| Commit message (Collapse) | Author | Age | Files | Lines |
|---|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Removes the UDP and Ethernet shim IPCPs. The unicast and broadcast
IPCPs can now directly attach to a "legacy" socket. We adopt Saltzer's
Point-of-Attachment terminology, also advocated in Day's "Patterns in
Network Architecture". The "poa" component manages these
PoA's with one management thread, one link monitoring thread and one
thread per attached point.
For Ethernet PoA's the irm connect and enroll can resolve the
destination IPCP or Layer name with a broadcast name query over the
attached PoAs (first reply wins). UDP PoA's require a destination IP
address or FQDN.
attach to a local endpoint (required both server and client side):
irm ipcp poa attach name a udp 10.0.0.1
irm ipcp poa attach name a udp 10.0.0.1:3435
irm ipcp poa attach name a udp [::1]:3435
irm ipcp poa attach name a eth dev eth0
irm ipcp poa attach name a eth dev eth0 ethertype 0xA000
release a PoA (refused while it carries a flow):
irm ipcp poa detach name a udp 10.0.0.1:3435
irm ipcp poa detach name a eth eth0
list an IPCP's PoAs:
irm ipcp poa list name a
connect to a peer, by name or at an address:
irm ipcp connect name b dst a
irm ipcp connect name b dst a eth
irm ipcp connect name b dst a eth dev eth0
irm ipcp connect name b dst a udp 10.0.0.1:3435
irm ipcp connect name b dst a udp peer.example.com:3435
disconnect by peer name, no address:
irm ipcp disconnect name b dst a
irm ipcp disconnect name b dst a component mgmt
enroll has the same shape as connect:
irm ipcp enroll name b layer lr autobind
irm ipcp enroll name b layer lr autobind eth dev eth0
irm ipcp enroll name b layer lr autobind udp 10.0.0.1:3435
the IRMd config file attaches PoAs and names peers the same way:
udp = [ "10.0.0.1", "10.0.0.1:3436" ]
eth = [ "eth0", {dev="eth1", ethertype=0xA007} ]
enrol={dst="LAN", eth={dev="eth0"}}
conn=[{dst="lan3", eth={}}, {dst="lan4", udp="10.0.0.1:3435"}]
Signed-off-by: Dimitri Staessens <dimitri@ouroboros.rocks>
Signed-off-by: Sander Vrijders <sander@ouroboros.rocks>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Congestion avoidance is a property of the layer, orthogonal to ARQ
and to flow control: FRCP retransmits and lets the peer pace the
sender, per flow, end-to-end; the IPCP paces path aggregates. Each
signal means one thing: a loss triggers a retransmission, a mark
means congestion, the peer window means a slow receiver. Every flow
is paced by the same rate law whatever its QoS, so a greedy raw
sender shares a bottleneck fairly with a reliable stream.
The unit of control is the (destination address, QoS cube)
aggregate: all flows toward that destination share one controller
and one rate; a start-time fair-queuing pacer divides the rate
across them by deadline instead of blocking the send path, and a
new flow rides the aggregate's estimates at its current rate, with
no probing of its own. Slow start runs once per aggregate.
The congestion signal is a multi-bit magnitude: forwarders mark
packets with their standing queue depth, MAX-combined across hops,
so a packet carries the deepest queue on its path. The receiver
feeds back a time-integral mean over a window that adapts to the
flow's byte rate, measuring a slow flow with the same fidelity as a
fast one. The sender runs AIMD scaled by elapsed wall-clock time,
which makes the steady-state allocation RTT-independent.
The PCI gains one byte: the path capacity as a quarter-log2 code.
Forwarders estimate their egress rate from busy-period drain and
MIN-stamp the byte, the receiver returns the window minimum with
its feedback, and the sender scales its rate floor and additive
slope to the bottleneck (C / 32). A deep cut implies a backlogged
bottleneck and a backlogged bottleneck advertises its capacity, so
the scaled floor is live exactly when recovery needs it: the probe
heals a halving in seconds at any link rate, and the floor bounds
the deepest hole to a factor 32 below the bottleneck.
Signed-off-by: Dimitri Staessens <dimitri@ouroboros.rocks>
Signed-off-by: Sander Vrijders <sander@ouroboros.rocks>
|
| |
|
|
|
|
|
|
| |
The eth send buffer needs to block quickly so we can mark congestion
correctly in the upper layer buffers.
Signed-off-by: Dimitri Staessens <dimitri@ouroboros.rocks>
Signed-off-by: Sander Vrijders <sander@ouroboros.rocks>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
The previous shape registered no-op _rib_read / _rib_readdir /
_rib_getattr handlers when IPCP_FLOW_STATS was off, and there was a
bug where *buf was not set in the no-op causing free on an
uninitialized pointer.
IPCP_FLOW_STATS was referenced by config.h.in but the declaration was
lost during the CMake refactor.
