chore: change the resolution of reply latency to measurement to ns (#6092)

Align test_reply_count to use /metrics for fetching the `reply_count` counter.

Author: romange

src/facade/reply_builder.cc

@@ -181,7 +181,7 @@ void SinkReplyBuilder::Send() {
 
   uint64_t after_ns = util::fb2::ProactorBase::GetMonotonicTimeNs();
   reply_stats.send_stats.count++;
-  reply_stats.send_stats.total_duration += (after_ns - pin.timestamp_ns) / 1'000;
+  reply_stats.send_stats.total_duration += (after_ns - pin.timestamp_ns);
   DVLOG(2) << "Finished writing " << total_size_ << " bytes";
 }
 

src/server/server_family.cc

@@ -1713,7 +1713,7 @@ void PrintPrometheusMetrics(uint64_t uptime, const Metrics& m, DflyCmd* dfly_cmd
                             MetricType::COUNTER, &resp->body());
   {
     AppendMetricWithoutLabels("reply_duration_seconds", "",
-                              m.facade_stats.reply_stats.send_stats.total_duration * 1e-6,
+                              m.facade_stats.reply_stats.send_stats.total_duration * 1e-9,
                               MetricType::COUNTER, &resp->body());
     AppendMetricWithoutLabels("reply_total", "", m.facade_stats.reply_stats.send_stats.count,
                               MetricType::COUNTER, &resp->body());
@@ -3061,8 +3061,6 @@ string ServerFamily::FormatInfoMetrics(const Metrics& m, std::string_view sectio
     append("defrag_attempt_total", m.shard_stats.defrag_attempt_total);
     append("defrag_realloc_total", m.shard_stats.defrag_realloc_total);
     append("defrag_task_invocation_total", m.shard_stats.defrag_task_invocation_total);
-    append("reply_count", reply_stats.send_stats.count);
-    append("reply_latency_usec", reply_stats.send_stats.total_duration);
 
     // Number of connections that are currently blocked on grabbing interpreter.
     append("blocked_on_interpreter", m.coordinator_stats.blocked_on_interpreter);

tests/dragonfly/connection_test.py

@@ -607,21 +607,23 @@ async def test_keyspace_events_config_set(async_client: aioredis.Redis):
 
 
 @dfly_args({"max_busy_read_usec": 50000})
-async def test_reply_count(async_client: aioredis.Redis):
+async def test_reply_count(df_server: DflyInstance):
     """Make sure reply aggregations reduce reply counts for common cases"""
 
     async def get_reply_count():
-        return (await async_client.info("STATS"))["reply_count"]
+        metrics = await df_server.metrics()
+        return int(metrics["dragonfly_reply"].samples[0].value)
 
     async def measure(aw):
         before = await get_reply_count()
         await aw
-        return await get_reply_count() - before - 1
+        return await get_reply_count() - before
 
+    async_client = df_server.client()
     await async_client.config_resetstat()
     base = await get_reply_count()
     info_diff = await get_reply_count() - base
-    assert info_diff == 1
+    assert info_diff == 0  # no commands yet
 
     # Warm client buffer up
     await async_client.lpush("warmup", *(i for i in range(500)))