VM
Quoted 3 lines
I've not reached any final conclusions on the VM - there are things that Rik's VM shows up that look like the VM algorithm is right but it triggers other stuff, and there are a couple of hackish bits left in still.
I have never done this comparison myself, but I was wondering how ugly it would be if stable versions of Andrea's and Rik's VMs were both available in your/Linus' kernel as compile-time options. Assuming that each provides better performance under certain conditions, wouldn't being able to choose a VM make sense, if they don't step on the rest of the kernel too much ...
Signature · 2 lines
Michael T. Babcock http://www.fibrespeed.net/~mbabcock
Quoted 4 lines
I have never done this comparison myself, but I was wondering how ugly it would be if stable versions of Andrea's and Rik's VMs were both available in your/Linus' kernel as compile-time options. Assuming that each provides better performance under certain conditions, wouldn't
Too ugly for words.
Quoted 6 lines · Alan Cox
Quoted 4 lines
I have never done this comparison myself, but I was wondering how ugly it would be if stable versions of Andrea's and Rik's VMs were both available in your/Linus' kernel as compile-time options. Assuming that each provides better performance under certain conditions, wouldn't
Too ugly for words.
Though, if it's done from the start of 2.5, it could be very possible. Is there a way to make it non-ugly?
Quoted 10 lines · Mike Fedyk
Quoted 6 lines · Alan Cox
Quoted 4 lines
I have never done this comparison myself, but I was wondering how ugly it would be if stable versions of Andrea's and Rik's VMs were both available in your/Linus' kernel as compile-time options. Assuming that each provides better performance under certain conditions, wouldn't
Too ugly for words.
Though, if it's done from the start of 2.5, it could be very possible. Is there a way to make it non-ugly?
Even if its non-ugly, its non-easy. Way too much overhead.
For 2.5 we'll probably be able to get people working together.
Quoted 4 lines
Quoted 1 line
Too ugly for words.
Though, if it's done from the start of 2.5, it could be very possible. Is there a way to make it non-ugly?
I would hope by then we have a definitive answer as to the best path in the VM world
Quoted 10 lines · Mike Fedyk
Quoted 6 lines · Alan Cox
Quoted 4 lines
I have never done this comparison myself, but I was wondering how ugly it would be if stable versions of Andrea's and Rik's VMs were both available in your/Linus' kernel as compile-time options. Assuming that each provides better performance under certain conditions, wouldn't
Too ugly for words.
Though, if it's done from the start of 2.5, it could be very possible. Is there a way to make it non-ugly?
No, not within the current structure of our config system. It touches the tree in many places break out nicely into a few defines or separable files. Both mm variants are under heavy development and injecting them with a bunch of cruft just to make it compile-time configurable would only add to the difficulty of maintaining a subsystem that already is very difficult to maintain.
This is properly a patch.
If you want to argue for something, argue for giving config the ability to apply patches, that would be lots of fun.
--
Daniel
Quoted 2 lines · Daniel Phillips
If you want to argue for something, argue for giving config the ability to apply patches, that would be lots of fun.
cc list trimmed.
It is kbuild rather than config that needs the ability. I could do it trivially in kbuild 2.5, I almost added the facility at one time. Alas it breaks when you get overlapping patches, select one config or another and it works, select both (assuming they are not exclusive) and it breaks.
I don't have a solution and the symptoms of overlapping patches are worse than the problem that patches are trying to fix, so I left patch support out of kbuild 2.5. You can use shadow trees where you overlay a new implementation of a subsystem over the base kernel, then switch between versions by specifying which set of trees you are using.
Quoted 9 lines · Keith Owens
Quoted 2 lines · Daniel Phillips
If you want to argue for something, argue for giving config the ability to apply patches, that would be lots of fun.
It is kbuild rather than config that needs the ability. I could do it trivially in kbuild 2.5, I almost added the facility at one time. Alas it breaks when you get overlapping patches, select one config or another and it works, select both (assuming they are not exclusive) and it breaks.
Yes, if someone was determined to set this up they'd have to laboriously break up overlapping patches into common vs independent pieces, and determine that other patches are simply mutually incompatible, thus requiring suitable config rule restrictions. Wow, way too much work for the tree owner, and things will re-break frequently when the patch owner makes updates.
Maybe this technique is something that would interest the FOLK guys, where the goal is to produce a single tree with as many options as possible, and where they're willing to put in extra maintainance work. Besides the two VM designs, there's the XFS patch, which we don't have a good way of integrating into a single tree just yet.
Please treat the above as idle speculation. It's evident that including patches in kbuild is an express route to madness. For one thing, I'd no longer be able to index the complete source tree for browsing.
