HP 2424M User Manual

Download

HP ProCurve Switches & Hu b s

HP ProCurve Switch 4000M HP ProCurve Switch 8000M HP ProCurve Switch 2424M HP ProCurve Switch 1600M

January 15, 2000 Version 3.2b

reviewer’s guide

HP ProCurve Switch 4000M

HP ProCurve Switch 2424M

Less Work, More Network

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

Table of Contents

1. BACKGROUND .............................................................................................................5

1.1 HP’s Proactive Networking...................................................................................................................................5

1.2 What is a Switch?...................................................................................................................................................5

1.3 Hewlett-Packard Switch Products........................................................................................................................5

1.3.1 ProCurve Switches Covered in this Guide ..........................................................................................................5

1.3.2 Other Switches Available From HP ....................................................................................................................6

1.4 HP Switch Positioning ...........................................................................................................................................8

1.4.1 Positioning for the HP ProCurve Switch 4000M/8000M/2424M/1600M ..........................................................8

1.4.2 Switch 8000M / 4000M / 2424M / 1600M Comparison.....................................................................................9

2. EVALUATION FEATURES AND BENEFITS...............................................................10

2.1 Feature Set Summary..........................................................................................................................................10

2.2 Architecture..........................................................................................................................................................11

2.2.1 Store-and-Forward ............................................................................................................................................11

2.2.2 Backplane Design..............................................................................................................................................11

2.2.2.1 Backplanes: Chassis vs. Stackable............................................................................................................12

2.2.3 Packet Buffer Memory ......................................................................................................................................12

2.2.4 HP ProCurve Switch 100/1000Base-T Module ................................................................................................12

2.2.5 HP ProCurve Switch 2424M Gigabit Stacking Module....................................................................................13

2.3 IEEE 802.3x Flow Control ..................................................................................................................................13

2.4 Automatic Broadcast Control.............................................................................................................................13

2.5 Automatic Gateway Configuration ....................................................................................................................14

2.6 Switch Meshing (LAN Aggregation) ..................................................................................................................14

2.7 QoS Features ........................................................................................................................................................15

2.7.1 Incoming IEEE 802.1p Priority Tag Support....................................................................................................15

2.7.2 In-Switch 802.1p Tagging.................................................................................................................................15

2.7.3 IP-ToS Support..................................................................................................................................................16

2.7.4 Diff-Serv Support..............................................................................................................................................16

2.8 IGMP Support .....................................................................................................................................................16

2.9 IEEE 802.1Q VLAN Support .............................................................................................................................17

2.10 Port Trunking (Link Aggregation) ....................................................................................................................17

2.10.1 Implementation of Cisco's Fast EtherChannel

2.10.2 HP Trunking..................................................................................................................................................18

2.11 Filtering ................................................................................................................................................................18

2.11.1 Layer 2 and Layer 3 Filtering .......................................................................................................................18

2.11.2 Broadcast Storm Prevention..........................................................................................................................19

............................................................................................18

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

2.12 Port Security.........................................................................................................................................................19

2.13 Flexibility ..............................................................................................................................................................19

2.14 Reliability..............................................................................................................................................................20

2.14.1 Availability....................................................................................................................................................20

2.14.1.1 MTBF...................................................................................................................................................20

2.14.2 Lifetime Warranty (Best in the Industry)......................................................................................................20

2.14.3 Service and Support ......................................................................................................................................21

2.14.4 Year 2000 Compliance..................................................................................................................................21

2.15 Network Management .........................................................................................................................................21

2.15.1 MIB Support .................................................................................................................................................22

2.15.2 RMON Support.............................................................................................................................................22

2.15.3 HP Extended RMON ....................................................................................................................................22

2.15.4 Network Monitoring Port..............................................................................................................................23

2.15.5 Console Support............................................................................................................................................23

3. PERFORMANCE TESTING .........................................................................................24

3.1 Throughput/Packet Loss Rate ............................................................................................................................24

3.1.1 HP ProCurve Switch 4000M / 8000M ..............................................................................................................24

3.1.2 HP ProCurve Switch 2424M.............................................................................................................................24

3.1.3 HP ProCurve Switch 1600M.............................................................................................................................25

3.1.4 Gigabit Port Throughput ...................................................................................................................................25

3.2 Congestion Control..............................................................................................................................................25

3.2.1 Unidirectional Congestion Testing....................................................................................................................25

3.2.2 Bi-directional Congestion Testing (X-Stream)..................................................................................................26

3.3 Latency .................................................................................................................................................................26

3.4 Broadcast Latency ...............................................................................................................................................27

4. ADDITIONAL INFORMATION .....................................................................................28

4.1 ProCurve Networking Web Site.........................................................................................................................28

4.2 Reseller Plaza .......................................................................................................................................................28

4.3 White papers ........................................................................................................................................................28

5. PRICING.......................................................................................................................29

6. APPENDIX A: PERFORMANCE FIGURES.................................................................30

6.1 HP ProCurve Switch 4000M / 8000M................................................................................................................30

6.1.1 Throughput test .................................................................................................................................................30

6.1.1.1 100BT .......................................................................................................................................................30

6.1.1.2 10BT .........................................................................................................................................................30

6.1.2 Latency Test - unicast traffic.............................................................................................................................30

6.1.2.1 100Mbps ...................................................................................................................................................30

6.1.2.2 10Mbps .....................................................................................................................................................30

6.1.3 Latency Test - broadcast traffic.........................................................................................................................31

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

6.1.3.1 100Mbps ...................................................................................................................................................31

6.1.3.2 10Mbps .....................................................................................................................................................31

6.2 HP ProCurve Switch 2424M...............................................................................................................................32

6.2.1 Throughput test .................................................................................................................................................32

6.2.1.1 100BT .......................................................................................................................................................32

6.2.1.2 10BT .........................................................................................................................................................32

6.2.2 Latency Test - unicast traffic.............................................................................................................................32

6.2.2.1 100Mbps ...................................................................................................................................................32

6.2.2.2 10Mbps .....................................................................................................................................................32

6.2.3 Latency Test - broadcast traffic.........................................................................................................................33

6.2.3.1 100Mbps ...................................................................................................................................................33

6.2.3.2 10Mbps .....................................................................................................................................................33

6.3 HP ProCurve Switch 1600M...............................................................................................................................34

6.3.1 Throughput test .................................................................................................................................................34

6.3.1.1 100BT .......................................................................................................................................................34

6.3.1.2 10BT .........................................................................................................................................................34

6.3.2 Latency Test - unicast traffic.............................................................................................................................34

6.3.2.1 100Mbps ...................................................................................................................................................34

6.3.2.2 10Mbps .....................................................................................................................................................34

6.3.3 Latency Test - broadcast traffic.........................................................................................................................35

6.3.3.1 100Mbps ...................................................................................................................................................35

6.3.3.2 10Mbps .....................................................................................................................................................35

6.4 HP ProCurve Switch 100/1000Base-T Module .................................................................................................36

6.4.1.1 1000BT .....................................................................................................................................................36

6.4.1.2 100BT .......................................................................................................................................................36

6.5 HP ProCurve Switch Gigabit-SX Module .........................................................................................................36

6.5.1.1 Gigabit-SX................................................................................................................................................36

6.6 HP ProCurve Switch Gigabit-LX Module.........................................................................................................36

6.6.1.1 Gigabit-LX................................................................................................................................................36

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

1. Background

This Switch Reviewer’s Guide will help network testing engineers at computer trade publications, resellers and end-user sites evaluate the merits of the HP ProCurve Switches. Hewlett-Packard Company created this guide to help reviewers understand the benefits of the HP ProCurve Switches.

1.1 HP’s Proactive Networking

HP proactive networking is an extensible line of products working together to provide the control network administrators need to deliver the network uptime and performance that their organizations require. This guide describes one part of HP proactive networking: the HP ProCurve Switch 4000M, HP ProCurve Switch 8000M, the HP ProCurve Switch 2424M and HP ProCurve Switch 1600M products.

The HP ProCurve Switches 4000M/8000M/2424M and 1600M have been designed from the start to provide not only a low cost, high performance, scalable switched environment, but to do so with minimal configuration requirements. This, combined with the industry-leading lifetime

warranty and network management designed to easily help the network administrator proactively provide network optimization, leads to a switched environment that is easy to implement, maintain and grow.

1.2 What is a Switch?

In their simplest form, switches are multi-port bridges. With the technology that now exists, switches can operate at or near media-speed on all their ports simultaneously, allowing data flow to different segments on the switch to appear to occur simultaneously. It is this simultaneity that provides the main benefits of a switch, lowering or eliminating traffic bottlenecks that might be present in a shared environment.

1.3 Hewlett-Packard Switch Products

1.3.1 ProCurve Switches Covered in this Guide

This guide covers the following Hewlett-Packard switch products:

HP ProCurve Switch 4000M

The HP ProCurve Switch 4000M is a modular wiring closet switch that comes standard with forty fully-switched 10/100 Base-T UTP autosensing ports, with five open slots for additional modules. The HP ProCurve Switch can support up to eighty 10/100 autosensing 10/100Base-T ports, and is ideal for scaleable/expandable low-cost 10/100 desktop switching for smaller groups of users. The switch includes embedded Web-based management and HP TopTools for Hubs and Switches. Modules available for the HP ProCurve Switch 4000M are:

• HP Switch 10/100Base-T module provides (8) autosensing 10/100 Ethernet UTP ports

• HP Switch Gigabit-SX module provides (1) 1000Mbps multi-mode fiber optic port

• HP Switch Gigabit-LX module provides (1) 1000Mbps multi-mode or single-mode fiber optic

port. Fully adheres to the IEEE 802.3z specification.

• HP Switch 100/1000Base-T module provides (1) autosensing 100/1000Mbps Category 5 UTP

connection at up to 100m. Implements autosensing Auto MDI/MDI-X, allowing either straight-through or crossover cabling to be used for interconnections between switches or switch-to-server.

• HP Switch 100Base-FL module provides (4) 100Mbps multi-mode fiber optic ports

For as long as you own the product.

Mode conditioning cable (not included) may be needed with multi-mode fiber cable per IEEE 802.3z specs.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

• HP Switch 10Base-FL module provides (4) 10Mbps multi-mode fiber optic ports

HP ProCurve Switch 8000M

A modular 10 slot mini-chassis. Essentially the HP ProCurve Switch 4000M without any ports preinstalled.

HP ProCurve Switch 2424M

The HP ProCurve Switch 2424M is a stackable switch that provides twenty-four 10/100 Base-T autosensing ports and one open slot. The HP ProCurve Switch 2424M is ideal for low cost managed 10/100 desktop switching for users that desire a stackable solution. The Stacking Module provides a convenient high-speed stacking connection between switches and has two transceiver slots left over to provide a high-speed standardized Gigabit uplink connection to the backbone or an aggregator switch.

Modules available for the HP ProCurve Switch 2424M slot are:

• Any of the modules listed under the HP ProCurve Switch 4000M above.

