Re: [NOT VERY SAFE] [TCP]: Set initial_ssthresh default to zero in Cubic and BIC.
Dear shemminger In which case it is zero because that is the default value. The default value of snd_ssthresh is 0x7fff, isn't it? [linux/net/ipv4/tcp_ipv4.c] static int tcp_v4_init_sock(struct sock *sk) ... tp-snd_ssthresh = 0x7fff; /* Infinity */ ... Best Regards Komuro Actually, tcp_sk(sk)-snd_ssthresh is not initialized, if initial_ssthresh is 0. The patch should be static void bictcp_init(struct sock *sk) { bictcp_reset(inet_csk_ca(sk)); - if (initial_ssthresh) - tcp_sk(sk)-snd_ssthresh = initial_ssthresh; + + tcp_sk(sk)-snd_ssthresh = initial_ssthresh; } - 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
Re: [NOT VERY SAFE] [TCP]: Set initial_ssthresh default to zero in Cubic and BIC.
Dear David Komuro, every single email I sent to you bounces with user unknown, I bet it is some spam filter or similar that doesn't like the fact that I lack reverse DNS. From mailing-list-archive, I can read your email. Best Regards Komuro Dear David Actually, tcp_sk(sk)-snd_ssthresh is not initialized, if initial_ssthresh is 0. The patch should be static void bictcp_init(struct sock *sk) { bictcp_reset(inet_csk_ca(sk)); - if (initial_ssthresh) - tcp_sk(sk)-snd_ssthresh = initial_ssthresh; + + tcp_sk(sk)-snd_ssthresh = initial_ssthresh; } Best Regards Komuro Dear David The patch [TCP]: Set initial_ssthresh default to zero in Cubic and BIC. is not very safe. With this patch, ftp-transfer stops in my system. (vsftpd-2.0.5-8) Please revert this patch. Best Regards Komuro commit 66e1e3b20cbbf99da63e6c1af0fc6d39c2ed099a Author: David S. Miller [EMAIL PROTECTED] Date: Wed Jun 13 01:03:53 2007 -0700 [TCP]: Set initial_ssthresh default to zero in Cubic and BIC. Because of the current default of 100, Cubic and BIC perform very poorly compared to standard Reno. In the worst case, this change makes Cubic and BIC as aggressive as Reno. So this change should be very safe. Signed-off-by: David S. Miller [EMAIL PROTECTED] diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index 281c9f9..dd9ef65 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -29,7 +29,7 @@ static int fast_convergence = 1; static int max_increment = 16; static int low_window = 14; static int beta = 819;/* = 819/1024 (BICTCP_BETA_SCALE) */ -static int initial_ssthresh = 100; +static int initial_ssthresh; static int smooth_part = 20; module_param(fast_convergence, int, 0644); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 1422448..ebfaac2 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -29,7 +29,7 @@ static int fast_convergence __read_mostly = 1; static int max_increment __read_mostly = 16; static int beta __read_mostly = 819; /* = 819/1024 (BICTCP_BETA_SCALE) */ -static int initial_ssthresh __read_mostly = 100; +static int initial_ssthresh __read_mostly; static int bic_scale __read_mostly = 41; static int tcp_friendliness __read_mostly = 1; -- Komuro [EMAIL PROTECTED] -- Komuro [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
Re: [NOT VERY SAFE] [TCP]: Set initial_ssthresh default to zero in Cubic and BIC.
Dear David Sorry, my mailer's mail-address setting is wrong. Best Regards Komuro - 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
Re: [BUG KERNEL 2.6.20-rc1] ftp: get or put stops during file-transfer
On Thu, 4 Jan 2007 14:23:30 +0200 Craig Schlenter [EMAIL PROTECTED] wrote: --- linux-2.6.20-rc3/net/ipv4/tcp_ipv4.c.orig 2007-01-03 11:50:04.0 +0900 +++ linux-2.6.20-rc3/net/ipv4/tcp_ipv4.c2007-01-03 15:30:44.0 +0900 @@ -648,7 +648,7 @@ static void tcp_v4_send_ack(struct tcp_t TCPOLEN_TIMESTAMP); rep.opt[1] = htonl(tcp_time_stamp); rep.opt[2] = htonl(ts); - arg.iov[0].iov_len = TCPOLEN_TSTAMP_ALIGNED; + arg.iov[0].iov_len = sizeof(rep); Perhaps this was supposed to be arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED; That's what the ipv6 stuff does in places. It works properly. Thanks! Best Regards Komuro - 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
Re: [BUG KERNEL 2.6.20-rc1] ftp: get or put stops during file-transfer
Hi, I made a patch below. With this patch, the ftp-transfer-stop problem does not happen. Therefore, I think this is not a problem of vsftpd. Mr.YOSHIFUJI san, why did you set TCPOLEN_TSTAMP_ALIGNED to iov_len? --- linux-2.6.20-rc3/net/ipv4/tcp_ipv4.c.orig 2007-01-03 11:50:04.0 +0900 +++ linux-2.6.20-rc3/net/ipv4/tcp_ipv4.c2007-01-03 15:30:44.0 +0900 @@ -648,7 +648,7 @@ static void tcp_v4_send_ack(struct tcp_t TCPOLEN_TIMESTAMP); rep.opt[1] = htonl(tcp_time_stamp); rep.opt[2] = htonl(ts); - arg.iov[0].iov_len = TCPOLEN_TSTAMP_ALIGNED; + arg.iov[0].iov_len = sizeof(rep); } /* Swap the send and the receive. */ Best Regards Komuro - 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
Re: [BUG KERNEL 2.6.20-rc1] ftp: get or put stops during file-transfer
