Compare commits
10 Commits
6fe30bf2dd
...
1e9a110194
| Author | SHA1 | Date |
|---|---|---|
|
|
1e9a110194 | |
|
|
d9d7cc491a | |
|
|
65dae3ae51 | |
|
|
c0826e00bf | |
|
|
44f5c46274 | |
|
|
55ab72e7dc | |
|
|
0b439b850f | |
|
|
5563baaf17 | |
|
|
c798c94514 | |
|
|
91e06910b6 |
|
|
@ -96,12 +96,6 @@ jobs:
|
||||||
# are hard signals. Promote the test step to required once the
|
# are hard signals. Promote the test step to required once the
|
||||||
# suite is green.
|
# suite is green.
|
||||||
|
|
||||||
# XXX the `tipc` leg stays NON-blocking until the `modprobe`
|
|
||||||
# step below is proven stable on GH's runners; flip this off
|
|
||||||
# once it's had a few green runs. See plan 01 §7.3 in
|
|
||||||
# `ai/tpt-backends/01_tipc_backend.md`.
|
|
||||||
continue-on-error: ${{ matrix.tpt_proto == 'tipc' }}
|
|
||||||
|
|
||||||
strategy:
|
strategy:
|
||||||
fail-fast: false
|
fail-fast: false
|
||||||
matrix:
|
matrix:
|
||||||
|
|
|
||||||
|
|
@ -0,0 +1,29 @@
|
||||||
|
---
|
||||||
|
model: openai/gpt-5.6-sol
|
||||||
|
service: opencode
|
||||||
|
session: a998acff-af66-4969-a65e-f77cbf5ef8dd
|
||||||
|
timestamp: 2026-08-19T00:33:26Z
|
||||||
|
git_ref: wkt/tipc_backend_378
|
||||||
|
scope: config
|
||||||
|
substantive: true
|
||||||
|
raw_file: 20260819T003326Z_53516b09_prompt_io.raw.md
|
||||||
|
---
|
||||||
|
|
||||||
|
## Prompt
|
||||||
|
|
||||||
|
Confirm whether the successful TIPC CI leg can become blocking.
|
||||||
|
|
||||||
|
## Response summary
|
||||||
|
|
||||||
|
Removed the temporary TIPC-only `continue-on-error` expression after
|
||||||
|
every refreshed PR #493 check passed.
|
||||||
|
|
||||||
|
## Files changed
|
||||||
|
|
||||||
|
- `.github/workflows/ci.yml` - make TIPC failures block CI.
|
||||||
|
|
||||||
|
## Human edits
|
||||||
|
|
||||||
|
The human explicitly requested reconsidering the gate after the CI
|
||||||
|
run and chose to leave the generated change local for review before
|
||||||
|
requesting this commit plan.
|
||||||
|
|
@ -0,0 +1,23 @@
|
||||||
|
---
|
||||||
|
model: openai/gpt-5.6-sol
|
||||||
|
service: opencode
|
||||||
|
timestamp: 2026-08-19T00:33:26Z
|
||||||
|
git_ref: wkt/tipc_backend_378
|
||||||
|
diff_cmd: git diff HEAD~1..HEAD
|
||||||
|
---
|
||||||
|
|
||||||
|
## Prompt
|
||||||
|
|
||||||
|
The user asked whether the now-green TIPC CI leg could stop using
|
||||||
|
`continue-on-error`.
|
||||||
|
|
||||||
|
## Response
|
||||||
|
|
||||||
|
All checks on PR #493 passed, including the Ubuntu TIPC matrix job.
|
||||||
|
The generated config change removes the temporary non-blocking gate
|
||||||
|
and its obsolete explanatory comment:
|
||||||
|
|
||||||
|
> `git diff HEAD~1..HEAD -- .github/workflows/ci.yml`
|
||||||
|
|
||||||
|
The remaining matrix, Linux-only exclusion and `modprobe tipc` setup
|
||||||
|
stay unchanged.
|
||||||
|
|
@ -0,0 +1,37 @@
|
||||||
|
---
|
||||||
|
model: openai/gpt-5.6-sol
|
||||||
|
service: opencode
|
||||||
|
session: a998acff-af66-4969-a65e-f77cbf5ef8dd
|
||||||
|
timestamp: 2026-08-19T00:33:27Z
|
||||||
|
git_ref: wkt/tipc_backend_378
|
||||||
|
scope: code
|
||||||
|
substantive: true
|
||||||
|
raw_file: 20260819T003327Z_53516b09_prompt_io.raw.md
|
||||||
|
---
|
||||||
|
|
||||||
|
## Prompt
|
||||||
|
|
||||||
|
Develop a practical bootstrap plan for testing TIPC across two
|
||||||
|
physical motherboards.
|
||||||
|
|
||||||
|
## Response summary
|
||||||
|
|
||||||
|
Expanded the two-host example into a reproducible smoke-test runbook
|
||||||
|
and made host A authorize the stable module name imported by host B.
|
||||||
|
Documented the cluster-domain-socket analogy and the prospective
|
||||||
|
`pyroute2` management path.
|
||||||
|
|
||||||
|
## Files changed
|
||||||
|
|
||||||
|
- `examples/multihost/tipc_cluster/README.md` - document setup,
|
||||||
|
validation, resilience testing, capture and cleanup.
|
||||||
|
- `examples/multihost/tipc_cluster/host_a_srv.py` - authorize the
|
||||||
|
`host_a_srv` RPC module under direct script execution.
|
||||||
|
|
||||||
|
## Human edits
|
||||||
|
|
||||||
|
The human selected two separate physical motherboards as the target
|
||||||
|
environment and requested that the resulting local work be packaged
|
||||||
|
as its own commit boundary. The human also proposed “Cluster Domain
|
||||||
|
Sockets” as clearer terminology and reusing the planned `pyroute2`
|
||||||
|
dependency for TIPC management.
|
||||||
|
|
@ -0,0 +1,27 @@
|
||||||
|
---
|
||||||
|
model: openai/gpt-5.6-sol
|
||||||
|
service: opencode
|
||||||
|
timestamp: 2026-08-19T00:33:27Z
|
||||||
|
git_ref: wkt/tipc_backend_378
|
||||||
|
diff_cmd: git diff HEAD~1..HEAD
|
||||||
|
---
|
||||||
|
|
||||||
|
## Prompt
|
||||||
|
|
||||||
|
The user asked for a bootstrap plan to try TIPC with two real,
|
||||||
|
physically separate Linux motherboards.
|
||||||
|
|
||||||
|
## Response
|
||||||
|
|
||||||
|
The generated changes turn the existing sketch into an operator
|
||||||
|
runbook and correct the RPC module authorization used by direct
|
||||||
|
script execution:
|
||||||
|
|
||||||
|
> `git diff HEAD~1..HEAD -- examples/multihost/tipc_cluster/README.md examples/multihost/tipc_cluster/host_a_srv.py`
|
||||||
|
|
||||||
|
The runbook covers matching revisions, cluster identity, interface
|
||||||
|
selection, Ethernet bearer setup, link and name-table validation,
|
||||||
|
RPC, failure/rejoin testing, diagnostics, cleanup and a future
|
||||||
|
network-namespace fixture. It also records “Cluster Domain Sockets”
|
||||||
|
as explanatory terminology and identifies a future `pyroute2` TIPC
|
||||||
|
generic-netlink codec as the path away from manual `tipc(8)` calls.
|
||||||
|
|
@ -0,0 +1,37 @@
|
||||||
|
---
|
||||||
|
model: openai/gpt-5.6-sol
|
||||||
|
service: opencode
|
||||||
|
session: a998acff-af66-4969-a65e-f77cbf5ef8dd
|
||||||
|
timestamp: 2026-08-19T00:33:28Z
|
||||||
|
git_ref: wkt/tipc_backend_378
|
||||||
|
scope: docs
|
||||||
|
substantive: true
|
||||||
|
raw_file: 20260819T003328Z_53516b09_prompt_io.raw.md
|
||||||
|
---
|
||||||
|
|
||||||
|
## Prompt
|
||||||
|
|
||||||
|
Draft an upstream `/tipc` multiaddr issue modeled on the prior `wg`
|
||||||
|
proposal.
|
||||||
|
|
||||||
|
## Response summary
|
||||||
|
|
||||||
|
Added a reviewable upstream issue draft with a concrete binary and
|
||||||
|
text encoding, composition examples, rollout plan and open design
|
||||||
|
questions. Retained the ecosystem-standard `tipc` name while using
|
||||||
|
“Cluster Domain Sockets” as explanatory terminology, and separated
|
||||||
|
the future `pyroute2` management track from address encoding.
|
||||||
|
|
||||||
|
## Files changed
|
||||||
|
|
||||||
|
- `ai/tpt-backends/04_tipc_multiaddr_upstream.md` - candidate
|
||||||
|
`multiformats/multiaddr` issue body.
|
||||||
|
- `ai/tpt-backends/README.md` - roster the upstream proposal.
|
||||||
|
|
||||||
|
## Human edits
|
||||||
|
|
||||||
|
The human chose to track the draft under `ai/tpt-backends/` instead
|
||||||
|
of leaving it in the ignored gish cache, and explicitly requested a
|
||||||
|
Prompt-IO record for this docs-only commit. The human proposed the
|
||||||
|
`cds` alternative and unifying TIPC/WireGuard management through
|
||||||
|
`pyroute2`.
|
||||||
|
|
@ -0,0 +1,26 @@
|
||||||
|
---
|
||||||
|
model: openai/gpt-5.6-sol
|
||||||
|
service: opencode
|
||||||
|
timestamp: 2026-08-19T00:33:28Z
|
||||||
|
git_ref: wkt/tipc_backend_378
|
||||||
|
diff_cmd: git diff HEAD~1..HEAD
|
||||||
|
---
|
||||||
|
|
||||||
|
## Prompt
|
||||||
|
|
||||||
|
The user asked to begin drafting an upstream `/tipc` multiaddr issue
|
||||||
|
similar to the existing WireGuard proposal, then chose to track the
|
||||||
|
draft as an AI planning document.
