Solution Overview

February 2017

Cisco HyperFlex
Systems

Cisco HyperFlex™ Systems

with Intel® Xeon® Processors
Cisco HyperFlex Systems
February 2017

Contents
The Challenge: Limitations of First-Generation Hyperconverged Systems........ 3

The Solution: Cisco HyperFlex Systems............................................................ 4

Complete End-to-End Solution.............................................................................. 4

Engineered on Cisco UCS Technology.................................................................. 5

Powered by Next-Generation Data Technology .................................................... 5

Agile, Efficient, and Adaptable Solution............................................................ 6

More Agile.............................................................................................................. 6

More Efficient......................................................................................................... 6

More Adaptable..................................................................................................... 7

Solution Architecture........................................................................................ 7

Complete Hyperconvergence with Cisco Networking............................................ 7

Integration with Cisco Application Centric Infrastructure........................................ 8

Cisco HyperFlex HX Data Platform.................................................................... 8

Cisco HyperFlex HX Data Platform Administration Plug-in..................................... 9

Cisco HyperFlex HTML 5 Management Interface................................................... 9

Cisco HyperFlex HX Data Platform Controller........................................................ 10

Data Distribution..................................................................................................... 10

Data Operations..................................................................................................... 11

Enterprise-Class Storage Features........................................................................ 12

Engineered on Cisco UCS Technology.............................................................. 13

Cisco HyperFlex HX-Series Nodes........................................................................ 13

Scaling with Cisco UCS Servers............................................................................ 13

Cluster Configuration Options................................................................................ 14

Encrypting Data at Rest.......................................................................................... 14

Connect to External Shared Storage...................................................................... 14

Powered by Intel Xeon Processors........................................................................ 15

Cisco UCS Management................................................................................... 15

Conclusion....................................................................................................... 15

Part of Our Broad Data Center Strategy................................................................. 16

For More Information........................................................................................ 16

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information. Page 2
Cisco HyperFlex Systems Solution Overview
February 2017

Highlights
The Challenge: Limitations of First-Generation
Hyperconverged Systems
Complete End-to-End Solution The first generation of hyperconverged systems arose from the need to more easily
• Cisco HyperFlex™ Systems, powered deploy a virtualization cluster without the complexity of enterprise shared storage
by Intel® Xeon® processors, deliver systems. These systems combined generic x86-architecture servers with software-
a new generation of hyperconverged
defined storage to create a simplified, distributed computing platform. But to achieve
solutions that are flexible, scalable,
and enterprise class. They combine simplicity and to get to market quickly, vendors made design trade-offs and took
the software-defined networking and many architectural shortcuts. As a result, these first attempts at hyperconvergence
software-defined computing of the fell short of full success:
Cisco Unified Computing System™
(Cisco UCS®) with Cisco HyperFlex
HX Data Platform software to provide • Networking is manual, not automated. First-generation hyperconverged
a single distributed, multitier, object- systems treat networking as an afterthought. They do not include an integrated
based data store with enterprise network fabric with consistent, low latency and high bandwidth between nodes,
storage features. nor do they attempt to integrate microsegmentation through software-defined
Agile networking. Network resources cannot be configured provisioned, or scaled
• Our end-to-end solution helps you automatically using profiles and templates, limiting the simplicity of deployment
work faster and more quickly achieve and system expansion.
your business’s digital transformation.
• Scaling is inflexible. Most hyperconverged products are based on white-box
Efficient
appliances that scale both computing and storage at fixed ratios. These resource
• Our solution keeps your data
optimized and your infrastructure ratios may or may not be appropriate for your applications and may cause you
aligned with application requirements. to overprovision components you don’t need. In the real world, every set of
Adaptable applications has a unique set of requirements, and first-generation products fail
• We help make you ready for an to let you independently scale computing, storage, and network resources.
expanding range of applications and • Performance requires trade-offs. The data platforms are implemented using
operating models.
off-the-shelf file systems that weren’t built specifically for hyperconvergence.
They lack some or all essential features, including local and remote replication,
snapshots, data encryption, and integration with enterprise shared storage and
enterprise backup strategies. Their deduplication and compression may require
performance trade-offs.
• New silos are created. First-generation infrastructure simplifies the deployment
and operation of cluster nodes, but they add new GUIs for storage management
while still requiring separate tools to manage server hardware. They don’t

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information.  Page 3
Cisco HyperFlex Systems
February 2017

integrate the network or provide support for software-defined networking

What’s New (SDN). They lack a unified control plane and open API to allow integration into
higher-level management, orchestration, backup, and disaster-recovery tools.
All-Flash Nodes As a result, these environments have spawned new islands of infrastructure
• Now you can choose even higher- and require administrators to learn a new set of management tools. To be most
performance and lower-latency all- effective, hyperconvergence must integrate with the data center you have today—
flash nodes for your Cisco HyperFlex
cluster. including balancing workloads across hybrid clouds.

