On Sep 14, 2007, at 5:03 PM, Walter Bays wrote:
> Good point. Speaking of which, as the clock frequency changes with
> power
> management events, should the CPU utilization change along with it?
What about completely asynchronous designs?
I guess I'm more of the Snead school of thought, the c
On Aug 21, 2007, at 8:58 AM, adrian cockcroft wrote:
Why can't you adapt ZFS for swap? It does the transactional
clustering of random writes into sequential related blocks,
aggressive prefetch on read, and would also guard against corrupt
blocks in swap. Anon-ZFS?
why not use a very smal
On Aug 2, 2007, at 3:55 PM, J. Bruce Fields wrote:
> On Thu, Aug 02, 2007 at 03:50:19PM -0600, Keith Bierman wrote:
>> Posit suitable battery backed up or nonvolatile cache. It would take
>> collusion (thus consent ;>) of both the client and server;
>
> No, it'd j
On Aug 2, 2007, at 1:38 PM, J. Bruce Fields wrote:
>
> There's not really any way out for servers--they have to get writes to
> stable storage on commit. The protocol changes required would be more
> substantial than that.
>
Posit suitable battery backed up or nonvolatile cache. It would take
On Aug 2, 2007, at 3:29 AM, Roch - PAE wrote:
> ...
> Is so, this is by design of NFS. Not much you can do about it.
> Maybe NFS V4++ will find a way
> ..
> http://blogs.sun.com/roch/entry/nfs_and_zfs_a_fine
>
great blog entry!
Any chance of a multithreaded tar in the default indiana
On Jul 10, 2007, at 11:33 AM, Richard Lowe wrote:
> Alexander Kolbasov <[EMAIL PROTECTED]> writes:
>
>> Richard Lowe <[EMAIL PROTECTED]> wrote:
> .many sage observations from both elided...
> Ah, it was using a web of symlinks to cross branches that I was
> missing.
>
>> I do not quite see
Alan Coopersmith wrote:
Making an MMX-capable Pentium Pro-class CPU (i.e. Pentium II, introduced
in May 1997) the minimum supported hardware for Solaris Nevada would make
a lot of sense to me.
Are OpenSolaris and "Solaris Nevada" tied at the hip for compiler
options? should they be?
--
Keith
Keith Bierman wrote:
Sorry to respond to myself..
(across a large MP) is stable over time, do you? Otherwise there'd be
no need for protocols like NTP :>
I meant, stable without some synchronization infrastructure ;>
--
Keith H. Bierman[EMAIL PROTECTED]|
http://blogs.
Roman wrote:
I thought an OS kernel was supposed to synchronise hardware counters on
multiple CPUs when it was loading??
Well, I don't know where that requirement is stated; but initialization
aside, over time you surely can't think that resolution down to a tick
(across a large MP) is stab
Eric Lowe wrote:
While it sounds interesting from an academic point of view, I wonder
how relevant this work (and any work related to paging) is when memory
can be purchased for under $200 a gigabyte.
When we're talking about "green" computing and TB of main memory,
compression and paging optim
10 matches
Mail list logo
