Right-size nRF52 heap tiers after 2.8.0 heap-exhaustion field reports

src/MessageStore.h

@@ -21,10 +21,12 @@
 // How many messages are stored (RAM + flash).
 // Define -DMESSAGE_HISTORY_LIMIT=N in build_flags to control memory usage.
 #ifndef MESSAGE_HISTORY_LIMIT
-#if defined(ARCH_ESP32) &&                                                                                                       \
-    !(defined(CONFIG_IDF_TARGET_ESP32C3) || defined(CONFIG_IDF_TARGET_ESP32S3) || defined(CONFIG_IDF_TARGET_ESP32S2))
-// Baseline ESP32 (non-PSRAM variants) has limited heap; reduce message history on resource-constrained builds.
-// Override with -DMESSAGE_HISTORY_LIMIT=N if needed.
+#if (defined(ARCH_ESP32) &&                                                                                                      \
+     !(defined(CONFIG_IDF_TARGET_ESP32C3) || defined(CONFIG_IDF_TARGET_ESP32S3) || defined(CONFIG_IDF_TARGET_ESP32S2))) ||       \
+    defined(NRF52840_XXAA)
+// Baseline ESP32 (non-PSRAM variants) and nRF52840 (~115 KB heap arena shared with SoftDevice +
+// FreeRTOS stacks; 2.8.0 field reports hit 99% use) have limited heap; reduce message history on
+// resource-constrained builds. Override with -DMESSAGE_HISTORY_LIMIT=N if needed.
 #define MESSAGE_HISTORY_LIMIT 10
 #else
 #define MESSAGE_HISTORY_LIMIT 20

src/mesh/mesh-pb-constants.h

@@ -17,6 +17,12 @@
 #ifndef MAX_RX_TOPHONE
 #if defined(ARCH_ESP32) && !(defined(CONFIG_IDF_TARGET_ESP32C3) || defined(CONFIG_IDF_TARGET_ESP32S3))
 #define MAX_RX_TOPHONE 8
+#elif defined(NRF52840_XXAA)
+// Each slot is a ~340 B MeshPacket in the static pool (Router.cpp MAX_PACKETS_STATIC), so 32 slots
+// cost ~11 KB of .bss on the RAM-tightest platform (2.8.0 field reports: 99% heap). 16 still doubles
+// the 8 classic ESP32 has shipped with for years; drops start when a stalled phone/serial client has
+// 16 packets queued.
+#define MAX_RX_TOPHONE 16
 #else
 #define MAX_RX_TOPHONE 32
 #endif
@@ -126,7 +132,10 @@ static inline int get_max_num_nodes()
 // Keyed on the NRF52840_XXAA build flag, not ARCH_NRF52: the latter (from
 // architecture.h via configuration.h) isn't defined this early in every include
 // chain. Backed by the raw-flash ring below LittleFS - see WarmNodeStore.h.
-#define WARM_NODE_COUNT 200
+// 100 (was 200): the RAM cache is 40 B/entry calloc'd from the ~115 KB heap
+// arena, which 2.8.0 field reports showed at 99% use; 120 hot + 100 warm
+// identities still covers meshes well past the hot cap.
+#define WARM_NODE_COUNT 100
 #elif (defined(CONFIG_IDF_TARGET_ESP32S3) && defined(BOARD_HAS_PSRAM)) || defined(ARCH_PORTDUINO)
 #define WARM_NODE_COUNT 2000 // PSRAM-equipped ESP32-S3 / native host; warm cache in PSRAM (~80 KB)
 #elif defined(CONFIG_IDF_TARGET_ESP32S3) || defined(CONFIG_IDF_TARGET_ESP32C6) || defined(CONFIG_IDF_TARGET_ESP32P4)
@@ -136,10 +145,11 @@ static inline int get_max_num_nodes()
 #elif defined(ARCH_RP2040)
 #define WARM_NODE_COUNT 150 // RP2040 (264 KB) / RP2350 (520 KB): bounded so warm.dat write fits the 8s watchdog (#10746)
 #else
-// nRF52840 is handled explicitly above (200, raw-flash ring). Any other nRF52 (non-XXAA) and any
-// future non-ESP32/non-RP LittleFS part fall through to this 320 default - flag for review if such a
-// RAM-constrained nRF52 target is ever added.
-#define WARM_NODE_COUNT 320 // other LittleFS-backed parts (e.g. non-nRF52840 nRF52)
+// nRF52840 is handled explicitly above (raw-flash ring). Any other nRF52 (non-XXAA) and any future
+// non-ESP32/non-RP LittleFS part lands here. Reviewed after the 2.8.0 nRF52840 heap-exhaustion
+// reports: fail small (match nRF52840) so an unclassified RAM-constrained part can't boot-allocate
+// 12.8 KB; RAM-rich targets should opt up explicitly in their variant.
+#define WARM_NODE_COUNT 100 // other LittleFS-backed parts (e.g. non-nRF52840 nRF52)
 #endif                      // platform
 #endif                      // WARM_NODE_COUNT
 
