TCPHA - Revision history

Wensong at 12:52, 15 November 2006

2006-11-15T12:52:22Z

Wensong at 15:55, 10 November 2006

2006-11-10T15:55:37Z

Wensong at 01:25, 24 July 2006

2006-07-24T01:25:57Z

Wensong at 12:28, 29 May 2006

2006-05-29T12:28:43Z

Wensong at 04:07, 27 May 2006

2006-05-27T04:07:28Z

Wensong at 12:41, 7 August 2005

2005-08-07T12:41:03Z

Wensong at 08:15, 14 June 2005

2005-06-14T08:15:25Z

New page

TCPHA (TCP HAndoff) implements an architecture for scalable content-aware request distribution in cluster-base servers. It implements Kernel layer-7 switching based on TCP Handoff protocol for the Linux operating system. Since the overhead of layer-7 switching in user-space is very high, it is good to implement it inside the kernel in order to avoid the overhead of context switching and memory copying between user-space and kernel-space, furthermore, the responses are sent directly to clients, not passing the dispatcher, which will greatly improve the performance of cluster.

See http://dragon.linux-vs.org/~dragonfly/

← Older revision		Revision as of 12:52, 15 November 2006
Line 1:		Line 1:
−	TCPHA (TCP ~~HAndoff~~) implements an architecture for scalable content-aware request distribution in cluster-base servers. It implements Kernel layer-7 switching based on [[TCP Handoff]] protocol for the Linux operating system. Since the overhead of layer-7 switching in user-space is very high, it is good to implement it inside the kernel in order to avoid the overhead of [[context switch]]ing and memory copying between user-space and kernel-space~~, furthermore~~, the responses are sent directly to clients~~, not~~ passing the dispatcher, which ~~will~~ greatly improve the performance of cluster.	+	TCPHA ('''TCP''' '''HA'''ndoff) implements an architecture for scalable content-aware request distribution in cluster-base servers. It implements Kernel layer-7 switching based on [[TCP Handoff]] protocol for the Linux operating system. Since the overhead of layer-7 switching in user-space is very high, it is good to implement it inside the kernel in order to avoid the overhead of [[context switch]]ing and memory copying between user-space and kernel-space. Furthermore, the responses are sent directly back to clients without passing through the dispatcher, which can greatly improve the performance of cluster.

	See http://dragon.linux-vs.org/~dragonfly/htm/tcpha.htm		See http://dragon.linux-vs.org/~dragonfly/htm/tcpha.htm

← Older revision		Revision as of 15:55, 10 November 2006
Line 3:		Line 3:
	See http://dragon.linux-vs.org/~dragonfly/htm/tcpha.htm		See http://dragon.linux-vs.org/~dragonfly/htm/tcpha.htm

		+	[[Category:LVS Software]]
	[[Category:Terms and Abbreviations]]		[[Category:Terms and Abbreviations]]

@@ Line 1: / Line 1: @@
 TCPHA (TCP HAndoff) implements an architecture for scalable content-aware request distribution in cluster-base servers. It implements Kernel layer-7 switching based on [[TCP Handoff]] protocol for the Linux operating system. Since the overhead of layer-7 switching in user-space is very high, it is good to implement it inside the kernel in order to avoid the overhead of [[context switch]]ing and memory copying between user-space and kernel-space, furthermore, the responses are sent directly to clients, not passing the dispatcher, which will greatly improve the performance of cluster.
-See http://dragon.linux-vs.org/~dragonfly/
+See http://dragon.linux-vs.org/~dragonfly/htm/tcpha.htm
 [[Category:Terms and Abbreviations]]

@@ Line 1: / Line 1: @@
-TCPHA (TCP HAndoff) implements an architecture for scalable content-aware request distribution in cluster-base servers. It implements Kernel layer-7 switching based on [[TCP Handoff]] protocol for the Linux operating system. Since the overhead of layer-7 switching in user-space is very high, it is good to implement it inside the kernel in order to avoid the overhead of context switching and memory copying between user-space and kernel-space, furthermore, the responses are sent directly to clients, not passing the dispatcher, which will greatly improve the performance of cluster.
+TCPHA (TCP HAndoff) implements an architecture for scalable content-aware request distribution in cluster-base servers. It implements Kernel layer-7 switching based on [[TCP Handoff]] protocol for the Linux operating system. Since the overhead of layer-7 switching in user-space is very high, it is good to implement it inside the kernel in order to avoid the overhead of [[context switch]]ing and memory copying between user-space and kernel-space, furthermore, the responses are sent directly to clients, not passing the dispatcher, which will greatly improve the performance of cluster.
 See http://dragon.linux-vs.org/~dragonfly/
 [[Category:Terms and Abbreviations]]

← Older revision		Revision as of 04:07, 27 May 2006
Line 2:		Line 2:

	See http://dragon.linux-vs.org/~dragonfly/		See http://dragon.linux-vs.org/~dragonfly/
		+
		+	[[Category:Terms and Abbreviations]]

← Older revision		Revision as of 12:41, 7 August 2005
Line 1:		Line 1:
−	TCPHA (TCP HAndoff) implements an architecture for scalable content-aware request distribution in cluster-base servers. It implements Kernel layer-7 switching based on TCP Handoff protocol for the Linux operating system. Since the overhead of layer-7 switching in user-space is very high, it is good to implement it inside the kernel in order to avoid the overhead of context switching and memory copying between user-space and kernel-space, furthermore, the responses are sent directly to clients, not passing the dispatcher, which will greatly improve the performance of cluster.	+	TCPHA (TCP HAndoff) implements an architecture for scalable content-aware request distribution in cluster-base servers. It implements Kernel layer-7 switching based on [[TCP Handoff]] protocol for the Linux operating system. Since the overhead of layer-7 switching in user-space is very high, it is good to implement it inside the kernel in order to avoid the overhead of context switching and memory copying between user-space and kernel-space, furthermore, the responses are sent directly to clients, not passing the dispatcher, which will greatly improve the performance of cluster.

	See http://dragon.linux-vs.org/~dragonfly/		See http://dragon.linux-vs.org/~dragonfly/