FYI: mmap_sem OOM patch
in [Kernel]
|
Prev: struct io panic on raid1 - Re: block: unify flags for struct bio and struct request will kernel panic
Next: SELinux: Add new labeling type native labels
From: KOSAKI Motohiro on 8 Jul 2010 07:10 > On Thu, 2010-07-08 at 19:57 +0900, KOSAKI Motohiro wrote: > > > On Thu, 2010-07-08 at 03:39 -0700, Michel Lespinasse wrote: > > > > > > > > > > > > One way to fix this is to have T4 wake from the oom queue and return an > > > > allocation failure instead of insisting on going oom itself when T1 > > > > decides to take down the task. > > > > > > > > How would you have T4 figure out the deadlock situation ? T1 is taking down T2, not T4... > > > > > > If T2 and T4 share a mmap_sem they belong to the same process. OOM takes > > > down the whole process by sending around signals of sorts (SIGKILL?), so > > > if T4 gets a fatal signal while it is waiting to enter the oom thingy, > > > have it abort and return an allocation failure. > > > > > > That alloc failure (along with a pending fatal signal) will very likely > > > lead to the release of its mmap_sem (if not, there's more things to > > > cure). > > > > > > At which point the cycle is broken an stuff continues as it was > > > intended. > > > > Now, I've reread current code. I think mmotm already have this. > > <snip code> > > [ small note on that we really should kill __GFP_NOFAIL, its utter > deadlock potential ] I disagree. __GFP_NOFAIL mean this allocation failure can makes really dangerous result. Instead, OOM-Killer should try to kill next process. I think. > > Thought? > > So either its not working or google never tried that code? Michel? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Peter Zijlstra on 8 Jul 2010 07:10 On Thu, 2010-07-08 at 19:57 +0900, KOSAKI Motohiro wrote: > > On Thu, 2010-07-08 at 03:39 -0700, Michel Lespinasse wrote: > > > > > > > > > One way to fix this is to have T4 wake from the oom queue and return an > > > allocation failure instead of insisting on going oom itself when T1 > > > decides to take down the task. > > > > > > How would you have T4 figure out the deadlock situation ? T1 is taking down T2, not T4... > > > > If T2 and T4 share a mmap_sem they belong to the same process. OOM takes > > down the whole process by sending around signals of sorts (SIGKILL?), so > > if T4 gets a fatal signal while it is waiting to enter the oom thingy, > > have it abort and return an allocation failure. > > > > That alloc failure (along with a pending fatal signal) will very likely > > lead to the release of its mmap_sem (if not, there's more things to > > cure). > > > > At which point the cycle is broken an stuff continues as it was > > intended. > > Now, I've reread current code. I think mmotm already have this. <snip code> [ small note on that we really should kill __GFP_NOFAIL, its utter deadlock potential ] > Thought? So either its not working or google never tried that code? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Peter Zijlstra on 8 Jul 2010 07:30 On Thu, 2010-07-08 at 20:06 +0900, KOSAKI Motohiro wrote: > > [ small note on that we really should kill __GFP_NOFAIL, its utter > > deadlock potential ] > > I disagree. __GFP_NOFAIL mean this allocation failure can makes really > dangerous result. Instead, OOM-Killer should try to kill next process. > I think. Say _what_?! you think NOFAIL is a sane thing? Pretty much everybody has been agreeing for years that the thing should die. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Peter Zijlstra on 8 Jul 2010 08:50 Could you please educate your mailer to not send HTML garbage? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: KOSAKI Motohiro on 8 Jul 2010 21:40
> On Thu, 2010-07-08 at 20:06 +0900, KOSAKI Motohiro wrote: > > > [ small note on that we really should kill __GFP_NOFAIL, its utter > > > deadlock potential ] > > > > I disagree. __GFP_NOFAIL mean this allocation failure can makes really > > dangerous result. Instead, OOM-Killer should try to kill next process. > > I think. > > Say _what_?! you think NOFAIL is a sane thing? insane obviously ;) but as far as my experience, some embedded system prefer to use NOFAIL. So, I don't like to make big hammer crash. NOFAIL killing need long year rather than you expected, I guess. > Pretty much everybody has > been agreeing for years that the thing should die. I'm not against this at all. but until it die, it should works correctly. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |