Internet Engineering Task Force                            E. Haleplidis
Internet-Draft                                      University of Patras
Intended status: Experimental                                 J. Halpern
Expires: March 9, April 13, 2015                                         Ericsson
                                                       September 5,
                                                        October 10, 2014

                     ForCES Packet Parallelization
              draft-ietf-forces-packet-parallelization-02
              draft-ietf-forces-packet-parallelization-03

Abstract

   Forwarding and Control Element Separation (ForCES) defines an
   architectural framework and associated protocols to standardize
   information exchange between the control plane and the forwarding
   plane in a ForCES Network Element (ForCES NE).  RFC5812 has defined
   the ForCES Model provides a formal way to represent the capabilities,
   state, and configuration of forwarding elements within the context of
   the ForCES protocol (RFC 5810), so that control elements Control Elements (CEs) can
   control the FEs Forwarding Elements (FEs) accordingly.  More
   specifically, the model describes the logical functions that are
   present in an FE, what capabilities these functions support, and how
   these functions are or can be interconnected.

   Many network devices support parallel packet processing.  This
   document describes how ForCES can model a network device's
   parallelization datapath.

Status of This Memo

   This Internet-Draft is submitted in full conformance with the
   provisions of BCP 78 and BCP 79.

   Internet-Drafts are working documents of the Internet Engineering
   Task Force (IETF).  Note that other groups may also distribute
   working documents as Internet-Drafts.  The list of current Internet-
   Drafts is at http://datatracker.ietf.org/drafts/current/.

   Internet-Drafts are draft documents valid for a maximum of six months
   and may be updated, replaced, or obsoleted by other documents at any
   time.  It is inappropriate to use Internet-Drafts as reference
   material or to cite them other than as "work in progress."

   This Internet-Draft will expire on March 9, April 13, 2015.

Copyright Notice

   Copyright (c) 2014 IETF Trust and the persons identified as the
   document authors.  All rights reserved.

   This document is subject to BCP 78 and the IETF Trust's Legal
   Provisions Relating to IETF Documents
   (http://trustee.ietf.org/license-info) in effect on the date of
   publication of this document.  Please review these documents
   carefully, as they describe your rights and restrictions with respect
   to this document.  Code Components extracted from this document must
   include Simplified BSD License text as described in Section 4.e of
   the Trust Legal Provisions and are provided without warranty as
   described in the Simplified BSD License.

Table of Contents

   1.  Introduction  . . . . . . . . . . . . . . . . . . . . . . . .   3
     1.1.  Requirements Language . . . . . . . . . . . . . . . . . .   3
     1.2.  Definitions . . . . . . . . . . . . . . . . . . . . . . .   3
   2.  Packet Parallelization  . . . . . . . . . . . . . . . . . . .   4
     2.1.  Core parallelization LFB  . . . . . . . . . . . . . . . .   6
     2.2.  Parallelization metadata  . . . . . . . . . . . . . . . .   9
   3.  Parallel Base Types . . . . . . . . . . . . . . . . . . . . .   9
     3.1.  Frame Types . . . . . . . . . . . . . . . . . . . . . . .   9
     3.2.  Data Types  . . . . . . . . . . . . . . . . . . . . . . .  10
     3.3.  MetaData Types  . . . . . . . . . . . . . . . . . . . . .  10
   4.  Parallel LFBs . . . . . . . . . . . . . . . . . . . . . . . .  11
     4.1.  Splitter  . . . . . . . . . . . . . . . . . . . . . . . .  11
       4.1.1.  Data Handling . . . . . . . . . . . . . . . . . . . .  11
       4.1.2.  Components  . . . . . . . . . . . . . . . . . . . . .  12
       4.1.3.  Capabilities  . . . . . . . . . . . . . . . . . . . .  12
       4.1.4.  Events  . . . . . . . . . . . . . . . . . . . . . . .  12
     4.2.  Merger  . . . . . . . . . . . . . . . . . . . . . . . . .  12
       4.2.1.  Data Handling . . . . . . . . . . . . . . . . . . . .  13
       4.2.2.  Components  . . . . . . . . . . . . . . . . . . . . .  14
       4.2.3.  Capabilities  . . . . . . . . . . . . . . . . . . . .  14
       4.2.4.  Events  . . . . . . . . . . . . . . . . . . . . . . .  14
     4.3.  CoreParallelization . . . . . . . . . . . . . . . . . . .  15
       4.3.1.  Data Handling . . . . . . . . . . . . . . . . . . . .  15
       4.3.2.  Components  . . . . . . . . . . . . . . . . . . . . .  15
       4.3.3.  Capabilities  . . . . . . . . . . . . . . . . . . . .  15
       4.3.4.  Events  . . . . . . . . . . . . . . . . . . . . . . .  15
   5.  XML for Parallel LFB library  . . . . . . . . . . . . . . . .  16
   6.  Acknowledgements  Acknowledgments . . . . . . . . . . . . . . . . . . . . . . .  23
   7.  IANA Considerations . . . . . . . . . . . . . . . . . . . . .  24
     7.1.  LFB Class Names and LFB Class Identifiers . . . . . . . .  24
     7.2.  Metadata ID . . . . . . . . . . . . . . . . . . . . . . .  25

   8.  Security Considerations . . . . . . . . . . . . . . . . . . .  25
   9.  References  . . . . . . . . . . . . . . . . . . . . . . . . .  25
     9.1.  Normative References  . . . . . . . . . . . . . . . . . .  25
     9.2.  Informative References  . . . . . . . . . . . . . . . . .  26
   Authors' Addresses  . . . . . . . . . . . . . . . . . . . . . . .  26

1.  Introduction

   A lot of network devices can process packets in a parallel manner.
   The ForCES Forwarding and Control Element Separation (ForCES) Model
   [RFC5812] presents a formal way to describe the Forwarding Plane's
   datapath with Logical Function Blocks (LFBs) using XML.  This
   document describes how packet parallelization can be described with
   the ForCES model.

