Compare commits
23
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
3f3654f679 | ||
|
|
e2323779d4 | ||
|
|
8c03e57990 | ||
|
|
6d11fad288 | ||
|
|
b3d8df0c37 | ||
|
|
2422bb3664 | ||
|
|
54fc5a0bf3 | ||
|
|
8196d6fc98 | ||
|
|
41dda224fc | ||
|
|
7541387d7c | ||
|
|
24af88be1d | ||
|
|
f7e26d9d07 | ||
|
|
b7dfe1d95b | ||
|
|
e038a44cb6 | ||
|
|
4ecc1fd752 | ||
|
|
fee4d31971 | ||
|
|
5b4bc4b72f | ||
|
|
a37b20979d | ||
|
|
af4a917d92 | ||
|
|
1cac244259 | ||
|
|
03d560eb10 | ||
|
|
fb58bac89d | ||
|
|
78b8ae2874 |
@@ -8,8 +8,23 @@ on:
|
||||
- cron: "0 22 * * *"
|
||||
|
||||
jobs:
|
||||
prebuild-common:
|
||||
name: prebuild-common-x86-64-v3
|
||||
runs-on: nix-cache-builder
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
# portal-1 is the smallest system closure: 95% of its derivations are
|
||||
# shared by all five systems, so it is a maintainable common cache seed.
|
||||
# Keep going so one failing package does not stop unrelated cache entries
|
||||
# from being built.
|
||||
- name: Build common packages
|
||||
run: nixos-rebuild build --keep-going --accept-flake-config --flake ./#portal-1
|
||||
- name: Copy common packages to nix-cache
|
||||
run: nix copy --accept-flake-config --to unix:///host-nix/var/nix/daemon-socket/socket .#nixosConfigurations.portal-1.config.system.build.toplevel
|
||||
|
||||
build:
|
||||
name: build-${{ matrix.system }}
|
||||
needs: prebuild-common
|
||||
runs-on: self-hosted
|
||||
strategy:
|
||||
matrix:
|
||||
|
||||
@@ -0,0 +1,46 @@
|
||||
{ pkgs, ... }:
|
||||
{
|
||||
environment.systemPackages = [
|
||||
pkgs.signal-cli
|
||||
];
|
||||
|
||||
users = {
|
||||
groups.signal-cli = { };
|
||||
users.signal-cli = {
|
||||
isSystemUser = true;
|
||||
group = "signal-cli";
|
||||
home = "/var/lib/signal-cli";
|
||||
};
|
||||
};
|
||||
|
||||
systemd.tmpfiles.rules = [
|
||||
"d /var/lib/signal-cli 0700 signal-cli signal-cli - -"
|
||||
"Z /var/lib/signal-cli - signal-cli signal-cli - -"
|
||||
];
|
||||
|
||||
systemd.services.signal-cli = {
|
||||
description = "Signal CLI JSON-RPC service";
|
||||
after = [ "network-online.target" ];
|
||||
wants = [ "network-online.target" ];
|
||||
wantedBy = [ "multi-user.target" ];
|
||||
unitConfig.RequiresMountsFor = [ "/var/lib/signal-cli" ];
|
||||
|
||||
serviceConfig = {
|
||||
Type = "simple";
|
||||
User = "signal-cli";
|
||||
Group = "signal-cli";
|
||||
ExecStart = "${pkgs.signal-cli}/bin/signal-cli --data-dir /var/lib/signal-cli daemon --socket /run/signal-cli/socket";
|
||||
Restart = "on-failure";
|
||||
RestartSec = "5s";
|
||||
SuccessExitStatus = 143;
|
||||
RuntimeDirectory = "signal-cli";
|
||||
RuntimeDirectoryMode = "0750";
|
||||
UMask = "0007";
|
||||
NoNewPrivileges = true;
|
||||
PrivateTmp = true;
|
||||
ProtectHome = true;
|
||||
ProtectSystem = "strict";
|
||||
ReadWritePaths = [ "/var/lib/signal-cli" ];
|
||||
};
|
||||
};
|
||||
}
|
||||
@@ -1,9 +0,0 @@
|
||||
{
|
||||
nixpkgs.hostPlatform = {
|
||||
system = "x86_64-linux";
|
||||
gcc = {
|
||||
arch = "x86-64-v3";
|
||||
tune = "generic";
|
||||
};
|
||||
};
|
||||
}
|
||||
@@ -0,0 +1,15 @@
|
||||
{
|
||||
nixpkgs = {
|
||||
hostPlatform = {
|
||||
system = "x86_64-linux";
|
||||
gcc = {
|
||||
arch = "x86-64-v3";
|
||||
tune = "generic";
|
||||
};
|
||||
};
|
||||
|
||||
# These patches repair tests and bundled dependencies that are sensitive
|
||||
# to the compiler flags used by the x86-64-v3 package set.
|
||||
overlays = [ (import ./patches) ];
|
||||
};
|
||||
}
|
||||
@@ -0,0 +1,38 @@
|
||||
# Package patches
|
||||
|
||||
Each package follows the [GnuTLS layout](gnutls/README.md):
|
||||
|
||||
- `default.nix` applies the patch through the package overlay.
|
||||
- A descriptive `.patch` file contains the standalone upstream source change.
|
||||
- `README.md` explains the problem, scope, reproduction, upstream status,
|
||||
Nix integration, and recorded validation limits.
|
||||
- Companion `verify-*` tools live beside the patch when needed; otherwise
|
||||
the README gives commands for the package's existing tests.
|
||||
|
||||
Keep package-specific evidence in its directory. Patch headers explain the
|
||||
change independently of Nix, and `default.nix` preserves existing patches.
|
||||
|
||||
| Package | Repair |
|
||||
| --- | --- |
|
||||
| [Abseil](abseil/README.md) | Public BMI2 header in Electron, Deno, and Signal's vendored copies |
|
||||
| [GnuTLS](gnutls/README.md) | Wait for the UDP server socket before connecting |
|
||||
| [Prometheus](prometheus/README.md) | Complete parsing before inspecting the test editor state |
|
||||
| [pytest-xdist](pytest-xdist/README.md) | Check worker replacements and allow startup on loaded builders |
|
||||
| [SciPy](scipy/README.md) | Account for floating-point rounding in STFT tests |
|
||||
|
||||
## Local NixOS integration
|
||||
|
||||
The [`x86-64-v3` optional module](../default.nix)
|
||||
imports this directory's [`default.nix`](default.nix) directly, so the patch
|
||||
overlay applies only to hosts using that package set. Prometheus patches its
|
||||
separate assets derivation; Python packages use `pythonPackagesExtensions`.
|
||||
|
||||
The [pytest-xdist directory](pytest-xdist/README.md) also owns its outer-worker
|
||||
limit and remote-worker event timeout. These package overrides add no skipped
|
||||
tests. Existing nixpkgs exclusions remain separate from these repairs.
|
||||
|
||||
The review used Python 3.14.7 and the pinned x86-64-v3 package set. Host-flake
|
||||
evaluation verified patch wiring, Python install checks, and Prometheus's
|
||||
reference to the patched assets. No complete NixOS rebuild was performed.
|
||||
Individual READMEs distinguish package builds, focused tests, and checks that
|
||||
have not been run.
|
||||
@@ -0,0 +1,59 @@
|
||||
# Abseil BMI2 public header
|
||||
|
||||
Vendored Abseil includes `bmi2intrin.h` directly when `__BMI2__` is enabled.
|
||||
Compilers reject that internal header without the umbrella-header setup.
|
||||
`bmi2-public-header.patch` includes `immintrin.h` instead, allowing builds
|
||||
that enable BMI2 through `-march=x86-64-v3`.
|
||||
|
||||
## Scope and behavior
|
||||
|
||||
The patch changes one include in
|
||||
`third_party/abseil-cpp/absl/container/internal/raw_hash_set.h`.
|
||||
`default.nix` applies it to Electron 43's unwrapped package, Deno's
|
||||
`librusty_v8`, and Signal's WebRTC dependency. It also supplies the patched
|
||||
Electron package to Signal. These overrides apply only to `x86-64-v3`.
|
||||
|
||||
The shared file path is relative to each vendoring project's source root,
|
||||
not the root of a standalone Abseil checkout. No hash-table algorithm or
|
||||
test exclusion changes.
|
||||
|
||||
## Reproduction and focused checks
|
||||
|
||||
From this directory, check and apply the patch to each vendored source tree:
|
||||
|
||||
```sh
|
||||
patch --dry-run --fuzz=0 -d /path/to/vendor-source -p1 < bmi2-public-header.patch
|
||||
patch --fuzz=0 -d /path/to/vendor-source -p1 < bmi2-public-header.patch
|
||||
```
|
||||
|
||||
A small compiler check isolates the header requirement. With GCC or Clang
|
||||
on x86-64, compile `#include <bmi2intrin.h>` using `-march=x86-64-v3`; the
|
||||
compiler rejects the direct include. Changing it to `#include <immintrin.h>`
|
||||
should compile. The full consumer builds below check integration with their
|
||||
actual toolchains.
|
||||
|
||||
## Upstream status
|
||||
|
||||
Abseil addressed this issue through
|
||||
[PR #2071](https://github.com/abseil/abseil-cpp/pull/2071), imported by its
|
||||
upstream workflow. That change uses `x86gprintrin.h`; this local variant uses
|
||||
the public `immintrin.h` umbrella header for the vendored toolchains.
|
||||
Keep the workaround until all three bundled copies include a compatible fix.
|
||||
This file is a local adaptation, not a verbatim copy of the upstream diff.
|
||||
|
||||
## Local NixOS integration and build results
|
||||
|
||||
[`../default.nix`](../default.nix) merges this directory's overlay fragment
|
||||
because it repairs multiple packages. From the repository root, the consumer
|
||||
build commands are:
|
||||
|
||||
```sh
|
||||
nix build --no-link -L .#nixosConfigurations.jeeves.pkgs.deno
|
||||
nix build --no-link -L .#nixosConfigurations.jeeves.pkgs.electron_43
|
||||
nix build --no-link -L .#nixosConfigurations.jeeves.pkgs.signal-desktop
|
||||
```
|
||||
|
||||
The earlier extraction checked the vendored header snapshots and evaluated
|
||||
all three patch attachments. Those records do not establish successful full
|
||||
consumer rebuilds. No new compiler or consumer build was run for the layout
|
||||
change; the patch and override are unchanged.
|
||||
@@ -0,0 +1,20 @@
|
||||
Subject: [PATCH] abseil: include BMI2 intrinsics through the public header
|
||||
|
||||
GCC and Clang reject direct inclusion of bmi2intrin.h. Include immintrin.h
|
||||
instead so that the compiler supplies the required intrinsic setup when
|
||||
BMI2 is enabled, including builds targeting x86-64-v3.
|
||||
|
||||
This patch is shared by the vendored Abseil copies in Electron, rusty_v8
|
||||
(Deno), and Signal's WebRTC build.
|
||||
|
||||
--- a/third_party/abseil-cpp/absl/container/internal/raw_hash_set.h
|
||||
+++ b/third_party/abseil-cpp/absl/container/internal/raw_hash_set.h
|
||||
@@ -226,7 +226,7 @@
|
||||
#endif
|
||||
|
||||
#ifdef __BMI2__
|
||||
-#include <bmi2intrin.h>
|
||||
+#include <immintrin.h>
|
||||
#endif // __BMI2__
|
||||
|
||||
namespace absl {
|
||||
@@ -0,0 +1,38 @@
|
||||
# Abseil accepted the upstream fix: https://github.com/abseil/abseil-cpp/pull/2071
|
||||
# Keep this workaround until Electron, Deno's rusty_v8, and Signal's WebRTC
|
||||
# update their bundled Abseil copies to include it.
|
||||
{ prev }:
|
||||
let
|
||||
patchAbseilBmi2Include =
|
||||
package:
|
||||
package.overrideAttrs (old: {
|
||||
# GCC and Clang require the public umbrella header for BMI2 intrinsics.
|
||||
patches = (old.patches or [ ]) ++ [ ./bmi2-public-header.patch ];
|
||||
});
|
||||
|
||||
electron43Unwrapped = patchAbseilBmi2Include prev.electron_43.unwrapped;
|
||||
electron43 = prev.electron_43.override {
|
||||
electron-unwrapped = electron43Unwrapped;
|
||||
};
|
||||
|
||||
signalCallPackage =
|
||||
path: args:
|
||||
let
|
||||
package = prev.callPackage path args;
|
||||
in
|
||||
if builtins.baseNameOf path == "webrtc.nix" then patchAbseilBmi2Include package else package;
|
||||
in
|
||||
prev.lib.optionalAttrs ((prev.stdenv.hostPlatform.gcc.arch or null) == "x86-64-v3") {
|
||||
deno =
|
||||
let
|
||||
librusty_v8 = patchAbseilBmi2Include prev.deno.passthru.librusty_v8;
|
||||
in
|
||||
prev.deno.override { inherit librusty_v8; };
|
||||
|
||||
electron_43 = electron43;
|
||||
|
||||
signal-desktop = prev.signal-desktop.override {
|
||||
electron_43 = electron43;
|
||||
callPackage = signalCallPackage;
|
||||
};
|
||||
}
|
||||
@@ -0,0 +1,13 @@
|
||||
_final: prev:
|
||||
(import ./abseil { inherit prev; })
|
||||
// {
|
||||
gnutls = import ./gnutls { inherit (prev) gnutls; };
|
||||
prometheus = import ./prometheus { inherit (prev) prometheus; };
|
||||
|
||||
pythonPackagesExtensions = prev.pythonPackagesExtensions ++ [
|
||||
(_pythonFinal: pythonPrev: {
|
||||
pytest-xdist = import ./pytest-xdist { inherit (pythonPrev) pytest-xdist; };
|
||||
scipy = import ./scipy { inherit (pythonPrev) scipy; };
|
||||
})
|
||||
];
|
||||
}
|
||||
@@ -0,0 +1,160 @@
|
||||
# GnuTLS UDP server readiness
|
||||
|
||||
Under load, the test client can start before `gnutls-serv` binds its UDP
|
||||
socket, and the first handshake fails with `Connection refused`.
|
||||
`serv-udp.sh` currently waits a fixed four seconds; elapsed time does not
|
||||
establish server readiness. `udp-server-readiness.patch` replaces that wait
|
||||
with polling for the local IPv4 UDP endpoint.
|
||||
|
||||
## Scope and waiting behavior
|
||||
|
||||
The patch changes the existing `wait_udp_server()` and adds a new
|
||||
`check_if_udp_port_bound()` beside it in `tests/scripts/common.sh`.
