Put the process's OS handle count on the sizes line and add a handle census by kind behind NX2NAVI_HANDLE_CENSUS.

A session of 2026-11-13 grew from 683 to 1095 OS handles in 11 minutes, rising at every area load and never falling,
while the guest's own handles stayed at 116-122 and the threads flat; the VMA block count fell back while the handle
count did not. The log could not show it: the 600-frame "mem: sizes" line had only the guest's handles, and nothing
told which kind of handle grows.

kernel.c kern_sizes now adds "process handles" (plat_handle_count, one system call every 600 frames under trace=perf)
beside the guest's "handles". platform.h gets plat_handle_census: on Windows the system's extended handle table
filtered by our process id, with the type names from NtQueryObject's ObjectTypesInformation; on Linux the
/proc/self/fd links grouped by kind. It never opens, duplicates or names a handle (a name query can block on a pipe).
With NX2NAVI_HANDLE_CENSUS=1 (default 0, read at start) and trace=perf, perf.c starts one long-lived thread that the
600-frame report wakes; when the count grew by 16 or more since its last census it logs "mem: handles frame N: T in
all (+D since the last census): Event a (+x), ...". The census reads a few MiB of the system's table in 2-5 ms, off
the drawing threads; one thread for the run keeps a new thread's own handle out of what it counts. New cfg rows:
HANDLE_CENSUS in known[], sections[] (diagnostics) and metas[] ("0", "0|1", restart), and an nx2navi.ini.example
entry.

New tests/handle_census_check.py builds the platform layer alone: 20 events and 5 sections show as Event +20 and
Section +5, the total stays within 2 of GetProcessHandleCount, the figures return once they are closed, and kinds
past the room given go into the last entry; docs/building.md describes it. Not reproduced before the change (the
growth needs a game run). handle_census_check, sync_wake_check and the cfg row check pass; every runtime file compiles
with the dev flags, and perf.c, kernel.c, win32.c and cfg.c add no -Wall -Wextra warnings.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
chrg6
2026-11-13 17:11:52 -05:00
parent baf83fda6a
commit 26b7cfd658
10 changed files with 360 additions and 2 deletions

View File

@@ -538,6 +538,13 @@ int plat_page_file_managed(void);
void plat_process_memory(uint64_t *resident, uint64_t *private_bytes);
// The handles (Windows) or file descriptors (Linux) this process holds; 0 when unknown.
uint32_t plat_handle_count(void);
// The same by kind: Windows the object type of each handle (Event, Section, Thread, File...), Linux what each file
// descriptor's link names (socket, pipe, an anon_inode kind, a /dev folder, file). Fills out with up to max kinds,
// unsorted, and returns how many, -1 on failure; the kinds past max are counted in the last entry, named "(more
// kinds)". Never opens, duplicates or names a handle. Windows reads the system's whole handle table into a buffer of a
// few MiB kept between calls: one thread calls it at a time.
typedef struct { char name[32]; uint32_t n; } PlatHandleKind;
int plat_handle_census(PlatHandleKind *out, int max);
// The C runtime's malloc heap in bytes, for the memory report (vk_memory.c system_log): what it took from the system
// (committed) and what of that it handed out (used), and how many other heaps the process has (Windows: those DLLs made
// with HeapCreate, the graphics driver's among them; their sizes are not asked, as a heap made without serialization