dpif-netlink: add GENEVE creation support

[cascardo/ovs.git] / vtep / vtep.xml

<?xml version="1.0" encoding="utf-8"?>
<database name="vtep" title="Hardware VTEP Database">
  <p>
    This schema specifies relations that a VTEP can use to integrate
    physical ports into logical switches maintained by a network
    virtualization controller such as NSX.
  </p>

  <p>Glossary:</p>

  <dl>
    <dt>VTEP</dt>
    <dd>
      VXLAN Tunnel End Point, an entity which originates and/or terminates
      VXLAN tunnels.
    </dd>

    <dt>HSC</dt>
    <dd>
      Hardware Switch Controller.
    </dd>

    <dt>NVC</dt>
    <dd>
      Network Virtualization Controller, e.g. NSX.
    </dd>

    <dt>VRF</dt>
    <dd>
      Virtual Routing and Forwarding instance.
    </dd>
  </dl>

  <h2>Common Column</h2>

  <p>
    Some tables contain a column, named <code>other_config</code>.
    This column has the same form and purpose each place that it appears,
    so we describe it here to save space later.
  </p>

  <dl>
    <dt><code>other_config</code>: map of string-string pairs</dt>
    <dd>
      <p>
        Key-value pairs for configuring rarely used or proprietary features.
      </p>
      <p>
        Some tables do not have <code>other_config</code> column because no
        key-value pairs have yet been defined for them.
      </p>
    </dd>
  </dl>

  <table name="Global" title="Top-level configuration.">
    Top-level configuration for a hardware VTEP.  There must be
    exactly one record in the <ref table="Global"/> table.

    <column name="switches">
      <p>
        The physical switch or switches managed by the VTEP.
      </p>

      <p>
        When a physical switch integrates support for this VTEP schema, which
        is expected to be the most common case, this column should point to one
        <ref table="Physical_Switch"/> record that represents the switch
        itself.  In another possible implementation, a server or a VM presents
        a VTEP schema front-end interface to one or more physical switches,
        presumably communicating with those physical switches over a
        proprietary protocol.  In that case, this column would point to one
        <ref table="Physical_Switch"/> for each physical switch, and the set
        might change over time as the front-end server comes to represent a
        differing set of switches.
      </p>
    </column>

    <group title="Database Configuration">
      <p>
        These columns primarily configure the database server
        (<code>ovsdb-server</code>), not the hardware VTEP itself.
      </p>

      <column name="managers">
        Database clients to which the database server should connect or
        to which it should listen, along with options for how these
        connection should be configured.  See the <ref table="Manager"/>
        table for more information.
      </column>
    </group>

    <group title="Common Column">
      The overall purpose of this column is described under <code>Common
      Column</code> at the beginning of this document.

      <column name="other_config"/>
    </group>

  </table>

  <table name="Manager" title="OVSDB management connection.">
    <p>
      Configuration for a database connection to an Open vSwitch Database
      (OVSDB) client.
    </p>

    <p>
      The database server can initiate and maintain active connections
      to remote clients.  It can also listen for database connections.
    </p>

    <group title="Core Features">
      <column name="target">
        <p>Connection method for managers.</p>
        <p>
          The following connection methods are currently supported:
        </p>
        <dl>
          <dt><code>ssl:<var>ip</var></code>[<code>:<var>port</var></code>]</dt>
          <dd>
            <p>
              The specified SSL <var>port</var> (default: 6640) on the host at
              the given <var>ip</var>, which must be expressed as an IP address
              (not a DNS name).
            </p>
            <p>
              SSL key and certificate configuration happens outside the
              database.
            </p>
          </dd>

          <dt><code>tcp:<var>ip</var></code>[<code>:<var>port</var></code>]</dt>
          <dd>
            The specified TCP <var>port</var> (default: 6640) on the host at
            the given <var>ip</var>, which must be expressed as an IP address
            (not a DNS name).
          </dd>
          <dt><code>pssl:</code>[<var>port</var>][<code>:<var>ip</var></code>]</dt>
          <dd>
            <p>
              Listens for SSL connections on the specified TCP <var>port</var>
              (default: 6640).  If <var>ip</var>, which must be expressed as an
              IP address (not a DNS name), is specified, then connections are
              restricted to the specified local IP address.
            </p>
          </dd>
          <dt><code>ptcp:</code>[<var>port</var>][<code>:<var>ip</var></code>]</dt>
          <dd>
            Listens for connections on the specified TCP <var>port</var>
            (default: 6640).  If <var>ip</var>, which must be expressed as an
            IP address (not a DNS name), is specified, then connections are
            restricted to the specified local IP address.
          </dd>
        </dl>
      </column>
    </group>

    <group title="Client Failure Detection and Handling">
      <column name="max_backoff">
        Maximum number of milliseconds to wait between connection attempts.
        Default is implementation-specific.
      </column>

      <column name="inactivity_probe">
        Maximum number of milliseconds of idle time on connection to the
        client before sending an inactivity probe message.  If the Open
        vSwitch database does not communicate with the client for the
        specified number of seconds, it will send a probe.  If a
        response is not received for the same additional amount of time,
        the database server assumes the connection has been broken
        and attempts to reconnect.  Default is implementation-specific.
        A value of 0 disables inactivity probes.
      </column>
    </group>

    <group title="Status">
      <column name="is_connected">
        <code>true</code> if currently connected to this manager,
        <code>false</code> otherwise.
      </column>

      <column name="status" key="last_error">
        A human-readable description of the last error on the connection
        to the manager; i.e. <code>strerror(errno)</code>.  This key
        will exist only if an error has occurred.
      </column>

