| To: | pablo@xxxxxxxxxxx |
|---|---|
| Subject: | Re: [RFC] textsearch infrastructure et al v2 |
| From: | "David S. Miller" <davem@xxxxxxxxxxxxx> |
| Date: | Tue, 31 May 2005 15:05:38 -0700 (PDT) |
| Cc: | tgraf@xxxxxxx, hadi@xxxxxxxxxx, netdev@xxxxxxxxxxx |
| In-reply-to: | <42986A85.9060001@xxxxxxxxxxx> |
| References: | <1117281581.6251.68.camel@xxxxxxxxxxxxxxxxxxxxx> <20050528123542.GR15391@xxxxxxxxxxxxxx> <42986A85.9060001@xxxxxxxxxxx> |
| Sender: | netdev-bounce@xxxxxxxxxxx |
From: Pablo Neira <pablo@xxxxxxxxxxx> Date: Sat, 28 May 2005 14:56:37 +0200 > Netfilter used to follow this approach in early 2.6 kernels and Patrick > McHardy demostrated with some oprofile stuff that skb_copy_bits > decreased performance. This case got converted into what skb_copy_bits() was probably meant to be, skb_header_pointer(). The idea is, if it's linear in the SKB already (headers almost certainly are) just pass back the pointer to it, else copy into the user provided temporary buffer and return a pointer to that. The text search stuff could easily do the same thing, using a 32-byte or so sliding window to run the text search on. |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: [RFC] textsearch infrastructure et al v2, David S. Miller |
|---|---|
| Next by Date: | Re: RFC: NAPI packet weighting patch, Jon Mason |
| Previous by Thread: | Re: [RFC] textsearch infrastructure et al v2, Thomas Graf |
| Next by Thread: | Re: [RFC] textsearch infrastructure et al v2, David S. Miller |
| Indexes: | [Date] [Thread] [Top] [All Lists] |