public inbox for pdm-devel@lists.proxmox.com
 help / color / mirror / Atom feed
From: Lukas Wagner <l.wagner@proxmox.com>
To: pdm-devel@lists.proxmox.com
Subject: [pdm-devel] [PATCH proxmox-datacenter-manager v7 12/24] metric collection: record remote response time in metric database
Date: Tue, 26 Aug 2025 15:51:07 +0200	[thread overview]
Message-ID: <20250826135119.336510-13-l.wagner@proxmox.com> (raw)
In-Reply-To: <20250826135119.336510-1-l.wagner@proxmox.com>

This gives us the ability to retrieve max/avg response times for a given
time window.

Signed-off-by: Lukas Wagner <l.wagner@proxmox.com>
Reviewed-by: Maximiliano Sandoval <m.sandoval@proxmox.com>
Reviewed-by: Dominik Csapak <d.csapak@proxmox.com>
Tested-by: Dominik Csapak <d.csapak@proxmox.com>
---
 .../src/metric_collection/collection_task.rs  | 13 +++++++-
 server/src/metric_collection/rrd_task.rs      | 31 +++++++++++++++++++
 2 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/server/src/metric_collection/collection_task.rs b/server/src/metric_collection/collection_task.rs
index c3448995..51bcd78a 100644
--- a/server/src/metric_collection/collection_task.rs
+++ b/server/src/metric_collection/collection_task.rs
@@ -266,6 +266,7 @@ impl MetricCollectionTask {
         let (result_tx, result_rx) = oneshot::channel();
 
         let now = proxmox_time::epoch_i64();
+        let start = Instant::now();
 
         let res: Result<RrdStoreResult, Error> = async {
             match remote.ty {
@@ -279,11 +280,16 @@ impl MetricCollectionTask {
                         )
                         .await?;
 
+                    let duration = start.elapsed();
+
                     sender
                         .send(RrdStoreRequest::Pve {
                             remote: remote.id.clone(),
                             metrics,
                             channel: result_tx,
+                            // TODO: use as_millis_f64 once stabilized
+                            response_time: duration.as_secs_f64() * 1000.,
+                            request_at: now,
                         })
                         .await?;
                 }
@@ -293,15 +299,20 @@ impl MetricCollectionTask {
                         .metrics(Some(true), Some(status.most_recent_datapoint))
                         .await?;
 
+                    let duration = start.elapsed();
+
                     sender
                         .send(RrdStoreRequest::Pbs {
                             remote: remote.id.clone(),
                             metrics,
                             channel: result_tx,
+                            // TODO: use as_millis_f64 once stabilized
+                            response_time: duration.as_secs_f64() * 1000.,
+                            request_at: now,
                         })
                         .await?;
                 }
-            }
+            };
 
             result_rx.await.map_err(Error::from)
         }
diff --git a/server/src/metric_collection/rrd_task.rs b/server/src/metric_collection/rrd_task.rs
index f65a9291..91927602 100644
--- a/server/src/metric_collection/rrd_task.rs
+++ b/server/src/metric_collection/rrd_task.rs
@@ -20,6 +20,10 @@ pub(super) enum RrdStoreRequest {
         metrics: ClusterMetrics,
         /// Oneshot channel to return the [`RrdStoreResult`].
         channel: oneshot::Sender<RrdStoreResult>,
+        /// Reponse time in ms for the API request.
+        response_time: f64,
+        /// Timestamp at which the request was done (UNIX epoch).
+        request_at: i64,
     },
     /// Store PBS metrics.
     Pbs {
@@ -29,6 +33,10 @@ pub(super) enum RrdStoreRequest {
         metrics: Metrics,
         /// Oneshot channel to return the [`RrdStoreResult`].
         channel: oneshot::Sender<RrdStoreResult>,
+        /// Reponse time in ms for the API request.
+        response_time: f64,
+        /// Timestamp at which the request was done (UNIX epoch).
+        request_at: i64,
     },
 }
 