|
||||
`serv-udp.sh` is its only caller in 3.8.13. The TCP helpers `wait_server()`
|
||||
and `wait_for_port()`, including their existing sleeps, are unchanged.
|
||||
Both original DTLS handshake checks remain unchanged.
|
||||
|
||||
Each iteration checks process liveness and the socket **before sleeping**.
|
||||
A ready socket returns immediately. An unsuccessful check sleeps two
|
||||
seconds only if another attempt remains: at most 90 attempts, consistent
|
||||
with the existing `wait_server()` budget implemented by `wait_for_port()`,
|
||||
with no sleep after the final check. Server exit fails early; exhausting the
|
||||
budget fails and terminates the server. No handshake is retried, and no
|
||||
protocol timeout is changed. Once bound, the kernel can queue datagrams
|
||||
while the server is scheduled; the probe itself sends no packets.
|
||||
|
||||
The existing `have_port_finder()` prefers `ss`, then `netstat`. If neither
|
||||
exists, it prints `neither ss nor netstat found` and exits **77 (skip)**.
|
||||
In the normal test flow, port selection calls it before launching a server.
|
||||
The probe runs in a subshell so that, even if this skip occurs after launch,
|
||||
the waiting helper can terminate and reap the server before exiting 77.
|
||||
|
||||
## Why an IPv4 socket is expected
|
||||
|
||||
This is specific to the server used by this test, not a general rule that
|
||||
IPv6 sockets cannot serve IPv4 clients. The client explicitly uses
|
||||
`127.0.0.1`. The server's `--udp` path calls `udp_server()`, which calls
|
||||
`listen_socket(..., SOCK_DGRAM)`. That function iterates the wildcard
|
||||
addresses returned by `getaddrinfo(NULL, ..., AI_PASSIVE)`:
|
||||
|
||||
| Server build / Linux setting | Binding behavior |
|
||||
| --- | --- |
|
||||
| IPv6 enabled, `net.ipv6.bindv6only=0` | Requests `IPV6_V6ONLY=1` on the IPv6 socket, binds `[::]:PORT`, and separately binds `0.0.0.0:PORT`. It overrides the system's dual-stack default. |
|
||||
| IPv6 enabled, `net.ipv6.bindv6only=1` | The same explicit socket option and separate IPv4/IPv6 binds. |
|
||||
| `HAVE_IPV6` undefined | Skips every address family except `AF_INET`; only the IPv4 wildcard is attempted. |
|
||||
|
||||
`udp_server()` uses `wait_for_connection()`, which puts **every listener**
|
||||
from that list into `select()` and returns a readable socket for `recvfrom()`;
|
||||
it does not permanently choose one socket based on `getaddrinfo()` order.
|
||||
|
||||
The first two cases were traced with the actual GnuTLS 3.8.13 binary in
|
||||
separate Linux network namespaces: `setsockopt(IPV6_V6ONLY, [1])` and both
|
||||
UDP binds returned success under each setting. The no-IPv6 case was checked
|
||||
in source, not by building a second binary. The same bind implementation
|
||||
was checked directly on GitLab master.
|
||||
|
||||
Thus, successful normal startup for this invocation provides an explicit
|
||||
IPv4 socket; a lone IPv6 wildcard is not the expected success path.
|
||||
There is one portability caveat: upstream discards the return value of
|
||||
`setsockopt(IPV6_V6ONLY)`. On a platform where that call fails and the server
|
||||
ends up with only a dual-stack socket, this helper would time out despite
|
||||
IPv4 reachability. Such a platform needs additional handling before this
|
||||
patch can claim support. Blindly accepting every IPv6 wildcard would also
|
||||
accept IPv6-only sockets before the separate IPv4 bind finishes.
|
||||
|
||||
Source: [`src/serv.c`, `listen_socket()`](https://gitlab.com/gnutls/gnutls/-/blob/master/src/serv.c#L937),
|
||||
[`src/udp-serv.c`](https://gitlab.com/gnutls/gnutls/-/blob/master/src/udp-serv.c),
|
||||
and [`tests/serv-udp.sh`](https://gitlab.com/gnutls/gnutls/-/blob/master/tests/serv-udp.sh).
|
||||
|
||||
## Port matching and ownership limit
|
||||
|
||||
Only `-an` is passed to the socket-listing tool: BSD `netstat -u` selects
|
||||
Unix-domain sockets, whereas Linux `netstat -u` selects UDP. The parser
|
||||
handles the extra state column in `ss`, Linux colon-separated endpoints,
|
||||
and BSD dot-separated endpoints, including `*.PORT`. It matches the full
|
||||
local port and rejects TCP, IPv6 entries, peer ports, and longer numbers.
|
||||
|
||||
A live PID plus a bound port does **not** prove that PID owns the socket.
|
||||
Existing `GETPORT` selection checks for an unused port and uses a test
|
||||
port-lock directory; `launch_bare_server()` also calls
|
||||
`wait_for_free_port()` before starting the process. These are advisory:
|
||||
the launcher does not enforce the latter's result, and another process
|
||||
can bind between the check and launch. The patch does not close that race
|
||||
or add nonportable PID parsing. An unrelated process can satisfy the
|
||||
socket check; the real handshakes remain the functional check and may
|
||||
fail (or reach the wrong server). This is a startup-order fix, not a
|
||||
socket-ownership guarantee.
|
||||
|
||||
## Reproduction and focused checks
|
||||
|
||||
Apply the patch to an unpacked source tree, then run the companion checks
|
||||
with Python's standard library and a shell:
|
||||
|
||||
```sh
|
||||
patch --fuzz=0 -d /path/to/gnutls -p1 < udp-server-readiness.patch
|
||||
SHELL=/bin/sh python3 verify-readiness.py /path/to/gnutls/tests/scripts/common.sh -v
|
||||
```
|
||||
|
||||
Set `NETSTAT=/path/to/netstat` to exercise one outside `PATH`. The checks
|
||||
cover Linux/BSD output samples, false matches, immediate readiness,
|
||||
missing tools, process exit, timeout cleanup, and real IPv4 UDP sockets
|
||||
whose bind is delayed six seconds. The missing-tools fixture is skipped
|
||||
if an absolute fallback `ss` path cannot be hidden with `PATH`. Native
|
||||
BSD execution remains untested.
|
||||
|
||||
To reproduce with GnuTLS itself, run `tests/serv-udp.sh` with `SERV` pointing
|
||||
to a wrapper that sleeps six seconds, then `exec`s `gnutls-serv` with all
|
||||
arguments. Set `CLI` to the matching `gnutls-cli`, `srcdir` to the source
|
||||
`tests` directory, and `abs_top_builddir` to a writable build directory.
|
||||
With GnuTLS 3.8.13, the original helper failed the first handshake with
|
||||
`Connection refused`; the patched helper passed both with the same binaries.
|
||||
|
||||
## GnuTLS submission
|
||||
|
||||
Development and merge requests are on [GitLab](https://gitlab.com/gnutls/gnutls).
|
||||
[`CONTRIBUTING.md` on master](https://gitlab.com/gnutls/gnutls/-/blob/master/CONTRIBUTING.md)
|
||||
was read directly for this review. It requires the contributor's DCO
|
||||
`Signed-off-by`, successful and failure test coverage, consistent coding
|
||||
style, and adequate documentation; GitLab CI runs for merge requests.
|
||||
Its commenting guidance asks for comments explaining non-obvious behavior
|
||||
or protocol expectations. It does not prescribe an additional special
|
||||
test-suite comment. The patch now explains its IPv4 binding assumption
|
||||
next to the probe.
|
||||
|
||||
The submission will contain the shell patch, without the Python verifier
|
||||
or a new Python test dependency. The existing `serv-udp.sh` supplies the
|
||||
functional success check. Running it through the six-second startup
|
||||
wrapper supplies a reproducible regression case: it fails before the fix
|
||||
and passes after it. The local verifier was used to validate socket-output
|
||||
parsing and the helper's success, process-exit, skip-cleanup, and timeout
|
||||
branches. Those branch checks are local evidence, not new automated
|
||||
coverage in the upstream suite; the MR must state that distinction.
|
||||
|
||||
No dedicated unit-test harness for these shell helpers was found in the
|
||||
3.8.13 tests inspected. That does not establish that Python cannot be used
|
||||
upstream; keeping this submission dependency-free is a scope choice. Use
|
||||
the existing test and before/after reproduction as the submission's
|
||||
coverage argument, retaining the platform limitations above. Apply the
|
||||
patch in an upstream checkout and include those results with the
|
||||
contributor's own sign-off. No MR or sign-off has been created.
|
||||
|
||||
## Local NixOS integration and build results
|
||||
|
||||
`overlays/default.nix` imports the `overlays/patches` overlay, which loads
|
||||
`gnutls/default.nix` to apply the patch and keep `serv-udp.sh` enabled.
|
||||
The patch itself has no Nix dependencies and applies to 3.8.13 and GitLab
|
||||
master without fuzz.
|
||||
|
||||
The final patch was rebuilt with:
|
||||
|
||||
```sh
|
||||
nix build --no-link -L .#nixosConfigurations.jeeves.pkgs.gnutls
|
||||
```
|
||||
|
||||
That x86-64-v3 build passed: 927 tests, 796 passes, 131 existing skips,
|
||||
zero failures/errors, and `PASS: serv-udp.sh`. The patch bytes in the built
|
||||
derivation were compared with the repository artifact; both have SHA-256
|
||||
`59013d47fd446f2dd065012a2259ccc1898fedc8a053a630e13efa0076368760`.
|
||||
All seven local checks passed, including skip cleanup and exactly 90
|
||||
probes with 89 sleeps on timeout. The six-second before/after reproduction
|
||||
was also repeated successfully with the final helper.
|
||||
@@ -0,0 +1,6 @@
|
||||
{ gnutls }:
|
||||
gnutls.overrideAttrs (old: {
|
||||
# Keep the UDP handshake test enabled on loaded builders by waiting for
|
||||
# the server to bind its socket. Kept as a standalone patch for upstream.
|
||||
patches = (old.patches or [ ]) ++ [ ./udp-server-readiness.patch ];
|
||||
})
|
||||
@@ -0,0 +1,70 @@
|
||||
Subject: [PATCH] tests: wait for the UDP server socket before connecting
|
||||
|
||||
A fixed four-second sleep does not guarantee that gnutls-serv has bound
|
||||
its UDP socket on a busy builder. Poll the local IPv4 UDP endpoint using
|
||||
the existing ss/netstat discovery, with the same retry budget as the TCP
|
||||
helper. Fail early if the server exits, and retain the original handshake
|
||||
checks in serv-udp.sh.
|
||||
|
||||
Use flags common to ss and BSD/Linux netstat. Match the local endpoint
|
||||
and complete port number, excluding TCP, IPv6-only and peer endpoints.
|
||||
|
||||
--- a/tests/scripts/common.sh
|
||||
+++ b/tests/scripts/common.sh
|
||||
@@ -185,10 +185,55 @@
|
||||
fi
|
||||
}
|
||||
|
||||
+check_if_udp_port_bound() {
|
||||
+ local PORT=$1
|
||||
+ have_port_finder
|
||||
+ # Use only -an, which is shared by ss and BSD/Linux netstat. UDP has
|
||||
+ # no LISTEN state. Match the local IPv4 endpoint, not a peer port or
|
||||
+ # a longer port number. serv-udp.sh connects to 127.0.0.1;
|
||||
+ # listen_socket() in serv.c binds IPv4 separately and requests
|
||||
+ # IPV6_V6ONLY=1 for its IPv6 socket.
|
||||
+ $PFCMD -an | awk -v port="$PORT" '
|
||||
+ $1 == "udp" || $1 == "udp4" {
|
||||
+ # ss includes a state column; netstat does not.
|
||||
+ address = ($2 == "UNCONN" || $2 == "ESTAB") ? $5 : $4
|
||||
+ if (address ~ ("^[0-9.]+[.:]" port "$") ||
|
||||
+ address == "*." port)
|
||||
+ found = 1
|
||||
+ }
|
||||
+ END { exit !found }
|
||||
+ '
|
||||
+}
|
||||
+
|
||||
wait_udp_server() {
|
||||
local PID=$1
|
||||
+ local ret
|
||||
trap "test -n \"${PID}\" && kill ${PID};exit 1" 1 15 2
|
||||
- sleep 4
|
||||
+ local i=0
|
||||
+ # Use the same retry budget as wait_for_port(), but also stop if the
|
||||
+ # server exits before binding its socket.
|
||||
+ while test $i -lt 90; do
|
||||
+ if ! kill -0 "$PID" 2>/dev/null; then
|
||||
+ fail "" "UDP server $PID exited before binding port $PORT"
|
||||
+ fi
|
||||
+ # Contain have_port_finder's exit so a skip also stops the server.
|
||||
+ if (check_if_udp_port_bound "$PORT"); then
|
||||
+ return 0
|
||||
+ else
|
||||
+ ret=$?
|
||||
+ if test "$ret" = 77; then
|
||||
+ kill "$PID" 2>/dev/null || :
|
||||
+ wait "$PID" 2>/dev/null || :
|
||||
+ exit 77
|
||||
+ fi
|
||||
+ fi
|
||||
+ i=$((i + 1))
|
||||
+ if test $i -lt 90; then
|
||||
+ echo "try $i: waiting for UDP port $PORT"
|
||||
+ sleep 2
|
||||
+ fi
|
||||
+ done
|
||||
+ fail "$PID" "UDP server $PORT did not come up"
|
||||
}
|
||||
|
||||
create_testdir() {
|
||||
@@ -0,0 +1,180 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Exercise patched common.sh without building GnuTLS (Python standard library only).
|
||||
|
||||
Usage: python3 verify-readiness.py /path/to/patched/tests/scripts/common.sh
|
||||
Set SHELL to test another shell, and NETSTAT to test a netstat outside PATH.
|
||||
"""
|
||||
|
||||
# Use unittest so this upstream companion tool needs no pytest installation.
|
||||
# ruff: noqa: PT009
|
||||
|
||||
import os
|
||||
import shutil
|
||||
import socket
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
import time
|
||||
import unittest
|
||||
from pathlib import Path
|
||||
|
||||
COMMON = str(Path(sys.argv.pop(1)).resolve())
|
||||
SHELL = os.environ.get("SHELL", "/bin/sh")
|
||||
|
||||
|
||||
class ReadinessTests(unittest.TestCase):
|
||||
"""Check endpoint parsing and the server startup lifecycle."""
|
||||
|
||||
def setUp(self) -> None:
|
||||
"""Create a socket-listing fixture for each check."""
