Class GeckoCollector

Lib/profiling/sampling/gecko_collector.py:65–793

class GeckoCollector(Collector):
    def __init__(self, sample_interval_usec, *, skip_idle=False, opcodes=False):
        self.sample_interval_usec = sample_interval_usec
        self.skip_idle = skip_idle
        self.opcodes_enabled = opcodes
        self.start_time = time.monotonic() * 1000  # milliseconds since start

        # Global string table (shared across all threads)
        self.global_strings = ["(root)"]  # Start with root
        self.global_string_map = {"(root)": 0}

        # Per-thread data structures
        self.threads = {}  # tid -> thread data

        # Global tables
        self.libs = []

        # Sampling interval tracking
        self.sample_count = 0
        self.last_sample_time = 0
        self.interval = 1.0  # Will be calculated from actual sampling

        # State tracking for interval markers (tid -> start_time)
        self.has_gil_start = {}           # Thread has the GIL
        self.no_gil_start = {}            # Thread doesn't have the GIL
        self.on_cpu_start = {}            # Thread is running on CPU
        self.off_cpu_start = {}           # Thread is off CPU
        self.python_code_start = {}       # Thread running Python code (has GIL)
        self.native_code_start = {}       # Thread running native code (on CPU without GIL)
        self.gil_wait_start = {}          # Thread waiting for GIL
        self.exception_start = {}         # Thread has an exception set
        self.no_exception_start = {}      # Thread has no exception set

        # GC event tracking: track GC start time per thread
        self.gc_start_per_thread = {}  # tid -> start_time

        # Track which threads have been initialized for state tracking
        self.initialized_threads = set()

        # Opcode state tracking per thread: tid -> (opcode, lineno, col_offset, funcname, filename, start_time)
        self.opcode_state = {}

        # For binary replay: track base timestamp (first sample's timestamp)
        self._replay_base_timestamp_us = None

    def _track_state_transition(self, tid, condition, active_dict, inactive_dict,
                                  active_name, inactive_name, category, current_time):
        """Track binary state transitions and emit markers.

        Args:
            tid: Thread ID
            condition: Whether the active state is true
            active_dict: Dict tracking start time of active state
            inactive_dict: Dict tracking start time of inactive state
            active_name: Name for active state marker
            inactive_name: Name for inactive state marker
            category: Gecko category for the markers
            current_time: Current timestamp