On Mon, 06 Feb 2006 15:50:28 -0800 (PST), "David S. Miller" <[EMAIL PROTECTED]> said:
> From: David Carlton <[EMAIL PROTECTED]> > Date: Mon, 06 Feb 2006 14:38:10 -0800 >> I'm working on an application that we're trying to switch from a 2.4 >> kernel to a 2.6 kernel. (I believe we're using 2.6.9.) One part of >> the program periodically sends out chunks of data (whose size is just >> over 1MB) via tcp. > Please reproduce with something more current and report to the correct > mailing list (netdev@vger.kernel.org). Thanks for the suggestion. The problem went away with 2.6.15 (I believe uname -a called it 2.6.15.3), which is nice. I'll try to see if I can figure out which patch caused the problem (it may or may not be easy for us to switch to that kernel); I don't suppose you have any idea what patch caused the problem? (The other endpoint is that the problem is still present in 2.6.10, where for the latter we're using whatever the latest 2.6.10 kernel is that's available for Fedora Core 2.) Also, is <http://linux.bkbits.net:8080/linux-2.6/hist/net/ipv4/> the right place to look for revision history? Recent commits don't have a change message, which makes me think I'm looking in the wrong place. I put up a tcpdump at <http://www.bactrian.org/~carlton/sender.tcpdump>, if anybody's curious. The problems start with packet 7367; the problematic transmission is from 64.12.82.96:33826 to 64.12.82.49:34483 (which starts at packet 6482). The tcpdump was taken on the sender side, and some packets are missing or corrupted in the dump (for reasons that I assume have nothing to do with the problem at hand.) David Carlton [EMAIL PROTECTED] - To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html
