Re: bin/60443: ftp ASCII transfers are too slow

"RVP via gnats" <[email protected]>
Newsgroups gmane.os.netbsd.bugs
Message-ID <[email protected]>
The following reply was made to PR bin/60443; it has been noted by GNATS.

From: RVP <[email protected]>
To: [email protected]
Cc: 
Subject: Re: bin/60443: ftp ASCII transfers are too slow
Date: Tue, 14 Jul 2026 00:23:30 +0000 (UTC)

 On Mon, 13 Jul 2026, Michael van Elst via gnats wrote:
 
 > > 04:43:22.966644 IP6 ::1.65425 > ::1.65424: Flags [P.], seq 314369:328705, ack 1, win 4096, options [nop,nop,TS val 7 ecr 7], length 14336
 >
 > + 200ms
 >
 > > 04:43:23.166607 IP6 ::1.65424 > ::1.65425: Flags [.], ack 328705, win 4096, options [nop,nop,TS val 7 ecr 7], length 0
 >
 > + 0ms
 >
 > > 04:43:23.166636 IP6 ::1.65425 > ::1.65424: Flags [P.], seq 328705:342017, ack 1, win 4096, options [nop,nop,TS val 7 ecr 7], length 13312
 >
 > + 200ms
 >
 > > 04:43:23.366620 IP6 ::1.65424 > ::1.65425: Flags [.], ack 342017, win 4096, options [nop,nop,TS val 7 ecr 7], length 0
 >
 >
 > Looks more like the ACKs are delayed and less like Nagle's algorithm. No
 > idea what is happening.
 >
 
 You're right. Mebbe delayed ACK interacting badly with Nagle. Is there a 
 TCP_QUICKACK[1] knob in NetBSD?
 
 -RVP
 
 [1]: https://man7.org/linux/man-pages/man7/tcp.7.html
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.