On 2/13/07, Justin C. Sherrill <[EMAIL PROTECTED]> wrote:
It has benefits that go beyond clustering ability; while it may be more
work to convert ZFS for clustering, I can't imagine a homegrown filesystem
is necessarily going to have the same amount of documentation, toolsets,
or external support
On Mon, Feb 12, 2007 at 09:59:58PM -0500, Matt Emmerton wrote:
> Luckily for me, the Math/Computer Science faculty resisted the urge to move
> to "commodity" languages for many years and continued to instruct using
> Pascal and Modula-3. I still recall the beauty of Modula-3's object model
> and c
> On Mon, February 12, 2007 8:46 pm, Matt Emmerton wrote:
> > My alma mater (University of Waterloo) went one step further -- instead
of
> > standardizing on Java (which has some potential to become an "open"
> > language allowing folks to dig into gcj and related projects) decided
> > to have all
On Mon, February 12, 2007 9:04 pm, Chris Csanady wrote:
> While I don't want it to distract you from the more important goals, I
> think a ZFS port would be well worth the minimal time investment to
> get it to the point where someone else could pick it up. It would
> also be a great selling poin
On Mon, February 12, 2007 8:46 pm, Matt Emmerton wrote:
> My alma mater (University of Waterloo) went one step further -- instead of
> standardizing on Java (which has some potential to become an "open"
> language allowing folks to dig into gcj and related projects) decided
> to have all of their e
On Mon, Feb 12, 2007 at 04:54:42PM -0800, Dave Hayes wrote:
> Bill Huey <(hui) <[EMAIL PROTECTED]>> writes:
> > They've substituted sensibility with a kind of conformity, various
> > indirect personality tests, etc... that constrain people to doing what
> > they are told versus doing what is actual
On 2/12/07, Matthew Dillon <[EMAIL PROTECTED]> wrote:
It would also be possible to assign redundancy, whereby two (or more)
chunks are considered to be mirrors of each other.
Are you also considering redundancy beyond basic mirroring? Over an
unreliable network, it would be desirable
> On Mon, Feb 12, 2007 at 04:05:53PM -0800, Matthew Dillon wrote:
> > [...]
> >
> > However, for robustness we would not mirror them in actual fact but
> > would instead assign dynamic block numbers (i.e. non-linear
> > addressing) every time a bit of data is flushed to physical storage,
> > allowi
:With the infinite snapshots scheme, how does one reclaim space?
You reclaim space by destroying the oldest (deleted) data, and
by collapsing snapshots (that is, collapsing time ranges).
So for example, under normal filesystem operation if a filesystem
sync occurs every 30 se
> Unfortunately this is carried by the current batch of CS kids that are
> brainwashed by the glory of how Java is going to save the world by
> preventing you from touching the bare metal, as they say, so you don't
> actual learn the true "fundamentals" any more so that you don't anything
> that's
On Mon, Feb 12, 2007 at 04:05:53PM -0800, Matthew Dillon wrote:
> [...]
>
> However, for robustness we would not mirror them in actual fact but
> would instead assign dynamic block numbers (i.e. non-linear
> addressing) every time a bit of data is flushed to physical storage,
> allowing the data ch
Bill Huey <(hui) <[EMAIL PROTECTED]>> writes:
> It's been flooded with a lot of so called "business" oriented folks
> that only care about the short term bottom line. It's a good mentality
> to have to produce and release product without infinitely long
> development cycles, but our industry is get
:Hi Matt,
:Is moving VFS to userland still part of your clustering master plan? :)
:if it is, is it planned for 2.0?
:
:Petr
SYSLINK certainly - the communications protocol that will be used for
filesystem access, thus allowing filesystems in userspace in addition
to filesystems acros
Matthew Dillon wrote:
:I can't uderstand whether snapshots are filesystems or files ?...or
:just both possible ?
A snapshot is just a view into a historical data set.
-Matt
Matthew Dillon
<[EMAIL PROTECTED]>
Hi Matt,
Is moving VFS
On Monday 12 February 2007 18:53, Matthew Dillon wrote:
[...]
> The write bit should not be cleared from fs.prot in that case. Check
> the conditionals on fault_type in vm_fault_object().
>
> case 1: line 751 vm/vm_fault.c (in HEAD).
>
> VM_PROT_WRITE is only cleared if fault_ty
:Right, but that's the read fault on writable page case. My question was about
:a _write_ fault on writable page. The way I'm reading the code, the host
:kernel again maps the page read only (vm_fault_object() clears the write bit
:from fs.prot, so after return to vm_fault(), pmap_enter() will
On Sat, Feb 10, 2007 at 12:14:45PM -0800, Matthew Dillon wrote:
...
> Ultimately the lesson that has to be learned (especially by the younger
> people on our forum) is that there has always been and will always be
> a fairly severe disconnect between people like us and the companies
>
17 matches
Mail list logo