      <column name="status" key="state"
              type='{"type": "string", "enum": ["set", ["VOID", "BACKOFF", "CONNECTING", "ACTIVE", "IDLE"]]}'>
        <p>
          The state of the connection to the manager:
        </p>
        <dl>
          <dt><code>VOID</code></dt>
          <dd>Connection is disabled.</dd>

          <dt><code>BACKOFF</code></dt>
          <dd>Attempting to reconnect at an increasing period.</dd>

          <dt><code>CONNECTING</code></dt>
          <dd>Attempting to connect.</dd>

          <dt><code>ACTIVE</code></dt>
          <dd>Connected, remote host responsive.</dd>

          <dt><code>IDLE</code></dt>
          <dd>Connection is idle.  Waiting for response to keep-alive.</dd>
        </dl>
        <p>
          These values may change in the future.  They are provided only for
          human consumption.
        </p>
      </column>

      <column name="status" key="sec_since_connect"
              type='{"type": "integer", "minInteger": 0}'>
        The amount of time since this manager last successfully connected
        to the database (in seconds). Value is empty if manager has never
        successfully connected.
      </column>

      <column name="status" key="sec_since_disconnect"
              type='{"type": "integer", "minInteger": 0}'>
        The amount of time since this manager last disconnected from the
        database (in seconds). Value is empty if manager has never
        disconnected.
      </column>

      <column name="status" key="locks_held">
        Space-separated list of the names of OVSDB locks that the connection
        holds.  Omitted if the connection does not hold any locks.
      </column>

      <column name="status" key="locks_waiting">
        Space-separated list of the names of OVSDB locks that the connection is
        currently waiting to acquire.  Omitted if the connection is not waiting
        for any locks.
      </column>

      <column name="status" key="locks_lost">
        Space-separated list of the names of OVSDB locks that the connection
        has had stolen by another OVSDB client.  Omitted if no locks have been
        stolen from this connection.
      </column>

      <column name="status" key="n_connections"
              type='{"type": "integer", "minInteger": 2}'>
        <p>
          When <ref column="target"/> specifies a connection method that
          listens for inbound connections (e.g. <code>ptcp:</code> or
          <code>pssl:</code>) and more than one connection is actually active,
          the value is the number of active connections.  Otherwise, this
          key-value pair is omitted.
        </p>
        <p>
          When multiple connections are active, status columns and key-value
          pairs (other than this one) report the status of one arbitrarily
          chosen connection.
        </p>
      </column>
    </group>

    <group title="Connection Parameters">
      <p>
        Additional configuration for a connection between the manager
        and the database server.
      </p>

      <column name="other_config" key="dscp"
              type='{"type": "integer"}'>
        The Differentiated Service Code Point (DSCP) is specified using 6 bits
        in the Type of Service (TOS) field in the IP header. DSCP provides a
        mechanism to classify the network traffic and provide Quality of
        Service (QoS) on IP networks.

        The DSCP value specified here is used when establishing the
        connection between the manager and the database server.  If no
        value is specified, a default value of 48 is chosen.  Valid DSCP
        values must be in the range 0 to 63.
      </column>
    </group>
  </table>

  <table name="Physical_Switch" title="A physical switch.">
    A physical switch that implements a VTEP.

    <column name="ports">
      The physical ports within the switch.
    </column>

    <column name="tunnels">
      Tunnels created by this switch as instructed by the NVC.
    </column>

    <group title="Network Status">
      <column name="management_ips">
        IPv4 or IPv6 addresses at which the switch may be contacted
        for management purposes.
      </column>

      <column name="tunnel_ips">
        <p>
          IPv4 or IPv6 addresses on which the switch may originate or
          terminate tunnels.
        </p>

        <p>
          This column is intended to allow a <ref table="Manager"/> to
          determine the <ref table="Physical_Switch"/> that terminates
          the tunnel represented by a <ref table="Physical_Locator"/>.
        </p>
      </column>
    </group>

    <group title="Identification">
      <column name="name">
        Symbolic name for the switch, such as its hostname.
      </column>

      <column name="description">
        An extended description for the switch, such as its switch login
        banner.
      </column>
    </group>
    <group title="Error Notification">
      <p>
        An entry in this column indicates to the NVC that this switch
        has encountered a fault. The switch must clear this column
        when the fault has been cleared.
      </p>

      <column name="switch_fault_status" key="mac_table_exhaustion">
        Indicates that the switch has been unable to process MAC
        entries requested by the NVC due to lack of table resources.
      </column>

      <column name="switch_fault_status" key="tunnel_exhaustion">
        Indicates that the switch has been unable to create tunnels
        requested by the NVC due to lack of resources.
      </column>

      <column name="switch_fault_status" key="lr_switch_bindings_fault">
        Indicates that the switch has been unable to create the logical router
        interfaces requested by the NVC due to conflicting configurations or a
        lack of hardware resources.
      </column>

      <column name="switch_fault_status" key="lr_static_routes_fault">
        Indicates that the switch has been unable to create the static routes
        requested by the NVC due to conflicting configurations or a lack of
        hardware resources.
      </column>

      <column name="switch_fault_status" key="lr_creation_fault">
        Indicates that the switch has been unable to create the logical router
        requested by the NVC due to conflicting configurations or a lack of
        hardware resources.
      </column>

      <column name="switch_fault_status" key="lr_support_fault">
        Indicates that the switch does not support logical routing.
      </column>

      <column name="switch_fault_status" key="unspecified_fault">
        Indicates that an error has occurred in the switch but that no
        more specific information is available.
      </column>

