Re: CONFIG_PRINTK_TIME woes

[tony . luck]

>Ah, thanks.  Presumably it'll be considerably longer with %d's and %s's in
>there.  But still, ~10 usecs is good resolution for I/O operations.

The variation in times from one call to the next seems to be
greater than the time to evaluate 4 "%d" arguments.

So we are back to how to get a timestamp in printk().

Earlier I said that it would be possible to provide a simplified
do_gettimeofday() call that met the no locks requirement.  I still
think this is possible, but most architectures would only get
jiffie resolution from this (only ia64, sparc64 and HPET users
have time interpolators registered).

-Tony
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/