Storage layer

Isilon is a scale-out NAS storage solution that delivers increased performance for file-based data applications and workflows from a single file-system architecture.

Isilon provides scale-out capacity for use as NFS and SMB CIFS shares within the VMware vSphere VMs.

Isilon is available in the following configurations:

• Isilon All-Flash
• Isilon Hybrid Scale-out NAS
• Isilon Archive Scale-out NAS

The following table shows the hardware components with each configuration:

The following Cisco Nexus switches provide front-end connectivity:

• Cisco Nexus 93180YC-FX
• Cisco Nexus 93180LC-EX
• Cisco Nexus 9336C-FX2

The Isilon back-end Ethernet switches provide:

• 10 GbE 24 port
• 10 GbE 48 port
• 10 GbE 96 port (2 x 48-port leaf modules)
• 10 GbE 48-port leaf module
• 40 GbE 32 port
• 40 GbE 64 port (2 x 32-port leaf modules)
• 40 GbE 32-port leaf module

Note:  Leaf modules are only applicable in chassis types that are 10 GbE over 48 nodes and 40 GbE over 32 nodes.

Array components and specifications

Isilon All-Flash, hybrid, and archive models are contained within a four-node chassis.

There are four compute slots per chassis each contain:

• Single-socket CPU
• Four DDR4 DIMM slots
• Front-end 10 GbE or 40 GbE optical (depending on the node type)
• Back-end 10 GbE or 40 GbE optical (depending on the node type)
• Single onboard 1 GbE
• DB-9 serial connection

Note: 1 GbE connections are not used.

• Up to 2 x 2.5 inch SSD for cache
• Up to 2 x M.2 vault disks
• Dual 1100 W or 1450 W PDUs
• The following models have 20 x 2.5 inch drive sleds
  • F800
  • F810
  • H600
• [7]The following models have 20 x 3.5 inch drive sleds
  • H500
  • H5600
  • H400
  • A200
  • A2000

The following table provides hardware and software specifications for each Isilon model:

Isilon network topology

Isilon network topology uses uplinks and peer-links to connect the ToR Cisco Nexus 9000 Series Switches to the VxBlock System.

The following figure provides Isilon network connectivity in a VxBlock System:

The following port channels are used in the Isilon network topology:

• 3: Uplinks to connect the Isilon ToR switch and the VxBlock System ToR switch.
• 50: Peer-links to the VxBlock System ToR switch.

Note: More Cisco Nexus 9000 Series Switch pair uplinks start from port channel or vPC ID 4, and increase for each switch pair.

• 51: Peer-links to the Converged Technology Extension for Isilon ToR switches.

Note: More Cisco Nexus 9000 series switch pair peer-links start from port channel or vPC ID 52, and increase for each switch pair.

• 1001: Isilon node and ToR switch.

Note: Isilon nodes start from port channel or vPC ID 1002 and increase for each LC node.

The following reservations apply for the Isilon topology:

• The last four ports on the Isilon ToR switches are reserved for uplinks.
• vPC connections between the Isilon switches and the VxBlock System switches must be cross connected.
• The two ports immediately preceding the uplink ports on the Isilon switches are reserved for peer-links.
• All the ports that are not uplinks or peer-links are reserved for nodes.
• Create a port channel for the nodes starting at PC/vPC 1001 to directly connect the Isilon nodes to the VxBlock System ToR switches.

Isilon back-end architecture

With the Isilon OneFS 8.2.0 operating system, the back-end topology supports scaling a sixth generation Isilon cluster up to 252 nodes.

Isilon uses a spine and leaf architecture that is based on the maximum internal bandwidth and 32-port count of Dell Z9100 switches. A spine and leaf architecture provides the following benefits:

• High scalability
• Provides redundancy
• Minimizes latency and the likelihood of bottlenecks in the back-end network.

Spine and leaf network deployments can have a minimum of one spine switch and two leaf switches. For small to medium clusters, the back-end network includes a pair redundant ToR switches. Only the Z9100 Ethernet switch is supported in the spine and leaf architecture.

Note: The Cisco Nexus operating system 9.3 is required on the ToR switch to support more than 144 Isilon nodes.

The Isilon backend architecture contains a spine and a leaf layer. The Isilon nodes connect to leaf switches in the leaf layer. The aggregation and core network layers are condensed into a single spine layer. The spine and leaf architecture requires the following conditions:

• Every leaf switch connects to every spine switch.
• Connections from the leaf switch to spine switch must be evenly distributed.
• There should be the same number of connections to each spine switch from each leaf switch.
• Cluster nodes connect to leaf switches which use spine switches to communicate.
• Switches of the same type (leaf or spine) do not connect to one another.
• Downlinks (links to Isilon nodes) support 1 x 40 Gbps or 4 x 10 Gbps using a breakout cable.

Scale planning

Scale planning prevents recabling of the backend network. Scale planing makes it easier to upgrade by installing the projected number of spine switches and scaling the cluster by adding leaf switches.

With the use of breakout cables, an A200 cluster can use three leaf switches and one spine switch for 252 nodes. The maximum nodes assume that each node is connected to a leaf switch using a 40 GB port.

