Why Multipathing ?

To maintain a constant connection between a host and its storage, ESXi supports multipathing. Multipathing is a technique that lets you use more than one physical path that transfers data between the host and an external storage device.

In case of a failure of any element in the SAN network, such as an adapter, switch, or cable, ESXi can switch to another physical path, which does not use the failed component. This process of path switching to avoid failed components is known as path failover.

In addition to path failover, multipathing provides load balancing. Load balancing is the process of distributing I/O loads across multiple physical paths. Load balancing reduces or removes potential bottlenecks.

To take advantage of this support, virtual volumes should be exported to multiple paths to the host server. For this we have to create a host definition on the HPE 3PAR Storage system that includes the World Wide Names (WWNs) of multiple HBA ports on the host server and then export the VLUNs to that host definition. For an ESXi cluster, the VLUNs must be exported to all of the host definitions for the cluster nodes, or a host set may be created containing all of the servers and the VLUNs.

Setting Round Robin path policy

VMware vSphere includes active/active multipath support to maintain a constant connection between the ESXi host and the HPE 3PAR StoreServ Storage array. Three path policies are available,

Fixed (VMware)

The host uses the designated preferred path, if it has been configured. Otherwise, it selects the first working path discovered at system boot time. If you want the host to use a particular preferred path, specify it manually. Fixed is the default policy for most active-active storage devices.

Note
If the host uses a default preferred path and the path’s status turns to Dead, a new path is selected as preferred. However, if you explicitly designate the preferred path, it will remain preferred even when it becomes inaccessible.

Most Recently Used (VMware)

The host selects the path that it used most recently. When the path becomes unavailable, the host selects an alternative path. The host does not revert back to the original path when that path becomes available again. There is no preferred path setting with the MRU policy. MRU is the default policy for most active-passive storage devices.

Round Robin (VMware)

The host uses an automatic path selection algorithm rotating through all active paths when connecting to active-passive arrays, or through all available paths when connecting to active-active arrays. RR is the default for a number of arrays and can be used with both active-active and active-passive arrays to implement load balancing across paths for different LUNs.

For HPE 3PAR storage, Round Robin is the recommended policy for best performance and load balancing; however, it may not be enabled by default. The path policies can be viewed and modified from the VMware vSphere Web Client on a per datastore basis as follows:

  1. In the vSphere Web Client, select the datastore.
    2. Select the Manage tab, then the Settings tab, and then click on Connectivity and multipathing
    3. Select one of the ESXi hosts and then click the Edit Multipathing button.
    4. In the pop-up window, select Round Robin from the Path selection policy drop-down menu.
    5. Click the OK button to save the new setting.
    6. Repeat steps 3 through 5 for each ESXi host.

 

Below Picture shows HPE 3PAR StoreServ Fast Class VLUN that has most recently used  and active IO only on one path .

Change the policy to Round Robin path  and check the status of “Active (I/O)” , it will be like below

 

Setting IOPS option for Round Robin policy

Managing a Round Robin I/O path policy scheme through the vSphere Web Client on a per datastore will not allow setting . We can modify the Round Robin policy details from command line on the ESXi host. To achieve better load balancing across paths,the –iops option may be issued on the command line to specify that the path should be switched after performing the specified number of I/Os on the current path. By default, the –iops option is set to 1000. The recommended setting for HPE 3PAR Storage is 1, and this setting may be changed as needed to suit the demands of various workloads.

Set the Round Robin policy for a specific device


# esxcli storage nmp device set –device <device-name> –psp VMW_PSP_RR


To set the device specified by –device to switch to the next path after 1 I/O operation has been performed on the current path


# esxcli storage nmp psp roundrobin deviceconfig set –type=iops –iops=1 –device <device-name>


Automating Round Robin policy for all LUNs

To automate this we have to edit the SATP rule or created using esxcli commands on the ESXi host to automatically achieve aRound Robin path policy for newly discovered LUNs.

Use the following command to create a custom SATP rule that will allow the ESXi host to configure the HPE 3PAR LUNs to use Round Robin multipath policy. The command must be executed on each ESXi host that is connected to the HPE 3PAR array.


#esxcli storage nmp satp rule add -s “VMW_SATP_ALUA” -P “VMW_PSP_RR” -O “iops=1” -c “tpgs_on” -V “3PARdata” -M “VV” -e “HP 3PAR Custom Rule”


Verify the new rule using the following command:


# esxcli storage nmp satp rule list | grep “3PARdata”


Note:New rule will be effective when adding new devices to the ESXi host, For existing LUNs, either a host reboot is required, or the path policy must be set for each LUN.

Reference