Wouldn't this have been caught by an exhaustive unit test or even a fuzz test? I don't know what kind of testing practices are applied to projects like zfs, nor what kinds or amounts of tests functions like this are subject to, but I would imagine that especially for low-level functions like this, unit tests with all of the known edge cases would be written.

(yes this is very much an armchair opinion, I mostly do front-end JS for a living)

The problems with C are real.

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.

Software verification tools based on abstract Interpretation are really good today.

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.

I found it. All that tells you is that it's a simple problem. Had I not been told it was broken I likely would not have.

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?

I missed it, but I was distracted by cols variable being initialised with the original width, but then being immediately overwritten with the logical width.

Unexpected issue (for me).

I would have expected that the compiler should complain that psize is computed but unused.

Why isn't -Wunused-variable enabled in OpenZFS?

Isn't it a case for eliminating all warnings and treat them as bugs?

It seems you are dooming your project the minute you start ignoring your first warning.

Having run into similar problems several times, I've also never really been satisfied with the solutions. You have to have different types to cause compile errors, but then you have throw those types away whenever you perform any actual operations on them.

    struct TypeA { int inner; };
    struct TypeB { int inner; };

    struct TypeA a1, a2;
    // whoops
    TypeB result = {.inner = a1.inner + a2.inner};

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.

I'm not sure why C is blamed in this case when you can do exactly the same strong typing fix in C, and with C99 struct literals it's also not much worse to work with:

    typedef struct { size_t size; } PhysicalSize;
    typedef struct { size_t size; } AllocatedSize;

    PhysicalSize psize = { 123 }; // or { .size = 123 }
    AllocatedSize asize = { 234 };

    psize = asize; // error

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.:

https://www.open-std.org/jtc1/sc22/wg14/www/docs/n3320.htm

FWIW you can do the same thing in cpp, too - but Rust’s syntax certainly makes it easier.

I'm surprised their testing didn't catch it. And while I get that turning on warnings in a code-base not designed with them can be annoying, `-Wunused` is certainly within reach. I've enabled and maintained `-Weverything` in a 30m LoC C code base that is older than myself. OpenZFS should try harder to enable such warnings in their CI.

How come in that function the local variable cols is assigned a value and then immediately it’s assigned another value without the original value being read?

It remind me a devlog from andrew kelley on the same topics : https://ziglang.org/devlog/2024/#2024-11-04

In this case any simple unit test would have catched it. Surprised it wasn't mentioned in the post.

How much would it cost/how long to give an LLM the entire OpenZfs repo and ask it to find every bug?

Thanks contribution to openzfs.

For my personal use, I have no need for ZFS on Linux (ext4) or *BSD (UFS/ffs).

I have been playing with NetBSD for a bit and I discovered their FS has a log parameter, using that on mount to me makes their file system almost as good as ext4. Interesting to me it is not advertised too much.

Gpt4o-mini response:

>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;

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.

So why is the solution Rust, and not any of the other 2000 "modern" languages?