Re: 2.2.16 TCP problems (again)

[Rajeev Bector]

| Yes, exaclty.
| 
| Actually, in 2.3 the problem is more deep.
| In 2.3 packet may be queued not only on backlog,
| it can spin on listening socket spinlock on another CPU,
| so that even if we searched in established connection list,
| we would fall to race window during accept().
| 

Oh . ok .

| > Did the splitup bringup other races in the code ?
| 
| In 2.2 it should not, if I remember correctly.
| But probably, I forgot something. The whole year passed since
| that time yet.

We hope you didnet forget anything :-))

| > (adding the code to do a  established hash queue lookup
| > in backlog processing fixes the problem !)
| 
| Yes, it does. 2.3/4 does exactly this.

Great  ! 

Thanks
Rajeev

| 
| Alexey