> Outside of the ACK cases, the other bogus case as I mentioned is
> for clones of real outgoing data packets, used for transmission,
> the SOCK gets charged again for the entire data area when in
> reality only sizeof(struct sk_buff) more memory is being tied up
> due to the clone.
I think this is bogus. I have a strong memory of _not_ updating the
socket counters at all for cloned skb's, exactly because that would
have gotten the counts wrong. The thing used to set "skb->truesize"
to zero for this reason.
I think. It's been a long time since I worked on that code, I have
to admit.
Good, we agree. I'll work on a fix for this, so it'll get into the
TCP sync-up patch I send you tomorrow evening.
Later,
David S. Miller
davem@dm.cobaltmicro.com
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu