On Thu, Nov 27, 2008 at 4:14 AM, Christof Hanke <[EMAIL PROTECTED]>wrote:
> Yes, thanks. That's what I meant.
The architecture for split cache should easily allow a differentiator based
on the even/odd vnode hack to be plugged in.
Sadly I never figured out how to make an interface for tuning it
Yes, thanks. That's what I meant.
Christof
From: Jeffrey Altman [EMAIL PROTECTED]
Sent: Wednesday, November 26, 2008 11:43 PM
To: Christof Hanke
Cc: openafs-info@openafs.org
Subject: Re: Linux tmpfs (Was: [OpenAFS] Solaris 10u6: ZFS cache?)
Christof
> .. I'd expect IBM's policy not to interfere
> with their Public License (i.e. OpenAFS's license).
Expectations are wonderful things, but should not
be confused with actual licenses and/or conditions
and covenants (especially when future litigations
can be reasonably forseen as a possibility(*))
If IBM/Sun had not patented it, cache management
using the ARC algorithms would probably be a
great improvement for that, and other cases.
(as to whether open source projects could gain
access to the patented algorithms is left as
an exercise to the reader.)
Interesting. But after looking at htt
Christof Hanke wrote:
> While talking about cache-performance (not that I know how they really work)
> Would it be beneficial to have a separate Meta-data cache from a File-data
> cache?
> I'm thinking of situations where the the performance is poor (long distance,
> whatever)
> It would me frust
> While talking about cache-performance (not that I know how
> they really work)
> Would it be beneficial to have a separate Meta-data cache
> from a File-data cache?
If IBM/Sun had not patented it, cache management
using the ARC algorithms would probably be a
great improvement for that, and ot
[EMAIL PROTECTED] [EMAIL PROTECTED] On Behalf Of Brandon S. Allbery KF8NH
[EMAIL PROTECTED]
Sent: Friday, November 14, 2008 8:28 PM
To: Chas Williams
Cc: Brandon S. Allbery KF8NH; Jason Edgecombe; Harald Barth; [EMAIL PROTECTED];
[EMAIL PROTECTED]; openafs-info@openafs.org
Subject: Re: Linux tmpfs (Wa
On 2008 Nov 14, at 7:18, Chas Williams (CONTRACTOR) wrote:
In message <5FB03AFA-8CA1-4B39-
[EMAIL PROTECTED]>,"Brandon S. Allbe
ry KF8NH" writes:
It used to be said (back when warlord was maintaining linux-afs and
Transarc 3.4a was the main release) that the memcache was much less
efficient tha
In message <[EMAIL PROTECTED]>,"Brandon S. Allbe
ry KF8NH" writes:
>It used to be said (back when warlord was maintaining linux-afs and
>Transarc 3.4a was the main release) that the memcache was much less
>efficient than the disk cache and that it was better to use disk cache
>in a ramdisk.
On Nov 13, 2008, at 09:39 , Jason Edgecombe wrote:
Harald Barth wrote:
On Linux, if you're using tmpfs as the cache, what's the difference
between letting the memcache swap out vs a disk cache in tmpfs?
Does memcache swap out? I was convinced it did not.
I don't believe that it does, but I w
Harald Barth wrote:
>> On Linux, if you're using tmpfs as the cache, what's the difference
>> between letting the memcache swap out vs a disk cache in tmpfs?
>>
>
> Does memcache swap out? I was convinced it did not.
>
>
I don't believe that it does, but I was asking about the hypothetical
11 matches
Mail list logo