      <column name="switch_fault_status"
        key="unsupported_source_node_replication">
        Indicates that the requested source node replication mode cannot be
        supported by the physical switch;  this specifically means in this
        context that the physical switch lacks the capability to support
        source node replication mode.  This error occurs when a controller
        attempts to set source node replication mode for one of the logical
        switches that the physical switch is keeping context for.  An NVC
        that observes this error should take appropriate action (for example
        reverting the logical switch to service node replication mode).
        It is recommended that an NVC be proactive and test for support of
        source node replication by using a test logical switch on vtep
        physical switch nodes and then trying to change the replication mode
        to source node on this logical switch, checking for error.  The NVC
        could remember this capability per vtep physical switch.  Using
        mixed replication modes on a given logical switch is not recommended.
        Service node replication mode is considered a basic requirement
        since it only requires sending a packet to a single transport node,
        hence it is not expected that a switch should report that service
        node mode cannot be supported.
      </column>
    </group>

    <group title="Common Column">
      The overall purpose of this column is described under <code>Common
      Column</code> at the beginning of this document.

      <column name="other_config"/>
    </group>

  </table>

  <table name="Tunnel" title="A tunnel created by a physical switch.">
    A tunnel created by a <ref table="Physical_Switch"/>.

    <column name="local">
      Tunnel end-point local to the physical switch.
    </column>

    <column name="remote">
      Tunnel end-point remote to the physical switch.
    </column>

    <group title="Bidirectional Forwarding Detection (BFD)">
      <p>
        BFD, defined in RFC 5880, allows point to point detection of
        connectivity failures by occasional transmission of BFD control
        messages. VTEPs are expected to implement BFD.
      </p>

      <p>
        BFD operates by regularly transmitting BFD control messages at a
        rate negotiated independently in each direction.  Each endpoint
        specifies the rate at which it expects to receive control messages,
        and the rate at which it's willing to transmit them.  An endpoint
        which fails to receive BFD control messages for a period of three
        times the expected reception rate will signal a connectivity
        fault.  In the case of a unidirectional connectivity issue, the
        system not receiving BFD control messages will signal the problem
        to its peer in the messages it transmits.
      </p>

      <p>
        A hardware VTEP is expected to use BFD to determine reachability of
        devices at the end of the tunnels with which it exchanges data. This
        can enable the VTEP to choose a functioning service node among a set of
        service nodes providing high availability. It also enables the NVC to
        report the health status of tunnels.
      </p>

      <p>
        In many cases the BFD peer of a hardware VTEP will be an Open vSwitch
        instance. The Open vSwitch implementation of BFD aims to comply
        faithfully with the requirements put forth in RFC 5880.  Open vSwitch
        does not implement the optional Authentication or ``Echo Mode''
        features.
      </p>

      <group title="BFD Local Configuration">
        <p>
          The HSC writes the key-value pairs in the
          <ref column="bfd_config_local"/> column to specify the local
          configurations to be used for BFD sessions on this tunnel.
        </p>

        <column name="bfd_config_local" key="bfd_dst_mac">
          Set to an Ethernet address in the form
          <var>xx</var>:<var>xx</var>:<var>xx</var>:<var>xx</var>:<var>xx</var>:<var>xx</var>
          to set the MAC expected as destination for received BFD packets.
          The default is <code>00:23:20:00:00:01</code>.
        </column>

        <column name="bfd_config_local" key="bfd_dst_ip">
          Set to an IPv4 address to set the IP address that is expected as destination
          for received BFD packets.  The default is <code>169.254.1.0</code>.
        </column>

      </group>

      <group title="BFD Remote Configuration">
        <p>
          The <ref column="bfd_config_remote"/> column is the remote
          counterpart of the <ref column="bfd_config_local"/> column.
          The NVC writes the key-value pairs in this column.
        </p>

        <column name="bfd_config_remote" key="bfd_dst_mac">
          Set to an Ethernet address in the form
          <var>xx</var>:<var>xx</var>:<var>xx</var>:<var>xx</var>:<var>xx</var>:<var>xx</var>
          to set the destination MAC to be used for transmitted BFD packets.
          The default is <code>00:23:20:00:00:01</code>.
        </column>

        <column name="bfd_config_remote" key="bfd_dst_ip">
          Set to an IPv4 address to set the IP address used as destination
          for transmitted BFD packets.  The default is <code>169.254.1.1</code>.
        </column>

      </group>

      <group title="BFD Parameters">
        <p>
          The NVC sets up key-value pairs in the <ref column="bfd_params"/>
          column to enable and configure BFD.
        </p>

        <column name="bfd_params" key="enable" type='{"type": "boolean"}'>
          True to enable BFD on this <ref table="Tunnel"/>.  If not
          specified, BFD will not be enabled by default.
        </column>

        <column name="bfd_params" key="min_rx"
                type='{"type": "integer", "minInteger": 1}'>
          The shortest interval, in milliseconds, at which this BFD session
          offers to receive BFD control messages.  The remote endpoint may
          choose to send messages at a slower rate.  Defaults to
          <code>1000</code>.
        </column>

        <column name="bfd_params" key="min_tx"
                type='{"type": "integer", "minInteger": 1}'>
          The shortest interval, in milliseconds, at which this BFD session is
          willing to transmit BFD control messages.  Messages will actually be
          transmitted at a slower rate if the remote endpoint is not willing to
          receive as quickly as specified.  Defaults to <code>100</code>.
        </column>