Can you reproduce it with other ftp client and/or server? I tried the proftpd-1.3.0a-1.fc6(kernel version is 2.6.19). The ftp stop problem does not happen. Therefore, this problem is reproduced when client's kernel-version is 2.6.20-rc1 or later and server is vsftpd. Server's kernel-version is not related with this problem. The ftp-stop-problem happens on client's PC. Please advise. Best Regards Komuro - 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
Re: [BUG KERNEL 2.6.20-rc1] ftp: get or put stops during file-transfer
Can you reproduce it with other ftp client and/or server? O.K. I wiil try to test other ftp client and server. Please provide the output of netstat -na command during the transfer, and the output of lsmod | grep conntrack (just for sure). Please see the output of netstat -na when stuck. (below) CONFIG_NETFILER is diabled in my test configuration ,conntrack modules is not loaded. (CONFIG_IP_DCCP, CONFIG_IP_SCTP, CONFIG_TIPC, CONFIG_IPV6 is also disabled) What kind of mode do you use? e.g. PORT/EPRT/LPRT/PASV/EPSV/LPSV PASV mode. When the transfer get stuck, are other communication still working? Other communication works properly. Actually, I can start other ftp session on other console of the same PC. Are there any workaround? e.g. stop-start vsftpd cycle, ifdown-ifup cycle, rmmod/insmod cycle etc. I only need to do the killall command. output of netstat -na Active Internet connections (servers and established) Proto Recv-Q Send-Q Local Address Foreign Address State tcp0 0 0.0.0.0:873 0.0.0.0:* LISTEN tcp0 0 0.0.0.0:111 0.0.0.0:* LISTEN tcp0 0 192.168.0.6:35737 192.168.0.2:26827 TIME_WAIT tcp0 0 192.168.0.6:51036 192.168.0.2:21 ESTABLISHED udp0 0 0.0.0.0:68 0.0.0.0:* udp0 0 0.0.0.0:867 0.0.0.0:* udp0 0 0.0.0.0:870 0.0.0.0:* udp0 0 0.0.0.0:111 0.0.0.0:* Active UNIX domain sockets (servers and established) Proto RefCnt Flags Type State I-Node Path unix 2 [ ACC ] STREAM LISTENING 5056 /tmp/.font-unix/fs7100 unix 2 [ ] DGRAM1234 @/org/kernel/udev/udevd unix 5 [ ] DGRAM4748 /dev/log unix 2 [ ACC ] STREAM LISTENING 4917 /var/run/dbus/system_bus_socket unix 2 [ ACC ] STREAM LISTENING 4989 /var/run/acpid.socket unix 2 [ ] DGRAM5390 unix 3 [ ] STREAM CONNECTED 4920 unix 3 [ ] STREAM CONNECTED 4919 unix 2 [ ] DGRAM4866 unix 2 [ ] DGRAM4756 Thanks, Best Regards Komuro - 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
Re: [BUG KERNEL 2.6.20-rc1] ftp: get or put stops during file-transfer
Hi, I investigated the ftp-file-transfer-stop problem by git-bisect method, and found this problem was introduced by [TCP]: MD5 Signature Option (RFC2385) support patch. Mr.YOSHIFUJI san, please fix this problem. commit cfb6eeb4c860592edd123fdea908d23c6ad1c7dc Author: YOSHIFUJI Hideaki [EMAIL PROTECTED] Date: Tue Nov 14 19:07:45 2006 -0800 [TCP]: MD5 Signature Option (RFC2385) support. Based on implementation by Rick Payne. Signed-off-by: YOSHIFUJI Hideaki [EMAIL PROTECTED] Signed-off-by: David S. Miller [EMAIL PROTECTED] Best Regards Komuro On Sun, Dec 17, 2006 at 11:23:11PM +0900, Komuro wrote: On Sun, 17 Dec 2006 04:02:22 + Al Viro [EMAIL PROTECTED] wrote: On Sun, Dec 17, 2006 at 09:27:52PM +0900, Komuro wrote: Hello, On kernel 2.6.20-rc1, ftp (get or put) stops during file-transfer. Client: ftp-0.17-33.fc6 (192.168.1.1) Server: vsftpd-2.0.5-8 (192.168.1.3) This problem does _not_ happen on kernel-2.6.19. is it caused by network-subsystem change on 2.6.20-rc1?? Do you have NAT between you and server? No. I don't have NAT between the client and the server. Actually, the client and the sever is located in same room. client -- 100MbpsHub -- server. - 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
Re: [BUG KERNEL 2.6.20-rc1] ftp: get or put stops during file-transfer
I investigated the ftp-file-transfer-stop problem by git-bisect method, and found this problem was introduced by [TCP]: MD5 Signature Option (RFC2385) support patch. Mr.YOSHIFUJI san, please fix this problem. Hmm, have you try disabling CONFIG_TCP_MD5SIG? (Is it already disabled?) This problem happens both CONFIG_TCP_MD5SIG is disabled and enabled. Are there any specific size of transfer to reproduce this? When I do ftp 40Mbytes file for 5-times or more, this problem happens. Do you see similar issue with other simple application? sorry, I don't reproduce this problem on other application. Thanks, Best Regards Komuro. - 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
Re: [BUG KERNEL 2.6.20-rc1] ftp: get or put stops during file-transfer
What network cards are in the client and the server? DL10022-based pcmcia network card(both client and server) The driver name is pcnet_cs. Are there any error messages your client gives or in the log files? no error messages. I capture the packet of ftp transfer by ethereal. I found the malformed packet when it stops. I will investigate it further. Thanks! Best Regards Komuro - 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