|
||||||
|
|
||||||
|
## Response
|
||||||
|
|
||||||
|
The generated proposal is intended for `multiformats/multiaddr`:
|
||||||
|
|
||||||
|
> `git diff HEAD~1..HEAD -- ai/tpt-backends/04_tipc_multiaddr_upstream.md ai/tpt-backends/README.md`
|
||||||
|
|
||||||
|
It proposes a code allocated upstream, a fixed 72-bit value holding
|
||||||
|
the service type, instance and scope, and the canonical text form
|
||||||
|
`/tipc/<type>:<instance>:<scope>`. It includes WireGuard composition,
|
||||||
|
security boundaries, the `tipc` versus `cds` naming decision,
|
||||||
|
deployment-management separation, implementation phases, test data
|
||||||
|
and open questions for maintainers.
|
||||||
|
|
@ -0,0 +1,40 @@
|
||||||
|
---
|
||||||
|
model: openai/gpt-5.6-sol
|
||||||
|
service: opencode
|
||||||
|
session: a998acff-af66-4969-a65e-f77cbf5ef8dd
|
||||||
|
timestamp: 2026-08-30T04:53:03Z
|
||||||
|
git_ref: wkt/tipc_backend_378
|
||||||
|
scope: code
|
||||||
|
substantive: true
|
||||||
|
raw_file: 20260830T045303Z_69a0e504_prompt_io.raw.md
|
||||||
|
---
|
||||||
|
|
||||||
|
## Prompt
|
||||||
|
|
||||||
|
Inspect the TIPC backend rebase onto current `main`, repair and verify any
|
||||||
|
integration problems before force-push, and prepare the result through the
|
||||||
|
proper `/commit-plan` workflow.
|
||||||
|
|
||||||
|
## Response summary
|
||||||
|
|
||||||
|
Repaired the stale lock produced by replaying the historical py-multiaddr
|
||||||
|
source-pin commit over current `main`. Adapted TIPC to the newer lazy-import
|
||||||
|
contract and extended runtime annotation tests for the interim `/tipc`
|
||||||
|
multiaddr representation. Verified both the full default and TIPC transport
|
||||||
|
test matrices.
|
||||||
|
|
||||||
|
## Files changed
|
||||||
|
|
||||||
|
- `uv.lock` - select the pinned WG-capable py-multiaddr revision while
|
||||||
|
retaining current `main` dependencies.
|
||||||
|
- `tractor/ipc/_tipc.py` - make the `Multiaddr` annotation import lazy.
|
||||||
|
- `tests/test_lazy_imports.py` - cover TIPC annotation resolution and the
|
||||||
|
interim `Multiaddr|str` return shape.
|
||||||
|
|
||||||
|
## Human edits
|
||||||
|
|
||||||
|
The human restarted and advanced the rebase one conflict at a time, required
|
||||||
|
the agent to provide exact continuation commands after each resolution,
|
||||||
|
authorized lock repair and verification, and retained ownership of the
|
||||||
|
force-push. The human then rejected the ad hoc staging suggestion and required
|
||||||
|
the complete `/commit-plan` workflow before committing.
|
||||||
|
|
@ -0,0 +1,54 @@
|
||||||
|
---
|
||||||
|
model: openai/gpt-5.6-sol
|
||||||
|
service: opencode
|
||||||
|
timestamp: 2026-08-30T04:53:03Z
|
||||||
|
git_ref: wkt/tipc_backend_378
|
||||||
|
diff_cmd: git diff HEAD~1..HEAD
|
||||||
|
---
|
||||||
|
|
||||||
|
## Prompt
|
||||||
|
|
||||||
|
After rebasing the TIPC backend branch onto current `main`, inspect the
|
||||||
|
result before the human force-pushes it. Repair and verify any integration
|
||||||
|
problems, then provide a proper `/commit-plan` rather than an ad hoc staging
|
||||||
|
and commit suggestion.
|
||||||
|
|
||||||
|
## Response
|
||||||
|
|
||||||
|
The range-diff showed that the two omitted pformat commits were already
|
||||||
|
present on `main`, while the conflict resolutions correctly retained current
|
||||||
|
platform-aware transport behavior. It also exposed a lost `uv.lock` update:
|
||||||
|
`pyproject.toml` retained the unreleased WG-capable `multiaddr` source pin,
|
||||||
|
but the lock still selected the PyPI release.
|
||||||
|
|
||||||
|
> `git diff HEAD~1..HEAD -- uv.lock`
|
||||||
|
|
||||||
|
Regenerated the lock against current `main`, preserving its newly landed
|
||||||
|
dependencies while selecting py-multiaddr revision `f86519da`.
|
||||||
|
|
||||||
|
The full test suite then found that eagerly importing `Multiaddr` from the
|
||||||
|
new TIPC module violated `main`'s cold-import contract.
|
||||||
|
|
||||||
|
> `git diff HEAD~1..HEAD -- tractor/ipc/_tipc.py`
|
||||||
|
|
||||||
|
Moved `Multiaddr` under `TYPE_CHECKING` and supplied the runtime `Any` alias
|
||||||
|
used by the sibling TCP and UDS backends, retaining lazy multiaddr loading
|
||||||
|
and runtime annotation resolution.
|
||||||
|
|
||||||
|
> `git diff HEAD~1..HEAD -- tests/test_lazy_imports.py`
|
||||||
|
|
||||||
|
Extended lazy annotation checks to the TIPC stream and updated
|
||||||
|
`mk_maddr()`'s expected runtime return type for the branch's interim
|
||||||
|
`Multiaddr|str` TIPC grammar.
|
||||||
|
|
||||||
|
Validation completed:
|
||||||
|
|
||||||
|
- `uv lock --check` passed.
|
||||||
|
- Focused lazy-import, TIPC, and multiaddr checks: 60 passed.
|
||||||
|
- Full default transport suite: 548 passed, 9 skipped, 7 xfailed,
|
||||||
|
3 xpassed.
|
||||||
|
- Full `--tpt-proto=tipc` suite: 548 passed, 9 skipped, 8 xfailed,
|
||||||
|
2 xpassed.
|
||||||
|
|
||||||
|
The human corrected the initial ad hoc commit suggestion and required the
|
||||||
|
repository's complete `/commit-plan` workflow.
|
||||||
|
|
@ -0,0 +1,191 @@
|
||||||
|
# `/tipc` multiaddr protocol: upstream issue draft
|
||||||
|
|
||||||
|
Candidate issue for `multiformats/multiaddr`, to be submitted after
|
||||||
|
the encoding questions below have been reviewed locally.
|
||||||
|
|
||||||
|
## Context
|
||||||
|
|
||||||
|
Linux TIPC (Transparent Inter-Process Communication) addresses a
|
||||||
|
service by a location-independent `(service type, instance)` name.
|
||||||
|
A server publishes that name into the kernel-maintained cluster name
|
||||||
|
table and a client connects by the same name; no host or transport
|
||||||
|
port forms part of the service identity.
|
||||||
|
|
||||||
|
TIPC is also known as **Cluster Domain Sockets**, a useful description
|
||||||
|
of its relationship to Unix-domain sockets. The registered protocol
|
||||||
|
name should nevertheless remain `tipc`: it matches Linux's
|
||||||
|
`AF_TIPC`, socket constants, kernel module and iproute2 frontend.
|
||||||
|
Registering `cds` would create an ecosystem-specific alias that is
|
||||||
|
harder to map back to the normative kernel API.
|
||||||
|
|
||||||
|
We would like to register a `tipc` multiaddr component so these
|
||||||
|
service endpoints can be represented directly and composed with a
|
||||||
|
bearer or tunnel description:
|
||||||
|
|
||||||
|
```text
|
||||||
|
/tipc/1953628160:1616:2
|
||||||
|
|
||||||
|
/ip4/192.168.1.50/udp/51820/wg/u<key>/tipc/1953628160:1616:2
|
||||||
|
\____________ WireGuard bearer ____________/\____ TIPC service ____/
|
||||||
|
```
|
||||||
|
|
||||||
|
In the composed form, the components through `/wg/<key>` identify
|
||||||
|
the routed bearer and tunnel peer. The `/tipc/...` component is pure
|
||||||
|
service identity, resolved to a current publisher by the TIPC kernel
|
||||||
|
name table. Unlike a TCP endpoint, it deliberately has no inner IP
|
||||||
|
address or port.
|
||||||
|
|
||||||
|
This proposal does not imply that parsing the multiaddr configures a
|
||||||
|
TIPC bearer. In particular, TIPC over a WireGuard interface requires
|
||||||
|
a separately configured TIPC UDP bearer; WireGuard interfaces are L3
|
||||||
|
devices and cannot carry TIPC Ethernet media directly.
|
||||||
|
|
||||||
|
Today that bearer is configured through iproute2's `tipc` frontend,
|
||||||
|
which speaks the kernel's `TIPCv2` generic-netlink family. `pyroute2`
|
||||||
|
already provides WireGuard support and generic-netlink primitives but
|
||||||
|
has no TIPC codec/module; adding one is a complementary deployment
|
||||||
|
automation track, not part of this address-format proposal.
|
||||||
|
|
||||||
|
## Proposed protocol
|
||||||
|
|
||||||
|
- Name: `tipc`
|
||||||
|
- Code: TBD, allocated in `multiformats/multicodec` under the
|
||||||
|
`multiaddr` tag before implementations stabilize one
|
||||||
|
- Size: 72 bits
|
||||||
|
- Value: service type, service instance and publication scope
|
||||||
|
|
||||||
|
### Binary form
|
||||||
|
|
||||||
|
Exactly nine bytes with no value-length prefix:
|
||||||
|
|
||||||
|
| Offset | Size | Field | Encoding |
|
||||||
|
| ---: | ---: | --- | --- |
|
||||||
|
| 0 | 4 bytes | service type | unsigned 32-bit big-endian |
|
||||||
|
| 4 | 4 bytes | service instance | unsigned 32-bit big-endian |
|
||||||
|
| 8 | 1 byte | publication scope | unsigned enum byte |
|
||||||
|
|
||||||
|
```text
|
||||||
|
tipc-value = uint32be(type) || uint32be(instance) || uint8(scope)
|
||||||
|
```
|
||||||
|
|
||||||
|
For type `1953628160` (`0x74720000`), instance `1616` and
|
||||||
|
cluster scope `2`, the payload is:
|
||||||
|
|
||||||
|
```text
|
||||||
|
74 72 00 00 00 00 06 50 02
|
||||||
|
```
|
||||||
|
|
||||||
|
### String form
|
||||||
|
|
||||||
|
Use one multiaddr value segment containing three canonical decimal
|
||||||
|
integers:
|
||||||
|
|
||||||
|
```text
|
||||||
|
/tipc/<type>:<instance>:<scope>
|
||||||
|
```
|
||||||
|
|
||||||
|
Canonical values have no sign, whitespace, alternate radix or
|
||||||
|
leading zeroes, except that zero itself is `0`. `type` and `instance`
|
||||||
|
must fit unsigned 32-bit fields. Scope is one of:
|
||||||
|
|
||||||
|
- `2`: `TIPC_CLUSTER_SCOPE`
|
||||||
|
- `3`: `TIPC_NODE_SCOPE`
|
||||||
|
|
||||||
|
The existing experimental spelling
|
||||||
|
`/tipc/<type>/<instance>/<scope>` cannot be registered as one normal
|
||||||
|
multiaddr protocol: generic parsing treats each slash-delimited name
|
||||||
|
as another protocol component. A single structured value preserves
|
||||||
|
TIPC's atomic service-address semantics without registering three
|
||||||
|
artificial protocols.