• HP ProCurve Switch 2424M Gigabit Stacking Module provides two Gigabit ports that are

transceiver-based. Transceivers available are:

• HP ProCurve Gigabit-SX Transceiver

• HP ProCurve Gigabit-LX Transceiver

• HP ProCurve Gigabit-Stacking Kit (allows a low cost Gigabit stacking connection

between two HP ProCurve Switch 2424Ms). Includes two transceivers and a .5m cable.

Note that the Gigabit Stacking Module only works in the HP ProCurve Switch 2424M. It cannot be used in the HP ProCurve Switches 8000M / 4000M / 1600M.

HP ProCurve Switch 1600M

A fixed port switch with sixteen fixed 10/100Mbps autosensing ports and one expansion slot, primarily for Gigabit connectivity, but will accept any of the modules listed with the HP ProCurve Switch 4000M above. Ideal for server farm connectivity.

1.3.2 Other Switches Available From HP

Below is a complete list of switches available from HP.

HP ProCurve Routing Switch 9308M

A feature-rich, modular, 8 slot chassis-based routing switch delivering 100 million pps performance with up to 64 Gigabit Ethernet ports and up to 184 10/100 Mbps autosensing ports. Routes IP, IPX and AppleTalk. This product is ideal for large networks and provides high performance as a collapsed backbone.

See the HP ProCurve Routing Switch 9304M/9308M/6308M-SX/6208M-SX Reviewer’s Guide details.

HP ProCurve Routing Switch 9304M

A feature-rich, modular, 4 slot chassis-based routing switch delivering 50 million pps performance with up to 32 Gigabit Ethernet port and up to 88 10/100 autosensing per-port. This product is ideal for medium-to-large networks and provides high performance in collapsed backbones, data centers, and server farms.

See the HP ProCurve Routing Switch 9304M/9308M/6308M-SX/6208M-SX Reviewer’s Guide details.

for more

HP ProCurve Routing Switch 6308M-SX

A feature-rich, 8 port wire-speed Gigabit-SX routing switch delivering 12 million pps performance. This product is ideal as a backbone switch for small-to-medium networks, or as a remote building aggregrator switch connected to the larger site switch.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

See the HP ProCurve Routing Switch 9304M/9308M/6308M-SX/6208M-SX Reviewer’s Guide for more details.

HP ProCurve Routing Switch 6208M-SX

A feature-rich, 8 port wire-speed Gigabit-SX Layer 2/4 switch delivering 12 million pps performance. This product is ideal as a backbone switch for small-to-medium networks, or as a remote building aggregrator switch connected to the larger site switch where full Layer 3 routing is not wanted or needed.

See the HP ProCurve Routing Switch 9304M/9308M/6308M-SX/6208M-SX Reviewer’s Guide details.

HP ProCurve Switch 2224

Fixed configuration unmanaged desktop switch with (24) autosensing 10/100 Mbps ports, one of the UTP ports can be used as a 100Base-FX port with the addition of an optional transceiver.

HP ProCurve Switch 212M

Fixed configuration top-of-stack switch with (12) 10Mbps Ethernet ports and two 100Base-T ports (one fixed TX and one transceiver-based port)

HP ProCurve Switch 224M

Fixed configuration desktop switch with (24) 10Mbps Ethernet ports and two 100Base-T ports (one fixed TX and one transceiver-based port)

HP AdvanceStack Switch 2000

A flexible six slot high speed backplane switch for connectivity into legacy LAN environments. Modules currently available include:

• Two port 100Base-T module (transceiver-based),

• Two port 100VG module (transceiver-based),

• Four port 10Base-T module,

• Four port 10Base-FL module

• One port DAS FDDI module, and

for more

See the HP AdvanceStack Switch 2000/800T Reviewer’s Guide for more details.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

1.4 HP Switch Positioning

HP identifies three different classifications for switches: node/desktop, top-of-stack (both classified as wiring closet switches) and backbone switches. These areas are loosely defined by the number of address table entries a switch supports, the speed at which a switch operates, the flexibility/modularity provided by a switch, and the number of ports supported by a switch. There are also some specialty areas, such as being able to handle centralized server farms.

Desktop switches are intended for connecting each end node in a workgroup directly to its own switch port, usually at 10Mbps, with maybe one or two higher-speed ports for fast server connectivity. Top-ofstack switches have larger address tables and higher throughput speeds. They are designed to interconnect smaller workgroup switches or shared hubs. Backbone switches are intended to be placed centrally in a network. Consequently, they have high port counts with flexible port configurations, ways of dealing with broadcast and multicast traffic, and the ability to provide Layer 3 functionality.

HP ProCurve LAN Solution Family

Gigabit Routing

Switches

fixed, L3, managed

Gigabit Switches

fixed, L2, managed

10/100/Gigabit

Routing Switches

flexible chassis configuration

10/100Mbps Switches

with up to 2 Gigabit links

10/100Mbps Switches

flexible chassis configuration

10/100Mbps

Increasing Performance

Switch

10Mbps

Hub

10/100Mbps Hubs

managed or unmanaged

10Mbps Hubs

managed or unmanaged

10/100Mbps Switches

entry level, unmanaged

10Mbps Switches

with 2 100 Mbps uplinks

Switches covered in this guide.

Wiring Closet BackboneOffice

1.4.1 Positioning for the HP ProCurve Switch 4000M/8000M/2424M/1600M

The HP ProCurve Switches 4000M/8000M/2424M/1600M are very flexible wiring closet switches. The universal slot architecture delivers high port density and media flexibility in a variety of form factors. The different switches’ form factors are discussed in Section 1.3.1. These switches all have the same feature set. Features such as Switch Meshing and Port Trunking provide high availability and high bandwidth capabilities for mission-critical applications. QoS Setting and in-switch tagging allows them to be 802.1q edge devices to provide end-to-end packet priority setting without requiring the explicit involvement of end nodes. HP Proactive Networking makes these switches the easiest way to build and maintain a high-speed network wiring closet.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

1.4.2 Switch 8000M / 4000M / 2424M / 1600M Comparison

All four switches run the same software and have the same features. Differences between the switches are largely physical and shown in the following chart.

Feature Switch 8000M Switch 1600M Switch 4000M Switch 2424M Programmable HP ASICs

Automatic Broadcast Control Switch Meshing Port Trunking

Fast EtherChannel

HP Port Trunking

Protocol Filtering

802.3x Flow Control

802.1p Priority QoS Settings, In-switch tagging IGMP (Version 2) VLANs (802.1Q tagged and

untagged) Broadcast Throttling Port Security Web-server based configuration TopTools for Hubs & Switches Number of addresses 10,000 10,000 10,000 10,000 Installed ports (10/100Mbps) 0 16 40 24 Open slots 10 1 5 1 Backplane Packets Per Second

           

 



                    

30 30 30 30

               

4.67 million 3.87 million5 4.67 million 3.926 million

EtherChannel® is a registered trademark of Cisco Systems, Inc.

64 byte packets

This figure indicates full media speed, full duplex on all ports. Gigabit card installed in 1600M.

Stacking Module with 2 Gigabit ports used in the 2424M.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

2. Evaluation Features and Benefits

2.1 Feature Set Summary

The HP ProCurve Switch 8000M and the HP ProCurve Switch 1600M are store-and-forward switches that feature:

• An innovative backplane design that results in very low latencies of 3.5-12 microseconds

(100Mbps streams). Speeds are: 4000M/8000M: 3.8 gigabit/sec, 1600M: 3.5 Gbps, 2424M: 3.2 Gbps

• LAN Aggregation - Switch Meshing (load balancing protocol) and multiple port trunking

allowing load-balancing meshed, scaleable, and redundant bandwidth on connections between switches. Create a virtual backplane between switches.

• Link Aggregation - Support for Cisco’s Fast EtherChannel

Protocol (PAgP) and manually configured HP Trunks

• Up to thirty 802.1Q compliant VLANs for segmentation of local LANs

• QoS Settings / In-switch tagging – set priority of packets through the switch as well as setting

the priority tag bits in the 802.1Q tag based on IP address, IP-ToS or Diff-Serv bits, protocol, VLAN membership or incoming 802.1Q priority setting. This In-switch tagging (actual modification of the priority bits) allows network QoS settings

including the Port Aggregation

without

end node involvement.

• Automatic Broadcast Control (ABC) that intelligently controls broadcasts to enable larger

switched topologies without the use of VLANs and routers. On the other hand, ABC is fully compatible with VLAN and router environments.

• Automatic Gateway Configuration of DHCP packets to set the default gateway of a node to its

own IP address if the HP ProCurve Switch 4000M/8000M/2424M/1600M is installed in place of a pre-existing router.

• IGMP support for control of multicast packets

• Source port and layer 3 protocol filtering for control of traffic and implementation of security

policies between ports

• Port Security – ability to deny access to all except a configured MAC address, or first seen

address on a port-by-port basis.

• Lifetime

warranty (best in the industry)

• Free end-user telephone support available worldwide

• Extensive net management capabilities including:

 Web-based management for anytime, anywhere configuration access  Find/fix/inform capability which finds common network problems, fixes them if possible,

and informs the net manager of the situation

 Top Tools for Switches, which provides device and traffic management, traffic optimization,

and traffic control tools

 SNMP/MIB II/RMON support on all ports for monitoring and control  HP’s Extended RMON support on all ports allowing the monitoring of traffic flows in the

network

 Ability to configure a network monitoring port for use with external probes or analyzers

For as long as you own the product.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

• Spanning Tree Protocol (802.1D) support, including “fast” mode to allow support of IPX client

environments (see the application note “HP Switches - Controlling Network Traffic” at

http://www.hp.com/rnd/products/solutions/techlib/techlib.htm

• Year 2000 compliant

for more details).

2.2 Architecture

2.2.1 Store-and-Forward

There are two techniques by which switches move packets from the source to destination ports, 1) store-and-forward or, 2) cut-through. In store-and-forward, the entire packet is received and stored in memory by the switch before any decision is made as to the destination port for that packet. For cutthrough, the switch makes the destination decision and forwards the packet as soon as it has the destination and source address of the packet. Since the destination address is contained at the beginning of the packet, it is possible to have the packet being sent out the destination port before it is entirely received on the incoming port. No CRC checking is done on the packet with cut-through switching.

The HP ProCurve Switches 4000M/8000M/2424M/1600M use a variation of the store-and-forward method of packet forwarding. The benefits of the store-and-forward approach over cut-through are:

• Allows multi-speed switching: Store-and-forward is the only way a switch can deal with

differing speeds on its various ports.

• Filters out bad packets: Packets that are too short (as well as collision fragments), too long, or

have bad checksums are not forwarded, preventing the proliferation of bad packets.

• Congestion management: All switches deal with packet congestion by using store-and-forward

methods.

• Priority Queuing: QoS priority queues work through a store-and-forward mechanism.

The usual concern with the store-and-forward method compared to cut-through is higher packet latencies through the switch. The HP ProCurve Switches 4000M/8000M/2424M/1600M have a novel backplane design that keeps packet latencies among the lowest in the industry for store-and-forward switches. This is discussed in more detail in the Backplane Design section below.

2.2.2 Backplane Design

The HP ProCurve Switches 4000M/8000M/2424M/1600M has backplanes controlled by an HP-designed programmable ASIC. Backplane speeds for the various switches are: 4000M/8000M: 3.8 gigabit/sec, 1600M: 3.5 Gbps, 2424M:

3.2 Gbps. The switches support 10,000 MAC addresses. Unlike many other switches on the market, data is stored on the incoming port module and only travels across the backplane once on its way to the outgoing port module. At a measured

latency of only 3.5-12 µsec (LIFO, 100Mbps speed), the HP ProCurve

Switches 4000M/8000M/2424M/1600M have low latency for a store-and-forward design. Latency is the same for both inter and intra-module destinations.

3.8 Gbit switch bus

Slot

Module

ASIC

Controller

Slot

Module

Slot

Module

For broadcast and multicast packets, LIFO latency is still at 4-21 µsec broadcast and multicast latency port-to-port in these switches is ±1.2 µsec, which is very low. For

for all ports

, and the variance in

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

multimedia data performance, particularly if this data is delivered through multicast mechanisms, it is low variance in latency that is the most important latency measurement for a switch.

2.2.2.1 Backplanes: Chassis vs. Stackable

The HP ProCurve Switch 4000M is positioned as a 10/100Mbps desktop or wiring closet switch. Most other products in this category, including the HP ProCurve Switch 2424M, are stackable switches. A quick list of the differences between chassis and stackable solutions is:

Chassis

• Chassis generally have higher backplane speeds than stackable switch backplanes. The stacking

backplane further limits bandwidth between switches as it is almost always lower speed than the switch backplane. In addition, some vendor stacking solutions use a shared rather than switched approach for the stacking backplane. The HP ProCurve Switch 2424M uses a fully switched stacking backplane.

• All ports in the chassis have equal bandwidth access to each other across the backplane

• No stacking hardware or cable is required up to port count capability of each chassis, resulting

in less cabling for the number of ports

• Higher port density possible

Stackable

• Less expensive, particularly at lower port counts

• No loss of ports when interconnecting multiple switches

Overall, the chassis solution is usually a better solution from a throughput and type-of-port flexibility perspective. A stackable solution is good for users that don’t require the higher backplane bandwidth, are very price-sensitive, or just prefer it.

2.2.3 Packet Buffer Memory

Both flow control and packet buffer memory are used by the switch to handle momentary packet congestion. The amount of packet buffer memory used within the HP ProCurve Switch 8000M and HP ProCurve Switch 1600M varies depending on the port module:

Module Total Memory Per Port Memory HP ProCurve Switch 10/100Base-TX module 4 MB 512 KB

HP ProCurve Switch 100Base-FX module 2 MB 512 KB HP ProCurve Switch Gigabit-SX module 4 MB 4 MB HP ProCurve Switch Gigabit-LX module 4 MB 4 MB HP ProCurve Switch 2424M Gigabit 8 MB 4 MB

Stacking Module

HP ProCurve Switch 100/1000Base-T module 4 MB 4 MB HP ProCurve Switch 10Base-FL module 2 MB 512 KB

2.2.4 HP ProCurve Switch 100/1000Base-T Module

The low cost HP ProCurve Switch 100/1000Base-T module implements Gigabit data rates over standard Category 5 or better UTP copper wiring at up to 100m. The module autosenses 100/1000, full or half duplex and MDI or MDI-X connections.

The Auto MDI/MDI-X feature is new and makes cabling between two switches or switch to server very easy as either a straight-through or crossover cable can be used in any of these circumstances.

For customers installing new copper cabling, Category 5e wire is recommended. Existing wiring and all new installations should be checked to make sure the end-to-end connections (including patch panels and cross-connect blocks) meet the specs necessary for 1000Base-T. Cable testers suitable for copper

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

Gigabit connections are available. See the white paper on the Gigabit Ethernet Alliance web site for more wiring details.

www.gigabit-ethernet.org

2.2.5 HP ProCurve Switch 2424M Gigabit Stacking Module

The HP ProCurve Switch 2424M Gigabit Stacking Module contains two full-duplex Gigabit ports that are transceiver based. Both Gigabit-SX and Gigabit-LX transceivers are available for high speed fiberoptic connections to the backbone or aggregator switches.

The HP ProCurve Gigabit Stacking Kit is also available. The kit contains two specialized full-duplex Gigabit transceivers and a .5m proprietary cable. This provides a 2 Gbps connection (1 Gbps in each direction) between switches. The Stacking Kit, used in conjunction with two Stacking Modules installed in two HP ProCurve Switch 2424Ms provides an inexpensive stacking mechanism. Up to 7 HP ProCurve Switch 2424Ms can be daisy-chained together this way to provide up to 168 ports in the stack. In any stack there will always be two open transceiver slots for use with Gigabit transceivers to provide standardized uplink connectivity.

The HP ProCurve Switch 2424M Gigabit Stacking Module does not fit or work in the HP ProCurve Switch 8000M/4000M/1600M. Modules available for the Switch 8000M/4000M/1600M will, however work in the switch module slot on the HP ProCurve Switch 2424M.

Pricing for the stacking components is given in the pricing section.

2.3 IEEE 802.3x Flow Control

The HP ProCurve Switches 4000M/8000M/2424M/1600M adhere to the IEEE 802.3x Flow Control specification. This provides industry standard support for managing heavy port traffic and helps the switches avoid memory buffer overflows. Flow control is enabled on a port-by-port basis.

2.4 Automatic Broadcast Control

As local LAN environments have grown larger there has been a need to segment the environment to control and isolate the broadcast domains. Broadcast traffic in particular needs to be controlled

every

because with the packet. Traditionally routers have been used to provide this broadcast isolation.

The HP ProCurve Switches 4000M/8000M/2424M/1600M have built it into the switch one of the primary services routers perform to isolate broadcasts in the form of Automatic Broadcast Control. This provides separation of broadcast domains to each individual port on the switch. ABC, which has obvious value in a router-less environment also has value in an environment with routers because the broadcasts propagate no farther than the individual switch ports, keeping these broadcasts off other segments between the switch and router.

ABC suppresses broadcasts by participating in the IP & IPX broadcast protocols for path/route discovery:

• For IP traffic, most broadcasts are generated as ARP requests. The HP ProCurve Switch builds

an ARP cache and can proxy ARP reply back to end nodes directly, keeping the initial ARP broadcast confined to the segment it went out on.

node that receives a broadcast packet must interrupt its CPU to determine what to do

• For IPX traffic, the switch builds a RIP/SAP table, proxy answering end node NSQs directly,

keeping this type of broadcast traffic on the segment it was generated on. Since IPX uses broadcast traffic extensively at this level, ABC functionality can substantially reduce overall broadcast traffic in this environment.

• RIP (IP) and RIP/SAP (IPX) broadcasts are only forwarded to those segments where RIP and

RIP/SAP broadcasts have been heard previously.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

• To prevent broadcast storms, the switch provides broadcast throttling, a filter defined on each

port that allows only a user-specified level of broadcast traffic from entering the switch from that port (default is 40%).

Actual packet forwarding is handled at layer 2 where high speed and low latency can be economically provided.

More details on ABC can be found in the paper “HP Switches - Controlling Network Traffic” in the technical library on HP’s networking web site at

http://www.hp.com/rnd/products/solutions/techlib/techlib.htm

2.5 Automatic Gateway Configuration

If the HP ProCurve Switch 4000M/8000M/2424M/1600M will be replacing an existing router with multiple subnets, the default gateway in end nodes connected to the switch need to be set to their own IP address, or, if the stack supports it, 0.0.0.0. This will force each end node to ARP whenever a packet is sent to a destination not previously known. Once changing the default gateway is done, no other administrative action is needed in the future when moving end-nodes around the network.

In DHCP environments the HP ProCurve Switch 4000M/8000M/2424M/1600M can set the end node default gateway setting to the same IP address as the end node. The switches do this by changing the default gateway field of the DHCP packets as they travel through the switch.

Any end nodes that are on the same switch segment as the DHCP server will not be modified since those packets do not travel through the switch. It is recommended when using the Automatic Gateway Configuration feature that DHCP servers be located on switch segments without any end nodes.

If the DHCP server itself allows setting the default gateway to the end node address it is better to use the DHCP server this way rather than the Automatic Gateway Configuration in the switch. Microsoft Windows NT with a registry change. For details see:

2000, when released, will allow this directly. Microsoft Windows NT 4.0 can also do this

http://support.microsoft.com/support/kb/articles/q167/6/86.asp

2.6 Switch Meshing (LAN Aggregation)

The HP ProCurve Switch 4000M/8000M/2424M/1600M support Switch Meshing, a way to interconnect these switches in a meshed topology. Meshed switch-to-switch links can all be used simultaneously to their full advantage, with traffic being load balanced through redundant links based on dynamically determined latency in the different possible paths between switches. High availability, fault tolerant networks can be easily built with very low network administration required.

In traditional switched environments, meshed topologies are not allowed without the use of the Spanning Tree Protocol (IEEE 802.1D). Spanning Tree detects loops in the topology and logically blocks as many links as necessary to avoid traffic loops. If one of the active links fails, Spanning Tree enables another link to re-establish the path, if possible. Unfortunately, Spanning Tree requires links to be available that are not being used for data, letting available bandwidth go unused.

Although Spanning Tree Protocol is supported by the 4000M/8000M/2424M/1600M (allowing them to participate in pre-existing switch/router environments), Switch Meshing is superior in that it provides a way for the switches to use all the available links between switches. With Switch Meshing, the switch selects the best traffic path for each new destination end-node it learns based on dynamically determined latency in each of the possible paths to the node. Recalculation of path latency in each switch is done every 30 seconds and is based on link speeds, input and output buffer queue lengths, and knowledge of any dropped packets on particular ports.

Microsoft and Windows NT are U.S. registered trademarks of Microsoft Corporation.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

Redundancy is also provided by Switch Meshing. If one of the links fails between switches, traffic is redirected through another path, if available. The switchover time of typically less than 1 second is very fast. Very robust high availability solutions can be implemented with a switch mesh.

Switch Meshing allows multiple HP ProCurve Switches 4000M/8000M/2424M/1600M to form a virtual backplane between the switches, allowing reliable high port density environments to be made inexpensively.

Up to 12 switches can participate in a Switch Meshing domain. Multiple Switch Meshing domains can exist in a single LAN environment, but not within the same switch. Switch Meshing works well for local environments as large as 5,000 nodes.

Routing switches and routers use a similar technique through routing protocols such as RIP, OSPF or BGP. But Switch Meshing is an improvement over these routing protocols because:

• The path decision in HP’s Switch Meshing is determined by dynamically determined latency

through the switches. Routing protocols do not take latency into account, only path costs based on link speeds (OSPF) or simply the lowest number of router hops (RIP).

• Switch Meshing works for all layer 3 protocols, as well as non-routable protocols such as DEC

LAT or NETBios, because path specification is performed using layer 2 MAC addresses. Routing switches can only specify paths based on supported Layer 3 protocols, (usually IP, sometimes IPX and rarely AppleTalk), otherwise they must simply bridge the packet and use Spanning Tree.

