The census could say which POOL held memory but never which allocation put it
there, so each hypothesis needed a code change plus an eight-minute soak to
test and the investigation could only ask one yes/no question at a time.
Records allocations at or above a threshold (default 32 KiB, since arena
fragmentation is driven by large transient runs) against their captured stack,
into fixed tables whose exhaustion is counted and reported rather than silently
dropped. Emitted alongside every census sample, so pool totals and attribution
always describe the same instant, plus an explicit unattributed remainder so
incomplete coverage announces itself.
scripts/memlab-report.py ranks sites by retained-byte growth using a linear fit
and can diff two platforms' profiles against each other.
Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
Martin Vogel