Back to Contents Page

Teaming: Broadcom NetXtreme^® 57XX User Guide

Broadcom Advanced Server Program Overview

Load Balancing and Fault Tolerance

NOTE: See Broadcom Gigabit Ethernet Teaming Services for detailed information on the following topics: Glossary of Terms and Acronyms Teaming Concepts Software Components Hardware Requirements Supported Teaming by Operating System Utilities for configuring Teaming by Operating System Supported Features by Team Type Selecting a Team Type Teaming Mechanisms Architecture Teaming Modes Driver Support by Operating System Supported Teaming Speeds Teaming and Other Advanced Networking Features General network Considerations Application Considerations Troubleshooting Teaming Problems Frequently-Asked Questions Event Log Messages

Broadcom Advanced Server Program Overview

Broadcom Advanced Server Program (BASP) is the Broadcom teaming software for Windows 2000, Windows Server 2003, NetWare, and Linux operating systems. For Windows operating systems, BASP runs within the Broadcom Advanced Control Suite 2 (BACS2) utility. For Linux operating systems (Red Hat distributions only), a BASP script is used to configure a team (see Configuring Teaming); for other Linux distributions, a command line tool is used to configure a team (see Configuring Teaming for Other Linux Distributions); for NetWare operating systems, teams are configured by loading BASP with all the necessary frames for the team (see Configuring Teaming).

BASP provides heterogeneous support for adapter teaming to include all of the Broadcom NetXtreme 57XX controllers as well as Dell shipping Intel NIC adapters including Intel® 10/100 server adapters/LOMs, and Intel® Pro1000 server adapters/LOMs.

BASP supports four types of load balancing teams: Smart Load Balancing and Failover, Link Aggregation (802.3ad), and Generic Trunking (FEC/GEC)/802.3ad-Draft Static.

NOTE: Enabling Windows Server 2003 built-in bridging is not advisable when you are using teaming software.

Load Balancing and Fault Tolerance

Teaming provides traffic load balancing and fault tolerance (redundant adapter operation in the event that a network connection fails). When multiple Gigabit Ethernet network adapters are installed in the same server, they can be grouped into teams, creating a virtual adapter.

A team can consist of 2 to 8 network interfaces, and each interface can be designated as a primary interface or a standby interface (standby interfaces can be used only in a Smart Load Balancing™ (SLB) type of team, and only one standby interface can be designated per SLB team). If traffic is not identified on any of the adapter team member connections due to failure of the adapter, cable, switch port, or switch (where the teamed adapters are attached to separate switches), the load distribution is reevaluated and reassigned among the remaining team members. In the event that all of the primary adapters are down, the hot standby adapter becomes active. Existing sessions are maintained and there is no impact on the user.

Types of Teams

The available types of teams for the supported operating systems are shown in the following table:

Smart Load Balancing™ and Failover

Smart Load Balancing™ and Failover is the Broadcom implementation of load balancing based on IP flow. This feature supports balancing IP traffic across multiple adapters (team members) in a bidirectional manner. In this type of team, all adapters in the team have separate MAC addresses. This type of team provides automatic fault detection and dynamic failover to other team member or to a hot standby member. This is done independently of layer 3 protocol (IP, IPX, NetBEUI); rather, it works with existing layer 2 and 3 switches. No switch configuration (such as trunk, link aggregation) is necessary for this type of team to work.

NOTES: If you do not enable LiveLink™ when configuring teams, disabling Spanning Tree Protocol (STP) at the switch is recommended. This minimizes the downtime due to spanning tree loop determination when failing over. LiveLink mitigates such issues. IPX balances only on the transmit side of the team; other protocols are limited to the primary adapter. If a team member is linked at 1000 Mbit/s and another team member is linked at 100 Mbit/s, most of the traffic is handled by the 1000 Mbit/s team member.

Link Aggregation (802.3ad)

This mode supports link aggregation and conforms to the IEEE 802.3ad (LACP) specification. Configuration software allows you to dynamically configure which adapters you want to participate in a given team. If the link partner is not correctly configured for 802.3ad link configuration, errors are detected and noted. With this mode, all adapters in the team are configured to receive packets for the same MAC address. The outbound load-balancing scheme is determined by our BASP driver. The team link partner determines the load-balancing scheme for inbound packets. In this mode, at least one of the link partners must be in active mode.

