netdev - Re: RT metric sharing...

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] [day] [month] [year] [list]

Message-ID: <4B2190D1.9080505@gmail.com>
Date:	Fri, 11 Dec 2009 01:22:41 +0100
From:	Eric Dumazet <eric.dumazet@...il.com>
To:	David Miller <davem@...emloft.net>
CC:	netdev@...r.kernel.org
Subject: Re: RT metric sharing...

Le 10/12/2009 23:14, David Miller a écrit :
> 
> This topic has come up a few times, but I had a reason to
> consider it again.
> 
> The routing metrics take up quite a bit of space in the
> dst_entry and thus every routing cache entry.
> 
> We could save some space with indirection.
> 
> Basically my idea is:
> 
> 1) dst_metrics are maintained in external structure
> 
> 2) when cache entry is created, read-only dst_metrics object
>    is allocated for it
> 
> 3) any attempt to change the metrics of such a read-only dst_entry
>    cow's it, all further writes proceed as normal
> 
> We currently have 13 (so 13 * sizeof(u32) == 52) and we're probably
> about to get a 14th (for the initial receive window stuff).
> 

Nice idea Dave.

(Note : we do have a hole available for the 14th metric
because of forced __refcnt alignement)
--
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