On Mon, 8 Nov 1999, Mike Smith wrote:
* Matthew Dillon
| FreeBSD boxes can handle up to 4 Gigabytes of main memory.
Is this true for the Alpha kernels too?
There are issues with 1GB of RAM on Alphas at the moment, which may
be easier to resolve soon. We have a 4100 with 1GB,
* Matthew Dillon
| FreeBSD boxes can handle up to 4 Gigabytes of main memory.
Is this true for the Alpha kernels too?
There are issues with 1GB of RAM on Alphas at the moment, which may
be easier to resolve soon. We have a 4100 with 1GB, which should be
upgraded to 1.5 shortly and
* Matthew Dillon
| FreeBSD boxes can handle up to 4 Gigabytes of main memory.
Is this true for the Alpha kernels too?
--
Andreas Dobloug : email: [EMAIL PROTECTED]
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
Michael Beckmann [EMAIL PROTECTED] wrote:
On Thu, Oct 28, 1999 at 04:42:42PM -0700, Scott Hess wrote:
Urk! I don't mean to be insulting, but the notion that you would roll
_any_ solution out for a problem of this size based on word of mouth
freaks
the crap out of me.
Hey ! You guys seem
On Fri, 29 Oct 1999, Oren Sarig wrote:
actual physical addresses, by using paging tables. Most of the addresses
are mapped outside of the actual memory, and so whenever somebody wants to
access them, a general protection fault occurs. The kernel taps the GPF,
gets the page from the swap,
On 29-Oct-99 Mike Smith wrote:
That's correct; it's why the ia32 architecture has a '32' in its name.
I don't believe that's true. I don't have any hard evidence within easy
reach, but with the introduction of the Pentium, the address space was
increased. A user process, of course, can
In the last episode (Oct 29), Lars Gerhard Kuehl said:
Think about it for a second. How big is a pointer?
The Intel architecture still supports segmented memory,
so the effective maximum pointer size is 48 bit.
gcc doesn't handle segmented memory architectures, though, so you'll
have to
At 09:56 29/10/99 -0500, Dan Nelson wrote:
In the last episode (Oct 29), Lars Gerhard Kuehl said:
Think about it for a second. How big is a pointer?
The Intel architecture still supports segmented memory,
so the effective maximum pointer size is 48 bit.
gcc doesn't handle segmented memory
In the last episode (Oct 29), Lars Gerhard Kuehl said:
Think about it for a second. How big is a pointer?
The Intel architecture still supports segmented memory,
so the effective maximum pointer size is 48 bit.
The extra 16 bits of the segment don't actually contribute to the
address
Hi !
1. What is the maximum size of a file on a filesystem ?
2. What is the maximum size of a filesystem ?
3. What is the maximum amount of RAM that FreeBSD can handle ?
4. What is the maximum size of a file that can be mmap´ed ?
Furthermore, I understand that FreeBSD can´t mmap a block device.
On Thu, 28 Oct 1999, Michael Beckmann wrote:
Hi !
1. What is the maximum size of a file on a filesystem ?
2. What is the maximum size of a filesystem ?
http://www.freebsd.org/FAQ/install.html#AEN704
-
Chris D. Faulhaber [EMAIL PROTECTED] | All the true gurus I've met never
:On Thu, 28 Oct 1999, Michael Beckmann wrote:
:
: Hi !
:
: 1. What is the maximum size of a file on a filesystem ?
: 2. What is the maximum size of a filesystem ?
:
:http://www.freebsd.org/FAQ/install.html#AEN704
:
:-
:Chris D. Faulhaber [EMAIL PROTECTED] | All the true gurus I've met
The document is not quite right. The maximum size is limited to
8 Terrabytes due to block-size conversions done in the kernel which are
independant of the filesystem block size.
The table in it is also completely hosed. :)
- Jordan
To Unsubscribe: send mail to [EMAIL
On Thu, 28 Oct 1999, Matthew Dillon wrote:
:Hi !
:
:1. What is the maximum size of a file on a filesystem ?
:2. What is the maximum size of a filesystem ?
:3. What is the maximum amount of RAM that FreeBSD can handle ?
:4. What is the maximum size of a file that can be mmap´ed ?
:
According to Michael Beckmann:
Furthermore, I understand that FreeBSD can´t mmap a block device.
Is it planned to change that ?
What is a block device ?
/me hides and runs
:-) for the humour impaired...
