metric: add started and killed walredo processes counter (#5809)

In OOM situations, knowing exactly how many walredo processes there were
at a time would help afterwards to understand why was pageserver OOM
killed. Add `pageserver_wal_redo_process_total` metric to keep track of
total wal redo process started, shutdown and killed since pageserver
start.

Closes #5722

---------

Signed-off-by: Rahul Modpur <rmodpur2@gmail.com>
Co-authored-by: Joonas Koivunen <joonas@neon.tech>
Co-authored-by: Christian Schwarz <me@cschwarz.com>

pageserver/src/metrics.rs

@@ -1252,6 +1252,46 @@ pub(crate) static WAL_REDO_RECORD_COUNTER: Lazy<IntCounter> = Lazy::new(|| {
     .unwrap()
 });
 
+pub(crate) struct WalRedoProcessCounters {
+    pub(crate) started: IntCounter,
+    pub(crate) killed_by_cause: enum_map::EnumMap<WalRedoKillCause, IntCounter>,
+}
+
+#[derive(Debug, enum_map::Enum, strum_macros::IntoStaticStr)]
+pub(crate) enum WalRedoKillCause {
+    WalRedoProcessDrop,
+    NoLeakChildDrop,
+    Startup,
+}
+
+impl Default for WalRedoProcessCounters {
+    fn default() -> Self {
+        let started = register_int_counter!(
+            "pageserver_wal_redo_process_started_total",
+            "Number of WAL redo processes started",
+        )
+        .unwrap();
+
+        let killed = register_int_counter_vec!(
+            "pageserver_wal_redo_process_stopped_total",
+            "Number of WAL redo processes stopped",
+            &["cause"],
+        )
+        .unwrap();
+        Self {
+            started,
+            killed_by_cause: EnumMap::from_array(std::array::from_fn(|i| {
+                let cause = <WalRedoKillCause as enum_map::Enum>::from_usize(i);
+                let cause_str: &'static str = cause.into();
+                killed.with_label_values(&[cause_str])
+            })),
+        }
+    }
+}
+
+pub(crate) static WAL_REDO_PROCESS_COUNTERS: Lazy<WalRedoProcessCounters> =
+    Lazy::new(WalRedoProcessCounters::default);
+
 /// Similar to `prometheus::HistogramTimer` but does not record on drop.
 pub struct StorageTimeMetricsTimer {
     metrics: StorageTimeMetrics,

pageserver/src/walredo.rs

@@ -43,7 +43,8 @@ use std::sync::atomic::{AtomicUsize, Ordering};
 
 use crate::config::PageServerConf;
 use crate::metrics::{
-    WAL_REDO_BYTES_HISTOGRAM, WAL_REDO_RECORDS_HISTOGRAM, WAL_REDO_RECORD_COUNTER, WAL_REDO_TIME,
+    WalRedoKillCause, WAL_REDO_BYTES_HISTOGRAM, WAL_REDO_PROCESS_COUNTERS,
+    WAL_REDO_RECORDS_HISTOGRAM, WAL_REDO_RECORD_COUNTER, WAL_REDO_TIME,
 };
 use crate::pgdatadir_mapping::{key_to_rel_block, key_to_slru_block};
 use crate::repository::Key;
@@ -662,10 +663,10 @@ impl WalRedoProcess {
             .close_fds()
             .spawn_no_leak_child(tenant_id)
             .context("spawn process")?;
-
+        WAL_REDO_PROCESS_COUNTERS.started.inc();
         let mut child = scopeguard::guard(child, |child| {
             error!("killing wal-redo-postgres process due to a problem during launch");
-            child.kill_and_wait();
+            child.kill_and_wait(WalRedoKillCause::Startup);
         });
 
         let stdin = child.stdin.take().unwrap();
@@ -996,7 +997,7 @@ impl Drop for WalRedoProcess {
         self.child
             .take()
             .expect("we only do this once")
-            .kill_and_wait();
+            .kill_and_wait(WalRedoKillCause::WalRedoProcessDrop);
         self.stderr_logger_cancel.cancel();
         // no way to wait for stderr_logger_task from Drop because that is async only
     }
@@ -1032,16 +1033,19 @@ impl NoLeakChild {
         })
     }
 
-    fn kill_and_wait(mut self) {
+    fn kill_and_wait(mut self, cause: WalRedoKillCause) {
         let child = match self.child.take() {
             Some(child) => child,
             None => return,
         };
-        Self::kill_and_wait_impl(child);
+        Self::kill_and_wait_impl(child, cause);
     }
 
-    #[instrument(skip_all, fields(pid=child.id()))]
-    fn kill_and_wait_impl(mut child: Child) {
+    #[instrument(skip_all, fields(pid=child.id(), ?cause))]
+    fn kill_and_wait_impl(mut child: Child, cause: WalRedoKillCause) {
+        scopeguard::defer! {
+            WAL_REDO_PROCESS_COUNTERS.killed_by_cause[cause].inc();
+        }
         let res = child.kill();
         if let Err(e) = res {
             // This branch is very unlikely because:
@@ -1086,7 +1090,7 @@ impl Drop for NoLeakChild {
                 // This thread here is going to outlive of our dropper.
                 let span = tracing::info_span!("walredo", %tenant_id);
                 let _entered = span.enter();
-                Self::kill_and_wait_impl(child);
+                Self::kill_and_wait_impl(child, WalRedoKillCause::NoLeakChildDrop);
             })
             .await
         });