strange interrupt behaviour when HAL is Standard PC

Let me add my $.02 before jan 1.

I found FreeBSD very lightweight and ROCK SOLID. It’s easy to manage with a 80x25 dumb terminal. Just migrated my last symbol server from w2k3 to FreeBSD 6.2, now all of my servers at home and at work are powered by FreeBSD. Linux appears to me less stable but its has richer set of app and driver support.


Calvin Guan
Broadcom Corp.
Connecting Everything(r)

----- Original Message ----
From: Maxim S. Shatskih
To: Windows System Software Devs Interest List
Sent: Tuesday, December 30, 2008 1:02:32 AM
Subject: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

>experience with these OSes. I can tell you from my own experience is that the performance
>differences are significant even in human perception

Yes, for instance, filesystem in FreeBSD is noticeably slower then in Windows XP Home on the same hardware, really so.

>amounts are involved. If the amounts of data moved are measured in terms of G, the difference will be
>measured in terms of minutes (and the number will be not-so-small either).

Did the same with FreeBSD, it loses big time. Don’t know on Linux, probably it is the same with Linux too.

FreeBSD is not a bad OS, but I would have doubts about it anywhere where performance is important.


Maxim S. Shatskih
Windows DDK MVP
xxxxx@storagecraft.com
http://www.storagecraft.com


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at http://www.osronline.com/page.cfm?name=ListServer

__________________________________________________________________
Get a sneak peak at messages with a handy reading pane with All new Yahoo! Mail: http://ca.promos.yahoo.com/newmail/overview2/

> I found FreeBSD very lightweight and ROCK SOLID. It’s easy to manage with a 80x25 dumb terminal.

Yes. The slowdown I experienced was due to copy of the huge file from disk to disk. Really slower then Windows, even with a proper command of “cat < Src | cat > Dst”. But this was FreeBSD 5, it is old.

work are powered by FreeBSD. Linux appears to me less stable but its has richer set of app

Most Linux apps run on FreeBSD, but you can need a recompile.


Maxim S. Shatskih
Windows DDK MVP
xxxxx@storagecraft.com
http://www.storagecraft.com

> Well, first of all, VFS is much more than simply the interface, don’t you think???

Interface only. Just a way to structure the interface between FSDs and the kernel. A good way, but decent performance is achievable without it too - even with copy-pastes of code from FASTFAT to RDBSS :slight_smile:

> Windows CE, Mac OS and Symbian beat Linux on mobile by far.

I really have no idea how WinCE performs on the mobile phones - AFAIK, its share is just tiny,

One of the most major players on advanced smartphones and PDAs. On PDAs, it was the most major player several years ago, since Symbian was too primitive these days.

compared even to Linux (which holds its modest 15%).

Some funny information. Everybody knows that, for smartphone with the possibility of app installation (the criteria of smartphone), WinCE is the most major player. But one can hardly name the phone with app installation possibility with Linux in it.

Symbian is, indeed, the king in the world of mobile phones.

Until recently, on low-end phones (not smartphones) only. PalmOS was major, but lost to WinCE due to being worse technically.

I believe this is directly related to the fact that “mainstream” Linux is not RTOS (and, unless a special
settings upon compilation is made, does not even support kernel-level preemption by default).

You do not need realtime in the phone except in GSM chip and voice processing, and this degree of realtime is surely achievable in WinCE and probably in Linux with user-level preemption.

Therefore, whenever you see it on the mobile you can be pretty sure that this is a special-purpose OS
that was just derived from Linux.

On low-end - Symbian, on high end - WinCE, PalmOS, Symbian and recently Mac OS :slight_smile:

Motorola I think was used the proprietary OS for years.


Maxim S. Shatskih
Windows DDK MVP
xxxxx@storagecraft.com
http://www.storagecraft.com

Many Qualcomm chipset powered smartphones actually have a dedicated core for radio link operations, and a higher clock core for application (OS) code - at least, according to what I’ve seen, anyway. This further reduces the need for smartphone OS’s to be truly real time systems, as most of the hard timing dependent logic isn’t run in the context of the OS as we think of it.