Independent Scaling with Variety of

Cisco UCS Servers The Solution: Cisco HyperFlex Systems
• Use variety of Cisco UCS servers as
computing-only nodes to achieve the Cisco HyperFlex™ Systems, powered by Intel® Xeon® processors, deliver a new
right balance of processing power and generation of more flexible, more scalable, enterprise-class hyperconverged
storage capacity for your workloads.
solutions. We deliver a complete solution based on a next-generation data platform—
Securely Encrypted Storage one that smoothly integrates into the data center you have today. In contrast to first-
• A self-encrypting drive option generation products, our solution includes an integrated network fabric and powerful
encrypts data in all storage tiers of
data optimization capabilities that unlock the full potential of hyperconvergence for
your Cisco HyperFlex cluster.
a wider range of workloads and use cases. Our solution is faster to deploy, simpler
Native Replication to manage, easier to scale, and ready to provide a unified pool of resources to
• Replicate your virtual machines to power applications as your business needs dictate. You harness these resources
local or remote sites for backup or
disaster recovery. with simplified, centralized management that is integrated, not isolated. Cisco
HyperFlex Systems integrate into the data center you have today without creating an
Enhanced Management
island. You can deploy our solution wherever you need it, from central data center
• Monitor and manage your Cisco
HyperFlex cluster from any device environments to remote locations and edge-computing environments (Figure 1).
with an advanced role-based HTML 5
interface. Your Choice of
VMware vSphere Device-Independent HTML 5
Management Intefaces
Management Plug-in Management Interface
Integrated Networking for Hardware and Software

• Integrated networking is even faster

with low-latency, lossless 40-Gbps
connectivity with Cisco UCS 6300
App App App App ...... App App App App Designed to Support
Virtualized Environments
with Rapid Scalability
Series Fabric Interconnects. Cisco HyperFlex HX Data Platform

Data Protection Ecosystem

Enhancement
Network CPU/Memory HDD SSD

... Network CPU/Memory NVMe Memory SSD Network CPU/Memory

Hybrid and All-Flash
Storage Options
(1 Type per Cluster)
• Native data protection APIs integrate
Compute-Only Nodes
with leading enterprise backup Cisco HyperFlex HX-Series Nodes Using Cisco UCS Servers

systems, enabling a single backup

approach across your entire data
Integrated
center. 10- or 40-Gbps
Unified Fabric
Cisco UCS 6200 or 6300 Series
Fabric Interconnects
Network Fabric

Integrated Third-Party Storage Cisco HyperFlex Hybrid Node with SSD Cache Cisco HyperFlex All-Flash Nodes with SSD and Cisco UCS Blade or Rack Servers
and Showing Optional Self-Encrypting Drives Cptional NVMe Cache (Encryption Optional) Can Add Computing Capacity to the Cluster
• Connect third-party enterprise storage
directly to your cluster through Fibre
Channel and IP network connectivity. Figure 1 Only Cisco HyperFlex Systems Can Deliver This Combination of Essential Features in
a Single Solution

Complete End-to-End Solution

We offer the first hyperconverged platform that is designed as an end-to-end
software-defined infrastructure that eliminates the compromises found in first-
generation products. We designed Cisco HyperFlex Systems to support a broader
range of applications and workloads in the data center, remote locations, and edge-
computing environments. This new generation extends the ease of hyperconverged
system deployment, management, and support beyond your central data center.

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information. Page 4
Cisco HyperFlex Systems
February 2017

Cisco HyperFlex Systems combine software-defined computing in the form of Cisco

Unified Computing System™ (Cisco UCS®) servers with Intel Xeon processors,
software-defined storage with the powerful Cisco HyperFlex HX Data Platform
software, and software-defined networking with Cisco UCS fabric that integrates
smoothly with Cisco® Application Centric Infrastructure (Cisco ACI™). Together,
these elements comprise an adaptive infrastructure that lets you integrate your
existing infrastructure. The result is a cluster comes up and configures itself in
an hour or less and that scales resources independently to closely match your
application resource needs.

Engineered on Cisco UCS Technology

Cisco UCS provides a single point of connectivity and hardware management that
integrates Cisco HyperFlex nodes into a single unified cluster. The system is built to
be self-aware and self-integrating so that when the system’s fabric interconnects
notice a new component attached, that component is automatically incorporated
into the cluster.

This capability automates your infrastructure. Rather than requiring you to configure
each element in the system manually through a variety of element managers,
Cisco UCS was built so that every aspect of server personality, configuration,
and connectivity can be set through software. Cisco HyperFlex Systems can be
configured in minutes with no risk of configuration creep or noncompliant settings.
Cisco UCS service profiles are preconfigured so that the system’s installation wizard
can get you up and running in less than an hour.

