Re: [PATCH next] ocfs2: Reduce object size of mlog uses

[Andrew Morton <akpm@linux-foundation.org>]

On Fri, 17 Apr 2015 00:17:50 -0700 Joe Perches <joe@perches.com> wrote:

> Using a function for __mlog_printk instead of a macro
> reduces the object size of built-in.o more than 120KB, or
> ~10% overall (x86-64 defconfig with all ocfs2 options)
> 
> $ size fs/ocfs2/built-in.o*
>    text	   data	    bss	    dec	    hex	filename
>  936255	 118071	 134408	1188734	 12237e	fs/ocfs2/built-in.o.new
> 1064081	 118071	 134408	1316560	 1416d0	fs/ocfs2/built-in.o.old

It's a start.

> --- a/fs/ocfs2/cluster/masklog.c
> +++ b/fs/ocfs2/cluster/masklog.c
> @@ -64,6 +64,23 @@ static ssize_t mlog_mask_store(u64 mask, const char *buf, size_t count)
>  	return count;
>  }
>  
> +void __mlog_printk(const char *level, const char *func, int line,
> +		   const char *fmt, ...)
> +{
> +	struct va_format vaf;
> +	va_list args;
> +
> +	va_start(args, fmt);
> +
> +	vaf.fmt = fmt;
> +	vaf.va = &args;
> +
> +	printk("%s(%s,%u,%lu):%s:%d %pV",
> +	       level, current->comm, task_pid_nr(current), __mlog_cpu_guess,
> +	       func, line, &vaf);
> +
> +	va_end(args);
> +}

Logging function-name and line-number was a bit weird.  I wonder if
anyone will mind if this is converted to file-n-line, as God intended. 
That will shrink rodata a bit, because number-of-files is a lot less
than number-of-functions.

>  struct mlog_attribute {
>  	struct attribute attr;
>  	u64 mask;
> diff --git a/fs/ocfs2/cluster/masklog.h b/fs/ocfs2/cluster/masklog.h
> index 7fdc25a..6036e6a 100644
> --- a/fs/ocfs2/cluster/masklog.h
> +++ b/fs/ocfs2/cluster/masklog.h
> @@ -168,7 +168,8 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits;
>   * scream.  just do this instead of trying to guess which we're building
>   * against.. *sigh*.
>   */
> -#define __mlog_cpu_guess ({		\
> +#define __mlog_cpu_guess		\
> +({					\

While we're in there we should turn this into __mlog_cpu_guess().

Or, preferably, just zap the sorry thing and use
raw_smp_processor_id().

>  	unsigned long _cpu = get_cpu();	\
>  	put_cpu();			\
>  	_cpu;				\
> @@ -178,21 +179,25 @@ extern struct mlog_bits mlog_and_bits, mlog_not_bits;
>   * before ##args is intentional. Otherwise, gcc 2.95 will eat the
>   * previous token if args expands to nothing.
>   */
> -#define __mlog_printk(level, fmt, args...)				\
> -	printk(level "(%s,%u,%lu):%s:%d " fmt, current->comm,		\
> -	       task_pid_nr(current), __mlog_cpu_guess,			\
> -	       __PRETTY_FUNCTION__, __LINE__ , ##args)
> +__printf(4, 5)
> +void __mlog_printk(const char *level, const char *func, int line,
> +		   const char *fmt, ...);
>  
> -#define mlog(mask, fmt, args...) do {					\
> +#define mlog(mask, fmt, ...)						\
> +do {									\
>  	u64 __m = MLOG_MASK_PREFIX | (mask);				\
>  	if ((__m & ML_ALLOWED_BITS) &&					\
>  	    __mlog_test_u64(__m, mlog_and_bits) &&			\
>  	    !__mlog_test_u64(__m, mlog_not_bits)) {			\
>  		if (__m & ML_ERROR)					\

All this goop can also be uninlined?

> -			__mlog_printk(KERN_ERR, "ERROR: "fmt , ##args);	\
> +			__mlog_printk(KERN_ERR, __func__, __LINE__,	\
> +				      "ERROR: " fmt, ##__VA_ARGS__);	\
>  		else if (__m & ML_NOTICE)				\
> -			__mlog_printk(KERN_NOTICE, fmt , ##args);	\
> -		else __mlog_printk(KERN_INFO, fmt , ##args);		\
> +			__mlog_printk(KERN_NOTICE, __func__, __LINE__,	\
> +				      fmt, ##__VA_ARGS__);		\
> +		else							\
> +			__mlog_printk(KERN_INFO, __func__, __LINE__,	\
> +				      fmt, ##__VA_ARGS__);		\
>  	}								\
>  } while (0)
>  

I guess this patch is a step on the way - a 10% shrink is decent.  But
I believe that with full uninlining of the ocfs2 logging code we can
shrink the filesystem's footprint by 50%.

This code needs some pretty serious rework and rethink, perhaps
involving a change to the emitted info.  I was hoping one of the ocfs2
developers would take the bait, but they're all in hiding.

If you feel like undertaking such a rotorooting then go wild - that should
wake 'em up ;)