The following table provides the switch requirements as the cluster scales:

* Although 16 leaf and 5 spine switches can connect 352 nodes, with the Isilon OneFS 8.2, 252 nodes are supported.

** Four spine switches are not supported. You must have even number of uplinks to each spine. A configuration with four spines and eight uplinks does not have enough bandwidth to support 22 nodes on each leaf.

Scaling guidelines

The uplink bandwidth must be equal to or more than the total bandwidth of all the nodes that are connected to the leaf. For example, each switch has nine downlink connections. Nine downlinks at 40 Gbps require 360 Gbps of bandwidth. That means four 100 Gbps uplink connections to the spine layer should be made from that leaf. The following maximums apply:

• Maximum 22 downlinks from each leaf switch (22 nodes on each switch).
• Maximum of 10 uplinks from each leaf switch to the spine.
• Maximum of 16 leaf and five spine switches.

SmartConnect with multiple SmartConnect Service IP

OneFS 8.2.0 uses SmartConnect with multiple SmartConnect Service IP (SSIP) per subnet.

The number of SSIP available per subnet depends on the SmartConnect license. SmartConnect Basic allows two SSIPs per subnet, while SmartConnect Advanced allows six SSIPs per subnet. SmartConnect Multi-SSIP is not an extra layer of load balancing for client connections. More SSIPs provide redundancy and reduce failure points in the client connection sequence.

SSIPs are only supported for use by a DNS server. Other implementations with SSIPs are not supported. The SSIP addresses and SmartConnect Zone names must not have reverse DNS entries, also known as pointer records.

The following figure shows the Isilon OneFS 8.2.0 support for multiple SmartConnect Service IP (SSIP) per subnet:

The following list provides the recommendations and considerations for the multiple SSIPs per subnet:

• The number of SSIPs available per subnet depends on the SmartConnect license. SmartConnect Basic allows two SSIPs per subnet, while SmartConnect Advanced allows six SSIPs per subnet.
• SmartConnect Multi-SSIP is not an extra layer of load balancing for client connections. More SSIPs provide redundancy and reduce failure points in the client connection sequence.
• SSIPs are supported only for use by a DNS server. Although SSIPs may be used in other configurations, the design intent was for a DNS server. Thus, other implementations with SSIPs are not supported.
• The Isilon SmartConnect Service IP addresses and SmartConnect Zone names must not have reverse DNS entries, also known as pointer (PTR) records.

Storage features

Isilon contains the OneFS operating system to provide encryption, file storage, and replication features.

Encryption

The Isilon OneFS operating system is available as a cluster of Isilon OneFS nodes that contain only self-encrypting drives (SEDs). The system requirements and management of data-at-rest on self-encrypting nodes are identical to the nodes without self-encrypting drives. Clusters of mixed node types are not supported.

Self-encrypting drives store data on an Isilon cluster designed for data-at-rest encryption (D@RE). D@RE on self-encrypted drives occurs when data stored on a device is encrypted to prevent unauthorized data access. All data written to the storage device is encrypted when it is stored, and all data read from the storage device is decrypted when it is read. The stored data is encrypted with a 256-bit data AES encryption key and decrypted in the same manner. OneFS controls data access by combining the drive authentication key with on-disk data-encryption keys. SED options are not included.

File storage

The Isilon OneFS operating system combines the three layers of traditional storage architectures (file system, volume manager, and data protection) into one unified software layer. This creates a single intelligent distributed file system that runs on an Isilon storage cluster.

VxBlock 1000 configures the two front-end interfaces of each node in an LACP port channel. The front-end interfaces are then used using SmartConnect to load balance share traffic across the nodes in the cluster depending on the configuration.

Replication

The Isilon OneFS operating system leverages the SyncIQ licensed feature for replication. SyncIQ is an application that enables you to manage and automate data replication between two Isilon clusters. SyncIQ delivers unique, highly parallel replication performance that scales with the dataset to provide a solid foundation for disaster recovery. SyncIQ can send and receive data on every node in the Isilon cluster so replication performance is increased as your data grows.

InsightIQ

InsightIQ provides performance monitoring and reporting tools to help you maximize the performance of an Dell EMC Isilon scale-out NAS platform. With InsightIQ, you can identify performance bottlenecks in workflows and optimize the amount of high-performance storage required in an environment. InsightIQ provides advanced analytics to optimize applications, correlate workflow and network events, and monitor storage requirements.

Software licensing

Isilon OneFS is available in a perpetual and subscription model, with various bundles.

The following table lists Isilon license features:

Isilon storage scale

The number of supported Isilon nodes depends on the 10 GbE or 40 GbE ports available in the system.

All node front-end ports (10 GbE or 40 GbE) are placed in LACP port channels. The front-end ports for each of the nodes are connected to a pair of redundant network switches.

For Isilon OneFS 8.1, the maximum Isilon configuration requires two pairs of ToR switches.

The following table indicates the number of nodes that are supported for Isilon OneFS 8.1:

The following table indicates the number of nodes that are supported for one Isilon OneFS 8.2.1:

Note: For Isilon OneFS 8.2.1, the maximum Isilon configuration requires a spine and leaf architecture backend 32-port Dell Z9100 switches.