• Configuration of Switch Meshing is trivial. Specifying which ports are part of the Switch

Meshing domain is all that is needed. The switch takes care of the rest. This is in sharp contrast to configuration of routing protocols which can be challenging.

• Convergence time (time to recover from a lost link) is fast - typically less than one second. This

is much faster than RIP and faster or on par with OSPF using triggered updates.

• Unlike a router, no packet modification is required as it travels through the switch, keeping the

latency through ProCurve switches lower than routing switches.

A white paper with more details on Switch Meshing can be found in the technical library on HP’s networking web site at

http://www.hp.com/rnd/products/solutions/techlib/techlib.htm

2.7 QoS Features

2.7.1 Incoming IEEE 802.1p Priority Tag Support

IEEE 802.1p packet tagging supports both designation of VLAN membership (see the VLAN section below) and packet priority (up to 8 levels). The architecture of the HP ProCurve Switches 4000M/8000M/2424M/1600M support two levels of priority through different port buffer queues, regular and high. If a tagged packet with the priority field value up to 3 comes into these switches, it will be put into the regular priority queue; at a priority value of 3 and above, the packet is put into the high priority queue. This allows the 4000M / 8000M / 2424M / 1600M to be responsive to time-sensitive applications that use the priority field in packet tagging for their data streams.

IGMP packets coming through the switch can be automatically assigned to the high priority queue through a single item in the switch configuration.

2.7.2 In-Switch 802.1p Tagging

Data networks are starting to carry types of data streams that have differing priorities in how they should be handled. The Switch 8000M / 1600M packet based on:

Starting with firmware revision C.07.23. Older revisions can be updated at no charge through the HP ProCurve web site.

can be configured to give a particular priority to a

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

• Source or destination IP address (up to 30 different addresses)

• IP-ToS or Diff-Serv field – Based on the IP Type of Service or Diff-Serv field

• Protocol type of the packet – Priority set based on whether packet is IP, IPX, ARP, DEC LAT,

AppleTalk, SNA or NetBeui

• VLAN membership

• Incoming 802.1p Priority setting

If a packet meets more than one of the conditions above, the priority setting of the packet is determined in the order given above, with the first in the list having the highest precedent.

These settings determine not only the priority of how the packet is handled in the HP ProCurve Switch 4000M/8000M/2424M/1600M itself, but the switch will also set the 802.1p priority tag for the packet outbound from the switch if it leaves via an 802.1p tagged port. This feature can be used to provide a network end-to-end priority for a packet. The HP ProCurve 9300 Routing Switches, for example, will internally maintain and prioritize the packet based on this 802.1p tag, even when the packet is routed through the 9300 Routing Switch.

End-to-end priority setting is thus possible even setting the priority in the packet. This is advantageous in that end node NIC cards do not have to be replaced or have their drivers updated in order to take advantage of priority settings. The end user also doesn’t have to wait for PC operating systems and applications to support priority settings. 4000M/8000M/2424M/1600M provides 802.1p edge or backbone services for end nodes into the rest of the network, a powerful capability as different data types converge in the data network.

In addition, this feature can be used to reset the incoming 802.1p priority setting, thus allowing the network manager an override capability from errant end nodes once they do support 802.1p priority settings.

without

the end node that created the packet explicitly

The Switch

2.7.3 IP-ToS Support

The IP-ToS (Type of Service) field has been in the IP header for a long time, but until recently has been largely unused. There are a number of applications now starting to use this field, such as IP-telephony, to provide priority handling of such packets within a network. Since many emerging switches use the

802.1p field to provide priority rather than the IP-ToS field, the HP ProCurve Switch 4000M/8000M/2424M/1600M’s ability to map this field to an 802.1p priority setting provides more flexibility in a network as to how this packet will be handled end-to-end.

2.7.4 Diff-Serv Support

An upcoming standard, Differential Services (Diff-Serv) will use the IP-ToS field to provide a standardized set of class-of-service for packets. Still in the standards definition phase, Diff-Serv will be used in the future to define a full set of delivery services for a packet. The HP ProCurve Switch 4000M/8000M/2424M/1600M can be configured to specify a particular 802.1p priority setting and set the 802.1p tag for each of the 32 different settings that the Diff-Serv field can take. This provides future proofing for a network using the HP ProCurve Switch 4000M/8000M/2424M/1600M.

2.8 IGMP Support

For multicast traffic, the switch eavesdrops on Internet Group Multicast Protocol (IGMP) traffic so that it knows which nodes are part of which multicast groups. If there is no multicast router available, the HP ProCurve Switch 4000M/8000M/2424M/1600M can act as an IGMP querier to learn which nodes have subscribed to which multicast streams. The switch can then direct a specific multicast stream to only those switch segments that have nodes that have joined the multicast group associated with that stream. Configuration of this feature is a single check box to turn it on. HP switches support version 2 of IGMP.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

The HP ProCurve Switch 4000M/8000M/2424M/1600M can also be configured through a single check box to automatically promote multicast streams that are part of an IGMP group to the high priority queue, moving these packets through the switch with as little latency as possible. This feature does not depend on 802.1Q packet tagging, so will work with existing IGMP environments.

More details on IGMP can be found in the paper “HP Switches - Controlling Network Traffic” in the technical library on HP’s networking web site at

http://www.hp.com/rnd/products/solutions/techlib/techlib.htm

2.9 IEEE 802.1Q VLAN Support

A Virtual LAN is a logical collection of ports or nodes that belong to a single broadcast/multicast domain. VLANs were originally devised as a solution to limit the size of any one broadcast domain to allow scaling of switched environments. With the advent of routing switch solutions, however, use of VLANs in end user environments is now largely done for network policy or security reasons. In any one VLAN, network traffic is completely independent of any other VLAN. A local router is required to interconnect multiple VLANs if traffic is to move between them. Automatic Broadcast Control and IGMP are compatible with, and work within, the context of each individual VLAN.

The HP ProCurve Switches 4000M/8000M/2424M/1600M support the IEEE 802.1Q standard for VLAN definition. Until the advent of the 802.1Q standard, identifying which network packets belonged to which VLANs was done differently by the different vendors, leading to interoperability concerns. The packet tagging in 802.1Q solves this problem by providing an identification field for VLANs. Now any device that supports 802.1Q can tell which VLAN a packet belongs to if that packet has been tagged. This allows packets from different VLANs to travel over the same link interconnecting switches. Switches from different vendors that adhere to 802.1Q can inter-operate at this level. In addition, since multiple VLANs can be identified within a single port, multiple VLANs can use the same server on a single port, as long as that server supports the 802.1Q tagging. As a final benefit, a router that supports

802.1Q can provide routing services between different VLANs through a single link to a switch (also known as a “one-armed router”).

The HP ProCurve Switch 8000M and HP ProCurve Switch 1600M support up to thirty (30) switch. VLANs are defined by port. A port-based VLAN is one where all packets that are untagged coming into a particular port are identified with the designated VLAN for untagged packets associated with that port, providing backwards compatibility to environments that do not support 802.1Q tags. Each port supports at most one untagged VLAN with the remainder for that port being tagged.

VLANs per

2.10 Port Trunking (Link Aggregation)

Link Aggregation is the industry term for the ability to combine multiple coterminous links (links that begin at the same point and end at the same point) as one logical link. There are two types supported by the HP ProCurve Switch 4000M/8000M/2424M/1600M, Cisco's Fast EtherChannel Trunking. Cisco’s Fast EtherChannel defines an automation protocol called PAgP while HP trunking is manually configured.

Link aggregation allows two HP ProCurve Switch 4000M/8000M/2424M/1600M switches to be interconnected by 2-to-4 of the same type of links, with all links acting as one higher-speed link. Since the number of links in a trunk is configurable, the bandwidth is scaleable to the needs of a particular network. For example, (4) 100Mbps links can be trunked to provide the equivalent of a 400 Mbps (800 Mbps full-duplex) link between two switches or (4) Gigabit links can be trunked for the equivalent of a 4 Gigabit (8 Gigabit full-duplex) link. Fiber-optic links can be trunked to interconnect switches across large campuses.

Switch firmware revision C.06.01 or later.

EtherChannel® is a registered trademark of Cisco Systems, Inc.

(FEC) and HP

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

Some servers also support link aggregation, allowing multiple links to be interconnected between the switch and server.

Up to 4 links of any one type can be used in either the FEC or HP trunk and a total of 10 trunks (FEC, HP Trunk and Switch Mesh) can be configured at one time in the HP ProCurve Switch 4000M/8000M/2424M/1600M.

2.10.1 Implementation of Cisco's Fast EtherChannel

The HP ProCurve Switches 4000M/8000M/2424M/1600M

Fast EtherChannel ports

trunked together act as one

implement Cisco’s Fast EtherChannel® (FEC) technology.

Switch 1

Switch 2

Switch 3

FEC provides support for the Port Aggregation Protocol (PAgP), a Cisco proprietary protocol that aids in configuration of the FEC links. This allows the HP ProCurve Switches 4000M/8000M/2424M/1600M switches to be compatible with other PAgP compliant switches, routers and servers.

Traffic running across an FEC trunk is load-balanced across the different physical links, providing the most complete use of the available bandwidth.

In addition, if one of the links in the trunk goes down, data is carried across the remaining links providing redundancy to the overall link.

Look at the FEC white paper on Cisco's web site for more details on server support.

2.10.2 HP Trunking

The HP ProCurve Switches 4000M/8000M/2424M/1600M also implement HP Trunks. HP Trunks are available in a number of other HP switches making the HP ProCurve Switch 4000M/8000M/2424M/1600M compatible with the link aggregation solution of these other switches.

HP Trunks will also work with other trunk technologies that do not use a protocol across the trunks, including FEC trunks that have PAgP disabled. In fact, if a FEC defined trunk in a HP ProCurve Switch 4000M/8000M/2424M/1600M is connected to a switch or server that does not support PAgP on their trunks, it will automatically try to connect using the HP Trunk. As a result, a trunk on the 4000M/8000M/2424M/1600M can be set up initially as FEC and have the greatest chance of interoperating with another switch or server.

2.11 Filtering

2.11.1 Layer 2 and Layer 3 Filtering

The HP ProCurve Switch 4000M/8000M/2424M/1600M support various filtering at Layer 2 and Layer 3. Traffic having the following frame types can be either forwarded or dropped on a per-port basis:

IP IPX ARP AppleTalk DEC LAT NetBEUI SNA

In addition, filters for specific multicast addresses can be defined to forward or drop multicast traffic on a per-port basis. Port filters can also be defined such that traffic from a specific port can be forwarded or dropped on a per-port basis.

Judicious use of the filters can streamline traffic flows or create security walls. For example, many networks have workgroups using a particular protocol that do not need to communicate outside their group. If a graphics workgroup is using AppleTalk, but the traffic is not desired elsewhere on the network, an AppleTalk filter in the HP ProCurve Switch 4000M/8000M/2424M/1600M will prevent the AppleTalk traffic from consuming bandwidth outside the workgroup. Alternatively, if a file server is

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

connected to a specific port, file server traffic can be excluded from other ports of the net manager’s choice, preventing users on designated ports access to the file server.

