From d6753e9ee4925166cced51cd1b1426fbee75ccad Mon Sep 17 00:00:00 2001
From: Em Sharnoff <sharnoff@neon.tech>
Date: Mon, 22 Jul 2024 11:28:08 -0700
Subject: [PATCH] vm-image: Expose new LFC working set size metrics (#8298)

In general, replace:

* 'lfc_approximate_working_set_size' with
* 'lfc_approximate_working_set_size_windows'

For the "main" metrics that are actually scraped and used internally,
the old one is just marked as deprecated.
For the "autoscaling" metrics, we're not currently using the old one, so
we can get away with just replacing it.

Also, for the user-visible metrics we'll only store & expose a few
different time windows, to avoid making the UI overly busy or bloating
our internal metrics storage.

But for the autoscaling-related scraper, we aren't storing the metrics,
and it's useful to be able to programmatically operate on the trendline
of how WSS increases (or doesn't!) with window size. So there, we can
just output datapoints for each minute.

Part of neondatabase/autoscaling#872
See also https://www.notion.so/neondatabase/cca38138fadd45eaa753d81b859490c6
---
 vm-image-spec.yaml | 29 +++++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/vm-image-spec.yaml b/vm-image-spec.yaml
index 3c446ecdea..224e9847f3 100644
--- a/vm-image-spec.yaml
+++ b/vm-image-spec.yaml
@@ -236,6 +236,7 @@ files:
         query: |
           select sum(pg_database_size(datname)) as total from pg_database;
 
+      # DEPRECATED
       - metric_name: lfc_approximate_working_set_size
         type: gauge
         help: 'Approximate working set size in pages of 8192 bytes'
@@ -244,6 +245,20 @@ files:
         query: |
           select neon.approximate_working_set_size(false) as approximate_working_set_size;
 
+      - metric_name: lfc_approximate_working_set_size_windows
+        type: gauge
+        help: 'Approximate working set size in pages of 8192 bytes'
+        key_labels: [duration]
+        values: [size]
+        # NOTE: This is the "public" / "human-readable" version. Here, we supply a small selection
+        # of durations in a pretty-printed form.
+        query: |
+          select
+            x as duration,
+            neon.approximate_working_set_size_seconds(extract('epoch' from x::interval)::int) as size
+          from
+            (values ('5m'),('15m'),('1h')) as t (x);
+
       - metric_name: current_lsn
         type: gauge
         help: 'Current LSN of the database'
@@ -377,13 +392,19 @@ files:
         query: |
           select pg_size_bytes(current_setting('neon.file_cache_size_limit')) as lfc_cache_size_limit;
 
-      - metric_name: lfc_approximate_working_set_size
+      - metric_name: lfc_approximate_working_set_size_windows
         type: gauge
         help: 'Approximate working set size in pages of 8192 bytes'
-        key_labels:
-        values: [approximate_working_set_size]
+        key_labels: [duration_seconds]
+        values: [size]
+        # NOTE: This is the "internal" / "machine-readable" version. This outputs the working set
+        # size looking back 1..60 minutes, labeled with the number of minutes.
         query: |
-          select neon.approximate_working_set_size(false) as approximate_working_set_size;
+          select
+            x::text as duration_seconds,
+            neon.approximate_working_set_size_seconds(x) as size
+          from
+            (select generate_series * 60 as x from generate_series(1, 60));
 build: |
   # Build cgroup-tools
   #