ice private data protection,
and ifnet lock for each ifnet struct protection (such as ifnet.if_mtx).
Maybe these locks should be adaptive or spin
And IFNET_*LOCK() should remain for adding/removing ifnet struct to
the global ifnet whose type is ifnethead.
In case of ifqueue, it should not need to acquire
Thanks to Alan Cox, kmem_malloc() is out from under Giant now.
Then what should be done to make each NIC device drivers mpsafe?
Can driver be mp-safe after adding if_dc style per-device data locking?
--
Kyunghwan Kim
[EMAIL PROTECTED]
To Unsubscribe: send mail to [EMAIL PROTECTED]
with
djade/patches/em_diff
http://atropos.snu.ac.kr/~redjade/patches/ti_diff
Thanks.
--
Kyunghwan Kim
[EMAIL PROTECTED]
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-net" in the body of the message
guaranteed. In other words, bandwidth
guarantee by reserving not by limiting.
How should dummynet be modified to meet the need?
If there is related works or papers, please let me know.
--
Kyunghwan Kim
[EMAIL PROTECTED]
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe free
at handles diverted packets in bridge is not yet implemented?
Regards,
Kyunghwan Kim
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-net" in the body of the message
there was no HEADUP and no UPDATING change
about this.
I've read Matthew's log about removing if_wx* in cvsweb, but
reasons which his conclusion is based on is not enough for me.
Would someone tell me in detail?
Thanks in advance.
Regards,
Kyunghwan Kim
[EMAIL PROTECTED]
To U
