Merge pull request 'store: judge memory pressure by swap RATE, not level' (#130) from fix/elc-rebuildable-compiler-builtins into dev

lang/runtime/engram_store.c

@@ -1870,6 +1870,53 @@ static uint64_t pc_ram_bytes_live(void){ return pc_physical_ram(); }
  * Returns 0 when undeterminable — callers then refuse to grow, the safe way. */
 static uint64_t pc_available_ram(void){
 #if defined(__APPLE__) || defined(__MACH__)
+    /* SWAP AND COMPRESSOR FIRST. free+inactive+purgeable is a LIE under memory
+     * pressure: a machine deep in swap still reports gigabytes "available",
+     * because inactive pages are only reclaimable by evicting them to swap.
+     * Observed 2026-08-15: this returned 9.43 GiB available while vm.swapusage
+     * showed 51.58 of 53.25 GiB used (97% full) and the compressor occupied
+     * 23.7 GiB — the host was thrashing to disk and the pool would have been
+     * cleared to grow into it. Growing a cache in that state is how a guard
+     * becomes the crash.
+     *
+     * So: if swap is nearly spent, report ZERO available. Callers refuse to
+     * grow on 0 and pc_relieve_pressure hands frames back. Only when the
+     * machine is genuinely not swapping do free+inactive+purgeable mean
+     * anything, and even then the compressor's footprint is subtracted because
+     * that RAM is already spoken for. */
+    /* RATE, NOT LEVEL. Swap *level* is a terrible signal: macOS grows swap files
+     * on demand and reclaims them lazily, so "47 of 48 GiB used" can mean the
+     * machine is dying OR that it recovered ten minutes ago and the file has not
+     * been trimmed yet. Measured both states on one host within minutes:
+     *   47.65/48.00 GiB used, 2047 swapouts/s  -> genuinely thrashing
+     *   26.67/28.00 GiB used,    0 swapouts/s  -> perfectly healthy, 15.6 GiB free
+     * A level check calls the second one an emergency and starves the pool for
+     * no reason. What distinguishes them is whether pages are moving NOW.
+     *
+     * So sample the swapout counter across calls and judge the delta. First call
+     * establishes the baseline and reports no pressure — one sample cannot have
+     * a rate, and guessing from a single reading is the whole mistake. */
+    {
+        static uint64_t prev_swapouts = 0;
+        static time_t   prev_t = 0;
+        static int      primed = 0;
+        mach_port_t h0 = mach_host_self();
+        vm_statistics64_data_t v0; mach_msg_type_number_t c0 = HOST_VM_INFO64_COUNT;
+        if (host_statistics64(h0, HOST_VM_INFO64, (host_info64_t)&v0, &c0) == KERN_SUCCESS){
+            uint64_t now_out = (uint64_t)v0.swapouts;
+            time_t   now_t   = time(NULL);
+            if (!primed){ prev_swapouts = now_out; prev_t = now_t; primed = 1; }
+            else if (now_t > prev_t){
+                double per_s = (double)(now_out - prev_swapouts) / (double)(now_t - prev_t);
+                prev_swapouts = now_out; prev_t = now_t;
+                /* Sustained outward paging with nothing coming back is the
+                 * signature of a host being pushed into swap. ~200 pages/s is
+                 * ~3 MiB/s — well above idle noise, well below the 2000+/s seen
+                 * while actually thrashing. */
+                if (per_s > 200.0) return 0;
+            }
+        }
+    }
     mach_port_t host = mach_host_self();
     vm_size_t page = 0;
     if (host_page_size(host, &page) != KERN_SUCCESS) return 0;
@@ -1877,6 +1924,10 @@ static uint64_t pc_available_ram(void){
     if (host_statistics64(host, HOST_VM_INFO64, (host_info64_t)&vm, &cnt) != KERN_SUCCESS) return 0;
     uint64_t avail = (uint64_t)vm.free_count + (uint64_t)vm.inactive_count
                    + (uint64_t)vm.purgeable_count;
+    /* the compressor is holding real RAM that nobody can hand us */
+    uint64_t compressed = (uint64_t)vm.compressor_page_count;
+    if (compressed >= avail) return 0;
+    avail -= compressed;
     return avail * (uint64_t)page;
 #else
     FILE* f = fopen("/proc/meminfo", "r");