On Sat, Nov 17, 2018 at 10:34:18AM +0800, Ming Lei wrote:

On Fri, Nov 16, 2018 at 06:06:23AM -0800, Greg Kroah-Hartman wrote:

quoted

On Fri, Nov 16, 2018 at 07:23:11PM +0800, Ming Lei wrote:

quoted

Now q->queue_ctx is just one read-mostly table for query the
'blk_mq_ctx' instance from one cpu index, it isn't necessary
to allocate it as percpu variable. One simple array may be
more efficient.

"may be", have you run benchmarks to be sure?  If so, can you add the
results of them to this changelog?  If there is no measurable
difference, then why make this change at all?

__blk_mq_get_ctx() is used in fast path, what do you think about which
one is more efficient?

- *per_cpu_ptr(q->queue_ctx, cpu);

- q->queue_ctx[cpu]

You need to actually test to see which one is faster, you might be
surprised :)

In other words, do not just guess.

At least the latter isn't worse than the former.

How do you know?

Especially q->queue_ctx is just a read-only look-up table, it doesn't
make sense to make it percpu any more.

Not mention q->queue_ctx[cpu] is more clean/readable.

Again, please test to verify this.

thanks,

greg k-h