--
Ollivier ROBERT -=- FreeBSD: The Power to Serve! -=- [EMAIL PROTECTED]
FreeBSD
:On Thu, Oct 28, 1999 at 02:56:00PM -0700, Julian Elischer wrote:
: Block devices are being removed from the system so the answer is
: no at the moment. If people have a need, we will probably introduce
: a block device overlay of some sort that would theoretically be mmapable.
:
On Thu, Oct 28, 1999 at 03:53:20PM -0700, Mike Smith wrote:
How many fd's do you plan to have open?
This would be 2^17 to 2^19. Would that be advisable ? I have never
seen anything like that.
How severe is the performance
penalty (have you actually measured it yet, or are you just going on
On Thu, Oct 28, 1999 at 03:53:20PM -0700, Mike Smith wrote:
How many fd's do you plan to have open?
This would be 2^17 to 2^19. Would that be advisable ? I have never
seen anything like that.
That would be difficult.
How severe is the performance
penalty (have you actually measured
Michael Beckmann [EMAIL PROTECTED] wrote:
On Thu, Oct 28, 1999 at 03:53:20PM -0700, Mike Smith wrote:
How severe is the performance
penalty (have you actually measured it yet, or are you just going on
word of mouth)?
The latter. Measuring would be difficult due to lack of tools, and I´d
On Thu, Oct 28, 1999 at 04:42:42PM -0700, Scott Hess wrote:
Urk! I don't mean to be insulting, but the notion that you would roll
_any_ solution out for a problem of this size based on word of mouth freaks
the crap out of me.
Hey ! You guys seem to have pretty strict opinions about how to
Michael Beckmann wrote:
On Thu, Oct 28, 1999 at 03:34:53PM -0700, Matthew Dillon wrote:
:OK, so I know now that I can have pretty large files in the Terabyte range.
:Very nice. But I assume I cannot mmap anything like a 100 GB file ?
:
:Michael
Intel cpu's only have a 4G
: Urk! I don't mean to be insulting, but the notion that you would roll
: _any_ solution out for a problem of this size based on word of mouth freaks
: the crap out of me.
:
:Hey ! You guys seem to have pretty strict opinions about how to solve problems.
:Right now I am just investigating the
:
: The document is not quite right. The maximum size is limited to
: 8 Terrabytes due to block-size conversions done in the kernel which are
: independant of the filesystem block size.
:
:Can you tell me how to get the 8TB value? I know all the things about
:indirect blocks and I
Here is the problem:
When you want to have 500 GB of storage, you will need 250 files. In the current
implementation of nnrpd, this will need 250 file descriptors per nnrpd. This will
limit the number of readers that can be supported on a system, because a nnrpd is
spawned for each reader. I
Matthew Dillon wrote:
: If you have a genuine need for 500Gig of news spool,
:
:This is roughly 10 days of newsfeed, btw.
This is roughly 20 days of newsfeed if one take the porn, warez, and
binaries groups, which contain mostly junk, and try to hold onto them
for the
That´s why I´m looking for a way of having large mmap´able
files. Are you saying that ALL Intel CPUs, including PIII, can only
address 4 GB?
That's correct; it's why the ia32 architecture has a '32' in its name.
I don't believe that's true. I don't have any hard evidence within
On 28-Oct-99 Mike Smith wrote:
That´s why I´m looking for a way of having large mmap´able
files. Are you saying that ALL Intel CPUs, including PIII, can only
address 4 GB?
That's correct; it's why the ia32 architecture has a '32' in its
name.
Note quite. With PAE (Page Address
On 29-Oct-99 Chuck Youse wrote:
That´s why I´m looking for a way of having large mmap´able
files. Are you saying that ALL Intel CPUs, including PIII, can
only
address 4 GB?
That's correct; it's why the ia32 architecture has a '32' in its
name.
I don't believe that's true. I
On Fri, 29 Oct 1999, Michael Beckmann wrote:
Here is the problem:
When you want to have 500 GB of storage, you will need 250 files. In the current
implementation of nnrpd, this will need 250 file descriptors per nnrpd. This will
limit the number of readers that can be supported on a
Yuch. The page address extension junk is just that... junk. Besides,
as was mentioned it wouldn't help mmap() at all. Registers are 32 bits
and nobody is going to revisit the segmentation (retch) stuff. Ugh, two
icky things in one paragraph, excuse me please while I take a
That's correct; it's why the ia32 architecture has a '32' in its name.
I don't believe that's true. I don't have any hard evidence within easy
reach, but with the introduction of the Pentium, the address space was
increased. A user process, of course, can only have 4G of addressible
31 matches
Mail list logo