When you make the move to automated infrastructure, you also reap the benefits of
the unified Cisco UCS management API. Cisco UCS Director can implement end-
to-end application lifecycle orchestration and automation. Cisco ONE™ Enterprise
Cloud Suite can turn your cluster into an on-premises cloud service with smooth
migration of workloads to and from public cloud facilities.

You can independently scale the computing power of your cluster by configuring
Cisco UCS servers as computing-only nodes. This feature lets you adjust the
balance of CPU and storage capacity, optimizing your total cost of ownership (TCO).
Incremental scalability allows you to start small and scale as your needs grow,

Powered by Next-Generation Data Technology

The HX Data Platform combines the cluster’s storage devices into a single
distributed, multitier, object-based data store. Performance scales linearly as
you scale the cluster because all components contribute processing and storage
capacity to the cluster. The data platform optimizes storage tiers for an excellent
balance between price and performance. For example, hybrid nodes use solid-state
disk (SSD) drives for caching and hard-disk drives (HDDs) for capacity; all-flash
nodes use fast SSD drives or Nonvolatile Memory (NVM) Express (NVMe) storage
for caching and SSDs for capacity.

A full set of enterprise-class data management features are built in: for example,
snapshots, thin provisioning, replication, data encryption, integration with third-
party backup tools, and instant and space-efficient cloning. Our networking secures
your data through its lifecycle, with security and compliance controls for protection
when you distribute, migrate, and replicate data across storage environments. New

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information. Page 5
Cisco HyperFlex Systems
February 2017

security features help you comply with industry and governmental standards. The
platform delivers high availability through parallel data distribution and replication,
accelerated by the low latency and high bandwidth of the Cisco unified fabric. Data
is continuously optimized with real-time, always-on deduplication, compression,
and optional encryption, helping reduce your storage costs without affecting
performance. Dynamic data placement in server memory, caching, and capacity
tiers increases application performance and reduces performance bottlenecks.

Agile, Efficient, and Adaptable Solution

Bringing benefits to your IT organization and to your business, Cisco HyperFlex
Systems overcome the limitations of first-generation products, delivering real
solutions that are agile, efficient, and adaptable. Our solution is well suited for
hosting environments such as virtual desktops, server virtualization deployments,
and test and development environments.

More Agile
Cisco HyperFlex Systems are more agile because they perform, scale, and
interoperate better:

• Deployment is fast and easy. Your cluster ships with the hypervisor and data
platform preinstalled and ready to launch through the installation wizard.
• Integrated networking brings high performance. Your cluster is interconnected
with low, consistent latency, and with 10- and 40-Gbps network bandwidth.
• Scaling is fast and simple. The system automatically discovers new hardware
when it is installed. Then adding it to the cluster takes only a few mouse clicks.
• Interoperability is straightforward. Management capabilities enable you to
install and operate your Cisco HyperFlex System in the data center you have
today, with high-level management tools that support operations across your
hyperconverged and your traditional infrastructure.

More Efficient
Our solution was designed from the beginning with a purpose-built, highly efficient
data platform that combines the cluster’s scale-out storage resources into a single,
distributed, multitier, object-based data store. Features you expect of enterprise
storage systems are built into Cisco HyperFlex Systems:

• Buy only the storage you need. Continuous inline data deduplication and
compression, fast, space-efficient clones, and thin provisioning contribute to
lowering the cost of your storage.
• Data protection is built in. You can use native HX Data Platform capabilities or
use the same data protection solutions you use in your data center because
Cisco HyperFlex Systems interoperate with leading backup tools.
• Your data is secure. You don’t need to take extra steps to secure your data at
rest when using self-encrypting drives. Cisco HyperFlex Systems help you save
time and ensure compliance.
• Save on storage administration. You don’t need to install a complex storage
network or worry about logical unit numbers (LUNs). If you already have
enterprise shared storage, you can connect it directly to your cluster to run virtual

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information. Page 6
Cisco HyperFlex Systems
February 2017

machines from it, migrate the storage to your cluster, or use the storage for
backup operations.

More Adaptable
Your business needs and your workloads are constantly changing. Your
infrastructure needs to quickly adapt to support your workloads and your business.

• Easy resource expansion and contraction. You can scale resources up and out
without having to adjust your software or networking capabilities.
• Nondisruptive scaling. Your infrastructure can easily scale out without the need
to take down your cluster to add a node.
• Pay as you grow. You can grow in small increments that won’t break your budget,
and you can independently scale your computing and capacity resources so they
adapt to fit your specific application needs.

Solution Architecture
Cisco HyperFlex Systems combine Cisco UCS networking and computing
technology, powerful Intel Xeon processors, and the HX Data Platform to deliver a
complete, preintegrated solution. After you run the configuration wizard, your cluster
is ready to work for you. You get a uniform pool of computing, networking, and
storage resources that is designed to power your applications.

