The second half of phase 5. A key now has a cost, a quota and a bill. Rate limits use a sliding window rather than a fixed one. A fixed window lets a caller send its whole minute's allowance in the last second of one window and again in the first second of the next, so the observed rate is twice the configured limit exactly when the system is least able to take it. Checking and charging are one operation, or two concurrent requests both see room and both take it. Token limits are checked against an estimate, because the real count only exists once the request has run; the difference is charged afterwards, so a caller who consistently underestimates is still bounded, one window late. A request with no max_tokens gets a modest assumption rather than zero — assuming zero would let an unbounded request through every token limit. Limits are checked before admission, not after: a request over its quota should be refused rather than queued, where it would occupy a band's capacity to no purpose. All refusals are 429, but a spent budget carries no Retry-After because waiting does not help until the period rolls over, and saying otherwise turns one client into a retry loop. Usage goes to a buffered channel and is written in batches. Record never blocks: if the buffer fills — a database stalled long enough to lose eight thousand records — records are dropped and counted, because losing accounting is bad and turning a stalled database into an outage is worse. A clean shutdown drains what is queued; those are requests that were already served. Failures are logged at error, since silently losing billing data is the kind of thing discovered at the end of a month. Requests are accounted whatever their outcome. A request that used a GPU and then failed still used it, and a key that could spend nothing by failing would be a way around a budget. Budgets are counted in memory and restored from the store at startup, so a restart does not hand every key a fresh allowance. The budget period travels with the reservation rather than being re-derived, because a monthly budget credited to a daily counter is a budget that never binds. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
350 lines
12 KiB
Go
350 lines
12 KiB
Go
// Package config loads llmgw's YAML configuration.
|
|
//
|
|
// Phase 1 only needs the router's half of it: the endpoint list is static here
|
|
// and will come from the control plane in phase 3 (plan §6.4). The shape is
|
|
// already the one the plan describes, so that later change stays additive.
|
|
package config
|
|
|
|
import (
|
|
"fmt"
|
|
"os"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/knadh/koanf/parsers/yaml"
|
|
env "github.com/knadh/koanf/providers/env/v2"
|
|
"github.com/knadh/koanf/providers/file"
|
|
"github.com/knadh/koanf/v2"
|
|
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/control/catalog"
|
|
"gitea.mynodes.xyz/ilker/llmgw/internal/tlsconf"
|
|
)
|
|
|
|
// Server is the whole server configuration.
|
|
type Server struct {
|
|
// Listen is the client-facing OpenAI API address.
|
|
Listen string `koanf:"listen"`
|
|
// AdminListen serves metrics, health and pprof. Kept separate so the
|
|
// client-facing port can be exposed without exposing diagnostics.
|
|
AdminListen string `koanf:"admin_listen"`
|
|
|
|
// AgentListen is where node agents connect. Separate from the client port
|
|
// so the fleet-facing surface can be firewalled independently.
|
|
AgentListen string `koanf:"agent_listen"`
|
|
|
|
// Auth turns on API keys on the client-facing port.
|
|
Auth Auth `koanf:"auth"`
|
|
|
|
// AgentTLS authenticates the fleet-facing port. It deliberately does not
|
|
// cover the client-facing one: that surface is fronted by a publicly
|
|
// trusted certificate, while this one is mutual and private.
|
|
AgentTLS tlsconf.Config `koanf:"agent_tls"`
|
|
|
|
Router Router `koanf:"router"`
|
|
Control Control `koanf:"control"`
|
|
Models []catalog.Model `koanf:"models"`
|
|
|
|
// Endpoints is the phase-1 static replica list. It is only consulted when
|
|
// no model declares a profile, which is what makes a router-only smoke test
|
|
// against sim-engines possible without a control plane.
|
|
Endpoints []Endpoint `koanf:"endpoints"`
|
|
}
|
|
|
|
// Auth configures client authentication (plan §7.9).
|
|
//
|
|
// Off by default, because a gateway on a trusted network with no keys issued
|
|
// still has to serve. Turning it on is what makes the client-facing port safe
|
|
// to expose.
|
|
type Auth struct {
|
|
Enabled bool `koanf:"enabled"`
|
|
// Store is the SQLite file holding keys, tenancy and usage.
|
|
Store string `koanf:"store"`
|
|
// CacheTTL bounds how long a revoked key keeps working, traded against a
|
|
// database read per key per TTL.
|
|
CacheTTL time.Duration `koanf:"cache_ttl"`
|
|
// NegativeTTL is how long a rejected key is remembered as rejected, so a
|
|
// client looping with a bad key cannot become a database read per request.