|
||||
self.tmp = tempfile.TemporaryDirectory()
|
||||
self.addCleanup(self.tmp.cleanup)
|
||||
self.root = Path(self.tmp.name)
|
||||
self.fixture = self.root / "sockets"
|
||||
self.fixture.write_text("")
|
||||
self.finder = self.root / "port-finder"
|
||||
self.finder.write_text('#!/bin/sh\ncat "$SOCKET_FIXTURE"\n')
|
||||
self.finder.chmod(0o755)
|
||||
|
||||
def run_shell(self, body: str, **env: str) -> subprocess.CompletedProcess[str]:
|
||||
"""Source the actual helper and run a shell scenario."""
|
||||
return subprocess.run(
|
||||
[SHELL, "-c", '. "$COMMON"\n' + body],
|
||||
env={
|
||||
**os.environ,
|
||||
"COMMON": COMMON,
|
||||
"SOCKET_FIXTURE": str(self.fixture),
|
||||
"PFCMD": str(self.finder),
|
||||
"PORT": "12345",
|
||||
**env,
|
||||
},
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=20,
|
||||
check=False,
|
||||
)
|
||||
|
||||
def test_socket_formats_and_false_matches(self) -> None:
|
||||
"""Accept IPv4 UDP local endpoints and reject unrelated sockets."""
|
||||
cases = [
|
||||
("udp UNCONN 0 0 0.0.0.0:12345 0.0.0.0:*", True),
|
||||
("udp UNCONN 0 0 127.0.0.1:12345 0.0.0.0:*", True),
|
||||
("udp 0 0 0.0.0.0:12345 0.0.0.0:*", True),
|
||||
("udp4 0 0 *.12345 *.*", True),
|
||||
("udp 0 0 127.0.0.1.12345 *.*", True),
|
||||
("udp 0 0 *.12345 *.*", True),
|
||||
("udp UNCONN 0 0 0.0.0.0:123456 0.0.0.0:*", False),
|
||||
("udp 0 0 0.0.0.0:123456 0.0.0.0:*", False),
|
||||
("udp ESTAB 0 0 127.0.0.1:54321 127.0.0.1:12345", False),
|
||||
("udp 0 0 127.0.0.1:54321 127.0.0.1:12345", False),
|
||||
("tcp LISTEN 0 128 0.0.0.0:12345 0.0.0.0:*", False),
|
||||
("tcp 0 0 0.0.0.0:12345 0.0.0.0:* LISTEN", False),
|
||||
("udp UNCONN 0 0 [::]:12345 [::]:*", False),
|
||||
("udp UNCONN 0 0 *:12345 *:*", False),
|
||||
("udp6 0 0 :::12345 :::*", False),
|
||||
("udp6 0 0 *.12345 *.*", False),
|
||||
("", False),
|
||||
]
|
||||
for row, ready in cases:
|
||||
with self.subTest(row=row):
|
||||
self.fixture.write_text(row + "\n")
|
||||
result = self.run_shell('check_if_udp_port_bound "$PORT"')
|
||||
self.assertEqual(result.returncode, 0 if ready else 1, result.stderr)
|
||||
|
||||
def test_exited_server_fails_immediately(self) -> None:
|
||||
"""Fail without sleeping when the server has already exited."""
|
||||
result = self.run_shell(
|
||||
'true &\npid=$!\nwait "$pid"\nsleep() { echo "unexpected sleep" >&2; }\nwait_udp_server "$pid"'
|
||||
)
|
||||
self.assertEqual(result.returncode, 1)
|
||||
self.assertIn("exited before binding", result.stderr)
|
||||
self.assertNotIn("unexpected sleep", result.stderr)
|
||||
|
||||
def test_ready_socket_does_not_sleep(self) -> None:
|
||||
"""Check readiness before the first sleep."""
|
||||
self.fixture.write_text("udp UNCONN 0 0 0.0.0.0:12345 0.0.0.0:*\n")
|
||||
result = self.run_shell('sleep() { echo "unexpected sleep" >&2; }\nwait_udp_server "$$"')
|
||||
self.assertEqual(result.returncode, 0, result.stderr)
|
||||
self.assertNotIn("unexpected sleep", result.stderr)
|
||||
|
||||
def test_missing_port_finders_skip(self) -> None:
|
||||
"""Skip and stop the live server when no finder is available."""
|
||||
# have_port_finder also tries these paths independently of PATH.
|
||||
if any(os.access(f"{directory}/ss", os.X_OK) for directory in ("/sbin", "/usr/sbin", "/usr/local/sbin")):
|
||||
self.skipTest("an absolute ss path cannot be hidden by this PATH-only fixture")
|
||||
with subprocess.Popen(["sleep", "60"]) as server:
|
||||
try:
|
||||
result = self.run_shell(
|
||||
'unset PFCMD\nPATH=/nonexistent\nwait_udp_server "$SERVER_PID"',
|
||||
SERVER_PID=str(server.pid),
|
||||
)
|
||||
self.assertEqual(result.returncode, 77)
|
||||
self.assertIn("neither ss nor netstat found", result.stderr)
|
||||
server.wait(timeout=3)
|
||||
self.assertLess(server.returncode, 0)
|
||||
finally:
|
||||
if server.poll() is None:
|
||||
server.kill()
|
||||
|
||||
def test_timeout_is_bounded_and_cleans_up(self) -> None:
|
||||
"""Stop polling after the retry budget and terminate the server."""
|
||||
# Only accelerate the polling delay; keep a real live server process.
|
||||
self.finder.write_text('#!/bin/sh\necho probe >&2\ncat "$SOCKET_FIXTURE"\n')
|
||||
with subprocess.Popen(["sleep", "60"]) as server:
|
||||
try:
|
||||
result = self.run_shell(
|
||||
'sleep() { echo polling-sleep; }\nwait_udp_server "$SERVER_PID"',
|
||||
SERVER_PID=str(server.pid),
|
||||
)
|
||||
self.assertEqual(result.returncode, 1)
|
||||
self.assertIn("did not come up", result.stderr)
|
||||
self.assertEqual(result.stderr.count("probe\n"), 90)
|
||||
self.assertEqual(result.stdout.count("polling-sleep"), 89)
|
||||
server.wait(timeout=3)
|
||||
self.assertLess(server.returncode, 0)
|
||||
finally:
|
||||
if server.poll() is None:
|
||||
server.kill()
|
||||
|
||||
def test_server_exits_while_waiting(self) -> None:
|
||||
"""Detect a startup failure that happens after polling begins."""
|
||||
result = self.run_shell('sleep 1 &\npid=$!\nwait_udp_server "$pid"')
|
||||
self.assertEqual(result.returncode, 1)
|
||||
self.assertIn("exited before binding", result.stderr)
|
||||
self.assertIn("waiting for UDP port", result.stdout)
|
||||
|
||||
def test_real_socket_delayed_beyond_four_seconds(self) -> None:
|
||||
"""Wait for a real delayed bind with each installed port finder."""
|
||||
finders = [shutil.which("ss"), os.environ.get("NETSTAT") or shutil.which("netstat")]
|
||||
finders = [finder for finder in finders if finder]
|
||||
if not finders:
|
||||
self.skipTest("neither ss nor netstat available")
|
||||
for finder in finders:
|
||||
with self.subTest(finder=finder):
|
||||
with socket.socket(socket.AF_INET, socket.SOCK_DGRAM) as sock:
|
||||
sock.bind(("127.0.0.1", 0))
|
||||
port = sock.getsockname()[1]
|
||||
code = (
|
||||
"import socket,time,sys; time.sleep(6); "
|
||||
"s=socket.socket(socket.AF_INET,socket.SOCK_DGRAM); "
|
||||
"s.bind(('127.0.0.1',int(sys.argv[1]))); time.sleep(30)"
|
||||
)
|
||||
with subprocess.Popen([sys.executable, "-c", code, str(port)]) as server:
|
||||
try:
|
||||
started = time.monotonic()
|
||||
result = self.run_shell(
|
||||
'wait_udp_server "$SERVER_PID"',
|
||||
SERVER_PID=str(server.pid),
|
||||
PORT=str(port),
|
||||
PFCMD=finder,
|
||||
)
|
||||
self.assertEqual(result.returncode, 0, result.stderr)
|
||||
self.assertGreaterEqual(time.monotonic() - started, 6)
|
||||
self.assertIsNone(server.poll())
|
||||
finally:
|
||||
server.terminate()
|
||||
server.wait(timeout=3)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
@@ -0,0 +1,66 @@
|
||||
# Prometheus complete test parsing
|
||||
|
||||
CodeMirror gives editor-state creation a 20 ms synchronous parsing budget.
|
||||
The shared `createEditorState()` test helper can therefore return an
|
||||
incomplete syntax tree when the process is descheduled. The completion and
|
||||
vector-matching tests immediately inspect that tree.
|
||||
|
||||
## Scope and behavior
|
||||
|
||||
`complete-test-parsing.patch` changes only
|
||||
`module/codemirror-promql/src/test/utils-test.ts` inside `web/ui`. It completes
|
||||
the small test expression with `ensureSyntaxTree(..., Infinity)` and publishes
|
||||
the completed parse through an empty transaction so `syntaxTree(state)` sees
|
||||
it. Failure to obtain a tree raises an error.
|
||||
|
||||
The original assertions remain enabled, including `autocomplete topk params 2`
|
||||
and `foo * on(test,blub) bar`. The unlimited budget applies to the test helper;
|
||||
production editor parsing budgets are unchanged.
|
||||
|
||||
## Reproduction and focused checks
|
||||
|
||||
Use a disposable Prometheus 3.14.0 checkout. The patch root is `web/ui`, matching
|
||||
the Nix assets derivation. From this directory:
|
||||
|
||||
```sh
|
||||
patch --fuzz=0 -d /path/to/prometheus/web/ui -p1 < complete-test-parsing.patch
|
||||
cd /path/to/prometheus/web/ui
|
||||
pnpm install --frozen-lockfile
|
||||
pnpm --filter @prometheus-io/lezer-promql build
|
||||
pnpm --filter @prometheus-io/codemirror-promql test
|
||||
```
|
||||
|
||||
To force the scheduling condition, temporarily append this clock to
|
||||
`module/codemirror-promql/setupJest.cjs` in the disposable checkout:
|
||||
|
||||
```js
|
||||
let parseClock = 0;
|
||||
Date.now = () => (parseClock += 25);
|
||||
```
|
||||
|
||||
Each clock read crosses the editor's initial parsing budget. Against the
|
||||
original helper, the hybrid and vector suites have 186 failures, including
|
||||
both locally excluded cases. With the patch, all 386 CodeMirror tests pass
|
||||
under that same clock. Remove the injected clock before normal builds.
|
||||
|
||||
## Upstream status
|
||||
|
||||
This is a standalone test-helper patch for Prometheus 3.14.0. No upstream
|
||||
submission was made during this work. Recheck the helper when updating
|
||||
Prometheus or CodeMirror, including how an ensured parse becomes visible
|
||||
through the editor state.
|
||||
|
||||
## Local NixOS integration and build results
|
||||
|
||||
[`../default.nix`](../default.nix) loads `default.nix`, which patches the
|
||||
separate assets derivation. It updates both `passthru.assets` and the main
|
||||
Prometheus build's reference to those assets. From the repository root:
|
||||
|
||||
```sh
|
||||
nix build --no-link -L .#nixosConfigurations.jeeves.pkgs.prometheus.assets
|
||||
```
|
||||
|
||||
The full x86-64-v3 assets build passed with the normal clock, including the
|
||||
CodeMirror and UI suites. Host-flake evaluation confirmed that the main
|
||||
Prometheus derivation refers to these patched assets. The Go server package
|
||||
was not rebuilt for this test-helper change.
|
||||
@@ -0,0 +1,36 @@
|
||||
Subject: [PATCH] tests: finish parsing before inspecting editor state
|
||||
|
||||
EditorState creation has a 20 ms parsing budget. A descheduled test can
|
||||
therefore observe an incomplete tree. Finish these small test documents
|
||||
without an interactive deadline and publish the result with a transaction.
|
||||
Keep the original completion and vector-matching assertions enabled.
|
||||
|
||||
--- a/module/codemirror-promql/src/test/utils-test.ts
|
||||
+++ b/module/codemirror-promql/src/test/utils-test.ts
|
||||
@@ -13,7 +13,7 @@
|
||||
|
||||
import { parser } from '@prometheus-io/lezer-promql';
|
||||
import { EditorState } from '@codemirror/state';
|
||||
-import { LRLanguage } from '@codemirror/language';
|
||||
+import { ensureSyntaxTree, LRLanguage } from '@codemirror/language';
|
||||
import nock from 'nock';
|
||||
import path from 'path';
|
||||
import { fileURLToPath } from 'url';
|
||||
@@ -23,10 +23,16 @@
|
||||
const __dirname = path.dirname(fileURLToPath(import.meta.url));
|
||||
|
||||
export function createEditorState(expr: string): EditorState {
|
||||
- return EditorState.create({
|
||||
+ const state = EditorState.create({
|
||||
doc: expr,
|
||||
extensions: lightPromQLSyntax,
|
||||
});
|
||||
+ // These tests need a complete tree, independent of the editor's time budget.
|
||||
+ if (!ensureSyntaxTree(state, state.doc.length, Infinity)) {
|
||||
+ throw new Error('Unable to parse the test expression');
|
||||
+ }
|
||||
+ // Publish the completed parse so syntaxTree(state) sees it too.
|
||||
+ return state.update({}).state;
|
||||
}
|
||||
|
||||
export function mockPrometheusServer(): void {
|
||||
@@ -0,0 +1,17 @@
|
||||
{ prometheus }:
|
||||
prometheus.overrideAttrs (
|
||||
old:
|
||||
let
|
||||
assets = old.passthru.assets.overrideAttrs (assetsOld: {
|
||||
patches = (assetsOld.patches or [ ]) ++ [ ./complete-test-parsing.patch ];
|
||||
});
|
||||
in
|
||||
{
|
||||
postPatch = builtins.replaceStrings [ "${old.passthru.assets}" ] [ "${assets}" ] (
|
||||
builtins.unsafeDiscardStringContext old.postPatch
|
||||
);
|
||||
passthru = old.passthru // {
|
||||
inherit assets;
|
||||
};
|
||||
}
|
||||
)
|
||||
@@ -0,0 +1,79 @@
|
||||
# pytest-xdist test fixes
|
||||
|
||||
With two workers and a restart limit of three, the fourth worker crash
|
||||
requests shutdown while another test can still be running. That test may
|
||||
also crash. The original queued-work test requires exactly four failures,
|
||||
even though five failures can occur without exceeding the replacement limit.
