Watch
0
0
Fork
You've already forked hyperhive
0

swarm-archive: external s3 backend (options, prune path, docs, module-eval cases, vm fake s3)

- swarm-archive.nix, lib/archive-server.nix: deploy.archive.backend and
  deploy.archive.s3.* options; the s3 server and the prune read the key from the
  store into rclone's environment; the prune lists and addresses repositories
  through rclone instead of a local directory
- swarm-bao.nix: the archive reads swarm/services/archive/s3/*
- docs: archive.md "External S3" section, two credentials-reference rows
- module-eval: builder.nix cases for local and s3, the missing-setting
  assertion; bao-grants.nix gains the s3 read grant
- vm test: second node with a fake rclone serve s3 whose key is generated at
  test time
This commit is contained in:
atlas 2026-11-10 20:47:49 +01:00 • committed by mara
commit 86c5dac89d

View file

@ -23,11 +23,11 @@
# therefore decrypt every backup, which is the cost of pruning where clients
# cannot delete.
#
# Both units log in as the archive's own store principal (a leaf of the store's
# The units log in as the archive's own store principal (a leaf of the store's
# CA, minted by ./glue-bao-tls.nix). Plain host units rather than a container:
# no secret crosses a mount, and the backend is one string
# (`reposDir`, in ./lib/archive-server.nix) that names where the repositories
# are.
# no secret crosses a mount. The backend is one argument (`reposDir` or `s3`, in
# ./lib/archive-server.nix); with `s3` the server also reads the S3 key from
# `swarm/services/archive/s3/…` as it starts and keeps it in rclone's environment.
{
pkgs,
lib,
@ -51,17 +51,40 @@ let
authFile = "${authDir}/htpasswd";
reposDir = "${cfg.dataDir}/repos";
server = import ./lib/archive-server.nix { inherit lib; } {
inherit (cfg) retention;
inherit authFile reposDir;
rclone = cfg.package;
restic = cfg.resticPackage;
addr = "127.0.0.1:${toString cfg.port}";
authGroup = user;
};
useS3 = cfg.backend == "s3";
server = import ./lib/archive-server.nix { inherit lib; } (
{
inherit (cfg) retention;
inherit authFile;
rclone = cfg.package;
restic = cfg.resticPackage;
addr = "127.0.0.1:${toString cfg.port}";
authGroup = user;
}
// (if useS3 then { inherit (cfg) s3; } else { inherit reposDir; })
);
storeRetry = import ./lib/store-retry.nix { };
# A unit that runs as the repositories' owner gets the store identity as
# credentials, which only that user can read.
ownerStoreCredentials = [
"bao-cert:${baoDeploy.archiveClientCertFile}"
"bao-key:${baoDeploy.archiveClientKeyFile}"
]
++ lib.optional (baoDeploy.serverCaFile != null) "bao-ca:${baoDeploy.serverCaFile}";
ownerStoreEnvironment = {
BAO_ADDR = storeEnvironment.BAO_ADDR;
BAO_CLIENT_CERT = "%d/bao-cert";
BAO_CLIENT_KEY = "%d/bao-key";
}
// lib.optionalAttrs (baoDeploy.serverCaFile != null) {
BAO_CACERT = "%d/bao-ca";
};
serveScript = pkgs.writeShellScript "swarm-archive-serve" server.s3ServerScript;
haveClientIdentity =
baoDeploy.archiveClientCertFile != null && baoDeploy.archiveClientKeyFile != null;
@ -101,6 +124,72 @@ in
description = "The restic package the prune unit runs.";
};
backend = lib.mkOption {
type = lib.types.enum [
"local"
"s3"
];
default = "local";
description = ''
Where the repositories are kept: `local` is a directory on this host
({option}`services.hyperhive.deploy.archive.dataDir`), `s3` a bucket of an
external S3 service (`services.hyperhive.deploy.archive.s3.*`).
Hives always talk to this archive, whatever the backend, and never see the
S3 key. The archive reads the key from the secret store, in the leaves
`swarm/services/archive/s3/access-key-id` and `…/secret-access-key`
(field `value`), which you write.
Switching does not move the repositories already stored. Copy them first
(`rclone copy <dataDir>/repos :s3:<bucket>/<prefix>`) or start with
empty repositories.
'';
};
s3 = {
endpoint = lib.mkOption {
type = lib.types.nullOr lib.types.str;
default = null;
example = "https://s3.eu-central-1.amazonaws.com";
description = "URL of the S3 service, scheme included. Required with `backend = \"s3\"`.";
};
bucket = lib.mkOption {
type = lib.types.nullOr (lib.types.strMatching "[A-Za-z0-9._-]+");