Quoted 5 lines
I don't have a solution and the symptoms of overlapping patches are worse than the problem that patches are trying to fix, so I left patch support out of kbuild 2.5. You can use shadow trees where you overlay a new implementation of a subsystem over the base kernel, then switch between versions by specifying which set of trees you are using.
--
Daniel
Daniel, I think the suggestion isn't to break out the differences in a bunch of config options, but rather to do something like duplicating all files that are VM related into two files, foo.c becomes foo.aa.c and foo.rik.c at that point your config file either uses all the .rik files or all the .aa files and both would be in the same tree, but not interact with each other.
yes, there would be a lot of duplication between them, but something like this would let people compare the two directly without also having all the other linus vs ac changes potentially affecting their tests.
David Lang
Quoted 47 lines · Daniel Phillips
Date: Tue, 23 Oct 2001 18:15:36 +0200
From: Daniel Phillips <[email protected]>
To: Keith Owens <[email protected]>
Cc: Linux Kernel <[email protected]>
Subject: Re: VMQuoted 9 lines · Keith Owens
Quoted 2 lines · Daniel Phillips
If you want to argue for something, argue for giving config the ability to apply patches, that would be lots of fun.
It is kbuild rather than config that needs the ability. I could do it trivially in kbuild 2.5, I almost added the facility at one time. Alas it breaks when you get overlapping patches, select one config or another and it works, select both (assuming they are not exclusive) and it breaks.
Yes, if someone was determined to set this up they'd have to laboriously break up overlapping patches into common vs independent pieces, and determine that other patches are simply mutually incompatible, thus requiring suitable config rule restrictions. Wow, way too much work for the tree owner, and things will re-break frequently when the patch owner makes updates.
Maybe this technique is something that would interest the FOLK guys, where the goal is to produce a single tree with as many options as possible, and where they're willing to put in extra maintainance work. Besides the two VM designs, there's the XFS patch, which we don't have a good way of integrating into a single tree just yet.
Please treat the above as idle speculation. It's evident that including patches in kbuild is an express route to madness. For one thing, I'd no longer be able to index the complete source tree for browsing.
Quoted 5 lines
I don't have a solution and the symptoms of overlapping patches are worse than the problem that patches are trying to fix, so I left patch support out of kbuild 2.5. You can use shadow trees where you overlay a new implementation of a subsystem over the base kernel, then switch between versions by specifying which set of trees you are using.
--
Daniel
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Quoted 10 lines · David Lang
Daniel, I think the suggestion isn't to break out the differences in a bunch of config options, but rather to do something like duplicating all files that are VM related into two files,
foo.cbecomesfoo.aa.candfoo.rik.cat that point your config file either uses all the .rik files or all the .aa files and both would be in the same tree, but not interact with each other.yes, there would be a lot of duplication between them, but something like this would let people compare the two directly without also having all the other linus vs ac changes potentially affecting their tests.
Patch and lilo are your friends.
--
Daniel
the problem is that there isn't a patchset available from either aa or rik that converts one to the other, the only patchset readily available converts linus+aa to ac+rik this changes a lot more then just the VM stuff so without going to a lot of effort it's not possible to directly compare the two VM designs while keeping the rest of the kernel the same.
David Lang
Quoted 24 lines · Daniel Phillips
Date: Wed, 24 Oct 2001 16:44:53 +0200
From: Daniel Phillips <[email protected]>
To: David Lang <[email protected]>
Cc: Keith Owens <[email protected]>,
Linux Kernel <[email protected]>
Subject: Re: VMQuoted 10 lines · David Lang
Daniel, I think the suggestion isn't to break out the differences in a bunch of config options, but rather to do something like duplicating all files that are VM related into two files,
foo.cbecomesfoo.aa.candfoo.rik.cat that point your config file either uses all the .rik files or all the .aa files and both would be in the same tree, but not interact with each other.yes, there would be a lot of duplication between them, but something like this would let people compare the two directly without also having all the other linus vs ac changes potentially affecting their tests.
Patch and lilo are your friends.
--
Daniel
Quoted 5 lines · David Lang
the problem is that there isn't a patchset available from either aa or rik that converts one to the other, the only patchset readily available converts linus+aa to ac+rik this changes a lot more then just the VM stuff so without going to a lot of effort it's not possible to directly compare the two VM designs while keeping the rest of the kernel the same.
A non-kernel-hacker can easily make the patch. Andrea posted a list of all the files affected back at the beginning of his 'vm rewrite' thread.
Quoted 7 lines
Quoted 7 lines
Quoted 7 lines
Daniel, I think the suggestion isn't to break out the differences in a bunch of config options, but rather to do something like duplicating all files that are VM related into two files,
foo.cbecomesfoo.aa.candfoo.rik.cat that point your config file either uses all the .rik files or all the .aa files and both would be in the same tree, but not interact with each other.
