The raw sumSq paired with a self/running mean yielded the raw variance
inflated by the squared mean gap. Accumulate the vector's own sum of
squares alongside its sum, like compare and frame statistics do.
Per-thread lists were dropped for threads without zones or samples, a rule
from when only profiled threads consumed them; the CPU data graph uses them
for any visible thread, so saved traces silently lost wake and wait data.
Block sizes weren't checked against the file length, so truncated files
made the decompression threads read off the mapping. Validate framing
(u32 size + payload) before the mapping and threads exist; also reject
zero-stream or empty files.
The client decoded sched_switch, sched_waking and drm_vblank_event at
fixed positions behind an 8-byte common header. The kernel can extend the
header, which shifts the field positions.
The format files are generated from the live trace_entry (offsetof/ALIGN),
making them the authoritative layout.
Sections are packed into timeline rows purely by length, so sections
from different categories share rows and the same category can move
between rows along the timeline. When categories mark different kinds of
activity (game levels, loading screens, cutscenes) this makes the row
layout hard to read.
The new "Group by category" option in the section options lays out each
category in its own set of rows, in category identifier order, with the
existing length-first packing applied within a category. Off by default,
so the current layout is unchanged unless the option is enabled. Only
shown when the trace has more than one section category.
Pandoc 3.11 appends the LaTeX caption label to Markdown table
captions as a {#id} identifier; strip it in tablecaption() since the
manual renderer has no identifiers.
The monitor embeds the capture side of the protocol (TracyWorker) to
save traces to disk; like tracy-capture, build it without statistics
and at C++20.
Only one daemon can write to a given output directory at a time. The
lock holds the daemon PID and is removed on a clean exit; a lock whose
owner is verifiably gone is taken over on the next start, and a lock
whose owner cannot be read or that reads as alive must be removed by
hand.
The data is written to <fn>.tmp in the same directory as the target
and moved to <fn> on Commit(); a failed or interrupted write leaves
the previous file untouched, with an orphaned .tmp.
The final compressed block was left in the stdio buffer until the
destructor closed the file, so a caller that inspected the file after
Finish() saw a truncated trace.
The old pre-flight truncated the output at startup with -f, so an
interrupted capture lost the trace, and the probe fopen followed a
symlink. The existing file is now moved to FILE~ for the duration of
the capture and restored if the trace cannot be written.
HasData() flips when the connection is established, but the rate
list is only filled by the worker periodic stats update, whose first
entry arrives ~200ms later, so the first render could read an empty
list.
As it is, the CI-built macOS binaries refuse to work on
macOS Sequoia because it defaults to the runner machine's level.
This sets a lower-than-default default for the target.
Adopting a pre-bound socket via SetReservedListenSocket left Worker()'s
port bookkeeping untouched, so GetPort() and the broadcast announcement
reported the computed default instead of the port the socket listens on.
The monitor kept this correct by mirroring the reserved port into
TRACY_PORT; direct users of the public API had no such coupling.
The bound socket is now authoritative: Worker() reads the local port
back via getsockname after binding. The search-loop bookkeeping stays
only as a fallback for a getsockname failure.
External sampling opens one event per CPU for each existing thread
(attach) or per CPU (launch) per event type, so a multithreaded target
needs many fds.
TRACY_NO_CALLSTACK, TRACY_NO_SYSTEM_TRACING, TRACY_NO_SAMPLING and
TRACY_SAMPLING_PROFILER_MANUAL_START either fail to build (the external
target API lives in the callstack code) or silently produce an empty
capture (no sampling event fails, so IsSystemTracingFailed stays false).
The first three are #error'd at compile time; the TRACY_NO_SYS_TRACE /
TRACY_NO_SAMPLING environment variables are refused at startup.
A caught signal (the handlers are inherited by the child) delivered
between PTRACE_TRACEME and exec first produces a signal-delivery stop;
without handling it, the setup would run on the still pre-exec child and
capture the monitor's own image as the target's. Re-inject the caught
signal and wait again until the exec stop is reached. Job-control stops
are the exception - re-injecting SIGSTOP/SIGTSTP re-stops the child, and
PTRACE_CONT rejects a stop carrying the 0x80 job-control bit - so resume
those without a signal instead.
The client's system tracing cannot start without a tracefs (or debugfs)
mount - the tracepoint ids live under it - so starting anyway would
capture no samples.
IsSystemTracingFailed reports a SysTraceStart that the preflight could
not predict (the target exiting between the checks, the kernel rejecting
the event setup); starting anyway would capture no samples.
Polling IsDataPortListening is the only reliable check: probing the port
itself cannot distinguish the client's listener from another process
holding it.
When TRACY_PORT is not pinned the client probes 8086..8105 at startup.
Reserve the first free port up front and hand the already-bound socket
to the client via SetReservedListenSocket, so the reservation is atomic
and the reported port matches what the client listens on. A pinned
TRACY_PORT is validated like --port, since the client pins to any
nonzero value with no fallback.
Bartosz Taudul
Chandan Singh
Aarni Koskela
Olivier Fouré