|
||||
|
||||
## Scope and behavior
|
||||
|
||||
`concurrent-worker-crashes.patch` changes the assertions in
|
||||
`TestNodeFailure.test_max_worker_restart_tests_queued` in
|
||||
`testing/acceptance_test.py`. It requires exactly three replacements, four or
|
||||
five failed tests, the failed-tests exit status, the limit message, and no
|
||||
internal error. It retains the two-worker workload and ten queued tests.
|
||||
|
||||
`worker-startup-timeout.patch` changes the remote-test helper's event timeout
|
||||
from 10 to 60 seconds so loaded builders have time to start workers. The
|
||||
helper returns immediately when an event arrives and still has a bounded wait.
|
||||
|
||||
The existing nixpkgs pytest-9 compatibility patches remain in place.
|
||||
Production scheduling and worker-restart behavior are unchanged.
|
||||
|
||||
## Reproduction and focused checks
|
||||
|
||||
Use a disposable pytest-xdist 3.8.0 checkout with its test dependencies and
|
||||
the nixpkgs pytest-9 compatibility patches where required. From this directory:
|
||||
|
||||
```sh
|
||||
patch --fuzz=0 -d /path/to/pytest-xdist -p1 < concurrent-worker-crashes.patch
|
||||
patch --fuzz=0 -d /path/to/pytest-xdist -p1 < worker-startup-timeout.patch
|
||||
cd /path/to/pytest-xdist
|
||||
python -m pytest testing/acceptance_test.py \
|
||||
-k test_max_worker_restart_tests_queued -q
|
||||
python -m pytest testing/test_remote.py -q
|
||||
```
|
||||
|
||||
Twenty unmodified runs passed during the review. To force the failing
|
||||
schedule, modify the generated crashing test in a disposable checkout to
|
||||
accept `worker_id`: make `gw3` wait for a marker created by `gw4`, and make
|
||||
`gw4` pause 0.1 seconds after creating the marker. Then both have in-flight
|
||||
tests when shutdown starts. Bound the marker wait so a reproduction failure
|
||||
cannot hang the suite. The original assertion fails on five reported
|
||||
failures; the patched test passes.
|
||||
|
||||
## Worker startup and outer concurrency
|
||||
|
||||
[`default.nix`](default.nix) runs the outer suite with one worker to limit
|
||||
nested process pools. This is a Nix test-runner setting; the source timeout
|
||||
change lives in [`worker-startup-timeout.patch`](worker-startup-timeout.patch).
|
||||
|
||||
A separate reproduction inserts an 11-second `pytest_sessionstart` delay
|
||||
into the child created by `test_basic_collect_and_runtests` in
|
||||
`testing/test_remote.py`. The original 10-second channel wait fails; the
|
||||
60-second wait passes. This bounds waits for test worker events, including
|
||||
startup, rather than changing a product deadline.
|
||||
|
||||
## Upstream status
|
||||
|
||||
These are standalone test patches for pytest-xdist 3.8.0. No upstream submission
|
||||
was made during this work. Recheck the allowed in-flight failures, replacement
|
||||
count, and remote-test wait when updating the scheduler or worker behavior.
|
||||
|
||||
## Local NixOS integration and build results
|
||||
|
||||
[`../default.nix`](../default.nix) loads `default.nix` through
|
||||
`pythonPackagesExtensions`. From the repository root:
|
||||
|
||||
```sh
|
||||
nix build --no-link -L .#nixosConfigurations.jeeves.pkgs.python314Packages.pytest-xdist
|
||||
```
|
||||
|
||||
After consolidating the settings in this directory, the full x86-64-v3 package
|
||||
build passed 185 tests, with 6 existing skips and 10 expected failures. Nix
|
||||
evaluation confirmed the same outer-worker limit and preserved existing
|
||||
patches, with the timeout now applied as a source patch.
|
||||
|
||||
The earlier forced concurrent-crash and delayed-startup reproductions passed
|
||||
after their fixes; the focused crash test also passed after formatting its
|
||||
assertion.
|
||||
@@ -0,0 +1,29 @@
|
||||
Subject: [PATCH] tests: count replacements when checking the worker restart limit
|
||||
|
||||
With two workers, another in-flight test may crash after the fourth
|
||||
crash requests shutdown. Either four or five failed tests is valid.
|
||||
Require exactly three replacements and the failed-tests exit status,
|
||||
while preserving the queued-work and no-internal-error assertions.
|
||||
|
||||
--- a/testing/acceptance_test.py
|
||||
+++ b/testing/acceptance_test.py
|
||||
@@ -1011,9 +1011,18 @@
|
||||
"worker*crashed while running*",
|
||||
"worker*crashed while running*",
|
||||
"* xdist: maximum crashed workers reached: 3 *",
|
||||
- "* 4 failed in *",
|
||||
]
|
||||
)
|
||||
+ # A second in-flight test may crash after shutdown is requested.
|
||||
+ # The restart limit constrains replacements, not concurrent failures.
|
||||
+ replacements = sum(
|
||||
+ line.startswith("replacing crashed worker ") for line in res.stdout.lines
|
||||
+ )
|
||||
+ assert replacements == 3
|
||||
+ failed = res.parseoutcomes()["failed"]
|
||||
+ assert failed in (4, 5)
|
||||
+ res.assert_outcomes(failed=failed)
|
||||
+ assert res.ret == pytest.ExitCode.TESTS_FAILED
|
||||
assert "INTERNALERROR" not in res.stdout.str()
|
||||
|
||||
def test_max_worker_restart_die(self, pytester: pytest.Pytester) -> None:
|
||||
@@ -0,0 +1,12 @@
|
||||
{ pytest-xdist }:
|
||||
pytest-xdist.overridePythonAttrs (old: {
|
||||
patches = (old.patches or [ ]) ++ [
|
||||
./concurrent-worker-crashes.patch
|
||||
./worker-startup-timeout.patch
|
||||
];
|
||||
|
||||
# The suite exercises its own worker pools. Limit the outer suite to one worker.
|
||||
preCheck = builtins.replaceStrings [ "--numprocesses=$NIX_BUILD_CORES" ] [ "--numprocesses=1" ] (
|
||||
old.preCheck or ""
|
||||
);
|
||||
})
|
||||
@@ -0,0 +1,19 @@
|
||||
Subject: [PATCH] tests: allow more time for remote worker events
|
||||
|
||||
Worker startup can exceed ten seconds on heavily loaded builders. Allow
|
||||
the remote-test helper to wait up to sixty seconds for worker events.
|
||||
The wait still returns as soon as an event arrives and remains bounded.
|
||||
Production worker timeouts and test assertions are unchanged.
|
||||
|
||||
--- a/testing/test_remote.py
|
||||
+++ b/testing/test_remote.py
|
||||
@@ -17,7 +17,8 @@
|
||||
from xdist.workermanage import WorkerController
|
||||
|
||||
|
||||
-WAIT_TIMEOUT = 10.0
|
||||
+# Allow worker events extra time on heavily loaded builders.
|
||||
+WAIT_TIMEOUT = 60.0
|
||||
|
||||
|
||||
def check_marshallable(d: object) -> None:
|
||||
@@ -0,0 +1,70 @@
|
||||
# SciPy STFT test tolerances
|
||||
|
||||
The x86-64-v3 build can produce small floating-point residuals in inverse-STFT
|
||||
comparisons and scaling round trips. The original bounds reject these results,
|
||||
including residuals around `4e-17` where a round trip expects zero for a signal
|
||||
with amplitude 2.
|
||||
|
||||
## Scope and behavior
|
||||
|
||||
`stft-test-tolerances.patch` changes only the signal tests:
|
||||
|
||||
- The inverse-STFT comparison in `_scipy_spectral_test_shim.py` uses
|
||||
`max(1e-7, 2 * np.finfo(x.dtype).eps)` as its relative tolerance. Float64
|
||||
keeps the original bound, and the existing i686 override remains.
|
||||
- Three scaling round trips in `test_spectral.py` gain an absolute tolerance
|
||||
of one epsilon for the input dtype, allowing small residuals near zero.
|
||||
|
||||
The tests remain enabled, and the production STFT implementation is unchanged.
|
||||
|
||||
## Reproduction and focused checks
|
||||
|
||||
From this directory, apply the patch to a disposable SciPy 1.18.0 checkout:
|
||||
|
||||
```sh
|
||||
patch --fuzz=0 -d /path/to/scipy -p1 < stft-test-tolerances.patch
|
||||
```
|
||||
|
||||
Build and install that tree with SciPy's test dependencies. From outside the
|
||||
source directory, run the installed tests:
|
||||
|
||||
```sh
|
||||
python -m pytest --pyargs scipy.signal.tests.test_spectral \
|
||||
-k 'roundtrip_float32 or roundtrip_scaling' -q
|
||||
```
|
||||
|
||||
Use the same compiler flags and numerical libraries for before/after runs.
|
||||
The earlier reproduction called `TestSTFT.test_roundtrip_float32` and
|
||||
`TestSTFT.test_roundtrip_scaling` against the x86-64-v3 libraries, then loaded
|
||||
patched copies of the test modules. Both failed with the original bounds
|
||||
and passed with the adjusted bounds.
|
||||
|
||||
## Upstream status
|
||||
|
||||
[SciPy issue #25488](https://github.com/scipy/scipy/issues/25488) records
|
||||
related test failures with architecture-specific compiler flags. It is
|
||||
context for the local tolerance repair; this exact patch has not been
|
||||
submitted upstream during this work.
|
||||
|
||||
## Local NixOS integration and build results
|
||||
|
||||
[`../default.nix`](../default.nix) loads [`default.nix`](default.nix) through
|
||||
`pythonPackagesExtensions`, preserving the package's existing patches.
|
||||
The override also covers SciPy used to test other Python dependencies,
|
||||
including pgvector in portal's shared Python environment.
|
||||
|
||||
From the repository root:
|
||||
|
||||
```sh
|
||||
nix build --no-link -L .#nixosConfigurations.portal-1.pkgs.python314Packages.scipy
|
||||
```
|
||||
|
||||
The original remote build of patched SciPy 1.18.0 passed 87,723 tests, with
|
||||
8,342 skips, 300 expected failures, and 22 unexpected passes. The patch and
|
||||
override have been restored byte-for-byte from commit `24cbf74f`; those counts
|
||||
describe the earlier full build.
|
||||
|
||||
Restoration checks confirmed that the patch applies to the pinned source
|
||||
without fuzz, portal's evaluated SciPy retains its existing patch and install
|
||||
checks, and pgvector uses the patched SciPy. A full package or system rebuild
|
||||
was not repeated for this restoration.
|
||||
@@ -0,0 +1,5 @@
|
||||
{ scipy }:
|
||||
scipy.overridePythonAttrs (old: {
|
||||
# Keep the STFT tests enabled with tolerances for x86-64-v3 rounding.
|
||||
patches = (old.patches or [ ]) ++ [ ./stft-test-tolerances.patch ];
|
||||
})
|
||||
@@ -0,0 +1,51 @@
|
||||
Subject: [PATCH] signal: allow floating-point rounding in STFT tests
|
||||
|
||||
Keep the STFT tests enabled for x86-64-v3 builds. Allow two float32
|
||||
epsilons of relative error when comparing inverse-STFT implementations;
|
||||
float64 and the existing i686 override remain unchanged. Allow one
|
||||
float64 epsilon of absolute error in all three scaling round trips,
|
||||
which otherwise require exact zeros (observed residual: 4e-17 for a
|
||||
signal with amplitude 2).
|
||||
|
||||
Upstream issue: https://github.com/scipy/scipy/issues/25488
|
||||
|
||||
--- a/scipy/signal/tests/_scipy_spectral_test_shim.py
|
||||
+++ b/scipy/signal/tests/_scipy_spectral_test_shim.py
|
||||
@@ -294,7 +294,7 @@
|
||||
|
||||
# Adapted tolerances to account for resolution loss:
|
||||
atol = np.finfo(x.dtype).resolution*2 # instead of default atol = 0
|
||||
- rtol = 1e-7 # default for np.allclose()
|
||||
+ rtol = max(1e-7, 2 * np.finfo(x.dtype).eps)