   The modelling modeling concept has been influenced by Cilc [Cilc].  Cilc Cilk [Cilk].  Cilk is a
   programming language that has been developed since 1994 at the MIT
   Laboratory to allow programmers to identify elements that can be
   executed in parallel.  The two Cilc Cilk concepts used in this document is
   spawn and sync.  Spawn being the place where parallel tasks can start
   and sync being the place where the parallel task finishes and must
   collect all parallel output.

   As task, we define a grouping of packets or pieces of a packet
   (chunks) that belong to the same original packet and are going to be
   processed in parallel.  All packets/chunks of the same task will be
   distinguished by an identifier, in the specific case we use a 32-bit
   identifier named task correlator.

   Being an experimental

   This document is in the experimental track and thus the LFB Class IDs cannot
   will not be included in the standard action's value and therefore values.  Therefore the
   LFB Class IDs must have a value of larger than 65535 and the LFB names
   must begin with the prefix 'Ext-'.  However for brevity, when we
   refer to the LFB Class names in the text of this document (not the
   formal definitions), we will omit the 'Ext-' prefix. prefix will be omitted.

1.1.  Requirements Language

   The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT",
   "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this
   document are to be interpreted as described in [RFC2119].

1.2.  Definitions

   This document follows the terminology defined by the ForCES Model in
   [RFC5812].  In particular, the reader is expected to be familiar with
   the following terms:

      FE

      CE

      FE Model

      LFB (Logical Functional Block) Class (or type)

      LFB Instance

      LFB Model

      Element

      Attribute

      LFB Metadata

      ForCES Component

      LFB Class Library

   This document also introduces the following terms:

      Chunk - Pieces of a packet

      Task - Grouping of packets or chunks belong to the same packet
      that are processed in parallel

      Task Correlator - A 32-bit identifier that uniquely distinguishes
      tasks

      Split Type - A parallel type where the packets are split into
      chunks to be processed in parallel.  Each task in a split type is
      composed only of chunks.

      Flood Type - A parallel type where the packets are copied as is to
      downstream LFBs to be processed in parallel.  Each task in a flood
      type is composed only of packets.

2.  Packet Parallelization

   This document addresses the following two types of packet
   parallelization:

   1.  Flood - where a copy of a packet is sent to multiple LFBs to be
       processed in parallel.

   2.  Split - where the packet will be split in equal size chunks
       specified by the CE and sent to multiple LFB instances probably
       of the same LFB class to be processed in parallel.

   It must be noted that the process of copying the packet in the Flood
   parallel type is implementation dependent and is loosely defined
   here.  An implementer may either decide to physical copy the packet
   and send all packets on the parallel paths, or may decide to
   logically copy the packet by simply sending, for example, pointers of
   the same packet provided that the necessary interlocks are taken into
   account.  The implementer has to take into account the device's
   characteristics to decide which approach fits best to the device.

   In the split parallel type, while harder, the implementer may also
   decide to logically split the packet and send, for example, pointers
   to parts of the packet, provided that the necessary interlocks are
   managed.  In addition, how chunks are distributed to the LFBs, e.g. e.g.,
   which chunk to which LFB, is implementation dependent.  For example
   while usually chunks are sent to the same LFB class, the number of
   LFB instances may not equal to the number of chunks.  It is up to the
   implementer to decide how these chunks will be sent, for example in a
   round-robin fashion.

   This document introduces two LFBs that are used in before and after
   the parallelization occurs:

   1.  Splitter - similar to Cilc's Cilk's spawn.  An LFB that will split the
       path of a packet which will be sent to multiple downstream LFBs
       to be processed in parallel.

   2.  Merger - similar to Cilc's Cilk's sync.  An LFB that will receive
       packets or chunks of the same initial packet and merge them and
       the results into one packet.

   Both parallel packet distribution types can currently be achieved
   with the ForCES model.  The splitter LFB has one group output that
   produces either chunks or packets to be sent to LFBs for processing
   and the merger LFB has one group input that expects either packets or
   chunks to aggregate all the parallel packets or chunks and produce a
   single packet.  Figure 1 shows a simple example of a split parallel
   datapath along with the splitter and merger LFB.  Figure 2 shows an
   example of a flood parallel datapath along with the splitter and
   merger LFB.