Quoted 5 lines
Quoted 5 lines
Quoted 3 lines
yes, there would be a lot of duplication between them, but something like this would let people compare the two directly without also having all the other linus vs ac changes potentially affecting their tests.
Patch and lilo are your friends.
--
Daniel
those were the files that his patches were changing, since then we also have had linus, rik and alan making changes in the various trees.
are you willing to bet that the only changes in those files are related to the VM system changes and that there are no other -ac related changes in those files due to the other ac changes? without someone who really understands the rik VM I wouldn't trust breaking them out of the -ac tree and the same thing goes for the aa VM and the linus tree (to add that into the ac tree)
as I see it this requires a few steps.
1. linus and alan agree to implement such a thing (which includes alanbeing willing to track the appropriate differences)
2. rik and/or aa and/or alan seperate out the rik VM from the ac tree and submit it to linus.
3. rik and/or aa and/or alan seperate out the aa VM from the linus tree and submit it to alan.
it's a lot of work to get it setup this way, and it does duplicate a bunch of files that could get out of sync if not carefully managed but it's about the only way that I can see people able to test just the different VM systems.
now if one of the above four states that there are files (or directories) that are only the VM system and it is as simple as swapping out everything in those files between the linus and ac trees then steps 2&3 get much simpler.
David Lang
Quoted 33 lines · Daniel Phillips
Date: Wed, 24 Oct 2001 19:56:00 +0200
From: Daniel Phillips <[email protected]>
To: David Lang <[email protected]>
Cc: Keith Owens <[email protected]>,
Linux Kernel <[email protected]>
Subject: Re: VMQuoted 5 lines · David Lang
the problem is that there isn't a patchset available from either aa or rik that converts one to the other, the only patchset readily available converts linus+aa to ac+rik this changes a lot more then just the VM stuff so without going to a lot of effort it's not possible to directly compare the two VM designs while keeping the rest of the kernel the same.
A non-kernel-hacker can easily make the patch. Andrea posted a list of all the files affected back at the beginning of his 'vm rewrite' thread.
Quoted 7 lines
Quoted 7 lines
Quoted 7 lines
Daniel, I think the suggestion isn't to break out the differences in a bunch of config options, but rather to do something like duplicating all files that are VM related into two files,
foo.cbecomesfoo.aa.candfoo.rik.cat that point your config file either uses all the .rik files or all the .aa files and both would be in the same tree, but not interact with each other.Quoted 5 lines
Quoted 5 lines
Quoted 3 lines
yes, there would be a lot of duplication between them, but something like this would let people compare the two directly without also having all the other linus vs ac changes potentially affecting their tests.
Patch and lilo are your friends.
--
Daniel
Quoted 10 lines · David Lang
those were the files that his patches were changing, since then we also have had linus, rik and alan making changes in the various trees.
are you willing to bet that the only changes in those files are related to the VM system changes and that there are no other -ac related changes in those files due to the other ac changes? without someone who really understands the rik VM I wouldn't trust breaking them out of the -ac tree and the same thing goes for the aa VM and the linus tree (to add that into the ac tree)
Quoted 4 lines
as I see it this requires a few steps.
1. linus and alan agree to implement such a thing (which includes alanbeing willing to track the appropriate differences)
My advice is: don't try to waste Linus's or Alan's time on this. Just make the patch, it isn't that hard. Just post it, and if you get it partly wrong Rik and/or Andrea will be sure to tell you.
Quoted 10 lines
2. rik and/or aa and/or alan seperate out the rik VM from the ac tree and submit it to linus.
3. rik and/or aa and/or alan seperate out the aa VM from the linus tree and submit it to alan.
it's a lot of work to get it setup this way, and it does duplicate a bunch of files that could get out of sync if not carefully managed but it's about the only way that I can see people able to test just the different VM systems.
So why are you asking developers who have plenty of other things to do, to do that work?
Quoted 4 lines
now if one of the above four states that there are files (or directories) that are only the VM system and it is as simple as swapping out everything in those files between the linus and ac trees then steps 2&3 get much simpler.
Do it whatever way you want, that's why you have the source. I'd suggest 'diff', starting with the files in Andrea's list. Then edit the patch by hand, removing the chunks that obviously aren't related.
--
Daniel
Quoted 7 lines · On 20011023 David Lang wrote:
Daniel, I think the suggestion isn't to break out the differences in a bunch of config options, but rather to do something like duplicating all files that are VM related into two files,
foo.cbecomesfoo.aa.candfoo.rik.cat that point your config file either uses all the .rik files or all the .aa files and both would be in the same tree, but not interact with each other.
