is working properly.

    Example:

    smartctl -d sat+megaraid,2 -t long /dev/sda

    • If yes, go to 17.
    • If no, go to 18.

16. If the configured RAID controller card does not support SMART, the disk does not support SMART. In this case, use the check tool provided by the corresponding RAID controller card vendor to rectify the fault. Then go to 17.

    For example, LSI is a MegaCLI tool.

17. On FusionInsight Manager, choose O&M > Alarm > Alarms, click Clear in the Operation column of the alarm, and check whether the alarm is reported on the same disk again.

    If the alarm is reported for three times, replace the disk.

    • If yes, go to 18.
    • If no, no further action is required.

Replace the disk.

18. On FusionInsight Manager, choose O&M. In the navigation pane on the left, choose Alarm > Alarms.
19. View the detailed information about the alarm. Check the values of HostName and DiskName in the location information to obtain the information about the faulty disk for which the alarm is reported.
20. Check whether the host for which the alarm is generated is the active OMS node or the active node of the instance in active/standby mode.
    • If yes, go to 21.
    • If no, go to 23.

21. Log in to the node for which the alarm is generated as the root user and run the following command to check the mount point of the faulty disk:

    df -h | grep "Name of the faulty disk"

    Check whether the mount point partition of the faulty disk is the cluster software installation directory (${BIGDATA_HOME}) or data disk directory (${BIGDATA_DATA_HOME} by default).

    • If yes, go to 22.
    • If no, go to 23.

22. Trigger an active/standby switchover to rectify the fault.
    • Active OMS node

      If O&M operations cannot be performed due to slow disk faults, such as system freezing, delayed page refreshing, or slow API response, and the alarm is generated for the active OMS node, perform the following operations to trigger an active/standby switchover to restore services:

      1. Log in to the active OMS node as user omm.
      2. Run the following command to perform an active/standby switchover:
         • For the IPv4 network: ${OMS_RUN_PATH}/workspace/ha/module/hacom/tools/ha_client_tool --ip=127.0.0.1 --port=20013 --switchover --name=product
         • For the IPv6 network: ${OMS_RUN_PATH}/workspace/ha/module/hacom/tools/ha_client_tool --ip=::1 --port=20013 --switchover --name=product
      3. After the active/standby switchover is successful, the system recovers. Perform 23 to replace the faulty disk.
    • Active node of an active/standby instance

      If the alarm is generated for the active node of an instance in active/standby mode and the slow disk fault affects the running of the instance, trigger an active/standby switchover on FusionInsight Manager to restore services.

      1. Log in to FusionInsight Manager and choose Cluster > Services > Name of the desired service.
      2. On the service details page, expand the More drop-down list and select Perform xxx Switchover.
      3. In the displayed dialog box, enter the password of the current login user and click OK.
      4. In the displayed dialog box, click OK to perform active/standby switchover.
      5. After the active/standby switchover is successful, the system recovers. Perform 23 to replace the faulty disk.

23. Replace the disk.
24. Check whether the alarm is cleared.
    • If yes, no further action is required.
    • If no, go to 25.

Collect the fault information.

25. On FusionInsight Manager, choose O&M. In the navigation pane on the left, choose Log > Download.
26. Select OMS for Service and click OK.
27. Click the edit icon in the upper right corner, and set Start Date and End Date for log collection to 10 minutes ahead of and after the alarm generation time, respectively. Then, click Download.
28. Contact O&M engineers and provide the collected logs.

Alarm Clearance

This alarm is automatically cleared after the fault is rectified.

Related Information

None.