##// END OF EJS Templates
revlog: add a mechanism to verify expected file position before appending...
revlog: add a mechanism to verify expected file position before appending If someone uses `hg debuglocks`, or some non-hg process writes to the .hg directory without respecting the locks, or if the repo's on a networked filesystem, it's possible for the revlog code to write out corrupted data. The form of this corruption can vary depending on what data was written and how that happened. We are in the "networked filesystem" case (though I've had users also do this to themselves with the "`hg debuglocks`" scenario), and most often see this with the changelog. What ends up happening is we produce two items (let's call them rev1 and rev2) in the .i file that have the same linkrev, baserev, and offset into the .d file, while the data in the .d file is appended properly. rev2's compressed_size is accurate for rev2, but when we go to decompress the data in the .d file, we use the offset that's recorded in the index file, which is the same as rev1, and attempt to decompress rev2.compressed_size bytes of rev1's data. This usually does not succeed. :) When using inline data, this also fails, though I haven't investigated why too closely. This shows up as a "patch decode" error. I believe what's happening there is that we're basically ignoring the offset field, getting the data properly, but since baserev != rev, it thinks this is a delta based on rev (instead of a full text) and can't actually apply it as such. For now, I'm going to make this an optional component and default it to entirely off. I may increase the default severity of this in the future, once I've enabled it for my users and we gain more experience with it. Luckily, most of my users have a versioned filesystem and can roll back to before the corruption has been written, it's just a hassle to do so and not everyone knows how (so it's a support burden). Users on other filesystems will not have that luxury, and this can cause them to have a corrupted repository that they are unlikely to know how to resolve, and they'll see this as a data-loss event. Refusing to create the corruption is a much better user experience. This mechanism is not perfect. There may be false-negatives (racy writes that are not detected). There should not be any false-positives (non-racy writes that are detected as such). This is not a mechanism that makes putting a repo on a networked filesystem "safe" or "supported", just *less* likely to cause corruption. Differential Revision: https://phab.mercurial-scm.org/D9952

File last commit:

r44704:6b7aef44 default
r47349:e9901d01 default
Show More
ref_sharing.rs
121 lines | 4.0 KiB | application/rls-services+xml | RustLexer
// ref_sharing.rs
//
// Copyright 2019 Raphaël Gomès <rgomes@octobus.net>
//
// Permission is hereby granted, free of charge, to any person obtaining a copy
// of this software and associated documentation files (the "Software"), to
// deal in the Software without restriction, including without limitation the
// rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
// sell copies of the Software, and to permit persons to whom the Software is
// furnished to do so, subject to the following conditions:
//
// The above copyright notice and this permission notice shall be included in
// all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
// FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
// IN THE SOFTWARE.
//! Macros for use in the `hg-cpython` bridge library.
/// Defines a `py_class!` that acts as a Python iterator over a Rust iterator.
///
/// TODO: this is a bit awkward to use, and a better (more complicated)
/// procedural macro would simplify the interface a lot.
///
/// # Parameters
///
/// * `$name` is the identifier to give to the resulting Rust struct.
/// * `$leaked` corresponds to `UnsafePyLeaked` in the matching `@shared data`
/// declaration.
/// * `$iterator_type` is the type of the Rust iterator.
/// * `$success_func` is a function for processing the Rust `(key, value)`
/// tuple on iteration success, turning it into something Python understands.
/// * `$success_func` is the return type of `$success_func`
///
/// # Safety
///
/// `$success_func` may take a reference, but it's lifetime may be cheated.
/// Do not copy it out of the function call.
///
/// # Example
///
/// ```
/// struct MyStruct {
/// inner: HashMap<Vec<u8>, Vec<u8>>;
/// }
///
/// py_class!(pub class MyType |py| {
/// @shared data inner: MyStruct;
///
/// def __iter__(&self) -> PyResult<MyTypeItemsIterator> {
/// let leaked_ref = self.inner_shared(py).leak_immutable();
/// MyTypeItemsIterator::from_inner(
/// py,
/// unsafe { leaked_ref.map(py, |o| o.iter()) },
/// )
/// }
/// });
///
/// impl MyType {
/// fn translate_key_value(
/// py: Python,
/// res: (&Vec<u8>, &Vec<u8>),
/// ) -> PyResult<Option<(PyBytes, PyBytes)>> {
/// let (f, entry) = res;
/// Ok(Some((
/// PyBytes::new(py, f),
/// PyBytes::new(py, entry),
/// )))
/// }
/// }
///
/// py_shared_iterator!(
/// MyTypeItemsIterator,
/// UnsafePyLeaked<HashMap<'static, Vec<u8>, Vec<u8>>>,
/// MyType::translate_key_value,
/// Option<(PyBytes, PyBytes)>
/// );
/// ```
macro_rules! py_shared_iterator {
(
$name: ident,
$leaked: ty,
$success_func: expr,
$success_type: ty
) => {
py_class!(pub class $name |py| {
data inner: RefCell<$leaked>;
def __next__(&self) -> PyResult<$success_type> {
let mut leaked = self.inner(py).borrow_mut();
let mut iter = unsafe { leaked.try_borrow_mut(py)? };
match iter.next() {
None => Ok(None),
// res may be a reference of cheated 'static lifetime
Some(res) => $success_func(py, res),
}
}
def __iter__(&self) -> PyResult<Self> {
Ok(self.clone_ref(py))
}
});
impl $name {
pub fn from_inner(
py: Python,
leaked: $leaked,
) -> PyResult<Self> {
Self::create_instance(
py,
RefCell::new(leaked),
)
}
}
};
}