rpm: make local repodata deterministic (fixes #117) (#118)

Local RPM repos regenerated `repomd.xml` on every request and advertised a `primary.xml.gz` sha256 that drifted every second, because `time.Now().Unix()` was embedded inside the gzipped `primary.xml` (and in `repomd` `<revision>`/`<timestamp>`). The advertised hash therefore never matched the content-addressed `<sha256>-primary.xml.gz` bytes a second later or on the other replica, so `dnf` failed with a checksum mismatch. Part of #117.

How:
- Derives `<time file=>` in `primary.xml` from the persisted `rpm_metadata.created_at` instead of the wall clock; unset timestamps collapse to a fixed `0`.
- Derives `repomd` `<revision>`/`<timestamp>` from the newest package upload time, so `repomd.xml` is byte-identical across replicas and requests.
- Adds `file_path` as a total-order tiebreak to the metadata `ORDER BY`.
- Pins the gzip header (`OS: 255`) so compressed bytes depend only on the payload.
- Adds regression tests: generators are byte-identical across two runs, and the sha256 in `repomd.xml` equals the sha256 of the bytes each `serve*` handler returns.

Reviewed-on: #118
Co-authored-by: unkin-agent <unkin-agent@unkin.net>
Co-committed-by: unkin-agent <unkin-agent@unkin.net>
This commit was merged in pull request #118.
This commit is contained in:
2026-08-12 23:14:51 +10:00
committed by BenVincent
parent 0e26d99228
commit a8aa0c231b
4 changed files with 190 additions and 6 deletions
+7 -2
View File
@@ -3,6 +3,7 @@ package database
import (
"context"
"encoding/json"
"time"
"git.unkin.net/unkin/artifactapi/internal/provider"
)
@@ -65,6 +66,7 @@ type RPMMetadataRow struct {
Obsoletes json.RawMessage
Files json.RawMessage
Changelogs json.RawMessage
CreatedAt time.Time
}
func (db *DB) ListRPMMetadataEntries(ctx context.Context, repoName string) ([]provider.RPMMetadata, error) {
@@ -94,6 +96,7 @@ func (db *DB) ListRPMMetadataEntries(ctx context.Context, repoName string) ([]pr
SourceRPM: r.SourceRPM,
URL: r.URL,
Packager: r.Packager,
CreatedAt: r.CreatedAt,
}
json.Unmarshal(r.Requires, &meta.Requires)
json.Unmarshal(r.Provides, &meta.Provides)
@@ -112,10 +115,11 @@ func (db *DB) ListRPMMetadata(ctx context.Context, repoName string) ([]RPMMetada
name, epoch, version, release, arch,
summary, description, rpm_size, installed_size,
license, vendor, build_group, build_host, source_rpm, url, packager,
requires, provides, conflicts, obsoletes, files, changelogs
requires, provides, conflicts, obsoletes, files, changelogs,
created_at
FROM rpm_metadata
WHERE repo_name = $1
ORDER BY name, epoch, version, release, arch
ORDER BY name, epoch, version, release, arch, file_path
`, repoName)
if err != nil {
return nil, err
@@ -131,6 +135,7 @@ func (db *DB) ListRPMMetadata(ctx context.Context, repoName string) ([]RPMMetada
&r.Summary, &r.Description, &r.RPMSize, &r.InstalledSize,
&r.License, &r.Vendor, &r.Group, &r.BuildHost, &r.SourceRPM, &r.URL, &r.Packager,
&r.Requires, &r.Provides, &r.Conflicts, &r.Obsoletes, &r.Files, &r.Changelogs,
&r.CreatedAt,
); err != nil {
return nil, err
}