f1820fd104
## Why
OS package remotes (rpm/deb/apk) fetch many small files and benefit from spreading upstream load across mirrors and surviving a mirror outage. A remote may now set a **`mirrorlist`** of additional upstream base URLs. The effective upstream pool is **`[base_url] + mirrorlist`**, which the shared proxy engine load-balances **round-robin** and, on a network error/timeout/5xx, **fails over** to the next mirror before returning an error. Selection happens in the engine, so it works for every provider that reaches upstream.
**Backward compatible:** `base_url` stays a plain string (providers read it unchanged), and a remote with **no mirrorlist behaves exactly as today** (single attempt, same error path).
## How
- `models.Remote.Mirrorlist` (`[]string`, `json:"mirrorlist,omitempty"`) + `UpstreamPool()` = `[base_url] + mirrorlist`.
- `ValidateMirrorlist`: a non-empty mirrorlist is allowed **only** when `repo_type==remote` **and** `package_type ∈ {rpm, deb, alpine}`; each entry must be an http/https URL. Enforced in the v2 create/update handlers (400 otherwise); `base_url` stays required for remotes.
- Persist the mirrorlist in a new additive `mirrorlist TEXT[]` column (`remoteCols`/`scanRemote`/`CreateRemote`/`UpdateRemote`); the `base_url` column is unchanged.
- Engine keeps a per-remote round-robin cursor over the pool; the fetch/head/revalidate upstream calls run in a failover loop that narrows the remote to one selected mirror per attempt. Only network errors and 5xx fail over (404/403/… return as-is). The circuit breaker stays keyed per remote and trips only after all mirrors fail.
## Scope
Round-robin + failover only, restricted to **remote rpm/deb/apk** repos. Least-connections and a per-remote strategy selector are a **follow-up PR**.
## Tests
- Unit: model JSON round-trip + validation gating (rejected on non-rpm/deb/apk and on local, accepted on rpm/deb/apk, bad URL rejected), engine round-robin/failover/no-mirrorlist-unchanged, DB mirrorlist round-trip. `make test` (`go test -race`) green.
- Docker acceptance (`e2e-docker`, `dockere2e` tag, wired into `docker-e2e.sh`): round-robin distribution across two mock upstreams, failover past a dead primary, no-mirrorlist regression, and a **real `dnf` makecache + install** through a two-mirror rpm remote whose `base_url` is dead. All four pass locally.
Reviewed-on: #121
Co-authored-by: unkin-agent <unkin-agent@unkin.net>
Co-committed-by: unkin-agent <unkin-agent@unkin.net>
153 lines
4.6 KiB
Go
153 lines
4.6 KiB
Go
package models
|
|
|
|
import (
|
|
"fmt"
|
|
"net/url"
|
|
"regexp"
|
|
"time"
|
|
)
|
|
|
|
type RepoType string
|
|
|
|
const (
|
|
RepoTypeRemote RepoType = "remote"
|
|
RepoTypeLocal RepoType = "local"
|
|
)
|
|
|
|
var validRepoTypes = map[RepoType]bool{
|
|
RepoTypeRemote: true,
|
|
RepoTypeLocal: true,
|
|
}
|
|
|
|
func (r RepoType) Valid() bool {
|
|
return validRepoTypes[r]
|
|
}
|
|
|
|
func (r RepoType) String() string {
|
|
return string(r)
|
|
}
|
|
|
|
func ParseRepoType(s string) (RepoType, error) {
|
|
rt := RepoType(s)
|
|
if !rt.Valid() {
|
|
return "", fmt.Errorf("unknown repo type: %q", s)
|
|
}
|
|
return rt, nil
|
|
}
|
|
|
|
type Remote struct {
|
|
Name string `json:"name"`
|
|
PackageType PackageType `json:"package_type"`
|
|
RepoType RepoType `json:"repo_type"`
|
|
BaseURL string `json:"base_url"`
|
|
// Mirrorlist holds additional upstream mirror base URLs. The effective
|
|
// upstream pool is [base_url] + mirrorlist, load-balanced round-robin with
|
|
// failover by the proxy engine. Only valid on remote rpm/deb/apk repos.
|
|
Mirrorlist []string `json:"mirrorlist,omitempty"`
|
|
Description string `json:"description,omitempty"`
|
|
Username string `json:"-"`
|
|
Password string `json:"-"`
|
|
|
|
ImmutableTTL int `json:"immutable_ttl"`
|
|
MutableTTL int `json:"mutable_ttl"`
|
|
CheckMutable bool `json:"check_mutable"`
|
|
|
|
// Upstream HTTP timeouts in seconds. 0 means use the server default.
