Earlier today I was on a site reading a gentleman's partitioning strategy and he recommended putting the pagefile on the first partition of a 2nd HDD.  I've seen this recommended before, but what prompts this post is that in his example this pagefile partition is a primary partition.

I guess I never gave much thought to it before, but now that I am thinking about it, does it have to be a primary partition, or could it be a logical partition?

This is the site I was on.  I think I might have gotten there through a link from another post on this board, actually.

http://www.aumha.org/a/parts.htm

The C Man,

This is another approach and is what I favour.

http://aumha.org/win5/a/xpvm.htm

I have a 400 MB (max 1000 MB) page file on the C: drive. My maximum usage has been 190 MB. Average usage is 12 MB. You will hear all sorts of combinations. Your decision.

The C Man, if your objective is to increase hard disk performance, you may wish to review the discussion of Diskeeper’s I-FAAST technology in this thread.

Thanks for the links, guys.  It's not so much that I want to eek out every last bit of HDD performance as it is that I want to cut down on fragmentation, that's the reason for my interest in locating the pagefile on a separate drive.  I don't know what I'm going to do for sure yet, but my initial question remains: if I do put the pagefile on a 2nd HDD, does the partition have to be a primary partition, or could it be a logical partition?

The C Man, you want to cut down on the fragmentation of your paging file?  If so, the free PageDefrag utility might be of interest.

Most good defragmentation utilities (including Diskeeper 2007) also have the capability to defrag the paging file, too.

I do not know the answer to your original question, but the motivation for asking it may dissipate if you adopt the use of a tool such as Diskeeper 2007 that continuously and unobtrusively defragments in the background.

wrote on Dec 15^th, 2006 at 11:18am:

I want to cut down on fragmentation, that's the reason for my interest in locating the pagefile on a separate drive.

I assume you are referring to pagefile defragmentation. It's rare and as Pleonasm mentioned, easily fixed with a good defrag program.

I used to have my pagefile in a logical partition on the second HD but it shouldn't matter if the partition was primary or logical.

Ok, thanks Brian.

most ppl move their swap/page file to another (physical) drive for performance reasons.

you just have to make sure the other hd is as fast (or faster) as the one you're moving it from (many aren't).

moving the page file was more of an issue back when memory was expensive. now that many systems come with 512-MB, or 1-GB, or even 2-gigs of memory, the swap/page files get limited use.

note that the link you reference refers to win 95/98. in other words, things have changed since then .. an one of the main changes is that systems come with more memory, and hence use less swap/page file.

i have moved my swap/page file off a scsi boot/system drive to another scsi (15K-rpm) and noticed no perf increase.

Rad wrote on Dec 15^th, 2006 at 4:20pm:

you just have to make sure the other hd is as fast (or faster) as the one you're moving it from (many aren't).

This partitioning strategy is for an upcoming build that I don't have the HDDs for yet.  I was thinking of getting a 74 GB WD Raptor as the main HDD.  You're saying it would be a bad move to put the pagefile on a slower 7200 rpm drive then, huh?

My main reason for doing it isn't necessarily to get a performance gain, but to cut down on the amount of space the OS takes up, thereby making my Ghost images smaller.  This build will have 512 MB RAM initially, and possibly permanently.  I may up that to 1 GB, but have no initial plans to do so.

As I understand it, there is pagefile fragmentation and data fragmentation within the pagefile:

A Windows managed pagefile may have a too small initial size and when it grows, fragments get spread out wherever there is free space. When the need is no longer there, it shrinks back in size and fewer fragments. At reboot, it gets all the way down to the initial size.

A user defined pagefile with a sensible minimum (initial) size and also a sensible maximum size will not get fragmented unless conditions other than normal require more than the minimum size. As soon as the exceptional need disappears, it will shrink back into a single fragment.

Data fragmentation within the pagefile, well, what are we going to do about that? The operating system assigns space in the pagefile and where stuff ends up is dificult to control, if at all possible. As I understand it, the operating system stores the information on what is where in the pagefile in RAM and on reboot, RAM is flushed and the pagefile is history.