|
||||
|
||||
# Relax atol on 32-Bit platforms a bit to pass CI tests.
|
||||
# - Not clear why there are discrepancies (in the FFT maybe?)
|
||||
--- a/scipy/signal/tests/test_spectral.py
|
||||
+++ b/scipy/signal/tests/test_spectral.py
|
||||
@@ -2044,7 +2044,7 @@
|
||||
|
||||
# Test round trip:
|
||||
x1 = istft(Zs, boundary=True, scaling='spectrum')[1]
|
||||
- assert_allclose(x1, x)
|
||||
+ assert_allclose(x1, x, atol=np.finfo(x.dtype).eps)
|
||||
|
||||
# For a Hann-windowed 256 sample length FFT, we expect a peak at
|
||||
# frequency 64 (since it is 1/4 the length of X) with a height of 1
|
||||
@@ -2074,7 +2074,7 @@
|
||||
|
||||
# Test round trip:
|
||||
x1 = istft(Zp, input_onesided=False, boundary=True, scaling='psd')[1]
|
||||
- assert_allclose(x1, x)
|
||||
+ assert_allclose(x1, x, atol=np.finfo(x.dtype).eps)
|
||||
|
||||
# The power of the one-sided psd-scaled STFT can be determined
|
||||
# analogously (note that the two sides are not of equal shape):
|
||||
@@ -2094,7 +2094,7 @@
|
||||
|
||||
# Test round trip:
|
||||
x1 = istft(Zp0, input_onesided=True, boundary=True, scaling='psd')[1]
|
||||
- assert_allclose(x1, x)
|
||||
+ assert_allclose(x1, x, atol=np.finfo(x.dtype).eps)
|
||||
|
||||
|
||||
class TestSampledSpectralRepresentations:
|
||||
@@ -7,11 +7,7 @@
|
||||
}:
|
||||
let
|
||||
cfg = config.services.snapshot_manager;
|
||||
snapshotManagerPackages =
|
||||
ps: with ps; [
|
||||
httpx
|
||||
typer
|
||||
];
|
||||
snapshotManagerPackages = ps: with ps; [ typer ];
|
||||
in
|
||||
{
|
||||
options = {
|
||||
|
||||
Generated
+100
-23
@@ -7,11 +7,11 @@
|
||||
]
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1781152676,
|
||||
"narHash": "sha256-RxWs5ND31KzTG7wvMM+PMfUjyNpmIEr999lqNARaM5o=",
|
||||
"lastModified": 1789770686,
|
||||
"narHash": "sha256-uZkBR7yHdIKUFB5SZdfgh1qkGfI3XmYmI/lTiquxbck=",
|
||||
"owner": "nix-community",
|
||||
"repo": "disko",
|
||||
"rev": "ff8702b4de27f72b4c78573dfb89ec74e36abdf1",
|
||||
"rev": "725ea35e410ad83be4931d1bff7e090eacaf3563",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
@@ -20,6 +20,24 @@
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"flake-utils": {
|
||||
"inputs": {
|
||||
"systems": "systems"
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1731533236,
|
||||
"narHash": "sha256-l0KFg5HjrsfsO/JpG+r7fRrqm12kzFHyUHqHCVpMMbI=",
|
||||
"owner": "numtide",
|
||||
"repo": "flake-utils",
|
||||
"rev": "11707dc2f618dd54ca8739b309ec4fc024de578b",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "numtide",
|
||||
"repo": "flake-utils",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"home-manager": {
|
||||
"inputs": {
|
||||
"nixpkgs": [
|
||||
@@ -27,11 +45,11 @@
|
||||
]
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1788651960,
|
||||
"narHash": "sha256-v9wJd32eZ2bvhBzVOd7TIjLQd011P7nwOhjKtWlci5I=",
|
||||
"lastModified": 1790819692,
|
||||
"narHash": "sha256-rvubAPbh3QCliic3sAK+CXTrPCGgJstY52OTs/5H1J4=",
|
||||
"owner": "nix-community",
|
||||
"repo": "home-manager",
|
||||
"rev": "2c0350c759688177331b8f5242311fae8877bdb3",
|
||||
"rev": "c8ecc29e5175452bee4a2aa1ba2383856d795338",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
@@ -40,16 +58,38 @@
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"jellyswarrm": {
|
||||
"inputs": {
|
||||
"flake-utils": "flake-utils",
|
||||
"nixpkgs": [
|
||||
"nixpkgs"
|
||||
],
|
||||
"rust-overlay": "rust-overlay"
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1790427786,
|
||||
"narHash": "sha256-8+Ip0HFW2oZiRr0zCZmPPIHfTdxxHy4CmSF1uOkM3Bw=",
|
||||
"owner": "LLukas22",
|
||||
"repo": "Jellyswarrm",
|
||||
"rev": "9e67c5ad12116add867ba6c1bf69f767879e9147",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "LLukas22",
|
||||
"repo": "Jellyswarrm",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"nixos-hardware": {
|
||||
"inputs": {
|
||||
"nixpkgs": "nixpkgs"
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1788860136,
|
||||
"narHash": "sha256-MhPMOFV4pVkygWEbQ8t1De/uQ9cWF1u++tRe2L5tG48=",
|
||||
"lastModified": 1790722812,
|
||||
"narHash": "sha256-XwFt1uLyaBCQU1/nUeGqeBnqNXPVgGRnz20YVYdmF6Y=",
|
||||
"owner": "nixos",
|
||||
"repo": "nixos-hardware",
|
||||
"rev": "62173785b9a18c78b4a15aca2623d02bceb9d077",
|
||||
"rev": "06f9ecaea5f64b6ff61cf42cb32f21621c4fa14a",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
@@ -61,11 +101,11 @@
|
||||
},
|
||||
"nixpkgs": {
|
||||
"locked": {
|
||||
"lastModified": 1767892417,
|
||||
"narHash": "sha256-8bW3q88CEg2u4hSP66Vf4lpbLonHz7hqDNBMcCY7E9U=",
|
||||
"rev": "3497aa5c9457a9d88d71fa93a4a8368816fbeeba",
|
||||
"lastModified": 1789546076,
|
||||
"narHash": "sha256-vWkSk5bbfTqdtMoSgD9FshACO8JCvXTFi+3cqEp0mH0=",
|
||||
"rev": "b1b875982b17dabde9b4a37f3e229e74913e6db3",
|
||||
"type": "tarball",
|
||||
"url": "https://releases.nixos.org/nixos/unstable/nixos-26.05pre924538.3497aa5c9457/nixexprs.tar.xz"
|
||||
"url": "https://releases.nixos.org/nixos/unstable/nixos-26.11pre1074753.b1b875982b17/nixexprs.tar.xz"
|
||||
},
|
||||
"original": {
|
||||
"type": "tarball",
|
||||
@@ -74,11 +114,11 @@
|
||||
},
|
||||
"nixpkgs-master": {
|
||||
"locked": {
|
||||
"lastModified": 1788892992,
|
||||
"narHash": "sha256-cIMFh9gyU4/aLeB3JCcsWM3tTAvD9pAq9Smr1Wa8aIU=",
|
||||
"lastModified": 1790862528,
|
||||
"narHash": "sha256-00jiK7QCLGuVe4mj3kDa6P/iDFKb87aK9ZtJDZCOvTc=",
|
||||
"owner": "nixos",
|
||||
"repo": "nixpkgs",
|
||||
"rev": "dff6994123e257ec9901c271bc2b52e64d7c8f05",
|
||||
"rev": "86f3f30260edec38090733d0667e818e6e2ea6f5",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
@@ -106,11 +146,11 @@
|
||||
},
|
||||
"nixpkgs_2": {
|
||||
"locked": {
|
||||
"lastModified": 1788752844,
|
||||
"narHash": "sha256-VaWGJ6+cIYN2erfSecbRV+4ljI185Ty2wUrXyvQbgOw=",
|
||||
"lastModified": 1790689126,
|
||||
"narHash": "sha256-ilerN1WLSvF+HMjziC/Wv99J5y02maDH+6hZPwsORKg=",
|
||||
"owner": "nixos",
|
||||
"repo": "nixpkgs",
|
||||
"rev": "dc5d91f840324650bac8c379428c7037a416959a",
|
||||
"rev": "b4fd65b198c599cbe814fcb9f42d25d021595ec9",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
@@ -124,12 +164,34 @@
|
||||
"inputs": {
|
||||
"disko": "disko",
|
||||
"home-manager": "home-manager",
|
||||
"jellyswarrm": "jellyswarrm",
|
||||
"nixos-hardware": "nixos-hardware",
|
||||
"nixpkgs": "nixpkgs_2",
|
||||
"nixpkgs-master": "nixpkgs-master",
|
||||
"nixpkgs-stable": "nixpkgs-stable",
|
||||
"sops-nix": "sops-nix",
|
||||
"systems": "systems"
|
||||
"systems": "systems_2"
|
||||
}
|
||||
},
|
||||
"rust-overlay": {
|
||||
"inputs": {
|
||||
"nixpkgs": [
|
||||
"jellyswarrm",
|
||||
"nixpkgs"
|
||||
]
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1779419951,
|
||||
"narHash": "sha256-dMX0PUslUHPajP6o8FEoRdFv9afq/dec4POR0vVfjK4=",
|
||||
"owner": "oxalica",
|
||||
"repo": "rust-overlay",
|
||||
"rev": "5b5c521d6cae9ef4aa32f888eb2c0ce595c9be52",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "oxalica",
|
||||
"repo": "rust-overlay",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"sops-nix": {
|
||||
@@ -139,11 +201,11 @@
|
||||
]
|
||||
},
|
||||
"locked": {
|
||||
"lastModified": 1788337237,
|
||||
"narHash": "sha256-gkSH8VUtCo6hnysNmb9DbTuDepH2t5pv+QWjP75xKAk=",
|
||||
"lastModified": 1790498116,
|
||||
"narHash": "sha256-rs9meAYxW3zzrh43yaW7htrqCD+X9+pupDPHN86fumI=",
|
||||
"owner": "Mic92",
|
||||
"repo": "sops-nix",
|
||||
"rev": "fbf759290e0cb0a98dfc813a4eb7d53ad1dacb57",
|
||||
"rev": "5efb5a6f4f5ab192817d28557dd4d650fa14d866",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
@@ -153,6 +215,21 @@
|
||||
}
|
||||
},
|
||||
"systems": {
|
||||
"locked": {
|
||||
"lastModified": 1681028828,
|
||||
"narHash": "sha256-Vy1rq5AaRuLzOxct8nz4T6wlgyUR7zLU309k9mBC768=",
|
||||
"owner": "nix-systems",
|
||||
"repo": "default",
|
||||
"rev": "da67096a3b9bf56a91d16901293e51ba5b49a27e",
|
||||
"type": "github"
|
||||
},
|
||||
"original": {
|
||||
"owner": "nix-systems",
|
||||
"repo": "default",
|
||||
"type": "github"
|
||||
}
|
||||
},
|
||||
"systems_2": {
|
||||
"locked": {
|
||||
"lastModified": 1689347949,
|
||||
"narHash": "sha256-12tWmuL2zgBgZkdoB6qXZsgJEH9LR3oUgpaQq2RbI80=",
|
||||
|
||||
@@ -21,6 +21,11 @@
|
||||
|
||||
nixos-hardware.url = "github:nixos/nixos-hardware/master";
|
||||
|
||||
jellyswarrm = {
|
||||
url = "github:LLukas22/Jellyswarrm";
|
||||
inputs.nixpkgs.follows = "nixpkgs";
|
||||
};
|
||||
|
||||
home-manager = {
|
||||
url = "github:nix-community/home-manager";
|
||||
inputs.nixpkgs.follows = "nixpkgs";
|
||||
|
||||
+10
-4
@@ -1,13 +1,13 @@
|
||||
{ inputs, ... }:
|
||||
{
|
||||
# When applied, the stable nixpkgs set (declared in the flake inputs) will be accessible through 'pkgs.stable'
|
||||
# Additional package sets are accessible through `pkgs.<name>`.
|
||||
stable = final: _prev: {
|
||||
stable = import inputs.nixpkgs-stable {
|
||||
system = final.stdenv.hostPlatform.system;
|
||||
config.allowUnfree = true;
|
||||
};
|
||||
};
|
||||
# When applied, the master nixpkgs set (declared in the flake inputs) will be accessible through 'pkgs.master'
|
||||
|
||||
master = final: _prev: {
|
||||
master = import inputs.nixpkgs-master {
|
||||
system = final.stdenv.hostPlatform.system;
|
||||
@@ -15,6 +15,12 @@
|
||||
};
|
||||
};
|
||||
|
||||
test-exclusions = import ./test-exclusions.nix;
|
||||
x86-64-v3-workarounds = import ./x86-64-v3-workarounds.nix;
|
||||
# Baseline x86-64 (v1) packages for prebuilt applications that should not
|
||||
# inherit an x86-64-v3 host platform.
|
||||
x86-v1 = final: _prev: {
|
||||
x86-v1 = import inputs.nixpkgs {
|
||||
system = final.stdenv.hostPlatform.system;
|
||||
config.allowUnfree = true;
|
||||
};
|
||||
};
|
||||
}
|
||||
|
||||
@@ -1,133 +0,0 @@
|
||||
# Test exclusions for the locally rebuilt x86-64-v3 package set.
|
||||
#
|
||||
# Selecting x86-64-v3 changes every affected derivation, so the normal
|
||||
# nixpkgs binary cache cannot be used and upstream test suites run locally.
|
||||
# The jeeves builder uses /tmp/nix-builds so filesystem tests run on tmpfs
|
||||
# instead of ZFS with normalization=formD and utf8only=on; those tests remain
|
||||
# enabled. The remaining workarounds cover UDP readiness, resource-sensitive
|
||||
# parser and nested-worker races, and mismatched timeout clocks, plus
|
||||
# architecture-dependent floating-point differences whose risk we accept for
|
||||
# our workloads. Keep these exceptions visible until their causes are fixed.
|
||||
_final: prev: {
|
||||
gnutls = prev.gnutls.overrideAttrs (old: {
|
||||
# This test uses a fixed four-second sleep instead of checking UDP
|
||||
# readiness; the client saw no listener in the x86-64-v3 build.
|
||||
postPatch = (old.postPatch or "") + ''
|
||||
sed '2iexit 77' -i tests/serv-udp.sh
|
||||
'';
|
||||
});
|
||||
|
||||
prometheus = prev.prometheus.overrideAttrs (
|
||||
old:
|
||||
let
|
||||
assets = old.passthru.assets.overrideAttrs (assetsOld: {
|
||||
# CodeMirror's bounded synchronous parser can return an incomplete tree
|
||||
# when these cases run on a heavily loaded builder.
|
||||
postPatch = (assetsOld.postPatch or "") + ''
|
||||
substituteInPlace module/codemirror-promql/src/complete/hybrid.test.ts \
|
||||
--replace-fail "it(value.title, () => {" \
|
||||
"(value.title === 'autocomplete topk params 2' ? it.skip : it)(value.title, () => {"
|
||||
substituteInPlace module/codemirror-promql/src/parser/vector.test.ts \
|
||||
--replace-fail "it(value.binaryExpr, () => {" \
|
||||
"(value.binaryExpr === 'foo * on(test,blub) bar' ? it.skip : it)(value.binaryExpr, () => {"
|
||||
'';
|
||||
});
|
||||
in
|
||||
{
|
||||
postPatch = builtins.replaceStrings [ "${old.passthru.assets}" ] [ "${assets}" ] (
|
||||
builtins.unsafeDiscardStringContext old.postPatch
|
||||
);
|
||||
passthru = old.passthru // {
|
||||
inherit assets;
|
||||
};
|
||||
}
|
||||
);
|
||||
|
||||
pythonPackagesExtensions = prev.pythonPackagesExtensions ++ [
|
||||
(_pythonFinal: pythonPrev: {
|
||||
backrefs = pythonPrev.backrefs.overridePythonAttrs (old: {
|
||||
# regex measures its timeout in process CPU time, while this test used
|
||||
# wall time and could miss the timeout when a busy builder descheduled it.
|
||||
postPatch = (old.postPatch or "") + ''
|
||||
substituteInPlace tests/test_bregex.py \
|
||||
--replace-fail "time.time()" "time.process_time()"
|
||||
'';
|
||||
});
|
||||
|
||||
pytest-xdist = pythonPrev.pytest-xdist.overridePythonAttrs (old: {
|
||||
# The suite exercises its own worker pools. Run the outer suite with one
|
||||
# worker and allow inner workers more time on heavily loaded builders.
|
||||
postPatch = (old.postPatch or "") + ''
|
||||
substituteInPlace testing/test_remote.py \
|
||||
--replace-fail "WAIT_TIMEOUT = 10.0" "WAIT_TIMEOUT = 60.0"
|
||||
'';
|
||||
preCheck = builtins.replaceStrings [ "--numprocesses=$NIX_BUILD_CORES" ] [ "--numprocesses=1" ] (
|
||||
old.preCheck or ""
|
||||
);
