Date: Sun, 20 Mar 2005 21:24:59 +0900 (JST) From: Noritoshi Demizu <demizu@dd.iij4u.or.jp> To: freebsd-net@freebsd.org Subject: Re: TCP SACK of FreeBSD stable Message-ID: <20050320.212459.21971983.Noritoshi@Demizu.ORG> In-Reply-To: <20050316.215730.84382579.Noritoshi@Demizu.ORG> References: <20050316.215730.84382579.Noritoshi@Demizu.ORG>
next in thread | previous in thread | raw e-mail | index | archive | help
Upon a request, I made two experiments to compare the TCP SACK behaviors when Limited Transmit is on and off. I put the new results at http://www.demizu.org/~noritosi/memo/2005/0320/ 1. In the first RTT of the recovery mode, FreeBSD stable sends one data segment for each duplicate ACK segment. As a result, the outstanding window size may not be halved while a loss is detected. 2. FreeBSD stable retransmits data upon the arrival of the first SACK block higher than the data. As a result, FreeBSD stable would retransmit data segments unnecessarily when data segments are reordered. 3. FreeBSD stable seems not to retransmit data higher than snd_recover even if the data can be infered as lost. Any comments are welcome. Thank you. Regards, Noritoshi Demizu
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050320.212459.21971983.Noritoshi>