|
|
NegativeTTL time.Duration `koanf:"negative_ttl"`
|
|
|
|
// Pricing is what each model costs, for budgets. A model absent from the
|
|
// table costs whatever DefaultPrice says, which is nothing unless set.
|
|
Pricing map[string]Price `koanf:"pricing"`
|
|
DefaultPrice Price `koanf:"default_price"`
|
|
|
|
// FlushInterval and BatchSize decide when usage records are written.
|
|
FlushInterval time.Duration `koanf:"flush_interval"`
|
|
BatchSize int `koanf:"batch_size"`
|
|
// BufferSize bounds the queue. Beyond it records are dropped rather than
|
|
// blocking a request: losing accounting is bad, turning a stalled database
|
|
// into an outage is worse.
|
|
BufferSize int `koanf:"buffer_size"`
|
|
}
|
|
|
|
// Price is a model's cost in micro-units per thousand tokens.
|
|
//
|
|
// What a unit means is the operator's choice — self-hosted models have no
|
|
// per-token price, so it may be GPU-seconds, a notional rate, or 1000
|
|
// everywhere, which turns a budget into a token quota (plan §7.9.4).
|
|
type Price struct {
|
|
PromptPer1k int64 `koanf:"prompt_per_1k"`
|
|
CompletionPer1k int64 `koanf:"completion_per_1k"`
|
|
}
|
|
|
|
// Control configures the control plane.
|
|
type Control struct {
|
|
// Interval is how often desired and actual state are compared.
|
|
Interval time.Duration `koanf:"interval"`
|
|
// BaseBackoff and MaxBackoff bound how fast a failing model is retried.
|
|
BaseBackoff time.Duration `koanf:"base_backoff"`
|
|
MaxBackoff time.Duration `koanf:"max_backoff"`
|
|
// UnreachableAfter and LostAfter stage node expiry. They are deliberately
|
|
// far apart: a network blip must not tear down replicas that still serve,
|
|
// and rebuilding a multi-node replica costs tens of minutes of loading.
|
|
UnreachableAfter time.Duration `koanf:"unreachable_after"`
|
|
LostAfter time.Duration `koanf:"lost_after"`
|
|
// PortRange is the per-node range for engine HTTP and dist-init ports.
|
|
PortRange []int `koanf:"port_range"`
|
|
// MgmtInterface is the ethernet interface NCCL bootstraps over.
|
|
MgmtInterface string `koanf:"mgmt_interface"`
|
|
}
|
|
|
|
// Router holds routing behaviour.
|
|
type Router struct {
|
|
ScrapeInterval time.Duration `koanf:"scrape_interval"`
|
|
ScrapeTimeout time.Duration `koanf:"scrape_timeout"`
|
|
// StaleAfter is how long an endpoint may go unscraped before being scored
|
|
// down (plan §7.6).
|
|
StaleAfter time.Duration `koanf:"stale_after"`
|
|
|
|
// Retries is how many *additional* endpoints may be tried after a failure,
|
|
// and only while nothing has been written to the client (plan §7.7).
|
|
Retries int `koanf:"retries"`
|
|
// Cooldown is how long a failing endpoint leaves the candidate pool.
|
|
Cooldown time.Duration `koanf:"cooldown"`
|
|
// FailureThreshold is the consecutive failure count that opens a breaker.
|
|
// 1 turns the breaker into a pure cooldown.
|
|
FailureThreshold int `koanf:"failure_threshold"`
|
|
|
|
// DefaultProfile names the routing profile used when a model picks none.
|
|
DefaultProfile string `koanf:"default_profile"`
|
|
// SessionHeader carries the session id for affinity (plan §7.5 tier 0).
|
|
SessionHeader string `koanf:"session_header"`
|
|
// InjectUsage asks engines for usage even when the client did not, so token
|
|
// accounting works regardless of client behaviour.
|
|
InjectUsage bool `koanf:"inject_usage"`
|
|
|
|
// MaxBodyBytes bounds the request body the router will read.
|
|
MaxBodyBytes int64 `koanf:"max_body_bytes"`
|
|
|
|
Timeouts Timeouts `koanf:"timeouts"`
|
|
Scoring Scoring `koanf:"scoring"`
|
|
Admission Admission `koanf:"admission"`
|
|
}
|
|
|
|
// Admission configures the flow control layer (plan §7.2).