|
||||
# This test deliberately crashes workers past the restart limit and
|
||||
# races while checking which replacement message was emitted.
|
||||
disabledTests = (old.disabledTests or [ ]) ++ [
|
||||
"test_max_worker_restart_tests_queued"
|
||||
];
|
||||
});
|
||||
|
||||
jupyter-server = pythonPrev.jupyter-server.overridePythonAttrs (old: {
|
||||
# The kernel reply arrived after the one-second outer deadline when the
|
||||
# builder was heavily loaded. Keep the regression test but allow it the
|
||||
# same margin as the other resource-sensitive tests.
|
||||
postPatch = (old.postPatch or "") + ''
|
||||
substituteInPlace tests/services/kernels/test_connection.py \
|
||||
--replace-fail \
|
||||
"await asyncio.wait_for(asyncio.wrap_future(conn2.request_kernel_info()), timeout=1.0)" \
|
||||
"await asyncio.wait_for(asyncio.wrap_future(conn2.request_kernel_info()), timeout=10.0)"
|
||||
'';
|
||||
});
|
||||
|
||||
scipy = pythonPrev.scipy.overridePythonAttrs (old: {
|
||||
# x86-64-v3 FFT implementations produce rounding differences outside
|
||||
# these tests' strict tolerances. We accept the numerical-precision
|
||||
# risk for our workloads.
|
||||
disabledTests = (old.disabledTests or [ ]) ++ [
|
||||
"test_roundtrip_float32"
|
||||
"test_roundtrip_scaling"
|
||||
];
|
||||
});
|
||||
|
||||
sentry-sdk = pythonPrev.sentry-sdk.overridePythonAttrs (old: {
|
||||
# This test globally mocks threading.current_thread while another
|
||||
# thread is running. On Python 3.14, Thread.join can race with that
|
||||
# mock and exhaust its single side effect before the worker removes it.
|
||||
disabledTests = (old.disabledTests or [ ]) ++ [
|
||||
"test_get_current_thread_meta_main_thread"
|
||||
];
|
||||
});
|
||||
|
||||
torchaudio = pythonPrev.torchaudio.overridePythonAttrs (old: {
|
||||
# x86-64-v3 pitch shifting produces batch-versus-single-item numerical
|
||||
# differences up to 2.9e-6. We accept that audio-precision risk for our
|
||||
# workloads.
|
||||
disabledTests = (old.disabledTests or [ ]) ++ [
|
||||
"test_batch_pitch_shift"
|
||||
];
|
||||
});
|
||||
|
||||
torchcodec = pythonPrev.torchcodec.overridePythonAttrs (old: {
|
||||
# For these 8 kHz MP3 cases, the x86-64-v3 API and CLI codec paths
|
||||
# differ in 0.8% of decoded samples. Retain the original tolerance for
|
||||
# 99% of samples and accept the localized audio-precision risk.
|
||||
postPatch = (old.postPatch or "") + ''
|
||||
substituteInPlace test/test_encoders.py \
|
||||
--replace-fail \
|
||||
'if sys.platform == "darwin":' \
|
||||
'if sys.platform == "darwin" or (
|
||||
format == "mp3"
|
||||
and sample_rate == 8_000
|
||||
and asset is SINE_MONO_S32
|
||||
and bit_rate in (None, 0)
|
||||
and num_channels in (None, 1)
|
||||
):'
|
||||
'';
|
||||
});
|
||||
})
|
||||
];
|
||||
}
|
||||
@@ -1,60 +0,0 @@
|
||||
# Compatibility fixes for packages rebuilt with x86-64-v3.
|
||||
#
|
||||
# The v3 baseline enables instructions that expose source assumptions hidden
|
||||
# by the generic x86-64 build. Keep compile fixes here, separate from test
|
||||
# exclusions, until upstream or nixpkgs incorporates them.
|
||||
_final: prev:
|
||||
let
|
||||
patchAbseilBmi2Include =
|
||||
package:
|
||||
package.overrideAttrs (old: {
|
||||
# GCC and Clang prohibit including their internal BMI2 header directly.
|
||||
# The public umbrella provides the same intrinsics with the required
|
||||
# compiler setup.
|
||||
postPatch = (old.postPatch or "") + ''
|
||||
substituteInPlace third_party/abseil-cpp/absl/container/internal/raw_hash_set.h \
|
||||
--replace-fail "#include <bmi2intrin.h>" "#include <immintrin.h>"
|
||||
'';
|
||||
});
|
||||
|
||||
removeSiblingOutputChecks =
|
||||
package:
|
||||
package.overrideAttrs (old: {
|
||||
# Nix 2.34 can validate a partial multi-output rebuild against only the
|
||||
# outputs still being realised. PostgreSQL's checks then reject valid
|
||||
# sibling names such as "out" and "lib". Keep the test suite and
|
||||
# disallowed-requisite checks; accept the loss of cross-output checks.
|
||||
outputChecks = builtins.mapAttrs (
|
||||
_output: checks: builtins.removeAttrs checks [ "disallowedReferences" ]
|
||||
) (old.outputChecks or { });
|
||||
});
|
||||
|
||||
electron43Unwrapped = patchAbseilBmi2Include prev.electron_43.unwrapped;
|
||||
electron43 = prev.electron_43.override {
|
||||
electron-unwrapped = electron43Unwrapped;
|
||||
};
|
||||
|
||||
signalCallPackage =
|
||||
path: args:
|
||||
let
|
||||
package = prev.callPackage path args;
|
||||
in
|
||||
if builtins.baseNameOf path == "webrtc.nix" then patchAbseilBmi2Include package else package;
|
||||
in
|
||||
prev.lib.optionalAttrs ((prev.stdenv.hostPlatform.gcc.arch or null) == "x86-64-v3") {
|
||||
deno =
|
||||
let
|
||||
librusty_v8 = patchAbseilBmi2Include prev.deno.passthru.librusty_v8;
|
||||
in
|
||||
prev.deno.override { inherit librusty_v8; };
|
||||
|
||||
electron_43 = electron43;
|
||||
|
||||
postgresql = removeSiblingOutputChecks prev.postgresql;
|
||||
postgresql_18 = removeSiblingOutputChecks prev.postgresql_18;
|
||||
|
||||
signal-desktop = prev.signal-desktop.override {
|
||||
electron_43 = electron43;
|
||||
callPackage = signalCallPackage;
|
||||
};
|
||||
}
|
||||
+48
-34
@@ -2,49 +2,63 @@
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
from os import getenv
|
||||
|
||||
import httpx
|
||||
import socket
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
SIGNAL_API_URL = "http://localhost:8989/v2/send"
|
||||
SIGNAL_API_TIMEOUT = 4.0
|
||||
|
||||
class SignalRPCError(RuntimeError):
|
||||
"""signal-cli returned an error or closed without responding."""
|
||||
|
||||
|
||||
def signal_alert(body: str, title: str = "") -> None:
|
||||
"""Send a signal alert.
|
||||
def signal_alert(body: str, from_phone: str, to_phone: str, *, timeout: float = 4.0) -> None:
|
||||
"""Send a Signal alert through the local signal-cli daemon.
|
||||
|
||||
Args:
|
||||
body (str): The body of the alert.
|
||||
title (str, optional): The title of the alert. Defaults to "".
|
||||
"""
|
||||
from_phone = getenv("SIGNAL_ALERT_FROM_PHONE")
|
||||
to_phone = getenv("SIGNAL_ALERT_TO_PHONE")
|
||||
if not from_phone or not to_phone:
|
||||
logger.info("SIGNAL_ALERT_FROM_PHONE or SIGNAL_ALERT_TO_PHONE not set")
|
||||
return
|
||||
body: The body of the alert.
|
||||
from_phone: The Signal account sending the alert.
|
||||
to_phone: The Signal account receiving the alert.
|
||||
timeout: Seconds to wait on each socket operation.
|
||||
|
||||
# Apprise's Signal integration did not support titles, so preserve that behavior.
|
||||
if title:
|
||||
logger.debug("Signal does not support notification titles; ignoring title")
|
||||
Raises:
|
||||
SignalRPCError: If signal-cli returns an error or closes the
|
||||
connection before responding.
|
||||
OSError: If the socket is unreachable or an operation times out.
|
||||
"""
|
||||
signal_rpc_id = "signal-alert"
|
||||
request = {
|
||||
"jsonrpc": "2.0",
|
||||
"method": "send",
|
||||
"params": {
|
||||
"account": from_phone,
|
||||
"recipient": [to_phone],
|
||||
"message": body,
|
||||
},
|
||||
"id": signal_rpc_id,
|
||||
}
|
||||
|
||||
try:
|
||||
response = httpx.post(
|
||||
SIGNAL_API_URL,
|
||||
json={
|
||||
"message": body,
|
||||
"number": from_phone,
|
||||
"recipients": [to_phone],
|
||||
"text_mode": "normal",
|
||||
},
|
||||
timeout=SIGNAL_API_TIMEOUT,
|
||||
follow_redirects=True,
|
||||
)
|
||||
except httpx.HTTPError:
|
||||
logger.exception("Unable to contact the Signal API")
|
||||
return
|
||||
with socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) as client:
|
||||
client.settimeout(timeout)
|
||||
client.connect("/run/signal-cli/socket")
|
||||
client.sendall(json.dumps(request).encode() + b"\n")
|
||||
|
||||
if response.status_code not in {httpx.codes.OK, httpx.codes.CREATED}:
|
||||
logger.error("Signal API returned HTTP status %d", response.status_code)
|
||||
buffer = b""
|
||||
while chunk := client.recv(65536):
|
||||
buffer += chunk
|
||||
while b"\n" in buffer:
|
||||
line, buffer = buffer.split(b"\n", maxsplit=1)
|
||||
response = json.loads(line)
|
||||
if response.get("id") != signal_rpc_id:
|
||||
continue
|
||||
if rpc_error := response.get("error"):
|
||||
error = f"Signal RPC returned an error: {rpc_error}"
|
||||
raise SignalRPCError(error)
|
||||
return
|
||||
error = "Signal RPC socket closed before returning a response"
|
||||
raise SignalRPCError(error)
|
||||
except (OSError, json.JSONDecodeError) as exc:
|
||||
error = f"Signal RPC failed: {exc!r}"
|
||||
raise SignalRPCError(error) from exc
|
||||
|
||||
@@ -6,6 +6,7 @@ import logging
|
||||
import sys
|
||||
import tomllib
|
||||
from functools import cache
|
||||
from os import getenv
|
||||
from pathlib import Path # noqa: TC003 This is required for the typer CLI
|
||||
from re import compile as re_compile
|
||||
from re import search
|
||||
@@ -24,6 +25,15 @@ def main(config_file: Path) -> None:
|
||||
configure_logger(level="DEBUG")
|
||||
logger.info("Starting snapshot_manager")
|
||||
|
||||
from_phone = getenv("SIGNAL_ALERT_FROM_PHONE")
|
||||
to_phone = getenv("SIGNAL_ALERT_TO_PHONE")
|
||||
if not from_phone:
|
||||
error = "SIGNAL_ALERT_FROM_PHONE environment variable is not set"
|
||||
raise ValueError(error)
|
||||
if not to_phone:
|
||||
error = "SIGNAL_ALERT_TO_PHONE environment variable is not set"
|
||||
raise ValueError(error)
|
||||
|
||||
try:
|
||||
time_stamp = get_time_stamp()
|
||||
|
||||
@@ -33,14 +43,14 @@ def main(config_file: Path) -> None:
|
||||
if status != "snapshot created":
|
||||
msg = f"{dataset.name} failed to create snapshot {time_stamp}"
|
||||
logger.error(msg)
|
||||
signal_alert(msg)
|
||||
signal_alert(msg, from_phone, to_phone)
|
||||
continue
|
||||
count_lookup = get_count_lookup(config_file, dataset.name)
|
||||
logger.info(f"using {count_lookup} for {dataset.name}")
|
||||
get_snapshots_to_delete(dataset, count_lookup)
|
||||
get_snapshots_to_delete(dataset, count_lookup, from_phone, to_phone)
|
||||
except Exception:
|
||||
logger.exception("snapshot_manager failed")
|
||||
signal_alert("snapshot_manager failed")
|
||||
signal_alert("snapshot_manager failed", from_phone, to_phone)
|
||||
sys.exit(1)
|
||||
else:
|
||||
logger.info("snapshot_manager completed")
|
||||
@@ -92,12 +102,16 @@ def load_config_data(config_file: Path) -> dict[str, dict[str, int]]:
|
||||
def get_snapshots_to_delete(
|
||||
dataset: Dataset,
|
||||
count_lookup: dict[str, int],
|
||||
from_phone: str,
|
||||
to_phone: str,
|
||||
) -> None:
|
||||
"""Get snapshots to delete.
|
||||
|
||||
Args:
|
||||
dataset (Dataset): the dataset
|
||||
count_lookup (dict[str, int]): the count lookup
|
||||
from_phone (str): The Signal account sending alerts.
|
||||
to_phone (str): The Signal account receiving alerts.