        <column name="bfd_params" key="decay_min_rx" type='{"type": "integer"}'>
          An alternate receive interval, in milliseconds, that must be greater
          than or equal to <ref column="bfd_params" key="min_rx"/>.  The
          implementation should switch from <ref column="bfd_params" key="min_rx"/>
          to <ref column="bfd_params" key="decay_min_rx"/> when there is no obvious
          incoming data traffic at the tunnel, to reduce the CPU and bandwidth
          cost of monitoring an idle tunnel.  This feature may be disabled by
          setting a value of 0.  This feature is reset whenever
          <ref column="bfd_params" key="decay_min_rx"/> or
          <ref column="bfd_params" key="min_rx"/> changes.
        </column>

        <column name="bfd_params" key="forwarding_if_rx" type='{"type": "boolean"}'>
          When <code>true</code>, traffic received on the <ref table="Tunnel"/>
          is used to indicate the capability of packet I/O.
          BFD control packets are still transmitted and received. At least one
          BFD control packet must be received every
          100 * <ref column="bfd_params" key="min_rx"/> amount of time.
          Otherwise, even if traffic is received, the
          <ref column="bfd_params" key="forwarding"/> will be <code>false</code>.
        </column>

        <column name="bfd_params" key="cpath_down" type='{"type": "boolean"}'>
          Set to true to notify the remote endpoint that traffic should not be
          forwarded to this system for some reason other than a connectivity
          failure on the interface being monitored.  The typical underlying
          reason is ``concatenated path down,'' that is, that connectivity
          beyond the local system is down.  Defaults to false.
        </column>

        <column name="bfd_params" key="check_tnl_key" type='{"type": "boolean"}'>
          Set to true to make BFD accept only control messages with a tunnel
          key of zero.  By default, BFD accepts control messages with any
          tunnel key.
        </column>

      </group>

      <group title="BFD Status">
        <p>
          The VTEP sets key-value pairs in the <ref column="bfd_status"/>
          column to report the status of BFD on this tunnel.  When BFD is
          not enabled, with <ref column="bfd_params" key="enable"/>, the
          HSC clears all key-value pairs from <ref column="bfd_status"/>.
        </p>

        <column name="bfd_status" key="enabled" type='{"type": "boolean"}'>
          Set to true if the BFD session has been successfully enabled.
          Set to false if the VTEP cannot support BFD or has insufficient
          resources to enable BFD on this tunnel. The NVC will disable
          the BFD monitoring on the other side of the tunnel once this
          value is set to false.
        </column>

        <column name="bfd_status" key="state"
                type='{"type": "string",
              "enum": ["set", ["admin_down", "down", "init", "up"]]}'>
          Reports the state of the BFD session.  The BFD session is fully
          healthy and negotiated if <code>UP</code>.
        </column>

        <column name="bfd_status" key="forwarding" type='{"type": "boolean"}'>
          Reports whether the BFD session believes this  <ref table="Tunnel"/>
          may be used to forward traffic.  Typically this means the local session
          is signaling <code>UP</code>, and the remote system isn't signaling a
          problem such as concatenated path down.
        </column>

        <column name="bfd_status" key="diagnostic">
          A diagnostic code specifying the local system's reason for the
          last change in session state. The error messages are defined in
          section 4.1 of [RFC 5880].
        </column>

       <column name="bfd_status" key="remote_state"
                type='{"type": "string",
              "enum": ["set", ["admin_down", "down", "init", "up"]]}'>
          Reports the state of the remote endpoint's BFD session.
        </column>

        <column name="bfd_status" key="remote_diagnostic">
          A diagnostic code specifying the remote system's reason for the
          last change in session state. The error messages are defined in
          section 4.1 of [RFC 5880].
        </column>

        <column name="bfd_status" key="info">
          A short message providing further information about the BFD status
          (possibly including reasons why BFD could not be enabled).
        </column>
      </group>
    </group>
  </table>

  <table name="Physical_Port" title="A port within a physical switch.">
    A port within a <ref table="Physical_Switch"/>.

    <column name="vlan_bindings">
      Identifies how VLANs on the physical port are bound to logical switches.
      If, for example, the map contains a (VLAN, logical switch) pair, a packet
      that arrives on the port in the VLAN is considered to belong to the
      paired logical switch. A value of zero in the VLAN field means
      that untagged traffic on the physical port is mapped to the
      logical switch.
    </column>

    <column name="acl_bindings">
      <p>
        Attach Access Control Lists (ACLs) to the physical port. The
        column consists of a map of VLAN tags to <ref table="ACL"/>s. If the value of
        the VLAN tag in the map is 0, this means that the ACL is
        associated with the entire physical port. Non-zero values mean
        that the ACL is to be applied only on packets carrying that VLAN
        tag value. Switches will not necessarily support matching on the
        VLAN tag for all ACLs, and unsupported ACL bindings will cause
        errors to be reported. The binding of an ACL to a specific
        VLAN and the binding of an ACL to the entire physical port
        should not be combined on a single physical port. That is, a
        mix of zero and non-zero keys in the map is not recommended.
      </p>
    </column>

    <column name="vlan_stats">
      Statistics for VLANs bound to logical switches on the physical port.  An
      implementation that fully supports such statistics would populate this
      column with a mapping for every VLAN that is bound in <ref
      column="vlan_bindings"/>.  An implementation that does not support such
      statistics or only partially supports them would not populate this column
      or partially populate it, respectively. A value of zero in the
      VLAN field refers to untagged traffic on the physical port.
    </column>

    <group title="Identification">
      <column name="name">
        Symbolic name for the port.  The name ought to be unique within a given
        <ref table="Physical_Switch"/>, but the database is not capable of
        enforcing this.
      </column>
      
