Mail Archive Search: <+subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*PATCH\:\s+kmalloc\s+packet\s+slab\s*$/>

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*PATCH\:\s+kmalloc\s+packet\s+slab\s*$/: 14 ]

Total 14 documents matching your query.

1. . (score: 1): Author: Puncer <domen@xxxxxxxxxxxx>; Date: Mon, 27 Dec 2004 18:17:32 +0100; rtot@xxxxxxx> : To put it short, could you please give me a link or a hint or whatever to let me set jumbo frames on r8169 (I'm currently running kernel 6.9.10; /archives/netdev/2004-12/msg00688.html (8,788 bytes)
2. uld ignore ECN bits (score: 1): Author: dy <kaber@xxxxxxxxx>; Date: Mon, 27 Dec 2004 14:23:50 -0800; e sense. The two bits were still unused at the time the code was written so this brings back the old behaviour. Signed-off-by: Thomas Graf <tgraf@xxxxxxx> -- l; /archives/netdev/2004-12/msg00691.html (9,576 bytes)
3. kmalloc packet slab (score: 1): Author: mieu@xxxxxxxxxxxxx>; Date: Mon, 27 Dec 2004 17:50:01 -0500; ctually helps for full sized frames. Another thing in the above equations is that on output you have to add in MAX_TCP_HEADER which is 128 + MAX_HEADER. MAX_HE; /archives/netdev/2004-12/msg00692.html (9,030 bytes)
4. kmalloc packet slab (score: 1): Author: as Graf <tgraf@xxxxxxx>; Date: Mon, 27 Dec 2004 14:58:07 -0800; l interface types if we do it at all, or would a special-case for 1 or 2 types that can use a slab without being wasteful be an acceptable solution? (Let's fac; /archives/netdev/2004-12/msg00693.html (9,910 bytes)
5. ame it to inet_sock (score: 1): Author: Francois Romieu <romieu@xxxxxxxxxxxxx>; Date: Tue, 28 Dec 2004 00:51:28 +0000; Dave, wait a while, I've just tried it with current BK, after Linus merged your 2.6.11 netdev queue and it breaks with things like Stephen's TCP ephemeral por; /archives/netdev/2004-12/msg00696.html (8,597 bytes)
6. ame it to inet_sock (score: 1): Author: xxxxxx>; Date: Tue, 28 Dec 2004 01:01:48 -0500; d-off-by: Roland Dreier <roland@xxxxxxxxxxx> -- /d; /archives/netdev/2004-12/msg00761.html (9,949 bytes)
7. in U32 classifier. (score: 1): Author: >; Date: Thu, 30 Dec 2004 19:00:25 +0100; xxxxxxxxxx> 2004-12-29 10:53 Understood, we could store a map in userspace mapping those IDs to pretty english match descriptions. I think avoiding to hardcode; /archives/netdev/2004-12/msg00892.html (8,767 bytes)
8. Re: PATCH: kmalloc packet slab (score: 1): Author: Patrick McHardy <kaber@xxxxxxxxx>; Date: Mon, 27 Dec 2004 18:17:32 +0100; Signed-off-by: Alan Cox <alan@xxxxxxxxxx> Why 1620 bytes ? Most drivers allocate packet_size + 2 bytes. dev_alloc_skb adds another 16 bytes, finally alloc_skb adds sizeof(struct skb_shared_info). So; /archives/netdev/2004-12/msg01639.html (8,813 bytes)
9. Re: PATCH: kmalloc packet slab (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Mon, 27 Dec 2004 14:23:50 -0800; Absolutely, there is no way this patch actually helps for full sized frames. Another thing in the above equations is that on output you have to add in MAX_TCP_HEADER which is 128 + MAX_HEADER. MAX_HE; /archives/netdev/2004-12/msg01642.html (9,685 bytes)
10. Re: PATCH: kmalloc packet slab (score: 1): Author: Valdis.Kletnieks@xxxxxx; Date: Mon, 27 Dec 2004 17:50:01 -0500; Would you prefer to see this done for all interface types if we do it at all, or would a special-case for 1 or 2 types that can use a slab without being wasteful be an acceptable solution? (Let's fac; /archives/netdev/2004-12/msg01643.html (9,188 bytes)
11. Re: PATCH: kmalloc packet slab (score: 1): Author: "David S. Miller" <davem@xxxxxxxxxxxxx>; Date: Mon, 27 Dec 2004 14:58:07 -0800; It's not even just device MTU based (which can change dynamically at run time), it's also based upon the PMTU for various paths. As for wastefulness, that's a good question. Adding a mechanism to do; /archives/netdev/2004-12/msg01644.html (10,102 bytes)
12. Re: PATCH: kmalloc packet slab (score: 1): Author: Alan Cox <alan@xxxxxxxxxxxxxxxxxxx>; Date: Tue, 28 Dec 2004 00:51:28 +0000; Fine by me, I'm just going through plausible looking changes in the Red Hat tree. You might want to slightly injure someone internally until they drop that too 8) Alan; /archives/netdev/2004-12/msg01647.html (8,756 bytes)
13. Re: PATCH: kmalloc packet slab (score: 1): Author: Dave Jones <davej@xxxxxxxxxx>; Date: Tue, 28 Dec 2004 01:01:48 -0500; Internal injuries unnecessary. Regardless of outcome of this patch, Fedora will pick up whatever happens upstream instead of carrying this any longer. This and a few other patches have been stagnatin; /archives/netdev/2004-12/msg01712.html (10,137 bytes)
14. Re: PATCH: kmalloc packet slab (score: 1): Author: Andi Kleen <ak@xxxxxx>; Date: Thu, 30 Dec 2004 19:00:25 +0100; Doesnt this clash a bit with yours and Arjans no-prisoners-taken quest to get rid of order>0 allocations? (4K stacks). I implemented this long ago (in 2.1 - bonus points if you still find the leftove; /archives/netdev/2004-12/msg01843.html (8,889 bytes)

Current List: 1 - 14
Page: [1]