Re: init's children list is long and slows reaping children.

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
From: Linus Torvalds
Date: Friday, April 6, 2007 - 3:51 pm

On Fri, 6 Apr 2007, Jeff Garzik wrote:

The counter-argument is that boxes with $BigNum CPU's really don't hurt 
from it either, and having per-process data structures is often simpler 
and more efficient than trying to have some thread pool.

IOW, once we get the processes off the global list, there just isn't any 
downside from them. Sure, they use some memory, but people who buy 
1024-cpu machines won't care about a few kB per CPU..

So the *only* downside is literally the process list, and one suggested 
patch already just removes kernel threads entirely from the parenthood 
lists.

The other potential downside could be "ps is slow", but on the other hand, 
having the things stick around and have things like CPU-time accumulate is 
probably worth it - if there are some issues, they'd show up properly 
accounted for in a way that process pools would have a hard time doing.

So I really don't think this is worth changing things over, apart from 
literally removing them from process lists, which I think everybody agrees 
we should just do - it just never even came up before!

			Linus
-
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Thu Apr 5, 7:15 pm)
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Fri Apr 6, 8:38 am)
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Fri Apr 6, 11:02 am)
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Fri Apr 6, 11:04 am)
Re: init's children list is long and slows reaping children., Christoph Hellwig, (Fri Apr 6, 11:05 am)
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Fri Apr 6, 11:30 am)
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Fri Apr 6, 11:56 am)
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Fri Apr 6, 12:39 pm)
Re: init's children list is long and slows reaping children., Linus Torvalds, (Fri Apr 6, 3:51 pm)
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Mon Apr 9, 1:00 pm)
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Mon Apr 9, 5:48 pm)
Re: init's children list is long and slows reaping children., Alexey Dobriyan, (Mon Apr 9, 10:07 pm)
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Tue Apr 10, 7:51 am)
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Tue Apr 10, 8:00 am)
[PATCH] Only send pdeath_signal when getppid changes., Eric W. Biederman, (Tue Apr 10, 8:16 am)
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Tue Apr 10, 8:22 am)
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Tue Apr 10, 9:17 am)
Re: [PATCH] Only send pdeath_signal when getppid changes., Oleg Nesterov, (Tue Apr 10, 9:37 am)
Re: [PATCH] Only send pdeath_signal when getppid changes., Eric W. Biederman, (Tue Apr 10, 10:41 am)
Re: [PATCH] Only send pdeath_signal when getppid changes., Roland McGrath, (Tue Apr 10, 10:48 am)
Re: init's children list is long and slows reaping children., Davide Libenzi, (Tue Apr 10, 12:17 pm)
Re: [PATCH] Only send pdeath_signal when getppid changes., Albert Cahalan, (Tue Apr 10, 8:17 pm)
[patch] uninline remove/add_parent() APIs, Ingo Molnar, (Tue Apr 10, 11:20 pm)
Re: [patch] uninline remove/add_parent() APIs, Eric W. Biederman, (Wed Apr 11, 12:00 am)
Re: init's children list is long and slows reaping children., Eric W. Biederman, (Wed Apr 11, 1:17 pm)
Re: [patch] uninline remove/add_parent() APIs, Andrew Morton, (Wed Apr 11, 3:06 pm)
Re: [patch] uninline remove/add_parent() APIs, Eric W. Biederman, (Thu Apr 12, 3:45 am)
Re: [patch] uninline remove/add_parent() APIs, Roland McGrath, (Thu Apr 12, 3:50 pm)