Spread the texture pool's entry creation over frames by a per-frame time budget, and stop looking up the slots it left.

The pool refresh runs before every draw that binds the pools, so its count budget of 16 creations held per draw, not
per submission. An area load in the 0.6.1.12 test made 4,925 entries (1.7 GB of uploads) in one 430 ms frame, and
2,018 in a 195 ms one. While slots were left over, every draw walked the whole table and looked each of them up again,
about 100 ms of the 430 ms frame in key hashing alone.

Once a frame's refreshes have taken pool_create_ms (default 6 ms; 0: no limit), they create nothing more until the next
frame, and skip the slots left earlier in the frame. The first refresh of each frame keeps its count budget. The slots
left keep their stand-in for a few frames during a large load.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
chrg6
2026-11-09 14:51:29 -05:00
parent 853449fd8d
commit 860bc9cf0b
4 changed files with 55 additions and 10 deletions

View File

@@ -66,7 +66,7 @@ static const char *const known[] = {
"ZSTD_CHECK", "ZSTD_NATIVE",
"BIND_REUSE", "DYN_DELTA", "STG_ARENA", "SUBMIT_BATCH", "ASTC_GPU_DESWIZZLE", "ASTC_SCRATCH_KEEP", "ASTC_ARENA",
"TEXUP_LOG_MS", "DYN_RES", "DYN_RES_TARGET", "DYN_RES_STEP",
"RECORDER_CORE", "RECORDER_PRIO", "REPLAY_TIME", "LOCK_TIME", "POOL_CREATE_BUDGET",
"RECORDER_CORE", "RECORDER_PRIO", "REPLAY_TIME", "LOCK_TIME", "POOL_CREATE_BUDGET", "POOL_CREATE_MS",
};
// The nx2navi.ini section a key cfg_set may write goes to when the file lacks it (nx2navi.ini.example's sections).
@@ -107,6 +107,7 @@ static const struct { const char *key, *section; } sections[] = {
{"RECORDER_CORE", "performance"}, {"RECORDER_PRIO", "performance"}, {"BIND_REUSE", "performance"},
{"DYN_DELTA", "performance"}, {"STG_ARENA", "performance"}, {"SUBMIT_BATCH", "performance"},
{"ASTC_GPU_DESWIZZLE", "performance"}, {"ASTC_SCRATCH_KEEP", "performance"}, {"ASTC_ARENA", "performance"}, {"POOL_CREATE_BUDGET", "performance"},
{"POOL_CREATE_MS", "performance"},
{"TIMER_1MS", "performance"}, {"PIPE_WAIT", "performance"}, {"PIPE_SKIP", "performance"}, {"ONESHOT_BUDGET", "performance"},
{"LIB_PREBUILD", "performance"}, {"LIB_PREBUILD_THREADS", "performance"}, {"PIPE_PREBUILD", "performance"},
{"PREWARM_XLATE", "performance"}, {"GPL", "performance"}, {"ASTC", "performance"}, {"MEMORY", "performance"},
@@ -197,7 +198,7 @@ static const CfgMeta metas[] = {
{"DYN_RES", "0", "0|1", LIVE}, {"DYN_RES_TARGET", "16.7", "1..100", LIVE}, {"DYN_RES_STEP", "45", "8..600", LIVE},
// the recording thread: a core of its own (auto: with 12 or more logical processors) and the highest priority
// (vk_exec.c vk_exec_record)
{"RECORDER_CORE", "auto", "auto|0|1", RESTART}, {"RECORDER_PRIO", "1", "0|1", RESTART}, {"REPLAY_TIME", "0", "0|1", RESTART}, {"LOCK_TIME", "0", "0|1", RESTART}, {"POOL_CREATE_BUDGET", "16", "1..4096", RESTART},
{"RECORDER_CORE", "auto", "auto|0|1", RESTART}, {"RECORDER_PRIO", "1", "0|1", RESTART}, {"REPLAY_TIME", "0", "0|1", RESTART}, {"LOCK_TIME", "0", "0|1", RESTART}, {"POOL_CREATE_BUDGET", "16", "1..4096", RESTART}, {"POOL_CREATE_MS", "6", "0..100", RESTART},
// held submissions handed to the queue together (vk_sync.c, submit batching)
{"SUBMIT_BATCH", "4", "1..16", RESTART},
// shaders and pipelines