Search results

P
Why can't Vista 32-bit use a separate memory address space for SuperFetch?

Try and read a bit about memory management
- pallejr
- Post #38
- Oct 18, 2008
- Forum: Operating Systems
P
Why can't Vista 32-bit use a separate memory address space for SuperFetch?

You say: "but the applications buffers may not be." I have said (how many times): if the memory manager ensures these buffers are below 4G ... hello?
- pallejr
- Post #36
- Oct 17, 2008
- Forum: Operating Systems
P
Why can't Vista 32-bit use a separate memory address space for SuperFetch?

I'm slow? Let us stop this here.
- pallejr
- Post #34
- Oct 17, 2008
- Forum: Operating Systems
P
Why can't Vista 32-bit use a separate memory address space for SuperFetch?

I said: if the memory manager makes sure that dma buffers are always allocated below 4G, no double buffering will ever be required.
- pallejr
- Post #31
- Oct 17, 2008
- Forum: Operating Systems
P
Why can't Vista 32-bit use a separate memory address space for SuperFetch?

Yes, I have read all that. You don't understand what I write, and what it means. So let us drop it. Just a note, now you are hooked on double buffering. In a 64bit OS, if the buffer is above 4G, and the device cannot reach that high, double buffering will also happen here.
- pallejr
- Post #29
- Oct 17, 2008
- Forum: Operating Systems
P
Why can't Vista 32-bit use a separate memory address space for SuperFetch?

It might be getting old, and this might not be the place to discuss it. But if the memory manager chooses only to give away memory below 4G to drivers, no double buffering will ever be needed.
- pallejr
- Post #26
- Oct 17, 2008
- Forum: Operating Systems
P
Why can't Vista 32-bit use a separate memory address space for SuperFetch?

Wind up double buffering? That technique is being used when buffers are above 4G, but the device cannot address that high. By only using ram below 4G, double buffering would never be used.
- pallejr
- Post #24
- Oct 17, 2008
- Forum: Operating Systems
P
Why can't Vista 32-bit use a separate memory address space for SuperFetch?

What I said about PAE. If drivers only get their buffers allocated below 4G, you won't have the problem. If superfetch should work like that, you would have another problem. At some point, you would run out of address space, and that would force Windows to page data out to the harddrive, or...
- pallejr
- Post #22
- Oct 17, 2008
- Forum: Operating Systems
P
Why can't Vista 32-bit use a separate memory address space for SuperFetch?

Unless you run in PAE mode and use the upper address space you won't be using it at all. So your idea would be that the memory manger caches data up there, and copy it down below 4G before being used?
- pallejr
- Post #20
- Oct 17, 2008
- Forum: Operating Systems
P
Why can't Vista 32-bit use a separate memory address space for SuperFetch?

No need to do any extra copying. If Microsoft made sure the address space above 4G wouldn't be used by drivers, the problem they talk so much about would go away.
- pallejr
- Post #18
- Oct 17, 2008
- Forum: Operating Systems
P
Why can't Vista 32-bit use a separate memory address space for SuperFetch?

If you have more ram than your OS is willing to use, maybe a ramdrive will make you happy. SuperSpeed has a product that they say will ignore this 4G boundary. And sometimes I wonder what makes PAE a "hack".
- pallejr
- Post #9
- Oct 16, 2008
- Forum: Operating Systems
P
Pagefile use when having lots of ram

Sure, but that wasn't the point at all.
- pallejr
- Post #33
- Oct 16, 2008
- Forum: Operating Systems
P
Pagefile use when having lots of ram

This is still something the memory manager takes care of. And pagefile backed sections can also be backed by physical memory alone. This subject has been discussed in these forum before.
- pallejr
- Post #26
- Oct 14, 2008
- Forum: Operating Systems
P
Pagefile use when having lots of ram

Personally, I am not happy about such statements. Because applications cannot address the paging file. Only the windows memory manager has access to it.
- pallejr
- Post #24
- Oct 14, 2008
- Forum: Operating Systems
P
Pagefile use when having lots of ram

What do you mean?
- pallejr
- Post #16
- Oct 11, 2008
- Forum: Operating Systems
P
When will Windows become sophisticated enough to...

In vista they have also developed a system, where you can update critial system components runtime...
- pallejr
- Post #24
- Oct 6, 2008
- Forum: Operating Systems
P
When will Windows become sophisticated enough to...

That is something completely else. That is because the service/application that uses those rules only reads them when it starts.
- pallejr
- Post #23
- Oct 6, 2008
- Forum: Operating Systems
P
XP Pro and 8 GB RAM useless?

PAE is clean. Sure it introduces a small overhead, but so does 64bit mode.
- pallejr
- Post #13
- Sep 26, 2008
- Forum: Memory and Storage
P
How much a Windows OS uses...

We are talking about the artificial memory limitation that Microsoft put in their OS. If they cap this one at 8GB. How do they count to eight gigabyte? Is it in address space, or just in RAM? If it is in address space, it will be 8GB minus MMIO, no matter how much address space the hardware...
- pallejr
- Post #14
- Sep 25, 2008
- Forum: Memory and Storage
P
How much a Windows OS uses...

Your statement: "Vista 64 Bit Basic - 8GB minus whatever the BIOS gives to hardware" If the hardware can address 64GB, and any overlapped RAM is remapped, what then?
- pallejr
- Post #12
- Sep 25, 2008
- Forum: Memory and Storage
P
How much a Windows OS uses...

