HP OpenVMS Systems Documentation

Figure 6-20 shows an invalid multipath configuration. The configuration is invalid because, if multiple hosts in a cluster are connected to an HSZ or HSG, they must all have connections to the same controller modules (see Table 6-1). In this configuration, each host is connected to a different controller module.

Figure 6-20 Invalid Multipath Configuration

Multipath support is enabled and qualified by the use of the system parameters described in Table 6-3. (Certain multipath system parameters are reserved for the operating system.)

The system management commands described in the following sections allow you to monitor and control the operation of multipath failover. These commands provide a path identifier to uniquely specify each path in a multipath set.

Direct Fibre Channel paths are identified by the local host adapter name and the remote Fibre Channel port WWID --- that is, the initiator and the target. For example, in Figure 6-21, the path identifier for the path from the host adapter on the left to the HSG storage controller on the left is PGB0.5000-1FE1-0000-0200. (The second port on each HSG is omitted for convenience.) You can obtain the WWID for a storage controller from its console.

Figure 6-21 Fibre Channel Path Naming

Direct parallel SCSI paths are identified by the local host adapter name and the remote SCSI bus ID --- that is, the initiator and the target. For example, in Figure 6-22, the path identifiers for node Edgar's two direct paths to the disk would be named PKB0.5 and PKC0.5.

The path identifier for MSCP served paths is MSCP .

Figure 6-22 Configuration With Multiple Direct Paths

When multipath support is enabled, you can display the multiple paths to a device using either of the following variants of the SHOW DEVICE DCL command:

SHOW DEVICE/FULL device-name

SHOW DEVICE/MULTIPATH_SET device-name

The SHOW DEVICE/FULL device-name command displays the traditional information about the device first and then lists all the paths to a device by their path identifiers (described in Section 6.7.4).

The SHOW DEVICE/MULTIPATH_SET device-name command lists only some brief multipath information about devices that have multiple paths.

Multipath information is displayed only on nodes that are directly connected to the multipath device.

6.7.5.1 Displaying Paths With SHOW DEVICE/FULL

The following example shows the output of a SHOW DEVICE/FULL device-name command. Note that the use of multiple paths is shown at the beginning of the display ( device has multiple I/O paths ), and the multiple path descriptions are shown toward the end of the display, beneath I/O paths to device . Note, too, that the values for Error count and Operations completed shown at the beginning of the display are the sums of the counts for each path.

$ SHOW DEVICE/FULL $1$DGA23:

Disk $1$DGA23: (WILD8), device type HSG80, is online, mounted, file-oriented
    device, shareable, device has multiple I/O paths, served to cluster via MSCP
    Server, error logging is enabled.

    Error count                    3    Operations completed           32814199
    Owner process                 ""    Owner UIC                      [SYSTEM]
    Owner process ID        00000000    Dev Prot            S:RWPL,O:RWPL,G:R,W
    Reference count                9    Default buffer size                 512
    WWID   01000010:6000-1FE1-0000-0D10-0009-8090-0677-0034
    Total blocks            17769177    Sectors per track                   169
    Total cylinders             5258    Tracks per cylinder                  20
    Host name                "WILD8"    Host type, avail Compaq AlphaServer GS160 6/731, yes
    Alternate host name     "W8GLX1"    Alt. type, avail Compaq AlphaServer GS160 6/731, yes
    Allocation class               1

    Volume label      "S5SH_V72_SSS"    Relative volume number                0
    Cluster size                  18    Transaction count                     8
    Free blocks             12812004    Maximum files allowed            467609
    Extend quantity                5    Mount count                           8
    Mount status              System    Cache name          "_$1$DGA8:XQPCACHE"
    Extent cache size             64    Maximum blocks in extent cache  1281200
    File ID cache size            64    Blocks currently in extent cache      0
    Quota cache size               0    Maximum buffers in FCP cache       1594
    Volume owner UIC           [1,1]    Vol Prot    S:RWCD,O:RWCD,G:RWCD,W:RWCD

  Volume Status:  ODS-2, subject to mount verification, file high-water marking,
      write-back caching enabled.
  Volume is also mounted on H2OFRD, FIBRE3, NORLMN, SISKO, BOOLA, FLAM10,
          W8GLX1.

  I/O paths to device              5
  Path PGA0.5000-1FE1-0000-0D12  (WILD8), primary path.
    Error count                    2    Operations completed             130666
  Path PGA0.5000-1FE1-0000-0D13  (WILD8), current path.
    Error count                    1    Operations completed           30879310
  Path PGA0.5000-1FE1-0000-0D11  (WILD8).
    Error count                    0    Operations completed             130521
  Path PGA0.5000-1FE1-0000-0D14  (WILD8).
    Error count                    0    Operations completed             130539
  Path MSCP (W8GLX1).
    Error count                    0    Operations completed            1543163

For each path of the multipath device, the path identifier, the host name associated with that path, the path status, the error count, and the operations count are displayed.

The terms that may appear in the multiple paths portion of the display are described in Table 6-4.