My conclusion is that on a modern computer with lots of RAM, pagefile fragmentation is nothing to worry about. In addition to that, even a WinXP managed pagefile has a sensible initial size, not like a Win9X managed pagefile which grew and shrunk all the time. Data fragmentation within the pagefile is nothing to worry about unless the computer is running 24/7 with reboots weeks or months apart.

Christer

Quote:

My main reason for doing it isn't necessarily to get a performance gain, but to cut down on the amount of space the OS takes up, thereby making my Ghost images smaller.

Don't worry about Image file size. In Ghost 2003, pagefile.sys, hiberfil.sys and other "one session files" are excluded from the Image. I don't know about Ghost 9 and up but I don't think that they backup useless crap.

Set the pagefile on C: to user managed with the sizes 768 MB - 1536 MB which is 1.5 x RAM - 3.0 x RAM. I use that setting and it has never been increased in size. As far as I know, used pagefile has never been over a few hundred MB when I work in Photoshop and PowerPoint simultaneously.

Christer

Christer wrote on Dec 15^th, 2006 at 4:47pm:

Don't worry about Image file size. In Ghost 2003, pagefile.sys, hiberfil.sys and other "one session files" are excluded from the Image.

Thanks very much, I didn't know that.  Maybe moving the pagefile isn't needed then.

I've read a lot of positives about the noticeable speed improvements with the 10000 rpm Raptors so I'm leaning towards getting one for my main HDD.  Once I get XP installed, activated, and Ghosted I'm going to go to work on cutting out as much excess as I can (I'm a minimalist).

Even with a 5 GB system partition I could easily set the pagefile size to 2GB and have no worries then, right?

With the pagefile on the same HDD as the OS it won't matter then if my 2nd HDD for storage/dowloads/backups is 7200 rpm, correct?

Quote:

Even with a 5 GB system partition ...

I use ~5 GB of my 12 GB system partition. I don't have very much installed, Office, Acrobat, Photoshop, Nero and a few smaller applications. Even if you go "lean", 5 GB is way too small. You will grow out of space. Personally, on a 74 GB Raptor, I would make the system partition 20% and the data partition 80%. The 7200 rpm SATA would be partitioned in two for data backup and Ghost Images. I never ever defragment the partition with Ghost Images. (I actually have an 80 GB HDD partitioned in two. When the first partition gets full, I shift to the second partition and when that one gets full, I reformat the first partition.)

You haven't mentioned (I think) separating programs on a partition of their own. No matter what, the installer writes to the system partition, in C:\Windows, C:\Documents and settings and to the registry. That would involve keeping two Images synchronised, one of the system partition and another of the programs partition. Any change to the programs partition would spill over on the system partition.


Quote:

... I could easily set the pagefile size to 2GB and have no worries then, right?

I am not sure that would be wise. Programs are designed to "request" a certain amount of Virtual Memory. Windows is smart enough to not assign all to RAM but most of it to the pagefile (programmers always overdo the request). I don't know if these "assignments" in the pagefile are counted in "pagefile usage" but no matter what, with 512 MB RAM, I would not go lower than 256 MB - 512 MB pagefile. Well, to be honest, I would let it have 768 MB - 1536 MB even if pagefile usage monitors indicate that it doesn't get used. (1.5xRAM - 3.0xRAM is the Microsoft recommendation for a "semi fixed" pagefile.)


Quote:

With the pagefile on the same HDD as the OS it won't matter then if my 2nd HDD for storage/dowloads/backups is 7200 rpm, correct?

That's my understanding of the matter.

Another thing to consider, if you use Photoshop, put the scratch file on a partition other than C:. Adobe recommends to put it on a different partition than the one with the pagefile. Some create a small partition for the scratch file alone.