Logically, a cluster of three or more Cisco HyperFlex HX-Series nodes provide

computing and storage resources to a hyperconvergence layer that supports
applications with a full-featured data platform. The data platform is implemented
using an HX Data Platform controller that runs on each node. This approach creates
a uniform pool of resources that supports applications across the cluster. When you
need to provision computing or storage capacity, that capacity is drawn from the
entire pool. No longer do you have to worry about creating LUNs and configuring
Fibre Channel switches. You simply serve virtual machine storage needs from the
pool of resources.

Physically, the system is delivered as a cluster of three or more HX-Series nodes.

These are integrated to form a single system by a pair of Cisco UCS 6200 or 6300
Series Fabric Interconnects with 10- or 40-Gbps connectivity (Figure 2). Up to an
equal number of Cisco UCS servers can act as computing-only nodes, participating
in the data platform but contributing only computing power to the cluster.

Complete Hyperconvergence with Cisco Networking

Networking in most hyperconverged environments is an afterthought. We give
you complete hyperconvergence with networking as an integral and essential
part of the system. Using Cisco UCS fabric interconnects, you have a single point
of connectivity and management that incorporates HX-Series nodes and Cisco
UCS servers: a feature that no other hyperconverged vendor can offer. After you
deploy a cluster, you can scale it to its maximum size without needing to redesign
the network. The solution is designed for easy, smooth scaling. Hyperconverged
systems need massive amounts of east-west traffic bandwidth and low latency, and
we deliver both with your choice of fabric interconnects supporting either 10- or
40-Gbps networking.

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information. Page 7
Cisco HyperFlex Systems
February 2017

Choice of Management Point

for Hardware and Software

Cisco UCS Management API Cisco HyperFlex Management

Compute-Only Nodes Cisco HyperFlex HX220c M4 Nodes Small-Footprint Cluster

Cisco UCS B200 M4

Cisco HyperFlex HX240c M4 Nodes High-Capacity Cluster

Cisco UCS 6200 or 6300

Series Fabric Interconnects Cisco UCS C220 M4

Cisco HyperFlex HX220c M4 All Flash Nodes High-Performance Cluster

Cisco UCS C240 M4

Cisco HyperFlex HX240c M4 All Flash Nodes High-Performance, High-Capacity Cluster

Figure 2 Cisco HyperFlex Systems Product Family

Networking is important in hyperconverged systems because the storage platform

performance depends on it. With Cisco UCS fabric interconnects, you get high-
bandwidth, low-latency unified fabric connectivity that carries all production IP
traffic, hyperconvergence-layer traffic, and management traffic over a single set of
cables. Every connection in the cluster is treated as its own microsegment, with the
same level of security as if it were supported with a separate physical link, making
the integrated network more secure than when commodity approaches are used.

The system is designed so that all traffic, even from different blade server chassis,
reaches any other node in the cluster with only a single network hop. No other
vendor can achieve this result because every other vendor builds switching into the
blade chassis—switching that adds latency. Our latency is deterministic, so you get
consistent network performance for the data platform, and you don’t have to worry
about network constraints on workload placement. This single-hop architecture
accelerates east-west traffic, enhancing cluster performance.

Integration with Cisco Application Centric Infrastructure

As your environment grows and begins to span your enterprise, you can use Cisco
ACI to implement a software-defined network. Cisco ACI provides automated,
policy-based network deployment that secures your applications within secure,
isolated containers. The network can attach directly to virtual machines and
physical servers with increased security, real-time monitoring and telemetry, and
automated performance optimization. You get consistency at scale because you
can use Cisco ACI to interconnect your entire data center network, integrating your
hyperconverged cluster into your existing infrastructure.

Cisco HyperFlex HX Data Platform

The HX Data Platform is a purpose-built, high-performance, scale-out file system
with a wide array of enterprise-class data management services. The data
platform’s innovations redefine distributed storage technology, giving you complete
hyperconvergence with enterprise storage features:

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information. Page 8
Cisco HyperFlex Systems
February 2017

• Enterprise-class data management features required for complete lifecycle

management and enhanced data protection in distributed storage environments
are provided. Features include deduplication, compression, thin provisioning, fast
space-efficient clones, snapshots, native replication, and integration with backup
solutions from leading vendors.
• Continuous data optimization with inline data deduplication and compression
increases resource utilization with more headroom for data scaling.
• Securely encrypted storage optionally encrypts both the caching and persistent
layers of the data platform. Integrated with enterprise key management software
or with passphrase-protected keys, encryption of data at rest helps you comply
with industry and government regulations. The platform itself is hardened to
Federal Information Processing Standard (FIPS) 140-1, and the encrypted drives
with key management comply with the FIPS 140-2 standard.
• Dynamic data placement optimizes performance and resilience by enabling
all cluster resources to participate in I/O responsiveness. Hybrid nodes use a
combination of SSD drives for caching and HDDs for the capacity layer; All-flash
nodes use SSD drives or NVME storage for the caching layer and SSDs for the
capacity layer.
• Clusterwide parallel data distribution implements clusterwide data replication
for high availability and performance, accelerated by the low latency and high
bandwidth of the Cisco UCS network fabric.
• Linear and incremental scaling provides faster, easier scalability compared to
enterprise shared-storage systems, in which controller resources become a
bottleneck and necessitate a complete upgrade of the storage system. Instead,
whenever you add an increment of storage in Cisco HyperFlex Systems, you also
increment the data platform processing capacity.
• API-based data platform architecture provides data virtualization flexibility to
support existing and new cloud-native data types. An API for data protection
allows enterprise backup solutions to create snapshot-based backups of virtual
machines.
• A simplified approach eliminates the need to configure LUNs or to require a
storage administrator to configure SANs. Storage and data services are managed
completely through hypervisor tools such as VMware vCenter.