You can obtain a brief listing of multiple paths for a specific device, for all the devices in an allocation class, or for all devices with the DCL command:

SHOW DEVICE/MULTIPATH_SET [device-name]

The device name is optional; when omitted, all devices that have formed multipath sets are shown. For each multipath device found, the device name, host name, device status, error count, number of accessible paths, total number of paths, and the current path's path identifier are displayed.

The host name displayed is the host name of the current path. For direct paths, this will be the local system's host name. For MSCP served paths, this will be the host name of the remote system which is serving access to the device.

The following example shows the output of a SHOW DEVICE /MULTIPATH command.

$ SHOW DEVICE/MULTIPATH
Device                  Device           Error  Paths  Current
 Name                   Status           Count Avl/Tot   path
$1$DGA8:      (H2OFRD)  Mounted              3   5/ 5  PGA0.5000-1FE1-0000-0D12
$1$DGA10:     (H2OFRD)  ShadowSetMember      1   5/ 5  PGA0.5000-1FE1-0000-0D14
$1$DGA11:      (WILD8)  ShadowSetMember      3   3/ 3  MSCP
$1$DGA23:     (H2OFRD)  Mounted              6   5/ 5  PGA0.5000-1FE1-0000-0D13
$1$DGA30:     (H2OFRD)  ShadowSetMember      8   5/ 5  PGA0.5000-1FE1-0000-0D13
$1$DGA31:      (WILD8)  ShadowMergeMbr       5   3/ 3  MSCP
$1$DGA33:     (H2OFRD)  Online               0   5/ 5  PGA0.5000-1FE1-0000-0D12
$1$DGA40:     (H2OFRD)  Mounted              2   5/ 5  PGA0.5000-1FE1-0000-0D13
$1$DGA41:     (H2OFRD)  ShadowMergeMbr       8   5/ 5  PGA0.5000-1FE1-0000-0D12
$70$DKA100:   (H2OFRD)  Mounted              0   3/ 3  PKD0.1
$70$DKA104:   (H2OFRD)  ShadowSetMember      0   3/ 3  PKD0.1
$70$DKA200:   (H2OFRD)  ShadowSetMember      0   3/ 3  PKD0.2
$70$DKA300:   (H2OFRD)  ShadowSetMember      0   3/ 3  PKC0.3
$80$DKA1104:  (H2OFRD)  ShadowSetMember      0   3/ 3  PKD0.11
$80$DKA1200:  (H2OFRD)  ShadowSetMember      0   3/ 3  PKD0.12
$80$DKA1204:  (H2OFRD)  ShadowSetMember      0   3/ 3  PKC0.12
$80$DKA1207:  (H2OFRD)  Mounted              0   3/ 3  PKD0.12
$80$DKA1300:  (H2OFRD)  Mounted              0   3/ 3  PKD0.13
$80$DKA1307:  (H2OFRD)  ShadowSetMember      0   3/ 3  PKD0.13
$80$DKA1500:  (H2OFRD)  Mounted              0   3/ 3  PKD0.15
$80$DKA1502:  (H2OFRD)  ShadowSetMember      0   3/ 3  PKD0.15

If you choose to specify a partial device name, such as $70$DKA, the display shows all devices with multiple paths whose names begin with $70$DKA.

6.7.6 Path Polling

When SCSI multipath support is in effect, the system periodically polls all the I/O paths from each host adapter to each HSZ or HSG controller to determine the status of each I/O path. If the system detects any changes to a path, it outputs a message, similar to the following messages, to the console and to the operator's log:

All multipath devices on path PKB0.5 are either disabled or not reachable.

or

At least one multipath device on path PKB0.5 is enabled and reachable.

If all the devices on a path are removed, a path failure is reported. The path from the host to the HSx controller may still function, but this cannot be determined when there are no devices to poll.

You can turn polling on or off with the following command:

SET DEVICE device/[NO]POLL/PATH=path-identifier

Turning off polling for a path that will be out of service for a prolonged period is useful because it can reduce system overhead.

6.7.7 Switching Current Paths Manually

You can switch a device's current path manually using the SET DEVICE command with the /SWITCH qualifier. The most common reason for doing this is to balance the aggregate I/O load across multiple HSx controller modules and buses.

The command syntax for switching the current path is:

SET DEVICE device-name/SWITCH/PATH=path-identifier

The following command switches the path of device $2$DKA502 to an MSCP served path.

$ SET DEVICE $2$DKA502/SWITCH/PATH=MSCP

Note that this command initiates the process of switching the path and then returns to the DCL prompt immediately. A delay may occur between when the DCL prompt reappears and when the path switch is complete.

A manual path switch of a mounted device takes place within mount verification, which is triggered by the path switch command. It is accompanied by the usual mount verification messages and a path switch message. This is shown in Example 6-1:

 %%%%%%%%%%%  OPCOM  15-JUN-2001 09:04:23.05  %%%%%%%%%%%
 Device $1$DGA23: (H2OFRD PGA) is offline.
 Mount verification is in progress.

