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: <200803312308.00946.phillips@phunq.net>
Date:	Mon, 31 Mar 2008 23:08:00 -0700
From:	Daniel Phillips <phillips@...nq.net>
To:	david@...g.hm
Cc:	David Newall <davidn@...idnewall.com>,
	Alan Cox <alan@...rguk.ukuu.org.uk>, Willy Tarreau <w@....eu>,
	linux-kernel@...r.kernel.org
Subject: Re: [ANNOUNCE] Ramback: faster than a speeding bullet

On Monday 31 March 2008 21:23, david@...g.hm wrote:
> > Continue this idea to achieve whatever bandwidth you want to the ramdisk,
> > subject to finding server motherboards that can take lots of PCI-e 8x
> > cards, which are admittedly rare, but see "have your checkbook ready".
> 
> so is it possible to use ramback safely without buying the violin boxes? 
> from your posts it doesn't seem like it.

Of course it does not depend on Violin's exact hardware, which is just
very nice hardware for this purpose if you can afford it, and makes it
easy to see how to provide proper safeguards for critical data.

> as a sample, say you were to take a pair of the sun x4600 boxes and 
> populate them with 256G of ram each. how would you use 200G of ram on the 
> box as a database with ramback?

Similar idea.  Dual power supplies come with these boxes, so connect
each to two independent UPS units.  Place a very fast interconnect
between the boxes, Infiniband or something more exotic.  Then the
configuration is a mirror of ramback devices, just as with the Violin
1010's.  Advantages of this arrangement: save some money; local memory
bus speed instead of PCI-e.  Disadvantages: no raided, hotpluggable
memory; cannot take one of the servers down without losing the mirror
level redundancy; less total capacity than the 1010's.

Regards,

Daniel
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