code wiki / (root) / nx_container_bench.nx

nx_container_bench.nx

buildroot/runtime/nx_container_bench.nx

12252 B240 linesdepth 3pulls 4 transitivereach 0 importersview sourcekind benchtopic container
docsdependenciesstructsconstsfunctions

about

nx_container_bench.nx -- SOVEREIGN measured-exceed scorecard: Nishi Container Host vs Docker Desktop. The no-wave JUDGE/AGGREGATOR (operator 2026-06-24: "s-class exceed container hosting strategy ... measured-exceed vs Docker first"). Mirrors nx_gpu_bench's judge pattern. ROLE: this organ does NOT assert numbers. It INGESTS measurements taken LIVE on this machine (knowledge/status/container_bench_measured.dat -- Docker booted+measured idle RAM/procs/cold-start then torn down; Nishi governance/footprint measured) and computes an HONEST per-axis verdict (EXCEEDS / PARITY / BEHIND / DIFFERENT-ALTITUDE). It REFUSES to score a different-config axis as an exceed (gpu latency: 512^2 native vs 640x896 WSL2 = not comparable). LIAR-KILL: the verdict is COMPUTED from the numbers, so a tampered "we win" cannot fool it; two negative controls prove the judge is not a rubber-stamp. NO fake greens. license_tier: ORIGINAL

dependencies 3 imports · 0 importers

nx_syscalls.nx nx_itoa_lib.nx nx_runtime.nx nx_container_bench.nx

imports: nx_syscalls.nxnx_itoa_lib.nxnx_runtime.nx

imported by: nobody (leaf or entry point)

call flow from main pre-order; caps 40 nodes / depth 6 declared; ↻ = already shown

main cb_p cb_w sys_write cb_verdict sys_mmap cb_read sys_openat_rd sys_read sys_close cb_read_int cb_strlen cb_find sys_openat_wr cb_w ↻ cb_row cb_w ↻ cb_wn nxi_fd sys_mmap ↻ ccz_cat_num sys_write ↻ sys_munmap cb_vname cb_w ↻ cb_wn ↻ sys_close ↻ cb_pn cb_wn ↻ cb_vname ↻ sys_openat_append sys_now_realtime_sec sys_mmap ↻ sys_clock_gettime_real

structs

none

consts

15const CB_MAGIC_999999: i64 = 999999
16const CB_MAGIC_2774: i64 = 2774
17const CB_MAGIC_9999: i64 = 9999
18const CB_MAGIC_65536: i64 = 65536
19const CB_MAGIC_65535: i64 = 65535
21const CB_DAT: *u8 = "knowledge/status/container_bench_measured.dat"
22const CB_TSV: *u8 = "knowledge/status/container_bench.tsv"
23const CB_LOG: *u8 = "knowledge/status/container_bench.log"

functions

25func cb_w(fd: i64, s: *u8) -> i64 { var n: i64 = 0; while s[n] != (0 as u8) { n = n + 1 } sys_write(fd, s, n); return 0 }
called by 4: cb_pcb_vnamecb_rowmain calls 1: sys_write
30func cb_wn(fd: i64, v: i64) -> i64 { nxi_fd(fd, v); return 0 }
called by 3: cb_pncb_rowmain calls 1: nxi_fd
31func cb_p(s: *u8) -> i64 { return cb_w(1, s) }
called by 1: main calls 1: cb_w
32func cb_pn(v: i64) -> i64 { return cb_wn(1, v) }
called by 1: main calls 1: cb_wn
34func cb_read(path: *u8, buf: *u8, cap: i64) -> i64
called by 1: main calls 3: sys_openat_rdsys_readsys_close
47func cb_strlen(s: *u8) -> i64 { var n: i64 = 0; while s[n] != (0 as u8) { n = n + 1 } return n }
called by 1: cb_read_int
48func cb_find(buf: *u8, n: i64, pat: *u8, pl: i64) -> i64
called by 1: cb_read_int
60func cb_read_int(buf: *u8, n: i64, key: *u8) -> i64
called by 1: main calls 2: cb_strlencb_find
75func cb_verdict(nishi: i64, docker: i64, dir_lower: i64, comparable: i64) -> i64
called by 1: main
86func cb_vname(fd: i64, v: i64) -> i64
called by 2: cb_rowmain calls 1: cb_w
93func cb_row(fd: i64, name: *u8, nishi: i64, docker: i64, unit: *u8, v: i64) -> i64
called by 1: main calls 3: cb_wcb_wncb_vname
103func main() -> i64