Cisco HyperFlex HX Data Platform Administration Plug-in

The HX Data Platform can be administered through a VMware vSphere web client
plug-in. Through this centralized point of control for the cluster, administrators
can create volumes, monitor the data platform health, and manage resource use.
Administrators can also use this data to predict when the cluster will need to be
scaled.

Cisco HyperFlex HTML 5 Management Interface

Your cluster can also be administered through the HTML 5 management interface,
which allows you to accomplish important daily tasks using a fast and intuitive
interface that can be accessed from both desktop and mobile devices.

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information. Page 9
Cisco HyperFlex Systems
February 2017

Data Platform Cisco HyperFlex HX Data Platform Controller

VM VM VM Controller
An HX Data Platform controller resides on each node and implements the distributed
file system (Figure 3). The controller runs in user space within a virtual machine

iovisor
Data Platform VAAI and intercepts and handles all I/O from guest virtual machines. When nodes are
configured with self-encrypting drives, the controller negotiates with Cisco UCS
ESXi Hypervisor
Manager to receive the encryption keys that enable the drives to encrypt and
Network CPU/Memory HDD SSD
decrypt data that flows to and from the various storage layers.

In a VMware environment, the controller occupies a virtual machine with a dedicated

Cisco HX-Series Node
number of Intel Xeon processor cores and memory, allowing it to deliver consistent
performance and not affect the performance of the other virtual machines in the
Figure 3 Cisco HyperFlex Data cluster. The controller can access all storage through the VMware VM_DIRECT_
Platform Controller Plugs into the PATH feature. It uses the node’s memory and SSD drives or NVMe storage as
Hypervisor in Each Node part of a distributed caching layer, and it uses the node’s HDDs for distributed
storage. The controller manages the self-encrypting drives in concert with the
fabric interconnects that interface with enterprise key management software. The
controller integrates the data platform into VMware software through the use of two
preinstalled VMware ESXi vSphere Installation Bundles (VIBs):

• IO Visor: This VIB provides a network file system (NFS) mount point so that the
ESXi hypervisor can access the virtual disk drives that are attached to individual
virtual machines. From the hypervisor’s perspective, it is simply attached to a
network file system.
• VMware API for Array Integration (VAAI): This storage offload API allows
vSphere to request advanced file system operations such as snapshots and
cloning. The controller implements these operations through manipulation of
metadata rather than actual data copying, providing rapid response, and thus
rapid deployment of new application environments.

Data Distribution
The HX Data Platform controller handles all read and write requests for volumes that
the hypervisor accesses and thus intermediates all I/O from the virtual machines.
Recognizing the importance of data distribution, the HX Data Platform is designed to
exploit low network latencies and parallelism, in contrast to other approaches that
emphasize data affinity.

With data distribution, the data platform stripes data evenly across all nodes,
with the number of data replicas determined by the policies you set (Figure 4).
This approach helps prevent both network and storage hot spots and makes I/O
performance the same regardless of virtual machine location. This feature gives
you more flexibility in workload placement and contrasts with other architectures
in which a locality approach does not fully utilize all available networking and I/O
resources.

• Data write operations: For write operations, data is written to the local SSD or
NVMe cache, and the replicas are written to remote caches in parallel before the
write operation is acknowledged.
• Data read operations: For read operations, data that is local will usually be read
directly from the local SSD drive. If the data is not local, the data is retrieved from
an SSD drive on the remote node. This approach allows the platform to use all

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information. Page 10
Cisco HyperFlex Systems
February 2017

Data Platform Data Platform Data Platform

VM VM VM Controller
VM VM VM Controller
VM VM VM Controller

IO Visor

IO Visor

IO Visor
VAAI

VAAI

VAAI
ESXi Hypervisor ESXi Hypervisor ESXi Hypervisor

Cisco HyperFlex HX Data Platform

File
A B C D
Blocks

A1 B1 C1 D1 B2 A2 C2 D2 C3 A3 D3 B3
Network CPU and Memory HDD SSD Network CPU and Memory HDD SSD Network CPU and Memory HDD SSD

Figure 4 Data Blocks Are Replicated Across the Cluster

SSD drives for read operations, eliminating bottlenecks and delivering superior
performance. All-flash nodes do not use a read buffer, and read operations take
data directly from the SSD drives in the capacity layer.

