Fediversity/deployment/check/cli/nixosTest.nix
Nicolas “Niols” Jeannerod ee5c2b90b7 Introduce test for deploying all services with nixops4 apply (#329)
Closes Fediversity/Fediversity#276

This PR adds a CLI deployment test. It builds on top of Fediversity/Fediversity#323. This test features a deployer node and four target nodes. The deployer node runs `nixops4 apply` on a deployment built with our actual code in `deployment/default.nix`, which pushes onto the four target machines combinations of Garage/Mastodon/Peertube/Pixelfed depending on a JSON payload. We check that the expected services are indeed deployed on the machines. Getting there involved reworking the existing basic test to extract common patterns, and adding support for ACME certificates negotiation inside the NixOS test.

What works:
- deployer successfully runs `nixops4 apply` with various payloads
- target machines indeed get the right services pushed onto them and removed
- services on target machines successfully negotiate ACME certificates

What does not work: the services themselves depend a lot on DNS and that is not taken care of at all, so they are probably very broken. Still, this is a good milestone.

Test it yourself by running `nix build .#checks.x86_64-linux.deployment-basic -vL` and `nix build .#checks.x86_64-linux.deployment-cli -vL`. On the very beefy machine that I am using, the basic test runs in ~4 minutes and the CLI test in ~17 minutes. We know from Fediversity/Fediversity#323 that the basic test runs in ~12 minutes on the CI runner, so maybe about an hour for the CLI test?

Co-authored-by: Valentin Gagarin <valentin.gagarin@tweag.io>
Reviewed-on: Fediversity/Fediversity#329
Reviewed-by: kiara Grouwstra <kiara@procolix.eu>
Reviewed-by: Valentin Gagarin <valentin.gagarin@tweag.io>
Co-authored-by: Nicolas “Niols” Jeannerod <nicolas.jeannerod@moduscreate.com>
Co-committed-by: Nicolas “Niols” Jeannerod <nicolas.jeannerod@moduscreate.com>
2025-05-19 02:18:54 +02:00

109 lines
4.2 KiB
Nix

{ inputs, hostPkgs, ... }:
let
## Some places need a dummy file that will in fact never be used. We create
## it here.
dummyFile = hostPkgs.writeText "dummy" "";
in
{
name = "deployment-cli";
nodes.deployer =
{ pkgs, ... }:
{
environment.systemPackages = [
inputs.nixops4.packages.${pkgs.system}.default
];
## FIXME: The following dependencies are necessary but I do not
## understand why they are not covered by the fake node.
system.extraDependencies = with pkgs; [
peertube
peertube.inputDerivation
gixy
gixy.inputDerivation
];
system.extraDependenciesFromModule = {
imports = [ ../../../services/fediversity ];
fediversity = {
domain = "fediversity.net"; # would write `dummy` but that would not type
garage.enable = true;
mastodon = {
enable = true;
s3AccessKeyFile = dummyFile;
s3SecretKeyFile = dummyFile;
};
peertube = {
enable = true;
secretsFile = dummyFile;
s3AccessKeyFile = dummyFile;
s3SecretKeyFile = dummyFile;
};
pixelfed = {
enable = true;
s3AccessKeyFile = dummyFile;
s3SecretKeyFile = dummyFile;
};
temp.cores = 1;
temp.initialUser = {
username = "dummy";
displayName = "dummy";
email = "dummy";
passwordFile = dummyFile;
};
};
};
};
## NOTE: The target machines may need more RAM than the default to handle
## being deployed to, otherwise we get something like:
##
## pixelfed # [ 616.785499 ] sshd-session[1167]: Conection closed by 2001:db8:1::2 port 45004
## deployer # error: writing to file: No space left on device
## pixelfed # [ 616.788538 ] sshd-session[1151]: pam_unix(sshd:session): session closed for user port
## pixelfed # [ 616.793929 ] systemd-logind[719]: Session 4 logged out. Waiting for processes to exit.
## deployer # Error: Could not create resource
##
## These values have been trimmed down to the gigabyte.
nodes.mastodon.virtualisation.memorySize = 4 * 1024;
nodes.pixelfed.virtualisation.memorySize = 4 * 1024;
nodes.peertube.virtualisation.memorySize = 5 * 1024;
## FIXME: The test of presence of the services are very simple: we only
## check that there is a systemd service of the expected name on the
## machine. This proves at least that NixOps4 did something, and we cannot
## really do more for now because the services aren't actually working
## properly, in particular because of DNS issues. We should fix the services
## and check that they are working properly.
extraTestScript = ''
with subtest("Run deployment with no services enabled"):
deployer.succeed("nixops4 apply check-deployment-cli-nothing --show-trace --no-interactive 1>&2")
with subtest("Check the status of the services - there should be none"):
garage.fail("systemctl status garage.service")
mastodon.fail("systemctl status mastodon-web.service")
peertube.fail("systemctl status peertube.service")
pixelfed.fail("systemctl status phpfpm-pixelfed.service")
with subtest("Run deployment with Mastodon and Pixelfed enabled"):
deployer.succeed("nixops4 apply check-deployment-cli-mastodon-pixelfed --show-trace --no-interactive 1>&2")
with subtest("Check the status of the services - expecting Garage, Mastodon and Pixelfed"):
garage.succeed("systemctl status garage.service")
mastodon.succeed("systemctl status mastodon-web.service")
peertube.fail("systemctl status peertube.service")
pixelfed.succeed("systemctl status phpfpm-pixelfed.service")
with subtest("Run deployment with only Peertube enabled"):
deployer.succeed("nixops4 apply check-deployment-cli-peertube --show-trace --no-interactive 1>&2")
with subtest("Check the status of the services - expecting Garage and Peertube"):
garage.succeed("systemctl status garage.service")
mastodon.fail("systemctl status mastodon-web.service")
peertube.succeed("systemctl status peertube.service")
pixelfed.fail("systemctl status phpfpm-pixelfed.service")
'';
}