| To: | davem@xxxxxxxxxx (David S. Miller) |
|---|---|
| Subject: | Re: TCP hang with 2.2.14 <-> 2.2.15pre5 |
| From: | kuznet@xxxxxxxxxxxxx (Alexey Kuznetsov) |
| Date: | Tue, 28 Mar 2000 01:37:40 +0800 (SGT) |
| Cc: | kuznet@xxxxxxxxxxxxx, sfr@xxxxxxxxxxxxxxxx, netdev@xxxxxxxxxxx |
| In-reply-to: | <200003261127.DAA01525@xxxxxxxxxxxxxxx> from "David S. Miller" at Mar 26, 2000 03:27:41 AM |
| Sender: | owner-netdev@xxxxxxxxxxx |
Hello! Parsing dumps shows that 2.2 moves snd_nxt beyond right edge of window... :-( The result is that acks from it are never accepted by another side and it is the finish, certainly. I still do not know why it occurs. It smells like a race condition. It is natural to suspect that immediate reason is full-duplex io in rsync, 2.2 is pretty dirty with mutual locking of multiple processes accessing the socket... Stephen, please, try 2.3 so aggressively as you are able. If it will also lockup, it is not a race and it is easier to investigate there. Alexey |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: 3c59x.c, Alexey Kuznetosv |
|---|---|
| Next by Date: | Hairy routing question., Ben Greear |
| Previous by Thread: | Re: TCP hang with 2.2.14 <-> 2.2.15pre5, Alexey Kuznetosv |
| Next by Thread: | 3c59x.c, Andrew Morton |
| Indexes: | [Date] [Thread] [Top] [All Lists] |