2.11.2 Broadcast Storm Prevention

The HP ProCurve Switches 4000M/8000M/2424M/1600M have a broadcast throttling filter to control high levels of broadcasts leaving the switch. Broadcast throttling has been covered in a previous section dealing with Automatic Broadcast Control.

2.12 Port Security

Port security can be set in the HP ProCurve Switch 4000M/8000M/2424M/1600M so that:

• Unicast packets are sent out the port only if they are for authorized end nodes on that port. All

other unicast packets are dropped. All multicast and broadcast packets are forwarded. (prevents eavesdropping of general network traffic at an open port on the switch)

Authorized nodes can be defined in two different ways:

• Continuous – any node connected to the port is authorized. Essentially any node address in the

bridge address table for this port becomes an authorized node for this port. This setting prevents generally flooded unicast packets from being sent out this port, but allows any actual nodes downstream from this port to receive unicast traffic specifically addressed to those nodes. Since these authorized port entries are dynamic, they age out at the rate set for the bridge address table.

• Static – The number of MAC addresses allowed for that port (up to 8) is specified. Actual MAC

addresses can then be entered. If the number of actual MAC addresses entered is less than the number of total addresses allowed, then the switch will fill the address list with the first addresses it sees that are not specifically configured. This allows the first ports seen to become authorized without their addresses being explicitly configured.

If a security violation does occur, the switch can be set to send an SNMP trap.

2.13 Flexibility

The HP ProCurve Switches 4000M/8000M/2424M/1600M have been designed with flexibility and high port density in mind. Any module type can be plugged into any of the module slots. The modules are hot swappable. Available module types are:

• Single port Gigabit-SX module. Works with 62.5/125 multi-mode fiber cable at up to 220M, or

50/125 multi-mode fiber cable at up to 500m. (SC connectors)

• Single port Gigabit-LX module. Works with single-mode fiber cable up to 5km, or with either

62.5/125 or 50/125 multi-mode fiber cable up to 550m (mode-conditioning cable may be needed for multi-mode use per IEEE 802.3z). (SC connectors)

• Single port 100/1000Base-T module. Works with Category 5 or better UTP wiring at up to 100m.

• Eight port UTP autosensing 10/100Base-TX module.

• Four port 100Base-FX module (SC connectors)

• Four port 10Base-FL module (ST connectors)

• HP ProCurve Switch 2424M Gigabit Stacking Module provides two Gigabit ports that are

transceiver-based. Transceivers available are:

• HP ProCurve Gigabit-SX Transceiver

Starting with firmware revision C.07.23. Older revisions can be updated at no charge through the HP ProCurve web site.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

• HP ProCurve Gigabit-LX Transceiver

• HP ProCurve Gigabit-Stacking Kit (allows a low cost Gigabit stacking connection between

two HP ProCurve Switch 2424Ms). Includes two transceivers and a .5m cable.

Note: The Gigabit Stacking Module only works in the HP ProCurve Switch 2424M. It cannot be used in the HP ProCurve Switch 8000M / 4000M / 1600M.

A fully loaded HP ProCurve Switch 4000M or 8000M can have eighty 10/100Mbps ports available in a box only 17.8cm (7") in height.

The HP ProCurve Switch 2424M provides twenty-four 10/100Mbps fixed UTP ports and has one module slot that accepts any of the modules listed above, including the Gigabit Stacking Module. It is 6.6cm (2.6") in height.

The HP ProCurve Switch 1600M provides sixteen 10/100Mbps fixed UTP ports and has one module slot that accepts any of the modules listed above. It is 6.6cm (2.6") in height.

2.14 Reliability

Overall reliability of a product is determined not only by how much time between product failures, but also how fast a failed unit can be repaired or replaced. HP, through the design of the HP ProCurve Switch 8000M and 1600M, and the lifetime (for as long as you own the product) warranty, has raised overall reliability to an industry-leading level. Details are provided in the following section.

2.14.1 Availability

Availability is the measure of the ability for the switch to remain running over a period of time with minimal impact to the network environment.

For the HP ProCurve Switch 4000M/8000M/2424M/1600M hot-swapping of the port modules can be done while the switch is still running without affecting the other port modules. This allows a defective port module to be replaced without affecting the rest of the network. When the replacement port module is swapped-in the HP ProCurve Switch 4000M/8000M/2424M/1600M runs the module through a self-test sequence that verifies the module is good.

An optional second power supply (identical to the primary supply) can be installed in either the HP ProCurve Switch 4000M or 8000M with both power supplies load-sharing, allowing both supplies to run cooler and extending both of their Mean Time Between Failure (MTBF) values. If one of the supplies does fail, the other one takes over without switch interruption. Either power supply can be hot-swapped during switch operation when both supplies are present. Each supply has its own power cord.

The HP ProCurve Switch 4000M/8000M/2424M/1600M supports Switch Meshing, Cisco Fast EtherChannel and HP port trunking which, in addition to increased bandwidth, provides for redundancy for switch-to-switch connections.

2.14.1.1 MTBF

The estimated Mean Time Before Failure (MTBF) of the HP ProCurve Switch 4000M or 8000M fully loaded with ten J4111A 10/100 Base-T modules (80 ports) is over 28,000 hours. It is the same for 72 10/100 ports and one gigabit port.

The estimated MTBF for the HP ProCurve Switch 2424M is 63,400 hours.

The estimated MTBF for the HP ProCurve Switch 1600M with one gigabit port is 53,300 hours.

2.14.2 Lifetime Warranty (Best in the Industry)

Warranties, and the ease of obtaining warranty service for the end user, is a product benefit that is easily overlooked in a technical evaluation, but ranks high as a concern of end users as they get ready to actually make a purchase decision. In order to maximize net uptime, all HP switches have a lifetime warranty for as long as you own the product. If any part of the switch fails, including the power supply

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

or fans, it will be replaced. In most parts of the world, the replacement unit is sent for next business day delivery in advance of the failing unit being returned to HP. Advance replacement gets the unit to the end user as fast as possible and minimizes down time by allowing the impaired unit to continue to be used if possible until the replacement unit arrives. This also allows for easy scheduling for when the actual unit swap occurs on the network.

The HP networking warranty is industry-leading with most other vendors offering only one year or less along with longer turnaround times. The HP warranty significantly lowers the long term cost of ownership for the end user.

The lifetime warranty duration on HP's networking products is for as long as you own the product, in contrast to the product's parts lifetime or technology lifetime, etc. As required by law in some countries, HP has provided this definition of lifetime which will be superseded by local law, if required.

2.14.3 Service and Support

HP provides free pre-sales and post-sales telephone support during normal business hours to end users and HP resellers through the HP Customer Care Centers located world-wide.

In addition to free support services such as the lifetime warranty and telephone support, HP offers various fee-based support services to meet more specialized needs. For example, the support product HP SupportPack for Onsite Service on HP Network Connectivity Products will, for a nominal fee (see the Pricing section), upgrade the warranty servicing on one Switch 4000M/8000M/2424M or 1600M to an on-site 4 hour response installed in the switch.

(8a-5p, M-F) for a period of three years. This fee also covers any modules

Support services are also available to upgrade telephone support to include non-business hours.

End users have the flexibility to either work with their local reseller or with HP to start a warranty claim or to obtain additional fee-based services.

More information can be found at http://www.hp.com/rnd/support/support_pack.htm

2.14.4 Year 2000 Compliance

The HP ProCurve Switches 4000M/8000M/2424M/1600M are Year 2000 compliant14. Refer to

http://www.hp.com/year2000/products/compliance.html

for HP’s Year 2000 compliance definitions.

2.15 Network Management

Network management is an important part of a switched solution. There are three levels of net management available for the HP ProCurve Switches 4000M/8000M/2424M/1600M:

• Web-based management - Management of individual switches can be done anytime, anywhere

through the web server available in each switch, accessible via a standard web browser. This method can also be used as the entire net management solution for small shops that do not want to run a net management application on a separate PC.

• HP TopTools for Hubs & Switches - Management of a network of HP hubs and switches can be

done through the included HP TopTools for Hubs & Switches application, part of the HP TopTools suite of management products. Provides a network map, device configuration, and traffic monitoring and optimization capabilities in an web-based format.

Available in most parts of the world.

HP has made every effort to ensure the accuracy of our product testing. However, because each customer's environment is

different from HP's laboratory test environment, it is the customer's responsibility to validate the Year 2000 readiness of these products in their own environment. Therefore, information about the Year 2000 status of HP products is provided "as is" without warranties of any kind and is subject to change without notice. HP makes no representation or warranty respecting the accuracy or reliability of information about non-HP products. Such information, if any, was provided by the manufacturers of those products and customers are urged to contact the manufacturer directly to verify Year 2000 readiness. The information provided here constitutes a Year 2000 Readiness Disclosure for purposes of the Year 2000 Information and Readiness Disclosure Act.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

• HP OpenView platforms - If management of a generic IP network is needed (i.e. management of

HP and other vendor’s devices):

NT platform - bridge software to HP OpenView/NT is available so that TopTools can run under HP OpenView/NT. For more details see the TopTools web site at

http://www.hp.com/toptools

UX platform - Management of the HP ProCurve Switch 4000M/8000M/2424M/1600M under HP OpenView/UX is available via the separately purchased J3250M HP Hub & Switch Management For HP OpenView-UX product.

TopTools will also run under Tivoli Enterprise and Tivoli NetView, as well as Unicenter TNG using the proper bridges to these environments. See the TopTools web site at more details.

For more details on network management of HP hubs and switches, see the separate Managing HP Hubs and Switches Reviewer’s Guide.

Net management features unique to the HP ProCurve Switch 4000M/8000M/2424M/1600M are described below.

http://www.hp.com/toptools for

2.15.1 MIB Support

The HP ProCurve Switch 4000M/8000M/2424M/1600M supports the following standard MIBs:

• MIB-II (RFC 1213)

• Bridge MIB (RFC 1493)

• Ethernet MAU MIB (RFC 1515)

• Interfaces Evolution MIB (RFC 1573)

• Ethernet Interface MIB (RFC 1650)

• RMON MIB (RFC 1757)

Groups: (1) Ethernet statistics, (2) Ethernet history, (3) Alarm, (9) Event,

In addition, a number of enterprise-specific MIBs are also supported for such things as VLANs, network management, TFTP parameters, and values needed for software download.

2.15.2 RMON Support

For those customers that use RMON applications, the HP ProCurve Switch 4000M/8000M/2424M/1600M support RMON groups 1 (Ethernet statistics), 2 (Ethernet history), 3 (Alarm), and 9 (Event). These four groups are available for all ports.

The Ethernet statistics group provides counters for packet counts, broadcast/multicast packets, packet length counts, missed packets and erred packets. Event and Alarm groups allow threshold setting and alarm generation based on the counters in the Ethernet group. History accumulates these counters over a period of time (30 samples deep).

