Pablo de Lara 5915699153 hash: fix scaling by reducing contention ... If using multiple cores on a system with hardware transactional memory support, thread scaling does not work, as there was a single point in the hash library which is a bottleneck for all threads, which is the "free_slots" ring, which stores all the indices of the free slots in the table. This patch fixes the problem, by creating a local cache per logical core, which stores locally indices of free slots, so most times, writer threads will not interfere each other. Fixes: 48a3991196 ("hash: replace with cuckoo hash implementation") Signed-off-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Bruce Richardson <bruce.richardson@intel.com>		2015-11-04 01:04:10 +01:00
..
cmdline_test	app: fix whitespace	2015-06-12 11:10:10 +02:00
proc_info	app: replace dump_cfg by proc_info	2015-07-17 02:26:38 +02:00
test	hash: fix scaling by reducing contention	2015-11-04 01:04:10 +01:00
test-acl	acl: remove old API	2015-09-03 19:22:48 +02:00
test-pipeline	port: move metadata offset reference at mbuf head	2015-10-19 17:00:36 +02:00
test-pmd	app/testpmd: add command to select filtering GRE key size	2015-11-04 00:45:54 +01:00
Makefile	app: replace dump_cfg by proc_info	2015-07-17 02:26:38 +02:00