@@ -177,11 +187,16 @@ static inline int get_max_num_nodes()
 #define TRAFFIC_MANAGEMENT_CACHE_SIZE 500 // 512 KB+ SRAM, no PSRAM (S3/C6/P4): ~5 KB heap (#10705)
 #elif defined(ARCH_ESP32)
 #define TRAFFIC_MANAGEMENT_CACHE_SIZE 400 // classic ESP32 / S2 / C3: tightest free heap, ~4 KB (#10705)
+#elif defined(NRF52840_XXAA)
+// Keyed on NRF52840_XXAA (not ARCH_NRF52) for the same include-order reason as WARM_NODE_COUNT above.
+// The 256 KB part shares its ~115 KB heap arena with SoftDevice and the FreeRTOS task stacks; 2.8.0
+// field reports hit 99% heap use with the old 1000-entry (~10 KB) cache. 250 entries (2.5 KB) still
+// tracks >2x the 120-node hot store; LRU victim recycling absorbs busier meshes.
+#define TRAFFIC_MANAGEMENT_CACHE_SIZE 250
 #else
-// nRF52 (incl. nRF52840) and RP2040/RP2350 fall through here - there is no nRF/RP branch above,
-// by design. These parts have no ESP32-style WiFi+BLE coexistence eating the heap, so the larger
-// 1000-entry (~10 KB) cache fits: nRF52840 is BLE-only on 256 KB RAM; RP2040/RP2350 have 264/520 KB.
-#define TRAFFIC_MANAGEMENT_CACHE_SIZE 1000 // nRF52 / RP2040 / RP2350 / other non-ESP32
+// RP2040/RP2350 and anything unclassified land here: match the classic-ESP32 tier rather than
+// defaulting large. RAM-rich targets should opt up explicitly in their variant.
+#define TRAFFIC_MANAGEMENT_CACHE_SIZE 400
 #endif
 #endif // TRAFFIC_MANAGEMENT_CACHE_SIZE
 

test/test_warm_store/test_main.cpp

@@ -257,6 +257,50 @@ void test_ws_v1_migration_discardsLastHeard()
     b.saveIfDirty();
 }
 
+// Shrink safety: a warm.dat snapshot recording more entries than this build's
+// WARM_NODE_COUNT (e.g. written before a per-platform tier reduction) must be
+// rejected cleanly at the header check - load() starts empty instead of reading
+// past entries[]. (The nRF52840 raw-flash ring backend has no such cliff: it
+// replays records through place(), whose LRU admission keeps the newest.)
+void test_ws_load_rejectsOversizedSnapshot()
+{
+    WarmNodeStore a;
+    a.absorb(0xA00, 111, NULL);
+    if (!a.saveIfDirty()) {
+        TEST_IGNORE_MESSAGE("Filesystem not available in this test environment");
+        return;
+    }
+
+    // Patch the header's count field (offset 8) to one past capacity.
+    std::vector<uint8_t> buf;
+    {
+        auto f = FSCom.open("/prefs/warm.dat", FILE_O_READ);
+        if (!f) {
+            TEST_IGNORE_MESSAGE("warm.dat not readable in this environment");
+            return;
+        }
+        buf.resize(f.size());
+        f.read(buf.data(), buf.size());
+        f.close();
+    }
+    TEST_ASSERT_TRUE(buf.size() >= 16);
+    const uint16_t oversized = (uint16_t)(WARM_NODE_COUNT + 1);
+    memcpy(buf.data() + 8, &oversized, sizeof(oversized));
+    {
+        auto f = FSCom.open("/prefs/warm.dat", FILE_O_WRITE);
+        TEST_ASSERT_TRUE((bool)f);
+        f.write(buf.data(), buf.size());
+        f.close();
+    }
+
+    WarmNodeStore b;
+    b.load();
+    TEST_ASSERT_EQUAL(0, b.count()); // rejected as invalid, started empty
+
+    b.clear();
+    b.saveIfDirty();
+}
+
 WS_TEST_ENTRY void setup()
 {
     initializeTestEnvironment();
@@ -273,6 +317,7 @@ WS_TEST_ENTRY void setup()
     RUN_TEST(test_ws_remove_and_clear);
     RUN_TEST(test_ws_persistence_roundTrip);
     RUN_TEST(test_ws_v1_migration_discardsLastHeard);
+    RUN_TEST(test_ws_load_rejectsOversizedSnapshot);
     exit(UNITY_END());
 }
 