Signed-off-by: Dimitri Staessens <dimitri@ouroboros.rocks>
Signed-off-by: Sander Vrijders <sander@ouroboros.rocks>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The Flow and Retransmission Control Protocol (FRCP) runs end-to-end
between two peers over a flow. It provides reliability, in-order
delivery, flow control, and liveness. Note that congestion avoidance
is orthogonal to FRCP and handled in the IPCP.
A fixed 16-octet header, network byte order, is prefixed to every FRCP
packet:
0 1 2 3
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| flags | hcs |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| window |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| seqno |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| ackno |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| payload (variable) ...
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
hcs is a CRC-16-CCITT-FALSE checksum over the PCI (and the stream
extension when present), verified before any flag-driven dispatch. A
single packet can simultaneously carry DATA + ACK + FC + RXM by OR-ing
flag bits. An optional CRC trailer covers the body on DATA when qs.ber
== 0, and on every SACK packet; an optional AEAD wrap (per-flow keys)
sits outermost.
Flag bits (MSB-first; bits 13..15 reserved, MUST be zero):
+------+--------+--------+----------------------------------------+
| Bit | Mask | Name | Meaning |
+------+--------+--------+----------------------------------------+
| 0 | 0x8000 | DATA | Carries caller payload |
| 1 | 0x4000 | DRF | Start of a fresh data run |
| 2 | 0x2000 | ACK | ackno field valid |
| 3 | 0x1000 | NACK | Pre-DRF nudge (seqno informational) |
| 4 | 0x0800 | FC | window field valid (rwe advertisement) |
| 5 | 0x0400 | RDVS | Rendezvous probe (window-closed) |
| 6 | 0x0200 | FFGM | First Fragment of a multi-fragment SDU |
| 7 | 0x0100 | LFGM | Last Fragment of a multi-fragment SDU |
| 8 | 0x0080 | RXM | Retransmission |
| 9 | 0x0040 | SACK | Block list follows in payload |
| 10 | 0x0020 | RTTP | RTT probe / echo (payload follows) |
| 11 | 0x0010 | KA | Keepalive |
| 12 | 0x0008 | FIN | End of stream marker |
| 13-15| -- | -- | Reserved (MUST be zero) |
+------+--------+--------+----------------------------------------+
(FFGM, LFGM) encodes the fragment role of a DATA packet (SCTP-style
B/E): 11=SOLE, 10=FIRST, 00=MID, 01=LAST. Each fragment carries its
own seqno; Retransmission recovers fragments individually, reassembly
runs at consume time. In stream mode FFGM/LFGM are unused; per-byte
position is carried by the stream extension below and end-of-stream is
signalled by FIN on a 0-byte DATA packet.
SACK payload (FRCT_ACK | FRCT_FC | FRCT_SACK):
0 1 2 3
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| n_blocks | padding (2 octets) |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| start[0] |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| end[0] |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
... n_blocks pairs total ...
Each block describes a *present* (received) range strictly above the
cumulative ACK in the PCI ackno. D-SACK (RFC 2883) is signalled
in-band as block[0] - no flag bit, no extra framing - and consumed by
the RACK reo_wnd_mult scaler (RFC 8985 sec. 7.2).
RTTP payload (FRCT_RTTP only; 24 octets):
0 1 2 3
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| probe_id |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| echo_id |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| |
+ nonce (16 octets, echoed verbatim) +
| |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
Stream PCI extension (in_order == STREAM only; 8 octets after the base
PCI on every DATA packet):
0 1 2 3
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| start |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
| end |
+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
start, end are monotonic 32-bit byte offsets; end - start equals the
on-wire payload length. Stream mode is negotiated at flow allocation;
the extension is present iff stream mode is in use, never on a
per-packet basis.
Service modes are an orthogonal (in_order, loss, ber) vector selected
at flow_alloc; the cubes above map to the axes:
+----------------+---------+------+-----+-----------------------+
| Cube | in_order| loss | ber | Engaged |
+----------------+---------+------+-----+-----------------------+
| qos_raw | 0 | 1 | 1 | Raw passthrough |
| qos_raw_safe | 0 | 1 | 0 | Raw + CRC trailer |
| qos_rt | 1 | 1 | 1 | FRCP, no FRTX, no CRC |
| qos_rt_safe | 1 | 1 | 0 | FRCP, no FRTX, CRC |
| qos_msg | 1 | 0 | 0 | FRCP + FRTX |
| qos_stream | 2 | 0 | 0 | FRCP + FRTX, stream |
+----------------+---------+------+-----+-----------------------+
in_order=0 sends raw datagrams with no PCI (UDP-equivalent);
in_order=1 engages FRCP with SDU framing; in_order=2 (stream) requires
loss=0 and is rejected otherwise. loss=0 engages the FRTX retransmit
machinery. ber=0 appends the CRC-32 trailer; QOS_DISABLE_CRC at build
time forces ber=1 for development. Encryption is a separate per-flow
attribute layered as an AEAD wrap outside the FRCP packet.
