jcoffey-dev
cd8aa290ca
Extends the agent, ingest, storage, api, and web with Windows Event Log/ETW sourcing and Tantivy-backed free-text search, per the approved Phase 1 plan. - CLAUDE.md: materialized on disk (never existed as a file before) with a new Phase 1 "done looks like" section. - agent: Windows Event Log (EvtSubscribe) and ETW sources, Windows service wrapper (install/uninstall/run-service), both feature- and target_os-gated so Linux builds/tests/clippy stay unaffected. Also fixed two pre-existing Phase 0 clippy gaps (dead-code on default-features-only builds, a type-inference edge case) found while testing every feature combination properly for the first time. UNVERIFIED on real Windows -- no Windows toolchain existed anywhere in the build environment; flagged prominently in three places. - proto/ingest: new record_id field, assigned once server-side in ingest's gRPC front end so ClickHouse and Tantivy agree on the same ID for the same record. - storage: record_id column + bloom filter index, verified against a live ClickHouse. - search: new service, Tantivy index, rskafka consumer as an independent second consumer group on the same Redpanda topic ingest already reads. - api/web: new /search endpoint and page, sharing the query page's result-table shape and component. - hack/windows-fixture: sends realistic Windows-shaped data straight to ingest, so the pipeline's handling of it is verifiable without a Windows host. Verified end-to-end on the live docker-compose stack: the same record_id comes back from both /query and /search for the same log line, including for windows-fixture's synthetic Windows Event Log data. Real bugs found and fixed along the way: api/Dockerfile missing proto/ in its build context, search's logs being completely silent (RUST_LOG gap), and search/target/ missing from .gitignore/.dockerignore.
61 lines
1.6 KiB
Go
61 lines
1.6 KiB
Go
// Package clickhousewriter batch-inserts normalized log rows into
|
|
// ClickHouse using the native protocol driver's batch API.
|
|
package clickhousewriter
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
|
|
"github.com/ClickHouse/clickhouse-go/v2"
|
|
"github.com/ClickHouse/clickhouse-go/v2/lib/driver"
|
|
|
|
"github.com/sentry/sentry/ingest/internal/config"
|
|
"github.com/sentry/sentry/ingest/internal/normalize"
|
|
logsv1 "github.com/sentry/sentry/proto/sentry/logs/v1"
|
|
)
|
|
|
|
type Writer struct {
|
|
conn driver.Conn
|
|
}
|
|
|
|
func New(ctx context.Context, cfg config.ClickHouseConfig) (*Writer, error) {
|
|
conn, err := clickhouse.Open(&clickhouse.Options{
|
|
Addr: []string{cfg.Addr},
|
|
Auth: clickhouse.Auth{
|
|
Database: cfg.Database,
|
|
Username: cfg.Username,
|
|
Password: cfg.Password,
|
|
},
|
|
})
|
|
if err != nil {
|
|
return nil, fmt.Errorf("opening clickhouse connection: %w", err)
|
|
}
|
|
if err := conn.Ping(ctx); err != nil {
|
|
return nil, fmt.Errorf("pinging clickhouse: %w", err)
|
|
}
|
|
return &Writer{conn: conn}, nil
|
|
}
|
|
|
|
func (w *Writer) Close() error {
|
|
return w.conn.Close()
|
|
}
|
|
|
|
func (w *Writer) WriteBatch(ctx context.Context, records []*logsv1.LogRecord) error {
|
|
batch, err := w.conn.PrepareBatch(ctx, "INSERT INTO logs (timestamp, host, service, severity, message, attributes, record_id)")
|
|
if err != nil {
|
|
return fmt.Errorf("preparing batch: %w", err)
|
|
}
|
|
|
|
for _, rec := range records {
|
|
row := normalize.ToRow(rec)
|
|
if err := batch.Append(row.Timestamp, row.Host, row.Service, row.Severity, row.Message, row.Attributes, row.RecordID); err != nil {
|
|
return fmt.Errorf("appending row to batch: %w", err)
|
|
}
|
|
}
|
|
|
|
if err := batch.Send(); err != nil {
|
|
return fmt.Errorf("sending batch: %w", err)
|
|
}
|
|
return nil
|
|
}
|