cpython/Modules/_remote_debugging/binary_io.h at main · python/cpython · GitHub

History

722 lines (630 loc) · 23.5 KB

Raw

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

149

150

151

152

153

154

155

156

157

158

159

160

161

162

163

164

165

166

167

168

169

170

171

172

173

174

175

176

177

178

179

180

181

182

183

184

185

186

187

188

189

190

191

192

193

194

195

196

197

198

199

200

201

202

203

204

205

206

207

208

209

210

211

212

213

214

215

216

217

218

219

220

221

222

223

224

225

226

227

228

229

230

231

232

233

234

235

236

237

238

239

240

241

242

243

244

245

246

247

248

249

250

251

252

253

254

255

256

257

258

259

260

261

262

263

264

265

266

267

268

269

270

271

272

273

274

275

276

277

278

279

280

281

282

283

284

285

286

287

288

289

290

291

292

293

294

295

296

297

298

299

300

301

302

303

304

305

306

307

308

309

310

311

312

313

314

315

316

317

318

319

320

321

322

323

324

325

326

327

328

329

330

331

332

333

334

335

336

337

338

339

340

341

342

343

344

345

346

347

348

349

350

351

352

353

354

355

356

357

358

359

360

361

362

363

364

365

366

367

368

369

370

371

372

373

374

375

376

377

378

379

380

381

382

383

384

385

386

387

388

389

390

391

392

393

394

395

396

397

398

399

400

401

402

403

404

405

406

407

408

409

410

411

412

413

414

415

416

417

418

419

420

421

422

423

424

425

426

427

428

429

430

431

432

433

434

435

436

437

438

439

440

441

442

443

444

445

446

447

448

449

450

451

452

453

454

455

456

457

458

459

460

461

462

463

464

465

466

467

468

469

470

471

472

473

474

475

476

477

478

479

480

481

482

483

484

485

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

617

618

619

620

621

622

623

624

625

626

627

628

629

630

631

632

633

634

635

636

637

638

639

640

641

642

643

644

645

646

647

648

649

650

651

652

653

654

655

656

657

658

659

660

661

662

663

664

665

666

667

668

669

670

671

672

673

674

675

676

677

678

679

680

681

682

683

684

685

686

687

688

689

690

691

692

693

694

695

696

697

698

699

700

701

702

703

704

705

706

707

708

709

710

711

712

713

714

715

716

717

718

719

720

721

722

/******************************************************************************

* Python Remote Debugging Module - Binary I/O Header

* This header provides declarations for high-performance binary file I/O

* for profiling data with optional zstd streaming compression.

******************************************************************************/

#ifndef Py_BINARY_IO_H

#define Py_BINARY_IO_H

#ifdef __cplusplus

extern "C" {

#endif

#include "Python.h"

#include "pycore_hashtable.h"

#include <stdint.h>

#include <stdio.h>

/* ============================================================================

* BINARY FORMAT CONSTANTS

* ============================================================================ */

#define BINARY_FORMAT_MAGIC 0x54414348 /* "TACH" (Tachyon) in native byte order */

#define BINARY_FORMAT_MAGIC_SWAPPED 0x48434154 /* Byte-swapped magic for endianness detection */

#define BINARY_FORMAT_VERSION 1

/* Sentinel values for optional frame fields */

#define OPCODE_NONE 255 /* No opcode captured (u8 sentinel) */

#define LOCATION_NOT_AVAILABLE (-1) /* lineno/column not available (zigzag sentinel) */

/* Conditional byte-swap macros for cross-endian file reading.

