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: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CAHOvCC4bYNkoku_HWDadEBNfWNJGFkVVmz5XcAeMe0EAT_5HEw@mail.gmail.com>
Date: Thu, 8 Aug 2024 07:13:56 +0900
From: JaeJoon Jung <rgbi3307@...il.com>
To: Matthew Wilcox <willy@...radead.org>
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>, 
	Linus Torvalds <torvalds@...ux-foundation.org>, Sasha Levin <levinsasha928@...il.com>, 
	"Liam R . Howlett" <Liam.Howlett@...cle.com>, linux-kernel@...r.kernel.org, linux-mm@...ck.org, 
	maple-tree@...ts.infradead.org, linux-fsdevel@...r.kernel.org
Subject: Re: [PATCH v2 1/2] lib/htree: Add locking interface to new Hash Tree

Hello, Matthew
Thank you so much for the advice above.
I've been analyzing your XArray for years now and it's helped me a lot.
Finding an index through bit shifting in XArray seems to very ingenious way.
If you have time, Could you talk a bit more on the dcache advice you gave above?
My guess is that it has to do with the memory cache associated with the MMU.

On Wed, 7 Aug 2024 at 12:48, Matthew Wilcox <willy@...radead.org> wrote:
>
> On Wed, Aug 07, 2024 at 09:21:12AM +0900, JaeJoon Jung wrote:
> > Performance comparison when the number of indexes(nr) is 1M stored:
> > The numeric unit is cycles as calculated by get_cycles().
> >
> > Performance  store    find    erase
> > ---------------------------------------------
> > XArray            4          6        14
> >
> > Maple Tree     7          8        23
> >
> > Hash Tree      5          3        12
> > ---------------------------------------------
> >
> > Please check again considering the above.
>
> I would suggest that you find something to apply your new data structure
> to.  My suggestion would be the dcache, as I did with rosebush.  That let
> us find out that rosebush was not good for that application, and so I
> abandoned work on it.

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