Phase G0 Day 3 ships catalogd: Arrow Parquet manifest codec, in-memory registry with the ADR-020 idempotency contract (same name+fingerprint reuses dataset_id; different fingerprint → 409 Conflict), HTTP client to storaged for persistence, and rehydration on startup. Acceptance smoke 6/6 PASSES end-to-end including rehydrate-across-restart — the load-bearing test that the catalog/storaged service split actually preserves state. dataset_id derivation diverges from Rust: UUIDv5(namespace, name) instead of v4 surrogate. Same name on any box generates the same dataset_id; rehydrate after disk loss converges to the same identity rather than silently re-issuing. Namespace pinned at a8f3c1d2-4e5b-5a6c-9d8e-7f0a1b2c3d4e — every dataset_id ever issued depends on these bytes. Cross-lineage scrum on shipped code: - Opus 4.7 (opencode): 1 BLOCK + 5 WARN + 3 INFO - Kimi K2-0905 (openrouter, validated D2): 2 BLOCK + 2 WARN + 1 INFO - Qwen3-coder (openrouter): 2 BLOCK + 2 WARN + 2 INFO Fixed: C1 list-offsets BLOCK (3-way convergent) → ValueOffsets(0) + bounds C2 Rehydrate mutex held across I/O → swap-under-brief-lock pattern S1 split-brain on persist failure → candidate-then-swap S2 brittle string-match for 400 vs 500 → ErrEmptyName/ErrEmptyFingerprint sentinels S3 Get/List shallow-copy aliasing → cloneManifest deep copy S4 keep-alive socket leak on error paths → drainAndClose helper Dismissed (false positives, all single-reviewer): Kimi BLOCK "Decode crashes on empty Parquet" — already handled Kimi INFO "safeKey double-escapes" — wrong, splitting before escape is required Qwen INFO "rb.NewRecord() error unchecked" — API returns no error Deferred to G1+: name validation regex, per-call deadlines, Snappy compression, list pagination continuation tokens (storaged caps at 10k with sentinel for now). Build clean, vet clean, all tests pass, smoke 6/6 PASS after every fix round. arrow-go/v18 + google/uuid added; Go 1.24 → 1.25 forced by arrow-go's minimum. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
110 lines
3.6 KiB
Go
110 lines
3.6 KiB
Go
// Package shared also provides the TOML config loader. Per ADR
|
|
// equivalent of Rust ADR-006 (TOML config over env vars), every
|
|
// service reads `lakehouse.toml` with sane defaults and env
|
|
// overrides. Config is hot-reload-unaware in G0; reload-on-SIGHUP
|
|
// is a G1+ concern.
|
|
package shared
|
|
|
|
import (
|
|
"errors"
|
|
"fmt"
|
|
"io/fs"
|
|
"log/slog"
|
|
"os"
|
|
|
|
"github.com/pelletier/go-toml/v2"
|
|
)
|
|
|
|
// Config is the unified Lakehouse config. Each service reads only
|
|
// the section it cares about, but they all share the same file so
|
|
// operators have one place to look.
|
|
type Config struct {
|
|
Gateway ServiceConfig `toml:"gateway"`
|
|
Storaged ServiceConfig `toml:"storaged"`
|
|
Catalogd CatalogConfig `toml:"catalogd"`
|
|
Ingestd ServiceConfig `toml:"ingestd"`
|
|
Queryd ServiceConfig `toml:"queryd"`
|
|
S3 S3Config `toml:"s3"`
|
|
Log LogConfig `toml:"log"`
|
|
}
|
|
|
|
// CatalogConfig adds catalogd-specific knobs on top of the standard
|
|
// bind. StoragedURL points at the storaged service for manifest
|
|
// persistence; G0 defaults to the localhost bind.
|
|
type CatalogConfig struct {
|
|
Bind string `toml:"bind"`
|
|
StoragedURL string `toml:"storaged_url"`
|
|
}
|
|
|
|
// ServiceConfig is the per-binary bind config. Default Bind ""
|
|
// means "use the service's hardcoded G0 default" — see DefaultConfig.
|
|
type ServiceConfig struct {
|
|
Bind string `toml:"bind"`
|
|
}
|
|
|
|
// S3Config holds S3-compatible storage settings. Endpoint blank →
|
|
// AWS default. Bucket "" → "lakehouse-primary".
|
|
type S3Config struct {
|
|
Endpoint string `toml:"endpoint"`
|
|
Region string `toml:"region"`
|
|
Bucket string `toml:"bucket"`
|
|
AccessKeyID string `toml:"access_key_id"`
|
|
SecretAccessKey string `toml:"secret_access_key"`
|
|
UsePathStyle bool `toml:"use_path_style"`
|
|
}
|
|
|
|
// LogConfig — slog level for now; structured fields land G1+.
|
|
type LogConfig struct {
|
|
Level string `toml:"level"`
|
|
}
|
|
|
|
// DefaultConfig returns the G0 dev defaults. Ports are shifted to
|
|
// 3110+ to coexist with the live Rust lakehouse on 3100/3201-3204
|
|
// during the migration. G5 cutover flips gateway back to 3100.
|
|
func DefaultConfig() Config {
|
|
return Config{
|
|
Gateway: ServiceConfig{Bind: "127.0.0.1:3110"},
|
|
Storaged: ServiceConfig{Bind: "127.0.0.1:3211"},
|
|
Catalogd: CatalogConfig{Bind: "127.0.0.1:3212", StoragedURL: "http://127.0.0.1:3211"},
|
|
Ingestd: ServiceConfig{Bind: "127.0.0.1:3213"},
|
|
Queryd: ServiceConfig{Bind: "127.0.0.1:3214"},
|
|
S3: S3Config{
|
|
Endpoint: "http://localhost:9000",
|
|
Region: "us-east-1",
|
|
Bucket: "lakehouse-primary",
|
|
UsePathStyle: true,
|
|
},
|
|
Log: LogConfig{Level: "info"},
|
|
}
|
|
}
|
|
|
|
// LoadConfig reads `lakehouse.toml` from path; if path is empty or
|
|
// the file doesn't exist, returns DefaultConfig. Any decode error is
|
|
// fatal (we don't want a misconfigured service silently falling back
|
|
// to defaults — that's the kind of bug you find at 2am).
|
|
//
|
|
// Per Opus + Qwen WARN #3: when path WAS given but the file is
|
|
// missing, log a warning so silent default-fallback doesn't hide
|
|
// misconfiguration. Empty path is fine (caller didn't ask for a
|
|
// file); non-empty + missing is suspicious.
|
|
func LoadConfig(path string) (Config, error) {
|
|
cfg := DefaultConfig()
|
|
if path == "" {
|
|
return cfg, nil
|
|
}
|
|
b, err := os.ReadFile(path)
|
|
if errors.Is(err, fs.ErrNotExist) {
|
|
slog.Warn("config file not found, using defaults",
|
|
"path", path,
|
|
"hint", "create the file or pass -config /path/to/lakehouse.toml")
|
|
return cfg, nil
|
|
}
|
|
if err != nil {
|
|
return cfg, fmt.Errorf("read config: %w", err)
|
|
}
|
|
if err := toml.Unmarshal(b, &cfg); err != nil {
|
|
return cfg, fmt.Errorf("parse config: %w", err)
|
|
}
|
|
return cfg, nil
|
|
}
|