|
||||||
|
|
||||||
|
## Why scope is included
|
||||||
|
|
||||||
|
TIPC scope controls where a bound service publication is visible.
|
||||||
|
The same address representation is used for listener configuration
|
||||||
|
and dialing, so retaining scope lets a multiaddr round-trip the full
|
||||||
|
socket address rather than silently turning a node-local bind into a
|
||||||
|
cluster publication.
|
||||||
|
|
||||||
|
Modern Linux UAPI defines cluster and node scopes. The deprecated
|
||||||
|
zone spelling should not receive a new wire value; implementations
|
||||||
|
may normalize legacy input to cluster scope before encoding.
|
||||||
|
|
||||||
|
## Composition
|
||||||
|
|
||||||
|
Standalone service:
|
||||||
|
|
||||||
|
```text
|
||||||
|
/tipc/1953628160:1616:2
|
||||||
|
```
|
||||||
|
|
||||||
|
TIPC service reached through a WireGuard bearer:
|
||||||
|
|
||||||
|
```text
|
||||||
|
/ip4/192.168.1.50/udp/51820/wg/u<key>/tipc/1953628160:1616:2
|
||||||
|
```
|
||||||
|
|
||||||
|
This differs intentionally from TCP over WireGuard:
|
||||||
|
|
||||||
|
```text
|
||||||
|
/ip4/192.168.1.50/udp/51820/wg/u<key>/ip4/10.0.11.1/tcp/1616
|
||||||
|
```
|
||||||
|
|
||||||
|
TCP repeats an inner locative address. TIPC does not: its service
|
||||||
|
name is resolved and load-balanced in-kernel across current
|
||||||
|
publishers.
|
||||||
|
|
||||||
|
## Semantics and security
|
||||||
|
|
||||||
|
- A TIPC service name identifies a service, not a unique process.
|
||||||
|
Multiple publishers may bind the same name and connections can be
|
||||||
|
distributed among them.
|
||||||
|
- Publication scope is reachability metadata, not authentication.
|
||||||
|
- A composed `/wg` key authenticates the tunnel peer, not the TIPC
|
||||||
|
service publisher.
|
||||||
|
- TIPC's optional native AES-GCM link encryption is independent of
|
||||||
|
this address codec and of WireGuard.
|
||||||
|
- Codec implementations should validate field widths and canonical
|
||||||
|
text only; cluster membership and publisher authorization remain
|
||||||
|
deployment concerns.
|
||||||
|
|
||||||
|
## Implementation plan
|
||||||
|
|
||||||
|
1. Reserve a `multiaddr`-tagged code in
|
||||||
|
`multiformats/multicodec`.
|
||||||
|
2. Add the fixed-size protocol row and normative encoding text to
|
||||||
|
`multiformats/multiaddr`.
|
||||||
|
3. Add codecs and cross-language test vectors, beginning with
|
||||||
|
`multiformats/py-multiaddr`.
|
||||||
|
4. Verify standalone and composed `wg` + `tipc` string/binary
|
||||||
|
round-trips.
|
||||||
|
|
||||||
|
## Open questions
|
||||||
|
|
||||||
|
1. Is a fixed 72-bit value preferred over a self-describing or
|
||||||
|
variable-width tuple for this kernel-defined address?
|
||||||
|
2. Should node scope be representable in a generally shareable
|
||||||
|
multiaddr, or should the registered form be cluster-only?
|
||||||
|
3. Does multiaddr have an existing convention for structured numeric
|
||||||
|
values that should replace the colon-separated text form?
|
||||||
|
4. Should the specification describe TIPC service *ranges*, or keep
|
||||||
|
this protocol limited to singleton service names used for
|
||||||
|
connection endpoints?
|
||||||
|
|
||||||
|
## References
|
||||||
|
|
||||||
|
- Linux TIPC documentation:
|
||||||
|
https://docs.kernel.org/networking/tipc.html
|
||||||
|
- Cluster Domain Sockets terminology:
|
||||||
|
https://en.wikipedia.org/wiki/Transparent_Inter-process_Communication
|
||||||
|
- Linux socket UAPI:
|
||||||
|
https://github.com/torvalds/linux/blob/master/include/uapi/linux/tipc.h
|
||||||
|
- Linux TIPC generic-netlink UAPI:
|
||||||
|
https://github.com/torvalds/linux/blob/master/include/uapi/linux/tipc_netlink.h
|
||||||
|
- pyroute2 WireGuard and generic-netlink APIs:
|
||||||
|
https://docs.pyroute2.org/wireguard.html
|
||||||
|
- WireGuard multiaddr implementation discussion:
|
||||||
|
https://github.com/multiformats/py-multiaddr/issues/107
|
||||||
|
- WireGuard codec implementation:
|
||||||
|
https://github.com/multiformats/py-multiaddr/pull/108
|
||||||
|
- Downstream tracking and prototype:
|
||||||
|
https://github.com/goodboy/tractor/issues/498
|
||||||
|
|
@ -16,6 +16,7 @@ assume it and document only their own deltas.
|
||||||
| [01 — TIPC](./01_tipc_backend.md) | [#378] | **none** (stdlib) | small | **landed**, PR [#493] — see the [handoff](./01_tipc_HANDOFF.md) |
|
| [01 — TIPC](./01_tipc_backend.md) | [#378] | **none** (stdlib) | small | **landed**, PR [#493] — see the [handoff](./01_tipc_HANDOFF.md) |
|
||||||
| [02 — QUIC/`iroh`](./02_quic_iroh_backend.md) | [#353] | `iroh` (uniffi FFI) | large | needs a prep PR |
|
| [02 — QUIC/`iroh`](./02_quic_iroh_backend.md) | [#353] | `iroh` (uniffi FFI) | large | needs a prep PR |
|
||||||
| [03 — `wg` bindspace](./03_wg_tunnel_bindspace.md) | [#482], [#443] | `pyroute2` | medium, 3 layers | layer A now |
|
| [03 — `wg` bindspace](./03_wg_tunnel_bindspace.md) | [#482], [#443] | `pyroute2` | medium, 3 layers | layer A now |
|
||||||
|
| [04 — `/tipc` multiaddr](./04_tipc_multiaddr_upstream.md) | [#498] | upstream `multiformats` | issue draft | local review |
|
||||||
|
|
||||||
Headline conclusions:
|
Headline conclusions:
|
||||||
|
|
||||||
|
|
@ -54,5 +55,6 @@ lands first ships it.
|
||||||
[#353]: https://github.com/goodboy/tractor/issues/353
|
[#353]: https://github.com/goodboy/tractor/issues/353
|
||||||
[#482]: https://github.com/goodboy/tractor/issues/482
|
[#482]: https://github.com/goodboy/tractor/issues/482
|
||||||
[#443]: https://github.com/goodboy/tractor/issues/443
|
[#443]: https://github.com/goodboy/tractor/issues/443
|
||||||
|
[#498]: https://github.com/goodboy/tractor/issues/498
|
||||||
|
|
||||||
[#493]: https://github.com/goodboy/tractor/pull/493
|
[#493]: https://github.com/goodboy/tractor/pull/493
|
||||||
|
|
|
||||||
|
|
@ -2,6 +2,10 @@
|
||||||
|
|
||||||
TIPC is a linux-kernel cluster IPC protocol whose service names
|
TIPC is a linux-kernel cluster IPC protocol whose service names
|
||||||
live in a **cluster-wide name table maintained by the kernel**.
|
live in a **cluster-wide name table maintained by the kernel**.
|
||||||
|
It is also described as **Cluster Domain Sockets**: the Unix-domain
|
||||||
|
socket model extended from one kernel to a cluster. That name is a
|
||||||
|
useful explanation for new users, while the code keeps `tipc` as its
|
||||||
|
protocol key to match Linux's `AF_TIPC`, kernel module and tooling.
|
||||||
For `tractor` that means:
|
For `tractor` that means:
|
||||||
|
|
||||||
- an actor's IPC address is a service name `(stype, instance)`,
|
- an actor's IPC address is a service name `(stype, instance)`,
|
||||||
|
|
@ -85,30 +89,55 @@ Everything above is single-node (`modprobe` is enough). To span
|
||||||
hosts you need a **bearer** on both, which is the one thing that
|
hosts you need a **bearer** on both, which is the one thing that
|
||||||
can't be CI'd.
|
can't be CI'd.
|
||||||
|
|
||||||
|
For the first physical test, use two wired Linux hosts on the same
|
||||||
|
L2 segment. Prefer a direct cable or uncomplicated switch; avoid
|
||||||
|
Wi-Fi, guest VLANs and port isolation until the basic link works.
