push ci run metrics to victoriametrics, with a grafana board
A swarm-ci-metrics host unit on a 5-minute timer lists every forge repo's Actions runs as the new read-only ci-metrics account and pushes each finished run's duration and queue wait over OTLP, stamped at the run's stop time. The first pass backfills from run 1. swarm-controller mints the account's token into bao and keeps a ci-metrics team with read on the Actions unit in every organisation. Closes #5376
This commit is contained in:
parent
8b7a4e7955
commit
b072fbf4d6
36 changed files with 2849 additions and 56 deletions
|
|
@ -449,6 +449,10 @@ let
|
|||
capabilities = ["create", "read", "update"]
|
||||
}
|
||||
|
||||
path "${credentialMountPath}/data/${ciMetricsForgeTokenLeaf}" {
|
||||
capabilities = ["create", "read", "update"]
|
||||
}
|
||||
|
||||
path "${credentialMountPath}/data/${swarmAppserviceTokenLeaf}" {
|
||||
capabilities = ["read"]
|
||||
}
|
||||
|
|
@ -504,8 +508,8 @@ let
|
|||
# The review classifier's forge token is denied too: the controller posts
|
||||
# the classifier's reviews with whatever token is there, so a write to it
|
||||
# picks the account those reviews come from.
|
||||
# So is the builder's: a write to it picks the account the builder fetches
|
||||
# config repos as.
|
||||
# So are the builder's and the CI run poller's: a write to either picks the
|
||||
# account that service reads the forge as.
|
||||
secretPublisherPolicyText = ''
|
||||
path "${credentialMountPath}/data/swarm/hives/*" {
|
||||
capabilities = ["create", "update"]
|
||||
|
|
@ -539,6 +543,10 @@ let
|
|||
capabilities = ["deny"]
|
||||
}
|
||||
|
||||
path "${credentialMountPath}/data/${ciMetricsForgeTokenLeaf}" {
|
||||
capabilities = ["deny"]
|
||||
}
|
||||
|
||||
path "${credentialMountPath}/data/${controllerClientLeaf}" {
|
||||
capabilities = ["create", "update"]
|
||||
}
|
||||
|
|
@ -620,6 +628,12 @@ let
|
|||
# to fetch config repos.
|
||||
builderForgeTokenLeaf = "swarm/services/builder/forge/token";
|
||||
|
||||
# The CI run poller's forge token, the nix half of
|
||||
# `swarm_secret_client::ci_metrics::forge_token_path`. The controller mints it
|
||||
# and reads it back before deciding whether to re-mint; the poller reads it
|
||||
# to list runs.
|
||||
ciMetricsForgeTokenLeaf = "swarm/services/ci-metrics/forge/token";
|
||||
|
||||
# The review classifier's ACP provider key, the nix half of
|
||||
# `swarm_secret_client::review_classifier::acp_provider_key_path`. Written
|
||||
# and read like the API key above.
|
||||
|
|
@ -1095,6 +1109,18 @@ let
|
|||
}
|
||||
];
|
||||
|
||||
# The CI run poller: its forge token and its own OIDC client secret, both
|
||||
# read once per pass by the host unit.
|
||||
ciMetricsReaders = [
|
||||
{
|
||||
name = "swarm-ci-metrics";
|
||||
cn = baoDeploy.ciMetricsCommonName;
|
||||
policyText =
|
||||
readStanza "${credentialMountPath}/data/${ciMetricsForgeTokenLeaf}"
|
||||
+ readStanza "${credentialMountPath}/data/swarm/services/${hyperhiveCfg.swarm.ci-metrics.clientId}/oidc/client";
|
||||
}
|
||||
];
|
||||
|
||||
# The claude login minter: every agent's `claude-credentials` leaf,
|
||||
# create and update so a relogin replaces the last, and nothing else under
|
||||
# an agent; and its own queue client secret, read at start.
|
||||
|
|
@ -2003,6 +2029,19 @@ in
|
|||
'';
|
||||
};
|
||||
|
||||
ciMetricsCommonName = lib.mkOption {
|
||||
type = lib.types.str;
|
||||
default = "swarm-ci-metrics";
|
||||
description = ''
|
||||
Subject the store's `swarm-ci-metrics` cert-auth role accepts: the
|
||||
identity the CI run poller presents from its host unit. Its grant is
|
||||
two paths, read only: `swarm/services/ci-metrics/forge/token` and its
|
||||
own OIDC client secret.
|
||||
|
||||
⚠️ Reserved as a hive name by ./swarm.nix, like its siblings.
|
||||
'';
|
||||
};
|
||||
|
||||
claudeLoginCommonName = lib.mkOption {
|
||||
type = lib.types.str;
|
||||
default = "swarm-claude-login";
|
||||
|
|
@ -2318,6 +2357,31 @@ in
|
|||
'';
|
||||
};
|
||||
|
||||
ciMetricsClientCertFile = lib.mkOption {
|
||||
type = lib.types.nullOr lib.types.str;
|
||||
default = null;
|
||||
example = "/var/lib/swarm-bao-pki/ci-metrics.pem";
|
||||
description = ''
|
||||
Certificate the CI run poller presents to the store. Its subject must
|
||||
be {option}`services.hyperhive.deploy.bao.ciMetricsCommonName`.
|
||||
|
||||
./glue-bao-tls.nix points it at the leaf it mints on the store's host.
|
||||
On a poller host without the store, it is a file the operator copies
|
||||
from the store's host. A path, never a value.
|
||||
'';
|
||||
};
|
||||
|
||||
ciMetricsClientKeyFile = lib.mkOption {
|
||||
type = lib.types.nullOr lib.types.str;
|
||||
default = null;
|
||||
example = "/var/lib/swarm-bao-pki/ci-metrics-key.pem";
|
||||
description = ''
|
||||
Private key for
|
||||
{option}`services.hyperhive.deploy.bao.ciMetricsClientCertFile`.
|
||||
A path, never a value.
|
||||
'';
|
||||
};
|
||||
|
||||
claudeLoginClientCertFile = lib.mkOption {
|
||||
type = lib.types.nullOr lib.types.str;
|
||||
default = null;
|
||||
|
|
@ -3435,6 +3499,8 @@ in
|
|||
|
||||
systemd.services.swarm-bao-builder-policy = readerPolicyUnit "write the swarm builder's forge-token-reader bao policy and cert-auth role" builderReaders;
|
||||
|
||||
systemd.services.swarm-bao-ci-metrics-policy = readerPolicyUnit "write the CI run poller's forge-token-reader bao policy and cert-auth role" ciMetricsReaders;
|
||||
|
||||
systemd.services.swarm-bao-claude-login-policy = readerPolicyUnit "write the claude login minter's credentials-writer bao policy and cert-auth role" claudeLoginWriters;
|
||||
|
||||
systemd.services.swarm-bao-forge-publisher-policy = readerPolicyUnit "write the forge's controller-token-publisher bao policy and cert-auth role" forgePublisherWriters;
|
||||
|
|
|
|||
Loading…
Reference in a new issue