mirror of
https://github.com/tangerineturtle1/NX2navi.git
synced 2026-11-18 02:39:57 -04:00
Merge the stability and memory pass into the 0.10.0 line.
Conflicts: the settings key lists and section maps take both sides' entries. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
This commit is contained in:
@@ -3068,6 +3068,41 @@ static void commit_evict(void) { // tex_lock held, the commit is low and the r
|
||||
if (freed < COMMIT_EVICT_STEP) evict_disused(COMMIT_EVICT_STEP - freed);
|
||||
}
|
||||
|
||||
// The released entries hold more than their bound (released_cap_bytes) after drop_stale took what it may: one line that
|
||||
// says what keeps the rest, at most every REL_CENSUS_SUBS submissions and REL_CENSUS_LINES times a run. The bound is
|
||||
// no bound for an entry a lookup still reaches, and the pool stamps every GPU-owned entry that a slot's last fill
|
||||
// resolved to in each submission (pool_touch), a finalized slot's released one too: at 5120x2160 a session's log had
|
||||
// 989 and then 2,172 released entries holding 9.2 and 10.1 GiB against a bound of 4,008 MiB, and its overwritten
|
||||
// render targets "last used 1 presents ago". Each entry counts once, under the first reason that holds.
|
||||
#define REL_CENSUS_SUBS 3600
|
||||
#define REL_CENSUS_LINES 24
|
||||
static void rel_census(uint64_t cap) { // tex_lock held
|
||||
static uint32_t last, lines;
|
||||
if (lines >= REL_CENSUS_LINES || (last && submit_epoch - last < REL_CENSUS_SUBS)) return;
|
||||
last = submit_epoch ? submit_epoch : 1, lines++;
|
||||
uint64_t now = __atomic_load_n(&gfx_counters.frames, __ATOMIC_RELAXED);
|
||||
enum { YOUNG, SLOT, SLOT_OVER, SAMPLED, LOOKED, NEXT, KINDS };
|
||||
uint64_t by[KINDS] = {0}, gpu = 0;
|
||||
int n[KINDS] = {0}, ngpu = 0;
|
||||
for (const Tex *e = rel_head; e; e = e->rel_next) {
|
||||
if (!e->bytes) continue;
|
||||
int shown = e->ph && pref[e->ph - 1].refs;
|
||||
int k = now - e->rel_frame < stale_after(e) ? YOUNG
|
||||
: now - e->samp_frame < STALE_FRAMES ? SAMPLED
|
||||
: shown ? (e->overwritten ? SLOT_OVER : SLOT)
|
||||
: !e->overwritten && !idle(e, now) ? LOOKED : NEXT;
|
||||
by[k] += e->bytes, n[k]++;
|
||||
if (!comes_back_intact(e)) gpu += e->bytes, ngpu++;
|
||||
}
|
||||
const double M = 1048576.0;
|
||||
rt_log("vk: released textures over their bound: %d entries, %.0f MiB of %.0f MiB (%d of them, %.0f MiB, hold content "
|
||||
"only the GPU made): %d, %.0f MiB, released too lately to go; %d, %.0f MiB, sampled or drawn into lately; %d, "
|
||||
"%.0f MiB, shown by a texture pool slot and not sampled, and %d more, %.0f MiB, that another target was drawn "
|
||||
"over; %d, %.0f MiB, reached by another lookup; %d, %.0f MiB, next to go", nreleased, rel_bytes / M, cap / M,
|
||||
ngpu, gpu / M, n[YOUNG], by[YOUNG] / M, n[SAMPLED], by[SAMPLED] / M, n[SLOT], by[SLOT] / M, n[SLOT_OVER],
|
||||
by[SLOT_OVER] / M, n[LOOKED], by[LOOKED] / M, n[NEXT], by[NEXT] / M);
|
||||
}
|
||||
|
||||
static void sweep_pressure(void) { // tex_lock held
|
||||
if (vram_pressure < 0) {
|
||||
const char *s = cfg_get("NX2NAVI_TEX_VRAM_PRESSURE");
|
||||
@@ -3128,6 +3163,7 @@ static void sweep_pressure(void) { // tex_lock held
|
||||
drop_overwritten();
|
||||
uint64_t cap = released_cap_bytes();
|
||||
if (rel_bytes > cap) drop_stale(cap, &n_cap_drops, DROP_CAP);
|
||||
if (cap != UINT64_MAX && rel_bytes > cap + cap / 4) rel_census(cap); // well over it still: what holds the rest
|
||||
if (rel_bytes > COMMIT_LOW_KEEP && low && !held)
|
||||
more = drop_stale(COMMIT_LOW_KEEP, &n_commit_drops, DROP_COMMIT) == PRESSURE_STEP;
|
||||
}
|
||||
@@ -3533,8 +3569,9 @@ static void upload(Tex *e) {
|
||||
}
|
||||
int check = bc1 || try1;
|
||||
// A CPU decode or copy stages at most UPLOAD_PART bytes per staging buffer (a region larger than that alone) and
|
||||
// records one copy per buffer; every part stays in the same upload batch, submitted as before. The GPU decoder
|
||||
// takes the raw blocks of every region from one buffer.
|
||||
// records one copy per buffer into the open upload batch (vk_upload_end may submit a batch that holds much staging
|
||||
// between two parts; queue order and the barriers keep them in order). The GPU decoder takes the raw blocks of
|
||||
// every region from one buffer.
|
||||
for (uint32_t k0 = 0, k1; k0 < n; k0 = k1) {
|
||||
VkDeviceSize base = rg[k0].bufferOffset, size;
|
||||
for (k1 = k0 + 1; k1 < n && (agpu || (k1 + 1 < n ? rg[k1 + 1].bufferOffset : total) - base <= UPLOAD_PART);) k1++;
|
||||
|
||||
Reference in New Issue
Block a user