From e77961c1c6f5b242a47f923299df2237d1ee1649 Mon Sep 17 00:00:00 2001
From: Suhas Thalanki <54014218+thesuhas@users.noreply.github.com>
Date: Tue, 27 May 2025 15:40:51 -0400
Subject: [PATCH] background worker that collects installed extensions (#11939)

## Problem

Currently, we collect metrics of what extensions are installed on
computes at start up time. We do not have a mechanism that does this at
runtime.

## Summary of changes

Added a background thread that queries all DBs at regular intervals and
collects a list of installed extensions.
---
 compute_tools/src/bin/compute_ctl.rs |  5 +++
 compute_tools/src/compute.rs         | 53 ++++++++++++++++++++++------
 2 files changed, 47 insertions(+), 11 deletions(-)

diff --git a/compute_tools/src/bin/compute_ctl.rs b/compute_tools/src/bin/compute_ctl.rs
index 20b5e567a8..02339f752c 100644
--- a/compute_tools/src/bin/compute_ctl.rs
+++ b/compute_tools/src/bin/compute_ctl.rs
@@ -136,6 +136,10 @@ struct Cli {
         requires = "compute-id"
     )]
     pub control_plane_uri: Option<String>,
+
+    /// Interval in seconds for collecting installed extensions statistics
+    #[arg(long, default_value = "3600")]
+    pub installed_extensions_collection_interval: u64,
 }
 
 fn main() -> Result<()> {
@@ -179,6 +183,7 @@ fn main() -> Result<()> {
             cgroup: cli.cgroup,
             #[cfg(target_os = "linux")]
             vm_monitor_addr: cli.vm_monitor_addr,
+            installed_extensions_collection_interval: cli.installed_extensions_collection_interval,
         },
         config,
     )?;
diff --git a/compute_tools/src/compute.rs b/compute_tools/src/compute.rs
index cb857e0a3e..ff49c737f0 100644
--- a/compute_tools/src/compute.rs
+++ b/compute_tools/src/compute.rs
@@ -97,6 +97,9 @@ pub struct ComputeNodeParams {
 
     /// the address of extension storage proxy gateway
     pub remote_ext_base_url: Option<String>,
+
+    /// Interval for installed extensions collection
+    pub installed_extensions_collection_interval: u64,
 }
 
 /// Compute node info shared across several `compute_ctl` threads.
@@ -742,17 +745,7 @@ impl ComputeNode {
 
             let conf = self.get_tokio_conn_conf(None);
             tokio::task::spawn(async {
-                let res = get_installed_extensions(conf).await;
-                match res {
-                    Ok(extensions) => {
-                        info!(
-                            "[NEON_EXT_STAT] {}",
-                            serde_json::to_string(&extensions)
-                                .expect("failed to serialize extensions list")
-                        );
-                    }
-                    Err(err) => error!("could not get installed extensions: {err:?}"),
-                }
+                let _ = installed_extensions(conf).await;
             });
         }
 
@@ -782,6 +775,9 @@ impl ComputeNode {
         // Log metrics so that we can search for slow operations in logs
         info!(?metrics, postmaster_pid = %postmaster_pid, "compute start finished");
 
+        // Spawn the extension stats background task
+        self.spawn_extension_stats_task();
+
         if pspec.spec.prewarm_lfc_on_startup {
             self.prewarm_lfc();
         }
@@ -2192,6 +2188,41 @@ LIMIT 100",
             info!("Pageserver config changed");
         }
     }
+
+    pub fn spawn_extension_stats_task(&self) {
+        let conf = self.tokio_conn_conf.clone();
+        let installed_extensions_collection_interval =
+            self.params.installed_extensions_collection_interval;
+        tokio::spawn(async move {
+            // An initial sleep is added to ensure that two collections don't happen at the same time.
+            // The first collection happens during compute startup.
+            tokio::time::sleep(tokio::time::Duration::from_secs(
+                installed_extensions_collection_interval,
+            ))
+            .await;
+            let mut interval = tokio::time::interval(tokio::time::Duration::from_secs(
+                installed_extensions_collection_interval,
+            ));
+            loop {
+                interval.tick().await;
+                let _ = installed_extensions(conf.clone()).await;
+            }
+        });
+    }
+}
+
+pub async fn installed_extensions(conf: tokio_postgres::Config) -> Result<()> {
+    let res = get_installed_extensions(conf).await;
+    match res {
+        Ok(extensions) => {
+            info!(
+                "[NEON_EXT_STAT] {}",
+                serde_json::to_string(&extensions).expect("failed to serialize extensions list")
+            );
+        }
+        Err(err) => error!("could not get installed extensions: {err:?}"),
+    }
+    Ok(())
 }
 
 pub fn forward_termination_signal() {