Merge #145352

145352: Add fine-grained checkpointing metrics to DRT clusters r=rharding6373 a=aerfrei

We added fine grained checkpointing for changefeeds in release 25.2. In order to monitor the additional resources involved in taking the checkpoints, we
added metrics on the total number of bytes, spans, timestamps and write time involved in these checkpoints. This commit makes those visible in datadog for DRT clusters.

Epic: none

Release note: None

Co-authored-by: Aerin Freilich <[email protected]>

Author: craig[bot]

pkg/roachprod/opentelemetry/cockroachdb_metrics.go

@@ -333,11 +333,24 @@ var cockroachdbMetrics = map[string]string{
 	"changefeed_buffer_pushback_nanos_aggregator":                         "changefeed.buffer_pushback_nanos.aggregator",
 	"changefeed_buffer_pushback_nanos_rangefeed":                          "changefeed.buffer_pushback_nanos.rangefeed",
 	"changefeed_bytes_messages_pushback_nanos":                            "changefeed.bytes.messages_pushback",
+	"changefeed_checkpoint_create_nanos":                                  "changefeed.checkpoint.create_nanos",
+	"changefeed_checkpoint_create_nanos_bucket":                           "changefeed.checkpoint.create_nanos.bucket",
+	"changefeed_checkpoint_create_nanos_count":                            "changefeed.checkpoint.create_nanos.count",
+	"changefeed_checkpoint_create_nanos_sum":                              "changefeed.checkpoint.create_nanos.sum",
 	"changefeed_checkpoint_hist_nanos":                                    "changefeed.checkpoint_hist",
 	"changefeed_checkpoint_hist_nanos_bucket":                             "changefeed.checkpoint_hist_nanos.bucket",
 	"changefeed_checkpoint_hist_nanos_count":                              "changefeed.checkpoint_hist_nanos.count",
 	"changefeed_checkpoint_hist_nanos_sum":                                "changefeed.checkpoint_hist_nanos.sum",
 	"changefeed_checkpoint_progress":                                      "changefeed.checkpoint_progress",
+	"changefeed_checkpoint_total_bytes":                                   "changefeed.checkpoint.total_bytes",
+	"changefeed_checkpoint_timestamp_count":                               "changefeed.checkpoint.timestamp_count",
+	"changefeed_checkpoint_timestamp_count_bucket":                        "changefeed.checkpoint.timestamp_count.bucket",
+	"changefeed_checkpoint_timestamp_count_count":                         "changefeed.checkpoint.timestamp_count.count",
+	"changefeed_checkpoint_timestamp_count_sum":                           "changefeed.checkpoint.timestamp_count.sum",
+	"changefeed_checkpoint_span_count":                                    "changefeed.checkpoint.span_count",
+	"changefeed_checkpoint_span_count_bucket":                             "changefeed.checkpoint.span_count.bucket",
+	"changefeed_checkpoint_span_count_count":                              "changefeed.checkpoint.span_count.count",
+	"changefeed_checkpoint_span_count_sum":                                "changefeed.checkpoint.span_count.sum",
 	"changefeed_cloudstorage_buffered_bytes":                              "changefeed.cloudstorage_buffered_bytes",
 	"changefeed_commit_latency":                                           "changefeed.commit.latency",
 	"changefeed_commit_latency_bucket":                                    "changefeed.commit_latency.bucket",