Scheduler: oversubscribe cores just a little to make up for slack

...not by factor of 10 as it was done previously

src/bin/sccache-dist/main.rs

@@ -309,7 +309,7 @@ fn init_logging() {
     }
 }
 
-const MAX_PER_CORE_LOAD: f64 = 10f64;
+const MAX_PER_CORE_LOAD: f64 = 2f64;
 const SERVER_REMEMBER_ERROR_TIMEOUT: Duration = Duration::from_secs(300);
 const UNCLAIMED_PENDING_TIMEOUT: Duration = Duration::from_secs(300);
 const UNCLAIMED_READY_TIMEOUT: Duration = Duration::from_secs(60);
@@ -399,6 +399,17 @@ impl Default for Scheduler {
     }
 }
 
+fn load_weight(job_count: usize, core_count: usize) -> f64 {
+    // Do not oversubscribe cores very much to avoid out of memory situations and cache thrashing -
+    // oversubscribe just a little to make up for network and other latency.
+    let cores_plus_slack = core_count + 1 + core_count / 8;
+    if job_count > cores_plus_slack {
+        MAX_PER_CORE_LOAD + 1f64 // no new jobs for now
+    } else {
+        job_count as f64 / core_count as f64
+    }
+}
+
 impl SchedulerIncoming for Scheduler {
     fn handle_alloc_job(
         &self,
@@ -415,7 +426,7 @@ impl SchedulerIncoming for Scheduler {
                 let mut best_load: f64 = MAX_PER_CORE_LOAD;
                 let now = Instant::now();
                 for (&server_id, details) in servers.iter_mut() {
-                    let load = details.jobs_assigned.len() as f64 / details.num_cpus as f64;
+                    let load = load_weight(details.jobs_assigned.len(), details.num_cpus);
 
                     if let Some(last_error) = details.last_error {
                         if load < MAX_PER_CORE_LOAD {