 %%%%%%%%%%%  OPCOM  15-JUN-2001 09:04:25.76  %%%%%%%%%%%
 09:04:25.76 Multipath access to device $1$DGA23: has been manually switched
 from path PGA0.5000-1FE1-0000-0D11 to path PGA0.5000-1FE1-0000-0D14

 %%%%%%%%%%%  OPCOM  15-JUN-2001 09:04:25.79  %%%%%%%%%%%
 Mount verification has completed for device $1$DGA23: (H2OFRD PGA)

You can check for completion of a path switch by issuing the SHOW DEVICE/FULL command, or the SHOW DEVICE/MULTIPATH command.

Note that if the path that is designated in a manual path switch fails during the switch operation, then automatic path switching takes over. This can result in a switch to a path different from the one designated in the command.

If a manual path switch causes a logical unit to switch from one HSG80 controller to another controller, then the command can affect other nodes in the cluster. These nodes will experience a mount verification on their current path. This will cause an automatic switch to a path on the other HSG80 controller. The messages indicating this event are shown in Example 6-2:

 %%%%%%%%%%%  OPCOM  15-JUN-2001 09:04:26.48  %%%%%%%%%%%
 Device $1$DGA23: (WILD8 PGA) is offline.
 Mount verification is in progress.

 %%%%%%%%%%%  OPCOM  15-JUN-2001 09:04:26.91  %%%%%%%%%%%
 09:04:29.91 Multipath access to device $1$DGA23: has been auto switched from
 path PGA0.5000-1FE1-0000-0D12 to path PGA0.5000-1FE1-0000-0D13

 %%%%%%%%%%%  OPCOM  15-JUN-2001 09:04:27.12  %%%%%%%%%%%
 Mount verification has completed for device $1$DGA23: (WILD8 PGA)

In a multipath configuration, the first path to a device that OpenVMS configures is the initial current path to the device by default. However, the current path can change as a result of a MOUNT command to a multipath device. The I/O performed by the MOUNT command triggers a search for a direct path that does not require the device to failover from one HSx controller module to another. This has the following benefits:

• Minimizes the disruption on other hosts
• Tends to preserve any static load balancing that has been manually set up
• Enables the use of HSx console commands to set up an initial default distribution of devices between the two HSx controllers
• Prefers direct paths over MSCP served paths

The MOUNT-time path selection proceeds as follows:

1. If the current path is a direct path and access to the device on this path does not require a controller failover, the current path is used.
2. If the current path is an MSCP path and it was selected by a manual path switch command, the current path is used.
3. All direct paths are checked. If a path is found where access to the device does not require a controller failover, that path is selected. If the selected path is not the current path, an automatic path switch is performed and an OPCOM message is issued.
4. All direct paths are tried. If necessary, an attempt is made to failover the device to the HSx controller on the selected path.
5. The MSCP served path is tried.

The MOUNT utility might trigger this path selection algorithm a number of times until a working path is found. The exact number of retries depends on the elapsed time for the prior attempts and the qualifiers specified with the MOUNT command.

Note that this selection process allows devices to be distributed between the two HSx controllers. You can accomplish this by using HSx console commands such as the following:

HSG> SET UNIT PREFERRED_PATH=THIS_CONTROLLER

HSG> SET UNIT PREFERRED_PATH=OTHER_CONTROLLER

In addition, you can use the manual path switching DCL commands, described in Section 6.7.7, to select a different host bus adapter, a different port on the same HSx controller, or to force the device to failover to a different HSx controller.

6.7.9 How OpenVMS Performs Multipath Failover

When an I/O operation fails on a mounted device and the failure status suggests that retries are warranted, mount verification is invoked. If the device is a multipath device, alternate paths to the device are tried during mount verification. This allows the system to transparently recover from cases where the device has failed over from one HSx controller to another and to transparently recover from failures in the path to the device. The path selection during mount verification proceeds as follows:

1. If the current path is a direct path and access to the device on this path does not require a controller failover, the current path is tried.
2. If the current path is an MSCP path and it was selected by a manual path switch command, the current path is tried.
3. All direct paths that do not require a controller failover are tried.
4. Step 3 is repeated the number of times specified by the MPDEV_LCRETRIES system parameter. This provides additional bias towards selection of a path that does not require an HSx controller failover. The default value for MPDEV_LCRETRIES is 1.
5. All direct paths are tried.
6. If present, the MSCP served path is tried.

Steps 1 through 6 are repeated until either a working path is found or mount verification times out. If a working path is found and the path is different, the current path is automatically switched to the new path and an OPCOM message is issued. Mount verification then completes, the failed I/O is restarted, and new I/O is allowed to proceed. This path selection procedure attempts to avoid unnecessary failover of devices from one HSx controller to another because:

• Failover from one HSx controller module to another causes a delay of approximately 1 to 15 seconds, depending on the amount of cached data that needs to be synchronized.
• Other nodes that share access to the device must reestablish communication using an alternate path.

This path selection procedure prefers direct paths over MSCP served paths because the use of an MSCP served path imposes additional CPU and I/O overhead on the server system. In contrast, the use of a direct path imposes no additional CPU or I/O overhead on the MSCP-server system. This procedure selects an MSCP served path only if none of the available direct paths are working.