quantumclaw/clawhdf5
3
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

format: monomorphise the Storage parsers so local files stay as fast

Browse Source 
Every `*_in` core and the read helpers take `file: &S` with
`S: Storage + ?Sized` instead of `&dyn Storage`, and the `&[u8]`
wrappers pass the slice itself, so they compile to a `[u8]` instance:
`as_contiguous()` inlines to `Some(self)` and each structure read is the
slice code's bounds check again, with no indirect call. `&dyn Storage`
still works (`S = dyn Storage`); there is one parser implementation.

Also, so the structure reads cost no more than the slice checks did:
- ObjectHeader::parse_in reads the prefix once (signature included)
  instead of the signature and then the prefix: two reads for a
  one-chunk header instead of three on a range backend;
- the symbol-table node and group B-tree (v1) loops walk their entries
  with chunks_exact over the bytes read, and the node's redundant second
  bounds check is gone (the entries' read is the check, same error);
- a version-1 header's message list is sized from its (capped) count.
Same results and errors; the unit and equivalence tests are unchanged.

New Criterion bench `clawhdf5/benches/local_metadata_bench.rs` over a
400-group version-1 file written by h5py (new fixture
`v1_groups_400.h5`): ObjectHeader::parse, symbol-table nodes, the group
B-tree walk and a facade listing, using only APIs that exist at f2ff2c4
so it builds there for an A/B.

Provisional A/B against f2ff2c4 (busy machine, not for docs): both
builds linked into one binary and timed in alternation, 200 rounds;
median ratio new/old: facade listing -0.5% to -3.5% (was +14%),
ObjectHeader::parse +1% to +2% (was +25%), symbol-table nodes -18%,
group B-tree walk -18%, local-heap names and resolve_group_children
within +-1.5%. An old-vs-old-copy run shows +-2% from code layout alone.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
This commit is contained in:
osobh
2026-09-26 14:22:37 -05:00
co-authored by Claude Opus 5.5
parent d2b25f154f
commit 052098bf36
18 changed files with 315 additions and 219 deletions
Download Patch File Download Diff File Expand all files Collapse all files
crates/clawhdf5-format/src/attribute.rs
+22 -22
View File
@@ -51,7 +51,7 @@ impl AttributeMessage {
///
/// `length_size` is needed for dataspace dimension parsing.
pub fn parse(data: &[u8], length_size: u8) -> Result<AttributeMessage, FormatError> {
Self::parse_impl(data, length_size, None)
Self::parse_impl(data, length_size, None::<(&[u8], u8)>)
}
/// [`AttributeMessage::parse`] with access to the rest of the file, which
@@ -66,24 +66,24 @@ impl AttributeMessage {
offset_size: u8,
length_size: u8,
) -> Result<AttributeMessage, FormatError> {
Self::parse_in_storage(data, &file_data, offset_size, length_size)
Self::parse_in_storage(data, file_data, offset_size, length_size)
}
/// [`AttributeMessage::parse_in_file`] with the file behind any
/// [`Storage`].
pub fn parse_in_storage(
pub fn parse_in_storage<S: Storage + ?Sized>(
data: &[u8],
file: &dyn Storage,
file: &S,
offset_size: u8,
length_size: u8,
) -> Result<AttributeMessage, FormatError> {
Self::parse_impl(data, length_size, Some((file, offset_size)))
}
fn parse_impl(
fn parse_impl<S: Storage + ?Sized>(
data: &[u8],
length_size: u8,
file: Option<(&dyn Storage, u8)>,
file: Option<(&S, u8)>,
) -> Result<AttributeMessage, FormatError> {
ensure_len(data, 0, 2)?;
let version = data[0];
@@ -98,12 +98,12 @@ impl AttributeMessage {
/// The bytes of an embedded datatype/dataspace message, following the
/// shared-message reference when `shared` is set.
fn embedded_message<'a>(
fn embedded_message<'a, S: Storage + ?Sized>(
bytes: &'a [u8],
shared: bool,
msg_type: MessageType,
length_size: u8,
file: Option<(&dyn Storage, u8)>,
file: Option<(&S, u8)>,
) -> Result<Cow<'a, [u8]>, FormatError> {
if !shared {
return Ok(Cow::Borrowed(bytes));
@@ -155,10 +155,10 @@ impl AttributeMessage {
})
}
fn parse_v2(
fn parse_v2<S: Storage + ?Sized>(
data: &[u8],
length_size: u8,
file: Option<(&dyn Storage, u8)>,
file: Option<(&S, u8)>,
) -> Result<AttributeMessage, FormatError> {
// Flags: bit 0 = datatype is shared, bit 1 = dataspace is shared.
let flags = data.get(1).copied().unwrap_or(0);
@@ -209,10 +209,10 @@ impl AttributeMessage {
})
}
fn parse_v3(
fn parse_v3<S: Storage + ?Sized>(
data: &[u8],
length_size: u8,
file: Option<(&dyn Storage, u8)>,
file: Option<(&S, u8)>,
) -> Result<AttributeMessage, FormatError> {
// Flags: bit 0 = datatype is shared, bit 1 = dataspace is shared.
let flags = data.get(1).copied().unwrap_or(0);
@@ -427,15 +427,15 @@ pub fn extract_attributes_full(
offset_size: u8,
length_size: u8,
) -> Result<Vec<AttributeMessage>, FormatError> {
extract_attributes_full_in(&file_data, header, offset_size, length_size)
extract_attributes_full_in(file_data, header, offset_size, length_size)
}
/// [`extract_attributes_full`] over any [`Storage`]. Dense attribute
/// storage is indexed by a v2 B-tree, which is not read over [`Storage`]
/// yet: on a backend without the whole file in memory an object with dense
/// attributes is [`FormatError::ContiguousStorageRequired`].
pub fn extract_attributes_full_in(
file: &dyn Storage,
pub fn extract_attributes_full_in<S: Storage + ?Sized>(
file: &S,
header: &ObjectHeader,
offset_size: u8,
length_size: u8,
@@ -457,13 +457,13 @@ pub fn extract_attributes_tolerant(
offset_size: u8,
length_size: u8,
) -> Result<(Vec<AttributeMessage>, Vec<FormatError>), FormatError> {
extract_attributes_tolerant_in(&file_data, header, offset_size, length_size)
extract_attributes_tolerant_in(file_data, header, offset_size, length_size)
}
/// [`extract_attributes_tolerant`] over any [`Storage`] (see
/// [`extract_attributes_full_in`] for dense storage).
pub fn extract_attributes_tolerant_in(
file_data: &dyn Storage,
pub fn extract_attributes_tolerant_in<S: Storage + ?Sized>(
file_data: &S,
header: &ObjectHeader,
offset_size: u8,
length_size: u8,
@@ -478,8 +478,8 @@ pub fn extract_attributes_tolerant_in(
/// Read every attribute; each one that fails goes to `on_error`, which
/// either stops the read (returns the error) or skips that attribute.
fn extract_attributes_with(
file_data: &dyn Storage,
fn extract_attributes_with<S: Storage + ?Sized>(
file_data: &S,
header: &ObjectHeader,
offset_size: u8,
length_size: u8,
@@ -572,8 +572,8 @@ fn find_attribute_info(
/// Extract attributes from dense storage (fractal heap + B-tree v2), and
/// each one's creation order into `orders`.
#[allow(clippy::too_many_arguments)]
fn extract_dense_attributes(
file_data: &dyn Storage,
fn extract_dense_attributes<S: Storage + ?Sized>(
file_data: &S,
attr_info: &AttributeInfoMessage,
fh_addr: u64,
offset_size: u8,