[4/4] dispatcher: use alloca instead of vla multi dimensional
Checks
Commit Message
RFC sample illustrating conversion of multi-dimensional VLA to use
alloca().
Signed-off-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
---
lib/dispatcher/rte_dispatcher.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
Comments
> From: Tyler Retzlaff [mailto:roretzla@linux.microsoft.com]
> Sent: Thursday, 4 April 2024 19.15
>
> RFC sample illustrating conversion of multi-dimensional VLA to use
> alloca().
>
> Signed-off-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
> ---
> lib/dispatcher/rte_dispatcher.c | 6 +++---
> 1 file changed, 3 insertions(+), 3 deletions(-)
>
> diff --git a/lib/dispatcher/rte_dispatcher.c
> b/lib/dispatcher/rte_dispatcher.c
> index 7934917..f154c26 100644
> --- a/lib/dispatcher/rte_dispatcher.c
> +++ b/lib/dispatcher/rte_dispatcher.c
> @@ -119,7 +119,7 @@ struct rte_dispatcher {
> struct rte_event *events, uint16_t num_events)
> {
> int i;
> - struct rte_event bursts[EVD_MAX_HANDLERS][num_events];
> + struct rte_event *bursts = alloca(sizeof(struct rte_event) *
> EVD_MAX_HANDLERS * num_events);
This is an interesting example, because keeping the allocated memory tight probably has better cache performance than a max sized multi dimensional array, such as bursts[EVD_MAX_HANDLERS][RTE_MAX_EVENT_BURST_SIZE].
And multiplication on modern CPUs are not much slower than left shifting, as they were on CPUs ages ago.
So this suggested solution for multi dimensional arrays seems preferable.
> uint16_t burst_lens[EVD_MAX_HANDLERS] = { 0 };
> uint16_t drop_count = 0;
> uint16_t dispatch_count;
> @@ -136,7 +136,7 @@ struct rte_dispatcher {
> continue;
> }
>
> - bursts[handler_idx][burst_lens[handler_idx]] = *event;
> + bursts[handler_idx * num_events + burst_lens[handler_idx]]
> = *event;
> burst_lens[handler_idx]++;
> }
>
> @@ -152,7 +152,7 @@ struct rte_dispatcher {
> continue;
>
> handler->process_fun(dispatcher->event_dev_id, port-
> >port_id,
> - bursts[i], len, handler->process_data);
> + &bursts[i * num_events], len, handler-
> >process_data);
>
> dispatched += len;
>
> --
> 1.8.3.1
@@ -119,7 +119,7 @@ struct rte_dispatcher {
struct rte_event *events, uint16_t num_events)
{
int i;
- struct rte_event bursts[EVD_MAX_HANDLERS][num_events];
+ struct rte_event *bursts = alloca(sizeof(struct rte_event) * EVD_MAX_HANDLERS * num_events);
uint16_t burst_lens[EVD_MAX_HANDLERS] = { 0 };
uint16_t drop_count = 0;
uint16_t dispatch_count;
@@ -136,7 +136,7 @@ struct rte_dispatcher {
continue;
}
- bursts[handler_idx][burst_lens[handler_idx]] = *event;
+ bursts[handler_idx * num_events + burst_lens[handler_idx]] = *event;
burst_lens[handler_idx]++;
}
@@ -152,7 +152,7 @@ struct rte_dispatcher {
continue;
handler->process_fun(dispatcher->event_dev_id, port->port_id,
- bursts[i], len, handler->process_data);
+ &bursts[i * num_events], len, handler->process_data);
dispatched += len;