? S

-----Original Message-----
From: Maxim S. Shatskih
Sent: Wednesday, December 31, 2008 12:41
To: Windows System Software Devs Interest List
Subject: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

> Well, first of all, VFS is much more than simply the interface, don’t you think???

Interface only. Just a way to structure the interface between FSDs and the kernel. A good way, but decent performance is achievable without it too - even with copy-pastes of code from FASTFAT to RDBSS :slight_smile:

>> Windows CE, Mac OS and Symbian beat Linux on mobile by far.
>
> I really have no idea how WinCE performs on the mobile phones - AFAIK, its share is just tiny,

One of the most major players on advanced smartphones and PDAs. On PDAs, it was the most major player several years ago, since Symbian was too primitive these days.

>compared even to Linux (which holds its modest 15%).

Some funny information. Everybody knows that, for smartphone with the possibility of app installation (the criteria of smartphone), WinCE is the most major player. But one can hardly name the phone with app installation possibility with Linux in it.

>Symbian is, indeed, the king in the world of mobile phones.

Until recently, on low-end phones (not smartphones) only. PalmOS was major, but lost to WinCE due to being worse technically.

> I believe this is directly related to the fact that “mainstream” Linux is not RTOS (and, unless a special
>settings upon compilation is made, does not even support kernel-level preemption by default).

You do not need realtime in the phone except in GSM chip and voice processing, and this degree of realtime is surely achievable in WinCE and probably in Linux with user-level preemption.

>Therefore, whenever you see it on the mobile you can be pretty sure that this is a special-purpose OS
>that was just derived from Linux.

On low-end - Symbian, on high end - WinCE, PalmOS, Symbian and recently Mac OS :slight_smile:

Motorola I think was used the proprietary OS for years.


Maxim S. Shatskih
Windows DDK MVP
xxxxx@storagecraft.com
http://www.storagecraft.com


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at http://www.osronline.com/page.cfm?name=ListServer

I don’t work for our mobile chipset group but I know that channel coding and baseband signal processing is handled by dedicated hw logic and DSP in our mobile chipsets. I’m pretty sure it’s true for other vendors. There are lot of processors and OSes running on a cell phone.


Calvin Guan
Broadcom Corp.
Connecting Everything(r)

----- Original Message ----
From: Skywing
To: Windows System Software Devs Interest List
Sent: Wednesday, December 31, 2008 11:21:57 AM
Subject: RE: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

Many Qualcomm chipset powered smartphones actually have a dedicated core for radio link operations, and a higher clock core for application (OS) code - at least, according to what I’ve seen, anyway. This further reduces the need for smartphone OS’s to be truly real time systems, as most of the hard timing dependent logic isn’t run in the context of the OS as we think of it.

– S

-----Original Message-----
From: Maxim S. Shatskih
Sent: Wednesday, December 31, 2008 12:41
To: Windows System Software Devs Interest List
Subject: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

> Well, first of all, VFS is much more than simply the interface, don’t you think???

Interface only. Just a way to structure the interface between FSDs and the kernel. A good way, but decent performance is achievable without it too - even with copy-pastes of code from FASTFAT to RDBSS :slight_smile:

>> Windows CE, Mac OS and Symbian beat Linux on mobile by far.
>
> I really have no idea how WinCE performs on the mobile phones - AFAIK, its share is just tiny,

One of the most major players on advanced smartphones and PDAs. On PDAs, it was the most major player several years ago, since Symbian was too primitive these days.

>compared even to Linux (which holds its modest 15%).

Some funny information. Everybody knows that, for smartphone with the possibility of app installation (the criteria of smartphone), WinCE is the most major player. But one can hardly name the phone with app installation possibility with Linux in it.

>Symbian is, indeed, the king in the world of mobile phones.

Until recently, on low-end phones (not smartphones) only. PalmOS was major, but lost to WinCE due to being worse technically.

> I believe this is directly related to the fact that “mainstream” Linux is not RTOS (and, unless a special
>settings upon compilation is made, does not even support kernel-level preemption by default).

You do not need realtime in the phone except in GSM chip and voice processing, and this degree of realtime is surely achievable in WinCE and probably in Linux with user-level preemption.

>Therefore, whenever you see it on the mobile you can be pretty sure that this is a special-purpose OS
>that was just derived from Linux.

