mbuf cluster leak?

[Paul Ripke <stix%stix.id.au@localhost>]

amd64, netbsd-10 circa 2025-01-26. So I got the dreaded:

WARNING: mclpool limit reached; increase kern.mbuf.nmbclusters

while rsync'ing 1TiB+ to a local machine over 1Gbit/s ethernet.
I've doubled nmbclusters, but it'd be nice to know why the clusters
appear to be leaking.

ksh$ netstat -mss
71288 mbufs in use:
        39721 mbufs allocated to data
        31532 mbufs allocated to packet headers
        35 mbufs allocated to socket names and addresses
3575324 calls to protocol drain routines
ksh$ vmstat -mCW | egrep '^Name|^mb|^mcl'
Name               Size     Requests    Fail     Releases    InUse    Avail      Pgreq      Pgrel    Npage PageSz   Hiwat Minpg    Maxpg    Idle   Flags   Util
mbpl                512      1706462       0       330207  1376255     6633     184085      11224   172861   4096  172863     0      inf     829 0x10000  99.5%
mclpl              2048       737672 3574894       213408   524264        8     290221      28085   262136   4096  262136     0   524288       4 0x10000 100.0%
Name          Spin GrpSz Full Emty PoolLayer CacheLayer  Hit%    CpuLayer  Hit%
mbpl           436    15  330    0   1706462  119455674  98.6  8992278669  98.7
mclpl         1086    15  109    0   4312566   55025278  92.2  2684169465  98.0

I assume MBUFTRACE might aid in hunting this down?

I kicked off the rsync again after the doubling, and ran out again a
few hours later. Local interface is alc0, which happens to be in a
bridge with a bunch of tap interfaces. I also have npf, and altq
configured on a pppoe0 interface.

I don't think I'm doing anything remarkably strange?

-- 
Paul Ripke
"Great minds discuss ideas, average minds discuss events, small minds
 discuss people."
-- Disputed: Often attributed to Eleanor Roosevelt. 1948.