Something everyone should read

Status
Not open for further replies.
There is so much wrong with these guides. First of all there is no need to disable services. This has already been discussed many times here.

The Disable Paging Executive tweak is also bogus. It does absolutely nothing for performance. Also it only applies to ntoskrnl.exe which is only a few MB in size. Since this will always be used and is such a small size it would rarely be paged out anyway unless under an extremely heavy load. If you do come under such a heavy load where those few MBs need to be paged out then you are most likely on your way to a crash anyway.

IOPageLockLimit is also completely ignored by Windows XP. It has been ignored since Windows 2000 SP1.

I am also sick of seeing IRQ#Priority tweaks in tweaking guides. Where the hell do they get this stuff? This is another tweak that does absolutely nothing. In terms of actual code in the OS, this hasn't been looked at since NT 3.5, if ever.

Also anything above 3 does not do anything for EnablePrefetcher.

AlwaysUnloadDLL ios also bogus. Has anyone ever noticed that this is under the "explorer" branch of the registry? If you have, did you ever wonder why? This is because it only has to do withy DLLs loaded as plug-ins by Explorer. Of course these will be paged out just like anything else if needed.

The QoS tweak is completely wrong too. It does not mean "a percentage (20% by default) of your bandwidth is sitting unused." as that article says. A program that uses it may reserve 20% of it, but if it is not sending enough data to utilize it completely, then the bandwidth can be used for other things.

SecondLevelDataCache is also a myth. This registry key is a secondary source for the size for older computers where the HAL cannot detect it. The HAL can on any CPU Pentuim II or newer. So if you have a system with a Pentuim 1 or older this may increase performance, but it won't be noticable and who the hell would bothyer tweaking an old machine like that? Pentuim II's or newer are not affected by this tweak.

I hope you learned something from all that. Take every tweak guide you read with a grain of salt.
 
KoolDrew said:
There is so much wrong with these guides. First of all there is no need to disable services. This has already been discussed many times here.

The Disable Paging Executive tweak is also bogus. It does absolutely nothing for performance. Also it only applies to ntoskrnl.exe which is only a few MB in size. Since this will always be used and is such a small size it would rarely be paged out anyway unless under an extremely heavy load. If you do come under such a heavy load where those few MBs need to be paged out then you are most likely on your way to a crash anyway.

IOPageLockLimit is also completely ignored by Windows XP. It has been ignored since Windows 2000 SP1.

I am also sick of seeing IRQ#Priority tweaks in tweaking guides. Where the hell do they get this stuff? This is another tweak that does absolutely nothing. In terms of actual code in the OS, this hasn't been looked at since NT 3.5, if ever.

Also anything above 3 does not do anything for EnablePrefetcher.

AlwaysUnloadDLL ios also bogus. Has anyone ever noticed that this is under the "explorer" branch of the registry? If you have, did you ever wonder why? This is because it only has to do withy DLLs loaded as plug-ins by Explorer. Of course these will be paged out just like anything else if needed.

The QoS tweak is completely wrong too. It does not mean "a percentage (20% by default) of your bandwidth is sitting unused." as that article says. A program that uses it may reserve 20% of it, but if it is not sending enough data to utilize it completely, then the bandwidth can be used for other things.

SecondLevelDataCache is also a myth. This registry key is a secondary source for the size for older computers where the HAL cannot detect it. The HAL can on any CPU Pentuim II or newer. So if you have a system with a Pentuim 1 or older this may increase performance, but it won't be noticable and who the hell would bothyer tweaking an old machine like that? Pentuim II's or newer are not affected by this tweak.

I hope you learned something from all that. Take every tweak guide you read with a grain of salt.
Click to expand...

I'm sure you're very knowledgable, however, if he said the guide gained him that much of a performance increase, it's tough to rag on it...

This is assuming he's being honest lol
 
Well there KoolDrew....I am not sure if you base your opions on actual fact or simply becuase you heard some one somwhere else tell you this is bad. I look at it this way....I install xp pro along with all the drivers for my system. I did bone stock benchies, then I did the tweaks. I noticed quite a bit of improvement over the stock OS. I also gained higher oc's and the system just seemed more stable.