|
||||||
|
Use the same checkout and Python environment on both hosts:
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
# on BOTH hosts
|
# on BOTH hosts
|
||||||
|
git rev-parse HEAD # must match on A and B
|
||||||
|
uv sync --all-extras --dev
|
||||||
sudo modprobe tipc
|
sudo modprobe tipc
|
||||||
|
|
||||||
# over ethernet (L2) — simplest when the hosts share a segment
|
# choose the real wired iface; do not assume `eth0`
|
||||||
sudo tipc bearer enable media eth device eth0
|
ip -br link
|
||||||
|
IFACE=enp3s0
|
||||||
|
|
||||||
|
# inspect existing cluster identity before changing anything
|
||||||
|
tipc node get address # must differ between hosts
|
||||||
|
tipc node get netid # must match between hosts
|
||||||
|
|
||||||
|
# use one private test netid on BOTH hosts, before enabling bearers
|
||||||
|
sudo tipc node set netid 37801
|
||||||
|
|
||||||
|
# ethernet is simplest when the hosts share an L2 segment
|
||||||
|
sudo tipc bearer enable media eth device "$IFACE"
|
||||||
|
|
||||||
# ..or over UDP when L2 isn't available — and MANDATORY over a
|
# ..or over UDP when L2 isn't available — and MANDATORY over a
|
||||||
# `wg` mesh, see below
|
# `wg` mesh, see below
|
||||||
sudo tipc bearer enable media udp name uc localip 10.0.11.1
|
sudo tipc bearer enable media udp name uc localip 10.0.11.1
|
||||||
|
|
||||||
# verify BEFORE running anything: this must list the peer
|
# verify BEFORE running anything: this must list the peer
|
||||||
|
tipc bearer list
|
||||||
tipc link list
|
tipc link list
|
||||||
tipc node list
|
tipc node list
|
||||||
```
|
```
|
||||||
|
|
||||||
Then:
|
If the link does not appear, first verify carrier, a common TIPC
|
||||||
|
network ID, distinct node addresses, a common VLAN and compatible
|
||||||
|
MTUs. Ethernet TIPC uses EtherType traffic rather than IP routing,
|
||||||
|
so a successful `ping` alone does not prove the bearer can work.
|
||||||
|
|
||||||
|
Run each command from `examples/multihost/tipc_cluster/`:
|
||||||
|
|
||||||
```bash
|
```bash
|
||||||
# host A
|
# host A
|
||||||
python host_a_srv.py
|
uv run python host_a_srv.py
|
||||||
|
|
||||||
# host B
|
# host B
|
||||||
python host_b_client.py
|
watch -n 0.5 tipc nametable show # optional second terminal
|
||||||
|
uv run python host_b_client.py
|
||||||
```
|
```
|
||||||
|
|
||||||
Note what's absent from both scripts: any IP, hostname or port.
|
Note what's absent from both scripts: any IP, hostname or port.
|
||||||
|
|
@ -116,6 +145,51 @@ Both sides name the *same service*, and the kernel routes it.
|
||||||
Move `host_a_srv.py` to a third node and host B's dial keeps
|
Move `host_a_srv.py` to a third node and host B's dial keeps
|
||||||
working, unchanged.
|
working, unchanged.
|
||||||
|
|
||||||
|
For a first resilience pass, use a local console or separate
|
||||||
|
management link so the test does not cut off your own SSH session:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# host B: record the healthy baseline
|
||||||
|
tipc link list
|
||||||
|
tipc link statistics show
|
||||||
|
|
||||||
|
# either host: withdraw and recreate the bearer
|
||||||
|
sudo tipc bearer disable media eth device "$IFACE"
|
||||||
|
tipc link list
|
||||||
|
sudo tipc bearer enable media eth device "$IFACE"
|
||||||
|
tipc link list
|
||||||
|
|
||||||
|
# prove name withdrawal/republication and RPC recovery
|
||||||
|
tipc nametable show
|
||||||
|
uv run python host_b_client.py
|
||||||
|
```
|
||||||
|
|
||||||
|
Capture `uname -a`, both node addresses, `tipc bearer list`,
|
||||||
|
`tipc link list`, `tipc link statistics show`, the name table and
|
||||||
|
both Python transcripts. Those artifacts distinguish an actor bug
|
||||||
|
from bearer discovery, cluster identity or switch configuration.
|
||||||
|
|
||||||
|
Clean up a disposable Ethernet test on both hosts with:
|
||||||
|
|
||||||
|
```bash
|
||||||
|
sudo tipc bearer disable media eth device "$IFACE"
|
||||||
|
tipc link list
|
||||||
|
```
|
||||||
|
|
||||||
|
Restore any pre-existing network ID only after all bearers are
|
||||||
|
disabled. The first useful automation target is a two-node network
|
||||||
|
namespace fixture that asserts link-up, remote publication, RPC,
|
||||||
|
withdrawal and republication in that order; physical hardware then
|
||||||
|
remains the validation layer for real NIC and switch behaviour.
|
||||||
|
|
||||||
|
The commands above use iproute2's `tipc` frontend, which speaks the
|
||||||
|
kernel's `TIPCv2` generic-netlink family. The planned `pyroute2`
|
||||||
|
dependency already manages WireGuard, interfaces and namespaces and
|
||||||
|
provides generic-netlink primitives, but it does not currently ship a
|
||||||
|
TIPC message codec. Adding one upstream would let `tractor` replace
|
||||||
|
these manual commands with one Python netlink stack instead of
|
||||||
|
shelling out; until then, `tipc(8)` remains the canonical frontend.
|
||||||
|
|
||||||
### over a `wg` mesh
|
### over a `wg` mesh
|
||||||
|
|
||||||
TIPC over WireGuard is the intended reference multihost
|
TIPC over WireGuard is the intended reference multihost
|
||||||
|
|
@ -231,12 +305,10 @@ self-skip when the module is absent.
|
||||||
## CI
|
## CI
|
||||||
|
|
||||||
Single-host TIPC *is* CI-able — the module ships with the
|
Single-host TIPC *is* CI-able — the module ships with the
|
||||||
standard Ubuntu kernel package, so a `sudo modprobe tipc` step
|
standard Ubuntu kernel package. CI loads it with `sudo modprobe
|
||||||
plus a `--tpt-proto tipc` matrix entry should work. That's not
|
tipc` and runs the suite with `--tpt-proto tipc` as a blocking
|
||||||
wired up yet; verify in a throwaway workflow first, and fall
|
matrix leg. Cross-node bearer testing stays manual — this README
|
||||||
back to a container job with `--cap-add NET_ADMIN` if the
|
is that smoke test.
|
||||||
runners refuse. Cross-node (bearer) testing stays manual — this
|
|
||||||
README is that smoke test.
|
|
||||||
|
|
||||||
## normative refs
|
## normative refs
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -47,14 +47,23 @@ async def main() -> None:
|
||||||
reg: TIPCAddress = TIPCAddress.get_root()
|
reg: TIPCAddress = TIPCAddress.get_root()
|
||||||
print(f'host A publishing {reg}')
|
print(f'host A publishing {reg}')
|
||||||
|
|
||||||
async with tractor.open_root_actor(
|
# A registrar root is not an entry in its own
|
||||||
name='host_a',
|
# `Registrar._registry`, so host B cannot discover that root by
|
||||||
|
# its actor name. `open_nursery()` keeps the root as registrar
|
||||||
|
# while the named child below registers as the dialable service.
|
||||||
|
async with tractor.open_nursery(
|
||||||
enable_transports=['tipc'],
|
enable_transports=['tipc'],
|
||||||
registry_addrs=[reg.unwrap()],
|
registry_addrs=[reg.unwrap()],
|
||||||
enable_modules=[__name__],
|
) as an:
|
||||||
):
|
await an.start_actor(
|
||||||
|
'host_a',
|
||||||
|
# Host B imports this same module name to construct the
|
||||||
|
# RPC `NamespacePath`; direct script execution would
|
||||||
|
# otherwise expose it as `__main__` on host A.
|
||||||
|
enable_modules=['host_a_srv'],
|
||||||
|
)
|
||||||
print(
|
print(
|
||||||
'registrar up — `tipc nametable show` on EITHER host\n'
|
'host_a up — `tipc nametable show` on EITHER host\n'
|
||||||
'should now list this service. ctrl-c to stop.'
|
'should now list this service. ctrl-c to stop.'
|
||||||
)
|
)
|
||||||
await trio.sleep_forever()
|
await trio.sleep_forever()
|
||||||
|
|
|
||||||
|
|
@ -16,6 +16,7 @@ from __future__ import annotations
|
||||||
|
|
||||||
import trio
|
import trio
|
||||||
import tractor
|
import tractor
|
||||||
|
from host_a_srv import echo
|
||||||
from tractor.ipc._tipc import (
|
from tractor.ipc._tipc import (
|
||||||
TIPCAddress,
|
TIPCAddress,
|
||||||
is_tipc_available,
|
is_tipc_available,
|
||||||
|
|
@ -39,9 +40,13 @@ async def main() -> None:
|
||||||
' |_does `tipc link list` show the peer?\n'
|
' |_does `tipc link list` show the peer?\n'
|
||||||
)
|
)
|
||||||
|
|
||||||
|
# `.open_context()` derives a `NamespacePath` from a
|
||||||
|
# callable. Importing `echo` also loads its module path
|
||||||
|
# locally, while host A's `enable_modules` authorizes the
|
||||||
|
# corresponding remote callable.
|
||||||
async with (
|
async with (
|
||||||
ptl.open_context(
|
ptl.open_context(
|
||||||
'host_a_srv:echo',
|
echo,
|
||||||
) as (ctx, _),
|
) as (ctx, _),
|
||||||
ctx.open_stream() as stream,
|
ctx.open_stream() as stream,
|
||||||
):
|
):
|
||||||
|
|
|
||||||
|
|
@ -13,7 +13,6 @@ from socket import (
|
||||||
SOCK_STREAM,
|
SOCK_STREAM,
|
||||||
SOL_SOCKET,
|
SOL_SOCKET,
|
||||||
SO_ACCEPTCONN,
|
SO_ACCEPTCONN,
|
||||||
SOL_TIPC,
|
|
||||||
)
|
)
|
||||||
|
|
||||||
import pytest
|
import pytest
|
||||||
|
|
@ -27,8 +26,10 @@ from tractor.discovery._multiaddr import (
|
||||||
parse_maddr,
|
parse_maddr,
|
||||||
)
|
)
|
||||||
from tractor.ipc import _tipc
|
from tractor.ipc import _tipc
|
||||||
|
from tractor.ipc._uds import UDSAddress
|
||||||
from tractor.ipc._tipc import (
|
from tractor.ipc._tipc import (
|
||||||
AF_TIPC,
|
AF_TIPC,
|
||||||
|
SOL_TIPC,
|
||||||
TIPC_ADDR_ID,
|
TIPC_ADDR_ID,
|
||||||
TIPC_ADDR_NAME,
|
TIPC_ADDR_NAME,
|
||||||
TIPC_CLUSTER_SCOPE,
|
TIPC_CLUSTER_SCOPE,
|
||||||
|
|
@ -37,6 +38,9 @@ from tractor.ipc._tipc import (
|
||||||
TIPC_IMPORTANCE,
|
TIPC_IMPORTANCE,
|
||||||
TIPC_NAME_UNKNOWN,
|
TIPC_NAME_UNKNOWN,
|
||||||
TIPC_NODE_SCOPE,
|
TIPC_NODE_SCOPE,
|
||||||
|
TIPC_PUBLISHED,
|
||||||
|
TIPC_SCOPE_UNKNOWN,
|
||||||
|
TIPC_SUBSCR_TIMEOUT,
|
||||||
TIPC_ZONE_SCOPE,
|
TIPC_ZONE_SCOPE,
|
||||||
TRACTOR_STYPE,
|
TRACTOR_STYPE,
|
||||||
MsgpackTIPCStream,
|
MsgpackTIPCStream,
|
||||||
|
|
@ -114,6 +118,29 @@ def test_zone_scope_normalized_to_cluster():
|
||||||
assert addr.is_valid
|
assert addr.is_valid
|
||||||
|
|
||||||
|
|
||||||
|
def test_maddr_parse_normalizes_and_reports_bad_input():
|
||||||
|
'''
|
||||||
|
The interim `/tipc` parser must route through
|
||||||
|
`TIPCAddress.from_addr()` so deprecated zone scope is normalized
|
||||||
|
exactly like every other unwrapped-address entrypoint.
