Jump to content

Welcome to MSFN Forum
Register now to gain access to all of our features. Once registered and logged in, you will be able to create topics, post replies to existing threads, give reputation to your fellow members, get your own private messenger, post status updates, manage your profile and so much more. This message will be removed once you have signed in.
Login to Account Create an Account



Photo

Windows 7: Possible, Advisable, to Disable the Page File?

Page File Paging File Virtual Memory

  • Please log in to reply
43 replies to this topic

#26
jaclaz

jaclaz

    The Finder

  • Developer
  • 15,791 posts
  • Joined 23-July 04
  • OS:none specified
  • Country: Country Flag

Well, of course a single device cannot be compared to an array, and benchmarks not always reflect actual speed or speed increase in "real" operations, but comparing this thingy with the fastest "conventional SATA" SSD drive Kingston makes (also said to be one of the fastest around) as the good guys at The Register did:

http://www.theregist...gb_ssd_storage/

seems to me fair enough, for completeness and to allow "at a glance comparison", here are the correspondent graphics for the Kingston Savage (which I will also add to the previous post):

kingston_hyperx_savage_240gb_ssd_3.jpg

kingston_hyperx_savage_240gb_ssd_4.jpg

 

@Telvm

Provided that the Savage is a "decent" SATA3 SSD, the net increase in 4K reads is still around 35%, not that bad as I see it.

 

jaclaz


Edited by jaclaz, 29 July 2015 - 06:44 AM.



How to remove advertisement from MSFN

#27
NoelC

NoelC

    Software Engineer

  • Member
  • PipPipPipPipPipPipPipPip
  • 2,674 posts
  • Joined 08-April 13
  • OS:Windows 8.1 x64
  • Country: Country Flag

 

Sorry but I'm not impressed. The 4K read speed (the one that really matter) isn't better than in a decent SATA3 SSD.

 

 

That there is so much difference between read and write speed clearly means write-back caching is involved, which means those numbers aren't worth as much as the publisher would like you to believe they are. 

 

Any system with Intel RST drivers and sufficiently large RAM will show very high numbers for write speeds because of write-back RAM caching.  Conversely, no device you will encounter will be able to sustain much higher tiny I/O rates until something fundamentally changes in the PC architecture.

 

Never forget that there are limitations based on the operating system itself that influence the speed at which a tiny I/O request can be turned around.  That's why you'll notice that even the tiny I/O write speed shown is still topping out at less than 100 MB/second.

 

I've mentioned this before - 4K bytes divided into 94.91 megabytes is 24,297 I/O operations in 1 second, or about 0.041 milliseconds per operation.  Even with today's giga processors 41 microseconds isn't a whole lot of time to do 1 I/O operation.  It simply takes some base time for the CPU to call through the proper layers to do an I/O operation.

 

Assuming a virtually zero latency operation for the write-back cache, the difference you're seeing between the actual reads and the (instantaneous writes) is 112 microseconds - 41 microseconds == 71 additional microseconds to do the I/O from the flash memory. 

 

71 microseconds to complete an I/O operation across ANY interface is phenomenally fast.  That 0.071 milliseconds round trip.  I don't know the specifics for this card, but I'm willing to bet the lion's share of that time is actually getting the data across the various interfaces.

 

You are simply NOT going to see a separate device be able to return I/O data to a CPU a whole heckuva lot faster than that.

 

NVMe will help, as the stack is shortened.  But the data is still out on the PCIe bus, which takes time to use.

 

Now, when gargantuan blobs of flash memory are integrated right into the processor chipset, THEN we'll see much greater tiny I/O throughput.

 

-Noel



#28
NoelC

NoelC

    Software Engineer

  • Member
  • PipPipPipPipPipPipPipPip
  • 2,674 posts
  • Joined 08-April 13
  • OS:Windows 8.1 x64
  • Country: Country Flag

Well, of course a single device cannot be compared to an array,

 

Actually, to me it seems a fair comparison in that you can plug, say 3 "traditional" SSDs into the SATA III ports on any given (modern) motherboard and make a super high performance RAID 0 array out of them.  Traditionally that's been cheaper and leaves the PCIe slot(s) free for your favorite game playing room heater.