Christer

Christer, if you using 5 GB of your 12 GB system partition is considered not having very much installed, I'm not sure what I do even constitutes computing!   :D

On my heavily customized WIn9x system, the O/S and all my programs totals less than 300 MB.  No Photoshop, no Office, no games.  I do use v5 of Acrobat.  I just checked my Program Files folder and there's 41 programs installed.  I am getting a DVD burner so I'll be adding a software burning program but other than that what I have now is pretty much what I live with.  Obviously with XP the OS will take up more space, but programs-wise I don't see myself ever using multi-gigabytes.

I'm still new to XP (2-3 months), still haven't activated it yet b/c I still need the HDDs for this new build, so so far I've just installed it on an unused HDD I have here and then after 28 days I reformat and reinstall.

Both times I've installed it I've done so on a 5 GB partition.  It feels like it runs the same speed as my Win9x system, and this is on an Athlon Thunderbird 1000 MHz from 2001.  :o  The new system will be using a Sempron 3400 2.0 GHz.

When I mentioned setting the pagefile to 2 GB, I just meant the upper ceiling for its size, not a fixed size.

You're right, I didn't mention putting both my data & programs on a separate partitions, but I was planning on it, and then using TweakUI or whatever reg hacks I need to to get Windows to behave appropriately.

For what it's worth, this is my thinking regarding having a separate partition for both the OS and Programs....

With them both installed on the same partition as they are on my system currently, it seems like you needlessly back up all those static program files every time you make a Ghost image.  With the programs on a separate partition this would again cut down on the size of the OS Ghost image.

So do a fresh install of Windows and immediately make an image of it.

Then customize Windows to your liking and image the OS partition again.

Then in your programs partition install all of your "core" programs (your mainstays, stuff you know you'll always want to have installed). Now your OS partition has changed somewhat because there are plenty of new registry entries and DLLs installed, so image it again.

You can now backup/clone your programs partition one time and be done with it (unless/until you found other programs you wanted to install permanently) and then never have to restore it again unless of a HDD failure.

At this point you have your system set up exactly as you want it. Any time you find another program you want to install permanently just install it to your programs partition and then immediately image the OS partition, and do an incremental backup of the Programs partition.

As I was developing this partition & image strategy in my mind it occurred to me that if you were in the habit of frequently experimenting with other software outside of your "core" apps and were constantly installing and uninstalling them, instead of using those program's own uninstall routines or Windows' Add/Remove Programs and not knowing for sure if it removed every last trace of the program and reg entries, you could just manually delete that program's folder from the programs partition, restore your OS image, and be back to where you were prior to installing the program in the first place.  Sure, it would take longer, but I'm just saying if you were really anal about it you could do it that way.  If not, then just uninstall them the 'normal' way.

I don't know if those reading this will think that this strategy is excessive or overblown or whatever, but in my mind it makes perfect sense.  :)

Rad wrote on Dec 15^th, 2006 at 4:20pm:

i have moved my swap/page file off a scsi boot/system drive to another scsi (15K-rpm) and noticed no perf increase.

I used to have a 2 GB pagefile on the second HD. I moved it to the C: drive and reduced its size to 400 MB. I haven't noticed a performance decrease.

If I read my posted link correctly I could get by with a 200 MB pagefile (minimum setting) because I never exceed that value. Tha maximum setting is 1 GB just in case of growth. What you see in the C: drive as pagefile.sys is the minimum setting. As Christer mentioned, the pagefile (and the hibernation file) isn't included in a Ghost 9/10 backup image.

The C Man


Quote:

does it have to be a primary partition, or could it be a logical partition?

It can be either--I run my page file on a second HDD that has only logical partitions inside a single extended partition.

The reason for making the second HDD a single extended partition is that it is then assigned drive letters last, and will not effect the current drive letters on the first HDD--if you are for instance adding a second HDD to an existing system whose first HDD has a primary and maybe a couple logical partitions in an extended partition.

When Windows, and especially DOS, initially assign drive letters--all non-hidden primary partitions get a drive letter first--so all visible primaries on the first HDD get a drive letter, then all visible primaries on the second HDD get a drive letter, then all logical partitions on the first HDD get drive letters, and then all logical partitions on the second HDD get drive letters.