* Uses Python's optimized byte-swap functions from pycore_bitutils.h */

#define SWAP16_IF(swap, x) ((swap) ? _Py_bswap16(x) : (x))

#define SWAP32_IF(swap, x) ((swap) ? _Py_bswap32(x) : (x))

#define SWAP64_IF(swap, x) ((swap) ? _Py_bswap64(x) : (x))

/* Header field offsets and sizes */

#define HDR_OFF_MAGIC 0

#define HDR_SIZE_MAGIC 4

#define HDR_OFF_VERSION (HDR_OFF_MAGIC + HDR_SIZE_MAGIC)

#define HDR_SIZE_VERSION 4

#define HDR_OFF_PY_VERSION (HDR_OFF_VERSION + HDR_SIZE_VERSION)

#define HDR_SIZE_PY_VERSION 4 /* 3 bytes: major, minor, micro + 1 reserved */

#define HDR_OFF_PY_MAJOR HDR_OFF_PY_VERSION

#define HDR_OFF_PY_MINOR (HDR_OFF_PY_VERSION + 1)

#define HDR_OFF_PY_MICRO (HDR_OFF_PY_VERSION + 2)

#define HDR_OFF_START_TIME (HDR_OFF_PY_VERSION + HDR_SIZE_PY_VERSION)

#define HDR_SIZE_START_TIME 8

#define HDR_OFF_INTERVAL (HDR_OFF_START_TIME + HDR_SIZE_START_TIME)

#define HDR_SIZE_INTERVAL 8

#define HDR_OFF_SAMPLES (HDR_OFF_INTERVAL + HDR_SIZE_INTERVAL)

#define HDR_SIZE_SAMPLES 8

#define HDR_OFF_THREADS (HDR_OFF_SAMPLES + HDR_SIZE_SAMPLES)

#define HDR_SIZE_THREADS 4

#define HDR_OFF_STR_TABLE (HDR_OFF_THREADS + HDR_SIZE_THREADS)

#define HDR_SIZE_STR_TABLE 8

#define HDR_OFF_FRAME_TABLE (HDR_OFF_STR_TABLE + HDR_SIZE_STR_TABLE)

#define HDR_SIZE_FRAME_TABLE 8

#define HDR_OFF_COMPRESSION (HDR_OFF_FRAME_TABLE + HDR_SIZE_FRAME_TABLE)

#define HDR_SIZE_COMPRESSION 4

#define FILE_HEADER_SIZE (HDR_OFF_COMPRESSION + HDR_SIZE_COMPRESSION)

#define FILE_HEADER_PLACEHOLDER_SIZE 64

static_assert(FILE_HEADER_SIZE <= FILE_HEADER_PLACEHOLDER_SIZE,

"FILE_HEADER_SIZE exceeds FILE_HEADER_PLACEHOLDER_SIZE");

/* Sample header field offsets and sizes */

#define SMP_OFF_THREAD_ID 0

#define SMP_SIZE_THREAD_ID sizeof(uint64_t)

#define SMP_OFF_INTERPRETER_ID (SMP_OFF_THREAD_ID + SMP_SIZE_THREAD_ID)

#define SMP_SIZE_INTERPRETER_ID sizeof(uint32_t)

#define SMP_OFF_ENCODING (SMP_OFF_INTERPRETER_ID + SMP_SIZE_INTERPRETER_ID)

#define SMP_SIZE_ENCODING sizeof(uint8_t)

#define SAMPLE_HEADER_FIXED_SIZE (SMP_OFF_ENCODING + SMP_SIZE_ENCODING)

static_assert(SAMPLE_HEADER_FIXED_SIZE == 13,

"SAMPLE_HEADER_FIXED_SIZE must remain 13");

/* Footer field offsets and sizes */

#define FTR_OFF_STRINGS 0

#define FTR_SIZE_STRINGS sizeof(uint32_t)

#define FTR_OFF_FRAMES (FTR_OFF_STRINGS + FTR_SIZE_STRINGS)

#define FTR_SIZE_FRAMES sizeof(uint32_t)

#define FTR_OFF_FILE_SIZE (FTR_OFF_FRAMES + FTR_SIZE_FRAMES)

#define FTR_SIZE_FILE_SIZE sizeof(uint64_t)

#define FTR_OFF_CHECKSUM (FTR_OFF_FILE_SIZE + FTR_SIZE_FILE_SIZE)

#define FTR_SIZE_CHECKSUM (2 * sizeof(uint64_t))

#define FILE_FOOTER_SIZE (FTR_OFF_CHECKSUM + FTR_SIZE_CHECKSUM)

static_assert(FILE_FOOTER_SIZE == 32,

"FILE_FOOTER_SIZE must remain 32");