                      C1+M   +------------+  C1+M
                       +---->| Regex LFB  |----+
        +----------+   |     +------------+    |       +----------+
        |          |---+                       +------>|          |
     P  |          |  C2+M   +------------+  C2+M      |          | P
    --->| Splitter |-------->| Regex LFB  |----------->|  Merger  |--->
        |   LFB    |  CN+M   +------------+  CN+M      |   LFB    |
        |          |---+                       +------>|          |
        +----------+   |     +------------+    |       +----------+
                       +---->| Regex LFB  |----+
                             +------------+

                Figure 1: Simple split parallel processing

        +----------+    +------------+    +-------+    +----------+
        |          |P+M | Classifier |P+M | Meter |P+M |          |
     P  |          |--->|     LFB    |--->|  LFB  |--->|          | P
    --->| Splitter |    +------------+    +-------+    |  Merger  |--->
        |   LFB    |                                   |   LFB    |
        |          |P+M       +------------+       P+M |          |
        |          |--------->|  IPv4 TTL  |---------->|          |
        +----------+          |  Decrement |           +----------+
                              |    LFB     |
                              +------------+

                Figure 2: Simple flood parallel processing

   This version of the modelling modeling framework does not allow for nested
   parallel datapath topologies.  This decision was reached by the
   authors and the ForCES working group as there was no strong use case
   or need at decision time.  This led to a simpler metadata definition,
   which was needed to be transported between the splitter and the
   corresponding merger.  If there is a need for nested parallel
   datapaths a new version of a splitter and merger will be needed to be
   defined as well as an augmentation to the defined metadata.

2.1.  Core parallelization LFB

   One important element to a developer is the ability to define which
   LFBs can be used in a parallel mode, which LFBs can be parallelized
   with which as well as the order in which parallel LFBs can be
   assembled.

   To access the parallelization details, we opted for defining a new
   LFB class - the CoreParallelization LFB.  This choice was an
   alternative to making another change to the core FEObject LFB.  The
   CoreParallelization exists merely to define the capabilities for an
   FE's LFB parallelization.  A CE using the ForCES Protocol [RFC5810]
   can check the existence of this LFB class in the FEObject's
   SupportedLFBs component.  The existence of the CoreParallelization
   LFB will indicate to the CE that the specific FE supports
   parallelization.  There MUST be only one instance of the
   CoreParallelization LFB per FE.

   The topology of the parallel datapath can be deferred and manipulated
   from the FEObject LFB's LFBTopology.

   The CoreParallelization requires only one capability in order to
   specify each LFB that can be used in a parallel mode:

   o  The Name of the LFB.

   o  The Class ID of the LFB.

   o  The Version of the LFB.

   o  The number of instances that class can support in parallel.

   o  A list of LFB classes that can follow this LFB class in a pipeline
      for a parallel path.

   o  A list of LFB classes that can exist before this LFB class in a
      pipeline for a parallel path.

   o  A list of LFB classes that can process packets or chunks in
      parallel with this LFB class.

       <!-- Datatype -->
       <dataTypeDef>
          <name>ParallelLFBType</name>
          <synopsis>Table entry for parallel LFBs</synopsis>
          <struct>
             <component componentID="1">
                <name>LFBName</name>
                <synopsis>The name of an LFB Class</synopsis>
                <typeRef>string</typeRef>
             </component>
             <component componentID="2">
                <name>LFBClassID</name>
                <synopsis>The id of the LFB Class</synopsis>
                <typeRef>uint32</typeRef>
             </component>
             <component componentID="3">
                <name>LFBVersion</name>
                <synopsis>The version of the LFB Class used by this FE
                </synopsis>
                <typeRef>string</typeRef>
             </component>
             <component componentID="4">
                <name>LFBParallelOccurenceLimit</name>
                <name>LFBParallelOccurrenceLimit</name>
                <synopsis>The upper limit of instances of the same
                   parallel LFBs of this class</synopsis>
                <optional />
                <typeRef>uint32</typeRef>
             </component>
             <component componentID="5">
                <name>AllowedParallelAfters</name>
                <synopsis>List of LFB Classes that can follow this LFB
                   in a parallel pipeline</synopsis>
                <optional />
                <array>
                   <typeRef>uint32</typeRef>
                </array>
             </component>
             <component componentID="6">
                <name>AllowedParallelBefores</name>
                <synopsis>List of LFB Classes that this LFB class can
                   follow in a parallel pipeline</synopsis>
                <optional />
                <array>
                   <typeRef>uint32</typeRef>
                </array>
             </component>
             <component componentID="7">
                <name>AllowedParallel</name>
                <synopsis>List of LFB Classes that this LFB class be run
                   in parallel with</synopsis>
                <array>
                   <typeRef>uint32</typeRef>
                </array>
             </component>
          </struct>
       </dataTypeDef>

       <!-- Capability -->
             <capability componentID="32">
                <name>ParallelLFBs</name>
                <synopsis>List of all supported parallel LFBs</synopsis>
                <array type="Variable-size">
                   <typeRef>ParallelLFBType</typeRef>
                </array>
             </capability>

           Figure 3: XML Definitions for CoreParallelization LFB

2.2.  Parallelization metadata

   It is expected that the splitting and merging mechanisms are an
   implementation issue.  This document plays the role of defining the
   operational parameters for the splitting and merging, namely, the
   size of the chunks, what happens if a packet or chunk has been marked
   as invalid and whether the merge LFB should wait for all packets or
   chunks to arrive.  The following metadata set is defined as a struct:

   1.  ParallelType - Flood or split

   2.  TaskCorrelator - Identify packets or chunks that belonged to the
       initial packet that entered the Splitter LFB

   3.  ParallelNum - Sequence Number of the packet or the chunk for a
       specific task.

   4.  ParralelPartsCount - Total number of packets or chunks for a
       specific task.

   This metadata is produced from the Splitter LFB and is opaque to LFBs
   in parallel paths and is passed along to the merger LFB without being
   consumed.

   In the case in which an LFB decides that a packet/chunk has to be
   dropped, the LFB MAY drop the packet/chunk but the metadata MUST be
   sent to the Merger LFB's InvalidIn input port for merging purposes.

   Additional metadata produced by LFBs inside a datapath MAY be
   aggregated within the Merger LFB and sent on after the merging
   process.  In case of receiving the same metadata definition with
   multiple values the merger LFB MUST keep the first received from a
   valid packet or chunk.

3.  Parallel Base Types

3.1.  Frame Types

   One frame type has been defined in this library.

   +---------------+---------------------------------------------------+
   | Frame Type    | Synopsis                                          |
   | Name          |                                                   |
   +---------------+---------------------------------------------------+
   | Chunk         | A chunk is a frame that is part of an original    |
   |               | larger frame                                      |
   +---------------+---------------------------------------------------+

                           Parallel Frame Types

3.2.  Data Types

   One data type has been defined in this library.

   +---------------+------------------------+--------------------------+
   | DataType Name | Type                   | Synopsis                 |
   +---------------+------------------------+--------------------------+
   | ParallelTypes | Atomic uchar. Special  | The type of              |
   |               | Values Flood (0),      | parallelization this     |
   |               | Split (1).             | packet will go through   |
   +---------------+------------------------+--------------------------+

                            Parallel Data Types

3.3.  MetaData Types

   The following metadata structure with ID 16, using the ForCES model
   extension [I-D.ietf-forces-model-extension], is defined for the
   parallelization library:

   +--------------------+--------+----+--------------------------------+
   |   Metadata Name    |  Type  | ID |            Synopsis            |
   +--------------------+--------+----+--------------------------------+
   |    ParallelType    | uchar  | 1  |  The type of parallelization   |
   |                    |        |    | this packet will go through. 0 |
   |                    |        |    |    for flood, 1 for split.     |
   |                    |        |    |                                |
   |   TaskCorrelator   | uint32 | 2  |  An identification number to   |
   |                    |        |    |   specify that a packet or a   |
   |                    |        |    |   chunks belongs to the same   |
   |                    |        |    |         parallel task.         |
   |                    |        |    |                                |
   |    ParallelNum     | uint32 | 3  |    Defines the number of a     |
   |                    |        |    | specific packet or chunk of a  |
   |                    |        |    |         specific task.         |
   |                    |        |    |                                |
   | ParallelPartsCount | uint32 | 4  |  Defines the total number of   |
   |                    |        |    |    packets or chunks for a     |
   |                    |        |    |         specific task.         |
   +--------------------+--------+----+--------------------------------+

                      Metadata Structure for Merging

4.  Parallel LFBs

4.1.  Splitter

   The splitter LFB takes part in parallelizing the processing datapath
   by sending either the same packet Figure 2 or chunks Figure 1 of the
   same packet to multiple LFBs.

                             +---------------+
                  SplitterIn |               | SplitterOut
                  ---------->| Splitter LFB  |------------->
                             |               |
                             +---------------+

                          Figure 4: Splitter LFB

4.1.1.  Data Handling

   The splitter LFB receives any kind of packet via the singleton input,
   Input.  Depending upon the CE's configuration of the ParallelType
   component, if the parallel type is of type flood (0), the same packet
   MUST be sent through all of the group output SplitterOut's instances.
   If the parallel type is of type split (1), the packet will be split
   into same size chunks except the last which MAY be smaller, with the
   max size being defined by the ChunkSize component.  Chunks MAY be
   sent out in a round-robin fashion through the group output
   ParallelOut's instances or in any other way defined by the
   implementer.  Each packet or chunk will be accompanied by the
   following metadata set as a struct:

   o  ParallelType - The parallel type, split or flood.

   o  ParallelID - generated by the splitter LFB to identify that chunks
      or packets belong to the same parallel task.

   o  ParallelNum - each chunk or packet of a parallel id will be
      assigned a number in order for the merger LFB to know when it has
      gathered them all along with the ParallelPartsCount metadata.

   o  ParallelPartsCount - the number of chunks or packets for the
      specific task.

4.1.2.  Components

   The splitter LFB has only two components.  The first is the
   ParallelType, an uint32 that defines how the packet will be processed
   by the Splitter LFB.  The second is the ChunkSize, an uint32 that
   specifies the size of each chunk when a packet is split into multiple
   same size chunks.  The last chunk MAY be smaller than the value of
   the ChunkSize.

4.1.3.  Capabilities

   This LFB has only one capability specified, the MinMaxChunkSize a
   struct of two uint32 to specify the minimum and maximum chunk size.

4.1.4.  Events

   This LFB has no events specified.

4.2.  Merger

   The merger LFB is the synchronization point for multiple packets or
   packet chunks of the same task, emanating out of the parallel path as
   illustrated in Figure 2 and Figure 1.

                               +-------------+
                      MergerIn |             |
                     --------->|             | MergerOut
                               | Merger LFB  |----------->
                     InvalidIn |             |
                     --------->|             |
                               +-------------+

                           Figure 5: Merger LFB

4.2.1.  Data Handling

   The merger LFB receives either a packet or a chunk via the group
   input ParallelIn, along with the ParallelType metadata that, the
   TaskCorrelator, the ParallelNum and the ParallelPartsCount.

   In case that an upstream LFB has dropped a packet or a chunk the
   merger LFB MAY receive only the metadata or both metadata and packet
   or chunk through the InvalidIn group input port.  It SHOULD receive a
   metadata specifying the error code.  Currently defined metadata's in
   the Base LFB Library [RFC6956] are the ExceptionID and the
   ValidateErrorID.

   If the MergeWaitType is set to false the Merger LFB will initiate the
   merge process upon receiving the first packet.  If false, for each
   task identified by the task correlator, it will wait for all packets/
   chunks to arrive unless the MergeWaitTimeoutTimer timer expires.  If
   the MergeWaitTimeoutTimer has expired, the Merger MUST consider the
   rest of the packets/chuncks, that have not been received, as invalid
   and MUST handle the packets according to the InvalidAction value.

   If one packet or chunk has been received through the InvalidIn port
   then the merging procedure will handle the packets/chuncks according
   to the InvalidAction value.  If the InvalidAction component has been
   set to 0 then if one packet or chunk is not valid all will dropped,
   else the process will initiate.  Once the merging process has been
   completed the resulting packet will be sent via the singleton output
   port MergerOut.

   If the Merger LFB receives different values for the same metadata
   from different packets or chunks that has the same task correlator
   then the Merger LFB will use the first metadata from a packet or
   chunk that entered the LFB through the MergerIn input port.

4.2.2.  Components

   This LFB has the following components specified:

   1.  InvalidAction - a uchar defining what the Merge LFB will do if an
       invalid chunk or packet is received.  If set to 0 (DropAll) the
       merge will be considered invalid and all chunks or packets will
       be dropped.  If set to 1 (Continue) the merge will continue.

   2.  MergeWaitTimeoutTimer - a uint32 defining the amount of time time, in
       milliseconds, that the Merger will wait for all packets or
       chuncks within the same task to arrive before considering them
       invalid.  The MergeWaitTimeoutTimer starts as soon as the first
       chunk or packet of a parallel task arrives.

   3.  MergeWaitType - a boolean.  If true the Merger LFB will wait for
       all packets or chunks to be received prior to performing the
       merge.  If false, when one packet or a chunk with a response is
       received by the merge LFB it will start with the merge process.

   4.  InvalidMergesCounter - a uint32 that counts the number of merges
       where there is at least one packet or chunk that entered the
       merger LFB through the InvalidIn input port.

   5.  InvalidTotalCounter - a uint 32 uint32 that counts the number of merges
       where all packets/chunks entered the merger LFB through the
       InvalidIn input port.

   6.  InvalidIDCounters - a struct of two arrays.  Each array has a
       uint32 per row.  Each array counts number of invalid merges where
       at least one packet or chunk entered through InvalidID per error
       ID.  The first array is the InvalidExceptionID and the second is
       the InvalidValidateErrorID.

4.2.3.  Capabilities

   This LFB has no capabilities specified.

4.2.4.  Events

   This LFB specifies only two event.  The first detects whether the
   InvalidMergesCounter has exceeded a specific value and the second
   detects whether the InvalidAllCounter has exceeded a specific value.
   Both error reports will send the respective counter value.  Event
   Filters can be used to limit the number of messages

4.3.  CoreParallelization

   A core LFB that specifies that the FE supports parallelization,
   instead of updating the FEObject LFB

4.3.1.  Data Handling

   The CoreParallelization does not handle data.

4.3.2.  Components

   This LFB has no components specified.

4.3.3.  Capabilities

   This LFB has only one capability specified.  The ParallelLFBs is a
   table which lists all the LFBs that can be parallelized.  Each row of
   the table contains:

   1.  LFBName - a string.  The Name of the parallel LFB.

   2.  LFBClassID - a uint32.  The Class ID of the parallel LFB.

   3.  LFBVersion - a string.  The Version of the parallel LFB.

   4.  LFBParallelOccurenceLimit  LFBParallelOccurrenceLimit - a uint32.  The upper limit of
       instances of the same parallel LFBs of this class.

   5.  AllowedParallelAfters - a table of uint32s (LFB Class IDs).  A
       list of LFB classes that can follow this LFB class in a pipeline
       for a parallel path.

   6.  AllowedParallelBefores - a table of uint32s (LFB Class IDs).  A
       list of LFB classes that can exist before this LFB class in a
       pipeline for a parallel path.

   7.  AllowedParallel - a table of uint32s (LFB Class IDs).  A list of
       LFB classes that can process packets or chunks in parallel with
       this LFB class.

4.3.4.  Events

   This LFB specifies no events

5.  XML for Parallel LFB library

  <?xml version="1.0" encoding="UTF-8"?>
  <LFBLibrary xmlns="urn:ietf:params:xml:ns:forces:lfbmodel:1.0" xmlns="urn:ietf:params:xml:ns:forces:lfbmodel:1.1"
     xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
     xsi:schemaLocation="urn:ietf:params:xml:ns:forces:lfbmodel:1.0"
     xsi:schemaLocation="urn:ietf:params:xml:ns:forces:lfbmodel:1.1"
     provides="Parallel">
    <load library="BaseTypeLibrary" location="BaseTypeLibrary.LFB"/>
    <frameDefs>
      <frameDef>
        <name>Chunk</name>
        <synopsis>A chunk is a frame that is part of an original
              larger frame</synopsis>
      </frameDef>
    </frameDefs>
    <dataTypeDefs>
      <dataTypeDef>
        <name>ParallelTypes</name>
        <synopsis>The type of parallelization this packet will go
              through</synopsis>
        <atomic>
          <baseType>uchar</baseType>
          <specialValues>
            <specialValue value="0">
              <name>Flood</name>
              <synopsis>The packet/chunk has been sent as a whole
                       to multiple recipients</synopsis>
            </specialValue>
            <specialValue value="1">
              <name>Split</name>
              <synopsis>The packet/chunk has been split into
                       multiple chunks and sent to recipients</synopsis>
            </specialValue>
          </specialValues>
        </atomic>
      </dataTypeDef>
      <dataTypeDef>
        <name>ParallelLFBType</name>
        <synopsis>Table entry for parallel LFBs</synopsis>
        <struct>
          <component componentID="1">
            <name>LFBName</name>
            <synopsis>The name of an LFB Class</synopsis>
            <typeRef>string</typeRef>
          </component>
          <component componentID="2">
            <name>LFBClassID</name>
            <synopsis>The id of the LFB Class</synopsis>
            <typeRef>uint32</typeRef>
          </component>
          <component componentID="3">
            <name>LFBVersion</name>
            <synopsis>The version of the LFB Class used by this FE
               </synopsis>
            <typeRef>string</typeRef>
          </component>
          <component componentID="4">
            <name>LFBParallelOccurenceLimit</name>
            <name>LFBParallelOccurrenceLimit</name>
            <synopsis>The upper limit of instances of the same
                  parallel LFBs of this class</synopsis>
            <optional/>
            <typeRef>uint32</typeRef>
          </component>
          <component componentID="5">
            <name>AllowedParallelAfters</name>
            <synopsis>List of LFB Classes that can follow this LFB
                  in a parallel pipeline</synopsis>
            <optional/>
            <array>
              <typeRef>uint32</typeRef>
            </array>
          </component>
          <component componentID="6">
            <name>AllowedParallelBefores</name>
            <synopsis>List of LFB Classes that this LFB class can
                  follow in a parallel pipeline</synopsis>
            <optional/>
            <array>
              <typeRef>uint32</typeRef>
            </array>
          </component>
          <component componentID="7">
            <name>AllowedParallel</name>
            <synopsis>List of LFB Classes that this LFB class be run
                  in parallel with</synopsis>
            <array>
              <typeRef>uint32</typeRef>
            </array>
          </component>
        </struct>
      </dataTypeDef>
    </dataTypeDefs>
    <metadataDefs>
      <metadataDef>
        <name>ParallelMetadataSet</name>
        <synopsis>A metadata Set for parallelization related LFBs
           </synopsis>
        <metadataID>32</metadataID>
        <struct>
          <component componentID="1">
            <name>ParallelType</name>
            <synopsis>The type of parallelization this packet/chunk
                    has gone through</synopsis>
            <typeRef>ParallelTypes</typeRef>
          </component>
          <component componentID="2">
            <name>TaskCorrelator</name>
            <synopsis>An identification number to specify that
                    packets or chunks originate from the same packet.
                 </synopsis>
            <typeRef>uint32</typeRef>
          </component>
          <component componentID="3">
            <name>ParallelNum</name>
            <synopsis>Defines the number of the specific packet or
                    chunk of the specific parallel ID.</synopsis>
            <typeRef>uint32</typeRef>
          </component>
          <component componentID="4">
            <name>ParallelPartsCount</name>
            <synopsis>Defines the total number of packets or chunks
                    for the specific parallel ID.</synopsis>
            <typeRef>uint32</typeRef>
          </component>
        </struct>
      </metadataDef>
    </metadataDefs>
    <LFBClassDefs>
      <LFBClassDef LFBClassID="65537">
        <name>Ext-Splitter</name>
        <synopsis>A splitter LFB takes part in parallelizing the
              processing datapath. It will either send the same packet
              or chunks of one packet to multiple LFBs</synopsis>
        <version>1.0</version>
        <inputPorts>
          <inputPort>
            <name>SplitterIn</name>
            <synopsis>An input port expecting any kind of frame
                 </synopsis>
            <expectation>
              <frameExpected>
                <ref>Arbitrary</ref>
              </frameExpected>
            </expectation>

          </inputPort>
        </inputPorts>
        <outputPorts>
          <outputPort group="true">
            <name>SplitterOut</name>
            <synopsis>A parallel output port that sends the same
                    packet to all output instances or chunks of the same
                    packet different chunk on each instance.</synopsis>
            <product>
              <frameProduced>
                <ref>Arbitrary</ref>
                <ref>Chunk</ref>
              </frameProduced>
              <metadataProduced>
                <ref>ParallelMetadataSet</ref>
              </metadataProduced>
            </product>
          </outputPort>
        </outputPorts>
        <components>
          <component componentID="1" access="read-write">
            <name>ParallelType</name>
            <synopsis>The type of parallelization this packet will
                    go through</synopsis>
            <typeRef>ParallelTypes</typeRef>
          </component>
          <component componentID="2" access="read-write">
            <name>ChunkSize</name>
            <synopsis>The size of a chunk when a packet is split
                    into multiple same size chunks</synopsis>
            <typeRef>uint32</typeRef>
          </component>
        </components>
        <capabilities>
          <capability componentID="31">
            <name>MinMaxChunkSize</name>
            <synopsis>The minimum and maximum size of a chunk
                    capable of split by this LFB</synopsis>
            <struct>
              <component componentID="1">
                <name>MinChunkSize</name>
                <synopsis>Minimum chunk size</synopsis>
                <optional/>
                <typeRef>uint32</typeRef>
              </component>
              <component componentID="2">
                <name>MaxChunkSize</name>
                <synopsis>Maximum chunk size</synopsis>
                <typeRef>uint32</typeRef>
              </component>
            </struct>
          </capability>
        </capabilities>
      </LFBClassDef>
      <LFBClassDef LFBClassID="65538">
        <name>Ext-Merger</name>
        <synopsis>A merger LFB receives multiple packets or multiple
              chunks of the same packet and merge them into one merged
              packet</synopsis>
        <version>1.0</version>
        <inputPorts>
          <inputPort group="true">
            <name>MergerIn</name>
            <synopsis>A parallel input port that accepts packets
                    or chunks from all output instances</synopsis>
            <expectation>
              <frameExpected>
                <ref>Arbitrary</ref>
                <ref>Chunk</ref>
              </frameExpected>
              <metadataExpected>
                <ref>ParallelMetadataSet</ref>
              </metadataExpected>
            </expectation>
          </inputPort>
          <inputPort group="true">
            <name>InvalidIn</name>
            <synopsis>When a packet is sent out of an error port of
                    an LFB in a parallel path will be sent to this
                    output port in the Merger LFB</synopsis>
            <expectation>
              <frameExpected>
                <ref>Arbitrary</ref>
                <ref>Chunk</ref>
              </frameExpected>
              <metadataExpected>
                <one-of>
                  <ref>ExceptionID</ref>
                  <ref>ValidateErrorID</ref>
                </one-of>
              </metadataExpected>
            </expectation>
          </inputPort>
        </inputPorts>
        <outputPorts>
          <outputPort>
            <name>MergerOut</name>
            <synopsis>An output port expecting any kind of frame
                 </synopsis>
            <product>
              <frameProduced>
                <ref>Arbitrary</ref>
              </frameProduced>
            </product>
          </outputPort>
        </outputPorts>
        <components>
          <component componentID="1" access="read-write">
            <name>InvalidAction</name>
            <synopsis>What the Merge LFB will do if an invalid
                    chunk or packet is received</synopsis>
            <atomic>
              <baseType>uchar</baseType>
              <specialValues>
                <specialValue value="0">
                  <name>DropAll</name>
                  <synopsis>Drop all packets or chunks
                          </synopsis>
                </specialValue>
                <specialValue value="1">
                  <name>Continue</name>
                  <synopsis>Continue with the merge</synopsis>
                </specialValue>
              </specialValues>
            </atomic>
          </component>
          <component componentID="2" access="read-write">
            <name>MergeWaitType</name>
            <synopsis>Whether the Merge LFB will wait for all
                    packets or chunks to be received prior to sending
                    out a response</synopsis>
            <typeRef>boolean</typeRef>
          </component>
          <component componentID="3" access="read-write">
            <name>MergeWaitTimeoutTimer</name>
            <synopsis>The time that the Merger will wait
            for all packets or chuncks within the same task to arrive
            before considering them invalid.</synopsis>
            <typeRef>uint32</typeRef>
          </component>
          <component componentID="4" access="read-reset">
            <name>InvalidMergesCounter</name>
            <synopsis>Counts the number of merges where there is at
                    least one packet/chunk that entered the merger LFB
                    through the InvalidIn input port</synopsis>
            <typeRef>uint32</typeRef>
          </component>
          <component componentID="5" access="read-reset">
            <name>InvalidTotalCounter</name>
            <synopsis>Counts the number of merges where all
                    packets/chunks entered the merger LFB through the
                    InvalidIn input port</synopsis>
            <typeRef>uint32</typeRef>
          </component>
          <component componentID="6" access="read-reset">
            <name>InvalidIDCounters</name>
            <synopsis>Counts number of invalid merges where at
                    least one packet/chunk entered through InvalidID per
                    error ID</synopsis>
            <struct>
              <component componentID="1">
                <name>InvalidExceptionID</name>
                <synopsis>Per Exception ID</synopsis>
                <array>
                  <typeRef>uint32</typeRef>
                </array>
              </component>
              <component componentID="2">
                <name>InvalidValidateErrorID</name>
                <synopsis>Per Validate Error ID</synopsis>
                <array>
                  <typeRef>uint32</typeRef>
                </array>
              </component>
            </struct>
          </component>
        </components>
        <events baseID="30">
          <event eventID="1">
            <name>ManyInvalids</name>
            <synopsis>An event that specifies if there are too many
                    invalids</synopsis>
            <eventTarget>
              <eventField>InvalidCounter</eventField>
            </eventTarget>
            <eventGreaterThan/>
            <eventReports>
              <eventReport>
                <eventField>InvalidMergesCounter</eventField>
              </eventReport>
            </eventReports>
          </event>
          <event eventID="2">
            <name>ManyTotalInvalids</name>
            <synopsis>An event that specifies if there are too many
                    invalids</synopsis>
            <eventTarget>
              <eventField>InvalidTotalCounter</eventField>
            </eventTarget>
            <eventGreaterThan/>
            <eventReports>
              <eventReport>
                <eventField>InvalidTotalCounter</eventField>
              </eventReport>
            </eventReports>
          </event>
        </events>
      </LFBClassDef>
      <LFBClassDef LFBClassID="65539">
        <name>Ext-CoreParallelization</name>
        <synopsis>A core LFB that specifies that the FE supports
          parallelization, instead of updating the FEObject
          LFB</synopsis>
        <version>1.0</version>
        <capabilities>
          <capability componentID="10">
            <name>ParallelLFBs</name>
            <synopsis>A table which lists all the LFBs that can be
                parallelized</synopsis>
            <array>
              <typeRef>ParallelLFBType</typeRef>
            </array>
          </capability>
        </capabilities>
      </LFBClassDef>
    </LFBClassDefs>
  </LFBLibrary>

                      Figure 6: Parallel LFB library

6.  Acknowledgements  Acknowledgments

   The authors would like to thank Edward Crabbe for the initial
   discussion that led to the creation of this document and Jamal Hadi
   Salim and Dave Hood for comments and discussions that made this
   document better.  Additionally Adrian Farrel for his AD review.
   Finally Francis Dupont for his Gen-Art review and Magnus Nystroem for
   his security review which refined this document to its final shape.

