Help
Table Of Contents
- Dell EMC Storage Systems Online Help for the metro node appliance
- Contents
- Figures
- Welcome
- Using the GUI
- Configuring GUI default settings
- Using storage hierarchy maps
- Viewing system status
- Monitoring the system
- Performance
- The Performance Monitoring dashboard
- Viewing a chart
- Modifying a dashboard layout
- Creating a custom dashboard
- Removing a chart
- Moving a chart
- Back-end Bandwidth Chart
- Back-end Throughput chart
- Back-end Errors chart
- Back-end Latency chart
- CPU utilization chart
- Heap Usage chart
- Front-end Queue Depth chart
- Front-end Bandwidth chart
- Front-end Latency chart
- Front-end Throughput chart
- Front-end Aborts chart
- Write Latency Delta chart
- WAN Port Performance chart
- WAN Latency chart
- Rebuild Status dashboard
- Virtual Volumes dashboard
- Front End Ports dashboard
- System Health
- Performance
- Provisioning storage
- Guide
- Provisioning from storage volumes
- Provision Job properties
- Distributed storage
- Storage arrays
- Storage volumes
- Devices
- About devices
- Using the Devices view
- The Create Devices wizard
- The Add Local/Remote Mirror wizards
- Viewing the status of IO to a device
- Creating a device
- Renaming a device
- Deleting a device
- Mirroring a device
- Device status
- Device component properties
- Device properties
- Distributed device properties
- Add capacity to virtual volumes
- Extent properties
- Extents
- Distributed devices
- About distributed devices
- The Distributed Devices view
- The Create Distributed Device from Claimed Storage Volumes wizard
- Distributed device rule sets
- Changing the rule set for a distributed device
- Creating a distributed device
- Deleting a distributed device
- Renaming a distributed device
- Distributed Device status
- Virtual volumes
- About virtual volumes
- The Virtual Volumes view
- The Distributed Virtual Volumes view
- Creating a virtual volume
- About virtual volume expansion
- Expanding a virtual volume using storage volumes
- Enabling or disabling remote access for a volume
- Manually assigning LUN numbers to volumes
- Deleting a volume
- Renaming a volume
- Tearing down a volume
- Virtual Volume status
- Pool properties
- Virtual volume properties
- Show ITLs dialog box
- Logical unit properties
- ALUA Support field values
- Visibility field values
- Extent or Device mobility job properties
- Metro node port properties
- Storage array properties
- Storage view properties
- Storage volume properties
- Create Virtual Volumes dialog box
- Consistency group
- About consistency groups
- Using the Consistency Groups view
- Distributed Consistency Groups view
- Create Consistency Group wizard
- Types of consistency groups
- Creating a consistency group
- Adding a volume to a consistency group
- Removing a volume from a consistency group
- Deleting a consistency group
- Consistency Group status
- Consistency group properties
- Step 1: Select or create a consistency group for the virtual volume
- Step 1: Create a consistency group
- Step 2: Select volume options
- Step 3: Select a storage pool
- Step 3: Select a pool for each mirror on the second cluster
- Step 3: Select a pool for each mirror in the cluster
- Step3: Create thin virtual volumes
- Select a storage view for the virtual volume(s) (optional)
- Step 5: Review your selections
- Step 6: View results
- Step 2: Select volume options
- Step 2: Select volume options
- Step 3: Select a storage volume to create the virtual volume
- Step 3: Select a source and target storage volume
- Step 3: Create thin volumes
- Step 3: Select a target storage volume on the remote cluster
- Step 3: Select target storage on the remote cluster
- Step 6: View results
- Show Logical Units
- Exporting storage
- Initiators and metro node ports
- Storage views
- About storage views
- Using the Storage Views screen
- The Create Storage View wizard
- Creating a storage view
- Deleting a storage view
- Renaming a storage view
- Adding or removing initiators from a storage view
- Adding virtual volumes to a storage view
- Removing virtual volumes from a storage view
- Adding or removing metro node ports from a storage view
- Storage view status
- Storage group properties
- Director properties
- Cluster properties
- Moving data
- Mobility
- Move Data Within Cluster
- Move Data Across Clusters
- Create Mobility Job wizards
- Mobility job transfer size
- Creating a mobility job
- Viewing job details
- Committing a job
- Canceling a job
- Pausing a job
- Resuming a job
- Removing the record of a job
- Changing a job transfer size
- Searching for a job
- Mobility job status
- Notifications
NOTE: The chart displays data for the cluster to which you are connected. To simultaneously view the statistics for a
remote cluster, open a second browser session and connect to the remote cluster's management console.
