From a9d81191d45deb906930632f664ba85cbb3b56eb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Tom=C3=A1s=20Gr=C3=BCner?=
 <47506558+MegaRedHand@users.noreply.github.com>
Date: Fri, 30 Oct 2026 19:17:59 -0300
Subject: [PATCH] fix(metrics): serve the process collector's memory and CPU
 metrics

The beacon dashboard's memory panel reads process_resident_memory_bytes, which
no ethlambda build exported: the prometheus crate only registers its process
collector with the default registry when its `process` feature is on. Only a
build that pulls ethrex's metrics in (the embedded follower) had it, through
feature unification, so every other node's memory panel was blank.

Turn the feature on for the workspace. On Linux the default registry, which the
metrics endpoint gathers from, now carries process_resident_memory_bytes and the
other process_* series; other platforms are unchanged.
---
 Cargo.lock                          | 51 ++++++++++++++++++++++++++---
 Cargo.toml                          |  2 +-
 crates/common/metrics/src/gather.rs | 18 ++++++++++
 docs/metrics.md                     |  7 ++++
 4 files changed, 73 insertions(+), 5 deletions(-)

diff --git a/Cargo.lock b/Cargo.lock
index 727d76a61..6a1a8a647 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -522,7 +522,7 @@ dependencies = [
  "futures-lite",
  "parking",
  "polling",
- "rustix",
+ "rustix 1.1.4",
  "slab",
  "windows-sys 0.61.2",
 ]
@@ -4714,6 +4714,12 @@ dependencies = [
  "vcpkg",
 ]
 
+[[package]]
+name = "linux-raw-sys"
+version = "0.4.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d26c52dbd32dccf2d10cac7725f8eae5296885fb5703b261f7d0a0739ec807ab"
+
 [[package]]
 name = "linux-raw-sys"
 version = "0.12.1"
@@ -5460,7 +5466,7 @@ dependencies = [
  "concurrent-queue",
  "hermit-abi",
  "pin-project-lite",
- "rustix",
+ "rustix 1.1.4",
  "windows-sys 0.61.2",
 ]
 
@@ -5628,6 +5634,28 @@ dependencies = [
  "unicode-ident",
 ]
 
+[[package]]
+name = "procfs"
+version = "0.17.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "cc5b72d8145275d844d4b5f6d4e1eef00c8cd889edb6035c21675d1bb1f45c9f"
+dependencies = [
+ "bitflags 2.11.1",
+ "hex",
+ "procfs-core",
+ "rustix 0.38.44",
+]
+
+[[package]]
+name = "procfs-core"
+version = "0.17.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "239df02d8349b06fc07398a3a1697b06418223b1c7725085e801e7c0fc6a12ec"
+dependencies = [
+ "bitflags 2.11.1",
+ "hex",
+]
+
 [[package]]
 name = "prometheus"
 version = "0.14.0"
@@ -5637,8 +5665,10 @@ dependencies = [
  "cfg-if",
  "fnv",
  "lazy_static",
+ "libc",
  "memchr",
  "parking_lot",
+ "procfs",
  "protobuf",
  "thiserror 2.0.18",
 ]
@@ -6386,6 +6416,19 @@ dependencies = [
  "nom",
 ]
 
+[[package]]
+name = "rustix"
+version = "0.38.44"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fdb5bc1ae2baa591800df16c9ca78619bf65c0488b41b96ccec5d11220d8c154"
+dependencies = [
+ "bitflags 2.11.1",
+ "errno",
+ "libc",
+ "linux-raw-sys 0.4.15",
+ "windows-sys 0.52.0",
+]
+
 [[package]]
 name = "rustix"
 version = "1.1.4"
@@ -6395,7 +6438,7 @@ dependencies = [
  "bitflags 2.11.1",
  "errno",
  "libc",
- "linux-raw-sys",
+ "linux-raw-sys 0.12.1",
  "windows-sys 0.60.2",
 ]
 
@@ -7149,7 +7192,7 @@ dependencies = [
  "fastrand",
  "getrandom 0.4.2",
  "once_cell",
- "rustix",
+ "rustix 1.1.4",
  "windows-sys 0.60.2",
 ]
 
diff --git a/Cargo.toml b/Cargo.toml
index 71effe4b1..e13475448 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -95,7 +95,7 @@ spawned-rt = "0.5.0"
 tokio = "1.0"
 tokio-util = "0.7"
 
-prometheus = "0.14"
+prometheus = { version = "0.14", features = ["process"] }
 
 clap = { version = "4.3", features = ["derive", "env"] }
 
diff --git a/crates/common/metrics/src/gather.rs b/crates/common/metrics/src/gather.rs
index c4e727e0c..8912d18e6 100644
--- a/crates/common/metrics/src/gather.rs
+++ b/crates/common/metrics/src/gather.rs
@@ -27,3 +27,21 @@ pub fn gather_default_metrics() -> Result<String, GatherError> {
 
     Ok(res)
 }
+
+/// The process collector comes from the `prometheus` crate's `process`
+/// feature, which registers it with the default registry on Linux only.
+/// Dashboards read the node's memory from it, so dropping the feature would
+/// leave them blank without any build failing.
+#[cfg(all(test, target_os = "linux"))]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn the_default_registry_serves_the_process_metrics() {
+        let metrics = gather_default_metrics().unwrap();
+        assert!(
+            metrics.contains("process_resident_memory_bytes"),
+            "{metrics}"
+        );
+    }
+}
diff --git a/docs/metrics.md b/docs/metrics.md
index 1ea07953f..7107778d1 100644
--- a/docs/metrics.md
+++ b/docs/metrics.md
@@ -13,6 +13,13 @@ The Lean Chain's metrics follow [the leanMetrics specification](https://github.c
 | `lean_node_info` | Gauge | Node information (always 1) | On node start | name, version | ✅ |
 | `lean_node_start_time_seconds` | Gauge | Start timestamp | On node start | | ✅ |
 
+On Linux the endpoint also serves the `prometheus` crate's process collector,
+read from `/proc/self` at each scrape: `process_resident_memory_bytes`,
+`process_virtual_memory_bytes`, `process_cpu_seconds_total`,
+`process_open_fds`, `process_max_fds`, `process_threads` and
+`process_start_time_seconds`. They are not part of the leanMetrics spec, and
+other platforms do not export them.
+
 
 ## PQ Signature Metrics