> This might be my fault! Just committed a fix from Mike Makonnen, that might > solve the problem you are seeing. Yes, the problem is solved. Thank you!!! BTW, I noticed that netstat -m shows odd informations after that netrate test at BETA5. It seems that memory leak or unnecessary freeing occur. > # netstat -m > 4294950224 mbufs in use > 10436/25600 mbuf clusters in use (current/max) > 0/3/6656 sfbufs in use (current/peak/max) > 16604 KBytes allocated to network > 0 requests for sfbufs denied > 0 requests for sfbufs delayed > 0 requests for I/O initiated by sendfile > 0 calls to protocol drain routines But, a combination of BETA5 kernel and sys/dev/em/* of -current does not have this problem. -- Shunsuke SHINOMIYA <shino_at_fornext.org>Received on Thu Sep 30 2004 - 07:25:24 UTC
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:38:14 UTC