Files
cairnobs/ingest/consumer/consumer_test.go
T
jcoffey-dev 1de77b969f Build per-tenant ClickHouse write-routing for ingest (Tantivy still deferred)
ingest tags every record with a tenant_id Kafka header (built previously),
but nothing consumed it to actually route the write. This closes that for
ClickHouse: enterprise/cmd/enterprise-ingest (a second binary, mirroring
enterprise-api) reuses ingest/consumer's own flush loop unchanged, with
enterprise/internal/chwriter.Registry -- a per-tenant clickhousewriter.Writer
registry -- swapped in as the writer. A batch pulled from the single shared
Redpanda topic can mix records from many tenants, so WriteBatch groups by
TenantID and dispatches each group to its own tenant's connection, fail-
closed on an empty or unrecognized tenant_id.

ingest/consumer and ingest/clickhousewriter move out of internal/ (same
reason api/internal/* moved earlier this phase: enterprise/ can't import
anything under another module's internal/). Their New() constructors now
take small local Config structs instead of ingest/internal/config types,
so enterprise/ doesn't need that import either.

Building this surfaced a real bug: tenantprovision.ProvisionClickHouse
only granted SELECT on a tenant's ClickHouse user, correct for chrunner's
read-only use but not enough for chwriter reusing the same credential to
write -- every real per-tenant write would have failed closed with a
permission error. Fixed by widening the grant to SELECT, INSERT; no
cross-tenant boundary is crossed by also allowing INSERT within a
tenant's own database.

Helm gates enterprise-ingest's Deployment on the same
ingest.requireTenantCredential flag that already gates tag validation --
write-routing is meaningless without tagging already being required, so
they're one decision, not two. docker-compose.yml's version is a
disclosed, weaker approximation: it can't achieve Helm's genuine
-mode=server/-mode=consumer split, so with the enterprise profile active
both ingest and enterprise-ingest independently consume every message
via different consumer groups -- harmless duplication for local
verification only.

Not built: Tantivy's independent Redpanda consumer (search/src/consumer.rs)
still doesn't read the tenant_id header at all -- every record still lands
in the one shared index regardless of tenant. Not run: the live-ClickHouse-
gated tests (chwriter's cross-tenant routing test, tenantprovision's INSERT
regression test) -- no Docker/database access in this environment; they're
correct Go that has never executed, disclosed as such in docs/security/
threat-model.md and docs/phase-4-runbook.md §14.
2026-08-14 19:26:09 -07:00