/* Optional profiling statistics immediately precede the footer. The

* signature and size live at the end so readers can discover extensions

* without changing the fixed header or moving streamed sample data. */

#define PROFILE_STATS_MAGIC "TACHSTAT"

#define PROFILE_STATS_MAGIC_SIZE 8

#define PROFILE_STATS_VERSION 1

#define PST_OFF_DURATION 0

#define PST_SIZE_DURATION 8

#define PST_OFF_SAMPLE_RATE (PST_OFF_DURATION + PST_SIZE_DURATION)

#define PST_SIZE_SAMPLE_RATE 8

#define PST_OFF_ERROR_RATE (PST_OFF_SAMPLE_RATE + PST_SIZE_SAMPLE_RATE)

#define PST_SIZE_ERROR_RATE 8

#define PST_OFF_MISSED_SAMPLES (PST_OFF_ERROR_RATE + PST_SIZE_ERROR_RATE)

#define PST_SIZE_MISSED_SAMPLES 8

#define PST_OFF_PRESENT (PST_OFF_MISSED_SAMPLES + PST_SIZE_MISSED_SAMPLES)

#define PST_SIZE_PRESENT 4

#define PST_OFF_RESERVED (PST_OFF_PRESENT + PST_SIZE_PRESENT)

#define PST_SIZE_RESERVED 4

#define PST_OFF_MAGIC (PST_OFF_RESERVED + PST_SIZE_RESERVED)

#define PST_OFF_VERSION (PST_OFF_MAGIC + PROFILE_STATS_MAGIC_SIZE)

#define PST_SIZE_VERSION 4

#define PST_OFF_SIZE (PST_OFF_VERSION + PST_SIZE_VERSION)

#define PST_SIZE_SIZE 4

#define PROFILE_STATS_SIZE (PST_OFF_SIZE + PST_SIZE_SIZE)

#define PROFILE_STATS_V1_SIZE 32

#define PROFILE_STATS_ERROR_RATE 0x01

#define PROFILE_STATS_MISSED 0x02

static_assert(PROFILE_STATS_SIZE == 56,

"PROFILE_STATS_SIZE must remain 56");

/* Minimum on-disk bytes of a string (1) and frame (7) table entry. */

#define MIN_STRING_ENTRY_SIZE 1

#define MIN_FRAME_ENTRY_SIZE 7

/* Buffer sizes: 512KB balances syscall amortization against memory use,

* and aligns well with filesystem block sizes and zstd dictionary windows */

#define WRITE_BUFFER_SIZE (512 * 1024)

#define COMPRESSED_BUFFER_SIZE (512 * 1024)

/* Compression types */

#define COMPRESSION_NONE 0

#define COMPRESSION_ZSTD 1

/* Stack encoding types for delta compression */

#define STACK_REPEAT 0x00 /* RLE: identical to previous, with count */

#define STACK_FULL 0x01 /* Full stack (first sample or no match) */

#define STACK_SUFFIX 0x02 /* Shares N frames from bottom */

#define STACK_POP_PUSH 0x03 /* Remove M frames, add N frames */

/* Maximum stack depth we'll buffer for delta encoding */

#define MAX_STACK_DEPTH 256

/* Initial capacities for dynamic arrays - sized to reduce reallocations */

#define INITIAL_STRING_CAPACITY 4096

#define INITIAL_FRAME_CAPACITY 4096

#define INITIAL_THREAD_CAPACITY 256

/* ============================================================================

* STATISTICS STRUCTURES

* ============================================================================ */

/* Writer statistics - tracks encoding efficiency */

typedef struct {

uint64_t repeat_records; /* Number of RLE repeat records written */

uint64_t repeat_samples; /* Total samples encoded via RLE */

uint64_t full_records; /* Number of full stack records */

uint64_t suffix_records; /* Number of suffix match records */

uint64_t pop_push_records; /* Number of pop-push records */

uint64_t total_frames_written;/* Total frame indices written */

uint64_t frames_saved; /* Frames avoided due to delta encoding */

uint64_t bytes_written; /* Total bytes written (before compression) */

} BinaryWriterStats;