      <column name="description">
        An extended description for the port.
      </column>
    </group>
    <group title="Error Notification">
      <p>
        An entry in this column indicates to the NVC that the physical port has
        encountered a fault. The switch must clear this column when the error
        has been cleared.
      </p>
      <column name="port_fault_status" key="invalid_vlan_map">
        <p>
          Indicates that a VLAN-to-logical-switch mapping requested by
          the controller could not be instantiated by the switch
          because of a conflict with local configuration.
        </p>
      </column>
      <column name="port_fault_status" key="invalid_ACL_binding">
        <p>
          Indicates that an error has occurred in associating an ACL
          with a port.
        </p>
      </column>
      <column name="port_fault_status" key="unspecified_fault">
        <p>
          Indicates that an error has occurred on the port but that no
          more specific information is available.
        </p>
      </column>
    </group>

    <group title="Common Column">
      The overall purpose of this column is described under <code>Common
      Column</code> at the beginning of this document.

      <column name="other_config"/>
    </group>

  </table>

  <table name="Logical_Binding_Stats" title="Statistics for a VLAN on a physical port bound to a logical network.">
    Reports statistics for the <ref table="Logical_Switch"/> with which a VLAN
    on a <ref table="Physical_Port"/> is associated.

    <group title="Statistics">
      These statistics count only packets to which the binding applies.

      <column name="packets_from_local">
        Number of packets sent by the <ref table="Physical_Switch"/>.
      </column>

      <column name="bytes_from_local">
        Number of bytes in packets sent by the <ref table="Physical_Switch"/>.
      </column>

      <column name="packets_to_local">
        Number of packets received by the <ref table="Physical_Switch"/>.
      </column>

      <column name="bytes_to_local">
        Number of bytes in packets received by the <ref
        table="Physical_Switch"/>.
      </column>
    </group>
  </table>

  <table name="Logical_Switch" title="A layer-2 domain.">
    A logical Ethernet switch, whose implementation may span physical and
    virtual media, possibly crossing L3 domains via tunnels; a logical layer-2
    domain; an Ethernet broadcast domain.



    <group title="Per Logical-Switch Tunnel Key">
      <p>
        Tunnel protocols tend to have a field that allows the tunnel
        to be partitioned into sub-tunnels: VXLAN has a VNI, GRE and
        STT have a key, CAPWAP has a WSI, and so on.  We call these
        generically ``tunnel keys.''  Given that one needs to use a
        tunnel key at all, there are at least two reasonable ways to
        assign their values:
      </p>

      <ul>
        <li>
          <p>
            Per <ref table="Logical_Switch"/>+<ref table="Physical_Locator"/>
            pair.  That is, each logical switch may be assigned a different
            tunnel key on every <ref table="Physical_Locator"/>.  This model is
            especially flexible.
          </p>

          <p>
            In this model, <ref table="Physical_Locator"/> carries the tunnel
            key.  Therefore, one <ref table="Physical_Locator"/> record will
            exist for each logical switch carried at a given IP destination.
          </p>
        </li>

        <li>
          <p>
            Per <ref table="Logical_Switch"/>.  That is, every tunnel
            associated with a particular logical switch carries the same tunnel
            key, regardless of the <ref table="Physical_Locator"/> to which the
            tunnel is addressed.  This model may ease switch implementation
            because it imposes fewer requirements on the hardware datapath.
          </p>

          <p>
            In this model, <ref table="Logical_Switch"/> carries the tunnel
            key.  Therefore, one <ref table="Physical_Locator"/> record will
            exist for each IP destination.
          </p>
        </li>
      </ul>

      <column name="tunnel_key">
        <p>
          This column is used only in the tunnel key per <ref
          table="Logical_Switch"/> model (see above), because only in that
          model is there a tunnel key associated with a logical switch.
        </p>

        <p>
          For <code>vxlan_over_ipv4</code> encapsulation, when the tunnel key
          per <ref table="Logical_Switch"/> model is in use, this column is the
          VXLAN VNI that identifies a logical switch.  It must be in the range
          0 to 16,777,215.
        </p>
      </column>
    </group>

    <group title="Replication Mode">
      <p>
        For handling L2 broadcast, multicast and unknown unicast traffic,
        packets can be sent to all members of a logical switch referenced by
        a physical switch.  There are different modes to replicate the
        packets.  The default mode of replication is to send the traffic to
        a service node, which can be a hypervisor, server or appliance, and
        let the service node handle replication to other transport nodes
        (hypervisors or other VTEP physical switches).  This mode is called
        service node replication.  An alternate mode of replication, called
        source node replication involves the source node sending to all
        other transport nodes.  Hypervisors are always responsible for doing
        their own replication for locally attached VMs in both modes.
        Service node replication mode is the default and considered a
        basic requirement because it only requires sending the packet to
        a single transport node.
      </p>

      <column name="replication_mode">
        <p>
          This optional column defines the replication mode per
          <ref table="Logical_Switch"/>.  There are 2 valid values,
          <code>service_node</code> and <code>source_node</code>.  If the
          column is not set, the replication mode defaults to service_node.
        </p>

      </column>
    </group>

    <group title="Identification">
      <column name="name">
        Symbolic name for the logical switch.
      </column>

      <column name="description">
        An extended description for the logical switch, such as its switch
        login banner.
      </column>
    </group>

    <group title="Common Column">
      The overall purpose of this column is described under <code>Common
      Column</code> at the beginning of this document.

