| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
Ticket: HICN-841
Change-Id: I4c5684db936835a0748715680cfbbc22ada642ff
Signed-off-by: Mauro Sardara <msardara@cisco.com>
|
|
Change-Id: I556bd8c44f0ff7a631a0df34b498ffd7952fcf4a
Signed-off-by: Mauro Sardara <msardara@cisco.com>
|
|
this task cover a large part of the codebase and involves several changes:
- the library provides a name data structure (hicn_name_t ), which is composed
of a name prefix (hicn_name_prefix_t) and a name suffix (hicn_name_suffix_t),
and it has been extended to provide all support functions required for name
manipulation, including common prefix computation, as required for the Longest
Prefix Match (LPM)in the forwarder, in addition to Exact Prefix Match (EPM).
- all code has been rewritten to use this data structure instead of having for
instance the forwarder define its own name class (used to be Name and NameBitVector)
the code has been refactored to minimize name allocations and copies, one remaining
aspect is the difference of name storage between PIT and CS entries (respectively
in the PIT entry, and in the message buffer), which causes the packet cache
index to be updated when a PIT entry is converted into a CS entry. By storing
the name in the PIT/CS entry everytime, we might save on this operation).
- hicn-light FIB has been rewritten : code has been refactored and should now be
shorter and documented; unit tests have been drafted but more would be required
to cover all cases and match the algorithms to add/remove nodes, as specified in the doc.
all protocol details and hICN header formats are now abstracted by the library
for the forwarder (and thus header.h and protocols/*.h have been removed from
public includes, and replaced by packet.h providing protocol agnostic packet
level functions, completely replacing the compat.h header that used to provide
similar functions.
- this works by exposing a opaque buffer to the application (a kind of socket buffer)
which is used by the lib to cache the packet format and offsets of the different
layers in the buffer and provider efficient operations (the packet format is
either defined for packet construction, or guessed at ingress, and this structure
is updated accordingly only once).
Co-authored-by: Jordan Augé <jordan.auge+fdio@cisco.com>
Signed-off-by: Luca Muscariello <muscariello@ieee.org>
Change-Id: I31e321897f85f0267fe8ba4720363c180564492f
|
|
- move infra data structure into the shared lib
- new packet cache using double hashing and lookup on prefix suffix
- testing updates
- authenticated requests using interest manifests
Co-authored-by: Mauro Sardara <msardara@cisco.com>
Co-authored-by: Jordan Augé <jordan.auge+fdio@cisco.com>
Co-authored-by: Michele Papalini <micpapal@cisco.com>
Co-authored-by: Olivier Roques <oroques+fdio@cisco.com>
Co-authored-by: Enrico Loparco <eloparco@cisco.com>
Change-Id: Iaddebfe6aa5279ea8553433b0f519578f6b9ccd9
Signed-off-by: Luca Muscariello <muscariello@ieee.org>
|
|
The current patch provides several new features, improvements,
bug fixes and also complete rewrite of entire components.
- lib
The hicn packet parser has been improved with a new packet
format fully based on UDP. The TCP header is still temporarily
supported but the UDP header will replace completely the new hicn
packet format. Improvements have been made to make sure every
packet parsing operation is made via this library. The current
new header can be used as header between the payload and the
UDP header or as trailer in the UDP surplus area to be tested
when UDP options will start to be used.
- hicn-light
The portable packet forwarder has been completely rewritten from
scratch with the twofold objective to improve performance and
code size but also to drop dependencies such as libparc which is
now removed by the current implementation.
- hicn control
the control library is the agent that is used to program the
packet forwarders via their binary API. This component has
benefited from significant improvements in terms of interaction
model which is now event driven and more robust to failures.
- VPP plugin has been updated to support VPP 22.02
- transport
Major improvement have been made to the RTC protocol, to the
support of IO modules and to the security sub system. Signed
manifests are the default data authenticity and integrity framework.
Confidentiality can be enabled by sharing the encryption key to the
prod/cons layer. The library has been tested with group key based
applications such as broadcast/multicast and real-time on-line
meetings with trusted server keys or MLS.
- testing
Unit testing has been introduced using GoogleTest. One third of
the code base is covered by unit testing with priority on
critical features. Functional testing has also been introduce
using Docker, linux bridging and Robot Framework to define
test with Less Code techniques to facilitate the extension
of the coverage.
Co-authored-by: Mauro Sardara <msardara@cisco.com>
Co-authored-by: Jordan Augé <jordan.auge+fdio@cisco.com>
Co-authored-by: Michele Papalini <micpapal@cisco.com>
Co-authored-by: Angelo Mantellini <manangel@cisco.com>
Co-authored-by: Jacques Samain <jsamain@cisco.com>
Co-authored-by: Olivier Roques <oroques+fdio@cisco.com>
Co-authored-by: Enrico Loparco <eloparco@cisco.com>
Co-authored-by: Giulio Grassi <gigrassi@cisco.com>
Change-Id: I75d0ef70f86d921e3ef503c99271216ff583c215
Signed-off-by: Luca Muscariello <muscariello@ieee.org>
Signed-off-by: Mauro Sardara <msardara@cisco.com>
|
|
The current patch provides a major refactory of the transportlibrary.
A summary of the different components that underwent major modifications is
reported below.
- Transport protocol updates
The hierarchy of classes has been optimized to have common transport services
across different transport protocols. This can allow to customize a transport
protocol with new features.
- A new real-time communication protocol
The RTC protocol has been optimized in terms of algorithms to reduce
consumer-producer synchronization latency.
- A novel socket API
The API has been reworked to be easier to consumer but also to have a more
efficient integration in L4 proxies.
- Several performance improvements
A large number of performance improvements have been included in
particular to make the entire stack zero-copy and optimize cache miss.
- New memory buffer framework
Memory management has been reworked entirely to provide a more efficient infra
with a richer API. Buffers are now allocated in blocks and a single buffer
holds the memory for (1) the shared_ptr control block, (2) the metadata of the
packet (e.g. name, pointer to other buffers if buffer is chained and relevant
offsets), and (3) the packet itself, as it is sent/received over the network.
- A new slab allocator
Dynamic memory allocation is now managed by a novel slab allocator that is
optimised for packet processing and connection management. Memory is organized
in pools of blocks all of the same size which are used during the processing of
outgoing/incoming packets. When a memory block Is allocated is always taken
from a global pool and when it is deallocated is returned to the pool, thus
avoiding the cost of any heap allocation in the data path.
- New transport connectors
Consumer and producer end-points can communication either using an hicn packet
forwarder or with direct connector based on shared memories or sockets.
The usage of transport connectors typically for unit and funcitonal
testing but may have additional usage.
- Support for FEC/ECC for transport services
FEC/ECC via reed solomon is supported by default and made available to
transport services as a modular component. Reed solomon block codes is a
default FEC model that can be replaced in a modular way by many other
codes including RLNC not avaiable in this distribution.
The current FEC framework support variable size padding and efficiently
makes use of the infra memory buffers to avoid additiona copies.
- Secure transport framework for signature computation and verification
Crypto support is nativelty used in hICN for integrity and authenticity.
Novel support that includes RTC has been implemented and made modular
and reusable acrosso different transport protocols.
- TLS - Transport layer security over hicn
Point to point confidentiality is provided by integrating TLS on top of
hICN reliable and non-reliable transport. The integration is common and
makes a different use of the TLS record.
- MLS - Messaging layer security over hicn
MLS integration on top of hICN is made by using the MLSPP implemetation
open sourced by Cisco. We have included instrumentation tools to deploy
performance and functional tests of groups of end-points.
- Android support
The overall code has been heavily tested in Android environments and
has received heavy lifting to better run natively in recent Android OS.
Co-authored-by: Mauro Sardara <msardara@cisco.com>
Co-authored-by: Michele Papalini <micpapal@cisco.com>
Co-authored-by: Olivier Roques <oroques+fdio@cisco.com>
Co-authored-by: Giulio Grassi <gigrassi@cisco.com>
Change-Id: If477ba2fa686e6f47bdf96307ac60938766aef69
Signed-off-by: Luca Muscariello <muscariello@ieee.org>
|
|
Signed-off-by: Mauro Sardara <msardara@cisco.com>
Change-Id: Ia116ad74ce78e2ca2d7ee624eea75a38936d27f8
Signed-off-by: Mauro Sardara <msardara@cisco.com>
|
|
service
Signed-off-by: Mauro Sardara <msardara@cisco.com>
Change-Id: I1810d96e001a4e6e097e1efa331b682af750925d
|
|
Signed-off-by: Mauro Sardara <msardara@cisco.com>
Change-Id: I8d8fdffef31a7013265d6529c5f52f3d5ec70d18
Signed-off-by: Mauro Sardara <msardara@cisco.com>
Signed-off-by: Mauro <you@example.com>
Signed-off-by: Mauro Sardara <msardara@cisco.com>
|
|
Signed-off-by: Mauro Sardara <msardara@cisco.com>
Change-Id: I701379bf0f088cad4a94209664de16e7bfe76f5e
Signed-off-by: Mauro Sardara <msardara@cisco.com>
|
|
- Implemented a udp decapsulation node
- Added a hash table to identify the incoming udp tunnel when
an interest or data packets are received
- Added udp punting through udp_register_dst_port
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
Change-Id: Iffea4d81c5ea8ce8ccbbfd749113f06a698a2afe
|
|
Updates on the vrf 0 will be reflected on the hicn vrf thanks to the
fib entry tracking.
Change-Id: I4afd6256593f27172c4b0a613316fb8428fa8e50
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
|
|
Changes in the new implementation are:
- the adjacency index is replaced with a dpo that allows the single face node
to dispatch the packet to the right vlib node.
- local and remote address in the face are replaced with a single nat address
which is used to perform the nat operation when rewriting an interest or a
data (in case of tunnels the nat address will be equal to 0)
- the list of next hop in the load balance is no longer a list of dpos but
a list of face id (this makes the code easier and increases the number of
next hop we supports)
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
Change-Id: I4ac2b4eb09425bfe1b3ca9f82d7d0ff564297b0d
|
|
Change-Id: I71767f732ec6ede1efc66e5a99f09c3207367dcb
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
|
|
Added two new messages in the binary api:
- hicn_api_face_cons_del to delete a consumer face
- hicn_api_face_prod_del to delete a producer face
Added the corresponding commands in the vpp_api_test for debugging and testing
Reworked the cache policy structure to add a new function that flash the content store
from the content coming from the destroyed producer face. This is required since the CS
while each producer face has its own lru list. Removing only the producer face without
flushing the CS from the content coming from the producer face will lead to a segfault
in case there is a hit in the CS as the lru no longer exists and it won't be possible
to update the head of the lru.
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
Change-Id: I8776c86952d50900aa504dd22aec521ed25c1dae
|
|
Change-Id: I054754ff722106a5be45324c1ace25447deeef2c
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
|
|
misconfiguration of parameters in param.h
Change-Id: Ia64eaebe267f87bd5f93abf3e5a9e80bab735765
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
|
|
Change-Id: I7a793e3664e30f765861fd5153c99fecb47ce863
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
|
|
Change-Id: Icfe9cd84bdc72afef3d714064e695d1abef368f5
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
|
|
- Handling the case in which a pushed data hit an existing pit entry (created after the data has gone through the data_pcslookup_node). In this case the data packet is forwarded to the data_fwd_node
- Handling the case in which the hash table (in pcs) is full and it is not possible to allocate another bucket. In this case the packet is dropped.
- Copying packets whose length is less than 128B. VPP prevents to create a chain of vlib_buffer where the first, or middle, vlib_buffer are holding less then 128B.
[HICN-72]
- Assign a /128 subnet to the producer app face.
Change-Id: I6c19d6d127774a7f59ac69ac965d4bcd6a72becc
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
|
|
Change-Id: I3a43b22194aa13ae5de1746e3d4bd9a275070261
Signed-off-by: Angelo Mantellini <manangel@cisco.com>
|
|
Change-Id: I6f2544ad9b9f8891c88cc4bcce3cf19bd3cc863f
Signed-off-by: Luca Muscariello <lumuscar+fdio@cisco.com>
|
Mauro Sardara
Luca Muscariello
Luca Muscariello
Alberto Compagno
Angelo Mantellini
Luca Muscariello