/* Reader statistics - tracks reconstruction performance */

typedef struct {

uint64_t repeat_records; /* RLE records decoded */

uint64_t repeat_samples; /* Samples decoded from RLE */

uint64_t full_records; /* Full stack records decoded */

uint64_t suffix_records; /* Suffix match records decoded */

uint64_t pop_push_records; /* Pop-push records decoded */

uint64_t total_samples; /* Total samples reconstructed */

uint64_t stack_reconstructions; /* Number of stack array reconstructions */

} BinaryReaderStats;

/* ============================================================================

* PLATFORM ABSTRACTION

* ============================================================================ */

#if defined(__linux__) || defined(__APPLE__)

#include <sys/mman.h>

#include <unistd.h>

#include <sys/stat.h>

#include <fcntl.h>

#define USE_MMAP 1

#else

#define USE_MMAP 0

#endif

/* 64-bit file position support for files larger than 2GB.

* On POSIX: use ftello/fseeko with off_t (already 64-bit on 64-bit systems)

* On Windows: use _ftelli64/_fseeki64 with __int64 */

#if defined(_WIN32) || defined(_WIN64)

#include <io.h>

typedef __int64 file_offset_t;

#define FTELL64(fp) _ftelli64(fp)

#define FSEEK64(fp, offset, whence) _fseeki64(fp, offset, whence)

#else

/* POSIX - off_t is 64-bit on 64-bit systems, ftello/fseeko handle large files */

typedef off_t file_offset_t;

#define FTELL64(fp) ftello(fp)

#define FSEEK64(fp, offset, whence) fseeko(fp, offset, whence)

#endif

/* Forward declare zstd types if available */

#ifdef HAVE_ZSTD

#include <zstd.h>

#endif

/* Branch prediction hints - same as Objects/obmalloc.c */

#if (defined(__clang__) || (defined(__GNUC__) && (__GNUC__ > 2))) && defined(__OPTIMIZE__)

# define UNLIKELY(value) __builtin_expect((value), 0)

# define LIKELY(value) __builtin_expect((value), 1)

#else

# define UNLIKELY(value) (value)

# define LIKELY(value) (value)

#endif

/* ============================================================================

* BINARY WRITER STRUCTURES

* ============================================================================ */

/* zstd compression state (only used if HAVE_ZSTD defined) */

typedef struct {

#ifdef HAVE_ZSTD

ZSTD_CCtx *cctx; /* Modern API: CCtx and CStream are the same since v1.3.0 */

#else

void *cctx; /* Placeholder */

#endif

uint8_t *compressed_buffer;

size_t compressed_buffer_size;

} ZstdCompressor;

/* Frame entry - combines all frame data for better cache locality.

* Stores full source position (line, end_line, column, end_column) and opcode.

* Delta values are computed during serialization for efficiency. */

typedef struct {

uint32_t filename_idx;

uint32_t funcname_idx;

int32_t lineno; /* Start line number (-1 for synthetic frames) */

int32_t end_lineno; /* End line number (-1 if not available) */

int32_t column; /* Start column in UTF-8 bytes (-1 if not available) */

int32_t end_column; /* End column in UTF-8 bytes (-1 if not available) */

uint8_t opcode; /* Python opcode (0-254) or OPCODE_NONE (255) */

} FrameEntry;

/* Frame key for hash table lookup - includes all fields for proper deduplication */

typedef struct {

uint32_t filename_idx;

uint32_t funcname_idx;

int32_t lineno;

int32_t end_lineno;

int32_t column;

int32_t end_column;

uint8_t opcode;

} FrameKey;

/* Thread entry - tracks per-thread state for delta encoding */

typedef struct {

uint64_t thread_id;

uint64_t prev_timestamp;

uint32_t interpreter_id;

/* Previous stack for delta encoding (frame indices, innermost first) */

uint32_t *prev_stack;

size_t prev_stack_depth;

size_t prev_stack_capacity;

/* RLE pending buffer - samples waiting to be written as a repeat group */

uint8_t *pending_rle;

size_t pending_rle_bytes;

size_t pending_rle_samples;