On low-end - Symbian, on high end - WinCE, PalmOS, Symbian and recently Mac OS :slight_smile:

Motorola I think was used the proprietary OS for years.


Maxim S. Shatskih
Windows DDK MVP
xxxxx@storagecraft.com
http://www.storagecraft.com


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at http://www.osronline.com/page.cfm?name=ListServer


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at http://www.osronline.com/page.cfm?name=ListServer

__________________________________________________________________
Looking for the perfect gift? Give the gift of Flickr!

http://www.flickr.com/gift/

OMG, How can it be possible to turn a discussion of Windows interrupt handling and Xen/QEMU interaction into a discussion that returns to the subject of VFS.

It’s 2009 in Hong Kong already, you know…

Peter
OSR

Btw, there is also a move toward software realization of (1) Channel coding
(2) Signalling systems ( i,e Common channel signalling, specially SS7 etc)

I think separating media from signalling systems making an inroad for
softwares to these applications … as opposed to HW/FW solutions.

Well, as if I’ve to sign something !
Prokash Sinha
http://prokash.squarespace.com
Success has many fathers, but failure is an orphan.

----- Original Message -----
From: “Calvin Guan”
To: “Windows System Software Devs Interest List”
Sent: Wednesday, December 31, 2008 11:43 AM
Subject: Re: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

I don’t work for our mobile chipset group but I know that channel coding and
baseband signal processing is handled by dedicated hw logic and DSP in our
mobile chipsets. I’m pretty sure it’s true for other vendors. There are lot
of processors and OSes running on a cell phone.


Calvin Guan
Broadcom Corp.
Connecting Everything(r)

----- Original Message ----
From: Skywing
To: Windows System Software Devs Interest List
Sent: Wednesday, December 31, 2008 11:21:57 AM
Subject: RE: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

Many Qualcomm chipset powered smartphones actually have a dedicated core for
radio link operations, and a higher clock core for application (OS) code -
at least, according to what I’ve seen, anyway. This further reduces the
need for smartphone OS’s to be truly real time systems, as most of the hard
timing dependent logic isn’t run in the context of the OS as we think of it.

– S

-----Original Message-----
From: Maxim S. Shatskih
Sent: Wednesday, December 31, 2008 12:41
To: Windows System Software Devs Interest List
Subject: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

> Well, first of all, VFS is much more than simply the interface, don’t you
> think???

Interface only. Just a way to structure the interface between FSDs and the
kernel. A good way, but decent performance is achievable without it too -
even with copy-pastes of code from FASTFAT to RDBSS :slight_smile:

>> Windows CE, Mac OS and Symbian beat Linux on mobile by far.
>
> I really have no idea how WinCE performs on the mobile phones - AFAIK, its
> share is just tiny,

One of the most major players on advanced smartphones and PDAs. On PDAs, it
was the most major player several years ago, since Symbian was too primitive
these days.

>compared even to Linux (which holds its modest 15%).

Some funny information. Everybody knows that, for smartphone with the
possibility of app installation (the criteria of smartphone), WinCE is the
most major player. But one can hardly name the phone with app installation
possibility with Linux in it.

>Symbian is, indeed, the king in the world of mobile phones.

Until recently, on low-end phones (not smartphones) only. PalmOS was major,
but lost to WinCE due to being worse technically.

> I believe this is directly related to the fact that “mainstream” Linux is
> not RTOS (and, unless a special
>settings upon compilation is made, does not even support kernel-level
>preemption by default).

You do not need realtime in the phone except in GSM chip and voice
processing, and this degree of realtime is surely achievable in WinCE and
probably in Linux with user-level preemption.

>Therefore, whenever you see it on the mobile you can be pretty sure that
>this is a special-purpose OS
>that was just derived from Linux.

On low-end - Symbian, on high end - WinCE, PalmOS, Symbian and recently Mac
OS :slight_smile:

Motorola I think was used the proprietary OS for years.