How can you say turning off servcies doesnt do anything. If a services is running and has to start up everytime with windows it is using some resource. It may not be a huge difference but I for one know that indexing, error reporting, auto updates all use memory if left on. They have too. I am sorry man, in my opinion you wasted a post.
 
I'm sure you're very knowledgable, however, if he said the guide gained him that much of a performance increase, it's tough to rag on it...
Assuming he is being honest. lol
Click to expand...

I will put it this way. I am not eduacated in programming, and I am sure that my tests arent done to scientific specifacations. However, using Sisandra, and the line of Futuremark benchmarks I noticed a nice increase.

As far as being honest, I didnt get on here and say that this allowed my to oc my 2.4ghz to 4ghz. I simply stated I noticed a decent gain in performace and thought maybe I would share. People like KoolDrew make forums a waste of time. Instead of discussing why he feels these tweaks are false, he want to tell me I dont know what I am talking about. Thats just not helpful
 
Joni Nitro said:
How can you say turning off servcies doesnt do anything. If a services is running and has to start up everytime with windows it is using some resource. It may not be a huge difference but I for one know that indexing, error reporting, auto updates all use memory if left on. They have too. I am sorry man, in my opinion you wasted a post.
Click to expand...
Before you decide to put down KoolDrew, go to the search function and read the several hundred posts concerning disabled services. If you read them, and understand how these services work, you'll find out that KoolDrew is right. It's a myth that's been debunked a hundred times over. I don't mean this to be offensive to you, as your only trying to be helpful, but the worst thing you can do on here is put someone down over a topic that's been proven time and time again.
 
Ok, if I am wrong I am wrong. I did not mean to put down Kool, I was just trying to help. Anyways, they seemed to help me so if anyone wants to try them go for it.
 
I'm sure you're very knowledgable, however, if he said the guide gained him that much of a performance increase, it's tough to rag on it...
Click to expand...

I see people say tweaks like IOpagelocklimit give them performance increases in Windows XP. Since there is no code in the OS related to this key there is no way it would have an affect on anything.

This guy did say he did have a higher OC and slightly higher 3Dmark scores. There are some tweaks in that guide that may bve helpful such as startup applications in msconfig. A lot of it is bogus though. The same with the thousands of over tweaks guides on the net.

Well there KoolDrew....I am not sure if you base your opions on actual fact or simply becuase you heard some one somwhere else tell you this is bad. I look at it this way....I install xp pro along with all the drivers for my system. I did bone stock benchies, then I did the tweaks. I noticed quite a bit of improvement over the stock OS. I also gained higher oc's and the system just seemed more stable.
Click to expand...

Most of my post was fact, if not all of it. Also as I said before some tweaks may help but the majority are bad advice or just plain false information. Just like every other guide out there.

How can you say turning off servcies doesnt do anything. If a services is running and has to start up everytime with windows it is using some resource. It may not be a huge difference but I for one know that indexing, error reporting, auto updates all use memory if left on. They have too. I am sorry man, in my opinion you wasted a post.
Click to expand...

This has been explained many times here. Here is a good example.
http://www.hardforum.com/showthread.php?t=878887&highlight=services

Read the post by GreNME about services at the beginning.
 
It's also worth noting that 3DMark is a completely synthetic, albeit worthless actual benchmark for system performance. My scores, in every version of 3DMark ever released, fluctuated greatly, just by re-running the tests. I always had different scores. 100 overall points is such a little change, I would attribute it to the randomness of the tests, and nothing more.
 
Thanks for the links Joni Nitro.

And don't get discouraged. You're simply posting info that differs from the opinions of a few others.
 
Does this one bother to prove they increase performacne, or do they just say it does?

 
Badger_sly said:
Thanks for the links Joni Nitro.

And don't get discouraged. You're simply posting info that differs from the opinions of a few others.
Click to expand...
If this was a matter of opinion, you'd be correct. See above.
 
Joni Nitro, sorry your post immediately got thread crapped. Tweak guides are a hot button for a lot of folks around here. Don't give up on the [H] because a few folks around here bring baggage into the discussion and smack you around a bit when all you were trying to do was help out.
 
