From 77251b60c42e9f4f3b39c40c383cdab27b2ee2c9 Mon Sep 17 00:00:00 2001
From: Marcin Rataj <lidel@lidel.org>
Date: Wed, 17 Aug 2022 01:27:50 +0200
Subject: [PATCH] test(rcmgr): regression test prometherus metrics

---
 docs/config.md                                |  2 ++
 ...prometheus_metrics_added_by_enabling_rcmgr |  4 +++
 test/sharness/t0119-prometheus.sh             | 27 +++++++++++++++++++
 3 files changed, 33 insertions(+)
 create mode 100644 test/sharness/t0116-prometheus-data/prometheus_metrics_added_by_enabling_rcmgr

diff --git a/docs/config.md b/docs/config.md
index 386ab584a..404debd1c 100644
--- a/docs/config.md
+++ b/docs/config.md
@@ -1719,6 +1719,8 @@ and tracking recource usage over time.
 Enables the libp2p Network Resource Manager and auguments the default limits
 using user-defined ones in `Swarm.ResourceMgr.Limits` (if present).
 
+Various `*rcmgr_*` metrics can be accessed as the prometheus endpoint at `{Addresses.API}/debug/metrics/prometheus` (default: `http://127.0.0.1:5001/debug/metrics/prometheus`)
+
 Default: `false`
 
 Type: `flag`
diff --git a/test/sharness/t0116-prometheus-data/prometheus_metrics_added_by_enabling_rcmgr b/test/sharness/t0116-prometheus-data/prometheus_metrics_added_by_enabling_rcmgr
new file mode 100644
index 000000000..382ab1256
--- /dev/null
+++ b/test/sharness/t0116-prometheus-data/prometheus_metrics_added_by_enabling_rcmgr
@@ -0,0 +1,4 @@
+libp2p_rcmgr_memory_allocations_allowed_total
+libp2p_rcmgr_memory_allocations_blocked_total
+libp2p_rcmgr_peer_blocked_total
+libp2p_rcmgr_peers_allowed_total
diff --git a/test/sharness/t0119-prometheus.sh b/test/sharness/t0119-prometheus.sh
index 0412179fe..cd7346735 100755
--- a/test/sharness/t0119-prometheus.sh
+++ b/test/sharness/t0119-prometheus.sh
@@ -26,4 +26,31 @@ test_expect_success "make sure metrics haven't changed" '
   diff -u ../t0116-prometheus-data/prometheus_metrics filtered_metrics
 '
 
+# Check what was added by enabling ResourceMgr.Enabled
+#
+# NOTE: we won't see all the dynamic ones, but that is  ok: the point of the
+# test here is to detect regression when rcmgr metrics dissapear due to
+# refactor/human error.
+
+test_expect_success "enable ResourceMgr in the config" '
+  ipfs config --json Swarm.ResourceMgr.Enabled true
+'
+
+test_launch_ipfs_daemon
+
+test_expect_success "collect metrics" '
+  curl "$API_ADDR/debug/metrics/prometheus" > raw_metrics
+'
+
+test_kill_ipfs_daemon
+
+test_expect_success "filter metrics and find ones added by enabling ResourceMgr" '
+  sed -ne "s/^\([a-z0-9_]\+\).*/\1/p" raw_metrics | LC_ALL=C sort > filtered_metrics &&
+  grep -v -x -f ../t0116-prometheus-data/prometheus_metrics filtered_metrics > rcmgr_metrics
+'
+
+test_expect_success "make sure initial metrics added by setting ResourceMgr.Enabled haven't changed" '
+  diff -u ../t0116-prometheus-data/prometheus_metrics_added_by_enabling_rcmgr rcmgr_metrics
+'
+
 test_done