net: set default rss queues num to physical cores / 2
Network drivers can call to netif_get_num_default_rss_queues to get the default number of receive queues to use. Right now, this default number is min(8, num_online_cpus()). Instead, as suggested by Jakub, use the number of physical cores divided by 2 as a way to avoid wasting CPU resources and to avoid using both CPU threads, but still allowing to scale for high-end processors with many cores. As an exception, select 2 queues for processors with 2 cores, because otherwise it won't take any advantage of RSS despite being SMP capable. Tested: Processor Intel Xeon E5-2620 (2 sockets, 6 cores/socket, 2 threads/core). NIC Broadcom NetXtreme II BCM57810 (10GBps). Ran some tests with `perf stat iperf3 -R`, with parallelisms of 1, 8 and 24, getting the following results: - Number of queues: 6 (instead of 8) - Network throughput: not affected - CPU usage: utilized 0.05-0.12 CPUs more than before (having 24 CPUs this is only 0.2-0.5% higher) - Reduced the number of context switches by 7-50%, being more noticeable when using a higher number of parallel threads. Suggested-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Íñigo Huguet <ihuguet@redhat.com> Link: https://lore.kernel.org/r/20220315091832.13873-1-ihuguet@redhat.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
parent
e89600ebee
commit
046e1537a3
|
@ -3664,7 +3664,6 @@ static inline unsigned int get_netdev_rx_queue_index(
|
|||
}
|
||||
#endif
|
||||
|
||||
#define DEFAULT_MAX_NUM_RSS_QUEUES (8)
|
||||
int netif_get_num_default_rss_queues(void);
|
||||
|
||||
enum skb_free_reason {
|
||||
|
|
|
@ -2990,13 +2990,25 @@ EXPORT_SYMBOL(netif_set_real_num_queues);
|
|||
/**
|
||||
* netif_get_num_default_rss_queues - default number of RSS queues
|
||||
*
|
||||
* This routine should set an upper limit on the number of RSS queues
|
||||
* used by default by multiqueue devices.
|
||||
* Default value is the number of physical cores if there are only 1 or 2, or
|
||||
* divided by 2 if there are more.
|
||||
*/
|
||||
int netif_get_num_default_rss_queues(void)
|
||||
{
|
||||
return is_kdump_kernel() ?
|
||||
1 : min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus());
|
||||
cpumask_var_t cpus;
|
||||
int cpu, count = 0;
|
||||
|
||||
if (unlikely(is_kdump_kernel() || !zalloc_cpumask_var(&cpus, GFP_KERNEL)))
|
||||
return 1;
|
||||
|
||||
cpumask_copy(cpus, cpu_online_mask);
|
||||
for_each_cpu(cpu, cpus) {
|
||||
++count;
|
||||
cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu));
|
||||
}
|
||||
free_cpumask_var(cpus);
|
||||
|
||||
return count > 2 ? DIV_ROUND_UP(count, 2) : count;
|
||||
}
|
||||
EXPORT_SYMBOL(netif_get_num_default_rss_queues);
|
||||
|
||||
|
|
Loading…
Reference in New Issue