From 92e7cd40e88825a489c8d3c19c78ef001b59d06c Mon Sep 17 00:00:00 2001
From: Anastasia Lubennikova <anastasia@neon.tech>
Date: Fri, 1 Dec 2023 13:40:49 +0000
Subject: [PATCH] add sql_exporter to vm-image (#5949)

expose LFC metrics
---
 vm-image-spec.yaml | 85 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 84 insertions(+), 1 deletion(-)

diff --git a/vm-image-spec.yaml b/vm-image-spec.yaml
index d0ba742a63..6f0ebe5f66 100644
--- a/vm-image-spec.yaml
+++ b/vm-image-spec.yaml
@@ -13,6 +13,10 @@ commands:
     user: nobody
     sysvInitAction: respawn
     shell: 'DATA_SOURCE_NAME="user=cloud_admin sslmode=disable dbname=postgres" /bin/postgres_exporter'
+  - name: sql-exporter
+    user: nobody
+    sysvInitAction: respawn
+    shell: '/bin/sql_exporter -config.file=/etc/sql_exporter.yml'
 shutdownHook: |
   su -p postgres --session-command '/usr/local/bin/pg_ctl stop -D /var/db/postgres/compute/pgdata -m fast --wait -t 10'
 files:
@@ -46,6 +50,77 @@ files:
           }
           memory {}
       }
+  - filename: sql_exporter.yml
+    content: |
+      # Configuration for sql_exporter
+      # Global defaults.
+      global:
+        # If scrape_timeout <= 0, no timeout is set unless Prometheus provides one. The default is 10s.
+        scrape_timeout: 10s
+        # Subtracted from Prometheus' scrape_timeout to give us some headroom and prevent Prometheus from timing out first.
+        scrape_timeout_offset: 500ms
+        # Minimum interval between collector runs: by default (0s) collectors are executed on every scrape.
+        min_interval: 0s
+        # Maximum number of open connections to any one target. Metric queries will run concurrently on multiple connections,
+        # as will concurrent scrapes.
+        max_connections: 1
+        # Maximum number of idle connections to any one target. Unless you use very long collection intervals, this should
+        # always be the same as max_connections.
+        max_idle_connections: 1
+        # Maximum number of maximum amount of time a connection may be reused. Expired connections may be closed lazily before reuse.
+        # If 0, connections are not closed due to a connection's age.
+        max_connection_lifetime: 5m
+
+      # The target to monitor and the collectors to execute on it.
+      target:
+        # Data source name always has a URI schema that matches the driver name. In some cases (e.g. MySQL)
+        # the schema gets dropped or replaced to match the driver expected DSN format.
+        data_source_name: 'postgresql://cloud_admin@127.0.0.1:5432/postgres?sslmode=disable'
+
+        # Collectors (referenced by name) to execute on the target.
+        # Glob patterns are supported (see <https://pkg.go.dev/path/filepath#Match> for syntax).
+        collectors: [neon_collector]
+
+      # Collector files specifies a list of globs. One collector definition is read from each matching file.
+      # Glob patterns are supported (see <https://pkg.go.dev/path/filepath#Match> for syntax).
+      collector_files:
+        - "neon_collector.yml"
+  - filename: neon_collector.yml
+    content: |
+      collector_name: neon_collector
+      metrics:
+      - metric_name: lfc_misses
+        type: gauge
+        help: 'lfc_misses'
+        key_labels:
+        values: [lfc_misses]
+        query: |
+          select lfc_value as lfc_misses from neon.neon_lfc_stats where lfc_key='file_cache_misses';
+
+      - metric_name: lfc_used
+        type: gauge
+        help: 'lfc_used'
+        key_labels:
+        values: [lfc_used]
+        query: |
+          select lfc_value as lfc_used from neon.neon_lfc_stats where lfc_key='file_cache_used';
+
+      - metric_name: lfc_hits
+        type: gauge
+        help: 'lfc_hits'
+        key_labels:
+        values: [lfc_hits]
+        query: |
+          select lfc_value as lfc_hits from neon.neon_lfc_stats where lfc_key='file_cache_hits';
+
+      - metric_name: lfc_writes
+        type: gauge
+        help: 'lfc_writes'
+        key_labels:
+        values: [lfc_writes]
+        query: |
+          select lfc_value as lfc_writes from neon.neon_lfc_stats where lfc_key='file_cache_writes';
+
 build: |
   # Build cgroup-tools
   #
@@ -82,6 +157,8 @@ build: |
 
   FROM quay.io/prometheuscommunity/postgres-exporter:v0.12.0 AS postgres-exporter
 
+  FROM burningalchemist/sql_exporter:0.13 AS sql-exporter
+
   # Build pgbouncer
   #
   FROM debian:bullseye-slim AS pgbouncer
@@ -116,13 +193,19 @@ merge: |
 
   COPY cgconfig.conf /etc/cgconfig.conf
   COPY pgbouncer.ini /etc/pgbouncer.ini
+  COPY sql_exporter.yml /etc/sql_exporter.yml
+  COPY neon_collector.yml /etc/neon_collector.yml
+
   RUN set -e \
       && chown postgres:postgres /etc/pgbouncer.ini \
       && chmod 0644 /etc/pgbouncer.ini \
-      && chmod 0644 /etc/cgconfig.conf
+      && chmod 0644 /etc/cgconfig.conf \
+      && chmod 0644 /etc/sql_exporter.yml \
+      && chmod 0644 /etc/neon_collector.yml
 
   COPY --from=libcgroup-builder /libcgroup-install/bin/*  /usr/bin/
   COPY --from=libcgroup-builder /libcgroup-install/lib/*  /usr/lib/
   COPY --from=libcgroup-builder /libcgroup-install/sbin/* /usr/sbin/
   COPY --from=postgres-exporter /bin/postgres_exporter /bin/postgres_exporter
+  COPY --from=sql-exporter      /bin/sql_exporter      /bin/sql_exporter
   COPY --from=pgbouncer         /usr/local/pgbouncer/bin/pgbouncer /usr/local/bin/pgbouncer