 

Edit:  Furthering the thought...

 

Kingston HyperX Predator 480 GB at NewEgg.com today:  $484.99

 

Kingston HyperX Savage 240 GB "Traditional" SATA III SSD:   $91.99

 

Put three of the latter in a RAID 0 arrangement with Intel RST and spend the other $200 on a big RAM upgrade, and not only will you have half again more storage but I'm willing to bet the system will run better overall than with one of the "dollar a gigabyte" PCIe cards.

 

-Noel


Edited by NoelC, 29 July 2015 - 12:56 PM.


#29
jaclaz

jaclaz

    The Finder

  • Developer
  • 15,791 posts
  • Joined 23-July 04
  • OS:none specified
  • Country: Country Flag

Whatever :yes:, comparing apples with oranges has been proved to be allowable alright :w00t:):

http://www.improb.co...1-3-apples.html

 

 

 

jaclaz



#30
NoelC

NoelC

    Software Engineer

  • Member
  • PipPipPipPipPipPipPipPip
  • 2,674 posts
  • Joined 08-April 13
  • OS:Windows 8.1 x64
  • Country: Country Flag

True, the PCIe card solution can't really be compared to the less expensive multi-SSD solution, since the latter delivers far more capacity and is more expandable.

 

-Noel



#31
jaclaz

jaclaz

    The Finder

  • Developer
  • 15,791 posts
  • Joined 23-July 04
  • OS:none specified
  • Country: Country Flag

Maybe next year :unsure: one of these new thingies may provide some x1000 :w00t: improvements.

http://newsroom.inte...mory-technology

 

jaclaz



#32
JorgeA

JorgeA

    FORMAT B: /V /S

  • MSFN Sponsor
  • 3,845 posts
  • Joined 08-April 10
  • OS:Vista Home Premium x64
  • Country: Country Flag

Whatever :yes:, comparing apples with oranges has been proved to be allowable alright :w00t:):

http://www.improb.co...1-3-apples.html

 

 

 

jaclaz

 

That's very cute :). It's a shame that the critical graph is so tiny that you can't tell, at any zoom level, what the author is measuring (X or Y axis). :}

 

--JorgeA



#33
jaclaz

jaclaz

    The Finder

  • Developer
  • 15,791 posts
  • Joined 23-July 04
  • OS:none specified
  • Country: Country Flag

That's very cute :). It's a shame that the critical graph is so tiny that you can't tell, at any zoom level, what the author is measuring (X or Y axis). :}

Well, guess why exactly I am The Finder :whistle:

;)

 

jaclaz



#34
Radish

Radish

    Newbie

  • Member
  • 31 posts
  • Joined 11-May 15
  • OS:Windows 7 x64
  • Country: Country Flag

Maybe next year :unsure: one of these new thingies may provide some x1000 :w00t: improvements.

Cripes, brilliant! Just when Noel's comments had brought me to the brink of seriously considering getting and installing a (I suppose I'd now have say) NAND SSD they start talking about this 3D XPoint SSD. If it's as fast and as durable as they say it is then it will sell like wildfire and the price will tumble too with the volume of sales. Guess I'll hold onto my HDD for now and wait.



#35
NoelC

NoelC

    Software Engineer

  • Member
  • PipPipPipPipPipPipPipPip
  • 2,674 posts
  • Joined 08-April 13
  • OS:Windows 8.1 x64
  • Country: Country Flag

Unveiled?  Seems to me 3D memory has been on the verge of bringing us the next big jumps in speed and capacity for a couple of years now.  This certainly isn't the first I've heard of it.

