netdev - Re: [PATCH] sky2: skb recycling

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <18685.54116.517096.363575@robur.slu.se>
Date:	Tue, 21 Oct 2008 15:04:36 +0200
From:	Robert Olsson <robert@...ur.slu.se>
To:	Eric Dumazet <dada1@...mosbay.com>
Cc:	Robert Olsson <Robert.Olsson@...a.slu.se>,
	Terry <hanfang@...du.com>,
	Stephen Hemminger <shemminger@...tta.com>,
	Jeff Garzik <jgarzik@...ox.com>, netdev@...r.kernel.org
Subject: Re: [PATCH] sky2: skb recycling


Eric Dumazet writes:

 > I suspect all this skb recycling stuff in forwarding workloads is defeated anyway...
 > 
 > By the copybreak feature... (RX_COPY_THRESHOLD = 256 for example on tg3)


 Right. I use to turn it off as forwarding is the major application. I'll remember 
 it was useful for you as it saved you lots of memory.

 Thinking of what we should be able to do with decent classifier on the NIC's
 
 Would could probably determine if packet is for localhost and tag skb for all 
 sorts of new tricks. copy_threshhold is one and maybe even skip dst cache on big 
 routers etc.

 > Checking drivers/net/tg3.c, we can even see that in case of copying to a smaller skb,
 > we allocate it with a call to netdev_alloc_skb(), while it would be better
 > to use a plain alloc_skb() ...

 I'll let others comment this...

 Cheers.
						--ro

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html