storage_controller: start adding chaos hooks (#7946)

Chaos injection bridges the gap between automated testing (where we do
lots of different things with small, short-lived tenants), and staging
(where we do many fewer things, but with larger, long-lived tenants).

This PR adds a first type of chaos which isn't really very chaotic: it's
live migration of tenants between healthy pageservers. This nevertheless
provides continuous checks that things like clean, prompt shutdown of
tenants works for realistically deployed pageservers with realistically
large tenants.

storage_controller/src/service/chaos_injector.rs

@@ -0,0 +1,71 @@
+use std::{sync::Arc, time::Duration};
+
+use rand::seq::SliceRandom;
+use rand::thread_rng;
+use tokio_util::sync::CancellationToken;
+
+use super::Service;
+
+pub struct ChaosInjector {
+    service: Arc<Service>,
+    interval: Duration,
+}
+
+impl ChaosInjector {
+    pub fn new(service: Arc<Service>, interval: Duration) -> Self {
+        Self { service, interval }
+    }
+
+    pub async fn run(&mut self, cancel: CancellationToken) {
+        let mut interval = tokio::time::interval(self.interval);
+
+        loop {
+            tokio::select! {
+                _ = interval.tick() => {}
+                _ = cancel.cancelled() => {
+                    tracing::info!("Shutting down");
+                    return;
+                }
+            }
+
+            self.inject_chaos().await;
+
+            tracing::info!("Chaos iteration...");
+        }
+    }
+
+    async fn inject_chaos(&mut self) {
+        // Pick some shards to interfere with
+        let batch_size = 128;
+        let mut inner = self.service.inner.write().unwrap();
+        let (nodes, tenants, scheduler) = inner.parts_mut();
+        let tenant_ids = tenants.keys().cloned().collect::<Vec<_>>();
+        let victims = tenant_ids.choose_multiple(&mut thread_rng(), batch_size);
+
+        for victim in victims {
+            let shard = tenants
+                .get_mut(victim)
+                .expect("Held lock between choosing ID and this get");
+
+            // Pick a secondary to promote
+            let Some(new_location) = shard
+                .intent
+                .get_secondary()
+                .choose(&mut thread_rng())
+                .cloned()
+            else {
+                tracing::info!("Skipping shard {victim}: no secondary location, can't migrate");
+                continue;
+            };
+
+            let Some(old_location) = *shard.intent.get_attached() else {
+                tracing::info!("Skipping shard {victim}: currently has no attached location");
+                continue;
+            };
+
+            shard.intent.demote_attached(scheduler, old_location);
+            shard.intent.promote_attached(scheduler, new_location);
+            self.service.maybe_reconcile_shard(shard, nodes);
+        }
+    }
+}