Could it be as simple as duplicating linux/mm subtree to mm-aa and mm-rik, and symlinking based on a CONFIG_ option ? Or are there any other touched files apart from that subtree ?
Or just adding separate config options, *config-aa and *config-rik, that make the symlink and call *config ?
Signature · 4 lines
J.A. Magallon # Let the source be with you... mailto:[email protected] Mandrake Linux release 8.2 (Cooker) for i586 Linux werewolf 2.4.12-ac6-beo #1 SMP Tue Oct 23 21:24:30 CEST 2001 i686
UGLY!
two VM is one kernel is a nonsense. To develop an OS you have to do also choices like this. I already wrote what i think of those VMs, they are both usefull, but with different conditions and with different worksload and HWs, depending on the behaviour you need.
Rik and Andrea know my point of view, I need a predictable VM for mission critical USE, on desktop people will need the fastest VM for low memory systems.
But to manage the development implys a choice, that could be different for different branches, but anyway someone has to say, "This is the right VM for this kernel, for what I think this kernel should do"!
Luigi
Quoted 28 lines · J . A . Magallon
Quoted 7 lines · On 20011023 David Lang wrote:
Daniel, I think the suggestion isn't to break out the differences in a bunch of config options, but rather to do something like duplicating all files that are VM related into two files,
foo.cbecomesfoo.aa.candfoo.rik.cat that point your config file either uses all the .rik files or all the .aa files and both would be in the same tree, but not interact with each other.Could it be as simple as duplicating linux/mm subtree to mm-aa and mm-rik, and symlinking based on a
CONFIG_option ? Or are there any other touched files apart from that subtree ?Or just adding separate config options, *config-aa and *config-rik, that make the symlink and call *config ?
--
J.A. Magallon # Let the source be with you...
mailto:[email protected]
Mandrake Linux release 8.2 (Cooker) for i586
Linux werewolf 2.4.12-ac6-beo #1 SMP Tue Oct 23 21:24:30 CEST 2001 i686 -
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Quoted 21 lines · Daniel Phillips
Quoted 8 lines · Mike Fedyk
Quoted 7 lines · Alan Cox
Quoted 6 lines
I have never done this comparison myself, but I was wondering how ugly it would be if stable versions of Andrea's and Rik's VMs were both
available in your/Linus' kernel as compile-time options. Assuming that each provides better performance under certain conditions, wouldn'tQuoted 4 lines
Quoted 1 line
Too ugly for words.
Though, if it's done from the start of 2.5, it could be very possible. Is there a way to make it non-ugly?
No, not within the current structure of our config system. It touches the tree in many places break out nicely into a few defines or separable files. Both mm variants are under heavy development and injecting them with a bunch of cruft just to make it compile-time configurable would only add to the difficulty of maintaining a subsystem that already is very difficult to maintain.
Quoted 4 lines
This is properly a patch.
If you want to argue for something, argue for giving config the ability to apply patches, that would be lots of fun.
Actually this _is_ a workable solution. IBM has done it for decades with its 'VM' operating system.
You get a base file, a couple of control files, and a lists of patches. When you go to build a nucleus (translate kernel) the patches are applied and the source assembled...
Ed Tomlinson
Quoted 10 lines · Ed Tomlinson
Quoted 2 lines · Daniel Phillips
If you want to argue for something, argue for giving config the ability to apply patches, that would be lots of fun.
Actually this _is_ a workable solution. IBM has done it for decades with its 'VM' operating system.
You get a base file, a couple of control files, and a lists of patches. When you go to build a nucleus (translate kernel) the patches are applied and the source assembled...
Same with the other mainframe systems, using something like SMP (System Mangling/Management Product) to track the interdependencies. But that only works when almost all of the patches come from a single source which does integration testing before releasing them. This method does not work well with multiple sources, look at the hassles third party vendors have to go through to keep up with IBM patches.
Keith Owens (who spent far too many years fighting SMP)
Quoted 7 lines · On 20011022 Alan Cox wrote:
Quoted 4 lines
I have never done this comparison myself, but I was wondering how ugly it would be if stable versions of Andrea's and Rik's VMs were both available in your/Linus' kernel as compile-time options. Assuming that each provides better performance under certain conditions, wouldn't
Too ugly for words.
-
and how about a CONFIG_ ?? So -ac patch size will become manageable again.
Signature · 4 lines
J.A. Magallon # Let the source be with you... mailto:[email protected] Mandrake Linux release 8.2 (Cooker) for i586 Linux werewolf 2.4.12-ac5-beo #1 SMP Mon Oct 22 02:05:06 CEST 2001 i686