Merge pull request 'store: bound the pool by available memory and let it shrink' (#129) from fix/elc-rebuildable-compiler-builtins into dev

lang/runtime/engram_store.c

@@ -46,6 +46,8 @@
 #include <unistd.h>
 #if defined(__APPLE__) || defined(__MACH__)
 #include <sys/sysctl.h>
+#include <mach/mach.h>
+#include <mach/mach_host.h>
 #endif
 #include <fcntl.h>
 #include <errno.h>
@@ -247,7 +249,8 @@ struct PgCache {
     uint64_t hits, misses, evictions, prefetch_reads;
     /* sliding-window marks so pressure reflects NOW, not lifetime totals */
     uint64_t adapt_last_acc, adapt_last_evic, adapt_last_hits;
-    uint64_t adapt_grows;        /* how many times the budget corrected upward */
+    uint64_t adapt_grows;        /* budget corrections upward   */
+    uint64_t adapt_shrinks;      /* budget corrections downward (memory pressure) */
 };
 
 /* ── little-endian scalar codecs ──────────────────────────────────────────── */
@@ -1685,6 +1688,8 @@ int store_scan_edges(EngramPagedStore* s, StoreEdgeScanCb cb, void* ctx){
 #define ENGRAM_POOL_FRAMES_FALLBACK (1u<<20)   /* ~1M frames × 16KiB = 16 GiB */
 #endif
 
+static uint64_t pc_available_ram(void);   /* fwd — defined with the controller */
+
 /* Physical RAM in bytes, 0 when it cannot be determined. */
 static uint64_t pc_physical_ram(void){
 #if defined(__APPLE__) || defined(__MACH__)
@@ -1707,6 +1712,9 @@ static size_t pc_default_cap(void){
     uint64_t ram = pc_physical_ram();
     if (!ram) return ENGRAM_POOL_FRAMES_FALLBACK;
     uint64_t budget_bytes = (ram / 100u) * pct;
+    /* Never start above what the machine can actually spare right now. */
+    uint64_t avail = pc_available_ram();
+    if (avail > (1ull<<30) && budget_bytes > avail - (1ull<<30)) budget_bytes = avail - (1ull<<30);
     uint64_t frames = budget_bytes / (uint64_t)STORE_PAGE_SIZE;
     if (frames < 4096) frames = 4096;            /* never absurdly small */
     return (size_t)frames;
@@ -1854,6 +1862,67 @@ static void pc_report(const PgCache* c, const char* cause){
 