} ThreadEntry;

/* Main binary writer structure */

typedef struct {

FILE *fp;

/* Write buffer for batched I/O */

uint8_t *write_buffer;

size_t buffer_pos;

size_t buffer_size;

/* Compression */

int compression_type;

ZstdCompressor zstd;

/* Metadata */

uint64_t start_time_us;

uint64_t sample_interval_us;

uint64_t total_samples;

double duration_sec;

double sample_rate;

double error_rate;

double missed_samples;

uint32_t profile_stats_present;

int has_profile_stats;

/* String hash table: PyObject* -> uint32_t index */

_Py_hashtable_t *string_hash;

/* String storage: array of UTF-8 encoded strings */

char **strings;

size_t *string_lengths;

size_t string_count;

size_t string_capacity;

/* Frame hash table: FrameKey* -> uint32_t index */

_Py_hashtable_t *frame_hash;

/* Frame storage: combined struct for better cache locality */

FrameEntry *frame_entries;

size_t frame_count;

size_t frame_capacity;

/* Thread timestamp tracking for delta encoding - combined for cache locality */

ThreadEntry *thread_entries;

size_t thread_count;

size_t thread_capacity;

/* Statistics */

BinaryWriterStats stats;

} BinaryWriter;

/* ============================================================================

* BINARY READER STRUCTURES

* ============================================================================ */

/* Per-thread state for stack reconstruction during replay */

typedef struct {

uint64_t thread_id;

uint32_t interpreter_id;

uint64_t prev_timestamp;

/* Reconstructed stack buffer (frame indices, innermost first) */

uint32_t *current_stack;

size_t current_stack_depth;

size_t current_stack_capacity;

} ReaderThreadState;

/* Main binary reader structure */

typedef struct {

#if USE_MMAP

uint8_t *mapped_data;

size_t mapped_size;

#else

FILE *fp;

uint8_t *file_data;

size_t file_size;

#endif

/* Decompression state */

int compression_type;

/* Note: ZSTD_DCtx is not stored - created/freed during decompression */

uint8_t *decompressed_data;

size_t decompressed_size;

/* Header metadata */

uint8_t py_major;

uint8_t py_minor;

uint8_t py_micro;

int needs_swap; /* Non-zero if file was written on different-endian system */

uint64_t start_time_us;

uint64_t sample_interval_us;

uint64_t sample_count;

uint32_t thread_count;

double duration_sec;

double sample_rate;

double error_rate;

double missed_samples;

uint32_t profile_stats_present;

int has_profile_stats;

uint64_t string_table_offset;

uint64_t frame_table_offset;

/* Parsed string table: array of Python string objects */

PyObject **strings;

uint32_t strings_count;

/* Parsed frame table: array of FrameEntry structures */

FrameEntry *frames;

uint32_t frames_count;

/* Sample data region */

uint8_t *sample_data;

size_t sample_data_size;

/* Per-thread state for stack reconstruction (used during replay) */

ReaderThreadState *thread_states;

size_t thread_state_count;

size_t thread_state_capacity;

/* Statistics */

BinaryReaderStats stats;

} BinaryReader;

/* ============================================================================

* VARINT ENCODING/DECODING (INLINE FOR PERFORMANCE)

* ============================================================================ */

/* Encode unsigned 64-bit varint (LEB128). Returns bytes written. */

static inline size_t

encode_varint_u64(uint8_t *buf, uint64_t value)

{

/* Fast path for single-byte values (0-127) - very common case */

if (value < 0x80) {

buf[0] = (uint8_t)value;

return 1;

}

size_t i = 0;

while (value >= 0x80) {

buf[i++] = (uint8_t)((value & 0x7F) | 0x80);

value >>= 7;

}

buf[i++] = (uint8_t)(value & 0x7F);

return i;

}

/* Encode unsigned 32-bit varint. Returns bytes written. */

static inline size_t

encode_varint_u32(uint8_t *buf, uint32_t value)

{

return encode_varint_u64(buf, value);

}

/* Encode signed 32-bit varint (zigzag encoding). Returns bytes written. */

static inline size_t

encode_varint_i32(uint8_t *buf, int32_t value)

{

/* Zigzag encode: map signed to unsigned */

uint32_t zigzag = ((uint32_t)value << 1) ^ (uint32_t)(value >> 31);

return encode_varint_u32(buf, zigzag);

}

/* Decode unsigned 64-bit varint (LEB128). Updates offset only on success.