|
|
UpstreamDialTimeout int `json:"upstream_dial_timeout,omitempty"`
|
|
UpstreamTLSTimeout int `json:"upstream_tls_timeout,omitempty"`
|
|
UpstreamResponseHeaderTimeout int `json:"upstream_response_header_timeout,omitempty"`
|
|
|
|
Patterns []string `json:"patterns,omitempty"`
|
|
Blocklist []string `json:"blocklist,omitempty"`
|
|
MutablePatterns []string `json:"mutable_patterns,omitempty"`
|
|
ImmutablePatterns []string `json:"immutable_patterns,omitempty"`
|
|
|
|
BanTagsEnabled bool `json:"ban_tags_enabled,omitempty"`
|
|
BanTags []string `json:"ban_tags,omitempty"`
|
|
|
|
QuarantineEnabled bool `json:"quarantine_enabled,omitempty"`
|
|
QuarantineDays int `json:"quarantine_days,omitempty"`
|
|
|
|
StaleOnError bool `json:"stale_on_error"`
|
|
|
|
ReleasesRemote string `json:"releases_remote,omitempty"`
|
|
ManagedBy string `json:"managed_by,omitempty"`
|
|
|
|
CreatedAt time.Time `json:"created_at"`
|
|
UpdatedAt time.Time `json:"updated_at"`
|
|
}
|
|
|
|
// mirrorlistPackageTypes are the package types for which a mirrorlist is
|
|
// allowed: OS package repos (rpm, deb, apk/alpine) that fetch many small files
|
|
// and benefit most from mirror load-balancing and failover.
|
|
var mirrorlistPackageTypes = map[PackageType]bool{
|
|
PackageRPM: true,
|
|
PackageDeb: true,
|
|
PackageAlpine: true,
|
|
}
|
|
|
|
// UpstreamPool returns the ordered upstream base URLs for this remote: the
|
|
// primary base_url first, followed by any mirrorlist entries. The proxy engine
|
|
// load-balances round-robin across the pool and fails over between them.
|
|
func (r Remote) UpstreamPool() []string {
|
|
pool := make([]string, 0, 1+len(r.Mirrorlist))
|
|
if r.BaseURL != "" {
|
|
pool = append(pool, r.BaseURL)
|
|
}
|
|
pool = append(pool, r.Mirrorlist...)
|
|
return pool
|
|
}
|
|
|
|
// ValidateMirrorlist enforces that a mirrorlist is only configured on remote
|
|
// rpm/deb/apk repositories and that every entry is a parseable http/https URL.
|
|
func (r *Remote) ValidateMirrorlist() error {
|
|
if len(r.Mirrorlist) == 0 {
|
|
return nil
|
|
}
|
|
if r.RepoType != RepoTypeRemote {
|
|
return fmt.Errorf("mirrorlist is only allowed on remote repositories")
|
|
}
|
|
if !mirrorlistPackageTypes[r.PackageType] {
|
|
return fmt.Errorf("mirrorlist is only allowed for rpm, deb and alpine package types, not %q", r.PackageType)
|
|
}
|
|
for _, u := range r.Mirrorlist {
|
|
parsed, err := url.ParseRequestURI(u)
|
|
if err != nil {
|
|
return fmt.Errorf("invalid mirrorlist url %q: %w", u, err)
|
|
}
|
|
if parsed.Scheme != "http" && parsed.Scheme != "https" {
|
|
return fmt.Errorf("mirrorlist url %q must be http or https", u)
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// ValidatePatterns ensures every configured regex compiles. Storing an
|
|
// invalid pattern would otherwise be silently dropped at match time, which
|
|
// for the blocklist is a fail-open: a mistyped deny rule becomes a no-op.
|
|
func (r *Remote) ValidatePatterns() error {
|
|
groups := []struct {
|
|
field string
|
|
patterns []string
|
|
}{
|
|
{"patterns", r.Patterns},
|
|
{"blocklist", r.Blocklist},
|
|
{"mutable_patterns", r.MutablePatterns},
|
|
{"immutable_patterns", r.ImmutablePatterns},
|
|
{"ban_tags", r.BanTags},
|
|
}
|
|
for _, g := range groups {
|
|
for _, p := range g.patterns {
|
|
if _, err := regexp.Compile(p); err != nil {
|
|
return fmt.Errorf("invalid regex in %s: %q: %w", g.field, p, err)
|
|
}
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
type RemoteWithStats struct {
|
|
Remote
|
|
Stats RemoteStats `json:"stats"`
|
|
}
|