Re: [PATCH 6/10]: [DCCP] CCID2: Tell DCCP to quickly check whether cwnd is available

2006-09-19 Thread David Miller
From: Arnaldo Carvalho de Melo [EMAIL PROTECTED] Date: Thu, 14 Sep 2006 14:12:07 -0300 If not enough cwnd is available, tell the sender to check again as soon as possible. This will increase CPU utilization (polling frequently for cwnd) but will improve network performance. That is, the

Re: [PATCH 8/10]: [DCCP] CCID2: Allocate seq records on demand

2006-09-19 Thread David Miller
From: Arnaldo Carvalho de Melo [EMAIL PROTECTED] Date: Thu, 14 Sep 2006 14:12:50 -0300 Allocate more sequence state on demand. Each time a packet is sent out by CCID2, a record of it needs to be kept. This list of records grows proportionally to cwnd. Previously, the length of this list was

Re: [PATCH 9/10]: [DCCP] CCID2: Halve cwnd once upon multiple losses in a single RTT

2006-09-19 Thread David Miller
From: Arnaldo Carvalho de Melo [EMAIL PROTECTED] Date: Thu, 14 Sep 2006 14:14:11 -0300 When multiple losses occur in one RTT, the window should be halved only once [a single congestion event]. This is now implemented, although not perfectly. Slightly changed the interface for changing the

Re: [PATCH 10/10]: [DCCP] CCID2: Add helper functions for changing important CCID2 state

2006-09-19 Thread Andrea Bittau
On Tue, Sep 19, 2006 at 01:16:50PM -0700, David Miller wrote: Trailing whitespace, again. It seems to proliferate into any new code blocks written by Andrea. Please fix this stuff up, oops, sorry. I'll watch out in the future. It's just my lame text editor skills. When closing a block with

Re: [PATCH 6/10]: [DCCP] CCID2: Tell DCCP to quickly check whether cwnd is available

2006-09-19 Thread Ian McDonald
On 9/20/06, David Miller [EMAIL PROTECTED] wrote: From: Arnaldo Carvalho de Melo [EMAIL PROTECTED] Date: Thu, 14 Sep 2006 14:12:07 -0300 If not enough cwnd is available, tell the sender to check again as soon as possible. This will increase CPU utilization (polling frequently for cwnd) but