2.15.3 HP Extended RMON

HP Extended RMON is the embedded sampling technology that allows HP TopTools to provide network traffic information in an effective and cost-efficient way. HP Extended RMON looks at traffic on all ports of a HP switch and/or hub simultaneously without burdening CPU performance. HP Extended RMON is composed of two parts: the sampling agent residing in most HP hubs and switches, and the data collector in HP TopTools for Hubs & Switches. HP Extended RMON technology has been included in many HP hubs and switches since 1992.

Because HP Extended RMON is a sampling technology that requires very little in terms of system resources, it is easily scaleable to monitor switched and shared high-speed technologies, such as Gigabit Ethernet, 100Base-T and FDDI.

HP Extended RMON is statistically accurate to a 95-percent confidence level. The sampling rate is adjusted once per hour to maintain this confidence level. This accuracy is more than adequate for

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

traffic flow analysis for network planning and for top-down network troubleshooting. Problems can quickly be identified so that segment-specific troubleshooting can be performed with a network analyzer.

2.15.4 Network Monitoring Port

If more RMON groups (such as packet capture) are desired, a RMON probe can be attached to one of the HP ProCurve Switch 4000M/8000M/2424M/1600M ports and a Network Monitoring Port can be configured into the switch. A Network Monitoring Port allows the end user to copy all traffic from a number of ports to a single destination port. (The source ports can be designated by specifically naming the ports, or on a VLAN basis.) This allows the probe to see all traffic on the selected ports to provide the probe with the proper global perspective.

LAN analyzers can also use this feature when doing specific monitoring or troubleshooting of network segments.

2.15.5 Console Support

Out-of-band management of HP switches can be done through the RS-232 console port either via a directly connected terminal emulator or over a modem connection. The console interface provides full screen access to all configuration parameters. Context sensitive help is available for specific configuration parameters. Full page help screens can be accessed to explain concepts or provide overviews of an entire configuration screen.

The 4000M/8000M/2424M/1600M also provide an extensive event log to rapidly establish detailed switch status and allow rapid troubleshooting of problems. Events from this log can be sent to a SNMP management station as traps. The entire event log can also be sent to a PC or workstation through TFTP.

The console interface is also available in-band through the telnet service.

For ease of use, the HP ProCurve Switch 4000M/8000M/2424M/1600M can search for particular values through the console interface. For example, a search for a particular MAC address anywhere in the configuration can be done saving the operator’s time when changing a configuration or reviewing the address forwarding table.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

3. Performance Testing

Switches are normally performance tested under a variety of conditions for three main parameters: throughput/packet loss rate, congestion control and latency. Definitions for throughput, packet loss rate and latency are specified in RFC 1242. See clear definition for congestion control. There are numerous tests that test different aspects of congestion control, none of which is considered the definitive test for congestion.

Keep in mind that most of these tests are performed in an artificial environment intended to measure the outer limits of switches and rarely, if ever, reflect circumstances a switch would consistently find in an actual network environment. This is particularly true for congestion type testing. The applicability of these performance numbers to real world networks has to be interpreted carefully, as most switches in these tests perform to a level significantly exceeding the needs of real world networks.

Additional comments on each of the parameters follows.

http://www.rfc-editor.org/

. Unfortunately, there is no

3.1 Throughput/Packet Loss Rate

Hardware is now available to the switch designer to allow designs that can handle media-speed streams on all ports simultaneously. This does, in most cases, come at an increased price for the switch to customers. As a result, designs for switches are a tradeoff of total throughput versus cost. This tradeoff is most apparent for high port density switches, where the cost of providing media-speed throughput on all ports simultaneously can be high, while the actual need for this level of throughput is doubtful.

3.1.1 HP ProCurve Switch 4000M / 8000M

This tradeoff can be seen in Appendix A in the throughput numbers for the HP ProCurve Switch 4000M or 8000M, both high port density switches. With 40 port pairs active (i.e. all 80 ports connected and passing half duplex traffic), the Switch 4000M or 8000M reported a 94.1% traffic throughput with 1518 byte packets and 78.5% with 64 byte packets. Forty full-duplex port pairs active at 100Mbps is the equivalent of sending 4 Gbps through the switch. With the Switch 4000M and 8000M backplanes rated at 3.8 Gbps (based on backplane clock speed) there are some packet drops to be expected at this traffic level and this is seen with 1024 byte packets and larger. Backplane throughput, calculated from these figures, is shown to be approximately 3.73 Gbps for actual throughput. The increase in drops (as shown by the lower percentage) below the 1024 byte packet length is due to the switch engine overhead of having to make many more forwarding decisions (as shown in the total packets column). This is particularly evident in the 64 byte packet test.

This test shows the maximum packet per second rate for the HP ProCurve Switch 4000M and 8000M is

4.67 million 64 byte packets. This performance is excellent, particularly given the HP ProCurve Switch 4000M and 8000M’s low cost.

3.1.2 HP ProCurve Switch 2424M

The HP ProCurve Switch 2424M has a backplane rated at 3.2 Gbps. When maximum full duplex traffic is sent through the 24 fixed 10/100 ports and 2 Gigabit ports on an installed Stacking Module, the data rate is theoretically 4.4 Gbps, so packet drops at this traffic level are expected. As seen in Appendix A, the HP ProCurve Switch 2424M with 512 byte packets and above show a throughput rate of about

72.5%. This is equivalent to a backplane speed of 3.19 Gbps, which lines up nicely with the actual backplane speed. With packets smaller than 512 bytes the throughput rate is affected the ability of the switch to handle the higher number of packets seen with smaller packet sizes. The maximum packet handling rate is with 64 byte packets where the HP ProCurve Switch 2424M handled 3.92 million packets per second. This packet handling ability is more than sufficient for the typical desktop switch environment and better than the other major vendors’ stackable solutions. Compare these numbers to those posted in a test conducted by the Tolly Group on several stackable switches. The report, No. 8286, is available at

http://www.tolly.com/

under Custom Tests in the Test Results area of the site.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

Throughput testing using just the installed 24 10/100 ports of the HP ProCurve Switch 2424M shows it to be media speed under these conditions for all packet sizes.

3.1.3 HP ProCurve Switch 1600M

For the HP ProCurve Switch 1600M, where the port count is lower than the Switch 8000M, throughput is at full media speed for all ports. The throughput numbers in Appendix A for the HP ProCurve Switch 1600M are for twenty-four 10/100Mbps ports at half-duplex. The test used to derive this result is the SmartApplications suite, revision 1.7, from NetCom Systems. This version does not support full duplex operation. In addition, the test will not test the backplane speed of the Switch 1600M with a Gigabit port installed because it cannot operate at full duplex. Backplane throughput was tested with the Gigabit port by using SmartWindows from NetCom Systems, another testing program that operates at a low level much like a LAN analyzer. SmartWindows, which can handle full duplex traffic, was set up to send theoretical maximum traffic into the Switch 1600M with the Gigabit module, while monitoring traffic coming out of the switch. All traffic sent into the switch was observed to also leave the switch indicating full media speed operation.

3.1.4 Gigabit Port Throughput

As shown in Appendix A, a Gigabit port, on an HP ProCurve switch tests out at ten times the throughput of a 100 Mbps port. In other words, as far as the throughput tests are concerned, a Gigabit module is equal to ten 10/100 ports, for both half and full-duplex tests.

3.2 Congestion Control

Congestion occurs any time more packets are destined for a particular segment than that segment can handle. All switches handle momentary congestion passively through buffering excess packets in memory. Some switches attempt to handle congestion actively by making a heavily used segment appear to have numerous collisions, causing all stations on that segment to back off in their sending of packets. This method is called “backpressure”. Since all nodes on a segment are prevented from talking during the time the switch is applying backpressure, even traffic not destined for the switch is also stopped during this time.

Another method of congestion control is to modify the Ethernet backoff algorithm parameters. This technique, sometimes called “forwardpressure”, makes a switch port more aggressive in getting any buffered packets out on a segment after a collision has occurred, at the expense of other nodes on that segment. Since this directly conflicts with Ethernet standards it is strongly criticized and discouraged by the various Ethernet standards groups. It is, however, very difficult to test for compliance in this area. HP switches do not employ forwardpressure.

In order to control congestion in a standardized manner, the 802.3x Flow Control standard has been implemented in the HP ProCurve Switch 4000M/8000M/2424M/1600M. This allows orderly control of segment traffic by allowing a port on the switch to signal its congestion to the segment and holding off segment traffic. For 802.3u to work correctly, the node(s) connected directly to switch ports with flow control enabled also have to support the flow control protocol. Current congestion control testing has not been done while using 802.3u, but should have similar results to switches employing backpressure.

3.2.1 Unidirectional Congestion Testing

As the HP ProCurve Switch 4000M/8000M/2424M/1600M does not utilize backpressure or forwardpressure, congestion control is through having adequate buffers available to handle periods of output port over-subscription or through the use of 802.3u Flow Control. In Section 6 of their 1997 Switched 10Mbps — 100Mbps Evaluation Report, Strategic Networks Consulting Inc., a well-respected network consultancy, reported that switches with passive congestion control can be as effective as switches with active congestion control. They further state that such switches “can be deployed throughout the network with somewhat less regard for the traffic flows and client-server system configurations.” In other words, deployment of switches with passive congestion control is easier to do (less upset to the network itself) without any loss in effectiveness of overall congestion control. So

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

while backpressure is an appealing idea, in real-world environments it is not necessary and may actually impede network traffic in times of high segment utilization.

In many respects this is true of 802.3u use as well. The one area where 802.3u can be beneficial and simple to implement is on links between the switch and an end node, such as a server. In times of network congestion this will allow the switch to hold off traffic originating on the server. The network card in the server has to support 802.3u for this to work.

Long term a better solution for congestion control than either backpressure or Flow Control will be implementation of QoS priority queues and policy-based networking, particularly in the network core.

3.2.2 Bi-directional Congestion Testing (X-Stream)

Another congestion test being used is the bi-directional, multi-stream spray test.15 In this test bursts of packet streams are sent into all tested ports at the same time. Collisions and congestion result simultaneously on all ports. Throughput and packet loss rate (PLR) are recorded for each port.

This is an ardent stress test because the conditions created in this test would not be seen in a properly designed network. Interpretation of the results of this type of test is not straightforward. It is important to look at both throughput and PLR. Switches with passive congestion control may have a non-zero PLR but throughput should be high. Switches that use backpressure will tend to have a 0% PLR but throughput will tend to be lower than passive congestion control switches. Switches that have 0% PLR and high throughput either have extensive packet buffers (an expensive proposition) or, more likely, are using some form of forwardpressure and are not within Ethernet specifications.

With the results of this test keep in mind that switches that are less expensive will tend to have higher PLRs and lower throughputs. This does not mean these switches are poorly designed, but rather that they are designed for lower traffic level areas such as workgroup settings where cost is a primary concern. For switches with active congestion control (both backpressure and forwardpressure), this type of test doesn’t measure the possible negative effects on the rest of the network that occur in real environments.

With the unrealistic conditions present in this test, interpretation is very difficult, particularly with regards to expected performance in a real-world network.