variants/nrf52840/heltec_mesh_node_t096/platformio.ini

@@ -15,6 +15,7 @@ board_level = pr
 debug_tool = jlink
 
 build_flags = ${nrf52840_base.build_flags}
+  -UOLEDDISPLAY_REDUCE_MEMORY ; TFTDisplay.cpp needs the lib's buffer_back for dirty-window diffing
   -Ivariants/nrf52840/heltec_mesh_node_t096
   -D HAS_LORA_FEM=1
   -D HELTEC_MESH_NODE_T096

variants/nrf52840/heltec_mesh_node_t1/platformio.ini

@@ -15,6 +15,7 @@ board_level = pr
 debug_tool = jlink
 
 build_flags = ${nrf52840_base.build_flags}
+  -UOLEDDISPLAY_REDUCE_MEMORY ; TFTDisplay.cpp needs the lib's buffer_back for dirty-window diffing
   -Ivariants/nrf52840/heltec_mesh_node_t1
   -DHELTEC_MESH_NODE_T1
   -DUSE_TFTDISPLAY

variants/nrf52840/heltec_mesh_node_t114/platformio.ini

@@ -18,7 +18,6 @@ debug_tool = jlink
 build_flags = ${nrf52840_base.build_flags}
   -Ivariants/nrf52840/heltec_mesh_node_t114
   -DHELTEC_T114
-  -DOLEDDISPLAY_REDUCE_MEMORY
 
 build_src_filter = ${nrf52_base.build_src_filter} +<../variants/nrf52840/heltec_mesh_node_t114>
 lib_deps = 

variants/nrf52840/heltec_mesh_solar/platformio.ini

@@ -107,7 +107,6 @@ extends = heltec_mesh_solar_base
 build_flags = ${heltec_mesh_solar_base.build_flags}
   -DHELTEC_MESH_SOLAR_TFT
   -DSPI_INTERFACES_COUNT=2
-  -DOLEDDISPLAY_REDUCE_MEMORY
   -DHAS_SPI_TFT=1
   -DUSE_ST7789
   -DST7789_NSS=41

variants/nrf52840/nrf52.ini

@@ -26,6 +26,8 @@ build_flags =
   -DLFS_NO_ASSERT                      ; Disable LFS assertions , see https://github.com/meshtastic/firmware/pull/3818
   -DMESHTASTIC_EXCLUDE_AUDIO=1
   -DMESHTASTIC_EXCLUDE_PAXCOUNTER=1
+  -DMESHTASTIC_EXCLUDE_PKT_HISTORY_HASH=1 ; drop PacketHistory's 1 KB hash index; O(n) over ~240 records is negligible at LoRa packet rates
+  -DOLEDDISPLAY_REDUCE_MEMORY          ; drop the ThingPulse OLED back buffer (~1 KB); TFT variants must -U this (TFTDisplay.cpp needs buffer_back)
   -Os
   -std=gnu++17
   -flto                 ; whole-image LTO (~-60KB) on every nrf52840 target; nrf52_lto.py (pre: extra_script) keeps the interrupt handlers out of LTO so they survive

variants/nrf52840/rak_wismeshtap/platformio.ini

@@ -12,6 +12,7 @@ custom_meshtastic_tags = RAK
 extends = nrf52840_base
 board = wiscore_rak4631
 build_flags = ${nrf52840_base.build_flags}
+  -UOLEDDISPLAY_REDUCE_MEMORY ; TFTDisplay.cpp needs the lib's buffer_back for dirty-window diffing
   -Ivariants/nrf52840/rak_wismeshtap
   -DWISMESH_TAP
   -DRAK_4631

variants/nrf52840/tracker-t1000-e/variant.h

@@ -154,15 +154,6 @@ extern "C" {
 
 #define HAS_SCREEN 0
 
-// Enable Traffic Management Module for testing on T1000-E
-// NRF52840 has 256KB RAM - 1024 entries uses ~10KB
-#ifndef HAS_TRAFFIC_MANAGEMENT
-#define HAS_TRAFFIC_MANAGEMENT 1
-#endif
-#ifndef TRAFFIC_MANAGEMENT_CACHE_SIZE
-#define TRAFFIC_MANAGEMENT_CACHE_SIZE 1024
-#endif
-
 #ifdef __cplusplus
 }
 #endif