Guidelines
● The absolute value of the bytes (or bandwidth) and packet (or throughput) related categories might not indicate a problem.
They will reflect the amount of traffic requested by other internal metro node firmware components, which is ultimately the
host application requested load.
● If the observed maximums appear to be much lower than the available inter-cluster bandwidth or what you expect to see
from your application, this is worth investigating.
● FC-COM specific: If Fibre Channel switches are used over dark fibre or DWDM WAN equipment, ensure that the WAN facing
Fibre Channel ports have sufficient buffer credits allocated to the ports. A lack of buffer credits imposes an undesired limit
on the maximum throughput on the WAN port.
● For Brocade switches:
○ An extended fabric license is required for each edge switch, and the WAN facing ports must be set to LS or LD mode.
See the portcfglongdistance command.
○ Monitor the port's counters for non-zero values for tim_txcrd_z or time transmission credits are zero. This means the
Fibre Channel port wanted to transmit a Fibre Channel packet, but did not have sufficient buffer credits to do so. Any
non-zero value in this category implies performance issues on the WAN port.
○ If FCIP gateway devices are used between metro node clusters, ensure that the FCIP tunnel is configured properly.
● For Brocade FCIP switches:
○ Check for bandwidth rate limiting setting on the tunnel. See the portshow fciptunnel command. Verify that the
values for Minimum/Maximum Communication Rate are not causing a bottleneck.
○ Check for improper QoS settings on the tunnel. In the portshow fciptunnel command output, check the values for
QoS Percentages. Note that only if QoS has been set on the LAN facing Fibre Channel ports will QoS settings affect the
fciptunnel settings.
Corrective actions
● Check the ip-com and fc-com ports health on the directors.
● Check the WAN products for improperly configured ports, link errors, packet loss, QoS limitations, or large observed
round-trip-times outside of supported metro node specs.
● If you suspect that you are not achieving optimal inter-cluster WAN throughput, verify the available inter-cluster bandwidth.
● Check the WAN latency using the director ping CLI command.
● Check the WAN Latency chart or the monitor category com-cluster-io for a history of WAN latency.
● Follow the WAN products' performance best practices.
● Find out from your WAN provider if anything has changed recently.
● WAN COM performance for remote read or remote write operations for distributed-devices and remote-devices are also
limited to the storage array's performance. Make sure that the back-end performance on your remote cluster is not your
bottleneck.
● IP-COM specific:
● Check the network's maximum supported MTU (maximum transmission unit) size. Standard networks support 1500 byte
MTUs. Jumbo frames can support up to about 9000 byte MTUs, which typically result in faster throughputs and consumes
fewer CPU cycles. Jumbo frames however must be explicitly enabled on every device in the network path (director
tracepath CLI command shows the number of hops.) WAN providers are typically reluctant to enable jumbo frames.
● Check the WAN Message Size chart.
● Check the port-group's socket buffer size (socket-buf-size in /clusters/cluster-#/cluster-connectivity/option-sets/
optionset-com-#/). The default is set to 1MB. The optimal value for this the network's delay-bandwidth product which is the
latency or delay of the network multiplied by the available bandwidth, which is the amount of data required to be outstanding
to fully utilize the network.
● If this value is too large for a low bandwidth connection, there will be connection keepalive timeouts and possibly cluster
departure events. Lower the socket-buf-size in this case.
● If this value is too low for a high bandwidth connection, there won't be enough in-flight data outstanding on the WAN
port to fully utilize its available capacity, and the observed performance will be much less than expected. Increase the
socket-buf-size to the minimum delay-bandwidth product.
Monitoring the system
45