|
|
type Admission struct {
|
|
// Enabled turns the layer on. Off, every request goes straight through,
|
|
// which is the v0.2.0 behaviour.
|
|
Enabled bool `koanf:"enabled"`
|
|
|
|
Bands []Band `koanf:"bands"`
|
|
DefaultBand string `koanf:"default_band"`
|
|
// BandHeader lets a client declare its band. Until authentication lands in
|
|
// v1.0.0 this is trusted, so the port must not be exposed to callers who
|
|
// should not be able to promote themselves.
|
|
BandHeader string `koanf:"band_header"`
|
|
|
|
QueueTTL time.Duration `koanf:"queue_ttl"`
|
|
QueueCapacityPerBand int `koanf:"queue_capacity_per_band"`
|
|
Interval time.Duration `koanf:"interval"`
|
|
}
|
|
|
|
// Band is one priority class.
|
|
type Band struct {
|
|
Name string `koanf:"name"`
|
|
Priority int `koanf:"priority"`
|
|
SaturationCeiling float64 `koanf:"saturation_ceiling"`
|
|
}
|
|
|
|
// Timeouts bounds each phase of an upstream request.
|
|
type Timeouts struct {
|
|
Dial time.Duration `koanf:"dial"`
|
|
ResponseHeader time.Duration `koanf:"response_header"`
|
|
FirstToken time.Duration `koanf:"first_token"`
|
|
Idle time.Duration `koanf:"idle"`
|
|
Total time.Duration `koanf:"total"`
|
|
}
|
|
|
|
// Scoring holds the thresholds the scorers normalize against. These want to be
|
|
// measured with ctl bench (plan §10), not guessed.
|
|
type Scoring struct {
|
|
TargetWaiting float64 `koanf:"target_waiting"`
|
|
TargetInflight float64 `koanf:"target_inflight"`
|
|
KVCeiling float64 `koanf:"kv_ceiling"`
|
|
SessionLoadFactor float64 `koanf:"session_load_factor"`
|
|
}
|
|
|
|
// Endpoint is one engine replica. Static in phase 1.
|
|
type Endpoint struct {
|
|
ID string `koanf:"id"`
|
|
URL string `koanf:"url"`
|
|
Models []string `koanf:"models"`
|
|
// Engine names the inference engine, which decides what its metrics are
|
|
// called. Empty means vLLM's names.
|
|
Engine string `koanf:"engine"`
|
|
Pool string `koanf:"pool"`
|
|
Weight float64 `koanf:"weight"`
|
|
Priority int `koanf:"priority"`
|
|
}
|
|
|
|
// Default returns the configuration used when nothing is specified.
|
|
func Default() Server {
|
|
return Server{
|
|
Listen: ":8080",
|
|
AdminListen: ":9090",
|
|
AgentListen: ":7443",
|
|
Control: Control{
|
|
Interval: 5 * time.Second,
|
|
BaseBackoff: 10 * time.Second,
|
|
MaxBackoff: 10 * time.Minute,
|
|
UnreachableAfter: 15 * time.Second,
|
|
LostAfter: 60 * time.Second,
|
|
PortRange: []int{20000, 20999},
|
|
MgmtInterface: "eth0",
|
|
},
|
|
Router: Router{
|
|
ScrapeInterval: 2 * time.Second,
|
|
ScrapeTimeout: time.Second,
|
|
StaleAfter: 10 * time.Second,
|
|
Retries: 2,
|
|
Cooldown: 15 * time.Second,
|
|
FailureThreshold: 3,
|
|
DefaultProfile: "chat",
|
|
SessionHeader: "x-session-id",
|
|
InjectUsage: true,
|
|
MaxBodyBytes: 32 << 20,
|
|
Timeouts: Timeouts{
|
|
Dial: 5 * time.Second,
|
|
ResponseHeader: 60 * time.Second,
|
|
FirstToken: 120 * time.Second,
|
|
Idle: 60 * time.Second,
|
|
Total: 30 * time.Minute,
|
|
},
|
|
Scoring: Scoring{
|
|
TargetWaiting: 4,
|
|
TargetInflight: 8,
|
|
KVCeiling: 0.9,
|
|
SessionLoadFactor: 1.25,
|
|
},
|
|
Admission: Admission{
|
|
Enabled: true,
|
|
BandHeader: "x-llmgw-band",
|
|
DefaultBand: "gold",
|
|
Bands: []Band{
|
|
{Name: "platinum", Priority: 400, SaturationCeiling: 1.00},
|
|
{Name: "gold", Priority: 300, SaturationCeiling: 0.85},
|
|
{Name: "silver", Priority: 200, SaturationCeiling: 0.60},
|
|
{Name: "bronze", Priority: 100, SaturationCeiling: 0.30},
|
|
},
|
|
QueueTTL: 30 * time.Second,
|
|
QueueCapacityPerBand: 2000,
|
|
Interval: 10 * time.Millisecond,
|
|
},
|
|
},
|
|
}
|
|
}
|
|
|
|
// Load reads configuration from path, overlaying it on the defaults, then
|
|
// applies LLMGW_-prefixed environment overrides.