In addition, when moving a virtual machine to a new location such as through

VMware Dynamic Resource Scheduling (DRS), the data platform does not require
data movement, and moving virtual machines has no performance impact or cost.

Data Operations
The data platform implements a log-structured file system that uses a caching layer
to accelerate read requests and write responses, and it implements a capacity layer
for persistent storage.

Incoming data is striped across the number of nodes that you define to meet your
data availability requirements. The log-structured file system assembles blocks
to be written to a configurable cache until the buffer is full or workload conditions
dictate that it be destaged to a spinning disk. When existing data is (logically)
overwritten, the log-structured approach simply appends a new block and updates
the metadata, requiring little use of the server’s Intel Xeon processors. When data
is destaged, the write operation consists of a single seek operation with a large
amount of data written. This approach improves performance significantly compared
to the traditional read-modify-write model, which is characterized by numerous seek
operations and small amounts of data written at a time.

When data is destaged to disk in each node, the data is deduplicated and
compressed. This process occurs after the write operation is acknowledged, so
there is no performance penalty for these operations. A small deduplication block
size helps increase the deduplication rate. Compression further reduces the data
footprint. Data is then moved to the capacity tier as cache segments become free
(Figure 5).

Read operations in hybrid nodes cache data on the SSD drives and in main
memory for high performance. In all-flash nodes they read directly from SSD
drives. Having the most frequently used data stored in the caching layer helps make
Cisco HyperFlex Systems with Intel Xeon processors perform well for virtualized
applications. When virtual machines modify data, the original block is likely read from
the cache, so there is often no need to read and then expand the data on a spinning

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information. Page 11
Cisco HyperFlex Systems
February 2017

VMware vSphere Plug-in for Single-Pane

Hardware and Hyperconvergence Management

Cisco HyperFlex Administration Plug-in

Cisco UCS Management Plug-in

Data Platform
Controller
VM VM VM .... VM VM VM
Data Platform
Controller

IO Visor

IO Visor

VAAI
VAAI
ESXi Hypervisor ESXi Hypervisor

VM_DIRECT_PATH
I/O Acceleration Replicate
Write to
Log on
SSD

C
B

B
C C

B
B C B C

A B B C C D Deduplicate A B B C C D

A B C D Compress A B C D

SSD-Based Caching Layer

Destage HDD-Based Capacity Layer

A B C D E F D A B C J K

T V X Z R S R S T V X Z

SSD HDD CPU and Memory Network

...
Physical Layer Network CPU and Memory HDD SSD

Node 1 Node n

Figure 5 Data Write Flow Through the Cisco HyperFlex HX Data Platform

disk. The data platform decouples the caching tier from the capacity tier and allows
independent scaling of I/O performance and storage capacity.

Enterprise-Class Storage Features

The data platform has all the features that you would expect of an enterprise shared
storage system, eliminating the need to configure and maintain complex Fibre
Channel storage networks and devices. The platform simplifies operations and helps
ensure data availability. Enterprise-class storage features include the following:

• Replication stripes and replicates data across the cluster so that data availability
is not affected if single or multiple components fail (depending on the replication
factor configured).
• Native replication transfers cluster data to local or remote clusters for backup or
disaster-recovery purposes.

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information. Page 12
Cisco HyperFlex Systems
February 2017

• Deduplication is always on, helping reduce storage requirements in virtualization

clusters in which multiple operating system instances in client virtual machines
result in large amounts of replicated data.
• Compression further reduces storage requirements, reducing costs, and the log-
structured file system is designed to store variable-sized blocks, reducing internal
fragmentation.
• Encryption protects your data at rest with self-encrypting drives combined with
enterprise key management software.
• Thin provisioning allows large data volumes to be created without requiring
storage to support them until the need arises, simplifying data volume growth and
making storage a “pay as you grow” proposition.
• Fast, space-efficient clones rapidly replicate storage volumes so that virtual
machines can be replicated simply through metadata operations, with actual data
copied only for write operations.
• Data protection API enables enterprise backup tools to access data volumes for
consistent, per-virtual-machine backup operations.

Engineered on Cisco UCS Technology

Cisco UCS, the foundation for Cisco HyperFlex Systems, is built with a single point
of management and connectivity for the entire system. The system is designed as a
single virtual blade server chassis that can span multiple chassis and racks of blade
and rack server–based nodes. Cisco thus is in the unique position of being able to
deliver a hyperconverged solution that can incorporate blade and rack systems in
its architecture, offering greater flexibility than any other solution. You can optimize
your system with the amount of computing and storage capacity that you need by
changing the ratio of Intel Xeon processor-intensive Cisco UCS blade and rack
servers to storage-intensive Cisco HyperFlex capacity nodes.