215 lines
5.6 KiB
Go

package consumer
import (
"context"
"errors"
"io"
"log/slog"
"sync"
"testing"
"time"
"github.com/segmentio/kafka-go"
"google.golang.org/protobuf/proto"
logsv1 "github.com/sentry/sentry/proto/sentry/logs/v1"
)
type fakeReader struct {
msgs chan kafka.Message
mu sync.Mutex
committed [][]kafka.Message
}
func newFakeReader() *fakeReader {
return &fakeReader{msgs: make(chan kafka.Message, 16)}
}
func (f *fakeReader) push(m kafka.Message) { f.msgs <- m }
func (f *fakeReader) FetchMessage(ctx context.Context) (kafka.Message, error) {
select {
case m := <-f.msgs:
return m, nil
case <-ctx.Done():
return kafka.Message{}, ctx.Err()
}
}
func (f *fakeReader) CommitMessages(_ context.Context, msgs ...kafka.Message) error {
f.mu.Lock()
defer f.mu.Unlock()
f.committed = append(f.committed, msgs)
return nil
}
func (f *fakeReader) Close() error { return nil }
func (f *fakeReader) commitCount() int {
f.mu.Lock()
defer f.mu.Unlock()
return len(f.committed)
}
type fakeWriter struct {
mu sync.Mutex
batches [][]Record
failNext bool
}
func (f *fakeWriter) WriteBatch(_ context.Context, records []Record) error {
f.mu.Lock()
defer f.mu.Unlock()
if f.failNext {
f.failNext = false
return errors.New("simulated clickhouse failure")
}
batch := make([]Record, len(records))
copy(batch, records)
f.batches = append(f.batches, batch)
return nil
}
func (f *fakeWriter) batchCount() int {
f.mu.Lock()
defer f.mu.Unlock()
return len(f.batches)
}
func newTestConsumer(r reader, w chWriter, cfg Config) *Consumer {
return &Consumer{
logger: slog.New(slog.NewTextHandler(io.Discard, nil)),
reader: r,
writer: w,
cfg: cfg,
}
}
func mustMarshal(t *testing.T, rec *logsv1.LogRecord) []byte {
t.Helper()
b, err := proto.Marshal(rec)
if err != nil {
t.Fatalf("marshal: %v", err)
}
return b
}
func waitFor(t *testing.T, timeout time.Duration, cond func() bool) {
t.Helper()
deadline := time.Now().Add(timeout)
for time.Now().Before(deadline) {
if cond() {
return
}
time.Sleep(5 * time.Millisecond)
}
t.Fatal("condition not met before timeout")
}
func TestConsumerFlushesOnBatchSize(t *testing.T) {
fr := newFakeReader()
fw := &fakeWriter{}
c := newTestConsumer(fr, fw, Config{BatchMaxSize: 2, FlushIntervalMS: 60_000})
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
done := make(chan error, 1)
go func() { done <- c.Run(ctx) }()
fr.push(kafka.Message{Value: mustMarshal(t, &logsv1.LogRecord{Message: "a"})})
fr.push(kafka.Message{Value: mustMarshal(t, &logsv1.LogRecord{Message: "b"})})
waitFor(t, time.Second, func() bool { return fw.batchCount() == 1 })
fw.mu.Lock()
if len(fw.batches[0]) != 2 {
t.Fatalf("expected batch of 2 records, got %d", len(fw.batches[0]))
}
fw.mu.Unlock()
waitFor(t, time.Second, func() bool { return fr.commitCount() == 1 })
}
func TestConsumerFlushesOnTimeout(t *testing.T) {
fr := newFakeReader()
fw := &fakeWriter{}
c := newTestConsumer(fr, fw, Config{BatchMaxSize: 1000, FlushIntervalMS: 20})
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
done := make(chan error, 1)
go func() { done <- c.Run(ctx) }()
fr.push(kafka.Message{Value: mustMarshal(t, &logsv1.LogRecord{Message: "only-one"})})
waitFor(t, time.Second, func() bool { return fw.batchCount() == 1 })
fw.mu.Lock()
if len(fw.batches[0]) != 1 {
t.Fatalf("expected batch of 1 record, got %d", len(fw.batches[0]))
}
fw.mu.Unlock()
}
func TestConsumerDoesNotCommitOnWriteFailure(t *testing.T) {
fr := newFakeReader()
fw := &fakeWriter{failNext: true}
c := newTestConsumer(fr, fw, Config{BatchMaxSize: 1, FlushIntervalMS: 60_000})
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
done := make(chan error, 1)
go func() { done <- c.Run(ctx) }()
fr.push(kafka.Message{Value: mustMarshal(t, &logsv1.LogRecord{Message: "will-fail"})})
// Give the flush a moment to run and fail.
time.Sleep(100 * time.Millisecond)
if got := fr.commitCount(); got != 0 {
t.Fatalf("expected no commits after a failed clickhouse write, got %d", got)
}
// The batch was attempted even though writer returned an error.
if fw.batchCount() != 0 {
t.Fatalf("fakeWriter should not record a failed batch, got %d recorded", fw.batchCount())
}
}
// TestConsumerExtractsTenantIDFromHeader is the read-side half of the
// producer/consumer tenant_id contract -- ingest/internal/grpcserver
// attaches this header on the way in; this proves the consumer reads it
// back correctly (and that a message with no header at all -- the
// single-tenant/no-resolver case -- gets an empty TenantID, not an
// error).
func TestConsumerExtractsTenantIDFromHeader(t *testing.T) {
fr := newFakeReader()
fw := &fakeWriter{}
c := newTestConsumer(fr, fw, Config{BatchMaxSize: 2, FlushIntervalMS: 60_000})
ctx, cancel := context.WithCancel(context.Background())
defer cancel()
go func() { _ = c.Run(ctx) }()
fr.push(kafka.Message{
Value: mustMarshal(t, &logsv1.LogRecord{Message: "tagged"}),
Headers: []kafka.Header{{Key: TenantIDHeaderKey, Value: []byte("acme")}},
})
fr.push(kafka.Message{Value: mustMarshal(t, &logsv1.LogRecord{Message: "untagged"})})
waitFor(t, time.Second, func() bool { return fw.batchCount() == 1 })
fw.mu.Lock()
defer fw.mu.Unlock()
byMessage := map[string]string{}
for _, r := range fw.batches[0] {
byMessage[r.Record.GetMessage()] = r.TenantID
}
if byMessage["tagged"] != "acme" {
t.Fatalf("TenantID for the tagged message = %q, want acme", byMessage["tagged"])
}
if byMessage["untagged"] != "" {
t.Fatalf("TenantID for the untagged message = %q, want empty", byMessage["untagged"])
}
}