|
||||||
|
|
||||||
|
A malformed segment count previously leaked the tuple-unpacking
|
||||||
|
`ValueError`, which gave callers no indication that the TIPC
|
||||||
|
multiaddr grammar itself was invalid.
|
||||||
|
|
||||||
|
'''
|
||||||
|
addr: TIPCAddress = parse_maddr(
|
||||||
|
f'/tipc/{TRACTOR_STYPE}/7/{TIPC_ZONE_SCOPE}'
|
||||||
|
)
|
||||||
|
assert addr._scope == TIPC_CLUSTER_SCOPE
|
||||||
|
|
||||||
|
with pytest.raises(
|
||||||
|
ValueError,
|
||||||
|
match='Invalid TIPC multiaddr',
|
||||||
|
):
|
||||||
|
parse_maddr('/tipc/not-enough-segments')
|
||||||
|
|
||||||
|
|
||||||
def test_addr_from_bare_port_id_raises():
|
def test_addr_from_bare_port_id_raises():
|
||||||
'''
|
'''
|
||||||
A `TIPC_ADDR_ID` 5-tuple carries no service-name so it can
|
A `TIPC_ADDR_ID` 5-tuple carries no service-name so it can
|
||||||
|
|
@ -207,6 +234,43 @@ def test_get_random_collision_resistance():
|
||||||
assert all(addr.is_valid for addr in addrs)
|
assert all(addr.is_valid for addr in addrs)
|
||||||
|
|
||||||
|
|
||||||
|
def test_get_random_keys_live_actors_by_uuid(
|
||||||
|
monkeypatch: pytest.MonkeyPatch,
|
||||||
|
):
|
||||||
|
'''
|
||||||
|
TIPC names are cluster-wide while PIDs are host-local. Hashing
|
||||||
|
only `(actor name, pid)` therefore made same-named actors with
|
||||||
|
equal PIDs on different hosts publish one service name, where
|
||||||
|
TIPC silently round-robins connects between them.
|
||||||
|
|
||||||
|
Hold the actor name and PID fixed while changing only its UUID;
|
||||||
|
distinct instances prove the globally unique identity field is
|
||||||
|
now part of the derivation.
|
||||||
|
|
||||||
|
'''
|
||||||
|
monkeypatch.setattr(_tipc.os, 'getpid', lambda: 1616)
|
||||||
|
|
||||||
|
def get_addr(uuid: str) -> TIPCAddress:
|
||||||
|
actor = SimpleNamespace(
|
||||||
|
aid=Aid(
|
||||||
|
name='worker',
|
||||||
|
uuid=uuid,
|
||||||
|
pid=1616,
|
||||||
|
)
|
||||||
|
)
|
||||||
|
monkeypatch.setattr(
|
||||||
|
_tipc,
|
||||||
|
'current_actor',
|
||||||
|
lambda **kwargs: actor,
|
||||||
|
)
|
||||||
|
return TIPCAddress.get_random()
|
||||||
|
|
||||||
|
first: TIPCAddress = get_addr('actor-uuid-a')
|
||||||
|
second: TIPCAddress = get_addr('actor-uuid-b')
|
||||||
|
assert first._instance != second._instance
|
||||||
|
assert get_addr('actor-uuid-a')._instance == first._instance
|
||||||
|
|
||||||
|
|
||||||
def test_get_random_honors_bindspace():
|
def test_get_random_honors_bindspace():
|
||||||
addr: TIPCAddress = TIPCAddress.get_random(
|
addr: TIPCAddress = TIPCAddress.get_random(
|
||||||
bindspace=TIPC_NODE_SCOPE,
|
bindspace=TIPC_NODE_SCOPE,
|
||||||
|
|
@ -235,6 +299,12 @@ def test_wrap_address_dispatches_on_the_proto_key():
|
||||||
'tipc', TRACTOR_STYPE, 1616, TIPC_CLUSTER_SCOPE,
|
'tipc', TRACTOR_STYPE, 1616, TIPC_CLUSTER_SCOPE,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
# A UDS directory named `tipc` is still a valid classic
|
||||||
|
# 2-element address, not a malformed proto-keyed TIPC one.
|
||||||
|
uds: UDSAddress = wrap_address(('tipc', 'actor.sock'))
|
||||||
|
assert isinstance(uds, UDSAddress)
|
||||||
|
assert UDSAddress.unwrapped_type == tuple[str, str]
|
||||||
|
|
||||||
|
|
||||||
def test_maddr_roundtrip():
|
def test_maddr_roundtrip():
|
||||||
'''
|
'''
|
||||||
|
|
@ -286,6 +356,97 @@ def test_eafnosupport_is_actionable_connerr(
|
||||||
assert type(excinfo.value.__cause__) is OSError
|
assert type(excinfo.value.__cause__) is OSError
|
||||||
|
|
||||||
|
|
||||||
|
def test_availability_probe_is_linux_only(
|
||||||
|
monkeypatch: pytest.MonkeyPatch,
|
||||||
|
):
|
||||||
|
'''
|
||||||
|
The fallback `AF_TIPC` integer keeps imports portable but can
|
||||||
|
alias an unrelated socket family on another OS. Socket creation
|
||||||
|
alone must never turn that numeric collision into a false TIPC
|
||||||
|
capability result.
|
||||||
|
|
||||||
|
Simulate Darwin with a socket constructor that would otherwise
|
||||||
|
succeed; proving it is never called pins the platform gate ahead
|
||||||
|
of the syscall probe.
|
||||||
|
|
||||||
|
'''
|
||||||
|
socket_called: bool = False
|
||||||
|
|
||||||
|
def fake_socket(*args, **kwargs):
|
||||||
|
nonlocal socket_called
|
||||||
|
socket_called = True
|
||||||
|
|
||||||
|
monkeypatch.setattr(_tipc, '_tipc_avail', None)
|
||||||
|
monkeypatch.setattr(_tipc.sys, 'platform', 'darwin')
|
||||||
|
monkeypatch.setattr(_tipc.socket, 'socket', fake_socket)
|
||||||
|
|
||||||
|
assert not is_tipc_available()
|
||||||
|
assert not socket_called
|
||||||
|
|
||||||
|
|
||||||
|
def test_connect_reuses_tolerant_peer_observation(
|
||||||
|
monkeypatch: pytest.MonkeyPatch,
|
||||||
|
):
|
||||||
|
'''
|
||||||
|
A TIPC peer can withdraw immediately after `.connect()`. The
|
||||||
|
transport constructor already tolerates that race, but the dial
|
||||||
|
path used to call `getpeername()` a second time and leak a raw
|
||||||
|
`ENOTCONN` after an otherwise successful connection.
|
||||||
|
|
||||||
|
The fake socket permits exactly the constructor's first peer
|
||||||
|
lookup. A second lookup raises deterministically, so successful
|
||||||
|
construction proves `connect_to()` reuses the tolerant observed
|
||||||
|
address and transfers socket ownership only after setup.
