| To: | Julian Anastasov <ja@xxxxxx> |
|---|---|
| Subject: | Re: PMTU issues due to TOS field manipulation (for DSCP) |
| From: | "David S. Miller" <davem@xxxxxxxxxx> |
| Date: | Wed, 10 Dec 2003 16:09:46 -0800 |
| Cc: | niv@xxxxxxxxxx, ak@xxxxxxx, ruddk@xxxxxxxxxx, kuznet@xxxxxxxxxxxxx, netdev@xxxxxxxxxxx, chester.f.johnson@xxxxxxxxx |
| In-reply-to: | <Pine.LNX.4.44.0312110135440.1519-100000@xxxxxxxxxxxx> |
| References: | <20031210152039.055e887a.davem@xxxxxxxxxx> <Pine.LNX.4.44.0312110135440.1519-100000@xxxxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
On Thu, 11 Dec 2003 02:06:09 +0200 (EET) Julian Anastasov <ja@xxxxxx> wrote: > But the common average chain length for full table is 16 and the > different TOS values are usually 1 or 2 per path. We do not talk > about intentional DoS. Your system has not configured it's rthash table size properly, see recent discussions Robert has been making here. You should have rthash sized somewhere near the number of entries a full system will have. But regardless, let us say that your system has complexity O(16) lookups as you mention, your proposal changes this to O(16+8). |
| Previous by Date: | Re: PMTU issues due to TOS field manipulation (for DSCP), Julian Anastasov |
|---|---|
| Next by Date: | RE: PMTU issues due to TOS field manipulation (for DSCP), Julian Anastasov |
| Previous by Thread: | Re: PMTU issues due to TOS field manipulation (for DSCP), Julian Anastasov |
| Next by Thread: | Re: PMTU issues due to TOS field manipulation (for DSCP), Julian Anastasov |
| Indexes: | [Date] [Thread] [Top] [All Lists] |