Age | Commit message (Collapse) | Author | Files | Lines |
|
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
|
|
packet generator. Hash table for the packet cache has been
changed with the bihash.
Co-authored-by: Mauro Sardara <msardara@cisco.com>
Signed-off-by: Luca Muscariello <muscariello@ieee.org>
Change-Id: I0e0191a9f109d37081d32cc55d577ea43533f8c0
Signed-off-by: Mauro Sardara <msardara@cisco.com>
|
|
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>
|
|
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: Alberto Compagno <acompagn+fdio@cisco.com>
Change-Id: If2bf7f4f310adf6adbbb9ea29eafcb2a0ee40d54
|
|
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>
|
|
a data hit the CS. Data packets coming from the network are dropped,
data packets coming from an application face are either dropped or
sent to the push node (which does not require a lock on the hash
entry)
Change-Id: Icf662dffa33b9dda2e2a69fc2104a69a82ef19fd
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
|
|
Change-Id: I9165a863ac29e9386f49fdbc09da85e2fcc57750
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
|
|
a priority problem between * and []
Change-Id: I423e58bc91db9dc16a75bdc8065a2740d0160c1d
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
|
|
deallocation when data are pushed from the application.
Change-Id: Ibc9625e420d0c8579be3d7f1310a08a5e37f765a
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
|
|
when data are pushed to the CS from a local application.
Change-Id: I64a2bab413e74460b048f7c716630d9fcd5200cc
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
|
|
application
Change-Id: I9f7d8bf0ffbebd43ee82112407da39473fa2ad7c
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>
|
|
- Removed full pit entry initialization in favor of a lighter initialization on few fields
- Squeezed pit entry size in order to store only the number of incomplete faces (as set in HICN_PARAM_PIT_ENTRY_PHOPS_MAX). The bitmap size is now determined by HICN_PARAM_FACES_MAX and optimized to do a fast lookup
Replaced the field is_appface with the field flags in the hicn_buffer_t:
- is_appface is now a flag with value 0x01 (HICN_BUFFER_FLAGS_FACE_IS_APP)
- Added flag HICN_BUFFER_FLAGS_PKT_LESS_TWO_CL (0x02) to handle the copy of pkt with length < than 2*CACHE_LINES (in this case cloning is prevented by the cloning function in vpp). Such flag is initialized by the incoming face of the pkt.
Change-Id: Ia956fd5719a28ee29f7fa2fd23d283964743efd8
Signed-off-by: Alberto Compagno <acompagn+fdio@cisco.com>
|
|
Change-Id: I6f2544ad9b9f8891c88cc4bcce3cf19bd3cc863f
Signed-off-by: Luca Muscariello <lumuscar+fdio@cisco.com>
|