If you add a second HDD to a system that already has drive letters assigned to the extended partitions on the first HDD--those drive letters will get *bumped* because the primary on the second HDD gets a drive letter before the logical partitions--now, this is only true in DOS, Win3.1, Win95, Win98, and WinMe--NT based OS's such as WinXP *remember* drive letter assignments based on the HDD's disk ID--so this *bumping* will not occur while in the WinXP OS--but if you boot to DOS for Ghost procedures--drive letter assignments will not match because in DOS--drive letters are assigned on each boot and are not *remembered*!

If you make the second HDD a single extended partition with logical partitions inside--now its drive letters are assigned last, and the drive letters on the first HDD will remain as they were!


Quote:

It's not so much that I want to eek out every last bit of HDD performance

As mentioned by others, the performance gain by placing the page file on a second HDD on systems with 512 MB or greater is probably greatly over-rated--except under one condition!--if you have multiple users who log on and off your system multiple times during the day, and you use *Fast User Switching*.

*Fast User Switching* saves the *system state* of a given user to the page file when one logs off, and another user logs on--now the page file is going to get *heavy usage* and you have to have a page file that is big enough to hold your system RAM times the # of users that will log on and off during the day + the amount of regular page file use.  On my system, on average I use about 180 MB for page file usage--so say for safety I set aside 325 MB for the page file (.325 GB).  If I had 1 GB of RAM and four users using Fast User Switching, then I would set aside a minimum of 4.325 GB for the page file.

Now, each time a user signs off and a new user signs on, the first users *system state* i.e. all of RAM is *paged out* to the page file--and all the second user's *system state* on the page file is read back into RAM when the second user signs on--now there is a performance benefit to having the page file on the outer part of the HDD platter on a second HDD!

Under *normal* single user use--the page file is usually not a major performance problem--programs place data there in case they have to be *paged out* because there's not enough system RAM, but if there is enough RAM, then the page file does not actually get used much--it's there and has data in it, but it's never accessed or used--so the second time a page file becomes a performance issue is if you have less than 512 MB of system RAM, or you open so many programs at once that the system runs out of RAM and has to *page out* the present program(s) in RAM so another program can take its place in RAM so the system can use that program.


Quote:

I want to cut down on fragmentation, that's the reason for my interest in locating the pagefile on a separate drive

That's probably the best reason to consider placing the page file in its own partition--even if it's not on a second HDD on the outer part of the disk as the first partition.

If the page file is being managed by Windows, it will grow and shrink as needed, and Windows will place it in all the holes or empty spaces during boot that are present--then Windows adds program files during use--the page file may grow adding to itself, but fragmented from the rest of the page file--and Windows adds more files after it--so the permanent Windows files have to work around all the fragmented page file segments on the OS partition--which is contributing to the fragmentation of the OS files.  On re-boot, the page file is re-created and fills the various holes, and Windows has to work around that again, and so on the fragmenting process goes.

So, placing the page file in its own partition can help reduce the fragmentation process.

NightOwl, that's the reason I asked whether the partition on the 2nd HDD could be logical instead of primary - because of the way the drive letters would shift if it had to be a primary partition.

I picked up this nice little program about a month ago, it lets you assign drive letters in Win9x and 'hold' them.  I successfully used it to keep my main HDD's drive letters assigned as C,D, & E (primary and two logicals) when I was dual booting between 9x and XP.

Not sure how much it'll interest anyone here since you're probably all on an NT based OS, but here's the link anyway.

http://www.v72735.f2s.com/LetAssig/

The C Man,


Quote:

When I mentioned setting the pagefile to 2 GB, I just meant the upper ceiling for its size, not a fixed size.

Hmm ... :-/ ... it must have been late (in Sweden) when I made my comment on the 2 GB pagefile ... ::) ... I read it as 2 MB which is the absolute minimum "recommended" by Microsoft. Sorry about that.

