Owner's manual

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
9
can be configured to give a particular priority to a
packet based on:
9
Starting with firmware revision C.07.23. Older revisions can be updated at no charge through the HP ProCurve web site.
©1998, 1999, 2000 Hewlett-Packard Co Revision 3.2b – 1/15/2000 Page 15 of 36