2 # IP Virtual Server configuration
5 tristate "IP virtual server support"
6 depends on NET && INET && NETFILTER
8 IP Virtual Server support will let you build a high-performance
9 virtual server based on cluster of two or more real servers. This
10 option must be enabled for at least one of the clustered computers
11 that will take care of intercepting incoming connections to a
12 single IP address and scheduling them to real servers.
14 Three request dispatching techniques are implemented, they are
15 virtual server via NAT, virtual server via tunneling and virtual
16 server via direct routing. The several scheduling algorithms can
17 be used to choose which server the connection is directed to,
18 thus load balancing can be achieved among the servers. For more
19 information and its administration program, please visit the
20 following URL: <http://www.linuxvirtualserver.org/>.
22 If you want to compile it in kernel, say Y. To compile it as a
23 module, choose M here. If unsure, say N.
28 bool "IPv6 support for IPVS"
29 depends on EXPERIMENTAL && (IPV6 = y || IP_VS = IPV6)
31 Add IPv6 support to IPVS. This is incomplete and might be dangerous.
33 See http://www.mindbasket.com/ipvs for more information.
38 bool "IP virtual server debugging"
40 Say Y here if you want to get additional messages useful in
41 debugging the IP virtual server code. You can change the debug
42 level in /proc/sys/net/ipv4/vs/debug_level
45 int "IPVS connection table size (the Nth power of 2)"
49 The IPVS connection hash table uses the chaining scheme to handle
50 hash collisions. Using a big IPVS connection hash table will greatly
51 reduce conflicts when there are hundreds of thousands of connections
54 Note the table size must be power of 2. The table size will be the
55 value of 2 to the your input number power. The number to choose is
56 from 8 to 20, the default number is 12, which means the table size
57 is 4096. Don't input the number too small, otherwise you will lose
58 performance on it. You can adapt the table size yourself, according
59 to your virtual server application. It is good to set the table size
60 not far less than the number of connections per second multiplying
61 average lasting time of connection in the table. For example, your
62 virtual server gets 200 connections per second, the connection lasts
63 for 200 seconds in average in the connection table, the table size
64 should be not far less than 200x200, it is good to set the table
67 Another note that each connection occupies 128 bytes effectively and
68 each hash entry uses 8 bytes, so you can estimate how much memory is
71 comment "IPVS transport protocol load balancing support"
73 config IP_VS_PROTO_TCP
74 bool "TCP load balancing support"
76 This option enables support for load balancing TCP transport
77 protocol. Say Y if unsure.
79 config IP_VS_PROTO_UDP
80 bool "UDP load balancing support"
82 This option enables support for load balancing UDP transport
83 protocol. Say Y if unsure.
85 config IP_VS_PROTO_AH_ESP
89 config IP_VS_PROTO_ESP
90 bool "ESP load balancing support"
91 select IP_VS_PROTO_AH_ESP
93 This option enables support for load balancing ESP (Encapsulation
94 Security Payload) transport protocol. Say Y if unsure.
97 bool "AH load balancing support"
98 select IP_VS_PROTO_AH_ESP
100 This option enables support for load balancing AH (Authentication
101 Header) transport protocol. Say Y if unsure.
103 comment "IPVS scheduler"
106 tristate "round-robin scheduling"
108 The robin-robin scheduling algorithm simply directs network
109 connections to different real servers in a round-robin manner.
111 If you want to compile it in kernel, say Y. To compile it as a
112 module, choose M here. If unsure, say N.
115 tristate "weighted round-robin scheduling"
118 The weighted robin-robin scheduling algorithm directs network
119 connections to different real servers based on server weights
120 in a round-robin manner. Servers with higher weights receive
121 new connections first than those with less weights, and servers
122 with higher weights get more connections than those with less
123 weights and servers with equal weights get equal connections.
125 If you want to compile it in kernel, say Y. To compile it as a
126 module, choose M here. If unsure, say N.
129 tristate "least-connection scheduling"
131 The least-connection scheduling algorithm directs network
132 connections to the server with the least number of active
135 If you want to compile it in kernel, say Y. To compile it as a
136 module, choose M here. If unsure, say N.
139 tristate "weighted least-connection scheduling"
141 The weighted least-connection scheduling algorithm directs network
142 connections to the server with the least active connections
143 normalized by the server weight.
145 If you want to compile it in kernel, say Y. To compile it as a
146 module, choose M here. If unsure, say N.
149 tristate "locality-based least-connection scheduling"
151 The locality-based least-connection scheduling algorithm is for
152 destination IP load balancing. It is usually used in cache cluster.
153 This algorithm usually directs packet destined for an IP address to
154 its server if the server is alive and under load. If the server is
155 overloaded (its active connection numbers is larger than its weight)
156 and there is a server in its half load, then allocate the weighted
157 least-connection server to this IP address.
159 If you want to compile it in kernel, say Y. To compile it as a
160 module, choose M here. If unsure, say N.
163 tristate "locality-based least-connection with replication scheduling"
165 The locality-based least-connection with replication scheduling
166 algorithm is also for destination IP load balancing. It is
167 usually used in cache cluster. It differs from the LBLC scheduling
168 as follows: the load balancer maintains mappings from a target
169 to a set of server nodes that can serve the target. Requests for
170 a target are assigned to the least-connection node in the target's
171 server set. If all the node in the server set are over loaded,
172 it picks up a least-connection node in the cluster and adds it
173 in the sever set for the target. If the server set has not been
174 modified for the specified time, the most loaded node is removed
175 from the server set, in order to avoid high degree of replication.
177 If you want to compile it in kernel, say Y. To compile it as a
178 module, choose M here. If unsure, say N.
181 tristate "destination hashing scheduling"
183 The destination hashing scheduling algorithm assigns network
184 connections to the servers through looking up a statically assigned
185 hash table by their destination IP addresses.
187 If you want to compile it in kernel, say Y. To compile it as a
188 module, choose M here. If unsure, say N.
191 tristate "source hashing scheduling"
193 The source hashing scheduling algorithm assigns network
194 connections to the servers through looking up a statically assigned
195 hash table by their source IP addresses.
197 If you want to compile it in kernel, say Y. To compile it as a
198 module, choose M here. If unsure, say N.
201 tristate "shortest expected delay scheduling"
203 The shortest expected delay scheduling algorithm assigns network
204 connections to the server with the shortest expected delay. The
205 expected delay that the job will experience is (Ci + 1) / Ui if
206 sent to the ith server, in which Ci is the number of connections
207 on the ith server and Ui is the fixed service rate (weight)
210 If you want to compile it in kernel, say Y. To compile it as a
211 module, choose M here. If unsure, say N.
214 tristate "never queue scheduling"
216 The never queue scheduling algorithm adopts a two-speed model.
217 When there is an idle server available, the job will be sent to
218 the idle server, instead of waiting for a fast one. When there
219 is no idle server available, the job will be sent to the server
220 that minimize its expected delay (The Shortest Expected Delay
221 scheduling algorithm).
223 If you want to compile it in kernel, say Y. To compile it as a
224 module, choose M here. If unsure, say N.
226 comment 'IPVS application helper'
229 tristate "FTP protocol helper"
230 depends on IP_VS_PROTO_TCP
232 FTP is a protocol that transfers IP address and/or port number in
233 the payload. In the virtual server via Network Address Translation,
234 the IP address and port number of real servers cannot be sent to
235 clients in ftp connections directly, so FTP protocol helper is
236 required for tracking the connection and mangling it back to that of
239 If you want to compile it in kernel, say Y. To compile it as a
240 module, choose M here. If unsure, say N.