fix(pci): handle error values for IRQ number#1985
Conversation
There was a problem hiding this comment.
Benchmark Results
Details
| Benchmark | Current: 417b254 | Previous: 4406c2f | Performance Ratio |
|---|---|---|---|
| startup_benchmark Build Time | 111.68 s |
112.50 s |
0.99 |
| startup_benchmark File Size | 0.91 MB |
0.91 MB |
1.00 |
| Startup Time - 1 core | 0.90 s (±0.02 s) |
0.89 s (±0.03 s) |
1.01 |
| Startup Time - 2 cores | 0.92 s (±0.02 s) |
0.91 s (±0.03 s) |
1.01 |
| Startup Time - 4 cores | 0.92 s (±0.03 s) |
0.91 s (±0.03 s) |
1.01 |
| multithreaded_benchmark Build Time | 111.68 s |
110.54 s |
1.01 |
| multithreaded_benchmark File Size | 1.02 MB |
1.02 MB |
1.00 |
| Multithreaded Pi Efficiency - 2 Threads | 85.90 % (±9.15 %) |
90.54 % (±7.97 %) |
0.95 |
| Multithreaded Pi Efficiency - 4 Threads | 42.86 % (±3.29 %) |
44.52 % (±2.89 %) |
0.96 |
| Multithreaded Pi Efficiency - 8 Threads | 24.31 % (±1.71 %) |
25.77 % (±1.78 %) |
0.94 |
| micro_benchmarks Build Time | 295.47 s |
294.62 s |
1.00 |
| micro_benchmarks File Size | 1.02 MB |
1.02 MB |
1.00 |
| Scheduling time - 1 thread | 166.68 ticks (±25.00 ticks) |
166.16 ticks (±24.75 ticks) |
1.00 |
| Scheduling time - 2 threads | 100.65 ticks (±19.98 ticks) |
98.92 ticks (±21.16 ticks) |
1.02 |
| Micro - Time for syscall (getpid) | 10.38 ticks (±5.04 ticks) |
10.37 ticks (±5.09 ticks) |
1.00 |
| Memcpy speed - (built_in) block size 4096 | 58106.08 MByte/s (±42190.00 MByte/s) |
57796.95 MByte/s (±42117.46 MByte/s) |
1.01 |
| Memcpy speed - (built_in) block size 1048576 | 13679.59 MByte/s (±11125.04 MByte/s) |
13855.92 MByte/s (±11377.70 MByte/s) |
0.99 |
| Memcpy speed - (built_in) block size 16777216 | 9908.55 MByte/s (±8019.41 MByte/s) |
10150.72 MByte/s (±8216.15 MByte/s) |
0.98 |
| Memset speed - (built_in) block size 4096 | 57118.36 MByte/s (±41930.55 MByte/s) |
58119.59 MByte/s (±42293.75 MByte/s) |
0.98 |
| Memset speed - (built_in) block size 1048576 | 13885.30 MByte/s (±11212.75 MByte/s) |
14269.30 MByte/s (±11639.09 MByte/s) |
0.97 |
| Memset speed - (built_in) block size 16777216 | 10173.04 MByte/s (±8184.49 MByte/s) |
10460.31 MByte/s (±8421.16 MByte/s) |
0.97 |
| Memcpy speed - (rust) block size 4096 | 53254.92 MByte/s (±39525.45 MByte/s) |
55022.44 MByte/s (±40292.12 MByte/s) |
0.97 |
| Memcpy speed - (rust) block size 1048576 | 13815.15 MByte/s (±11318.99 MByte/s) |
14053.62 MByte/s (±11588.02 MByte/s) |
0.98 |
| Memcpy speed - (rust) block size 16777216 | 10252.13 MByte/s (±8313.98 MByte/s) |
9918.94 MByte/s (±7990.50 MByte/s) |
1.03 |
| Memset speed - (rust) block size 4096 | 53591.12 MByte/s (±39703.11 MByte/s) |
55564.64 MByte/s (±40644.56 MByte/s) |
0.96 |
| Memset speed - (rust) block size 1048576 | 14138.99 MByte/s (±11484.08 MByte/s) |
14210.72 MByte/s (±11709.13 MByte/s) |
0.99 |
| Memset speed - (rust) block size 16777216 | 10504.87 MByte/s (±8464.06 MByte/s) |
10199.88 MByte/s (±8172.52 MByte/s) |
1.03 |
| alloc_benchmarks Build Time | 302.86 s |
293.32 s |
1.03 |
| alloc_benchmarks File Size | 0.98 MB |
0.98 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 | 20363.98 Ticks (±891.88 Ticks) |
19796.71 Ticks (±1011.78 Ticks) |
1.03 |
| Allocations - Average Allocation time (no fail) | 20363.98 Ticks (±891.88 Ticks) |
19796.71 Ticks (±1011.78 Ticks) |
1.03 |
| Allocations - Average Deallocation time | 3068.46 Ticks (±1241.23 Ticks) |
2618.08 Ticks (±1032.57 Ticks) |
1.17 |
| mutex_benchmark Build Time | 293.78 s |
293.46 s |
1.00 |
| mutex_benchmark File Size | 1.02 MB |
1.02 MB |
1.00 |
| Mutex Stress Test Average Time per Iteration - 1 Threads | 36.22 ns (±3.63 ns) |
36.58 ns (±5.95 ns) |
0.99 |
| Mutex Stress Test Average Time per Iteration - 2 Threads | 29.56 ns (±3.39 ns) |
29.58 ns (±3.24 ns) |
1.00 |
This comment was automatically generated by workflow using github-action-benchmark.
mkroening
left a comment
There was a problem hiding this comment.
Looks good, thanks! :)
Would it make sense to log these as errors instead of warnings?
I think they are not all necessarily error conditions. For example it is possible that a driver tries the legacy interrupt mechanism first and if it fails falls back to MSI. In my opinion it would make more sense to print an error on the driver side if it is not able to handle the lack of a legacy interrupt line. |
|
Yeah, for the first one, warn makes sense. We might even want to downgrade that once we can handle non-legacy interrupts. The other ones are clear errors, though, right? 🤔 |
e5259b5 to
417b254
Compare
No description provided.