russell@unturf.com
87503f60ef
Closes the three tractable pending buckets (all non-no_dir work):
+ lean4-0004..0007: 4 correctness/race benches (ir_interp DCL, jobreg
IO.Ref race, g_opts thread-local leakage, process envvar hash).
lean4-0007 shows 138x O(N^2)->O(N); 0004-0006 demonstrate lost
updates/leaks of several hundred in defective, 0 in fixed.
+ 0ad-0001..0004: 3 CWE-407 list.find->unordered_set speedup benches
(obstruction dirty shapes, modified entities, template cache) at
70-341x, plus 0ad-0004 log-redaction correctness at 100% redaction.
+ activemq-0001..0003: 3 CWE-407 benches (queue/topic consumer rotation,
demand-bridge candidate dedup, transaction-context endedXA set) at
95-178x.
+ linux-0001..0008: 8 Python complexity-class models for the kernel
patches. Coexist with the existing build-and-bench.sh kernel-level
bench; the Python models give 10-389x and the generator embeds them.
+ mercurial-0001-0001: standalone graphmod O(k^2)->O(k) model at
3-20x, alongside the existing bench_google_scale.py (which imports
the real mercurial graphmod).
Progress: 13 -> 33 full coverage. Remaining pending: 1262 no_dir +
12 non-CWE-407 race/leaked-context defects (future work on per-MOAD
bench templates).
48 lines
2.5 KiB
Text
48 lines
2.5 KiB
Text
=== linux-0001: headerdep detect_cycles BFS list-grep ===
|
|
D=100 K=10 : defective=0.123ms fixed=0.013ms speedup=9.7x
|
|
D=500 K=20 : defective=0.786ms fixed=0.051ms speedup=15.4x
|
|
D=1000 K=30 : defective=1.919ms fixed=0.091ms speedup=21.0x
|
|
D=2000 K=50 : defective=5.459ms fixed=0.312ms speedup=17.5x
|
|
|
|
=== linux-0002: auditsc audit_filter_rules inode-list scan ===
|
|
F=100 R=20 : defective=0.252ms fixed=0.015ms speedup=17.0x
|
|
F=500 R=50 : defective=1.407ms fixed=0.045ms speedup=31.0x
|
|
F=1000 R=100 : defective=4.392ms fixed=0.084ms speedup=52.2x
|
|
F=2000 R=200 : defective=17.351ms fixed=0.163ms speedup=106.7x
|
|
|
|
=== linux-0003: dev.c __dev_alloc_name altname linear scan ===
|
|
D=100 A=10 : defective=0.086ms fixed=0.009ms speedup=9.7x
|
|
D=500 A=20 : defective=0.637ms fixed=0.041ms speedup=15.4x
|
|
D=1000 A=30 : defective=1.661ms fixed=0.079ms speedup=21.0x
|
|
D=2000 A=50 : defective=4.854ms fixed=0.188ms speedup=25.8x
|
|
|
|
=== linux-0004: neighbour.c lookup_neigh_parms list walk ===
|
|
P=100 : defective=0.097ms fixed=0.004ms speedup=25.4x
|
|
P=500 : defective=2.472ms fixed=0.023ms speedup=108.6x
|
|
P=1000 : defective=10.423ms fixed=0.051ms speedup=205.4x
|
|
P=2000 : defective=36.584ms fixed=0.094ms speedup=389.2x
|
|
|
|
=== linux-0005: component.c find_component nested matches ===
|
|
A=50 M=50 : defective=0.049ms fixed=0.005ms speedup=9.9x
|
|
A=100 M=100 : defective=0.185ms fixed=0.010ms speedup=19.4x
|
|
A=200 M=200 : defective=0.716ms fixed=0.018ms speedup=38.8x
|
|
A=500 M=500 : defective=4.691ms fixed=0.056ms speedup=84.0x
|
|
|
|
=== linux-0006: btf.c bpf_find_btf_id IDR scan per field ===
|
|
F=50 M=100 : defective=0.049ms fixed=0.005ms speedup=9.4x
|
|
F=100 M=500 : defective=0.184ms fixed=0.010ms speedup=18.7x
|
|
F=200 M=1000 : defective=0.724ms fixed=0.019ms speedup=37.6x
|
|
F=500 M=2000 : defective=4.906ms fixed=0.057ms speedup=86.4x
|
|
|
|
=== linux-0007: pktgen.c thread-dev list walk ===
|
|
T=50 D=100 : defective=0.049ms fixed=0.005ms speedup=9.7x
|
|
T=100 D=200 : defective=0.184ms fixed=0.010ms speedup=19.3x
|
|
T=200 D=500 : defective=0.730ms fixed=0.038ms speedup=19.3x
|
|
T=500 D=1000 : defective=4.909ms fixed=0.055ms speedup=88.9x
|
|
|
|
=== linux-0008: taskstats.c add_del_listener per-CPU list ===
|
|
CPUs=32 L=50 : defective=0.021ms fixed=0.003ms speedup=6.3x
|
|
CPUs=64 L=100 : defective=0.078ms fixed=0.006ms speedup=12.3x
|
|
CPUs=128 L=200 : defective=0.297ms fixed=0.013ms speedup=23.5x
|
|
CPUs=256 L=500 : defective=1.226ms fixed=0.024ms speedup=50.8x
|
|
|