I don't think we are on the same page. If the hardware supports 8GB address space, and you have 4GB RAM and 2GB MMIO. You then remap, lets say, 2GB. That gives 4GB RAM and 6GB address space. Before SP2, XP would accept this, because you still only have four GB RAM. The same goes with bigger...
- pallejr
- Post #10
- Sep 25, 2008
- Forum: Memory and Storage
P
How much a Windows OS uses...

Do you know for sure, or do you have some documentation? I'm just curious, because the amount of address space needed for MMIO is not included in that "x number of GB" in all editions, like I said.
- pallejr
- Post #8
- Sep 25, 2008
- Forum: Memory and Storage
P
How much a Windows OS uses...

tcsenter, are you sure that MMIO is included in this calculation (for 64bit)? In XP, before SP2, it was 4GB RAM + MMIO. They changed that in SP2 due to driver issues (that issue doesn't exist here).
- pallejr
- Post #6
- Sep 21, 2008
- Forum: Memory and Storage
P
beyond 4 gigs ram in xp ???

If the driver is written "correctly", according to the guidelines, it will work on all systems. All hardware specific addressing should be taken care of by Windows.
- pallejr
- Post #15
- Sep 18, 2008
- Forum: Memory and Storage
P
beyond 4 gigs ram in xp ???

I think this has been said many times before. If you can access more than 4GB with a 64bit OS, you can do the exact same thing with a 32bit OS - if the developer choose to support it. The limitations with PCI addressing does NOT go away just because you install a 64bit OS.
- pallejr
- Post #9
- Sep 17, 2008
- Forum: Memory and Storage
P
Vista 64 vs Vista 32bit

No!
- pallejr
- Post #17
- Sep 4, 2008
- Forum: Operating Systems
P
Low level format recovery

the pdf smilin links to is only four years old. I too, have shit to do. Just read (and understand) what they actually write about it.
- pallejr
- Post #39
- Sep 4, 2008
- Forum: Operating Systems
P
Low level format recovery

Do you understand the term "proof of concept"? Have you read what "actionfront" says about it? They cannot even recover the contents of a single sector. I'm not sure how money takes part in this.
- pallejr
- Post #36
- Sep 3, 2008
- Forum: Operating Systems
P
Low level format recovery

They wont do it just to prove a point? You are way off with that statement. If they could, they would, I assure you.
- pallejr
- Post #34
- Sep 3, 2008
- Forum: Operating Systems
P
Low level format recovery

*isn't commercially viable* Did you not read what I said: proof-of-concept? They cannot even produce such one, just a single sector...
- pallejr
- Post #32
- Sep 3, 2008
- Forum: Operating Systems
P
Low level format recovery

The paper says the exact same thing. Look back where I quoted the author. He has never seen this technique demonstrated in pratice, to actually recover user data. If the companies could do it, don't you think they would at least recover a couple of such sectors just for the proof-of-concept...
- pallejr
- Post #30
- Sep 3, 2008
- Forum: Operating Systems
P
Low level format recovery

http://www.actionfront.com/ts_...moval.aspx#Overwriting Read this, will you. They very clearly states that it is not possible. You can do nothing with a few random (raw) bits here and there (applies to older drives - with new drives, you get nothing). (If you care to note, this company...
- pallejr
- Post #28
- Sep 2, 2008
- Forum: Operating Systems
P
Low level format recovery

You are right, the OP asked if this was urban legend. It is. It is true that researches have been able to recover a bit here and there on old harddrives. I'm puzzled, what will you do with those few random bits? Read your own paper again, and the link I provided. The data density and precision...
- pallejr
- Post #22
- Aug 13, 2008
- Forum: Operating Systems
P
Low level format recovery

Try and read what you link to yourself. "4.2.4 Exotic Recovery It is *theoretically* possible to read some overwritten data. I have found no evidence of commercially viable recoveries being perfomed with them... Furthermore, I have seen no public demonstrations of any of these methods...
- pallejr
- Post #18
- Aug 13, 2008
- Forum: Operating Systems
P
Low level format recovery

I see it. Where is the proof? People is these forums like very much to say all this, but they can never referer to a source. The recovery companies themselves say they cannot do it. So who can? http://blogs.computerworld.com/node/5687 for example
- pallejr
- Post #15
- Aug 13, 2008
- Forum: Operating Systems
P
Low level format recovery

Like I asked earlier in the thread. Can you tell me of anyone in the real world that has done that with a modern harddrive?
- pallejr
- Post #13
- Aug 13, 2008
- Forum: Operating Systems
P
Safe Web Surfing - Can using a Virtual Machine (Virtualbox, VMware, etc.) deliver?

Why should that be impossible? If there is a security breach in the virtual machine software, which allows it to break out, it is very much possible.
- pallejr
- Post #7
- Aug 13, 2008
- Forum: Operating Systems
P
Low level format recovery

I know of that already. And surely there exists ways to recover magnetic data that has been overwritten. But in the real world today, with modern harddrives, the data density and precision makes it a no go. One reason why the government might a bit paranoid, is because you never know what the...
- pallejr
- Post #9
- Aug 12, 2008
- Forum: Operating Systems
P
Low level format recovery

Do you have some kind of proff that the government can restore a harddrive that has been overwritten just once? Because normal recovery companies cannot do it.
- pallejr
- Post #7
- Aug 12, 2008
- Forum: Operating Systems
P
8GB of RAM necessary to fully utilize 64bit memory addressing

That article is wrong. As said earlier in the thread, the PAE kernel is crippled, so you cannot address anything above 4G. Edit: to back that up with a kb: http://support.microsoft.com/kb/888137 "Additionally, the kernel memory manager ignores any physical address that is more than 4...
- pallejr
- Post #20
- Aug 6, 2008
- Forum: Memory and Storage

RESOURCES

Top Bottom