DF-3780 / run.log
=== netstat -m BEFORE === 7/146632 mbufs in use (current/max): 256/33296 mbuf clusters in use (current/max) 0/8260 mbuf jumbo clusters in use (current/max) 263 mbufs and mbuf clusters allocated to data 515 Kbytes allocated to network (0% of mb_map in use) 0 requests for memory denied hw.vmxrep.run: 0 -> 0 === netstat -m AFTER run1 === 7/146632 mbufs in use (current/max): 1256/33296 mbuf clusters in use (current/max) 0/8260 mbuf jumbo clusters in use (current/max) 1263 mbufs and mbuf clusters allocated to data 2515 Kbytes allocated to network (1% of mb_map in use) 0 requests for memory denied hw.vmxrep.run: 0 -> 0 === netstat -m AFTER run2 === 7/146632 mbufs in use (current/max): 2256/33296 mbuf clusters in use (current/max) 0/8260 mbuf jumbo clusters in use (current/max) 2263 mbufs and mbuf clusters allocated to data 4515 Kbytes allocated to network (3% of mb_map in use) 0 requests for memory denied === dmesg === vmxrep3780: after cycle 1: avail=511 (ring claims EMPTY) while P2 mbuf still outstanding vmxrep3780: packets sent=2000 mbufs alloc=2000 freed=1000 LEAKED=1000 (each leaked mbuf pins a 2048-byte cluster) vmxrep3780: guest mbuf pool state via netstat -m shows the same deficit; driver never recovers the skipped slots vmxrep3780: after cycle 1: avail=511 (ring claims EMPTY) while P2 mbuf still outstanding vmxrep3780: packets sent=2000 mbufs alloc=4000 freed=2000 LEAKED=2000 (each leaked mbuf pins a 2048-byte cluster) vmxrep3780: guest mbuf pool state via netstat -m shows the same deficit; driver never recovers the skipped slots