Nightowl,


Quote:

... and you have to have a page file that is big enough to hold your system RAM times the # of users that will log on and off during the day + the amount of regular page file use.

I never thought of that. I have set up a computer for a family of four with the standard pagefile setting 1.5-3.0xRAM. That computer is primarily used by one user and maybe another but never all four "fast user switching".


Quote:

On re-boot, the page file is re-created and fills the various holes, and Windows has to work around that again, and so on the fragmenting process goes.

If a system has been set up with a Windows managed pagefile, change it to a "semi-fixed" pagefile with sensible minimum and maximum sizes. Create a Ghost Image, check the integrity and immediately restore it. Since the pagefile is excluded from the image (there is a place holder displaying the size but it is empty, 0 bytes), it gets recreated in a single contiguous chunk during the restoration of the Image. Not only that, it also gets located towards the front of the partition, only the most important system files have higher priority.

Christer

The C Man


Quote:

Not sure how much it'll interest anyone here since you're probably all on an NT based OS, but here's the link anyway.

Actually, I dual boot to Win98se on one system--and another is still exclusively Win98se--always happy to see links to interesting programs and utilities--thanks for the link!

Looks like you would still see drive letter re-assignment in DOS however--in your experience is that true?

Christer

Couple references to *Fast User Switching*:

How To Use the Fast User Switching Feature in Windows XP

Optimize Windows XP--Fast User Switching

In that last link above--apparently the recommendation as to how to *optimize* Fast User Switching is to *not* use it!

I found the information on Fast User Switching and the page file buried in this reference:

Virtual Memory in Windows XP


Quote:

What about Fast User Switching then? If you use Fast User Switching, there are special considerations. When a user is not active, there will need to be space available in the page file to ‘roll out’ his or her work: therefore, the page file will need to be larger. Only experiment in a real situation will establish how big, but a start point might be an initial size equal to half the size of RAM for each user logged in.

It looks like that segment of the webpage has changed from what I originally read--now says to start by using *half the size of RAM*--used to say the *full amount of RAM* per user!

This is another interesting *page file* link:

How can I optimize the Windows 2000/XP/2003 virtual memory (Pagefile)?

***********************************************
Christer wrote:


Quote:

If a system has been set up with a Windows managed pagefile, change it to a "semi-fixed" pagefile with sensible minimum and maximum sizes. Create a Ghost Image, check the integrity and immediately restore it. Since the pagefile is excluded from the image (there is a place holder displaying the size but it is empty, 0 bytes), it gets recreated in a single contiguous chunk during the restoration of the Image. Not only that, it also gets located towards the front of the partition, only the most important system files have higher priority.

Another forum poster had mentioned that he used Ghost image restores as his *defragmenter* rather than programs like Perfect Disk or Disk Keeper--interesting concept!  I think if you create a page file where both the min and max are the same, you then create a *permanent* page file in one contiguous space and now Windows will not resize it--and that reduces *fragmentation* of files also if the page file is on the OS partition.

The C Man, one option to possibly consider is disabling the use of the paging file – see How to stop the NT Executive from paging to disk.  Of course, before testing this approach, it would be wise to create a Ghost backup of your system.

Pleonasm wrote on Dec 16^th, 2006 at 10:06am:

The C Man, one option to possibly consider is disabling the use of the paging file – see How to stop the NT Executive from paging to disk.  Of course, before testing this approach, it would be wise to create a Ghost backup of your system.

This is a good tweak.  I've used it on several pc's that have 1gb of memory and it definitely improves the responsiveness of XP.

Here's another reference to it:

http://www.winguides.com/registry/display.php?id=399

NightOwl wrote on Dec 16^th, 2006 at 9:20am:

Looks like you would still see drive letter re-assignment in DOS however--in your experience is that true?

From personal experience, I don't remember, but I'm looking in the program's folder right now and see both Letassig.exe & Letassig32.exe.  Oh, and I see in the small text file 'manual' that it says it works in DOS too.  There ya go.

