roachtest: import-cancellation: use a fixed seed; smaller import

Currently, due to the randomness present in the test, there may be
significant variance in test runs. In some situations, the nature of the
random import cancellations may result in the test timing out. This
makes the test flaky.

Use a fixed seed for the test's PRNG to make the test more
deterministic.

Reduce the size of the overall import by lowering the
number of files used to generate the `lineitem` table. This should also
help stabilize the runtime.

Force the collection of table statistics as soon as the table has
finished importing.

Reduce the number of time each TPC-H query is repeated, from three to
two.

Fix #90510.

Release note: None.

pkg/cmd/roachtest/tests/import_cancellation.go

@@ -83,7 +83,8 @@ func runImportCancellation(ctx context.Context, t test.Test, c cluster.Cluster)
 		t.Fatal(err)
 	}
 
-	rng, seed := randutil.NewPseudoRand()
+	seed := int64(1666467482296309000)
+	rng := randutil.NewTestRandWithSeed(seed)
 
 	tablesToNumFiles := map[string]int{
 		"region":   1,
@@ -93,7 +94,7 @@ func runImportCancellation(ctx context.Context, t test.Test, c cluster.Cluster)
 		"partsupp": 8,
 		"customer": 8,
 		"orders":   8,
-		"lineitem": 8,
+		"lineitem": 2,
 	}
 	for tbl := range tablesToNumFiles {
 		fixtureURL := fmt.Sprintf("gs://cockroach-fixtures/tpch-csv/schema/%s.sql?AUTH=implicit", tbl)
@@ -157,8 +158,8 @@ func runImportCancellation(ctx context.Context, t test.Test, c cluster.Cluster)
 	m.Go(func(ctx context.Context) error {
 		t.WorkerStatus(`running tpch workload`)
 		// maxOps flag will allow us to exit the workload once all the queries
-		// were run 3 times.
-		const numRunsPerQuery = 3
+		// were run 2 times.
+		const numRunsPerQuery = 2
 		const maxLatency = 500 * time.Second
 		maxOps := numRunsPerQuery * numQueries
 		cmd := fmt.Sprintf(
@@ -299,6 +300,16 @@ func (t *importCancellationTest) runImportSequence(
 		t.Fatalf("Expected zero remaining %q files after final attempt, but %d remaining.",
 			tableName, len(filesToImport))
 	}
+
+	// Kick off a stats collection job for the table. This serves a dual purpose.
+	// Up-to-date statistics on the table helps the optimizer during the query
+	// phase of the test. The stats job also requires scanning a large swath of
+	// the keyspace, which results in greater test coverage.
+	stmt := fmt.Sprintf(`CREATE STATISTICS %s_stats FROM csv.%s`, tableName, tableName)
+	_, err := conn.ExecContext(ctx, stmt)
+	if err != nil {
+		t.Fatal(err)
+	}
 }
 
 // remove removes all elements from a that exist in b.