3.3 Latency

Latency is the amount of time the switch takes to process a packet. In store-and-forward switches, such as with the HP ProCurve Switches 4000M/8000M/2424M/1600M, latency is reported by vendors on a LIFO basis (last bit in, first bit out), i.e. the time elapsed between the end of the last bit of the packet going into the switch to the beginning of the first bit of that packet emerging from the switch. Cutthrough switch latency is measured on a FIFO basis (first in, first out), time measured from the beginning of the first bit of the packet going in to the switch to the beginning of the first bit of the outbound packet coming out of the switch. Latency figures should be used with care when comparing store-and-forward switches versus cut-through switches.

To add to the confusion, many testing houses report store-and-forward latency as FIFO because the test equipment reports it that way. Following the actual definition of latency (RFC1242), which is the time taken by the switch to decide where to send a particular packet, store-and-forward switch latencies should be reported as LIFO. At any rate, latency figures should be labeled as to whether they are LIFO or FIFO.

Occasionally store-and-forward switch latency will be reported on a FIFO basis. To convert FIFO to LIFO results, the time associated with the packet itself must be subtracted out. For 10Mbps Ethernet frames the following formula can be used:

LIFO = FIFO - (packet length (bytes) * .8 µsec)

The SmartBits version of this test is the X-Stream test in the Advanced Switch Test suite. SmartBits (NetCom Systems) is a

network tester commonly used for switch testing.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

For 100Mbps Ethernet the formula is:

LIFO = FIFO - (packet-length (bytes) * .08 µsec)

At what point latency is measured is also a variable. Some tests show latency based on a single packet sent into the switch. Other testing has latency measured for a packet in the middle of a stream of packets. Generally, a switch will have more favorable latency times for the mid-stream packet than for a single packet, so how the testing is done should be spelled out.

Latency is usually measured with the NetCom SmartBits tester, a special-purpose test unit that can measure latency down to the nearest bit time for the technology under test.

In normal testing, latency should be measured for a variety of packet sizes and all ports should be tested since latency, being sensitive to the architecture of the switch, can vary from port to port.

Latency for the HP ProCurve Switches 4000M/8000M/2424M/1600M are very good at around 3.5-12 µsec for a store-and-forward switch. As is seen in the figures in Appendix A, this latency varies little port-toport for unicast or broadcast packets. This is an ideal situation for multimedia environments where both low latency, and low variability in latency, is important. See section 2.2.2, Backplane Design, for a discussion on how this low latency is achieved.

3.4 Broadcast Latency

For broadcast latencies, the difference in times of the emerging broadcast packets from all ports relative to the source port is an important consideration. The lower the time variance between ports, the better the switch is considered to perform in the broadcast latency test. The HP ProCurve Switches 4000M/8000M/2424M/1600M have very low variance in times between ports making these switches excellent in multimedia and other time sensitive environments.

In addition to the actual broadcast latency data from the SmartBits tester in Appendix A, the computed mean and average deviation is also shown. The mean shows the average latency across all ports and is indicative of overall latency of broadcast packets through the switch. Comparing the mean to the typical latency with unicast packets shows that the HP ProCurve Switch 4000M/8000M/2424M/1600M’s ability to handle broadcasts is excellent.

Average deviation is the measure of deviation across all ports from the computed mean, showing the actual variability of values between ports from the mean. The smaller this deviation, the better. The variability seen in the HP ProCurve Switch 4000M/8000M/2424M/1600M is very low, a direct result of the backplane architecture.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

4. Additional Information

4.1 ProCurve Networking Web Site

Additional information, including the latest data sheets, design guides, white papers, product documentation and support information can be obtained through the HP ProCurve Networking web site. HP ProCurve Networking can be reached at:

http://www.hp.com/go/procurve

4.2 Reseller Plaza

The dedicated reseller web site for HP Networking products can be reached either through the ProCurve Networking site, or directly at:

http://www.hp.com/go/sellprocurve

Admission to the reseller site requires registration.

4.3 White papers

White papers covering some of the technical details described here in more detail can be found in the Technical Library section of ProCurve Networking at:

http://www.hp.com/rnd/products/solutions/techlib/techlib.htm

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

5. Pricing

All HP switches ship with HP TopTools for Hubs & Switches.

US List Price

Prod No. Description December 1, 1999 J4121A

HP ProCurve Switch 4000M base unit

Includes (40) 10/100 autosensing UTP ports, (5) open module slots

$3,599

J4110A

HP ProCurve Switch 8000M base unit

Ten module slot chassis

J4093A

HP ProCurve Switch 2424M

(24) 10/100 autosensing UTP ports, (1) open module slot

J4120A

HP ProCurve Switch 1600M base unit

(16) 10/100 autosensing UTP ports, (1) open module slot

J4111A HP ProCurve Switch 10/100Base-T Module

(8) autosensing UTP ports

J4112A HP ProCurve Switch 100Base-FX Module

(4) multi-mode fiber optic ports, SC connectors

J4113A HP ProCurve Switch Gigabit-SX Module

(1) multi-mode fiber optic port, SC connectors

J4114A HP ProCurve Switch Gigabit LX Module

(1) single/multi-mode fiber port, SC connectors

J4115A HP ProCurve Switch 100/1000Base-T Module

(1) Gigabit copper port, RJ-45 connector

J4118A HP ProCurve Switch 10Base-FL Module

(4) multi-mode fiber optic ports, ST connectors

J4130A HP ProCurve Switch 2424M Gigabit Stacking Module

Can only be used in the HP ProCurve Switch 2424M J4131A HP ProCurve Gigabit-SX Transceiver (used in the J4130A) J4132A HP ProCurve Gigabit-LX Transceiver (used in the J4130A) J4116A HP ProCurve Gigabit Stacking Kit (used in the J4130A)

(Contains (2) transceivers and (1) .5m cable)

$1,999

$1,899

$1,599

$699

$1,299

$1,499

$1,999

$699

$2,499

$639

$899

$1,429

$299

J4119A HP ProCurve Switch 4000M/8000M Redundant Power Supply

H5481A

HP SupportPack for Onsite Service on HP Network Connectivity

$1,799

$300

Products

Provides warranty upgrade on one 8000M, 4000M, 2424M, or

1600M to on-site 4 hour response (8a-5p, M-F) for 3 years

Available in most parts of the world.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

6. Appendix A: Performance Figures

These numbers have been generated by Hewlett-Packard, using the SmartBits tester and the SmartApplications (revision 1.70) software suite, both from NetCom Systems. This combination is used by most network testing houses and the press to determine basic performance numbers for networking equipment. The maximum number of test ports with SmartBits at 10Mbps or 100Mbps is 80. SmartApplications v1.70 does not support full duplex streams even when the switch is configured for full duplex. Numbers presented here are taken directly from the SmartBits reports, except for a few calculated values which are clearly marked.

See Section 3 for an analysis of these numbers.

6.1 HP ProCurve Switch 4000M / 8000M

6.1.1 Throughput test

6.1.1.1 100BT

Port pairs active: 40, (80 ports) = 4Gbps data out of the tester

Test length: 60 seconds

Packet size (bytes) 64 128 256 512 1024 1280 1518 Total Packets 4,672,880 3,105,600 1,686,360 881,040 450,840 362,320 306,035

Percentage 78.5 91.9 93.1 93.7 94.1 94.2 94.1

See section 3 for interpretation of the above results.

Port pairs active: 30, (60 ports) = 3Gbps data out of the tester

Test length: 60 seconds

Packet size (bytes) 64 128 256 512 1024 1280 1518 Total Packets 4,464,300 2,533,770 1,358,700 704,880 359,190 288,450 243,810

Percentage 100.0 100.0 100.0 100.0 100.0 100.0 100.0

6.1.1.2 10BT

Port pairs active: 40, (80 ports) = 400Mbps data out of the tester

Test length: 60 seconds

Packet size (bytes) 64 128 256 512 1024 1280 1518 Total Packets 595,240 337,840 181,160 94,000 47,880 38,480 32,520

Percentage 100.0 100.0 100.0 100.0 100.0 100.0 100.0

6.1.2 Latency Test - unicast traffic

6.1.2.1 100Mbps

Port pairs active: 1 Latency test length: 10 seconds Port-Pair Latency in microsec (µs)

Packet size (bytes) 64 128 256 512 1024 1280 1518 Port 1 to 2 8.70 14.50 25.50 47.30 91.20 113.20 133.30 FIFO

3.58 4.26 5.02 6.34 9.28 10.80 11.86 LIFO (Calculated)

6.1.2.2 10Mbps

Port pairs active: 1 Latency test length: 10 seconds Port-Pair Latency in microsec (µs)

Packet size (bytes) 64 128 256 512 1024 1280 1518 Port 1 to 2 65.20 117.20 220.10 426.50 839.10 1045.2 1237.1 FIFO

14.00 14.80 15.30 16.90 19.90 21.2 22.7 LIFO (Calculated)

See the Latency discussion in section 3 of this guide for the LIFO calculation.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

6.1.3 Latency Test - broadcast traffic

In this SmartApplications test a 64 byte broadcast packet is sent into port 1 of the switch. The FIFO time it takes for the packet to emerge from the different ports is then recorded. The important measurement here is the variability between ports.

6.1.3.1 100Mbps

64 byte broadcast packet

Port Latency 16 9.5 µs 31 9.2 µs 46 10.1 µs 61 9.3 µs 76 9.5 µs

2 9.7 µs 17 9.7 µs 32 9.5 µs 47 9 µs 62 9.5 µs 77 9.8 µs 3 9.8 µs 18 9.8 µs 33 9.7 µs 48 9.1 µs 63 9.9 µs 78 9.9 µs 4 9.9 µs 19 9 µs 34 9.9 µs 49 9 µs 64 10.1 µs 79 9.5 µs 5 8.9 µs 20 9.2 µs 35 9 µs 50 9.1 µs 65 10 µs 80 9.6 µs 6 9.2 µs 21 9.4 µs 36 10 µs 51 10 µs 66 10.1 µs 7 8

9 10 11 12 13 14 15

9 µs 22 9.5 µs 37 9 µs 52 10.2 µs 67 9.9 µs

9.2 µs 23 9.6 µs 38 9.1 µs 53 9.3 µs 68 10.1 µs

9.4 µs 24 9.8 µs 39 9.4 µs 54 9.6 µs 69 10 µs

9.5 µs 25 9 µs 40 9.6 µs 55 9.8 µs 70 10.1 µs

9.6 µs 26 9.2 µs 41 9.7 µs 56 9.9 µs 71 10 µs

9.9 µs 27 9.4 µs 42 9.8 µs 57 10.1 µs 72 10.2 µs 9 µs 28 9.6 µs 43 9.7 µs 58 10.2 µs 73 10 µs

9.2 µs 29 9.8 µs 44 9.8 µs 59 8.9 µs 74 10.1 µs

9.5 µs 30 9.9 µs 45 10 µs 60 9.2 µs 75 9.4 µs

Mean:

9.60 (Calculated)

Average Deviation: 0.32 (Calculated)

