The oprofile event buffer is unsigned long [], and stores cookie values.
Surely that would require us to use u64 there too, doubling the buffer
sizes on 32-bit machines ?
I suppose we could do so magic to spread the cookie value across two
buffer entries if necessary, but that's ugly...
True.
What if you could query the cookie size at runtime?
Would that help?
Really, if you make it long it's going to be impossible
to support this in 32/64 environments (ppc/sparc/mips/x86_64/
ia64/etc.)
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/