Skip to content

⚡ Bolt: [performance improvement] Optimize Tarjan DFS allocations #234

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
bashandbone wants to merge 1 commit into
base: main
Choose a base branch
from
Open

⚡ Bolt: [performance improvement] Optimize Tarjan DFS allocations #234

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 6 additions & 4 deletions crates/ast-engine/src/tree_sitter/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -553,9 +553,8 @@ impl ContentExt for String {
let mut bytes = std::mem::take(self).into_bytes();
let original_len = bytes.len();
bytes.splice(safe_start..safe_end, full_inserted);
*self = Self::from_utf8(bytes).unwrap_or_else(|e| {
Self::from_utf8_lossy(&e.into_bytes()).into_owned()
});
*self = Self::from_utf8(bytes)
.unwrap_or_else(|e| Self::from_utf8_lossy(&e.into_bytes()).into_owned());

// We calculate new_end_byte using the difference in the new overall string length
// to correctly align the end offset, taking any potential replacement bytes from
Expand Down Expand Up @@ -791,7 +790,10 @@ mod test {

let tree2 = parse_lang(|p| p.parse(&src, Some(&tree)), &Tsx.get_ts_language())?;
let fresh_tree = parse(&src)?;
assert_eq!(tree2.root_node().to_sexp(), fresh_tree.root_node().to_sexp());
assert_eq!(
tree2.root_node().to_sexp(),
fresh_tree.root_node().to_sexp()
);
Ok(())
}
}
17 changes: 9 additions & 8 deletions crates/flow/src/incremental/invalidation.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -340,13 +340,14 @@ impl InvalidationDetector {

/// DFS helper for Tarjan's algorithm
fn tarjan_dfs(&self, v: &Path, state: &mut TarjanState, sccs: &mut Vec<Vec<PathBuf>>) {
let v_buf = v.to_path_buf();
// Initialize node
let index = state.index_counter;
state.indices.insert(v.to_path_buf(), index);
state.lowlinks.insert(v.to_path_buf(), index);
state.indices.insert(v_buf.clone(), index);
state.lowlinks.insert(v_buf.clone(), index);
state.index_counter += 1;
state.stack.push(v.to_path_buf());
state.on_stack.insert(v.to_path_buf());
state.stack.push(v_buf.clone());
state.on_stack.insert(v_buf.clone());
Comment on lines 348 to +350
Copy link
Copy Markdown
Contributor

@sourcery-ai sourcery-ai Bot May 15, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

suggestion (performance): Reduce redundant cloning of v_buf when initializing Tarjan state for a node.

v_buf is now allocated once, which is good, but it’s still cloned four times (for indices, lowlinks, stack, and on_stack). You can avoid one clone by moving v_buf into the last insertion:

let v_buf = v.to_path_buf();
state.indices.insert(v_buf.clone(), index);
state.lowlinks.insert(v_buf.clone(), index);
state.stack.push(v_buf.clone());
state.on_stack.insert(v_buf);
Suggested change
state.index_counter += 1;
state.stack.push(v.to_path_buf());
state.on_stack.insert(v.to_path_buf());
state.stack.push(v_buf.clone());
state.on_stack.insert(v_buf.clone());
state.index_counter += 1;
state.stack.push(v_buf.clone());
state.on_stack.insert(v_buf);


// Visit all successors (dependencies)
let dependencies = self.graph.get_dependencies(v);
Expand All @@ -358,19 +359,19 @@ impl InvalidationDetector {

// Update lowlink
let w_lowlink = *state.lowlinks.get(dep).unwrap();
let v_lowlink = state.lowlinks.get_mut(&v.to_path_buf()).unwrap();
let v_lowlink = state.lowlinks.get_mut(v).unwrap();
*v_lowlink = (*v_lowlink).min(w_lowlink);
} else if state.on_stack.contains(dep) {
// Successor is on stack (part of current SCC)
let w_index = *state.indices.get(dep).unwrap();
let v_lowlink = state.lowlinks.get_mut(&v.to_path_buf()).unwrap();
let v_lowlink = state.lowlinks.get_mut(v).unwrap();
*v_lowlink = (*v_lowlink).min(w_index);
}
}

// If v is a root node, pop the stack to create an SCC
let v_index = *state.indices.get(&v.to_path_buf()).unwrap();
let v_lowlink = *state.lowlinks.get(&v.to_path_buf()).unwrap();
let v_index = *state.indices.get(v).unwrap();
let v_lowlink = *state.lowlinks.get(v).unwrap();

if v_lowlink == v_index {
let mut scc = Vec::new();
Expand Down
8 changes: 4 additions & 4 deletions crates/rule-engine/src/check_var.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -104,9 +104,9 @@ fn get_vars_from_rules<'r>(rule: &'r Rule, utils: &'r RuleRegistration) -> Rapid
vars
}

fn check_var_in_constraints<'r>(
fn check_var_in_constraints(
mut vars: RapidSet<String>,
constraints: &'r RapidMap<thread_ast_engine::meta_var::MetaVariableID, Rule>,
constraints: &RapidMap<thread_ast_engine::meta_var::MetaVariableID, Rule>,
) -> RResult<RapidSet<String>> {
for rule in constraints.values() {
for var in rule.defined_vars() {
Expand All @@ -125,9 +125,9 @@ fn check_var_in_constraints<'r>(
Ok(vars)
}

fn check_var_in_transform<'r>(
fn check_var_in_transform(
mut vars: RapidSet<String>,
transform: &'r Option<Transform>,
transform: &Option<Transform>,
) -> RResult<RapidSet<String>> {
let Some(transform) = transform else {
return Ok(vars);
Expand Down
6 changes: 5 additions & 1 deletion crates/rule-engine/src/rule/mod.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -246,7 +246,11 @@ impl Rule {

pub fn defined_vars(&self) -> RapidSet<String> {
match self {
Rule::Pattern(p) => p.defined_vars().into_iter().map(|s| s.to_string()).collect(),
Rule::Pattern(p) => p
.defined_vars()
.into_iter()
.map(|s| s.to_string())
.collect(),
Rule::Kind(_) => RapidSet::default(),
Rule::Regex(_) => RapidSet::default(),
Rule::NthChild(n) => n.defined_vars(),
Expand Down
5 changes: 1 addition & 4 deletions crates/rule-engine/src/rule/referent_rule.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,10 +27,7 @@ impl<R> Clone for Registration<R> {

impl<R> Registration<R> {
fn read(&self) -> Arc<RapidMap<String, R>> {
self.0
.read()
.unwrap_or_else(|e| e.into_inner())
.clone()
self.0.read().unwrap_or_else(|e| e.into_inner()).clone()
}
pub(crate) fn contains_key(&self, key: &str) -> bool {
self.read().contains_key(key)
Expand Down