|
|
//
|
|
// An empty path loads the defaults, which is what makes `llmgw server` with a
|
|
// couple of --endpoint flags usable for a smoke test.
|
|
func Load(path string) (Server, error) {
|
|
cfg := Default()
|
|
k := koanf.New(".")
|
|
|
|
if path != "" {
|
|
if _, err := os.Stat(path); err != nil {
|
|
return cfg, fmt.Errorf("config file: %w", err)
|
|
}
|
|
if err := k.Load(file.Provider(path), yaml.Parser()); err != nil {
|
|
return cfg, fmt.Errorf("parsing %s: %w", path, err)
|
|
}
|
|
}
|
|
|
|
// LLMGW_ROUTER__RETRIES=3 maps onto router.retries.
|
|
err := k.Load(env.Provider(".", env.Opt{
|
|
Prefix: "LLMGW_",
|
|
TransformFunc: func(key, value string) (string, any) {
|
|
key = strings.ToLower(strings.TrimPrefix(key, "LLMGW_"))
|
|
return strings.ReplaceAll(key, "__", "."), value
|
|
},
|
|
}), nil)
|
|
if err != nil {
|
|
return cfg, fmt.Errorf("environment overrides: %w", err)
|
|
}
|
|
|
|
if err := k.UnmarshalWithConf("", &cfg, koanf.UnmarshalConf{Tag: "koanf"}); err != nil {
|
|
return cfg, fmt.Errorf("decoding configuration: %w", err)
|
|
}
|
|
return cfg, cfg.Validate()
|
|
}
|
|
|
|
// Validate rejects configurations that would otherwise fail confusingly at
|
|
// request time.
|
|
func (s Server) Validate() error {
|
|
if s.Listen == "" {
|
|
return fmt.Errorf("listen is empty")
|
|
}
|
|
if err := s.AgentTLS.Validate(); err != nil {
|
|
return err
|
|
}
|
|
if s.Auth.Enabled && s.Auth.Store == "" {
|
|
return fmt.Errorf("auth.store is required when auth is enabled")
|
|
}
|
|
|
|
seen := make(map[string]struct{}, len(s.Endpoints))
|
|
for i, e := range s.Endpoints {
|
|
switch {
|
|
case e.ID == "":
|
|
return fmt.Errorf("endpoints[%d]: id is required", i)
|
|
case e.URL == "":
|
|
return fmt.Errorf("endpoint %q: url is required", e.ID)
|
|
case !strings.HasPrefix(e.URL, "http://") && !strings.HasPrefix(e.URL, "https://"):
|
|
return fmt.Errorf("endpoint %q: url must start with http:// or https://", e.ID)
|
|
case len(e.Models) == 0:
|
|
return fmt.Errorf("endpoint %q: at least one model is required", e.ID)
|
|
}
|
|
if _, dup := seen[e.ID]; dup {
|
|
return fmt.Errorf("endpoint id %q is used twice", e.ID)
|
|
}
|
|
seen[e.ID] = struct{}{}
|
|
}
|
|
|
|
// The catalog enforces the rest — aliases, fallbacks, parallelism
|
|
// arithmetic — so there is one place those rules live.
|
|
if _, err := s.Catalog(); err != nil {
|
|
return err
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// Catalog builds the model catalog from the configuration.
|
|
func (s Server) Catalog() (*catalog.Catalog, error) {
|
|
return catalog.New(s.Models)
|
|
}
|
|
|
|
// ControlPlaneMode reports whether the server should run a control plane.
|
|
//
|
|
// A model with no profiles cannot be placed, so a configuration of bare names
|
|
// plus a static endpoint list is the router-only mode used for testing against
|
|
// sim-engines.
|
|
func (s Server) ControlPlaneMode() bool {
|
|
for _, m := range s.Models {
|
|
if len(m.Profiles) > 0 {
|
|
return true
|
|
}
|
|
}
|
|
return false
|
|
}
|