* On error (overflow or incomplete), offset is NOT updated, allowing callers

* to detect errors via (offset == prev_offset) check. Sets PyErr on error. */

static inline uint64_t

decode_varint_u64(const uint8_t *data, size_t *offset, size_t max_size)

{

size_t pos = *offset;

uint64_t result = 0;

int shift = 0;

/* Fast path for single-byte varints (0-127) - most common case */

if (LIKELY(pos < max_size && (data[pos] & 0x80) == 0)) {

*offset = pos + 1;

return data[pos];

}

while (pos < max_size) {

uint8_t byte = data[pos++];

result |= (uint64_t)(byte & 0x7F) << shift;

if ((byte & 0x80) == 0) {

*offset = pos;

return result;

}

shift += 7;

if (UNLIKELY(shift >= 64)) {

PyErr_SetString(PyExc_ValueError, "Invalid or incomplete varint in binary data");

return 0;

}

PyErr_SetString(PyExc_ValueError, "Invalid or incomplete varint in binary data");

return 0;

}

/* Decode unsigned 32-bit varint. If value exceeds UINT32_MAX, treats as error. */

static inline uint32_t

decode_varint_u32(const uint8_t *data, size_t *offset, size_t max_size)

{

size_t saved_offset = *offset;

uint64_t value = decode_varint_u64(data, offset, max_size);

if (*offset == saved_offset) {

return 0; /* decode_varint_u64 already set PyErr */

}

if (UNLIKELY(value > UINT32_MAX)) {

*offset = saved_offset;

PyErr_SetString(PyExc_ValueError, "Invalid or incomplete varint in binary data");

return 0;

}

return (uint32_t)value;

}

/* Decode signed 32-bit varint (zigzag encoding). */

static inline int32_t

decode_varint_i32(const uint8_t *data, size_t *offset, size_t max_size)

{

size_t saved_offset = *offset;

uint32_t zigzag = decode_varint_u32(data, offset, max_size);

if (*offset == saved_offset) {

return 0; /* decode_varint_u32 already set PyErr */

}

return (int32_t)((zigzag >> 1) ^ -(int32_t)(zigzag & 1));

}

/* ============================================================================

* SHARED UTILITY FUNCTIONS

* ============================================================================ */

/* Generic array growth - returns new pointer or NULL (sets PyErr_NoMemory)

* Includes overflow checking for capacity doubling and allocation size. */

static inline void *

grow_array(void *ptr, size_t *capacity, size_t elem_size)

{

size_t old_cap = *capacity;

/* Check for overflow when doubling capacity */

if (old_cap > SIZE_MAX / 2) {

PyErr_SetString(PyExc_OverflowError, "Array capacity overflow");

return NULL;

}

size_t new_cap = old_cap * 2;

/* Check for overflow when calculating allocation size */

if (new_cap > SIZE_MAX / elem_size) {

PyErr_SetString(PyExc_OverflowError, "Array allocation size overflow");

return NULL;

}

void *new_ptr = PyMem_Realloc(ptr, new_cap * elem_size);

if (new_ptr) {

*capacity = new_cap;

} else {

PyErr_NoMemory();

}

return new_ptr;

}

static inline int

grow_array_inplace(void **ptr_addr, size_t count, size_t *capacity, size_t elem_size)

{

if (count < *capacity) {

return 0;

}

void *tmp = grow_array(*ptr_addr, capacity, elem_size);

if (tmp == NULL) {

return -1;

}

*ptr_addr = tmp;

return 0;

}

#define GROW_ARRAY(ptr, count, cap, type) \

grow_array_inplace((void**)&(ptr), (count), &(cap), sizeof(type))

/* ============================================================================

* BINARY WRITER API

* ============================================================================ */

* Create a new binary writer.