It's also worth noting that 3DMark is a completely synthetic, albeit worthless actual benchmark for system performance. My scores, in every version of 3DMark ever released, fluctuated greatly, just by re-running the tests. I always had different scores. 100 overall points is such a little change, I would attribute it to the randomness of the tests, and nothing more.
Click to expand...

I agree. Same with Sandra

And don't get discouraged. You're simply posting info that differs from the opinions of a few others.
Click to expand...

What exactly are you refering to as an opinion? All the tweaks I posted in my post are bogus and that is fact.

Joni Nitro, sorry your post immediately got thread crapped. Tweak guides are a hot button for a lot of folks around here. Don't give up on the [H] because a few folks around here bring baggage into the discussion and smack you around a bit when all you were trying to do was help out.
Click to expand...

And all I was doing was trying to help by pointing out the bogus tweaks.
 
KoolDrew said:
All the tweaks I posted in my post are bogus and that is fact.
Click to expand...

I will agree with a lot of what you say. However, there is still plenty of room for conjecture about some of the things you say. Rather than debate those things, I'd rather say that you should recognize the difference between a fact and an opinion. The problem is that there is no agreement or consensus about several of the arguments that you make. People have either been bored and gave up, or threads have been locked without resolution.

I have no desire to nitpick through tweaks because I truly don't care about the whole subject anymore. Please cool off on declaring facts though. It's really annoying to have someone state an opinion as a fact regardless of whether or not they're right.
 
Ya, because tweaks like IOPageLockLimit which is not even in the code for Windows XP is opinion :rolleyes:
 
KoolDrew said:
Ya, because tweaks like IOPageLockLimit which is not even in the code for Windows XP is opinion :rolleyes:
Click to expand...


I love how you have a hardon for one tweak.

Pages and pages of tweaks and you can't get over one. Seeing how this is the 3rd time you have mentioned it on just one page :rolleyes:
 
I have mentione it three times because it is a perfect example of a tweak that is in just about every popular tweak guide yet it does nothing at all. I also mentioned way more then just this tweak in my original post.
 
KoolDrew said:
Ya, because tweaks like IOPageLockLimit which is not even in the code for Windows XP is opinion :rolleyes:
Click to expand...

That would be an example of a fact. I'm not making the generalization that you don't present facts. I am saying that you present facts and data alongside other statements that are opinions and so long as your facts support your conclusions then you believe your conclusions are facts as well. However, I'm not going to get sucked into an argument about any of your conclusions about things that are not as clear cut. What I am going to say is that your conclusions are not facts even if I agree that your conclusions are correct. A fact is a measurable and observable thing. A conclusion attibutes meaning or value to the few facts of the many available that we've selected to recognize.

More to the point, instead of trying to 'help' by dissecting the tweak tips one by one, perhaps you could have simply said something to the effect that there have been a lot of discussions on these boards about tweak guides, and that many folks here are skeptical of the information presented in them. That would be sufficient to nullify any implicit endorsement of the guide and warn the uninformed that they should take the guide with a grain of salt. No one needs to be put on the defensive to the degree that you put the OP on simply for trying to help by passing along what he considered to be useful advice.

Think about it.
 
I see what you are saying. I felt that explaining the tweaks would be better then saying what you suggested though. That way at least the OP knows what they actually do.
 
Badger_sly said:
Thanks for the links Joni Nitro.

And don't get discouraged. You're simply posting info that differs from the opinions of a few others.
Click to expand...

djnes said:
If this was a matter of opinion, you'd be correct. See above.
Click to expand...

So you agree with me. That's nice.
 
Badger_sly said:
So you agree with me. That's nice.
Click to expand...
Actually, no, since this is not a matter of opinion. It's been proven to be fact. As I said before, read above. If your still not satisfied, search along these forums.

As they say in the NBA, Reading is FUNdamental.

The difference in his score was only 100 points. That was due to the absolute randomness of the scoring in 3DMark, not any actual tweaking. The facts are readily available...it's up to you to read them or not.
 
djnes said:
As they say in the NBA, Reading is FUNdamental.

