mirror of
https://github.com/tangerineturtle1/NX2navi.git
synced 2026-11-16 15:59:59 -04:00
Name the work behind each frame on any thread under the perf trace: RomFS reads, zstd decodes, pipeline creates, guest memory maps, pool initialize and finalize, and device memory allocations.
A slow frame's line and the 60-frame window's line now say how long each kind took on any thread, how often, how many bytes and the longest single one, so a hitch outside the render thread's own waits has a named cause. While NX2NAVI_TRACE=perf is off each site pays one branch. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -895,6 +895,7 @@ uint32_t mem_map_gen(void) { return __atomic_load_n(&map_gen, __ATOMIC_ACQUIRE);
|
||||
|
||||
// ---- 0x01 SetHeapSize
|
||||
uint32_t mem_set_heap_size(uint64_t size, uint64_t *addr) {
|
||||
uint64_t t0 = perf_mark_begin(); // NX2NAVI_TRACE=perf: the commit or decommit, the wait for the lock included
|
||||
plat_mutex_lock(&lock);
|
||||
if (size > HEAP_CAP || size % 0x200000 || size + image_bytes() > L.pool) {
|
||||
plat_mutex_unlock(&lock);
|
||||
@@ -902,9 +903,11 @@ uint32_t mem_set_heap_size(uint64_t size, uint64_t *addr) {
|
||||
}
|
||||
if (size > heap_size) commit(L.heap.base + heap_size, size - heap_size, "heap");
|
||||
if (size < heap_size) decommit(L.heap.base + size, heap_size - size, "heap");
|
||||
uint64_t moved = size > heap_size ? size - heap_size : heap_size - size;
|
||||
heap_size = size;
|
||||
__atomic_store_n(&map_gen, map_gen + 1, __ATOMIC_RELEASE);
|
||||
plat_mutex_unlock(&lock);
|
||||
perf_mark_end(PERF_M_GMEM, t0, moved);
|
||||
if (addr) *addr = L.heap.base;
|
||||
return R_OK;
|
||||
}
|
||||
@@ -1061,7 +1064,7 @@ static uint32_t alias_map(int unmap, uint64_t a, uint64_t n) {
|
||||
n = (n + PAGE - 1) & ~(uint64_t)(PAGE - 1); // the SDK asks for byte ranges; a mapping is whole pages
|
||||
if ((a | n) & (PAGE - 1)) return R_INVALID_ADDRESS;
|
||||
if (!inside(a, n, L.alias)) return R_INVALID_REGION;
|
||||
uint64_t first = (a - L.alias.base) / PAGE, count = n / PAGE;
|
||||
uint64_t first = (a - L.alias.base) / PAGE, count = n / PAGE, t0 = perf_mark_begin();
|
||||
plat_mutex_lock(&lock);
|
||||
uint32_t r = R_OK;
|
||||
if (unmap) {
|
||||
@@ -1087,6 +1090,7 @@ static uint32_t alias_map(int unmap, uint64_t a, uint64_t n) {
|
||||
out:
|
||||
__atomic_store_n(&map_gen, map_gen + 1, __ATOMIC_RELEASE);
|
||||
plat_mutex_unlock(&lock);
|
||||
perf_mark_end(PERF_M_GMEM, t0, n);
|
||||
if (r) rt_log("%sMapPhysicalMemory %#llx+%#llx failed %#x (alias %#llx used, heap %#llx)", unmap ? "Un" : "",
|
||||
(unsigned long long)a, (unsigned long long)n, r, (unsigned long long)alias_bytes,
|
||||
(unsigned long long)heap_size);
|
||||
|
||||
Reference in New Issue
Block a user