@@ -54,11 +62,14 @@ pub(super) async fn store_in_rrd_task(
                     remote,
                     metrics,
                     channel,
+                    response_time,
+                    request_at,
                 } => {
                     for data_point in metrics.data {
                         most_recent_timestamp = most_recent_timestamp.max(data_point.timestamp);
                         store_metric_pve(&cache_clone, &remote, &data_point);
                     }
+                    store_response_time(&cache_clone, &remote, response_time, request_at);
 
                     channel
                 }
@@ -66,11 +77,14 @@ pub(super) async fn store_in_rrd_task(
                     remote,
                     metrics,
                     channel,
+                    response_time,
+                    request_at,
                 } => {
                     for data_point in metrics.data {
                         most_recent_timestamp = most_recent_timestamp.max(data_point.timestamp);
                         store_metric_pbs(&cache_clone, &remote, &data_point);
                     }
+                    store_response_time(&cache_clone, &remote, response_time, request_at);
 
                     channel
                 }
@@ -137,6 +151,12 @@ fn store_metric_pbs(cache: &RrdCache, remote_name: &str, data_point: &MetricData
     );
 }
 
+fn store_response_time(cache: &RrdCache, remote_name: &str, response_time: f64, timestamp: i64) {
+    let name = format!("remotes/{remote_name}/metric-collection-response-time");
+
+    cache.update_value(&name, response_time, timestamp, DataSourceType::Gauge);
+}
+
 #[cfg(test)]
 mod tests {
     use proxmox_rrd_api_types::{RrdMode, RrdTimeframe};
@@ -199,6 +219,8 @@ mod tests {
             remote: "some-remote".into(),
             metrics,
             channel: tx_back,
+            response_time: 10.0,
+            request_at: now,
         };
 
         // Act
@@ -224,6 +246,15 @@ mod tests {
             assert!(data.data.iter().any(Option::is_some));
         }
 
+        if let Some(data) = cache.extract_data(
+            "remotes/some-remote",
+            "metric-collection-response-time",
+            RrdTimeframe::Hour,
+            RrdMode::Max,
+        )? {
+            assert!(data.data.iter().any(Option::is_some));
+        }
+
         Ok(())
     }
 }
-- 
2.47.2



_______________________________________________
pdm-devel mailing list
pdm-devel@lists.proxmox.com
https://lists.proxmox.com/cgi-bin/mailman/listinfo/pdm-devel


  parent reply	other threads:[~2025-08-26 13:51 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-08-26 13:50 [pdm-devel] [PATCH proxmox-datacenter-manager v7 00/24] metric collection improvements (concurrency, API, CLI) Lukas Wagner
2025-08-26 13:50 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 01/24] metric collection: split top_entities split into separate module Lukas Wagner
2025-08-26 13:50 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 02/24] metric collection: save metric data to RRD in separate task Lukas Wagner
2025-08-26 13:50 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 03/24] metric collection: rework metric poll task Lukas Wagner
2025-08-26 13:50 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 04/24] metric collection: persist state after metric collection Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 05/24] metric collection: skip if last_collection < MIN_COLLECTION_INTERVAL Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 06/24] metric collection: collect overdue metrics on startup/timer change Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 07/24] metric collection: add tests for the fetch_remotes function Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 08/24] metric collection: add test for fetch_overdue Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 09/24] metric collection: pass rrd cache instance as function parameter Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 10/24] metric collection: add test for rrd task Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 11/24] metric collection: wrap rrd_cache::Cache in a struct Lukas Wagner
2025-08-26 13:51 ` Lukas Wagner [this message]
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 13/24] metric collection: save time needed for collection run to RRD Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 14/24] metric collection: periodically clean removed remotes from statefile Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 15/24] api: add endpoint to trigger metric collection Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 16/24] api: remotes: trigger immediate metric collection for newly added nodes Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 17/24] api: add api for querying metric collection RRD data Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 18/24] api: metric-collection: add status endpoint Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 19/24] pdm-client: add metric collection API methods Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 20/24] cli: add commands for metric-collection trigger and status Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 21/24] metric collection: skip missed timer ticks Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 22/24] metric collection: use JoinSet instead of joining from handles in a Vec Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 23/24] metric collection: allow to wait until completion when triggering collection manually Lukas Wagner
2025-08-26 13:51 ` [pdm-devel] [PATCH proxmox-datacenter-manager v7 24/24] api: pve: rrd: trigger and wait for metric collection when requesting RRD data Lukas Wagner
2025-08-28 19:37 ` [pdm-devel] applied: [PATCH proxmox-datacenter-manager v7 00/24] metric collection improvements (concurrency, API, CLI) Thomas Lamprecht

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250826135119.336510-13-l.wagner@proxmox.com \
    --to=l.wagner@proxmox.com \
    --cc=pdm-devel@lists.proxmox.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
Service provided by Proxmox Server Solutions GmbH | Privacy | Legal