      <column name="other_config"/>
    </group>

  </table>

  <table name="Ucast_Macs_Local" title="Unicast MACs (local)">
    <p>
      Mapping of unicast MAC addresses to tunnels (physical
      locators). This table is written by the HSC, so it contains the
      MAC addresses that have been learned on physical ports by a
      VTEP. 
    </p>

    <column name="MAC">
      A MAC address that has been learned by the VTEP.
    </column>

    <column name="logical_switch">
      The Logical switch to which this mapping applies.
    </column>

    <column name="locator">
      The physical locator to be used to reach this MAC address. In
      this table, the physical locator will be one of the tunnel IP
      addresses of the appropriate VTEP.
    </column>

    <column name="ipaddr">
      The IP address to which this MAC corresponds. Optional field for
      the purpose of ARP supression.
    </column>

  </table>

  <table name="Ucast_Macs_Remote" title="Unicast MACs (remote)">
    <p>
      Mapping of unicast MAC addresses to tunnels (physical
      locators). This table is written by the NVC, so it contains the
      MAC addresses that the NVC has learned. These include VM MAC
      addresses, in which case the physical locators will be
      hypervisor IP addresses. The NVC will also report MACs that it
      has learned from other HSCs in the network, in which case the
      physical locators will be tunnel IP addresses of the
      corresponding VTEPs.
    </p>

    <column name="MAC">
      A MAC address that has been learned by the NVC.
    </column>

    <column name="logical_switch">
      The Logical switch to which this mapping applies.
    </column>

    <column name="locator">
      The physical locator to be used to reach this MAC address. In
      this table, the physical locator will be either a hypervisor IP
      address or a tunnel IP addresses of another VTEP.
    </column>

    <column name="ipaddr">
      The IP address to which this MAC corresponds. Optional field for
      the purpose of ARP supression.
    </column>

  </table>

  <table name="Mcast_Macs_Local" title="Multicast MACs (local)">
    <p>
      Mapping of multicast MAC addresses to tunnels (physical
      locators). This table is written by the HSC, so it contains the
      MAC addresses that have been learned on physical ports by a
      VTEP. These may be learned by IGMP snooping, for example. This
      table also specifies how to handle unknown unicast and broadcast packets.
    </p>

    <column name="MAC">
      <p>
        A MAC address that has been learned by the VTEP.
      </p>
      <p>
        The keyword <code>unknown-dst</code> is used as a special
        ``Ethernet address'' that indicates the locations to which
        packets in a logical switch whose destination addresses do not
        otherwise appear in <ref table="Ucast_Macs_Local"/> (for
        unicast addresses) or <ref table="Mcast_Macs_Local"/> (for
        multicast addresses) should be sent.
      </p>
    </column>

    <column name="logical_switch">
      The Logical switch to which this mapping applies.
    </column>

    <column name="locator_set">
      The physical locator set to be used to reach this MAC address. In
      this table, the physical locator set will be contain one or more tunnel IP
      addresses of the appropriate VTEP(s).
    </column>

    <column name="ipaddr">
      The IP address to which this MAC corresponds. Optional field for
      the purpose of ARP supression.
    </column>
  </table>

  <table name="Mcast_Macs_Remote" title="Multicast MACs (remote)">
    <p>
      Mapping of multicast MAC addresses to tunnels (physical
      locators). This table is written by the NVC, so it contains the
      MAC addresses that the NVC has learned. This
      table also specifies how to handle unknown unicast and broadcast
      packets.
    </p>
    <p>
      Multicast packet replication may be handled by a service node,
      in which case the physical locators will be IP addresses of
      service nodes. If the VTEP supports replication onto multiple
      tunnels, using source node replication, then this may be used to
      replicate directly onto VTEP-hypervisor or VTEP-VTEP tunnels.
    </p>

    <column name="MAC">
      <p>
        A MAC address that has been learned by the NVC.
      </p>
      <p>
        The keyword <code>unknown-dst</code> is used as a special
        ``Ethernet address'' that indicates the locations to which
        packets in a logical switch whose destination addresses do not
        otherwise appear in <ref table="Ucast_Macs_Remote"/> (for
        unicast addresses) or <ref table="Mcast_Macs_Remote"/> (for
        multicast addresses) should be sent.
      </p>
    </column>

    <column name="logical_switch">
      The Logical switch to which this mapping applies.
    </column>

    <column name="locator_set">
      The physical locator set to be used to reach this MAC address. In
      this table, the physical locator set will be either a set of service
      nodes when service node replication is used or the set of transport
      nodes (defined as hypervisors or VTEPs) participating in the associated
      logical switch, when source node replication is used. When service node
      replication is used, the VTEP should send packets to one member of the
      locator set that is known to be healthy and reachable, which could be
      determined by BFD.  When source node replication is used, the VTEP
      should send packets to all members of the locator set.
    </column>

    <column name="ipaddr">
      The IP address to which this MAC corresponds. Optional field for
      the purpose of ARP supression.
    </column>

  </table>

  <table name="Logical_Router" title="A logical L3 router.">
    <p>
      A logical router, or VRF. A logical router may be connected to one or more
      logical switches. Subnet addresses and interface addresses may be configured on the
      interfaces.
    </p>

    <column name="switch_binding">
      Maps from an IPv4 or IPv6 address prefix in CIDR notation to a
      logical switch. Multiple prefixes may map to the same switch. By
      writing a 32-bit (or 128-bit for v6) address with a /N prefix
      length, both the router's interface address and the subnet
      prefix can be configured. For example, 192.68.1.1/24 creates a
      /24 subnet for the logical switch attached to the interface and
      assigns the address 192.68.1.1 to the router interface.
    </column>

    <column name="static_routes">
      One or more static routes, mapping IP prefixes to next hop IP addresses.
    </column>

