On my 5.3-RELEASE system, sysctl -a | grep net | grep space gives:
net.local.stream.sendspace: 8192
net.local.stream.recvspace: 8192
net.local.dgram.recvspace: 4096
net.inet.tcp.sendspace: 32768
net.inet.tcp.recvspace: 65536
net.inet.udp.recvspace: 42080
net.inet.raw.recvspace: 8192
Where is
On my 5.3-RELEASE system, sysctl -a | grep net | grep space gives:
net.local.stream.sendspace: 8192
net.local.stream.recvspace: 8192
net.local.dgram.recvspace: 4096
net.inet.tcp.sendspace: 32768
net.inet.tcp.recvspace: 65536
net.inet.udp.recvspace: 42080
net.inet.raw.recvspace: 8192
Where is
On Sun, Feb 06, 2005 at 07:54:15AM -0500, Michael R. Hines wrote:
On my 5.3-RELEASE system, sysctl -a | grep net | grep space gives:
net.local.stream.sendspace: 8192
net.local.stream.recvspace: 8192
net.local.dgram.recvspace: 4096
net.inet.tcp.sendspace: 32768
net.inet.tcp.recvspace:
I see. I'll modify the application.
Is there also a way of controlling the kernel's UDP buffer queue - the
queue used to store user-space packets before they're put on the link?
I've seen other mailing lists through searching where users listed the
existence of a udp.sendspace. Where those just
On Sun, Feb 06, 2005 at 05:16:08PM -0500, Michael R. Hines wrote:
I see. I'll modify the application.
Is there also a way of controlling the kernel's UDP buffer queue - the
queue used to store user-space packets before they're put on the link?
AFAIK they're queued directly to the