default = null;
description = ''
The bucket that holds the repositories. Required with `backend = "s3"`.
It must exist already: the archive creates none.
'';
};
prefix = lib.mkOption {
type = lib.types.strMatching "([A-Za-z0-9._-]+(/[A-Za-z0-9._-]+)*)?";
default = "";
example = "archive";
description = ''
A path in the bucket, without leading or trailing slash. The
repositories sit at `<prefix>/<agent>/`; empty puts them at the top.
'';
};
region = lib.mkOption {
type = lib.types.nullOr lib.types.str;
default = null;
example = "eu-central-1";
description = "The bucket's region, for services that require one. `null` leaves rclone's default.";
};
provider = lib.mkOption {
type = lib.types.str;
default = "Other";
example = "AWS";
description = ''
rclone's `--s3-provider` value, which selects the service's quirks.
`Other` suits a generic S3-compatible service.
'';
};
};
port = lib.mkOption {
type = lib.types.port;
default = 8911;
@ -114,8 +203,8 @@ in
type = lib.types.path;
default = "/var/lib/swarm-archive";
description = ''
Where the repositories live, under `repos/<agent>/`. Holds restic
ciphertext: every backup of every agent, so size it for that.
Where the repositories live with `backend = "local"`, under `repos/<agent>/`.
Holds restic ciphertext: every backup of every agent, so size it for that.
'';
};
@ -172,6 +261,14 @@ in
host's /var/lib/swarm-bao-pki/ and name them in those two options.
'';
}
{
assertion = !useS3 || (cfg.s3.endpoint != null && cfg.s3.bucket != null);
message = ''
services.hyperhive.deploy.archive.backend = "s3" requires both
services.hyperhive.deploy.archive.s3.endpoint and
services.hyperhive.deploy.archive.s3.bucket.
'';
}
];
users.users.${user} = {
@ -212,9 +309,11 @@ in
];
systemd.tmpfiles.rules = [
"d ${authDir} 0750 root ${user} -"
]
++ lib.optionals (!useS3) [
"d ${cfg.dataDir} 0750 ${user} ${user} -"
"d ${reposDir} 0750 ${user} ${user} -"
"d ${authDir} 0750 root ${user} -"
];
systemd.services.swarm-archive = {
@ -227,9 +326,16 @@ in
"systemd-tmpfiles-setup.service"
];
# rclone writes no config, and reads none.
environment.RCLONE_CONFIG = "/dev/null";
environment = {
RCLONE_CONFIG = "/dev/null";
}
// lib.optionalAttrs useS3 (ownerStoreEnvironment // server.environment);
path = lib.optionals useS3 [
baoDeploy.package
pkgs.coreutils
];
serviceConfig = {
ExecStart = server.serverCommand;
ExecStart = if useS3 then serveScript else server.serverCommand;
User = user;
Group = user;
Restart = "on-failure";
@ -246,9 +352,10 @@ in
"AF_INET"
"AF_INET6"
];
ReadWritePaths = [ reposDir ];
ReadOnlyPaths = [ authDir ];
};
}
// lib.optionalAttrs useS3 { LoadCredential = ownerStoreCredentials; }
// lib.optionalAttrs (!useS3) { ReadWritePaths = [ reposDir ]; };
};
# The users file, from the store. A failed run leaves the file as it is;
@ -303,37 +410,30 @@ in
pkgs.coreutils
pkgs.gnugrep
pkgs.jq
];
# The unit runs as the repositories' owner, so the store identity comes
# in as credentials, which only it can read.
environment = {
BAO_ADDR = storeEnvironment.BAO_ADDR;
BAO_CLIENT_CERT = "%d/bao-cert";
BAO_CLIENT_KEY = "%d/bao-key";
RESTIC_CACHE_DIR = "%C/swarm-archive-prune";
}
// lib.optionalAttrs (baoDeploy.serverCaFile != null) {
BAO_CACERT = "%d/bao-ca";
};
]
# restic's rclone backend starts rclone.
++ lib.optional useS3 cfg.package;
environment =
ownerStoreEnvironment
// {
RESTIC_CACHE_DIR = "%C/swarm-archive-prune";
}
// lib.optionalAttrs useS3 ({ RCLONE_CONFIG = "/dev/null"; } // server.environment);
serviceConfig = {
Type = "oneshot";
User = user;
Group = user;
SyslogIdentifier = "swarm-archive-prune";
CacheDirectory = "swarm-archive-prune";
LoadCredential = [
"bao-cert:${baoDeploy.archiveClientCertFile}"
"bao-key:${baoDeploy.archiveClientKeyFile}"
]
++ lib.optional (baoDeploy.serverCaFile != null) "bao-ca:${baoDeploy.serverCaFile}";
LoadCredential = ownerStoreCredentials;
NoNewPrivileges = true;
ProtectSystem = "strict";
ProtectHome = true;
PrivateTmp = true;
PrivateDevices = true;
ReadWritePaths = [ reposDir ];
TimeoutStartSec = "6h";
};
}
// lib.optionalAttrs (!useS3) { ReadWritePaths = [ reposDir ]; };
script = server.pruneScript;
};