 

My advice:  Don't wait for new tech to mature.  Everything available is always obsolete.  You'll wait a long time for the price to get just right, look back on what a crappy experience you put yourself through, then at the same time realize some even newer technology is on the horizon.  It's the nature of high tech.

 

If it helps, think of it as having waited for last decade's new tech (SATA SSDs) to mature.

 

Just throwing out a thought...  A workable strategy might be:  Get a couple of cheap used SSDs (OCZ Vertex 3 is a good model) and plug 'em into your computer now.  THEN get new 3D XPoint tech when the prices fall.

 

http://www.ebay.com/...3" 120&_sacat=0

 

:)

 

-Noel

 

 

Edit:  FYI, 3 x Vertex 3 120GB on a Dell PowerEdge T20 motherboard with a very modest dual core Pentium G3220 (Haswell) running Win 7 and using only the motherboard SATA connectors to make a RAID 5 (note: optimized for redundancy/reliability, not speed):

 

Disk_Benchmarks_07-29-2015.png


Edited by NoelC, 01 August 2015 - 11:59 AM.


#36
jaclaz

jaclaz

    The Finder

  • Developer
  • 15,791 posts
  • Joined 23-July 04
  • OS:none specified
  • Country: Country Flag

And, if you want to spend TODAY some good money :ph34r: you can have one of these (provided that the OS and hardware support them :unsure:):

http://www.sandisk.i...ulltradimm-ssd/

 

But yes, used SSD's of (relatively) little size can be found cheap enough and - depending on your use of the system - you do not really need at the same time a fast storage subsystem and a large one, in normal use 100 Gb or so are enough for OS, tools/programs and the "working data".

 

jaclaz



#37
NoelC

NoelC

    Software Engineer

  • Member
  • PipPipPipPipPipPipPipPip
  • 2,674 posts
  • Joined 08-April 13
  • OS:Windows 8.1 x64
  • Country: Country Flag

And, if you want to spend TODAY some good money :ph34r: you can have one of these (provided that the OS and hardware support them :unsure:):

http://www.sandisk.i...ulltradimm-ssd/

 

Now THAT's cool!

 

The performance numbers seem a little low (sequential numbers are 600 / 880 MB/s for read and write).  Have you ever come across test numbers gathered on a system equipped with ULLtraDIMM SSDs?

 

140K IOPS read based on 4 KByte transfers and ultra low latency to the RAM bus could start to yield that super fast 4K I/O rate that TELVM keeps craving.  There will still be the time it takes for the CPU to go through the file system and hardware drivers, of course.

 

I kind of wonder, though...  If the system can't do any RAM access outside of the CPU cache while I/O to these DIMMs is occurring, whether this could introduce its own breed of problems.

 

-Noel



#38
JorgeA

JorgeA

    FORMAT B: /V /S

  • MSFN Sponsor
  • 3,845 posts
  • Joined 08-April 10
  • OS:Vista Home Premium x64
  • Country: Country Flag

 

And, if you want to spend TODAY some good money :ph34r: you can have one of these (provided that the OS and hardware support them :unsure:):

http://www.sandisk.i...ulltradimm-ssd/

 

Now THAT's cool!

 

The performance numbers seem a little low (sequential numbers are 600 / 880 MB/s for read and write).  Have you ever come across test numbers gathered on a system equipped with ULLtraDIMM SSDs?

 

...and if it turned out that these kinds of drives could work only with the privacy-invading, resource-hogging, customer-contemptuous Windows 10 -- would you still get one?  ;)  (A question for all readers to think about, not directed specifically at you guys.)