|
||||
"""
|
||||
snapshots = dataset.get_snapshots()
|
||||
|
||||
@@ -127,7 +141,7 @@ def get_snapshots_to_delete(
|
||||
for snapshot in snapshots_being_deleted:
|
||||
if error := dataset.delete_snapshot(snapshot):
|
||||
error_message = f"{dataset.name}@{snapshot} failed to delete: {error}"
|
||||
signal_alert(error_message)
|
||||
signal_alert(error_message, from_phone, to_phone)
|
||||
logger.error(error_message)
|
||||
|
||||
|
||||
|
||||
Executable
+37
@@ -0,0 +1,37 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
set -Eeuo pipefail
|
||||
|
||||
if [[ "$(hostname)" != "jeeves" ]]; then
|
||||
echo "Signal device authorization must run on jeeves." >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ "$EUID" -ne 0 ]]; then
|
||||
echo "Signal device authorization must run as root." >&2
|
||||
exit 1
|
||||
fi
|
||||
if [[ "$#" -ne 1 ]]; then
|
||||
echo "Usage: signal_authorize.sh DEVICE_URI" >&2
|
||||
exit 2
|
||||
fi
|
||||
if [[ "$1" != sgnl://linkdevice\?* ]]; then
|
||||
echo "Invalid Signal device link URI." >&2
|
||||
exit 2
|
||||
fi
|
||||
|
||||
service_name="signal-cli"
|
||||
data_dir="/var/lib/signal-cli"
|
||||
device_uri="$1"
|
||||
restart_service=false
|
||||
|
||||
cleanup() {
|
||||
if [[ "$restart_service" == true ]]; then
|
||||
systemctl start "$service_name"
|
||||
fi
|
||||
}
|
||||
trap cleanup EXIT
|
||||
|
||||
restart_service=true
|
||||
systemctl stop "$service_name"
|
||||
runuser -u signal-cli -- \
|
||||
signal-cli --data-dir "$data_dir" -a +12016554378 addDevice --uri "$device_uri"
|
||||
Executable
+60
@@ -0,0 +1,60 @@
|
||||
#!/usr/bin/env bash
|
||||
|
||||
set -Eeuo pipefail
|
||||
|
||||
host_name="$(hostname)"
|
||||
if [[ "$#" -ne 0 ]]; then
|
||||
echo "Usage: signal_link.sh" >&2
|
||||
exit 2
|
||||
fi
|
||||
|
||||
service_name="signal-cli"
|
||||
data_dir="/var/lib/signal-cli"
|
||||
link_pid=""
|
||||
temp_dir=""
|
||||
restart_service=false
|
||||
|
||||
cleanup() {
|
||||
if [[ -n "$link_pid" ]] && kill -0 "$link_pid" 2>/dev/null; then
|
||||
kill "$link_pid" 2>/dev/null || true
|
||||
wait "$link_pid" 2>/dev/null || true
|
||||
fi
|
||||
|
||||
if [[ -n "$temp_dir" ]]; then
|
||||
rm -f -- "$temp_dir/link-uri"
|
||||
rmdir -- "$temp_dir"
|
||||
fi
|
||||
|
||||
if [[ "$restart_service" == true ]]; then
|
||||
sudo systemctl start "$service_name"
|
||||
fi
|
||||
}
|
||||
trap cleanup EXIT
|
||||
|
||||
restart_service=true
|
||||
sudo systemctl stop "$service_name"
|
||||
|
||||
temp_dir="$(mktemp -d)"
|
||||
link_fifo="$temp_dir/link-uri"
|
||||
mkfifo "$link_fifo"
|
||||
|
||||
sudo -u signal-cli \
|
||||
signal-cli --data-dir "$data_dir" link --name "$host_name" >"$link_fifo" &
|
||||
link_pid="$!"
|
||||
|
||||
if ! IFS= read -r device_uri <"$link_fifo"; then
|
||||
wait "$link_pid"
|
||||
exit 1
|
||||
fi
|
||||
if [[ "$device_uri" != sgnl://linkdevice\?* ]]; then
|
||||
echo "signal-cli returned an invalid device link URI." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "Run this command manually on jeeves in another dotfiles dir:"
|
||||
printf "sudo ./scripts/signal/authorize.sh %q\n" "$device_uri"
|
||||
echo "Waiting for jeeves to authorize this device..."
|
||||
|
||||
wait "$link_pid"
|
||||
link_pid=""
|
||||
echo "$host_name is now linked to the Signal account on jeeves."
|
||||
@@ -8,12 +8,12 @@
|
||||
"${inputs.self}/common/optional/monitoring-agent.nix"
|
||||
"${inputs.self}/common/optional/nvidia.nix"
|
||||
"${inputs.self}/common/optional/scanner.nix"
|
||||
"${inputs.self}/common/optional/steam.nix"
|
||||
"${inputs.self}/common/optional/signal-cli.nix"
|
||||
"${inputs.self}/common/optional/syncthing_base.nix"
|
||||
"${inputs.self}/common/optional/systemd-boot.nix"
|
||||
"${inputs.self}/common/optional/tailscale.nix"
|
||||
"${inputs.self}/common/optional/update.nix"
|
||||
"${inputs.self}/common/optional/x86-64-v3.nix"
|
||||
"${inputs.self}/common/optional/x86-64-v3"
|
||||
"${inputs.self}/common/optional/zfs"
|
||||
./hardware.nix
|
||||
./syncthing.nix
|
||||
|
||||
@@ -4,12 +4,13 @@
|
||||
"${inputs.self}/users/richie"
|
||||
"${inputs.self}/common/global"
|
||||
"${inputs.self}/common/optional/docker.nix"
|
||||
"${inputs.self}/common/optional/signal-cli.nix"
|
||||
"${inputs.self}/common/optional/ssh_decrypt.nix"
|
||||
"${inputs.self}/common/optional/syncthing_base.nix"
|
||||
"${inputs.self}/common/optional/systemd-boot.nix"
|
||||
"${inputs.self}/common/optional/tailscale.nix"
|
||||
"${inputs.self}/common/optional/update.nix"
|
||||
"${inputs.self}/common/optional/x86-64-v3.nix"
|
||||
"${inputs.self}/common/optional/x86-64-v3"
|
||||
"${inputs.self}/common/optional/zfs"
|
||||
./docker
|
||||
./hardware.nix
|
||||
|
||||
@@ -9,11 +9,12 @@ in
|
||||
"${inputs.self}/common/global"
|
||||
"${inputs.self}/common/optional/docker.nix"
|
||||
"${inputs.self}/common/optional/monitoring-agent.nix"
|
||||
"${inputs.self}/common/optional/signal-cli.nix"
|
||||
"${inputs.self}/common/optional/ssh_decrypt.nix"
|
||||
"${inputs.self}/common/optional/syncthing_base.nix"
|
||||
"${inputs.self}/common/optional/tailscale.nix"
|
||||
"${inputs.self}/common/optional/update.nix"
|
||||
"${inputs.self}/common/optional/x86-64-v3.nix"
|
||||
"${inputs.self}/common/optional/x86-64-v3"
|
||||
"${inputs.self}/common/optional/zfs"
|
||||
./monitoring
|
||||
./docker
|
||||
|
||||
@@ -1,18 +0,0 @@
|
||||
let
|
||||
vars = import ../vars.nix;
|
||||
in
|
||||
{
|
||||
virtualisation.oci-containers.containers.signal_cli_rest_api = {
|
||||
image = "bbernhard/signal-cli-rest-api:0.199-dev";
|
||||
ports = [
|
||||
"8989:8080"
|
||||
];
|
||||
volumes = [
|
||||
"${vars.docker_configs}/signal-cli-config:/home/.local/share/signal-cli"
|
||||
];
|
||||
environment = {
|
||||
MODE = "json-rpc";
|
||||
};
|
||||
autoStart = true;
|
||||
};
|
||||
}
|
||||
@@ -7,13 +7,13 @@ let
|
||||
gitea_ssh = 2223;
|
||||
grafana = 3000;
|
||||
jellyfin_http = 8096;
|
||||
jellyswarrm = 3100;
|
||||
nix_binary_cache = 5000;
|
||||
nornsight = 8001;
|
||||
ollama = 11434;
|
||||
open_webui = 8080;
|
||||
postgresql = 5432;
|
||||
share = 8091;
|
||||
signal_cli = 8989;
|
||||
syncthing = 8384;
|
||||
};
|
||||
in
|
||||
@@ -28,6 +28,7 @@ in
|
||||
ports.audiobookshelf
|
||||
ports.gems
|
||||
ports.jellyfin_http
|
||||
ports.jellyswarrm
|
||||
ports.nix_binary_cache
|
||||
ports.nornsight
|
||||
ports.share
|
||||
@@ -40,7 +41,6 @@ in
|
||||
ports.ollama
|
||||
ports.open_webui
|
||||
ports.postgresql
|
||||
ports.signal_cli
|
||||
ports.syncthing
|
||||
];
|
||||
};
|
||||
|
||||
@@ -21,5 +21,16 @@
|
||||
nix-builder-12.enable = true;
|
||||
nix-builder-13.enable = true;
|
||||
nix-builder-14.enable = true;
|
||||
|
||||
# Warm the shared x86-64-v3 cache before the smaller per-system runners
|
||||
# start. Eight jobs with eight cores each can use Jeeves' 64 logical CPUs,
|
||||
# while the 6000% quota leaves some capacity for its normal services.
|
||||
nix-cache-builder = {
|
||||
enable = true;
|
||||
labels = [ "nix-cache-builder:host" ];
|
||||
cores = 8;
|
||||
maxJobs = 8;
|
||||
cpuQuota = "6000%";
|
||||
};
|
||||
};
|
||||
}
|
||||
|
||||
@@ -11,11 +11,8 @@ let
|
||||
cfg = config.services.nix_builder;
|
||||
runnerUsername = "gitea-runner";
|
||||
runnerUserid = 601;
|
||||
runnerLabels = [
|
||||
"self-hosted:host"
|
||||
"nixos:host"
|
||||
];
|
||||
containerConfig =
|
||||
containerCfg:
|
||||
{
|
||||
config,
|
||||
pkgs,
|
||||
@@ -50,8 +47,8 @@ let
|
||||
useHostResolvConf = false;
|
||||
};
|
||||
nix.settings = {
|
||||
cores = 8;
|
||||
max-jobs = 2;
|
||||
inherit (containerCfg) cores;
|
||||
max-jobs = containerCfg.maxJobs;
|
||||
system-features = lib.mkAfter [
|
||||
"gccarch-x86-64-v2"
|
||||
"gccarch-x86-64-v3"
|
||||
@@ -94,7 +91,7 @@ let
|
||||
enable = true;
|
||||
name = "jeeves-nix-builder";
|
||||
url = "http://192.168.99.14:6443/";
|
||||
labels = runnerLabels;
|
||||
labels = containerCfg.labels;
|
||||
tokenFile = "/run/secrets/gitea-runners/registration-token";
|
||||
settings.runner.timeout = "12h";
|
||||
hostPackages = with pkgs; [
|
||||
@@ -109,6 +106,7 @@ let
|
||||
nixfmt
|
||||
nixos-rebuild
|
||||
nodejs
|
||||
ruff
|
||||
treefmt
|
||||
wget
|
||||
];
|
||||
@@ -119,20 +117,21 @@ let
|
||||
User = mkForce runnerUsername;
|
||||
Group = mkForce runnerUsername;
|
||||
ExecStartPre = mkForce [
|
||||
"${getExe registerRunner} builder http://192.168.99.14:6443/ ${runnerConfigFile} ${escapeShellArgs runnerLabels}"
|
||||
"${getExe registerRunner} builder http://192.168.99.14:6443/ ${runnerConfigFile} ${escapeShellArgs containerCfg.labels}"
|
||||
];
|
||||
};
|
||||
};
|
||||
system.stateVersion = "24.05";
|
||||
};
|
||||
sharedContainerPath =
|
||||
mkContainerPath =
|
||||
containerCfg:
|
||||
(import "${pkgs.path}/nixos/lib/eval-config.nix" {
|
||||
modules = [
|
||||
{
|
||||
boot.isNspawnContainer = true;
|
||||
nixpkgs.pkgs = pkgs;
|
||||
}
|
||||
containerConfig
|
||||
(containerConfig containerCfg)
|
||||
];
|
||||
system = null;
|
||||
}).config.system.build.toplevel;
|
||||
@@ -150,7 +149,36 @@ in
|
||||
types.submodule (
|
||||
{ name, ... }:
|
||||
{
|
||||
options.enable = mkEnableOption "Gitea runner container";
|
||||
options = {
|
||||
enable = mkEnableOption "Gitea runner container";
|
||||
|
||||
labels = mkOption {
|
||||
type = types.listOf types.str;
|
||||
default = [
|
||||
"self-hosted:host"
|
||||
"nixos:host"
|
||||
];
|
||||
description = "Gitea Actions labels advertised by this runner.";
|
||||
};
|
||||
|
||||
cores = mkOption {
|
||||
type = types.ints.positive;
|
||||
default = 8;
|
||||
description = "Number of cores made available to each Nix build job.";
|
||||
};
|
||||
|
||||
maxJobs = mkOption {
|
||||
type = types.ints.positive;
|
||||
default = 2;
|
||||
description = "Maximum number of Nix build jobs run in parallel.";
|
||||
};
|
||||
|
||||
cpuQuota = mkOption {
|
||||
type = types.str;
|
||||
default = "800%";
|
||||
description = "systemd CPU quota for the runner container.";
|
||||
};
|
||||
};
|
||||
}
|
||||
)
|
||||
);
|
||||
@@ -172,7 +200,7 @@ in
|
||||
containers = mapAttrs (
|
||||
name: containerCfg:
|
||||
mkIf containerCfg.enable {
|
||||
path = sharedContainerPath;
|
||||
path = mkContainerPath containerCfg;
|
||||
autoStart = true;
|
||||
privateNetwork = true;
|
||||
hostBridge = cfg.bridgeName;
|
||||
@@ -198,16 +226,14 @@ in
|
||||
) cfg.containers;
|
||||
|
||||
systemd = {
|
||||
services = builtins.listToAttrs (
|
||||
map (name: {
|
||||
name = "container@${name}";
|
||||
value = {
|
||||
requires = [ "gitea.service" ];
|
||||
after = [ "gitea.service" ];
|
||||
serviceConfig.CPUQuota = "800%";
|
||||
};
|
||||
}) (builtins.attrNames (filterAttrs (_: c: c.enable) cfg.containers))
|
||||
);
|
||||
services = mapAttrs' (
|
||||
name: containerCfg:
|
||||
nameValuePair "container@${name}" {
|
||||
requires = [ "gitea.service" ];
|
||||
after = [ "gitea.service" ];
|
||||
serviceConfig.CPUQuota = containerCfg.cpuQuota;
|
||||
}
|
||||
) (filterAttrs (_: c: c.enable) cfg.containers);
|
||||
|
||||
tmpfiles.rules = [
|
||||
"d ${vars.uv_cache} 0755 ${runnerUsername} ${runnerUsername} - -"
|
||||
|
||||
@@ -0,0 +1,16 @@
|
||||
{ inputs, ... }:
|
||||
let
|
||||
vars = import ../vars.nix;
|
||||
in
|
||||
{
|
||||
imports = [ inputs.jellyswarrm.nixosModules.default ];
|
||||
|
||||
services.jellyswarrm = {
|
||||
enable = true;
|
||||
host = "0.0.0.0";
|
||||
port = 3100;
|
||||
dataDir = "${vars.services}/jellyswarrm";
|
||||
username = "admin";
|
||||
passwordFile = "${vars.secrets}/services/jellyswarrm-password";
|
||||
};
|
||||
}
|
||||
@@ -9,8 +9,9 @@
|
||||
inputs.disko.nixosModules.disko
|
||||
"${inputs.self}/users/richie"
|
||||
"${inputs.self}/common/global"
|
||||
"${inputs.self}/common/optional/signal-cli.nix"
|
||||
"${inputs.self}/common/optional/tailscale.nix"
|
||||
"${inputs.self}/common/optional/x86-64-v3.nix"
|
||||
"${inputs.self}/common/optional/x86-64-v3"
|
||||
./disk-config.nix
|
||||
./haproxy
|
||||
./monitoring.nix
|
||||
|
||||
@@ -9,7 +9,6 @@
|
||||
"${inputs.self}/common/optional/syncthing_base.nix"
|
||||
"${inputs.self}/common/optional/systemd-boot.nix"
|
||||
"${inputs.self}/common/optional/tailscale.nix"
|
||||
"${inputs.self}/common/optional/x86-64-v3.nix"
|
||||
"${inputs.self}/common/optional/yubikey.nix"
|
||||
"${inputs.self}/common/optional/zfs"
|
||||
./hardware.nix
|
||||
|
||||
+40
-52
@@ -2,80 +2,68 @@
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from os import environ
|
||||
import json
|
||||
import socket
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import httpx
|
||||
import pytest
|
||||
|
||||
from python.signal_alert import signal_alert
|
||||
from python.signal_alert import SignalRPCError, signal_alert
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from pytest_mock import MockerFixture
|
||||
|
||||
|
||||
def test_signal_alert(mocker: MockerFixture) -> None:
|
||||
"""test_signal_alert."""