6.1.3.2 10Mbps

64 byte broadcast packet

Port Latency 16 67.5 µs 31 66.7 µs 46 68.2 µs 61 66.6 µs 76 67.6 µs

2 65.8 µs 17 67.4 µs 32 66 µs 47 66.9 µs 62 66.3 µs 77 67.5 µs 3 66.1 µs 18 67.5 µs 33 66.1 µs 48 67.1 µs 63 66.8 µs 78 67.5 µs 4 66.4 µs 19 66.7 µs 34 66.3 µs 49 66.6 µs 64 66.8 µs 79 67.4 µs 5 65.3 µs 20 66.9 µs 35 66.7 µs 50 66.8 µs 65 66.8 µs 80 67.4 µs 6 66 µs 21 67 µs 36 66.7 µs 51 67.9 µs 66 66.5 µs 7 65.6 µs 22 67.3 µs 37 67 µs 52 68.2 µs 67 67.8 µs 8 65.9 µs 23 67.5 µs 38 66.8 µs 53 67.1 µs 68 67.7 µs

9 65.9 µs 24 67.5 µs 39 67.5 µs 54 67.2 µs 69 67.8 µs 10 66.5 µs 25 66.9 µs 40 66.3 µs 55 67.5 µs 70 68.1 µs 11 67.5 µs 26 67.4 µs 41 67.9 µs 56 68 µs 71 67.8 µs 12 66.4 µs 27 67.4 µs 42 67.6 µs 57 67.8 µs 72 68.3 µs 13 65.8 µs 28 67.5 µs 43 67.7 µs 58 68.1 µs 73 67.8 µs 14 67 µs 29 66.2 µs 44 67.8 µs 59 66.8 µs 74 67.8 µs 15 66.3 µs 30 66.7 µs 45 67.9 µs 60 66.8 µs 75 66.9 µs

Mean:

67.05 (Calculated)

Average Deviation: 0.60 (Calculated)

See the Latency discussion in section 3 of this guide for details on FIFO versus LIFO figures.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

6.2 HP ProCurve Switch 2424M

These numbers have been generated by Hewlett-Packard, using the SmartBits tester and the SmartApplications (revision 3.01) software suite, both from NetCom Systems. This combination is used by most network testing houses and the press to determine basic performance numbers for networking equipment. Numbers presented here are taken directly from the SmartBits reports, except for a few calculated values which are clearly marked.

6.2.1 Throughput test

6.2.1.1 100BT

Port pairs active: 26  (24) 100 Mbps full duplex + (2) 1 Gbps full duplex ports = 4.4 Gbps data out of the tester

Test length: 60 seconds

Packet size (bytes) 64 128 256 512 1024 1280 1518 Total Packets 3928578 2602734 1417514 751378 381956 306908 259198

Percentage 60.0 70.2 71.1 72.7 72.5 72.5 72.5

See section 3 for interpretation of the above results.

6.2.1.2 10BT

Port pairs active: 24, = 240 Mbps data out of the tester

Test length: 60 seconds

Packet size (bytes) 64 128 256 512 1024 1280 1518 Total Packets 357144 202704 108696 56400 28728 23088 19512

Percentage 100.0 100.0 100.0 100.0 100.0 100.0 100.0

6.2.2 Latency Test - unicast traffic

6.2.2.1 100Mbps

Port pairs active: 1 Latency test length: 10 seconds Port-Pair Latency in microsec (µs)

Packet size (bytes) 64 128 256 512 1024 1280 1518 Port 1 to 2 8.70 14.90 25.70 47.80 92.20 116.80 137.20 FIFO

3.58 4.66 5.22 6.84 10.28 14.40 15.76 LIFO (Calculated)

6.2.2.2 10Mbps

Port pairs active: 1 Latency test length: 10 seconds Port-Pair Latency in microsec (µs)

Packet size (bytes) 64 128 256 512 1024 1280 1518 Port 1 to 2 66.10 118.40 221.50 428.00 840.70 1047.1 1238.5 FIFO

14.90 16.00 16.70 18.40 21.50 23.1 24.19 LIFO (Calculated)

See the Latency discussion in section 3 of this guide for the LIFO calculation.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

6.2.3 Latency Test - broadcast traffic

6.2.3.1 100Mbps

64 byte broadcast packet

Port Latency 13 12.0µs

2 13.5µs 14 12.5µs 3 12.0µs 15 13.1µs 4 12.5µs 16 13.5µs 5 13.0µs 17 12.0µs 6 13.5µs 18 12.7µs 7 13.0µs 19 11.7µs 8 13.3µs 20 12.2µs

9 11.7µs 21 12.9µs 10 12.2µs 22 13.3µs 11 12.7µs 23 11.7µs 12 13.3µs 24 12.3µs

Mean:

12.63 (Calculated FIFO) 7.51 (Calculated LIFO)

Average Deviation: 0.54 (Calculated)

6.2.3.2 10Mbps

64 byte broadcast packet

Port Latency 13 86.7µs

2 89.4µs 14 87.3µs

3 87.7µs 15 87.6µs

4 88.4µs 16 88.2µs

5 89.0µs 17 86.9µs

6 89.5µs 18 87.6µs

7 89.1µs 19 86.3µs

8 89.1µs 20 87.0µs

9 87.9µs 21 87.4µs 10 88.0µs 22 88.2µs 11 88.6µs 23 86.6µs 12 89.5µs 24 87.2µs

Mean:

97.97 (Calculated FIFO) 36.77 (Calculated LIFO)

Average Deviation: 0.82 (Calculated)

See the Latency discussion in section 3 of this guide for details on FIFO versus LIFO figures.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

6.3 HP ProCurve Switch 1600M

6.3.1 Throughput test

6.3.1.1 100BT

Port pairs active: 12, (24 ports) = 1.2Gbps data out of the tester

Test length: 60 seconds

Packet size (bytes) 64 128 256 512 1024 1280 1518 Total Packets 1785720 1013508 543480 281952 143676 115380 97524

Percentage 100.0 100.0 100.0 100.0 100.0 100.0 100.0

6.3.1.2 10BT

Port pairs active: 12, (24 ports) = 120Mbps data out of the tester

Test length: 60 seconds

Packet size (bytes) 64 128 256 512 1024 1280 1518 Total Packets 178572 101352 54348 28200 14364 11544 9756

Percentage 100.0 100.0 100.0 100.0 100.0 100.0 100.0

6.3.2 Latency Test - unicast traffic

6.3.2.1 100Mbps

Port pairs active: 1 Latency test length: 10 seconds Port-Pair Latency in microsec (µs)

Packet size (bytes) 64 128 256 512 1024 1280 1518 Port 1 to 2 8.70 14.90 25.80 47.60 92.50 117.30 134.30 FIFO

3.58 4.66 5.32 6.64 10.58 14.90 12.86 LIFO (Calculated)

6.3.2.2 10Mbps

Port pairs active: 1 Latency test length: 10 seconds Port-Pair Latency in microsec (µs)

Packet size (bytes) 64 128 256 512 1024 1280 1518 Port 1 to 2 66.10 117.90 221.10 427.30 839.90 1045.9 0 1237.8 0 FIFO

14.90 15.50 16.60 17.70 20.70 21.90 23.40 LIFO (Calculated)

SmartApplications, version 1.7, does not support full duplex operation out of the tester ports. Testing done through NetCom

Systems SmartWindows revision 6.23 has verified full media speed, full duplex simultaneously on all ports at both 10Mbps and 100Mbps for the Switch 1600M.

See the Latency discussion in section 3 of this guide for the LIFO calculation.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

6.3.3 Latency Test - broadcast traffic

6.3.3.1 100Mbps

64 byte broadcast packet

Port Latency 13

2 9.0 µs 14 3 9.4 µs 15 4 9.6 µs 16 5 9.7 µs 17 6 9.9 µs 18 7 10.0 µs 19 8 10.2 µs 20

9 9.0 µs 21 10 9.4 µs 22 11 9.7 µs 23 12 9.9 µs 24

10.0 µs

10.2 µs

10.4 µs

10.5 µs

9.0 µs

9.2 µs

10.3 µs

10.4 µs

9.5 µs

9.8 µs

10.0 µs

10.1 µs

Mean:

Average Deviation:

6.3.3.2 10Mbps

64 byte broadcast packet

Port Latency 13

2 67.1 µs 14

3 67.0 µs 15

4 67.3 µs 16

5 67.3 µs 17

6 67.5 µs 18

7 67.8 µs 19

8 67.8 µs 20

9 66.6 µs 21 10 67.0 µs 22 11 67.3 µs 23 12 67.6 µs 24

Mean:

Average Deviation:

9.79 (Calculated)

0.38 (Calculated)

67.8 µs

68.0 µs

68.1 µs

68.3 µs

67.9 µs

67.8 µs

68.3 µs

68.6 µs

65.7 µs

67.3 µs

67.6 µs

67.5 (Calculated)

0.46 (Calculated)

See the Latency discussion in section 3 of this guide for details on FIFO versus LIFO figures.

HP ProCurve Switch 4000M / 8000M / 2424M / 1600M Reviewer’s Guide

6.4 HP ProCurve Switch 100/1000Base-T Module

The HP ProCurve Switch 100/1000Base-T Module was tested by Hewlett-Packard using the IXIA Communications tester with the 1000Base-T Modules running the RFC 2544 Throughput Test.

6.4.1.1 1000BT

Port pairs active: 1, (2 ports) = 1000Mbps data out of the tester

Test length: 20 seconds

Packet size (bytes) 64 128 256 512 1024 1280 1518 Total Packets

1488096 844595 452899 234963 119732 96154 81275

Percentage 100.0 100.0 100.0 100.0 100.0 100.0 100.0

6.4.1.2 100BT

Port pairs active: 1, (2 ports) = 100Mbps data out of the tester

Test length: 20 seconds

Packet size (bytes) 64 128 256 512 1024 1280 1518 Total Packets

148810 84460 45290 23497 11973 9616 8128

Percentage 100.0 100.0 100.0 100.0 100.0 100.0 100.0

6.5 HP ProCurve Switch Gigabit-SX Module

These numbers have been generated by Hewlett-Packard, using the SmartBits tester

6.5.1.1 Gigabit-SX

Port pairs active: 1, (2 ports) = 1000Mbps data out of the tester

Test length: 10 seconds

Packet size (bytes) 64 128 256 512 1024 1280 1518 Total Packets

1488096 844595 452899 234963 119732 96154 81275

Percentage 100.0 100.0 100.0 100.0 100.0 100.0 100.0

6.6 HP ProCurve Switch Gigabit-LX Module

These numbers have been generated by Hewlett-Packard, using the SmartBits tester

6.6.1.1 Gigabit-LX

Port pairs active: 1, (2 ports) = 1000Mbps data out of the tester

Test length: 10 seconds

Packet size (bytes) 64 128 256 512 1024 1280 1518 Total Packets Percentage 100.0 100.0 100.0 100.0 100.0 100.0 100.0

1488096 844595 452899 234963 119732 96154 81275

HP 2424M User Manual

Specifications and Main Features

Frequently Asked Questions

User Manual