Pleonasm, I'll look at that tweak here in a bit.  Ghost4me, glad you can verify that it works well.

Last month I had shut off the page file temporarily just to see what would happen, and everything booted up and worked fine.  Again, this was with 512 MB RAM on an Athlon Thunderbird 1000 MHz from 2001.

I'm going to reinstall XP in about an hour I hope (going to try doing it off the HDD w/o booting into Win9x first), and I'll definitely try out that tweak.

Pleonasm


Quote:

one option to possibly consider is disabling the use of the paging file

The tweak you mentioned above does not appear to *disable the use of the paging file* in general--it appears to only apply to one system function of whether the NT Kernel uses the paging file or not.

Ghost4me


Quote:

This is a good tweak.  I've used it on several pc's that have 1gb of memory and it definitely improves the responsiveness of XP.

I tried the tweak myself--did not see any obvious performance change on my system--and I've also run across several references that question whether it has any performance effects because the *normal* behavior of WinXP is to keep the kernel in RAM as long as there is enough in the first place--and if there isn't enough RAM, well you will have other performance problems far sooner--here's one:

See *Disable Paging of Kernel*

Here's another:

See:  *Update: I asked Windows guru Ed Bott... *

NightOwl,


Quote:

I think if you create a page file where both the min and max are the same, you then create a *permanent* page file in one contiguous space and now Windows will not resize it--and that reduces *fragmentation* of files also if the page file is on the OS partition.

I see no reason to not give the OS the possibility to temporarily increase the pagefile if needed. The initial chunk (1.5xRAM) will always be static and any additional increase (up to 1.5xRAM with my setting) will be in additional fragments but they will be deleted when the need no longer exists. That setting would actually work with fast user switching and two users.

Christer

Interesting links in Reply #24, NightOwl (although the experience of Ghost4me seems to contradict the author's assertion about the lack of an impact of the tweak described in Reply #21).

Here's another tip that might be of interest to readers of this thread.


Quote:

If your PC has at least 1GB of RAM, you may be able to speed up your PC by disabling the swap file in your virtual memory settings. Simply click No paging file in the Virtual Memory dialog box (see Figure 1). To open your virtual memory settings in Windows XP, right-click My Computer, click Properties, Advanced, choose the Settings button under "Performance", click the Advanced tab, and select the Change button.

Source:  http://www.pcworld.com/article/id,123413-c,optimization/article.html#

From a security perspective, one tweak that I have used is to Clear the Windows Paging File at Shutdown, in order to ensure that all content stored in virtual memory is erased.

Pleonasm


Quote:

Here's another tip that might be of interest to readers of this thread. Source:  http://www.pcworld.com/article/id,123413-c,optimization/article.html#

See here for a discussion of why this tweak may be counter productive:  Virtual Memory in Windows XP--See the heading: *Can the Virtual Memory be turned off on a really large machine?*


Quote:

Strictly speaking Virtual Memory is always in operation and cannot be “turned off.” What is meant by such wording is “set the system to use no page file space at all.” Doing this would waste a lot of the RAM. The reason is that when programs ask for an allocation of Virtual memory space, they may ask for a great deal more than they ever actually bring into use — the total may easily run to hundreds of megabytes. These addresses have to be assigned to somewhere by the system. If there is a page file available, the system can assign them to it — if there is not, they have to be assigned to RAM, locking it out from any actual use.

I guess if you don't really need all that RAM in the first place that the virtual memory is locking up, then this tweak causes no harm--but, if you have that much RAM, I doubt it helps performance either--because virtual memory is never used!

RE:  "if you have that much RAM, I doubt it helps performance either -- because virtual memory is never used"

NightOwl, I have read that Windows XP will fulfill some memory allocation requests with virtual memory even when there is unused physical RAM available.  I don't know the algorithms and rules of how this works, but my understanding is that even if a user has a huge amount of physical RAM, an enabled paging file will still be employed.

Pleonasm


Quote:

my understanding is that even if a user has a huge amount of physical RAM, an enabled paging file will still be employed.

