Added Clarion codes.#67
Open
asparsa wants to merge 1 commit into
Open
Conversation
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
Adds ClarIOn utilities for generating, persisting, and comparing call trees, plus a helper script to split trace files by PID.
Changes:
- Introduces a shared call tree node type and binary serialization/deserialization helpers.
- Adds two new binaries: one to build/deduplicate call trees and another to diff/visualize two saved call trees.
- Updates build system to compile the new binaries and install the split script.
Reviewed changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 16 comments.
Show a summary per file
| File | Description |
|---|---|
| src/dftracer/utils/utilities/call_tree/call_tree.h | Adds shared Node type and binary save/load helpers for call trees. |
| src/dftracer/utils/binaries/clarIOn_comparator.cpp | New CLI tool to diff two call trees and emit text or Graphviz .dot output. |
| src/dftracer/utils/binaries/clarIOn_calltree.cpp | New CLI tool to parse traces, build/deduplicate a call tree, and write outputs. |
| src/dftracer/utils/binaries/ClarIOn_split.sh | New script to split an input trace archive into per-PID gzip files. |
| src/CMakeLists.txt | Wires new binaries into the build and copies the split script to the bin dir. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| for (const Node* cb : b->children) | ||
| children_b[cb->name] = cb; | ||
|
|
||
| std::unordered_set<std::string> visited; |
| for (const Node* r : roots_b) map_b[r->name] = r; | ||
|
|
||
| std::vector<DiffNode*> result; | ||
| std::unordered_set<std::string> visited; |
Comment on lines
+22
to
+38
| #include <thread> | ||
|
|
||
| using namespace dftracer::utils; | ||
| using namespace dftracer::utils::utilities::indexer::internal; | ||
| using namespace dftracer::utils::utilities::reader::internal; | ||
| #include <algorithm> | ||
| #include <cmath> | ||
| #include <cstdio> | ||
| #include <cstring> | ||
| #include <functional> | ||
| #include <iostream> | ||
| #include <limits> | ||
| #include <memory> | ||
| #include <string> | ||
| #include <unordered_map> | ||
| #include <vector> | ||
|
|
| .scan<'g', double>(); | ||
| program.add_argument("--dot") | ||
| .help("Output a .dot file for visualization (optional)") | ||
| .default_value<bool>(true); |
Comment on lines
+411
to
+412
| " fillcolor=\"#6dcf94\", fontcolor=\"#FFFFFF\"," | ||
| " fontsize=10, shape=box];\n" |
Comment on lines
+80
to
+83
| fread(&name_len, sizeof(name_len), 1, f); | ||
| n->name.resize(name_len); | ||
| fread(n->name.data(), 1, name_len, f); | ||
| fread(&n->dur, sizeof(n->dur), 1, f); |
Comment on lines
+38
to
+46
| struct Node { | ||
| long long ts, dur, ts_end; | ||
| int depth = 0, count = 1; | ||
| std::string name; | ||
| long long max, min; | ||
| std::size_t structural_hash = 0; | ||
| std::vector<Node*> children; | ||
| std::unordered_map<std::size_t, Node*> child_map; | ||
| }; |
Comment on lines
+283
to
+286
| static constexpr uint32_t CALLTREE_MAGIC = 0xCA117EE1; | ||
| static constexpr uint32_t CALLTREE_VERSION = 0x00000001; | ||
|
|
||
| static void write_node(FILE* f, const Node* n) { |
| pipes[pid] = "gzip > " dir "/output-" pid ".pfw.gz" | ||
| } | ||
| print | pipes[pid] | ||
| } |
Comment on lines
880
to
+885
| target_set_warnings(${bin_exec}) | ||
| configure_file( | ||
| ${CMAKE_CURRENT_SOURCE_DIR}/dftracer/utils/binaries/clarIOn_split.sh | ||
| ${CMAKE_BINARY_DIR}/bin/ClarIOn_split.sh | ||
| COPYONLY | ||
| ) |
rayandrew
requested changes
May 21, 2026
Comment on lines
+330
to
+372
| program.add_description( | ||
| "ClarIOn utility for reading and creating call trees from compressed files (GZIP, " | ||
| "TAR.GZ)"); | ||
| program.add_argument("file") | ||
| .help("Compressed file to process (GZIP, TAR.GZ)") | ||
| .required(); | ||
| program.add_argument("-i", "--index") | ||
| .help("Index file to use") | ||
| .default_value<std::string>(""); | ||
| program.add_argument("-c", "--checkpoint-size") | ||
| .help("Checkpoint size for indexing in bytes (default: " + | ||
| default_checkpoint_size_str + ")") | ||
| .scan<'d', std::size_t>() | ||
| .default_value( | ||
| static_cast<std::size_t>(Indexer::DEFAULT_CHECKPOINT_SIZE)); | ||
| program.add_argument("-f", "--force-rebuild") | ||
| .help("Force rebuild index") | ||
| .flag(); | ||
| program.add_argument("--check").help("Check if index is valid").flag(); | ||
| program.add_argument("--read-buffer-size") | ||
| .help("Size of the read buffer in bytes (default: 1MB)") | ||
| .default_value<std::size_t>(1 * 1024 * 1024) | ||
| .scan<'d', std::size_t>(); | ||
| program.add_argument("--index-dir") | ||
| .help("Directory to store index files (default: system temp directory)") | ||
| .default_value<std::string>(""); | ||
| program.add_argument("-t", "--time-exclusive") | ||
| .help("Exclusive timing when building tree (default: inclusive)") | ||
| .flag(); | ||
| program.add_argument("-o", "--output") | ||
| .help("Output type: 'text' or 'binary' (default: text)") | ||
| .default_value<std::string>("text"); | ||
| try { | ||
| program.parse_args(argc, argv); | ||
| } catch (const std::exception &err) { | ||
| DFTRACER_UTILS_LOG_ERROR("Error occurred: %s", err.what()); | ||
| std::cerr << program; | ||
| return 1; | ||
| } | ||
|
|
||
| std::string gz_path = program.get<std::string>("file"); | ||
| std::string index_path = program.get<std::string>("--index"); | ||
| std::size_t checkpoint_size = Indexer::DEFAULT_CHECKPOINT_SIZE; // default 1MB |
Collaborator
There was a problem hiding this comment.
can you follow other binary patterns by extending cli::ArgParse?
Comment on lines
+535
to
+547
| std::vector<NodeList> per_thread_nodes(line_ranges.size()); | ||
| std::vector<std::thread> threads; | ||
| for (std::size_t i = 0; i < line_ranges.size(); ++i) { | ||
| auto [start_line, end_line] = line_ranges[i]; | ||
| threads.emplace_back(line_worker, | ||
| start_line, | ||
| end_line, | ||
| std::ref(per_thread_nodes[i]));} | ||
|
|
||
| // 4. Join threads | ||
| for (auto &t : threads) { | ||
| t.join(); | ||
| } |
Collaborator
There was a problem hiding this comment.
we have pipeline and executor via coroutine that can do this. can you reuse the pattern?
rayandrew
requested changes
May 21, 2026
Collaborator
rayandrew
left a comment
rayandrew
left a comment
There was a problem hiding this comment.
we also have TraceReader now to do this which i optimize greatly using coroutine.
please look at the API
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Clarion consists of three main files:
splitter, calltree, and comparator.
1 header file is also added for structures used in these files