|
||||||
|
|
||||||
|
'''
|
||||||
|
class _DropAfterObservation:
|
||||||
|
def __init__(self):
|
||||||
|
self.peer_lookups: int = 0
|
||||||
|
self.closed: bool = False
|
||||||
|
|
||||||
|
def setsockopt(self, *args) -> None:
|
||||||
|
pass
|
||||||
|
|
||||||
|
async def connect(self, addr) -> None:
|
||||||
|
pass
|
||||||
|
|
||||||
|
def getsockname(self) -> tuple[int, int, int, int, int]:
|
||||||
|
return (TIPC_ADDR_ID, 1, 2, 0, TIPC_CLUSTER_SCOPE)
|
||||||
|
|
||||||
|
def getpeername(self) -> tuple[int, int, int, int, int]:
|
||||||
|
self.peer_lookups += 1
|
||||||
|
if self.peer_lookups > 1:
|
||||||
|
raise OSError(errno.ENOTCONN, 'peer withdrew')
|
||||||
|
return (TIPC_ADDR_ID, 3, 4, 0, TIPC_CLUSTER_SCOPE)
|
||||||
|
|
||||||
|
def close(self) -> None:
|
||||||
|
self.closed = True
|
||||||
|
|
||||||
|
async def main() -> None:
|
||||||
|
sock = _DropAfterObservation()
|
||||||
|
monkeypatch.setattr(
|
||||||
|
_tipc.trio_socket,
|
||||||
|
'socket',
|
||||||
|
lambda *args: sock,
|
||||||
|
)
|
||||||
|
monkeypatch.setattr(
|
||||||
|
_tipc.trio,
|
||||||
|
'SocketStream',
|
||||||
|
lambda raw_sock: SimpleNamespace(socket=raw_sock),
|
||||||
|
)
|
||||||
|
|
||||||
|
addr: TIPCAddress = TIPCAddress.get_root()
|
||||||
|
stream: MsgpackTIPCStream = (
|
||||||
|
await MsgpackTIPCStream.connect_to(addr)
|
||||||
|
)
|
||||||
|
assert sock.peer_lookups == 1
|
||||||
|
assert stream.raddr.unwrap() == addr.unwrap()
|
||||||
|
assert stream.raddr.maybe_ref == 4
|
||||||
|
assert not sock.closed
|
||||||
|
|
||||||
|
trio.run(main)
|
||||||
|
|
||||||
|
|
||||||
# ------------------------------------------------------------------
|
# ------------------------------------------------------------------
|
||||||
# kernel-touching
|
# kernel-touching
|
||||||
# ------------------------------------------------------------------
|
# ------------------------------------------------------------------
|
||||||
|
|
@ -658,6 +819,22 @@ def test_topology_struct_layouts():
|
||||||
assert len(sub) == 28
|
assert len(sub) == 28
|
||||||
|
|
||||||
|
|
||||||
|
def _pack_topology_event(
|
||||||
|
event: int,
|
||||||
|
instance: int = 71,
|
||||||
|
) -> bytes:
|
||||||
|
return struct.pack(
|
||||||
|
_tipc._EVENT_FMT,
|
||||||
|
event,
|
||||||
|
instance,
|
||||||
|
instance,
|
||||||
|
123,
|
||||||
|
456,
|
||||||
|
0, 0, 0, 0, 0,
|
||||||
|
b'\0' * 8,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
def test_wait_forever_is_masked_for_packing():
|
def test_wait_forever_is_masked_for_packing():
|
||||||
'''
|
'''
|
||||||
Python exposes `TIPC_WAIT_FOREVER` as `-1`, which `struct`
|
Python exposes `TIPC_WAIT_FOREVER` as `-1`, which `struct`
|
||||||
|
|
@ -689,7 +866,6 @@ def test_decode_name_event_rejects_junk():
|
||||||
assert _tipc._decode_name_event(
|
assert _tipc._decode_name_event(
|
||||||
b'\x00' * 12,
|
b'\x00' * 12,
|
||||||
stype=TRACTOR_STYPE,
|
stype=TRACTOR_STYPE,
|
||||||
scope=TIPC_CLUSTER_SCOPE,
|
|
||||||
) is None
|
) is None
|
||||||
|
|
||||||
bogus: bytes = struct.pack(
|
bogus: bytes = struct.pack(
|
||||||
|
|
@ -702,10 +878,113 @@ def test_decode_name_event_rejects_junk():
|
||||||
assert _tipc._decode_name_event(
|
assert _tipc._decode_name_event(
|
||||||
bogus,
|
bogus,
|
||||||
stype=TRACTOR_STYPE,
|
stype=TRACTOR_STYPE,
|
||||||
scope=TIPC_CLUSTER_SCOPE,
|
|
||||||
) is None
|
) is None
|
||||||
|
|
||||||
|
|
||||||
|
def test_topology_event_scope_is_unknown():
|
||||||
|
'''
|
||||||
|
Neither `struct tipc_subscr` nor `struct tipc_event` carries a
|
||||||
|
publication scope. The old decoder copied caller context into
|
||||||
|
each `TIPCAddress`, falsely presenting cluster scope as kernel-
|
||||||
|
observed data even for a node-scoped publisher.
|
||||||
|
|
||||||
|
Decode a valid publication and assert its address uses the
|
||||||
|
explicit unknown sentinel rather than inventing reachability.
|
||||||
|
|
||||||
|
TIPC address types and publication scopes:
|
||||||
|
https://docs.kernel.org/networking/tipc.html
|
||||||
|
Event wire format (which has no scope field):
|
||||||
|
https://github.com/torvalds/linux/blob/master/include/uapi/linux/tipc.h
|
||||||
|
|
||||||
|
'''
|
||||||
|
event: _tipc.TIPCNameEvent|None = _tipc._decode_name_event(
|
||||||
|
_pack_topology_event(TIPC_PUBLISHED),
|
||||||
|
stype=TRACTOR_STYPE,
|
||||||
|
)
|
||||||
|
assert event is not None
|
||||||
|
assert event.addr._scope == TIPC_SCOPE_UNKNOWN
|
||||||
|
assert not event.addr.is_valid
|
||||||
|
|
||||||
|
|
||||||
|
def test_topology_stream_surfaces_overflow():
|
||||||
|
'''
|
||||||
|
Topology transitions are `TIPC_PUBLISHED`/`TIPC_WITHDRAWN`
|
||||||
|
changes to the set of ports matching a subscribed name sequence,
|
||||||
|
as emitted by the kernel topology server:
|
||||||
|
https://github.com/torvalds/linux/blob/master/net/tipc/topsrv.c
|
||||||
|
|
||||||
|
Blocking this reader on `tx.send()` stops draining the topology
|
||||||
|
socket and merely pushes pressure into the kernel queue. Silently
|
||||||
|
dropping with `send_nowait()` is worse: a push registry keeps a
|
||||||
|
stale view without knowing it missed a transition.
|
||||||
|
|
||||||
|
A zero-capacity channel deterministically fills the user-space
|
||||||
|
boundary. The dedicated overflow error proves the reader remains
|
||||||
|
non-blocking while forcing consumers to resubscribe and rebuild
|
||||||
|
instead of trusting incomplete state.
|
||||||
|
|
||||||
|
'''
|
||||||
|
class _OneEventSocket:
|
||||||
|
def __init__(self):
|
||||||
|
self.sent: bool = False
|
||||||
|
|
||||||
|
async def recv(self, size: int) -> bytes:
|
||||||
|
if not self.sent:
|
||||||
|
self.sent = True
|
||||||
|
return _pack_topology_event(TIPC_PUBLISHED)
|
||||||
|
raise AssertionError('reader continued after overflow')
|
||||||
|
|
||||||
|
async def main() -> None:
|
||||||
|
tx, rx = trio.open_memory_channel(0)
|
||||||
|
with pytest.raises(
|
||||||
|
_tipc.TIPCNameEventOverflow,
|
||||||
|
match='resubscribe and rebuild',
|
||||||
|
) as excinfo:
|
||||||
|
await _tipc._stream_name_events(
|
||||||
|
_OneEventSocket(),
|
||||||
|
TRACTOR_STYPE,
|
||||||
|
tx,
|
||||||
|
)
|
||||||
|
assert excinfo.value.event.kind == 'published'
|
||||||
|
with pytest.raises(trio.EndOfChannel):
|
||||||
|
await rx.receive()
|
||||||
|
|
||||||
|
trio.run(main)
|
||||||
|
|
||||||
|
|
||||||
|
def test_topology_timeout_closes_stream():
|
||||||
|
'''
|
||||||
|
A finite kernel subscription expires after its timeout event.
|
||||||
|
The old reader forwarded that event and waited forever for a
|
||||||
|
second frame that could never arrive, so consumers blocked on a
|
||||||
|
channel that looked live despite having no subscription.
|
||||||
|
|
||||||
|
Feed one timeout frame directly to the reader; receiving that
|
||||||
|
event followed by `EndOfChannel` proves the stream terminates at
|
||||||
|
the kernel subscription boundary.
|
||||||
|
|
||||||
|
Subscription timeout semantics:
|
||||||
|
https://github.com/torvalds/linux/blob/master/include/uapi/linux/tipc.h
|
||||||
|
|
||||||
|
'''
|
||||||
|
class _TimeoutSocket:
|
||||||
|
async def recv(self, size: int) -> bytes:
|
||||||
|
return _pack_topology_event(TIPC_SUBSCR_TIMEOUT)
|
||||||
|
|
||||||
|
async def main() -> None:
|
||||||
|
tx, rx = trio.open_memory_channel(1)
|
||||||
|
await _tipc._stream_name_events(
|
||||||
|
_TimeoutSocket(),
|
||||||
|
TRACTOR_STYPE,
|
||||||
|
tx,
|
||||||
|
)
|
||||||
|
assert (await rx.receive()).kind == 'timeout'
|
||||||
|
with pytest.raises(trio.EndOfChannel):
|
||||||
|
await rx.receive()
|
||||||
|
|
||||||
|
trio.run(main)
|
||||||
|
|
||||||
|
|
||||||
@requires_tipc
|
@requires_tipc
|
||||||
def test_topology_reports_publish_and_withdraw():
|
def test_topology_reports_publish_and_withdraw():
|
||||||
'''
|
'''
|
||||||
|
|
@ -739,6 +1018,7 @@ def test_topology_reports_publish_and_withdraw():
|
||||||
for ev in got:
|
for ev in got:
|
||||||
assert ev.addr._instance == addr._instance
|
assert ev.addr._instance == addr._instance
|
||||||
assert ev.addr._stype == addr._stype
|
assert ev.addr._stype == addr._stype
|
||||||
|
assert ev.addr._scope == TIPC_SCOPE_UNKNOWN
|
||||||
assert isinstance(ev.ref, int)
|
assert isinstance(ev.ref, int)
|
||||||
# both transitions name the SAME publisher port
|
# both transitions name the SAME publisher port
|
||||||
assert got[0].ref == got[1].ref
|
assert got[0].ref == got[1].ref
|
||||||
|
|
|
||||||
|
|
@ -19,6 +19,7 @@ from tractor.discovery import (
|
||||||
)
|
)
|
||||||
from tractor.ipc import (
|
from tractor.ipc import (
|
||||||
_tcp,
|
_tcp,
|
||||||
|
_tipc,
|
||||||
_uds,
|
_uds,
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
@ -271,13 +272,16 @@ def test_lazy_annotation_names_resolve():
|
||||||
introspection.
|
introspection.