Cisco HyperFlex HX-Series Nodes

A cluster requires a minimum of three homogeneous nodes (with disk storage).
Data is replicated across at least two of these nodes, and a third node is required
for continuous operation in the event of a single-node failure. Each node is
equipped with at least one high-performance SSD drive for data caching and rapid
acknowledgment of write requests. Hybrid nodes use SSD drives for caching and
HDDs for the capacity layer. All-flash nodes use SSD drives or NVMe storage for
caching, and SSD drives for the capacity layer.

Scaling with Cisco UCS Servers

If you need more computing power than a cluster of HX-Series nodes provides, you
can add Cisco UCS servers to your cluster to increase the ratio of computing power
to storage. These servers become computing-only nodes that participate in the data
platform layer but with no local cache or storage. You need to have a minimum of
three HX-Series nodes in your cluster, and you can add Cisco UCS servers up to the
point where you have one Cisco UCS server for each HX-Series node in the cluster.
Supported servers include the Cisco UCS B200 M4 Blade Server and the Cisco
UCS C220 and C240 Rack Servers.

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information. Page 13
Cisco HyperFlex Systems
February 2017

Scale Up with Cisco HyperFlex Nodes Scale Out with Cisco HyperFlex Nodes Scale Computing Capacity
Add Storage or Cache Add More Nodes with Computing and Storage with Cisco UCS Blade and Rack Servers

VM VM VM
Data Platform
Controller
.... VM VM VM
Data Platform
Controller
.. VM VM VM VM

IO Visor

IO Visor

IO Visor
VAAI

VAAI
Cisco HyperFlex
ESXi Hypervisor ESXi Hypervisor ESXi Hypervisor
HX Data Platform
Network CPU and Memory HDD SSD Network CPU and Memory HDD SSD Network CPU and Memory

... ...

Figure 6 Scale Computing Capacity with Cisco UCS Blade and Rack Servers

Cluster Configuration Options

A good starting point is either a small-footprint cluster or a capacity-intensive
cluster. You can scale up specific nodes to increase memory, caching, and disk
capacity (Figure 6). You can scale out with Cisco UCS servers if you need additional
computing capacity. Or you can scale out with more of the same nodes if you need
additional storage capacity. Each cluster has an all-flash drive option, and each
Cisco HyperFlex HX220c M4
cluster can be equipped with self-encrypting drives. All nodes ship with the ESXi
and All Flash Nodes
hypervisor preinstalled to reduce deployment time.

• Small-footprint cluster with Cisco HyperFlex HX220c M4 Nodes: This starting

configuration contains a minimum of three nodes. Each node includes two Cisco
Flexible Flash (FlexFlash) Secure Digital (SD) cards for booting, a single 120- or
240-GB SSD data-logging drive, a single 400-GB SSD write log drive, and up to
six 1.2-terabyte (TB) SAS HDDs or up to six 3.8-TB or 960-GB SATA SSD drives,
for a contribution of up to 22.8 TB of storage capacity to the cluster.
• Capacity-intensive cluster with Cisco HyperFlex HX240c M4 Nodes: This
Cisco HyperFlex HX240c M4 and configuration contains a minimum of three nodes. Each node includes two
All Flash Nodes FlexFlash SD cards, a single 120- or 240-GB SSD data-logging drive, a single
1.6-TB SSD write log drive, and up to 23 3.8-TB SAS HDDs or 960-GB SATA
SSD drives, for a contribution of up to 87.4 TB of storage capacity to the cluster.

Encrypting Data at Rest

The self-encrypting drive option uses self-encrypting SSDs and HDDs and is
available for both hybrid and all-flash nodes. Cisco UCS Manager interfaces with
third-party key management systems to keep disk encryption keys safe.

Connect to External Shared Storage

Many organizations use external shared storage in existing environments. Your
Cisco HyperFlex Systems can connect to that shared storage directly through the
fabric interconnects. You can connect through 8-Gbps Fibre Channel or up to 40-
Gbps Small Computer System Interface over IP (iSCSI). With this capability you can:

• Boot and run virtual machines stored on the shared storage system
• Migrate virtual machines to your more scalable hyperconverged cluster
• Use shared storage for backing up your existing environment

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information. Page 14
Cisco HyperFlex Systems
February 2017

Fibre Channel storage can be connected directly to each hypervisor with separate
Fibre Channel interfaces that are configured through software on the Cisco UCS
virtual interface cards (VICs) in each node. These interfaces allow the cluster to
be configured to follow the hypervisor vendor’s recommended best practices for
traffic separation by creating separate network interfaces for each type of traffic,
configured through software.

Powered by Intel Xeon Processors

Each node offered in these three packages is powered by two Intel
Xeon processor E5-2600 v4 series CPUs. This Intel Xeon product
series is at the core of an agile, efficient data center. It delivers
significantly greater performance and power efficiency than the
previous generation of Intel Xeon processors. The series provides
more cores with more threads, more processor cache space, faster
main memory, and reduced power consumption by intelligently matching core,
memory, cache, and I/O power to system demand. Each HX-Series node includes a
range of processor choices, with up to 16 cores, clock rates of up to 2.6 GHz, and
128 to 768 GB of main memory.

Cisco UCS Management

Bringing you complete infrastructure automation, Cisco UCS management detects
any component plugged into the system, making it self-aware and self-integrating.
With the system itself able to adapt to changes in hardware configuration, you need
only a few mouse clicks to incorporate new servers into a cluster. With Cisco UCS
service profiles, every aspect of a node’s identity, configuration, and connectivity is set
through software, increasing efficiency and security and reducing deployment time.

Cisco HyperFlex Systems integrate easily into existing environments and operation
processes. Cisco UCS management’s API enables integration into higher-level
management tools from Cisco and more than a dozen independent software
vendors (ISVs). Tools include monitoring and analysis tools such as VMware vRealize
Operations Manager and vCenter, other deployment and configuration tools, and
service orchestration tools such as VMware vRealize Orchestrator. Cisco UCS
management is also integrated into Cisco UCS Performance Manager for monitoring
and analysis. When Cisco HyperFlex Systems are managed with Cisco UCS Director
or Cisco ONE Enterprise Cloud Suite, they can be managed as infrastructure as a
service (IaaS) or even as part of a hybrid cloud along with other Cisco and third-
party hardware.

Conclusion
With Cisco HyperFlex Systems and Intel Xeon processors, we deliver a complete,
next-generation hyperconverged solution that you can use anywhere: from your
enterprise data center to your remote locations. We unlock the full potential of
hyperconvergence so that you can use a common platform to support more of
your applications and use cases, including virtual desktops, server virtualization
deployments, and test and development environments. Cisco HyperFlex Systems
deliver the operational requirements for agility, scalability, and pay-as-you-grow
economics of the cloud—but with the benefits of on-premises infrastructure.

© 2016–2017 Cisco and/or its affiliates. All rights reserved. This document is Cisco Public information. Page 15
Cisco HyperFlex Systems
February 2017

Part of Our Broad Data Center Strategy

As part of our overall data center vision, integration with Cisco ACI and Enterprise
Cloud Suite will put you on the road to a hybrid cloud environment (Figure 7).
Cisco UCS Director enables you to use your Cisco HyperFlex Systems to deliver
IaaS and create a hybrid cloud. Your customers and clients can use the integrated
service catalog to order customized application infrastructure. And when you need
to augment capacity to handle periodic peaks, Enterprise Cloud Suite will help you
use a policy-based approach for engaging public cloud services. When you choose
Cisco HyperFlex Systems and Intel Xeon processors, you take your organization
beyond a point-product solution, putting your business on a path to a more agile,
adaptable, and efficient future.

Single Unified System | Single Management Model

Cisco UCS Cisco Integrated Cisco UCS Cisco UCS

Cisco UCS B-Series Blade Infrastructure Cisco HyperFlex C-Series Rack S-Series
Mini Servers Solutions Systems Servers Storage Servers

Remote- and Traditional Preconfigured Virtualized, Big Data Web-Scale

Branch-Office Virtualized Application Containerized, Environments Environments
Environments Environments Environments and Bare-Metal
Environments

Edge Data Center Web Scale

Figure 7 A Single Management Model Supports the Entire Cisco Product Portfolio

Cisco HyperFlex Services

Cisco Hyperflex services offers expertise that can help you rapidly migrate to Cisco
Hyperflex systems and gain faster time to value. Cisco Hyperflex services can help
you identify workloads, applications, and storage to migrate as well as verify I/O
profiles and availability requirements of your applications.

For More Information

For more information about Cisco HyperFlex Systems, visit http://www.cisco.com/
go/hyperflex.

For more information about Cisco HyperFlex services, visit https://www.cisco.

com/c/dam/en/us/solutions/collateral/data-center-virtualization/services-hyperflex-
aag.pdf.

Americas Headquarters Asia Pacific Headquarters Europe Headquarters

Cisco Systems, Inc. Cisco Systems (USA) Pte. Ltd. Cisco Systems International BV Amsterdam,
San Jose, CA Singapore The Netherlands
Cisco has more than 200 offices worldwide. Addresses, phone numbers, and fax numbers are listed on the Cisco Website at www.cisco.com/go/offices.

Cisco and the Cisco logo are trademarks or registered trademarks of Cisco and/or its affiliates in the U.S. and other countries. To view a list of Cisco trademarks, go to this
URL: www.cisco.com/go/trademarks. Third party trademarks mentioned are the property of their respective owners. The use of the word partner does not imply a partnership
relationship between Cisco and any other company. Intel, the Intel logo, Xeon, and Xeon Inside are trademarks or registered trademarks of Intel Corporation in the U.S. and/or other countries.
(1110R) LE-54801-01 01/17