    <column name="acl_binding">
      Maps ACLs to logical router interfaces. The router interfaces
      are indicated using IP address notation, and must be the same
      interfaces created in the <ref column="switch_binding"/>
      column. For example, an ACL could be associated with the logical
      router interface with an address of 192.68.1.1 as defined in the
      example above.
    </column>

    <group title="Identification">
      <column name="name">
        Symbolic name for the logical router.
      </column>
      
      <column name="description">
        An extended description for the logical router.
      </column>
    </group>

    <group title="Error Notification">
      <p>
        An entry in this column indicates to the NVC that the HSC has
        encountered a fault in configuring state related to the
        logical router.
      </p>
      <column name="LR_fault_status" key="invalid_ACL_binding">
        <p>
          Indicates that an error has occurred in associating an ACL
          with a logical router port.
        </p>
      </column>
      <column name="LR_fault_status" key="unspecified_fault">
        <p>
          Indicates that an error has occurred in configuring the
          logical router but that no
          more specific information is available.
        </p>
      </column>
    </group>

    <group title="Common Column">
      The overall purpose of this column is described under <code>Common
      Column</code> at the beginning of this document.

      <column name="other_config"/>
    </group>

  </table>

  <table name="Arp_Sources_Local" title="ARP source addresses for logical routers">
    <p>
      MAC address to be used when a VTEP issues ARP requests on behalf
      of a logical router.
    </p>

    <p>
      A distributed logical router is implemented by a set of VTEPs
      (both hardware VTEPs and vswitches). In order for a given VTEP
      to populate the local ARP cache for a logical router, it issues
      ARP requests with a source MAC address that is unique to the VTEP. A
      single per-VTEP MAC can be re-used across all logical
      networks. This table contains the MACs that are used by the
      VTEPs of a given HSC. The table provides the mapping from MAC to
      physical locator for each VTEP so that replies to the ARP
      requests can be sent back to the correct VTEP using the
      appropriate physical locator.
    </p>

    <column name="src_mac">
      The source MAC to be used by a given VTEP.
    </column>

    <column name="locator">
      The <ref table="Physical_Locator"/> to use for replies to ARP
      requests from this MAC address.
    </column>
  </table>

  <table name="Arp_Sources_Remote" title="ARP source addresses for logical routers">
    <p>
      MAC address to be used when a remote VTEP issues ARP requests on behalf
      of a logical router.
    </p>

    <p>
      This table is the remote counterpart of <ref
      table="Arp_sources_local"/>. The NVC writes this table to notify
      the HSC of the MACs that will be used by remote VTEPs when they
      issue ARP requests on behalf of a distributed logical router.
    </p>

    <column name="src_mac">
      The source MAC to be used by a given VTEP.
    </column>

    <column name="locator">
      The <ref table="Physical_Locator"/> to use for replies to ARP
      requests from this MAC address.
    </column>
  </table>

  <table name="Physical_Locator_Set">
    <p>
      A set of one or more <ref table="Physical_Locator"/>s.
    </p>

    <p>
      This table exists only because OVSDB does not have a way to
      express the type ``map from string to one or more <ref
      table="Physical_Locator"/> records.''
    </p>

    <column name="locators"/>
  </table>

  <table name="Physical_Locator">
    <p>
      Identifies an endpoint to which logical switch traffic may be
      encapsulated and forwarded.
    </p>

    <p>
      The <code>vxlan_over_ipv4</code> encapsulation, the only encapsulation
      defined so far, can use either tunnel key model described in the ``Per
      Logical-Switch Tunnel Key'' section in the <ref table="Logical_Switch"/>
      table.  When the tunnel key per <ref table="Logical_Switch"/> model is in
      use, the <ref table="Logical_Switch" column="tunnel_key"/> column in the
      <ref table="Logical_Switch"/> table is filled with a VNI and the <ref
      column="tunnel_key"/> column in this table is empty; in the
      key-per-tunnel model, the opposite is true.  The former model is older,
      and thus likely to be more widely supported.  See the ``Per
      Logical-Switch Tunnel Key'' section in the <ref table="Logical_Switch"/>
      table for further discussion of the model.
    </p>

    <column name="encapsulation_type">
      The type of tunneling encapsulation.
    </column>

    <column name="dst_ip">
      <p>
        For <code>vxlan_over_ipv4</code> encapsulation, the IPv4 address of the
        VXLAN tunnel endpoint.
      </p>

      <p>
        We expect that this column could be used for IPv4 or IPv6 addresses in
        encapsulations to be introduced later.
      </p>
    </column>

    <column name="tunnel_key">
      <p>
        This column is used only in the tunnel key per <ref
        table="Logical_Switch"/>+<ref table="Physical_Locator"/> model (see
        above).
      </p>

      <p>
        For <code>vxlan_over_ipv4</code> encapsulation, when the <ref
        table="Logical_Switch"/>+<ref table="Physical_Locator"/> model is in
        use, this column is the VXLAN VNI.  It must be in the range 0 to
        16,777,215.
      </p>
    </column>

