February 2011 - kernelnewbies@kernelnewbies.org

> 2GB memset is very slow
by Jason Nymble Feb. 1, 2011

Feb. 1, 2011

I was using memset on a reserved area of memory (64bit x86 kernel and system), and noticed that as soon as I exceed a size of 2GB, the function becomes extremely slow, e.g just below 2GB it takes typically about 0.3s, and just above 2GB is takes about 39s to complete... I tried tracing the eventual function that is called in the kernel, and I think it resolves to the below (even on x86_64 if I'm not mistaken): static inline void *__memset_generic(void *s, char c, size_t count) { int d0, d1; asm volatile("rep\n\t" "stosb" : "=&c" (d0), "=&D" (d1) : "a" (c), "1" (s), "0" (count) : "memory"); return s; } size_t is defined as (unsigned long) on my platform, but I suspect the d0 and d1 variables above cause problems because they are int... Is this a kernel bug, or known limitation, or what?

3 4

what is spinlock depth
by Sri Ram Vemulpali Feb. 1, 2011

Feb. 1, 2011

Hi all, I am reading spinlock code and looking at struct raw_spinlock. I found struct lockdep_map as member. which is defined as struct lockdep_map { struct lock_class_key *key; struct lock_class *class_cache[NR_LOCKDEP_CACHING_CLASSES]; const char *name; #ifdef CONFIG_LOCK_STAT int cpu; unsigned long ip; #endif }; Can anyone help me explain, how this struct helps the spinlock. Why do we need lockdepth. Thanks for help in advance. -- Regards, Sri.

2 1

storing the logs
by mohit verma Feb. 1, 2011

Feb. 1, 2011

hi , my module produces some data (very cititcal) and that i want to log that to some disk residing file like log files. So among several ways like using syslog (and family) ,audit daemon i am not finding the way to use the functionalities of any of these subsystems .i mean : practically i am still unable to do that. can someone point me to some practical implementations used by some other modules or some practically sound articles to achieve this? thanks a lot in advance. -- ........................ *MOHIT VERMA*

3 4

process exception
by Sri Ram Vemulpali Feb. 1, 2011

Feb. 1, 2011

Hi all, This is regarding segment fault. Is there any feature that we can allow kernel to kill only the thread that generate seg fault rather than killing whole process in which it is running. Why is that we did not implement in such way. Is there any specific reason. Thanks in advance for explanation. -- Regards, Sri.

3 2