Source Hashing Scheduling - Revision history

Wensong at 15:27, 17 June 2007

2007-06-17T15:27:07Z

Wensong at 15:24, 17 June 2007

2007-06-17T15:24:34Z

Wensong at 05:29, 23 February 2007

2007-02-23T05:29:48Z

Tom at 21:33, 16 June 2006

2006-06-16T21:33:50Z

Tom at 21:32, 16 June 2006

2006-06-16T21:32:03Z

Tom at 21:24, 16 June 2006

2006-06-16T21:24:26Z

Wensong at 10:47, 20 July 2005

2005-07-20T10:47:49Z

New page

The source hashing scheduling algorithm assigns network connections to the servers through looking up a statically assigned hash table by their source IP addresses.

[[Category:Job Scheduling Algorithms]]

@@ Line 20: / Line 20: @@
 Notes that servernode is a 256-bucket hash table that maps the hash
 index derived from packet source IP address to the current server
-array. If the sh scheduler is used in cache cluster, it is good to
+array.
-combine it with cache_bypass feature. When the statically assigned
-server is dead or overloaded, the load balancer can bypass the cache
-server and send requests to the original server directly.
 </pre>
 [[Category:Job Scheduling Algorithms]]

@@ Line 17: / Line 17: @@
        return n;
 </pre>
 [[Category:Job Scheduling Algorithms]]

@@ Line 3: / Line 3: @@
 ''Maybe, it would be nice to put this in the HOWTO, a lot of people, me too, don't understand why SH seems to lose connections. It's not a bug but a misconfiguration due to a lack of documentation. (The manpage of ipvsadm doesn't mention the following)''
-'''But''', careful, the weight of a realserver with the SH scheduler means the maximum number of connections, multiplied by 2, allowed on this realserver. The meaning of the weight argument is very different in SH and DH than RR, LC and others.
+'''But''', careful, the weight of a realserver with the SH scheduler means the maximum number of connections, multiplied by 2, allowed on this realserver. The meaning of the weight argument is very different in SH and [[Destination Hashing Scheduling|DH]] than [[Round-Robin Scheduling|RR]], [[Least-Connection Scheduling|LC]] and others.
 Just read this thread in lvs-users : [http://archive.linuxvirtualserver.org/html/lvs-users/2006-06/msg00001.html Persistence vs SH scheduler]. Thanks to Martijn Grendelman to pointing this out.

@@ Line 1: / Line 1: @@
 The source hashing scheduling algorithm assigns network connections to the servers through looking up a statically assigned hash table by their source IP addresses.
-''Maybe, it would be nice to put this in the HOWTO, a lot of people, me too, don't understand why SH seems to lose connections. It's not a bug but a misconfiguration due to a lack of documentation. (The manpage of ipvsadm doesn't mention the following:''
+''Maybe, it would be nice to put this in the HOWTO, a lot of people, me too, don't understand why SH seems to lose connections. It's not a bug but a misconfiguration due to a lack of documentation. (The manpage of ipvsadm doesn't mention the following)''
 '''But''', careful, the weight of a realserver with the SH scheduler means the maximum number of connections, multiplied by 2, allowed on this realserver. The meaning of the weight argument is very different in SH and DH than RR, LC and others.
-Just read this thread lvs-users : [http://archive.linuxvirtualserver.org/html/lvs-users/2006-06/msg00001.html Persistence vs SH scheduler]. Thanks to Martijn Grendelman to pointing this out.
+Just read this thread in lvs-users : [http://archive.linuxvirtualserver.org/html/lvs-users/2006-06/msg00001.html Persistence vs SH scheduler]. Thanks to Martijn Grendelman to pointing this out.
 <pre>

@@ Line 1: / Line 1: @@
 The source hashing scheduling algorithm assigns network connections to the servers through looking up a statically assigned hash table by their source IP addresses.
+''Maybe, it would be nice to put this in the HOWTO, a lot of people, me too, don't understand why SH seems to lose connections. It's not a bug but a misconfiguration due to a lack of documentation. (The manpage of ipvsadm doesn't mention the following:''
-''Maybe, it would be nice to put this in the HOWTO, a lot of people, me too, don't understand why SH seems to lose connections. It's not a bug but a misconfiguration due to a lack of documentation. Like the man of ipvsadm doesn't mention the following:''
 '''But''', careful, the weight of a realserver with the SH scheduler means the maximum number of connections, multiplied by 2, allowed on this realserver. The meaning of the weight argument is very different in SH and DH than RR, LC and others.
@@ Line 8: / Line 7: @@
 Just read this thread lvs-users : [http://archive.linuxvirtualserver.org/html/lvs-users/2006-06/msg00001.html Persistence vs SH scheduler]. Thanks to Martijn Grendelman to pointing this out.
 [[Category:Job Scheduling Algorithms]]

← Older revision		Revision as of 21:24, 16 June 2006
Line 1:		Line 1:
	The source hashing scheduling algorithm assigns network connections to the servers through looking up a statically assigned hash table by their source IP addresses.		The source hashing scheduling algorithm assigns network connections to the servers through looking up a statically assigned hash table by their source IP addresses.
		+
		+
		+	''Maybe, it would be nice to put this in the HOWTO, a lot of people, me too, don't understand why SH seems to lose connections. It's not a bug but a misconfiguration due to a lack of documentation. Like the man of ipvsadm doesn't mention the following:''
		+
		+	'''But''', careful, the weight of a realserver with the SH scheduler means the maximum number of connections, multiplied by 2, allowed on this realserver. The meaning of the weight argument is very different in SH and DH than RR, LC and others.
		+
		+	Just read this thread lvs-users : [http://archive.linuxvirtualserver.org/html/lvs-users/2006-06/msg00001.html Persistence vs SH scheduler]. Thanks to Martijn Grendelman to pointing this out.
		+
		+

	[[Category:Job Scheduling Algorithms]]		[[Category:Job Scheduling Algorithms]]