comparison rust/hg-cpython/src/revlog.rs @ 47799:3fffb48539ee stable

rust-nodemap: falling back to C impl as mitigation

This is a mitigation for https://bz.mercurial-scm.org/show_bug.cgi?id=6554

We see sometimes almost all data except the most recent revisions
removed from the persistent nodemap, but we don't know how to
reproduce yet.

This has sadly repercussions beyond just needing to reconstruct the
persistent nodemap: for instance, this automatically filters out
all bookmarks pointing to revisions that the nodemap cannot resolve.
If such filtering happens in a transaction, the update of the
bookmarks file that happens at the end of transaction loses all
bookmarks that have been affected. There may be similar consequences
for other data.

So this is a data loss, something that we have to prevent as soon as
possible.

As a mitigation measure, we will now fallback to the C implementation
in case nodemap lookups failed. This will add some latency, e.g., in
discovery, yet less than disabling the persistent nodemap entirely.

We considered implementing the fallback directly on the Python
side, but `revlog.get_rev()` is not systematically used, there are
also several direct calls to the index method (`self.index.rev()` for
a `revlog` instance). It is therefore more direct to implement the
mitigation in the rust-cpython wrapper.

Differential Revision: https://phab.mercurial-scm.org/D11238

47798:2cd00052ae4d

    // Index API involving nodemap, as defined in mercurial/pure/parsers.py

    /// Return Revision if found, raises a bare `error.RevlogError`
    /// in case of ambiguity, same as C version does
    def get_rev(&self, node: PyBytes) -> PyResult<Option<Revision>> {
        let opt = self.get_nodetree(py)?.borrow();
        let nt = opt.as_ref().unwrap();
        let idx = &*self.cindex(py).borrow();
        let node = node_from_py_bytes(py, &node)?;
        nt.find_bin(idx, node.into()).map_err(|e| nodemap_error(py, e))
    }

    /// same as `get_rev()` but raises a bare `error.RevlogError` if node
    /// is not found.
    ///

            Ok(None) => Err(revlog_error(py)),
            Err(e) => Err(nodemap_error(py, e)),
        }
    }

    def partialmatch(&self, node: PyObject) -> PyResult<Option<PyBytes>> {
        let opt = self.get_nodetree(py)?.borrow();
        let nt = opt.as_ref().unwrap();
        let idx = &*self.cindex(py).borrow();

        let node_as_string = if cfg!(feature = "python3-sys") {
            node.cast_as::<PyString>(py)?.to_string(py)?.to_string()
        }
        else {
            let node = node.extract::<PyBytes>(py)?;
            String::from_utf8_lossy(node.data(py)).to_string()
        };

        let prefix = NodePrefix::from_hex(&node_as_string).map_err(|_| PyErr::new::<ValueError, _>(py, "Invalid node or prefix"))?;

        nt.find_bin(idx, prefix)
            // TODO make an inner API returning the node directly
            .map(|opt| opt.map(
                |rev| PyBytes::new(py, idx.node(rev).unwrap().as_bytes())))
            .map_err(|e| nodemap_error(py, e))

    }

    /// append an index entry
    def append(&self, tup: PyTuple) -> PyResult<PyObject> {
        if tup.len(py) < 8 {

47799:3fffb48539ee

    // Index API involving nodemap, as defined in mercurial/pure/parsers.py

    /// Return Revision if found, raises a bare `error.RevlogError`
    /// in case of ambiguity, same as C version does
    def get_rev(&self, pynode: PyBytes) -> PyResult<Option<Revision>> {
        let opt = self.get_nodetree(py)?.borrow();
        let nt = opt.as_ref().unwrap();
        let idx = &*self.cindex(py).borrow();
        let node = node_from_py_bytes(py, &pynode)?;
        match nt.find_bin(idx, node.into())
        {
            Ok(None) =>
                // fallback to C implementation, remove once
                // https://bz.mercurial-scm.org/show_bug.cgi?id=6554
                // is fixed (a simple backout should do)
                self.call_cindex(py, "get_rev", &PyTuple::new(py, &[pynode.into_object()]), None)?
                .extract(py),
            Ok(Some(rev)) => Ok(Some(rev)),
            Err(e) => Err(nodemap_error(py, e)),
        }
    }

    /// same as `get_rev()` but raises a bare `error.RevlogError` if node
    /// is not found.
    ///

            Ok(None) => Err(revlog_error(py)),
            Err(e) => Err(nodemap_error(py, e)),
        }
    }

    def partialmatch(&self, pynode: PyObject) -> PyResult<Option<PyBytes>> {
        let opt = self.get_nodetree(py)?.borrow();
        let nt = opt.as_ref().unwrap();
        let idx = &*self.cindex(py).borrow();

        let node_as_string = if cfg!(feature = "python3-sys") {
            pynode.cast_as::<PyString>(py)?.to_string(py)?.to_string()
        }
        else {
            let node = pynode.extract::<PyBytes>(py)?;
            String::from_utf8_lossy(node.data(py)).to_string()
        };

        let prefix = NodePrefix::from_hex(&node_as_string).map_err(|_| PyErr::new::<ValueError, _>(py, "Invalid node or prefix"))?;

        match nt.find_bin(idx, prefix) {
            Ok(None) =>
                // fallback to C implementation, remove once
                // https://bz.mercurial-scm.org/show_bug.cgi?id=6554
                // is fixed (a simple backout should do)
                self.call_cindex(
                    py, "partialmatch",
                    &PyTuple::new(py, &[pynode]), None
                )?.extract(py),
            Ok(Some(rev)) =>
                Ok(Some(PyBytes::new(py, idx.node(rev).unwrap().as_bytes()))),
            Err(e) => Err(nodemap_error(py, e)),
        }
    }

    /// append an index entry
    def append(&self, tup: PyTuple) -> PyResult<PyObject> {
        if tup.len(py) < 8 {