Documentation/networking/ipvs-sysctl.txt

   1 /proc/sys/net/ipv4/vs/* Variables:
   2
   3 am_droprate - INTEGER
   4         default 10
   5
   6         It sets the always mode drop rate, which is used in the mode 3
   7         of the drop_rate defense.
   8
   9 amemthresh - INTEGER
  10         default 1024
  11
  12         It sets the available memory threshold (in pages), which is
  13         used in the automatic modes of defense. When there is no
  14         enough available memory, the respective strategy will be
  15         enabled and the variable is automatically set to 2, otherwise
  16         the strategy is disabled and the variable is  set  to 1.
  17
  18 backup_only - BOOLEAN
  19         0 - disabled (default)
  20         not 0 - enabled
  21
  22         If set, disable the director function while the server is
  23         in backup mode to avoid packet loops for DR/TUN methods.
  24
  25 conntrack - BOOLEAN
  26         0 - disabled (default)
  27         not 0 - enabled
  28
  29         If set, maintain connection tracking entries for
  30         connections handled by IPVS.
  31
  32         This should be enabled if connections handled by IPVS are to be
  33         also handled by stateful firewall rules. That is, iptables rules
  34         that make use of connection tracking.  It is a performance
  35         optimisation to disable this setting otherwise.
  36
  37         Connections handled by the IPVS FTP application module
  38         will have connection tracking entries regardless of this setting.
  39
  40         Only available when IPVS is compiled with CONFIG_IP_VS_NFCT enabled.
  41
  42 cache_bypass - BOOLEAN
  43         0 - disabled (default)
  44         not 0 - enabled
  45
  46         If it is enabled, forward packets to the original destination
  47         directly when no cache server is available and destination
  48         address is not local (iph->daddr is RTN_UNICAST). It is mostly
  49         used in transparent web cache cluster.
  50
  51 debug_level - INTEGER
  52         0          - transmission error messages (default)
  53         1          - non-fatal error messages
  54         2          - configuration
  55         3          - destination trash
  56         4          - drop entry
  57         5          - service lookup
  58         6          - scheduling
  59         7          - connection new/expire, lookup and synchronization
  60         8          - state transition
  61         9          - binding destination, template checks and applications
  62         10         - IPVS packet transmission
  63         11         - IPVS packet handling (ip_vs_in/ip_vs_out)
  64         12 or more - packet traversal
  65
  66         Only available when IPVS is compiled with CONFIG_IP_VS_DEBUG enabled.
  67
  68         Higher debugging levels include the messages for lower debugging
  69         levels, so setting debug level 2, includes level 0, 1 and 2
  70         messages. Thus, logging becomes more and more verbose the higher
  71         the level.
  72
  73 drop_entry - INTEGER
  74         0  - disabled (default)
  75
  76         The drop_entry defense is to randomly drop entries in the
  77         connection hash table, just in order to collect back some
  78         memory for new connections. In the current code, the
  79         drop_entry procedure can be activated every second, then it
  80         randomly scans 1/32 of the whole and drops entries that are in
  81         the SYN-RECV/SYNACK state, which should be effective against
  82         syn-flooding attack.
  83
  84         The valid values of drop_entry are from 0 to 3, where 0 means
  85         that this strategy is always disabled, 1 and 2 mean automatic
  86         modes (when there is no enough available memory, the strategy
  87         is enabled and the variable is automatically set to 2,
  88         otherwise the strategy is disabled and the variable is set to
  89         1), and 3 means that that the strategy is always enabled.
  90
  91 drop_packet - INTEGER
  92         0  - disabled (default)
  93
  94         The drop_packet defense is designed to drop 1/rate packets
  95         before forwarding them to real servers. If the rate is 1, then
  96         drop all the incoming packets.
  97
  98         The value definition is the same as that of the drop_entry. In
  99         the automatic mode, the rate is determined by the follow
 100         formula: rate = amemthresh / (amemthresh - available_memory)
 101         when available memory is less than the available memory
 102         threshold. When the mode 3 is set, the always mode drop rate
 103         is controlled by the /proc/sys/net/ipv4/vs/am_droprate.
 104
 105 expire_nodest_conn - BOOLEAN
 106         0 - disabled (default)
 107         not 0 - enabled
 108
 109         The default value is 0, the load balancer will silently drop
 110         packets when its destination server is not available. It may
 111         be useful, when user-space monitoring program deletes the
 112         destination server (because of server overload or wrong
 113         detection) and add back the server later, and the connections
 114         to the server can continue.
 115
 116         If this feature is enabled, the load balancer will expire the
 117         connection immediately when a packet arrives and its
 118         destination server is not available, then the client program
 119         will be notified that the connection is closed. This is
 120         equivalent to the feature some people requires to flush
 121         connections when its destination is not available.
 122
 123 expire_quiescent_template - BOOLEAN
 124         0 - disabled (default)
 125         not 0 - enabled
 126
 127         When set to a non-zero value, the load balancer will expire
 128         persistent templates when the destination server is quiescent.
 129         This may be useful, when a user makes a destination server
 130         quiescent by setting its weight to 0 and it is desired that
 131         subsequent otherwise persistent connections are sent to a
 132         different destination server.  By default new persistent
 133         connections are allowed to quiescent destination servers.
 134
 135         If this feature is enabled, the load balancer will expire the
 136         persistence template if it is to be used to schedule a new
 137         connection and the destination server is quiescent.
 138
 139 nat_icmp_send - BOOLEAN
 140         0 - disabled (default)
 141         not 0 - enabled
 142
 143         It controls sending icmp error messages (ICMP_DEST_UNREACH)
 144         for VS/NAT when the load balancer receives packets from real
 145         servers but the connection entries don't exist.
 146
 147 secure_tcp - INTEGER
 148         0  - disabled (default)
 149
 150         The secure_tcp defense is to use a more complicated TCP state
 151         transition table. For VS/NAT, it also delays entering the
 152         TCP ESTABLISHED state until the three way handshake is completed.
 153
 154         The value definition is the same as that of drop_entry and
 155         drop_packet.
 156
 157 sync_threshold - INTEGER
 158         default 3
 159
 160         It sets synchronization threshold, which is the minimum number
 161         of incoming packets that a connection needs to receive before
 162         the connection will be synchronized. A connection will be
 163         synchronized, every time the number of its incoming packets
 164         modulus 50 equals the threshold. The range of the threshold is
 165         from 0 to 49.
 166
 167 snat_reroute - BOOLEAN
 168         0 - disabled
 169         not 0 - enabled (default)
 170
 171         If enabled, recalculate the route of SNATed packets from
 172         realservers so that they are routed as if they originate from the
 173         director. Otherwise they are routed as if they are forwarded by the
 174         director.
 175
 176         If policy routing is in effect then it is possible that the route
 177         of a packet originating from a director is routed differently to a
 178         packet being forwarded by the director.
 179
 180         If policy routing is not in effect then the recalculated route will
 181         always be the same as the original route so it is an optimisation
 182         to disable snat_reroute and avoid the recalculation.
 183
 184 sync_version - INTEGER
 185         default 1
 186
 187         The version of the synchronisation protocol used when sending
 188         synchronisation messages.
 189
 190         0 selects the original synchronisation protocol (version 0). This
 191         should be used when sending synchronisation messages to a legacy
 192         system that only understands the original synchronisation protocol.
 193
 194         1 selects the current synchronisation protocol (version 1). This
 195         should be used where possible.
 196
 197         Kernels with this sync_version entry are able to receive messages
 198         of both version 1 and version 2 of the synchronisation protocol.