* Arguments:

* path: Path to output file

* sample_interval_us: Sampling interval in microseconds

* compression_type: COMPRESSION_NONE or COMPRESSION_ZSTD

* start_time_us: Start timestamp in microseconds (from time.monotonic() * 1e6)

* Returns:

* New BinaryWriter* on success, NULL on failure (PyErr set)

BinaryWriter *binary_writer_create(

PyObject *path,

uint64_t sample_interval_us,

int compression_type,

uint64_t start_time_us

);

* Write a sample to the binary file.

* Arguments:

* writer: Writer from binary_writer_create

* stack_frames: List of InterpreterInfo struct sequences

* timestamp_us: Current timestamp in microseconds (from time.monotonic() * 1e6)

* Returns:

* 0 on success, -1 on failure (PyErr set)

int binary_writer_write_sample(

BinaryWriter *writer,

PyObject *stack_frames,

uint64_t timestamp_us

);

* Finalize and close the binary file.

* Writes string/frame tables, footer, and updates header.

* Arguments:

* writer: Writer to finalize

* Returns:

* 0 on success, -1 on failure (PyErr set)

int binary_writer_finalize(BinaryWriter *writer);

/* Store measured statistics to write during finalization. */

int binary_writer_set_stats(

BinaryWriter *writer,

double duration_sec,

double sample_rate,

double error_rate,

double missed_samples,

uint32_t present

);

* Destroy a binary writer and free all resources.

* Safe to call even if writer is partially initialized.

* Arguments:

* writer: Writer to destroy (may be NULL)

void binary_writer_destroy(BinaryWriter *writer);

/* ============================================================================

* BINARY READER API

* ============================================================================ */

* Open a binary file for reading.

* Arguments:

* path: Path to input file

* Returns:

* New BinaryReader* on success, NULL on failure (PyErr set)

BinaryReader *binary_reader_open(PyObject *path);

* Replay samples from binary file through a collector.

* Arguments:

* reader: Reader from binary_reader_open

* collector: Python collector with collect() method

* progress_callback: Optional callable(current, total) or NULL

* Returns:

* Number of samples replayed on success, -1 on failure (PyErr set)

Py_ssize_t binary_reader_replay(

BinaryReader *reader,

PyObject *collector,

PyObject *progress_callback

);

* Get metadata about the binary file.

* Arguments:

* reader: Reader from binary_reader_open

* Returns:

* Dict with file metadata on success, NULL on failure (PyErr set)

PyObject *binary_reader_get_info(BinaryReader *reader);

* Close a binary reader and free all resources.

* Arguments:

* reader: Reader to close (may be NULL)

void binary_reader_close(BinaryReader *reader);

/* ============================================================================

* STATISTICS FUNCTIONS

* ============================================================================ */

* Get writer statistics as a Python dict.

* Arguments:

* writer: Writer to get stats from

* Returns:

* Dict with statistics on success, NULL on failure (PyErr set)

PyObject *binary_writer_get_stats(BinaryWriter *writer);

* Get reader statistics as a Python dict.

* Arguments:

* reader: Reader to get stats from

* Returns:

* Dict with statistics on success, NULL on failure (PyErr set)

PyObject *binary_reader_get_stats(BinaryReader *reader);

/* ============================================================================

* UTILITY FUNCTIONS

* ============================================================================ */

* Check if zstd compression is available.

* Returns:

* 1 if zstd available, 0 otherwise

int binary_io_zstd_available(void);

* Get the best available compression type.

* Returns:

* COMPRESSION_ZSTD if available, COMPRESSION_NONE otherwise

int binary_io_get_best_compression(void);

#ifdef __cplusplus

}

#endif

#endif /* Py_BINARY_IO_H */

cpython/Modules/_remote_debugging/binary_io.h at main · python/cpython · GitHub

Uh oh!

Uh oh!

cpython/Modules/_remote_debugging/binary_io.h at main · python/cpython · GitHub

Uh oh!

Uh oh!

Expand file tree

Breadcrumbs

binary_io.h

Latest commit

History

Breadcrumbs

binary_io.h

File metadata and controls