MacKwnoX/NX2navi
1
0
Fork 0
mirror of https://github.com/tangerineturtle1/NX2navi.git synced 2026-11-15 19:19:58 -04:00
Code Issues Packages Projects Releases Wiki Activity

Count the page generation tables in trace=perf's "mem: sizes" line, so a play-test shows what the 64-bit generations cost in host memory.

Browse Source 
The tables of page write generations take 8 bytes a page since the generations became 64-bit: each 256 MiB chunk of
guest address space stamped is 512 KiB a table instead of 256 KiB, and reg_max and creg_max are 2 MiB each. The
estimate for an outdoor area was 27 MiB of chunks at most, with less resident, but nothing in a log said how many
chunks a session allocates. slot_in now counts them (under gen_lock, an atomic add read without the lock), and
vk_mem_sizes adds "page generation table chunks N, X MiB" after "page generations handed out": the chunks of both
tables and the two per-region arrays, as allocated (only the pages that hold stamps become resident).

Only trace=perf logs the line; slot_in allocates a chunk a few dozen times a session. Checks that passed:
pass_cc_check on vk_memory.c, no new -Wall -Wextra warnings, gen_wrap_check, gen_width_check.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
chrg6
2026-11-13 18:57:56 -05:00
parent 6b95c867c8
commit 028a6ce128
1 changed files with 7 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
runtime/vk_memory.c
View File

@@ -1171,6 +1171,7 @@ int vk_mem_vram_live(uint64_t *used, uint64_t *budget) {
#define GEN_PER_CHUNK (1u << (GEN_CHUNK_SHIFT - GEN_PAGE_SHIFT))
static uint64_t *gen_chunk[GEN_CHUNKS];
static uint64_t gen_now; // last generation handed out (gen_lock; read without it atomically)
static uint32_t n_gen_chunks; // chunks slot_in allocated, both tables (gen_lock; vk_mem_sizes reads it)
static PlatMutex gen_lock = PLAT_MUTEX_INIT;
static uint64_t gen_pages[1024];
// lazy_clean, cpu_wrote_since, verify_cb and vk_mem_sizes read generations without gen_lock: 64-bit loads and stores
@@ -1281,6 +1282,7 @@ static uint64_t *slot_in(uint64_t **tab, uint64_t page_addr, int create) {
if (!p) rt_fatal("vk: out of memory for page generations");
// published with release: lazy_clean and cpu_wrote_since load the chunk pointers without gen_lock
__atomic_store_n(&tab[ci], p, __ATOMIC_RELEASE);
__atomic_add_fetch(&n_gen_chunks, 1, __ATOMIC_RELAXED);
}
return &tab[ci][(page_addr >> GEN_PAGE_SHIFT) & (GEN_PER_CHUNK - 1)];
}
@@ -6277,4 +6279,9 @@ void vk_mem_sizes(PerfSizes *s) {
perf_size(s, "shadow base copies", sb, 0, sb * SB_PAGE);
// the page generations handed out so far (gen_now, 64 bits: they do not run out)
perf_size(s, "page generations handed out", (uint64_t)__atomic_load_n(&gen_now, __ATOMIC_RELAXED), 0, PERF_SIZE_NONE);
// their tables: the chunks of both (8 bytes a page of each 256 MiB of guest address space stamped, allocated in
// full though only the pages holding stamps become resident) and the per-region maxima reg_max and creg_max
uint64_t gch = __atomic_load_n(&n_gen_chunks, __ATOMIC_RELAXED);
perf_size(s, "page generation table chunks", gch, 0,
gch * GEN_PER_CHUNK * sizeof **gen_chunk + sizeof reg_max + sizeof creg_max);
}