 

--JorgeA



#39
JorgeA

JorgeA

    FORMAT B: /V /S

  • MSFN Sponsor
  • 3,845 posts
  • Joined 08-April 10
  • OS:Vista Home Premium x64
  • Country: Country Flag

 

That's very cute :). It's a shame that the critical graph is so tiny that you can't tell, at any zoom level, what the author is measuring (X or Y axis). :}

Well, guess why exactly I am The Finder :whistle:

;)

 

jaclaz

 

 

Thank you, that takes care of it!  :thumbup

 

--JorgeA



#40
dencorso

dencorso

    Iuvat plus qui nihil obstat

  • Supervisor
  • 6,014 posts
  • Joined 07-April 07
  • OS:98SE
  • Country: Country Flag

Donator

Well, when one wants fast... these are fast! :)

And one can RAID 0 'em, too...



#41
NoelC

NoelC

    Software Engineer

  • Member
  • PipPipPipPipPipPipPipPip
  • 2,674 posts
  • Joined 08-April 13
  • OS:Windows 8.1 x64
  • Country: Country Flag

 

...and if it turned out that these kinds of drives could work only with the privacy-invading, resource-hogging, customer-contemptuous Windows 10 -- would you still get one?  ;)  (A question for all readers to think about, not directed specifically at you guys.)

 

I'd consider it.

 

Face it, we're all going to be running something else in a few years.

 

Windows 10 is just another set of technical challenges to overcome in the pursuit of deriving value.

 

Windows 8 shipped without a Start Menu, a useless Metro subsystem, and a cruddy desktop without Aero Glass, and now it's the OS I'll be sticking with for a while.  Frankly, bleak as things looked in 2012, my computing experience is now the best it's ever been - not because of what Microsoft shipped, but because of what can be done with it.

 

We already have a thread here where it's been figured out how to thwart the privacy-invading stuff - almost certainly to a level that's better than Windows 7 out of the box (where do you think Microsoft got all that "telemetry" data they misused to justify what they did with Windows 8?).  I have a test system running those tweaks with a local account and UAC disabled, and it's still pretty good for running desktop stuff.

 

-Noel



#42
jaclaz

jaclaz

    The Finder

  • Developer
  • 15,791 posts
  • Joined 23-July 04
  • OS:none specified
  • Country: Country Flag

We already have a thread here where it's been figured out how to thwart the privacy-invading stuff - almost certainly to a level that's better than Windows 7 out of the box (where do you think Microsoft got all that "telemetry" data they misused to justify what they did with Windows 8?).

If we assume that telemetry data was actually used, judging from results those telemetry data were redirected to the NUL device :w00t: and the good MS guys did whatever (the heck) they intended to do anyway (the alternative could be much more sad, IF they actually used telemetry data and those shaped the current abomination then clearly humanity is doomed, self-destroyed by stupidity).

 

jaclaz


  • NoelC likes this

#43
bphlpt

bphlpt

    MSFN Master

  • Patrons
  • 2,012 posts
  • Joined 12-May 07
  • OS:none specified
  • Country: Country Flag

We already have a thread here where it's been figured out how to thwart the privacy-invading stuff - almost certainly to a level that's better than Windows 7 out of the box (where do you think Microsoft got all that "telemetry" data they misused to justify what they did with Windows 8?).


If that's the case, then I'd like to see the same type of telemetry gathering, privacy-invading stuff blocked for Windows 7 and 8.x. I would think you would, too. :)

Cheers and Regards


Posted Image


#44
NoelC

NoelC

    Software Engineer

  • Member
  • PipPipPipPipPipPipPipPip
  • 2,674 posts
  • Joined 08-April 13
  • OS:Windows 8.1 x64
  • Country: Country Flag

I long ago turned off all the overt settings (e.g., "participate in the Customer Experience Improvement Program") on this score, but I have occasionally wondered what's still cranking away in my Win 7 and 8.1 systems under the covers.  I've not taken the time to research it like ptd163 has.

 

I'm sure much of the stuff listed in the OP of this thread will be applicable.  Figuring out precisely what will be a challenge, but not an insoluble one.  I'm not saying I have time to undertake it just now, but good idea.  Thanks.

 

-Noel






0 user(s) are reading this topic

0 members, 0 guests, 0 anonymous users