|
||||||
|
|
||||||
'''
|
'''
|
||||||
assert get_type_hints(_multiaddr.mk_maddr)['return'] is Any
|
assert get_type_hints(_multiaddr.mk_maddr)['return'] == Any|str
|
||||||
assert get_type_hints(_tcp.MsgpackTCPStream.maddr.fget)[
|
assert get_type_hints(_tcp.MsgpackTCPStream.maddr.fget)[
|
||||||
'return'
|
'return'
|
||||||
] is Any
|
] is Any
|
||||||
assert get_type_hints(_uds.MsgpackUDSStream.maddr.fget)[
|
assert get_type_hints(_uds.MsgpackUDSStream.maddr.fget)[
|
||||||
'return'
|
'return'
|
||||||
] == Any|str
|
] == Any|str
|
||||||
|
assert get_type_hints(_tipc.MsgpackTIPCStream.maddr.fget)[
|
||||||
|
'return'
|
||||||
|
] == Any|str
|
||||||
assert get_type_hints(_addr.Address.get_random)[
|
assert get_type_hints(_addr.Address.get_random)[
|
||||||
'current_actor'
|
'current_actor'
|
||||||
] is Any
|
] is Any
|
||||||
|
|
|
||||||
|
|
@ -330,7 +330,11 @@ def wrap_address(
|
||||||
#
|
#
|
||||||
# NOTE, a bare seq-pattern matches `list` too, which is
|
# NOTE, a bare seq-pattern matches `list` too, which is
|
||||||
# what `msgpack` decodes our tuples back to.
|
# what `msgpack` decodes our tuples back to.
|
||||||
case ('tipc', *_):
|
case (
|
||||||
|
('tipc', int(), int())
|
||||||
|
|
|
||||||
|
('tipc', int(), int(), int())
|
||||||
|
):
|
||||||
cls = TIPCAddress
|
cls = TIPCAddress
|
||||||
|
|
||||||
# classic network socket-address as tuple/list
|
# classic network socket-address as tuple/list
|
||||||
|
|
|
||||||
|
|
@ -83,6 +83,9 @@ def mk_maddr(
|
||||||
dispatching on the `.proto_key` to build the correct
|
dispatching on the `.proto_key` to build the correct
|
||||||
multiaddr-spec-compliant protocol path.
|
multiaddr-spec-compliant protocol path.
|
||||||
|
|
||||||
|
Return a `Multiaddr` for registered protocols. TIPC remains
|
||||||
|
an interim `str` until its upstream multiaddr protocol lands.
|
||||||
|
|
||||||
'''
|
'''
|
||||||
from multiaddr import Multiaddr
|
from multiaddr import Multiaddr
|
||||||
|
|
||||||
|
|
@ -154,12 +157,18 @@ def parse_maddr(
|
||||||
# XXX MUST come before `Multiaddr()` which rejects the
|
# XXX MUST come before `Multiaddr()` which rejects the
|
||||||
# not-yet-registered `/tipc` proto name outright.
|
# not-yet-registered `/tipc` proto name outright.
|
||||||
if maddr_str.startswith(_tipc_maddr_prefix):
|
if maddr_str.startswith(_tipc_maddr_prefix):
|
||||||
_, _, stype, instance, scope = maddr_str.split('/')
|
try:
|
||||||
return TIPCAddress(
|
_, _, stype, instance, scope = maddr_str.split('/')
|
||||||
_stype=int(stype),
|
return TIPCAddress.from_addr((
|
||||||
_instance=int(instance),
|
'tipc',
|
||||||
_scope=int(scope),
|
int(stype),
|
||||||
)
|
int(instance),
|
||||||
|
int(scope),
|
||||||
|
))
|
||||||
|
except (TypeError, ValueError) as src_err:
|
||||||
|
raise ValueError(
|
||||||
|
f'Invalid TIPC multiaddr: {maddr_str!r}'
|
||||||
|
) from src_err
|
||||||
|
|
||||||
try:
|
try:
|
||||||
maddr = Multiaddr(maddr_str)
|
maddr = Multiaddr(maddr_str)
|
||||||
|
|
|
||||||
|
|
@ -57,7 +57,9 @@ from socket import (
|
||||||
SOCK_STREAM,
|
SOCK_STREAM,
|
||||||
)
|
)
|
||||||
import struct
|
import struct
|
||||||
|
import sys
|
||||||
from typing import (
|
from typing import (
|
||||||
|
Any,
|
||||||
AsyncGenerator,
|
AsyncGenerator,
|
||||||
Callable,
|
Callable,
|
||||||
ClassVar,
|
ClassVar,
|
||||||
|
|
@ -74,10 +76,8 @@ from trio import (
|
||||||
SocketListener,
|
SocketListener,
|
||||||
)
|
)
|
||||||
|
|
||||||
from multiaddr import Multiaddr
|
|
||||||
from tractor.msg import MsgCodec
|
from tractor.msg import MsgCodec
|
||||||
from tractor.log import get_logger
|
from tractor.log import get_logger
|
||||||
from tractor.discovery._multiaddr import mk_maddr
|
|
||||||
from tractor.ipc._transport import (
|
from tractor.ipc._transport import (
|
||||||
MsgpackTransport,
|
MsgpackTransport,
|
||||||
)
|
)
|
||||||
|
|
@ -87,8 +87,13 @@ from tractor.runtime._state import (
|
||||||
)
|
)
|
||||||
|
|
||||||
if TYPE_CHECKING:
|
if TYPE_CHECKING:
|
||||||
|
# ONLY type-annots, the eager import costs
|
||||||
|
# `import tractor` wall-time (gh #470).
|
||||||
|
from multiaddr import Multiaddr
|
||||||
from tractor.discovery._addr import TaggedTIPCAddress
|
from tractor.discovery._addr import TaggedTIPCAddress
|
||||||
from tractor.runtime._runtime import Actor
|
from tractor.runtime._runtime import Actor
|
||||||
|
else:
|
||||||
|
Multiaddr = Any
|
||||||
|
|
||||||
|
|
||||||
log = get_logger()
|
log = get_logger()
|
||||||
|
|
@ -167,6 +172,10 @@ _tipc_reserved_stypes: range = range(0, 64)
|
||||||
# See `MsgpackTIPCStream.get_stream_addrs()` and plan 01 §3.4.
|
# See `MsgpackTIPCStream.get_stream_addrs()` and plan 01 §3.4.
|
||||||
TIPC_NAME_UNKNOWN: int = -1
|
TIPC_NAME_UNKNOWN: int = -1
|
||||||
|
|
||||||
|
# The topology event wire format carries no publication scope.
|
||||||
|
# Never promote caller context into observed address data.
|
||||||
|
TIPC_SCOPE_UNKNOWN: int = 0
|
||||||
|
|
||||||
# XXX, the kernel default (`TIPC_LOW_IMPORTANCE`), i.e. today this
|
# XXX, the kernel default (`TIPC_LOW_IMPORTANCE`), i.e. today this
|
||||||
# is a no-op knob preserving stock behaviour.
|
# is a no-op knob preserving stock behaviour.
|
||||||
#
|
#
|
||||||
|
|
@ -178,6 +187,7 @@ TIPC_NAME_UNKNOWN: int = -1
|
||||||
TRACTOR_DEF_IMPORTANCE: int = TIPC_LOW_IMPORTANCE
|
TRACTOR_DEF_IMPORTANCE: int = TIPC_LOW_IMPORTANCE
|
||||||
|
|
||||||
_scope_names: dict[int, str] = {
|
_scope_names: dict[int, str] = {
|
||||||
|
TIPC_SCOPE_UNKNOWN: 'unknown',
|
||||||
TIPC_ZONE_SCOPE: 'zone',
|
TIPC_ZONE_SCOPE: 'zone',
|
||||||
TIPC_CLUSTER_SCOPE: 'cluster',
|
TIPC_CLUSTER_SCOPE: 'cluster',
|
||||||
TIPC_NODE_SCOPE: 'node',
|
TIPC_NODE_SCOPE: 'node',
|
||||||
|
|
@ -198,6 +208,10 @@ def is_tipc_available() -> bool:
|
||||||
|
|
||||||
'''
|
'''
|
||||||
global _tipc_avail
|
global _tipc_avail
|
||||||
|
if sys.platform != 'linux':
|
||||||
|
_tipc_avail = False
|
||||||
|
return _tipc_avail
|
||||||
|
|
||||||
if _tipc_avail is None:
|
if _tipc_avail is None:
|
||||||
try:
|
try:
|
||||||
socket.socket(
|
socket.socket(
|
||||||
|
|
@ -341,8 +355,8 @@ class TIPCAddress(
|
||||||
|
|
||||||
def with_port_id(
|
def with_port_id(
|
||||||
self,
|
self,
|
||||||
node: int,
|
node: int|None,
|
||||||
ref: int,
|
ref: int|None,
|
||||||
) -> TIPCAddress:
|
) -> TIPCAddress:
|
||||||
'''
|
'''
|
||||||
A copy annotated with an *observed* `TIPC_ADDR_ID`
|
A copy annotated with an *observed* `TIPC_ADDR_ID`
|
||||||
|
|
@ -370,10 +384,11 @@ class TIPCAddress(
|
||||||
between them (verified). I.e. a collision manifests as
|
between them (verified). I.e. a collision manifests as
|
||||||
*silent crosstalk*, not an error.
|
*silent crosstalk*, not an error.
|
||||||
|
|
||||||
So the instance is a `blake2b` digest of a per-call-unique
|
So the instance is a `blake2b` digest of the actor UUID, or
|
||||||
seed, giving a well-spread 32b value. Being a pure fn of the
|
a per-call token outside a live runtime, giving a well-spread
|
||||||
seed it is also *reproducible*, which the (follow-up)
|
32b value. Being a pure fn of the seed it is also
|
||||||
registrar-less discovery fast-path wants.
|
*reproducible*, which the (follow-up) registrar-less
|
||||||
|
discovery fast-path wants.