Maxim S. Shatskih
Windows DDK MVP
xxxxx@storagecraft.com
http://www.storagecraft.com


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at
http://www.osronline.com/page.cfm?name=ListServer


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at
http://www.osronline.com/page.cfm?name=ListServer

__________________________________________________________________
Looking for the perfect gift? Give the gift of Flickr!

http://www.flickr.com/gift/


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at
http://www.osronline.com/page.cfm?name=ListServer



Sure. In the case of every Qualcomm powered smartphone I’ve ever used (all two of them), the radio logic had its own firmware image seperate from the OS, and according to the specs I’ve seen, has its own dedicated processor core.

Just because things are heading towards software to a degree doesn’t require that it will need the general purpose OS on the device to be hard real time and fully embedded in that stuff at every level, though.

(I’m pretty sure my devices are hardly pure software radios either FWIW, but I think the higher level aspects of the cell link are software managed on a dedicated firmware blob/tiny OS.)

Of course, the distinction between “firmware” and “software” on devices like these, where you’re really just somewhere pretty close to flashing different flash sectors depending on whether you are updating the OS or radio blob, isn’t exactly a well-demarcated line anymore, either.

  • S

(Resending because Lyris ate my mail. Again. We don’ like no stinkin’ UTF8…)

-----Original Message-----
From: xxxxx@lists.osr.com [mailto:xxxxx@lists.osr.com] On Behalf Of Prokash Sinha
Sent: Wednesday, December 31, 2008 3:13 PM
To: Windows System Software Devs Interest List
Subject: Re: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

Btw, there is also a move toward software realization of (1) Channel coding
(2) Signalling systems ( i,e Common channel signalling, specially SS7 etc)

I think separating media from signalling systems making an inroad for
softwares to these applications … as opposed to HW/FW solutions.

Well, as if I’ve to sign something !
Prokash Sinha
http://prokash.squarespace.com
Success has many fathers, but failure is an orphan.

----- Original Message -----
From: “Calvin Guan”
To: “Windows System Software Devs Interest List”
Sent: Wednesday, December 31, 2008 11:43 AM
Subject: Re: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

I don’t work for our mobile chipset group but I know that channel coding and
baseband signal processing is handled by dedicated hw logic and DSP in our
mobile chipsets. I’m pretty sure it’s true for other vendors. There are lot
of processors and OSes running on a cell phone.


Calvin Guan
Broadcom Corp.
Connecting Everything(r)

----- Original Message ----
From: Skywing
To: Windows System Software Devs Interest List
Sent: Wednesday, December 31, 2008 11:21:57 AM
Subject: RE: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

Many Qualcomm chipset powered smartphones actually have a dedicated core for
radio link operations, and a higher clock core for application (OS) code -
at least, according to what I’ve seen, anyway. This further reduces the
need for smartphone OS’s to be truly real time systems, as most of the hard
timing dependent logic isn’t run in the context of the OS as we think of it.

- S

-----Original Message-----
From: Maxim S. Shatskih
Sent: Wednesday, December 31, 2008 12:41
To: Windows System Software Devs Interest List
Subject: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

> Well, first of all, VFS is much more than simply the interface, don’t you
> think???

Interface only. Just a way to structure the interface between FSDs and the
kernel. A good way, but decent performance is achievable without it too -
even with copy-pastes of code from FASTFAT to RDBSS :slight_smile:

>> Windows CE, Mac OS and Symbian beat Linux on mobile by far.
>
> I really have no idea how WinCE performs on the mobile phones - AFAIK, its
> share is just tiny,

One of the most major players on advanced smartphones and PDAs. On PDAs, it
was the most major player several years ago, since Symbian was too primitive
these days.

>compared even to Linux (which holds its modest 15%).

Some funny information. Everybody knows that, for smartphone with the
possibility of app installation (the criteria of smartphone), WinCE is the
most major player. But one can hardly name the phone with app installation
possibility with Linux in it.

>Symbian is, indeed, the king in the world of mobile phones.

Until recently, on low-end phones (not smartphones) only. PalmOS was major,
but lost to WinCE due to being worse technically.

> I believe this is directly related to the fact that “mainstream” Linux is
> not RTOS (and, unless a special
>settings upon compilation is made, does not even support kernel-level
>preemption by default).

You do not need realtime in the phone except in GSM chip and voice
processing, and this degree of realtime is surely achievable in WinCE and
probably in Linux with user-level preemption.

