feat: device alloc: appropriate entire pages, lazily

[zyuiop]

This is a partial rewrite of #1815.

The goal is to mapping memory lazily when it's requested, but by 2MB blocks.
When memory is requested, if there is not enough memory in the free list, we claim a 2MB page from the available free list, then we remap it at the offset

[github-actions]

Benchmark Results

Details

Benchmark	Current: 92b1387	Previous: a025f19	Performance Ratio
startup_benchmark Build Time	110.61 s	116.82 s	0.95 ❗
startup_benchmark File Size	0.77 MB	0.77 MB	1.00 ❗
Startup Time - 1 core	0.83 s (±0.08 s)	1.00 s (±0.03 s)	0.83 ❗
Startup Time - 2 cores	1.03 s (±0.03 s)	1.04 s (±0.05 s)	0.99
Startup Time - 4 cores	1.01 s (±0.03 s)	1.02 s (±0.05 s)	0.99
multithreaded_benchmark Build Time	120.56 s	117.48 s	1.03 ❗
multithreaded_benchmark File Size	0.83 MB	0.84 MB	1.00 ❗
Multithreaded Pi Efficiency - 2 Threads	92.84 % (±10.16 %)	85.06 % (±19.28 %)	1.09
Multithreaded Pi Efficiency - 4 Threads	45.77 % (±4.92 %)	42.20 % (±9.32 %)	1.08
Multithreaded Pi Efficiency - 8 Threads	24.90 % (±2.96 %)	23.57 % (±5.00 %)	1.06
micro_benchmarks Build Time	95.13 s	92.09 s	1.03 ❗
micro_benchmarks File Size	0.84 MB	0.84 MB	1.00 ❗
Scheduling time - 1 thread	72.57 ticks (±3.97 ticks)	73.19 ticks (±3.39 ticks)	0.99
Scheduling time - 2 threads	41.56 ticks (±6.12 ticks)	44.10 ticks (±6.54 ticks)	0.94
Micro - Time for syscall (getpid)	3.02 ticks (±0.21 ticks)	3.09 ticks (±0.16 ticks)	0.98
Memcpy speed - (built_in) block size 4096	74425.40 MByte/s (±51313.71 MByte/s)	73877.55 MByte/s (±50900.64 MByte/s)	1.01
Memcpy speed - (built_in) block size 1048576	29443.39 MByte/s (±24050.95 MByte/s)	29621.41 MByte/s (±24412.82 MByte/s)	0.99
Memcpy speed - (built_in) block size 16777216	23957.92 MByte/s (±19818.40 MByte/s)	26615.80 MByte/s (±21973.01 MByte/s)	0.90
Memset speed - (built_in) block size 4096	74530.29 MByte/s (±51385.58 MByte/s)	74082.46 MByte/s (±51039.25 MByte/s)	1.01
Memset speed - (built_in) block size 1048576	30145.26 MByte/s (±24479.12 MByte/s)	30381.08 MByte/s (±24836.90 MByte/s)	0.99
Memset speed - (built_in) block size 16777216	24629.77 MByte/s (±20242.39 MByte/s)	27365.04 MByte/s (±22427.19 MByte/s)	0.90
Memcpy speed - (rust) block size 4096	67392.19 MByte/s (±47160.50 MByte/s)	67998.13 MByte/s (±47775.53 MByte/s)	0.99
Memcpy speed - (rust) block size 1048576	29331.78 MByte/s (±24083.46 MByte/s)	29415.03 MByte/s (±24216.28 MByte/s)	1.00
Memcpy speed - (rust) block size 16777216	24408.56 MByte/s (±19946.25 MByte/s)	26645.15 MByte/s (±21980.78 MByte/s)	0.92
Memset speed - (rust) block size 4096	67201.00 MByte/s (±47041.15 MByte/s)	68410.01 MByte/s (±48051.67 MByte/s)	0.98
Memset speed - (rust) block size 1048576	30095.61 MByte/s (±24531.26 MByte/s)	30182.39 MByte/s (±24662.20 MByte/s)	1.00
Memset speed - (rust) block size 16777216	25093.93 MByte/s (±20381.77 MByte/s)	27320.66 MByte/s (±22364.88 MByte/s)	0.92
alloc_benchmarks Build Time	89.78 s	91.56 s	0.98 ❗
alloc_benchmarks File Size	0.85 MB	0.85 MB	1.00 ❗
Allocations - Allocation success	100.00 %	100.00 %	1
Allocations - Deallocation success	100.00 %	100.00 %	1
Allocations - Pre-fail Allocations	100.00 %	100.00 %	1
Allocations - Average Allocation time	4058.15 Ticks (±54.61 Ticks)	4553.50 Ticks (±57.46 Ticks)	0.89 ❗
Allocations - Average Allocation time (no fail)	4058.15 Ticks (±54.61 Ticks)	4553.50 Ticks (±57.46 Ticks)	0.89 ❗
Allocations - Average Deallocation time	648.58 Ticks (±45.02 Ticks)	1035.15 Ticks (±129.57 Ticks)	0.63 ❗
mutex_benchmark Build Time	90.40 s	88.37 s	1.02 ❗
mutex_benchmark File Size	0.84 MB	0.84 MB	1.00 ❗
Mutex Stress Test Average Time per Iteration - 1 Threads	13.66 ns (±0.65 ns)	14.02 ns (±0.84 ns)	0.97
Mutex Stress Test Average Time per Iteration - 2 Threads	16.40 ns (±4.60 ns)	17.80 ns (±4.95 ns)	0.92

This comment was automatically generated by workflow using github-action-benchmark.