|
||||
environ["SIGNAL_ALERT_FROM_PHONE"] = "1234567890"
|
||||
environ["SIGNAL_ALERT_TO_PHONE"] = "0987654321"
|
||||
|
||||
mock_logger = mocker.patch("python.signal_alert.logger")
|
||||
mock_response = mocker.MagicMock(spec=httpx.Response, status_code=httpx.codes.CREATED)
|
||||
mock_post = mocker.patch("python.signal_alert.httpx.post", return_value=mock_response)
|
||||
mock_socket = mocker.patch("python.signal_alert.socket.socket")
|
||||
client = mock_socket.return_value.__enter__.return_value
|
||||
client.recv.side_effect = [b'{"jsonrpc":"2.0","result":{},"id":"signal-alert"}\n']
|
||||
|
||||
signal_alert("test")
|
||||
assert signal_alert("test", "1234567890", "0987654321") is None
|
||||
|
||||
mock_logger.info.assert_not_called()
|
||||
mock_post.assert_called_once_with(
|
||||
"http://localhost:8989/v2/send",
|
||||
json={
|
||||
mock_socket.assert_called_once_with(socket.AF_UNIX, socket.SOCK_STREAM)
|
||||
client.settimeout.assert_called_once_with(4.0)
|
||||
client.connect.assert_called_once_with("/run/signal-cli/socket")
|
||||
request = json.loads(client.sendall.call_args.args[0])
|
||||
assert request == {
|
||||
"jsonrpc": "2.0",
|
||||
"method": "send",
|
||||
"params": {
|
||||
"account": "1234567890",
|
||||
"recipient": ["0987654321"],
|
||||
"message": "test",
|
||||
"number": "1234567890",
|
||||
"recipients": ["0987654321"],
|
||||
"text_mode": "normal",
|
||||
},
|
||||
timeout=4.0,
|
||||
follow_redirects=True,
|
||||
)
|
||||
"id": "signal-alert",
|
||||
}
|
||||
|
||||
|
||||
def test_signal_alert_no_phones(mocker: MockerFixture) -> None:
|
||||
"""test_signal_alert_no_phones."""
|
||||
if "SIGNAL_ALERT_FROM_PHONE" in environ:
|
||||
del environ["SIGNAL_ALERT_FROM_PHONE"]
|
||||
if "SIGNAL_ALERT_TO_PHONE" in environ:
|
||||
del environ["SIGNAL_ALERT_TO_PHONE"]
|
||||
mock_logger = mocker.patch("python.signal_alert.logger")
|
||||
signal_alert("test")
|
||||
def test_signal_alert_socket_error(mocker: MockerFixture) -> None:
|
||||
mocker.patch("python.signal_alert.socket.socket", side_effect=ConnectionError("connection failed"))
|
||||
|
||||
mock_logger.info.assert_called_once_with("SIGNAL_ALERT_FROM_PHONE or SIGNAL_ALERT_TO_PHONE not set")
|
||||
with pytest.raises(SignalRPCError, match="Signal RPC failed") as exc_info:
|
||||
signal_alert("test", "1234567890", "0987654321")
|
||||
|
||||
assert isinstance(exc_info.value.__cause__, ConnectionError)
|
||||
|
||||
|
||||
def test_signal_alert_http_error(mocker: MockerFixture) -> None:
|
||||
"""HTTP errors are logged rather than propagated."""
|
||||
environ["SIGNAL_ALERT_FROM_PHONE"] = "1234567890"
|
||||
environ["SIGNAL_ALERT_TO_PHONE"] = "0987654321"
|
||||
def test_signal_alert_rpc_error(mocker: MockerFixture) -> None:
|
||||
mock_socket = mocker.patch("python.signal_alert.socket.socket")
|
||||
client = mock_socket.return_value.__enter__.return_value
|
||||
client.recv.side_effect = [b'{"jsonrpc":"2.0","error":{"code":-1,"message":"failed"},"id":"signal-alert"}\n']
|
||||
|
||||
mock_logger = mocker.patch("python.signal_alert.logger")
|
||||
request = httpx.Request("POST", "http://localhost:8989/v2/send")
|
||||
mocker.patch(
|
||||
"python.signal_alert.httpx.post",
|
||||
side_effect=httpx.ConnectError("connection failed", request=request),
|
||||
)
|
||||
|
||||
signal_alert("test")
|
||||
|
||||
mock_logger.exception.assert_called_once_with("Unable to contact the Signal API")
|
||||
with pytest.raises(SignalRPCError, match=r"Signal RPC returned an error:.*failed"):
|
||||
signal_alert("test", "1234567890", "0987654321")
|
||||
|
||||
|
||||
def test_signal_alert_unsuccessful_response(mocker: MockerFixture) -> None:
|
||||
"""Unexpected response statuses are logged."""
|
||||
environ["SIGNAL_ALERT_FROM_PHONE"] = "1234567890"
|
||||
environ["SIGNAL_ALERT_TO_PHONE"] = "0987654321"
|
||||
def test_signal_alert_ignores_notifications(mocker: MockerFixture) -> None:
|
||||
mock_socket = mocker.patch("python.signal_alert.socket.socket")
|
||||
client = mock_socket.return_value.__enter__.return_value
|
||||
client.recv.side_effect = [
|
||||
b'{"jsonrpc":"2.0","method":"receive"}\n{"jsonrpc":"2.0","result":{},"id":"signal-alert"}\n'
|
||||
]
|
||||
|
||||
mock_logger = mocker.patch("python.signal_alert.logger")
|
||||
mock_response = mocker.MagicMock(spec=httpx.Response, status_code=httpx.codes.BAD_GATEWAY)
|
||||
mocker.patch("python.signal_alert.httpx.post", return_value=mock_response)
|
||||
assert signal_alert("test", "1234567890", "0987654321") is None
|
||||
|
||||
signal_alert("test")
|
||||
|
||||
mock_logger.error.assert_called_once_with("Signal API returned HTTP status %d", httpx.codes.BAD_GATEWAY)
|
||||
assert client.recv.call_count == 1
|
||||
|
||||
@@ -16,6 +16,17 @@ if TYPE_CHECKING:
|
||||
from pytest_mock import MockerFixture
|
||||
|
||||
SNAPSHOT_MANAGER = "python.tools.snapshot_manager"
|
||||
FROM_PHONE = "1234567890"
|
||||
TO_PHONE = "0987654321"
|
||||
|
||||
|
||||
def patch_phone_numbers(mocker: MockerFixture) -> None:
|
||||
"""Patch the Signal phone number environment variables."""
|
||||
phone_numbers = {
|
||||
"SIGNAL_ALERT_FROM_PHONE": FROM_PHONE,
|
||||
"SIGNAL_ALERT_TO_PHONE": TO_PHONE,
|
||||
}
|
||||
mocker.patch(f"{SNAPSHOT_MANAGER}.getenv", side_effect=phone_numbers.get)
|
||||
|
||||
|
||||
def patch_utcnow(mocker: MockerFixture, datetime_value: datetime) -> None:
|
||||
@@ -34,6 +45,7 @@ def create_mock_snapshot(mocker: MockerFixture, name: str) -> Snapshot:
|
||||
def test_main(mocker: MockerFixture, fs: FakeFilesystem) -> None:
|
||||
"""Test main."""
|
||||
load_config_data.cache_clear()
|
||||
patch_phone_numbers(mocker)
|
||||
|
||||
mocker.patch(f"{SNAPSHOT_MANAGER}.get_time_stamp", return_value="2023-01-01T00:00:00")
|
||||
|
||||
@@ -58,12 +70,15 @@ def test_main(mocker: MockerFixture, fs: FakeFilesystem) -> None:
|
||||
"daily": 0,
|
||||
"monthly": 0,
|
||||
},
|
||||
FROM_PHONE,
|
||||
TO_PHONE,
|
||||
)
|
||||
|
||||
|
||||
def test_main_create_snapshot_failure(mocker: MockerFixture, fs: FakeFilesystem) -> None:
|
||||
"""Test main."""
|
||||
load_config_data.cache_clear()
|
||||
patch_phone_numbers(mocker)
|
||||
|
||||
mocker.patch(f"{SNAPSHOT_MANAGER}.get_time_stamp", return_value="2023-01-01T00:00:00")
|
||||
|
||||
@@ -78,7 +93,11 @@ def test_main_create_snapshot_failure(mocker: MockerFixture, fs: FakeFilesystem)
|
||||
fs.create_file("/mock_snapshot_config.toml", contents=mock_snapshot_config_toml)
|
||||
main(Path("/mock_snapshot_config.toml"))
|
||||
|
||||
mock_signal_alert.assert_called_once_with("test_dataset failed to create snapshot 2023-01-01T00:00:00")
|
||||
mock_signal_alert.assert_called_once_with(
|
||||
"test_dataset failed to create snapshot 2023-01-01T00:00:00",
|
||||
FROM_PHONE,
|
||||
TO_PHONE,
|
||||
)
|
||||
mock_get_datasets.assert_called_once()
|
||||
mock_get_snapshots_to_delete.assert_not_called()
|
||||
|
||||
@@ -86,6 +105,7 @@ def test_main_create_snapshot_failure(mocker: MockerFixture, fs: FakeFilesystem)
|
||||
def test_main_exception(mocker: MockerFixture, fs: FakeFilesystem) -> None:
|
||||
"""Test main."""
|
||||
load_config_data.cache_clear()
|
||||
patch_phone_numbers(mocker)
|
||||
|
||||
mocker.patch(f"{SNAPSHOT_MANAGER}.get_time_stamp", return_value="2023-01-01T00:00:00")
|
||||
|
||||
@@ -103,7 +123,7 @@ def test_main_exception(mocker: MockerFixture, fs: FakeFilesystem) -> None:
|
||||
|
||||
assert isinstance(pytest_wrapped_e.value, SystemExit)
|
||||
assert pytest_wrapped_e.value.code == 1
|
||||
mock_signal_alert.assert_called_once_with("snapshot_manager failed")
|
||||
mock_signal_alert.assert_called_once_with("snapshot_manager failed", FROM_PHONE, TO_PHONE)
|
||||
mock_get_datasets.assert_called_once()
|
||||
mock_get_snapshots_to_delete.assert_not_called()
|
||||
|
||||
@@ -120,7 +140,12 @@ def test_get_snapshots_to_delete(mocker: MockerFixture) -> None:
|
||||
|
||||
mock_signal_alert = mocker.patch(f"{SNAPSHOT_MANAGER}.signal_alert")
|
||||
|
||||
get_snapshots_to_delete(mock_dataset, {"15_min": 1, "hourly": 0, "daily": 0, "monthly": 0})
|
||||
get_snapshots_to_delete(
|
||||
mock_dataset,
|
||||
{"15_min": 1, "hourly": 0, "daily": 0, "monthly": 0},
|
||||
FROM_PHONE,
|
||||
TO_PHONE,
|
||||
)
|
||||
|
||||
mock_signal_alert.assert_not_called()
|
||||
mock_dataset.delete_snapshot.assert_called_once_with("auto_202509150415")
|
||||
@@ -135,7 +160,12 @@ def test_get_snapshots_to_delete_no_snapshot(mocker: MockerFixture) -> None:
|
||||
|
||||
mock_signal_alert = mocker.patch(f"{SNAPSHOT_MANAGER}.signal_alert")
|
||||
|
||||
get_snapshots_to_delete(mock_dataset, {"15_min": 1, "hourly": 0, "daily": 0, "monthly": 0})
|
||||
get_snapshots_to_delete(
|
||||
mock_dataset,
|
||||
{"15_min": 1, "hourly": 0, "daily": 0, "monthly": 0},
|
||||
FROM_PHONE,
|
||||
TO_PHONE,
|
||||
)
|
||||
|
||||
mock_signal_alert.assert_not_called()
|
||||
mock_dataset.delete_snapshot.assert_not_called()
|
||||
@@ -153,10 +183,17 @@ def test_get_snapshots_to_delete_errored(mocker: MockerFixture) -> None:
|
||||
|
||||
mock_signal_alert = mocker.patch(f"{SNAPSHOT_MANAGER}.signal_alert")
|
||||
|
||||
get_snapshots_to_delete(mock_dataset, {"15_min": 1, "hourly": 0, "daily": 0, "monthly": 0})
|
||||
get_snapshots_to_delete(
|
||||
mock_dataset,
|
||||
{"15_min": 1, "hourly": 0, "daily": 0, "monthly": 0},
|
||||
FROM_PHONE,
|
||||
TO_PHONE,
|
||||
)
|
||||
|
||||
mock_signal_alert.assert_called_once_with(
|
||||
"test_dataset@auto_202509150415 failed to delete: snapshot has dependent clones"
|
||||
"test_dataset@auto_202509150415 failed to delete: snapshot has dependent clones",
|
||||
FROM_PHONE,
|
||||
TO_PHONE,
|
||||
)
|
||||
mock_dataset.delete_snapshot.assert_called_once_with("auto_202509150415")
|
||||
|
||||
|
||||
@@ -41,6 +41,7 @@ in
|
||||
"ollama"
|
||||
"plugdev"
|
||||
"scanner"
|
||||
"signal-cli"
|
||||
"transmission"
|
||||
"uaccess"
|
||||
"uucp"
|
||||
|
||||
@@ -21,7 +21,6 @@
|
||||
vlc
|
||||
# browser
|
||||
brave
|
||||
chromium
|
||||
# dev tools
|
||||
gparted
|
||||
jetbrains.datagrip
|
||||
|
||||
Reference in New Issue
Block a user