Heritage: delta-t (Watson 1981) supplies timer-based connection
management - no SYN/FIN handshake, the DRF marker, the t_mpl / t_a /
t_r timers. RINA (Day 2008) supplies the unified flow_alloc(name, qos,
...) primitive and the orthogonal QoS-cube axes. Loss detection
follows TCP/QUIC practice (RFCs 2018, 2883, 6582, 6298, 8985); RTT
probing is nonce-authenticated like QUIC PATH_CHALLENGE.
Adds oftp, a minimal file-transfer tool over an FRCP stream flow. The
client reads from stdin or --in FILE and writes through a
flow_alloc(qos_stream); the server (--listen) calls flow_accept and
writes to stdout or --out FILE. Both sides compute a CRC-64/NVMe over
the bytes they handle and print the result. The server rejects flows
whose negotiated qs.in_order != STREAM.
Two FRCP knobs are exposed via env vars on either side:
OFTP_FRCT_RTO_MIN fccntl FRCTSRTOMIN (ns)
OFTP_FRCT_STREAM_RING_SZ fccntl FRCTSRRINGSZ (octets)
The ocbr_client gains an OCBR_QOS env var to pick the cube the client
uses for flow_alloc; recognised values are raw, safe, rt, rt_safe,
msg, stream. Unknown values fall back to raw with a warning on
stderr. Without the env set behaviour is unchanged.
Removes the deprecated lib/timerwheel.c
Signed-off-by: Dimitri Staessens <dimitri@ouroboros.rocks>
Signed-off-by: Sander Vrijders <sander@ouroboros.rocks>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add IPCP_ETH_SNDBUF/RCVBUF cmake build options so deployments can size
the AF_PACKET socket buffers without patching code. Drop the
O_NONBLOCK fcntl on the raw socket in favour of per-recvfrom
MSG_DONTWAIT so race-loser reader threads exit with EAGAIN without
spamming the log.
Track frame send failures and the SO_SNDBUF size in the eth/summary
RIB; log a one-shot warning when the kernel reports AF_PACKET drops.
Retry name queries up to NAME_QUERY_RETRIES times within
NAME_QUERY_TIMEO; a single lost ARP-style mgmt frame no longer fails
the query. Bump IRMd QUERY_TIMEOUT from 200 ms to 2200 ms so the IRMd
budget exceeds the new shim retry window.
Signed-off-by: Dimitri Staessens <dimitri@ouroboros.rocks>
Signed-off-by: Sander Vrijders <sander@ouroboros.rocks>
|
| |
|
|
|
|
|
|
|
| |
FRCT needs to know the MTU for fragmentation. The MTU is now passed
from the layer serving the flow to the process as part of flow
allocation.
Signed-off-by: Dimitri Staessens <dimitri@ouroboros.rocks>
Signed-off-by: Sander Vrijders <sander@ouroboros.rocks>
|
| |
|
|
|
|
|
|
|
|
|
|
|
| |
Adds an IPCP_ETH_FLOW_STATS cmake option (gated on HAVE_FUSE; default
off) exposing per-flow and aggregate frame counters at
/<ipcp>/eth/{summary,<fd>}.
Counters use RELAXED atomics; the macros expand to ((void) 0) when the
option is off. Per-flow and global counters live in nested stat
structs.
Signed-off-by: Dimitri Staessens <dimitri@ouroboros.rocks>
Signed-off-by: Sander Vrijders <sander@ouroboros.rocks>
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The IPCP_*_TARGET variables (e.g., set(IPCP_LOCAL_TARGET ipcpd-local))
were defined locally in each IPCP's CMakeLists.txt (e.g.,
CMakeLists.txt), but the configure_file() that substitutes
@IPCP_LOCAL_TARGET@ into config.h.in runs in a sibling scope that is
processed before ipcpd. Since CMake variables don't propagate between
sibling directory scopes, all @IPCP_*_TARGET@ substituted to empty
strings, resulting in IPCP_LOCAL_EXEC "".
Moved the IPCP_*_TARGET definitions into the cmake/config/ipcp/*.cmake
files so they are known when generating config.h.
Signed-off-by: Dimitri Staessens <dimitri@ouroboros.rocks>
Signed-off-by: Sander Vrijders <sander@ouroboros.rocks>
|
|
|
This moves the build definitions back to src/ subdirectories
(CMakeLists.txt per component). Configuration and dependencies are
kept out of tree. Configuration options are bundled into cmake/config/
modules. Dependencies are grouped by component (system/, crypt/, eth/,
coverage/, etc.). It now consistently uses target-based commands
(target_include_directories, target_link_libraries) instead of global
include_directories(). Proper PRIVATE/PUBLIC visibility for executable
link libraries. CONFIG_OUROBOROS_DEBUG now properly set based on being
a valid debug config (not just checking the string name).
It also adds OuroborosTargets export for find_package() support and
CMake package config files (OuroborosConfig.cmake) for easier
integration with CMake projects.
The build logic now follows more idiomatic CMake practices with
configuration separated from target definitions.
Signed-off-by: Dimitri Staessens <dimitri@ouroboros.rocks>
Signed-off-by: Sander Vrijders <sander@ouroboros.rocks>
|