 static uint64_t pc_ram_bytes_live(void){ return pc_physical_ram(); }
 
+/* AVAILABLE memory right now — free + reclaimable, not total.
+ *
+ * Sizing a cache against TOTAL ram is what turns a cache into a memory leak:
+ * total does not shrink when other processes need memory, so a pool that only
+ * grows never notices it is starving the machine it runs on. Availability does.
+ * Returns 0 when undeterminable — callers then refuse to grow, the safe way. */
+static uint64_t pc_available_ram(void){
+#if defined(__APPLE__) || defined(__MACH__)
+    mach_port_t host = mach_host_self();
+    vm_size_t page = 0;
+    if (host_page_size(host, &page) != KERN_SUCCESS) return 0;
+    vm_statistics64_data_t vm; mach_msg_type_number_t cnt = HOST_VM_INFO64_COUNT;
+    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;
+    return avail * (uint64_t)page;
+#else
+    FILE* f = fopen("/proc/meminfo", "r");
+    if (!f) return 0;
+    char line[256]; unsigned long long kb = 0;
+    while (fgets(line, sizeof line, f))
+        if (sscanf(line, "MemAvailable: %llu kB", &kb) == 1) break;
+    fclose(f);
+    return (uint64_t)kb * 1024ull;
+#endif
+}
+
+/* Shrink the budget when the machine is short on memory.
+ *
+ * A pool that can only grow is a leak with extra steps. This is the other half
+ * of the control loop: if free memory drops below a floor, hand frames back.
+ * The resident set follows on the next eviction pass, so the memory is actually
+ * returned rather than merely re-labelled. */
+#ifndef ENGRAM_POOL_FREE_FLOOR_BYTES
+#define ENGRAM_POOL_FREE_FLOOR_BYTES (2ull*1024ull*1024ull*1024ull)   /* 2 GiB */
+#endif
+static int pc_relieve_pressure(PgCache* c){
+    uint64_t avail = pc_available_ram();
+    if (!avail) return 0;
+    uint64_t floor_b = ENGRAM_POOL_FREE_FLOOR_BYTES;
+    const char* fe = getenv("ENGRAM_POOL_FREE_FLOOR_MB");
+    if (fe && *fe){ unsigned long v = strtoul(fe, NULL, 10); if (v) floor_b = (uint64_t)v * 1024ull * 1024ull; }
+    if (avail >= floor_b) return 0;                 /* machine has room */
+    if (!c->cap || c->count == 0) return 0;
+    size_t was = c->cap;
+    size_t want = c->count - (c->count / 4);        /* give back ~25% of what we hold */
+    if (want < 4096) want = 4096;
+    if (want >= c->cap) return 0;
+    c->cap = want;
+    c->adapt_shrinks++;
+    fprintf(stderr,
+        "[engram] memory pressure: %.2f GiB available (floor %.2f GiB) — shrinking pool "
+        "budget %zu -> %zu frames (%.2f -> %.2f GiB) and releasing frames.\n",
+        (double)avail/(1024.0*1024.0*1024.0), (double)floor_b/(1024.0*1024.0*1024.0),
+        was, c->cap,
+        (double)was   * (double)STORE_PAGE_SIZE/(1024.0*1024.0*1024.0),
+        (double)c->cap* (double)STORE_PAGE_SIZE/(1024.0*1024.0*1024.0));
+    fflush(stderr);
+    return 1;
+}
+
 static void pc_adapt_budget(PgCache* c){
     if (!c->cap) return;                     /* unlimited: nothing to adapt */
     if (getenv("ENGRAM_POOL_FRAMES")) return; /* explicit operator override wins */
@@ -1872,12 +1941,26 @@ static void pc_adapt_budget(PgCache* c){
     if (d_evic * 3 < d_acc) return;          /* < 1/3 of accesses evict: healthy */
     if (d_hits * 4 < d_acc) return;          /* little reuse: a scan, not pressure */
 
-    uint64_t ram = pc_ram_bytes_live();       /* live, not a boot-time constant */
+    /* Growth is bounded by what is AVAILABLE, never by total RAM. Sizing against
+     * total is how a cache starves its own host: total never shrinks when other
+     * processes need memory. Refuse to grow at all if availability is unknown or
+     * already under the floor — a cache is never worth swapping the machine. */
+    uint64_t avail = pc_available_ram();
+    uint64_t floor_b = ENGRAM_POOL_FREE_FLOOR_BYTES;
+    const char* fe = getenv("ENGRAM_POOL_FREE_FLOOR_MB");
+    if (fe && *fe){ unsigned long v = strtoul(fe, NULL, 10); if (v) floor_b = (uint64_t)v * 1024ull * 1024ull; }
+    if (!avail || avail <= floor_b) return;
+    uint64_t ram = pc_ram_bytes_live();
     if (!ram) return;
-    unsigned pct = 80;                        /* hard ceiling for autonomous growth */
+    unsigned pct = 50;                        /* ceiling as a share of TOTAL, belt-and-braces */
     const char* mp = getenv("ENGRAM_POOL_MAX_PCT");
     if (mp && *mp){ unsigned long v = strtoul(mp, NULL, 10); if (v > 0 && v <= 95) pct = (unsigned)v; }
     size_t ceiling = (size_t)(((ram / 100u) * pct) / (uint64_t)STORE_PAGE_SIZE);
+    /* and never grow into the free-memory floor */
+    uint64_t headroom = avail - floor_b;
+    size_t   ceil_avail = (size_t)((c->count * (uint64_t)STORE_PAGE_SIZE + headroom)
+                                   / (uint64_t)STORE_PAGE_SIZE);
+    if (ceil_avail < ceiling) ceiling = ceil_avail;
     if (c->cap >= ceiling) return;            /* already at the machine's limit */
 
     size_t want = c->cap + (c->cap / 2) + 1;  /* ×1.5, geometric */
@@ -1908,7 +1991,7 @@ static void pc_evict_to_budget(PgCache* c){
         }
         if (!freed) break;                  /* nothing evictable — allowed to exceed cap */
     }
-    pc_adapt_budget(c);
+    if (!pc_relieve_pressure(c)) pc_adapt_budget(c);
 }
 
 static PgEnt* pc_get(EngramPagedStore* s, uint64_t id){