Dear TIPC developers:

May I ask you to give some feedback the following messages (parts given down 
below) may deserve:

https://sourceforge.net/p/tipc/mailman/message/7248018/
[tipc-discussion] TIPC SOCK_STREAM performance improvement idea
From: Stephens, Allan <allan.stephens@...> - 2006-08-09 18:50:08
> I've coded up a prototype patch (see below) that avoids the unwanted
> fragmentation problem by using the port's maximum packet size "hint"
> field to help it determine how big a chunk can be sent without exceeding
> the link MTU.

https://sourceforge.net/p/tipc/mailman/message/37073434/
[tipc-discussion] Comments on TIPC SOCK_STREAM protocol overhead?
From: <login2@ai...> - 2020-07-29 22:11:30
> Lack of write coalescing usually introduces overhead in form of a small extra 
> network frame for each send(2) unless buf_len is divisible by link MTU minus 
> headers.
> Fragmentation for SOCK_STREAM writes caused by upper record boundary set to 
> TIPC_MAX_USER_MSG_SIZE [1] instead of (link MTU - SHORT_H_SIZE) [2].
> pktmax - INT_H_SIZE in msg.c effectively reduces link MTU by 40 even though 
> the accounted space is left unused.

Please give a bit of attention those messages may deserve:


_______________________________________________
tipc-discussion mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/tipc-discussion

Reply via email to