>Therefore, whenever you see it on the mobile you can be pretty sure that
>this is a special-purpose OS
>that was just derived from Linux.

On low-end - Symbian, on high end - WinCE, PalmOS, Symbian and recently Mac
OS :slight_smile:

Motorola I think was used the proprietary OS for years.


Maxim S. Shatskih
Windows DDK MVP
xxxxx@storagecraft.com
http://www.storagecraft.com


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at
http://www.osronline.com/page.cfm?name=ListServer


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at
http://www.osronline.com/page.cfm?name=ListServer

__________________________________________________________________
Looking for the perfect gift? Give the gift of Flickr!

http://www.flickr.com/gift/


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at
http://www.osronline.com/page.cfm?name=ListServer


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at http://www.osronline.com/page.cfm?name=ListServer

> Let me add my $.02 before jan 1.

I found FreeBSD very lightweight and ROCK SOLID. It’s easy to manage
with
a 80x25 dumb terminal. Just migrated my last symbol server from w2k3
to
FreeBSD 6.2, now all of my servers at home and at work are powered by
FreeBSD. Linux appears to me less stable but its has richer set of
app
and driver support.

No fair! You guys in different timezones get more time than us east
coast Australians!!! (your email was sent at 4am AEDT)

Happy new year!

James

Peter,

It’s 2009 in Hong Kong already, you know…

My local time is 12.36. Therefore, I already don’t reply to Maxim’s comments - I am already in 2009, so that the new rules,apparently, already apply to me…

Happy New Year everyone!!!

Anton Bassov



The trend I’ve seen so far and may not be totally enlightened yet is that -
propritary chipset, protocol, and embedding into main(motherboard) or
integrate into the main processors for any new technologies ( Real time or
otherwise ).

Then there are other factors come into play that knocks off the structures
due to a wide ranges of demands; flexiblity, low cost, on demand updates,
add-on values, thermal and electrical constraints etc …

I’ve never opened up any old cell phones or look thru any specs… But, due
to high frequency processors, miniaturization, compitition form others and a
whole lot of other improvements in the area of line encoding, signalling
systems and protocols
, it is becoming harder and harder to justify the use
of DSPs for anything other than a mere low-lelvel PHY implementations for
radio.

In particular, if you take just the cell phone area, you would be surprised
to see how much of the controll signalling and media trasports are becoming
more and more software oriented… Here is a ref. that tells how much of
SS7 being used in the cell phone are ( smart or otherwise) …
http://www.ss7-training.net/sigtran-training/main.html

I don’t work in the cell phone area and not a PHY implementation person, but
along the area of those protocols that relates to call processing and media
trasport. And as far as I know, none of them really belong to Hard Real
time.

One thing to note is that, in most cases our perception is farily fixed. For
voice, we want to hear at a bit rate (64Kbit channel enough) and within
certain herz (less than 4KHz), and there are similar characterizations for
video etc… But improvements in the technology and protocols area changes
the center of gravity.

Well, as if I’ve to sign something !
Prokash Sinha
http://prokash.squarespace.com
Success has many fathers, but failure is an orphan.

----- Original Message -----
From: “Skywing”
To: “Windows System Software Devs Interest List”
Sent: Wednesday, December 31, 2008 12:34 PM
Subject: RE: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC



Sure. In the case of every Qualcomm powered smartphone I’ve ever used (all
two of them), the radio logic had its own firmware image seperate from the
OS, and according to the specs I’ve seen, has its own dedicated processor
core.

Just because things are heading towards software to a degree doesn’t require
that it will need the general purpose OS on the device to be hard real time
and fully embedded in that stuff at every level, though.

(I’m pretty sure my devices are hardly pure software radios either FWIW, but
I think the higher level aspects of the cell link are software managed on a
dedicated firmware blob/tiny OS.)

Of course, the distinction between “firmware” and “software” on devices like
these, where you’re really just somewhere pretty close to flashing different
flash sectors depending on whether you are updating the OS or radio blob,
isn’t exactly a well-demarcated line anymore, either.



