| To: | Donald Becker <becker@xxxxxxxxx> |
|---|---|
| Subject: | Re: I need sk_buff frag_list info. |
| From: | Andi Kleen <ak@xxxxxxx> |
| Date: | Sun, 17 Mar 2002 10:59:28 +0100 |
| Cc: | Mark Wisner <markwiz@xxxxxxxxxx>, netdev@xxxxxxxxxxx |
| In-reply-to: | <Pine.LNX.4.33.0203152124160.1150-100000@localhost.localdomain> |
| References: | <OF1B1A2F76.97320533-ON85256B7D.00695592@raleigh.ibm.com> <Pine.LNX.4.33.0203152124160.1150-100000@localhost.localdomain> |
| Sender: | owner-netdev@xxxxxxxxxxx |
| User-agent: | Mutt/1.3.22.1i |
On Fri, Mar 15, 2002 at 10:43:12PM -0500, Donald Becker wrote: > A final related note: drivers should always allocate consistently > sized skbuffs. Specifically, Ethernet drivers should always allocate > 1536 byte buffers. Using a single buffer size gives the skbuff > allocator the opportunity to efficiently recycle buffers rather than > having to allocate and free a mix of sizes. The current skbuff allocator uses kmalloc for the data part. kmalloc currently always rounds to a power of two. So for any 2K>=value+sizeof(struct skb_shared_info)>1K you will get a 2K buffer. The skbuff head recycling works independently of the data size. -Andi |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | Re: I need sk_buff frag_list info., Donald Becker |
|---|---|
| Next by Date: | Kernel Packet filter and 68 bytes, Fernando Anton |
| Previous by Thread: | Re: I need sk_buff frag_list info., Donald Becker |
| Next by Thread: | Re: I need sk_buff frag_list info., Donald Becker |
| Indexes: | [Date] [Thread] [Top] [All Lists] |