The difference in his score was only 100 points. That was due to the absolute randomness of the scoring in 3DMark, not any actual tweaking. <snip>
Click to expand...
The OP states a score differential of a couple of thousand points, and an OC delta of 100 mhz. I think you might have confused the two.

IME, 3DMark score variability is in the low hundreds, an order of magnitude lower than what the OP claimed. I wouldn't feel comfortable attributing the score differential to pure test variability (though it could account for some).

My guess - if the guides do contain false information, there are some valid tweaks that do help in synthetic benchmarks (if not real world apps). I'll leave it to others to debate exactly which tweaks are beneficial, and which are worthless.
 
I wasnt even going to come back and say anything, but you all have been misquoting me the whole time.

This is what I said:
Going through this guide will definitely speed up any pc, and it gained me 100mhz higher OC and a couple thousand points in 3dmark benchies.
Click to expand...

This what you ppl are saying:
100 overall points is such a little change, I would attribute it to the randomness of the tests, and nothing more.
Click to expand...

Had I gained 100 points in benchies I would have dismissed this totally. However, 100mhz and more closely 1,560 pionts in 3dMark benchies. I am not a noob to pc, and overclocking. I wouldnt have said anything if I thought there were nazi out there with a stick up their...well. Just take or leave it and let this thread die. I wasnt trying to open a can of worms here.
 
Mind telling me how disabling services allowed you a higher overclock??
 
Joni Nitro said:
..........it gained me 100mhz higher OC and a couple thousand points .............
Click to expand...


djnes said:
.........Reading is FUNdamental.
Click to expand...

Joni witnessed the benefit, therefore it is a fact, contrary to your opinion.

And, what was that about reading?.............
 
djnes said:
Mind telling me how disabling services allowed you a higher overclock??
Click to expand...

What service or services did you disable?

Did the ambient room temperature remain the same thu out your process of applying these tweaks?

Please identify which service(s) are limiting overclocking and state your theory on why you credit disabling these service(s) with your increased clock rate on your CPU.
 
Badger_sly said:
Joni witnessed the benefit, therefore it is a fact, contrary to your opinion.

And, what was that about reading?.............
Click to expand...
So your agreeing with him that services were holding back his overclocking???? As I've stated before, you need to gain some understanding on these services "tweaks".
 
Badger_sly said:
Joni witnessed the benefit, therefore it is a fact, contrary to your opinion.
Click to expand...
Joni also increased the OC on the machine, why couldn't that account for the increase? You are not comparing apples to apples.

 
lol, sorry i cannot help it.

Everytime i read thread about services there is a huge argument that results from it. It is plain amazing. It is also amazing that some people jstu dont repsect other peoples opinion. I'll try to be fair an honest. The [H] is awesome, most of my online time is spend here. But he is right, i mean this is what sometimes kind of puts me of: forcing opinions.

Anyways, let's just shake hands, and whoever wants to try it, go ahead.... You can see for yourself! ;)
 
ive never heard of disabling services allowing a higher OC. its *possible* but highly remote. sounds to me like

1) i disabled some services
2) I OC' the cpu 100mhz
3) i did some registry tweaks
4) I wore pink panties on my head

3d mark higher scores WOOT!!!!

when actually the only thing that really mattered was 2)
 
Jesus, if you don't believe in it, then don't do it. Isnt this forum meant to help and exchange opinions?
 
jeez.jpg
 
Steel Chicken said:
1) i disabled some services
2) I OC' the cpu 100mhz
3) i did some registry tweaks
4) I wore pink panties on my head

3d mark higher scores WOOT!!!!

when actually the only thing that really mattered was 2)
Click to expand...


Excellent.
My pink panty overclocking method is still a secret.
Soon.... soon I will rule the world. Mha-mha-haha-ha-ha-ha-ha-ha!
 
Well I believe that by doing some of the tweaks....namely the irq priority tweak help the sytem to rum more stable. I know that this will be shot down almost certainly, but I am just a guy who noticed a difference. I tell you what, the tweaks are safe so try out for yourself and then tell me I am a liar.

Oh, and I tried to find some pink paties, but your mom was fresh out.....lol..just messing with ya man.
 
namely the irq priority tweak help the sytem to rum more stable
Click to expand...

I find it funny you find a difference using a tweak that does absolutely nothing. I already told you this tweak does absolutely nothing at all in my original post. If you don't believe me read this

Debunking the "Speed Up your Windows XP Box with IRQ Prioritization" Myth

Yikes! We've been caught with our pants down again. It appears that the IRQ Prioritization tweak I shared with your last week was bogus. Who would have guessed? I could have sworn that the system seemed faster, and I do know that the system locked up after making the change. Nevertheless, Jamie Hanrahan of Windows Driver Consulting and Training (www.cmkrnl.com) provides a compelling explanation for why this does not work:

"There is an easy (although I must admit not definitive) way to demonstrate that the system is unaware of this registry value. To do this requires the www.sysinternals.com utility called "strings". If you're not familiar with it, it's a Win32 character-mode version of something Unix has had for decades (not that I'm a Unix fan...) You use it like so:
c:> strings file.d a t

and it emits all printable sequences of characters from file.d a t, one per line. It's very useful when searching exe's and the like for things like file names, registry keys and values, etc. (And it's a favorite cracker's tool.) Much better than examining diskprobe output looking for printable strings! And unlike the Unix version this one works for either Unicode or Ascii.

Ok, so we do this:
c:> strings \windows\system32\ntoskrnl.e x e >ntstrings.txt

Actually that produces more output than is useful. Let's try a minimum string length of 8, that being the number of characters in "priority":
c:> strings \windows\system32\ntoskrnl.e x e -n 8 >ntstrings.txt

Add the -a option to get the ascii strings instead:
c:> strings \windows\system32\ntoskrnl.e x e -a -n 8 >ntstringsa.txt

Now of course we open ntstrings.txt and ntstringsa.txt in Notepad, or your favorite other text editor.

If you search in the files for, for example, "LargeSystemCache" or "DisablePagingExecutive", you WILL find them. Those are the constant strings compiled into the exec by which it looks up those well-known registry values.

But you WON'T find "IRQ8PRIORITY". In fact you won't even find "priority" by itself, in either the ASCII or unicode strings -- otherwise we could still think that the system was building up the name "IRQ8PRIORITY" from shorter strings, perhaps looking for IRQ0Priority, IRQ1Priority, etc., with the number being a variable.

Actually we could still think that; the string could be "assembled" from even smaller fragments, and that's why I say this isn't absolutely definitive -- but I think this is very unlikely. Some other data points:
Interrupts -- IRQs -- don't even HAVE a concept of "priority" in the NT family; they do have something called "IRQL" (interrupt request level) associated with them. But the interval timer interrupt is already assigned a higher IRQL than any IO devices, second only to the inter-processor interrupt used in an MP machine.
The NT family of OSs don't even use the real-time clock (IRQ8) for timekeeping in the first place! They use programmable interval timer (8254, on IRQ0) for driving system timekeeping, CPU time accounting, and so on. IRQ8 is used for profiling, but profiling is almost never turned on except in very rare development environments.
The same "strings" output will show that another long-written-about registry hack, IoPageLockLimit, is also missing in action. This one at least used to be there, in Win2K RTM and earlier; in Win2K SP1 they kept the mechanism but the limit was then spec'd by a new value, IoPageLockPercentage; in Win2K SP2 and later they dropped the whole thing.
I have to conclude that all reports of increased performance after making the IRQ8PRIORITY registry change, and IoPageLockLimit on Win2K SP1 and later, are due to _post hoc_ fallacy and/or placebo effect. IoPageLockLimit at least worked at one time (though the values suggested on almost every web site that mentions it actually cause the system to end up using its default of 512K anyway!). I don't know where the IRQ8PRIORITY thing came from; it's too obscure to have been made up out of whole cloth -- maybe it was valid for some version of Win9x?"

Thanks Jamie! For those of you who added this entry, just go back into the Registry and delete the value you created and restart the computer.
Click to expand...

http://www.winxpnews.com/index.cfm?id=39&search=irq8priority

So basically there is no code in the OS that even looks at this registry key. Every tweak I mentioned in my original post will do nothing for performance.
 
Status
Not open for further replies.
Back
Top