  </table>
  <table name="ACL_entry">
    <p>
      Describes the individual entries that comprise an Access Control List.
    </p>
    <p>
      Each entry in the table is a single rule to match on certain
      header fields. While there are a large number of fields that can
      be matched on, most hardware cannot match on arbitrary
      combinations of fields. It is common to match on either L2
      fields (described below in the L2 group of columns) or L3/L4 fields
      (the L3/L4 group of columns) but not both. The hardware switch
      controller may log an error if an ACL entry requires it to match
      on an incompatible mixture of fields.
    </p>
    <column name="sequence">
      <p>
        The sequence number for the ACL entry for the purpose of
        ordering entries in an ACL. Lower numbered entries are matched
        before higher numbered entries.
      </p>
    </column>
    <group title="L2 fields">
      <column name="source_mac">
        <p>
          Source MAC address, in the form
          <var>xx</var>:<var>xx</var>:<var>xx</var>:<var>xx</var>:<var>xx</var>:<var>xx</var>
        </p>
      </column>
      <column name="dest_mac">
        <p>
          Destination MAC address, in the form
          <var>xx</var>:<var>xx</var>:<var>xx</var>:<var>xx</var>:<var>xx</var>:<var>xx</var>
        </p>
      </column>
      <column name="ethertype">
        <p>
          Ethertype in hexadecimal, in the form
          <var>0xAAAA</var>
        </p>
      </column>
    </group>
    <group title="L3/L4 fields">
      <column name="source_ip">
        <p>
          Source IP address, in the form
          <var>xx.xx.xx.xx</var> for IPv4 or appropriate
          colon-separated hexadecimal notation for IPv6.
        </p>
      </column>
      <column name="source_mask">
        <p>
          Mask that determines which bits of source_ip to match on, in the form
          <var>xx.xx.xx.xx</var> for IPv4 or appropriate
          colon-separated hexadecimal notation for IPv6.
        </p>
      </column>
      <column name="dest_ip">
        <p>
          Destination IP address, in the form
          <var>xx.xx.xx.xx</var> for IPv4 or appropriate
          colon-separated hexadecimal notation for IPv6.
        </p>
      </column>
      <column name="dest_mask">
        <p>
          Mask that determines which bits of dest_ip to match on, in the form
          <var>xx.xx.xx.xx</var> for IPv4 or appropriate
          colon-separated hexadecimal notation for IPv6.
        </p>
      </column>
      <column name="protocol">
        <p>
          Protocol number in the IPv4 header, or value of the "next
          header" field in the IPv6 header.
        </p>
      </column>
      <column name="source_port_min">
        <p>
          Lower end of the range of source port values. The value
          specified is included in the range.
        </p>
      </column>
      <column name="source_port_max">
        <p>
          Upper end of the range of source port values. The value
          specified is included in the range.
        </p>
      </column>
      <column name="dest_port_min">
        <p>
          Lower end of the range of destination port values. The value
          specified is included in the range.
        </p>
      </column>
      <column name="dest_port_max">
        <p>
          Upper end of the range of destination port values. The value
          specified is included in the range.
        </p>
      </column>
      <column name="tcp_flags">
        <p>
          Integer representing the value of TCP flags to match. For
          example, the SYN flag is the second least significant bit in
          the TCP flags. Hence a value of 2 would indicate that the "SYN"
          flag should be set (assuming an appropriate mask).
        </p>
      </column>
      <column name="tcp_flags_mask">
        <p>
          Integer representing the mask to apply when matching TCP
          flags. For example, a value of 2 would imply that the "SYN"
          flag should be matched and all other flags ignored.
        </p>
      </column>
      <column name="icmp_type">
        <p>
          ICMP type to be matched.
        </p>
      </column>
      <column name="icmp_code">
        <p>
          ICMP code to be matched.
        </p>
      </column>
    </group>
    <column name="direction">
      <p>
        Direction of traffic to match on the specified port, either
        "ingress" (toward the logical switch or router) or "egress"
        (leaving the logical switch or router).
      </p>
    </column>
    <column name="action">
      <p>
        Action to take for this rule, either "permit" or "deny".
      </p>
    </column>
    <group title="Error Notification">
      <p>
        An entry in this column indicates to the NVC that the ACL
        could not be configured as requested. The switch must clear this column when the error
        has been cleared.
      </p>
      <column name="acle_fault_status" key="invalid_acl_entry">
        <p>
          Indicates that an ACL entry requested by
          the controller could not be instantiated by the switch,
          e.g. because it requires an unsupported combination of
          fields to be matched.
        </p>
      </column>
      <column name="acle_fault_status" key="unspecified_fault">
        <p>
          Indicates that an error has occurred in configuring the ACL
          entry but no
          more specific information is available.
        </p>
      </column>
    </group>
  </table>
  <table name="ACL">
    <p>
      Access Control List table. Each ACL is constructed as a set of
      entries from the <ref table="ACL_entry"/> table. Packets that
      are not matched by any entry in the ACL are allowed by default.
    </p>
    <column name="acl_entries">
      <p>
        A set of references to entries in the <ref table="ACL_entry"/> table.
      </p>
    </column>
    <column name="acl_name">
      <p>
        A human readable name for the ACL, which may (for example) be displayed on
        the switch CLI.
      </p>
    </column>
    <group title="Error Notification">
      <p>
        An entry in this column indicates to the NVC that the ACL
        could not be configured as requested. The switch must clear this column when the error
        has been cleared.
      </p>
      <column name="acl_fault_status" key="invalid_acl">
        <p>
          Indicates that an ACL requested by
          the controller could not be instantiated by the switch,
          e.g., because it requires an unsupported combination of
          fields to be matched.
        </p>
      </column>
      <column name="acl_fault_status" key="resource_shortage">
        <p>
          Indicates that an ACL requested by
          the controller could not be instantiated by the switch due
          to a shortage of resources (e.g. TCAM space).
        </p>
      </column>
      <column name="acl_fault_status" key="unspecified_fault">
        <p>
          Indicates that an error has occurred in configuring the ACL
          but no
          more specific information is available.
        </p>
      </column>
    </group>
  </table>
</database>