7.  IANA Considerations

7.1.  LFB Class Names and LFB Class Identifiers

   LFB classes defined by this document do not belong to LFBs defined by
   Standards Track RFCs in the http://www.iana.org/assignments/forces/
   forces.xml http://www.iana.org/assignments/forces
   registry.  As such the values defined in this document are in the
   above 65535 value range.

   This specification includes the following LFB class names and LFB
   class identifiers:

   +----------+--------------------+--------+---------------+----------+
   |   LFB    |   LFB Class Name   | LFB Ve |  Description  | Referenc |
   | Class Id |                    | rsion  |               |    e     |
   | entifier |                    |        |               |          |
   +----------+--------------------+--------+---------------+----------+
   |  65537   |    Ext-Splitter    |  1.0   |   A splitter  |   This   |
   |          |                    |        |    LFB will   | document |
   |          |                    |        |  either send  |          |
   |          |                    |        |    the same   |          |
   |          |                    |        |   packet or   |          |
   |          |                    |        | chunks of one |          |
   |          |                    |        |   packet to   |          |
   |          |                    |        |    multiple   |          |
   |          |                    |        |     LFBs.     |          |
   |          |                    |        |               |          |
   |  65538   |     Ext-Merger     |  1.0   |  A merger LFB |   This   |
   |          |                    |        |    receives   | document |
   |          |                    |        |    multiple   |          |
   |          |                    |        |   packets or  |          |
   |          |                    |        |    multiple   |          |
   |          |                    |        | chunks of the |          |
   |          |                    |        |  same packet  |          |
   |          |                    |        |   and merge   |          |
   |          |                    |        |   them into   |          |
   |          |                    |        |      one.     |          |
   |          |                    |        |               |          |
   |  65539   | Ext-CoreParalleliz |  1.0   | A core LFB to |   This   |
   |          |       ation        |        | signify the p | document |
   |          |                    |        | arallelizatio |          |
   |          |                    |        |  n capability |          |
   +----------+--------------------+--------+---------------+----------+

     Logical Functional Block (LFB) Class Names and Class Identifiers

7.2.  Metadata ID

   The Metadata ID namespace is 32 bits long.  Values assigned by this
   specification are:

           +------------+---------------------+---------------+
           |   Value    |         Name        |   Definition  |
           +------------+---------------------+---------------+
           | 0x00000010 | ParallelMetadataSet | This document |
           +------------+---------------------+---------------+

                Metadata ID assigned by this specification

8.  Security Considerations

   This document does not alter either the ForCES model [RFC5812] or the
   ForCES protocol [RFC5810] and as such has no impact on their security
   considerations.  This document simply defines the operational
   parameters and capabilities of LFBs that perform parallelization and
   not how parallelization is implemented.  However as parallezation
   tasks have security issues, a designer  Finally, this document does
   not attempt to analyze the presence or an implementer must take
   into account any possibility of security considerations that regards packet
   parallelization.
   interactions created by allowing parallel operations on packets.  Any
   such issues, if they exist, are for the designers of the particular
   data path, not the general mechanism.

9.  References

9.1.  Normative References

   [I-D.ietf-forces-model-extension]
              Haleplidis, E., "ForCES Model Extension", draft-ietf-
              forces-model-extension-04
              forces-model-extension-05 (work in progress), August September
              2014.

   [RFC2119]  Bradner, S., "Key words for use in RFCs to Indicate
              Requirement Levels", BCP 14, RFC 2119, March 1997.

   [RFC5810]  Doria, A., Hadi Salim, J., Haas, R., Khosravi, H., Wang,
              W., Dong, L., Gopal, R., and J. Halpern, "Forwarding and
              Control Element Separation (ForCES) Protocol
              Specification", RFC 5810, March 2010.

   [RFC5812]  Halpern, J. and J. Hadi Salim, "Forwarding and Control
              Element Separation (ForCES) Forwarding Element Model", RFC
              5812, March 2010.

   [RFC6956]  Wang, W., Haleplidis, E., Ogawa, K., Li, C., and J.
              Halpern, "Forwarding and Control Element Separation
              (ForCES) Logical Function Block (LFB) Library", RFC 6956,
              June 2013.

9.2.  Informative References

   [Cilc]

   [Cilk]     MIT, "Cilk language",
              <http://supertech.csail.mit.edu/cilk/>.

Authors' Addresses

   Evangelos Haleplidis
   University of Patras
   Department of Electrical and Computer Engineering
   Patras  26500
   Greece

   Email: ehalep@ece.upatras.gr

   Joel Halpern
   Ericsson
   P.O. Box 6049
   Leesburg  20178 VA  20178
   USA

   Phone: +1 703 371 3043
   Email: joel.halpern@ericsson.com