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:
chrg6
2026-11-10 19:27:58 -05:00
parent a33135c435
commit 66aedffcdd
8 changed files with 103 additions and 8 deletions

View File

@@ -152,7 +152,9 @@ static size_t tracked_decode(Cpu *c, uint64_t dst, uint64_t cap, uint64_t src, u
if (d) __atomic_store_n(d, *d + 1, __ATOMIC_RELAXED);
int away = size >= AWAY_BYTES ? kern_core_away() : 0;
if (away) __atomic_add_fetch(&S.away, 1, __ATOMIC_RELAXED);
uint64_t t0 = perf_mark_begin();
size_t r = host_decode(dst, cap, src, size, dict, dict_size, ddict, ok);
perf_mark_end(PERF_M_ZSTD, t0, *ok && !ZSTD_isError(r) ? r : 0);
kern_core_back(&away);
if (d) {
int n = *d - 1;
@@ -372,12 +374,14 @@ static size_t stream_run(Cpu *c, Stream *st, ZSTD_outBuffer *out, ZSTD_inBuffer
if (d) __atomic_store_n(d, *d + 1, __ATOMIC_RELAXED);
int away = in->size >= AWAY_BYTES ? kern_core_away() : 0;
if (away) __atomic_add_fetch(&S.away, 1, __ATOMIC_RELAXED);
size_t r = 1;
size_t r = 1, o_start = out->pos;
uint64_t t0 = perf_mark_begin();
while (in->pos < in->size) {
size_t i0 = in->pos, o0 = out->pos;
r = ZSTD_decompressStream(st->dctx, out, in);
if (ZSTD_isError(r) || !r || (in->pos == i0 && out->pos == o0)) break;
}
perf_mark_end(PERF_M_ZSTD, t0, out->pos - o_start);
kern_core_back(&away);
if (d) {
int n = *d - 1;