typedef struct { size_t size; } PhysicalSize;
typedef struct { size_t size; } AllocatedSize;
PhysicalSize psize = { 123 }; // or { .size = 123 }
AllocatedSize asize = { 234 };
psize = asize; // error
...and in reverse, Rust wouldn't protect you from that exact same bug if the programmer decided to use usize like in the original C code.IME overly strong typing is a double-edged sword though, on one hand it makes the code more robust, but on the other hand also more 'change resistant'.
I still would like to see a strong typedef variant in C so that the struct wrapping wouldn't be needed, e.g.:
(yes this is very much an armchair opinion, I mostly do front-end JS for a living)
A single call where the psize is different than the asize would have caught it.
It's the kind of bug that makes you stop breathing for a brief moment. So I ran this function through Gemini 2.5 Pro, ChatGPT o3 and Grok 3. No context other than the source code fragment was provided. All three also clearly identified the problem.
There is no longer a reason for trivial flaws such as this surviving to release code. We're past that now, and that's an astonishing thing.
These are the questions I ponder: Should we consider the possibility that the ongoing, incomplete and decades long pursuit of "better" languages is now misguided? Or, that perhaps "better" might now mean whatever properties make code easier for LLMs to analyze and validate against specifications, as opposed to merely preventing the flaws humans are prone to make?
So double down on languages that are more represented in training data? I think it's still worthwhile to actually improve programming languages. Relying only on LLMs is fragile. So ideally do both: improve language and AI.
The pragmatic answer to that is: this appears to be highly effective.
What I have in mind is something else, however. Consider the safety nets we try to build with, for example, elaborate type systems. These new analysis tools can operate on enormous contexts and infer and enforce "type" with a capacity far greater what a human mind can hope to approach. So perhaps there is little value to complex types. Instead, a simple type system supported by specification will be the superior approach. seL4 is an example of the concept: C, but exhaustively specified and verified.
Not totally clear what you mean here - are you saying you’re the author of the article or PR, or that you independently discovered the same issue (after the fact)?
The author asked that the reader attempt to find the flaw by inspecting the provided code. The flaw was obvious enough that I was able to find it. The implication is that if it were less obvious, I might not have. I was not attempting to take any credit at all: exactly the opposite.
Excellent question. What would it end up looking like? Would it be full of monads and HKTs? Lambda calculus? WebAssembly?
I hope to learn the answer one day.
This is unrelated to "no longer due to ChatGPT times".
We've been able to detect this issue for decades already, see -Wunused-variable.
struct TypeA { int inner; };
struct TypeB { int inner; };
struct TypeA a1, a2;
// whoops
TypeB result = {.inner = a1.inner + a2.inner};
Don't get me wrong, where I've used this sort of pattern it's definitely caught issues, and it definitely massively lowers the surface area for this type of bug. But I still feel like it's quite fragile.The use case I felt worked best was seperating out UTC datetime vs localised datetime structs - mainly since it's something you already had to use function calls to add/subtract from, you couldn't play with raw values.
If you want free software I recommend IKOS - a is a sound static analyzer for C/C++ developed at NASA. Checks: https://github.com/NASA-SW-VnV/ikos/blob/master/analyzer/REA... Numerical abstract domains: https://github.com/NASA-SW-VnV/ikos/blob/master/analyzer/REA...
Commercial tool like Astree https://www.absint.com/astree/index.htm if you have money.
It seems you are dooming your project the minute you start ignoring your first warning.
I would have expected that the compiler should complain that psize is computed but unused.
Why isn't -Wunused-variable enabled in OpenZFS?
>The provided code snippet is a function that converts an allocation size (asize) into the largest physical size (psize) that can be safely written to an allocation for a given virtual device (vdev). Here are some observations and potential issues in the code:
Return Value: The function currently returns asize instead of psize. This seems to be a mistake, as the purpose of the function is to compute and return the psize. The correct return statement should be:
return psize;
Comment Clarity: The comments mention that the function does not take into account the effect of gang headers. It might be helpful to clarify what "gang headers" are and how they affect the allocation sizes, especially for someone unfamiliar with the context.Variable Initialization: The variable psize is calculated based on asize, ashift, cols, and nparity. Ensure that these values are correctly initialized and that vdev_raidz_get_logical_width returns a valid value for cols. If cols is zero, it could lead to division by zero in the DIV_ROUND_UP macro.
Assertions: The assertion ASSERT0(asize % (1 << ashift)); checks that asize is a multiple of 2^ashift. If this assertion fails, it will cause the program to terminate. Ensure that this condition is always met before calling this function, or consider handling this case more gracefully.
Macro Usage: The DIV_ROUND_UP macro should be checked to ensure it handles edge cases correctly, such as when psize is zero. If psize is zero, the division could lead to unexpected behavior.
Code Readability: Consider adding more comments to explain the logic behind the calculations, especially for someone who may not be familiar with the RAID-Z implementation.
Error Handling: There is no error handling in the function. Depending on the context in which this function is used, it might be beneficial to add checks for invalid input values and return an error code or handle exceptions accordingly.
Here is a revised version of the function with the return value corrected:
.....(Snipped for formatting issues)
Make sure to test the function thoroughly to ensure it behaves as expected under various conditions.
jpfr•2h ago
At the same time, the tooling has gotten much better in the last years.
Clang-analyzer is fast enough to run as part of the CI. Newer gcc also give quite a few more warnings for unused results.
My recommendation to the project is to
- Remove all compiler warnings and enable warning-as-error
- Increase the coverage of unit tests to >80%
That is a lot of work. But that's what is required for high-criticality systems engineering.