Generic Trunking (FEC/GEC)/802.3ad-Draft Static

The Generic Trunking (FEC/GEC)/802.3ad-Draft Static type of team is very similar to the Link Aggregation (802.3ad) type of team in that all adapters in the team need to be configured to receive packets for the same MAC address. The Generic Trunking (FEC/GEC)/802.3ad-Draft Static) type of team, however, does not provide LACP or marker protocol support. This type of team supports a variety of environments in which the adapter link partners are statically configured to support a proprietary trunking mechanism. For instance, this type of team could be used to support Lucent�s OpenTrunk or Cisco�s Fast EtherChannel (FEC). Basically, this type of team is a light version of the Link Aggregation (802.3ad) type of team. This approach is much simpler, in that there is not a formalized link aggregation control protocol (LACP). As with the other types of teams, the creation of teams and the allocation of physical adapters to various teams is done statically through user configuration software.

The Generic Trunking (FEC/GEC/802.3ad-Draft Static) type of team supports load balancing and failover for both outbound and inbound traffic.

SLB (Auto-Fallback Disable)

The SLB (Auto-Fallback Disable) type of team is identical to the Smart Load Balancing and Failover type of team, with the following exception—when the standby member is active, if a primary member comes back on line, the team continues using the standby member, rather than switching back to the primary member.

All primary interfaces in a team participate in load-balancing operations by sending and receiving a portion of the total traffic. Standby interfaces take over in the event that all primary interfaces have lost their links.

Failover teaming provides redundant adapter operation (fault tolerance) in the event that a network connection fails. If the primary adapter in a team is disconnected because of failure of the adapter, cable, or switch port, the secondary team member becomes active, redirecting both inbound and outbound traffic originally assigned to the primary adapter. Sessions will be maintained, causing no impact to the user.

Limitations of Smart Load Balancing and Failover/SLB (Auto-Fallback Disable) Types of Teams

Smart Load Balancing™ (SLB) is a protocol-specific scheme. The level of support for IP, IPX, and NetBEUI protocols is listed below.

Drivers for third-party network adapters must be patched with Broadcom Network Interface Card Extension (NICE) patches for Linux, or be Netware Event Service Layer (NESL) compliant for NetWare to be fault tolerant and load balanced in a multivendor team.

The Smart Load Balancing type of team works with all Ethernet switches without having to configure the switch ports to any special trunking mode. Only IP traffic is load-balanced in both inbound and outbound directions. IPX traffic is load-balanced in the outbound direction only. Other protocol packets are sent and received through one primary interface only. Failover for non-IP traffic is supported only for Broadcom network adapters. The Generic Trunking type of team requires the Ethernet switch to support some form of port trunking mode (for example, Cisco's Gigabit EtherChannel or other switch vendor's Link Aggregation mode). The Generic Trunking type of team is protocol-independent, and all traffic should be load-balanced and fault-tolerant.

NOTE: If you do not enable LiveLink™ when configuring teams, disabling Spanning Tree Protocol (STP) at the switch is recommended. This minimizes the downtime due to the spanning tree loop determination when failing over. LiveLink mitigates such issues.

LiveLink™

LiveLink™ is a feature of BASP that is available only for the Smart Load Balancing™ type of teaming. The purpose of LiveLink is to detect link loss beyond the switch and to route traffic only through team members that have a live link. This function is accomplished though the teaming software (for Windows operating systems, see Configuring LiveLink; for Linux operating systems, see Configuring LiveLink). The teaming software periodically probes (issues a link packet from each team member) one or more specified target network device(s). The probe target(s) responds when it receives the link packet. If a team member does not detect the response within a specified amount of time, this indicates that the link has been lost, and the teaming software discontinues passing traffic through that team member. Later, if that team member begins to detect a response from a probe target, this indicates that the link has been restored, and the teaming software automatically resumes passing traffic through that team member. LiveLink works only with TCP/IP.

LiveLink™ is supported in both 32-bit and 64-bit operating systems of Linux and Windows, but is not supported in NetWare systems.

Teaming and Large Send Offload/Checksum Offload Support

Large Send Offload (LSO) and Checksum Offload are automatically enabled for a team only if LSO and Checksum Offload are supported and configured on all members of a team.

Please read all restrictions and disclaimers.

Back to Contents Page