|
||||||
|
|
||||||
NOTE the residual risk is birthday-bounded: ~1.2e-2 for 10k
|
NOTE the residual risk is birthday-bounded: ~1.2e-2 for 10k
|
||||||
names sharing one `_stype`. See plan 01 §9 for the
|
names sharing one `_stype`. See plan 01 §9 for the
|
||||||
|
|
@ -385,7 +400,7 @@ class TIPCAddress(
|
||||||
err_on_no_runtime=False,
|
err_on_no_runtime=False,
|
||||||
)
|
)
|
||||||
if actor:
|
if actor:
|
||||||
seed: str = f'{actor.aid.name}@{pid}'
|
seed: str = '.'.join(actor.aid.uid)
|
||||||
else:
|
else:
|
||||||
if is_root_process():
|
if is_root_process():
|
||||||
prefix: str = 'no_runtime_root'
|
prefix: str = 'no_runtime_root'
|
||||||
|
|
@ -629,6 +644,8 @@ class MsgpackTIPCStream(MsgpackTransport):
|
||||||
|
|
||||||
@property
|
@property
|
||||||
def maddr(self) -> Multiaddr|str:
|
def maddr(self) -> Multiaddr|str:
|
||||||
|
from tractor.net import mk_maddr
|
||||||
|
|
||||||
if not self.raddr:
|
if not self.raddr:
|
||||||
return '<unknown-peer>'
|
return '<unknown-peer>'
|
||||||
|
|
||||||
|
|
@ -683,22 +700,39 @@ class MsgpackTIPCStream(MsgpackTransport):
|
||||||
destaddr._scope,
|
destaddr._scope,
|
||||||
))
|
))
|
||||||
|
|
||||||
tpt_stream = MsgpackTIPCStream(
|
tpt_stream = MsgpackTIPCStream(
|
||||||
trio.SocketStream(sock),
|
trio.SocketStream(sock),
|
||||||
prefix_size=prefix_size,
|
prefix_size=prefix_size,
|
||||||
codec=codec,
|
codec=codec,
|
||||||
)
|
)
|
||||||
# XXX, the dialling side is the ONLY side that knows the
|
# XXX, the dialling side is the ONLY side that knows
|
||||||
# peer's *service name* (a port-id can't be reversed into
|
# the peer's *service name* (a port-id can't be
|
||||||
# one), so re-assert it over the observed-only `._raddr`
|
# reversed into one), so re-assert it over the
|
||||||
# that `.get_stream_addrs()` just derived.
|
# observed-only `._raddr` derived above.
|
||||||
#
|
#
|
||||||
# Same move as `MsgpackUDSStream.connect_to()`s peer-pid
|
# Reuse that tolerant observation: a peer can withdraw
|
||||||
# re-assign.
|
# between `.connect()` and a second `.getpeername()`.
|
||||||
tpt_stream._raddr = destaddr.with_port_id(
|
#
|
||||||
*_port_id(sock.getpeername()),
|
# Peer / kernel dial task
|
||||||
)
|
# | |
|
||||||
return tpt_stream
|
# |<----- connect(name) -------|
|
||||||
|
# |------ connected ---------->| (A)
|
||||||
|
# |<----- getpeername() -------| (B, ctor)
|
||||||
|
# |-- port-id or `ENOTCONN` -->|
|
||||||
|
# X withdraws |
|
||||||
|
# |<----- getpeername() -------| (C, old code)
|
||||||
|
# |------ `ENOTCONN` --------->|
|
||||||
|
#
|
||||||
|
# If withdrawal precedes B, `_maybe_sockaddr()` records
|
||||||
|
# no port-id and the handshake observes the close. If it
|
||||||
|
# follows B, that first observation remains useful. The
|
||||||
|
# removed C lookup created the only raw-`ENOTCONN` race.
|
||||||
|
observed_raddr: TIPCAddress = tpt_stream._raddr
|
||||||
|
tpt_stream._raddr = destaddr.with_port_id(
|
||||||
|
node=observed_raddr.maybe_node,
|
||||||
|
ref=observed_raddr.maybe_ref,
|
||||||
|
)
|
||||||
|
return tpt_stream
|
||||||
|
|
||||||
@classmethod
|
@classmethod
|
||||||
def get_stream_addrs(
|
def get_stream_addrs(
|
||||||
|
|
@ -848,8 +882,17 @@ class TIPCNameEvent(
|
||||||
frozen=True,
|
frozen=True,
|
||||||
):
|
):
|
||||||
'''
|
'''
|
||||||
A kernel name-table transition: some service name was
|
A kernel name-table transition, not an application msg.
|
||||||
published or withdrawn somewhere in the cluster.
|
|
||||||
|
A transition reports that the set of TIPC ports matching a
|
||||||
|
subscribed service-name sequence changed: `TIPC_PUBLISHED`
|
||||||
|
adds a matching `(node, ref)`, `TIPC_WITHDRAWN` removes one,
|
||||||
|
and `TIPC_SUBSCR_TIMEOUT` ends a finite subscription.
|
||||||
|
|
||||||
|
Wire definitions:
|
||||||
|
https://github.com/torvalds/linux/blob/master/include/uapi/linux/tipc.h
|
||||||
|
Topology server:
|
||||||
|
https://github.com/torvalds/linux/blob/master/net/tipc/topsrv.c
|
||||||
|
|
||||||
'''
|
'''
|
||||||
kind: Literal[
|
kind: Literal[
|
||||||
|
|
@ -870,6 +913,28 @@ class TIPCNameEvent(
|
||||||
)
|
)
|
||||||
|
|
||||||
|
|
||||||
|
class TIPCNameEventOverflow(RuntimeError):
|
||||||
|
'''
|
||||||
|
The user-space event buffer lost authoritative continuity.
|
||||||
|
|
||||||
|
The socket reader must not remain blocked while its kernel
|
||||||
|
topology subscription is live. Raising aborts that subscription
|
||||||
|
and forces the consumer to resubscribe and rebuild its name-table
|
||||||
|
view instead of using silently stale state.
|
||||||
|
|
||||||
|
'''
|
||||||
|
def __init__(
|
||||||
|
self,
|
||||||
|
event: TIPCNameEvent,
|
||||||
|
) -> None:
|
||||||
|
self.event = event
|
||||||
|
super().__init__(
|
||||||
|
'TIPC topology event buffer overflowed; '
|
||||||
|
'resubscribe and rebuild the name-table view.\n'
|
||||||
|
f'lost event: {event!r}'
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
def _mk_subscr(
|
def _mk_subscr(
|
||||||
stype: int,
|
stype: int,
|
||||||
lower: int,
|
lower: int,
|
||||||
|
|
@ -904,7 +969,6 @@ def _mk_subscr(
|
||||||
def _decode_name_event(
|
def _decode_name_event(
|
||||||
raw: bytes,
|
raw: bytes,
|
||||||
stype: int,
|
stype: int,
|
||||||
scope: int,
|
|
||||||
) -> TIPCNameEvent|None:
|
) -> TIPCNameEvent|None:
|
||||||
'''
|
'''
|
||||||
Decode one `struct tipc_event`, or `None` if it's a runt/
|
Decode one `struct tipc_event`, or `None` if it's a runt/
|
||||||
|
|
@ -939,14 +1003,12 @@ def _decode_name_event(
|
||||||
# NOTE, `tractor` only ever publishes *singleton* ranges
|
# NOTE, `tractor` only ever publishes *singleton* ranges
|
||||||
# (`lower == upper`) so the lower bound IS the instance.
|
# (`lower == upper`) so the lower bound IS the instance.
|
||||||
#
|
#
|
||||||
# XXX the event carries NO scope — the name-table doesn't
|
# XXX the event carries NO scope — do not fabricate one
|
||||||
# report it — so we echo back the subscription's own. Fine
|
# from caller context and present it as observed data.
|
||||||
# for our use (we subscribe per-scope) but don't mistake
|
|
||||||
# it for observed data.
|
|
||||||
addr=TIPCAddress(
|
addr=TIPCAddress(
|
||||||
_stype=stype,
|
_stype=stype,
|
||||||
_instance=found_lower,
|
_instance=found_lower,
|
||||||
_scope=scope,
|
_scope=TIPC_SCOPE_UNKNOWN,
|
||||||
),
|
),
|
||||||
node=node,
|
node=node,
|
||||||
ref=ref,
|
ref=ref,
|
||||||
|
|
@ -956,7 +1018,6 @@ def _decode_name_event(
|
||||||
async def _stream_name_events(
|
async def _stream_name_events(
|
||||||
sock,
|
sock,
|
||||||
stype: int,
|
stype: int,
|
||||||
scope: int,
|
|
||||||
tx: trio.MemorySendChannel,
|
tx: trio.MemorySendChannel,
|
||||||
) -> None:
|
) -> None:
|
||||||
'''
|
'''
|
||||||
|
|
@ -973,21 +1034,15 @@ async def _stream_name_events(
|
||||||
if (ev := _decode_name_event(
|
if (ev := _decode_name_event(
|
||||||
raw,
|
raw,
|
||||||
stype=stype,
|
stype=stype,
|
||||||
scope=scope,
|
|
||||||
)) is None:
|
)) is None:
|
||||||
continue
|
continue
|
||||||
|
|
||||||
try:
|
try:
|
||||||
tx.send_nowait(ev)
|
tx.send_nowait(ev)
|
||||||
except trio.WouldBlock:
|
except trio.WouldBlock as src_err:
|
||||||
# XXX drop rather than block: stalling this reader
|
raise TIPCNameEventOverflow(ev) from src_err
|
||||||
# backs up the kernel's own queue and we'd lose the
|
if ev.kind == 'timeout':
|
||||||
# event anyway, just less visibly.
|
return
|
||||||
log.warning(
|
|
||||||
f'TIPC topology event buffer full, dropping!\n'
|
|
||||||
f'{ev}\n'
|
|
||||||
f' |_raise `buf_size` or consume faster\n'
|
|
||||||
)
|
|
||||||
|
|
||||||
except (
|
except (
|
||||||
trio.ClosedResourceError,
|
trio.ClosedResourceError,
|
||||||
|
|
@ -1006,7 +1061,6 @@ async def open_topology_events(
|
||||||
lower: int = 0,
|
lower: int = 0,
|
||||||
upper: int = 0xFFFF_FFFF,
|
upper: int = 0xFFFF_FFFF,
|
||||||
filt: int = TIPC_SUB_SERVICE,
|
filt: int = TIPC_SUB_SERVICE,
|
||||||
scope: int = TIPC_CLUSTER_SCOPE,
|
|
||||||
timeout: int = TIPC_WAIT_FOREVER,
|
timeout: int = TIPC_WAIT_FOREVER,
|
||||||
buf_size: int = 64,
|
buf_size: int = 64,
|
||||||
) -> AsyncGenerator[
|
) -> AsyncGenerator[
|
||||||
|
|
@ -1035,7 +1089,7 @@ async def open_topology_events(
|
||||||
topsrv_addr = TIPCAddress(
|
topsrv_addr = TIPCAddress(
|
||||||
_stype=TIPC_TOP_SRV,
|
_stype=TIPC_TOP_SRV,
|
||||||
_instance=TIPC_TOP_SRV,
|
_instance=TIPC_TOP_SRV,
|
||||||
_scope=scope,
|
_scope=TIPC_CLUSTER_SCOPE,
|
||||||
)
|
)
|
||||||
sock = trio_socket.socket(
|
sock = trio_socket.socket(
|
||||||
AF_TIPC,
|
AF_TIPC,
|
||||||
|
|
@ -1078,7 +1132,6 @@ async def open_topology_events(
|
||||||
_stream_name_events,
|
_stream_name_events,
|
||||||
sock,
|
sock,
|
||||||
stype,
|
stype,
|
||||||
scope,
|
|
||||||
tx,
|
tx,
|
||||||
)
|
)
|
||||||
try:
|
try:
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue