Blog Automation

Adaptable, Pervasive, and Intelligent Solutions for Cloud Data Centers

Alan Sardella Published 31 Jan 2018

In previous posts, we’ve talked about cloud strategy in the enterprise, enterprise hybrid cloud connectivity options, the rise of IP fabrics, and guidelines for where place applications in hybrid clouds.

Here, we’ll take a look at the requirements and solutions for cloud data centers, and how Extreme’s data center portfolio addresses them.

An Adaptable Infrastructure

First, let’s start with a portfolio scale overview (Table 1) for the SLX series.  The following table provides this cross-portfolio comparison.

Table 1: SLX Portfolio Scale Comparisons

table, th, td { border: 1px solid black; }

 

SLX 9140

SLX 9240

SLX 9540

SLX 9850

Place in Network

ToR

ToR, Spine

ToR, WAN Edge,

Spine, Super Spine, WAN Edge

Interfaces (max)

100 GbE (6)

40 GbE (6)

25 GbE (48->72)

10 GbE (48)

1 GbE (48)

100 GbE (32)

40 GbE (32)

25 GbE (128)

10 GbE (128)

1 GbE (N/A)

100 GbE (6)

40 GbE (6)

25 GbE (24)*

10 GbE (72)

1 GbE (48)

100 GbE (288)

40 GbE (288)

25 GbE (1152)*

10 GbE (1920)

1 GbE (576)

Max I/O Capacity

3.6 Tbps

6.4 Tbps

1.6 Tbps

Up to 230 Tbps

Buffers

24 MB tunable

24 MB tunable

6 GB tunable

Up to 36 GB tunable

ASIC

Cavium Xpliant

Cavium Xpliant

Broadcom Qumran (Dune)

Broadcom Jericho (Dune)

Form Factor

Fixed

Fixed

Fixed

Modular Chassis

(4-slot, 8-slot)

1.5 RU interface modules

Very low distance, not suitable for most applications

Interface scale is a paramount requirement. As you can see from Table 1, SLX 9850 is unsurpassed here, with a modular chassis architecture and a 1.5RU interface module.

All SLX platforms have many future-proofing capabilities that include advanced thermal, cooling and power.  As Table 1 shows, there are platforms that are suitable for any location in the cloud data center; this includes spine and super spine locations, along with border leaf and WAN edge.

Of course, a chassis architecture may not be suitable for top of rack (TOR) or smaller locations, and a fixed platform is the way to go. Accordingly, the SLX 9540 fits the bill.

Both platforms support multiple architectures (Table 2). 

Table 2: Elements of Extreme’s Adaptable Infrastructure

Adaptable Infrastructure

BGP-EVPN

Higher scale application support with increased control plane performance and simplified operations

VLL and VPLS

Traffic engineering, OAM, QoS – support  carrier-grade topologies by leveraging high performance MPLS stack

High Density 100GbE

Lower cost/bit to handle rapid, unpredictable traffic growth (SLX 9850 and new SLX9540)

 

Either VPLS or BGP-EVPN, when supplied with appropriate density, agility and visibility, is geared to hyperscale to increase service innovation according to evolving market needs.  We’ll talk more about these architectures in a future posting.  

Pervasive Visibility

Visibility is of course more relevant in collocation and cloud exchange than in IX peering. We’ve recently blogged about how inbuilt visibility options (Table 3) are used in concert with automation to quickly debug a slow-performing application within your cloud hosting environment.

Table 3: Elements of Extreme’s Pervasive Visibility

Pervasive Visibility

Streaming  

Faster troubleshooting, remediation (find link congestion problems)

Insight Architecture

Isolate problems by digging into specific packets on specific servers. Example: Wireshark

Visibility Services

Drill into specific service or application traffic to identify abnormalities, even deeper into the packet. Example: VXLAN

We’ve also recently illustrated the use of these tools with examples, highlighting the relationships between streaming, visibility services and the Insight architecture for debugging a distributed application or a container-based application.

Intelligent Automation

Our automation solutions (Table 4) are tightly integrated with our platforms.

Table 4: Elements of Extreme’s Intelligent Automation

Intelligent Automation

Workflow Composer with Automation Suites

Automation, troubleshooting, remediation to increase operational efficiencies

Flow Optimizer

Balance flows and secure traffic against DDoS attacks

 

In terms of the automation suites, Network Essentials, for instance, automates configuration and validation of VLAN and ACL provisioning to scale with cloud growth and tenant capacity.  And Data Center Fabrics can be used to validate BGP settings and state, BGP neighbors, BGP EVPN peering, and switch reachability.

For more information please contact your Extreme Networks’ representative to learn how these integrated offerings provide:

  • Hyperscale architecture with dynamic scalability and proven performance in large network deployments
  • Faster innovation to drive market share and competitive advantage
  • CapEx and OpEx savings through industry-leading cost-efficiency, future-proofing and automation, and
  • Improved customer SLAs through differentiated visibility capabilities.

Related N/A Stories