netdev - Re: [PATCH net-next v9 05/15] net: homa: create homa_peer.h and homa

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: <CAGXJAmySuyiB3+c0_Rj=1X9wZwG7H0qhRtuvowfHke392vEpAg@mail.gmail.com>
Date: Fri, 13 Jun 2025 11:02:27 -0700
From: John Ousterhout <ouster@...stanford.edu>
To: Simon Horman <horms@...nel.org>
Cc: netdev@...r.kernel.org, pabeni@...hat.com, edumazet@...gle.com, 
	kuba@...nel.org
Subject: Re: [PATCH net-next v9 05/15] net: homa: create homa_peer.h and homa_peer.c

On Fri, Jun 13, 2025 at 10:18 AM Simon Horman <horms@...nel.org> wrote:
>
> I'm suggesting moving murmurhash3_128(), say to lib/ at the top
> of the Kernel tree. And I'm happy to assist with this.
>
> Aside from being accessible, does murmurhash3_128() meet your
> needs in it's current form?

I think so. I'm currently using a 32-bit version of murmurhash3. I
assume that the 128-bit version will be fine functionally, but I'm
wondering about performance. The keys I'm hashing are small (24 bytes)
so the 128-bit version will spend most of its time in the tail code;
will that end up being significantly slower than the 32-bit version
(where there is no tail code because the keys are multiples of 32
bits)?

-John-