- S

(Resending because Lyris ate my mail. Again. We don’ like no stinkin’
UTF8…)

-----Original Message-----
From: xxxxx@lists.osr.com
[mailto:xxxxx@lists.osr.com] On Behalf Of Prokash Sinha
Sent: Wednesday, December 31, 2008 3:13 PM
To: Windows System Software Devs Interest List
Subject: Re: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

Btw, there is also a move toward software realization of (1) Channel coding
(2) Signalling systems ( i,e Common channel signalling, specially SS7 etc)


I think separating media from signalling systems making an inroad for
softwares to these applications … as opposed to HW/FW solutions.

Well, as if I’ve to sign something !
Prokash Sinha
http://prokash.squarespace.com
Success has many fathers, but failure is an orphan.

----- Original Message -----
From: “Calvin Guan”
To: “Windows System Software Devs Interest List”
Sent: Wednesday, December 31, 2008 11:43 AM
Subject: Re: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

I don’t work for our mobile chipset group but I know that channel coding and
baseband signal processing is handled by dedicated hw logic and DSP in our
mobile chipsets. I’m pretty sure it’s true for other vendors. There are lot
of processors and OSes running on a cell phone.


Calvin Guan
Broadcom Corp.
Connecting Everything(r)

----- Original Message ----
From: Skywing
To: Windows System Software Devs Interest List
Sent: Wednesday, December 31, 2008 11:21:57 AM
Subject: RE: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

Many Qualcomm chipset powered smartphones actually have a dedicated core for
radio link operations, and a higher clock core for application (OS) code -
at least, according to what I’ve seen, anyway. This further reduces the
need for smartphone OS’s to be truly real time systems, as most of the hard
timing dependent logic isn’t run in the context of the OS as we think of it.

- S

-----Original Message-----
From: Maxim S. Shatskih
Sent: Wednesday, December 31, 2008 12:41
To: Windows System Software Devs Interest List
Subject: Re:[ntdev] strange interrupt behaviour when HAL is Standard PC

> Well, first of all, VFS is much more than simply the interface, don’t you
> think???

Interface only. Just a way to structure the interface between FSDs and the
kernel. A good way, but decent performance is achievable without it too -
even with copy-pastes of code from FASTFAT to RDBSS :slight_smile:

>> Windows CE, Mac OS and Symbian beat Linux on mobile by far.
>
> I really have no idea how WinCE performs on the mobile phones - AFAIK, its
> share is just tiny,

One of the most major players on advanced smartphones and PDAs. On PDAs, it
was the most major player several years ago, since Symbian was too primitive
these days.

>compared even to Linux (which holds its modest 15%).

Some funny information. Everybody knows that, for smartphone with the
possibility of app installation (the criteria of smartphone), WinCE is the
most major player. But one can hardly name the phone with app installation
possibility with Linux in it.

>Symbian is, indeed, the king in the world of mobile phones.

Until recently, on low-end phones (not smartphones) only. PalmOS was major,
but lost to WinCE due to being worse technically.

> I believe this is directly related to the fact that “mainstream” Linux is
> not RTOS (and, unless a special
>settings upon compilation is made, does not even support kernel-level
>preemption by default).

You do not need realtime in the phone except in GSM chip and voice
processing, and this degree of realtime is surely achievable in WinCE and
probably in Linux with user-level preemption.

>Therefore, whenever you see it on the mobile you can be pretty sure that
>this is a special-purpose OS
>that was just derived from Linux.

On low-end - Symbian, on high end - WinCE, PalmOS, Symbian and recently Mac
OS :slight_smile:

Motorola I think was used the proprietary OS for years.


Maxim S. Shatskih
Windows DDK MVP
xxxxx@storagecraft.com
http://www.storagecraft.com


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at
http://www.osronline.com/page.cfm?name=ListServer


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at
http://www.osronline.com/page.cfm?name=ListServer

__________________________________________________________________
Looking for the perfect gift? Give the gift of Flickr!

http://www.flickr.com/gift/


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at
http://www.osronline.com/page.cfm?name=ListServer


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at
http://www.osronline.com/page.cfm?name=ListServer


NTDEV is sponsored by OSR

For our schedule of WDF, WDM, debugging and other seminars visit:
http://www.osr.com/seminars

To unsubscribe, visit the List Server section of OSR Online at
http://www.osronline.com/page.cfm?name=ListServer