I too believe that is correct--but the page file is just a place holder for when some programs load--they are programed to tell the system that they need "X" amount of virtual memory addresses (be it the page file on a HDD, or the RAM set aside for virtual memory if you have disabled the HDD page file option) set aside in case the program needs to be *paged out* to virtual memory.  Once that *record keeping* function has occurred--then the program does not access the virtual memory (be it HDD page file or RAM virtual memory) until the system actually determines that it has run out of RAM, and has to send one or more program that's in regular program RAM memory to virtual memory.  If virtual memory is in RAM--then you are in a loosing spiral of counter productive activity--the system is sending programs from regular program RAM to virtual memory RAM--sounds self defeating to me!


Quote:

because virtual memory is never used

What I mean here, is that it is not actively accessed or used on an on-going basis once the place holder actions have been performed--data has been place in the page file, it's there, but the programs are not being *paged out* unless you have actually run out of regular program RAM for the system to use.

Pleonasm

As regards to Ghost4me's performance results, the author of this website--  Bad Tweaks, has offered to test and review legitimate and verifiable data:


Quote:

*****Conclusion I’m sure some will argue with my conclusions. I'm always looking for information about new tweaks and why tweaks either do or do not work. I will entertain arguments about this information but I will require a few things: 1 – You must submit documentation for your argument from a legitimate source. In matters involving the registry it should be from Microsoft or from some entity of equal weight. 2 - I hear things like “my benchmarking” and “my tests”. That, to be quite frank, is a load of crap. What “benchmarks”? What “tests”? Any benchmarks/tests used in your argument must be fully documented. They must also be able to be replicated and if your argument has any merit, I will attempt to do just that. If it can’t be replicated it fails the scientific method and the argument is null. I’ve already benchmarked/tested these settings extensively.

Based on the fact that apparently the website's author has not changed his recommendations on the items presented, apparently no one has presented data to make him change his recommendations.

I would suggest Ghost4me present his data for peer review!

I saw a perceptible improvement in the consistency of responsiveness of XP.  The real improvement came with IE7 and multiple tabs (multiple websites open at once).  Perhaps that explains the memory loading or strain and the conditions upon which it improved performance.

Regarding peer review, I suggest that TweakHound has not followed his own practice.  Where is his requirement that "1 – You must submit documentation for your argument from a legitimate source. In matters involving the registry it should be from Microsoft or from some entity of equal weight."?

His statement is without any reference:


Quote:

Disable Paging of Kernel [HKEY_LOCAL_MACHINE\SYSTEM\CurrentControlSet\Control\Session Manager\Memory Management] "DisablePagingExecutive"=dword:00000001 Under all but the most very extreme circumstances it does nothing. What this setting does is force XP to keep the kernel (the core of the operating system) in RAM. This means that the kernel will reside in the fastest storage area in your computer. Sounds great right? Guess what? XP does this anyway unless the system comes under such an extremely heavy load that it needs the space. The very millisecond that the system has free memory, it will put the kernel right back into RAM. If the system is in such dire straights that it needs to use the space that the kernel is using I would say you are on your way to a crash and you better let whatever wants the space have it. You also better add more memory ASAP.

1 – You must submit documentation for your argument from a legitimate source. In matters involving the registry it should be from Microsoft or from some entity of equal weight.


Quote:

What “benchmarks”? What “tests”? Any benchmarks/tests used in your argument must be fully documented. They must also be able to be replicated and if your argument has any merit, I will attempt to do just that. If it can’t be replicated it fails the scientific method and the argument is null.

I would suggest NightOwl and others present their data for peer review!

Ghost4me, you’re marching to the tune of the right drummer!  

Let he who is making the assertion provide the facts.  Empiricism rules!  ;)

I wasn't trying to claim that my comments and testing would stand up to scientific scrutiny.  Just a simple before-and-after comparison.  

It seemed to help on the pc's (1gb memory) that I tried it.  Your mileage may vary.