On 1/21/20 8:29 AM, Peter Zijlstra wrote:

On Mon, Dec 30, 2019 at 02:40:41PM -0500, Alex Kogan wrote:

quoted

+/*
+ * Controls the threshold for the number of intra-node lock hand-offs before
+ * the NUMA-aware variant of spinlock is forced to be passed to a thread on
+ * another NUMA node. By default, the chosen value provides reasonable
+ * long-term fairness without sacrificing performance compared to a lock
+ * that does not have any fairness guarantees. The default setting can
+ * be changed with the "numa_spinlock_threshold" boot option.
+ */
+int intra_node_handoff_threshold __ro_after_init = 1 << 16;

There is a distinct lack of quantitative data to back up that
'reasonable' claim there.

Where is the table of inter-node latencies observed for the various
values tested, and on what criteria is this number deemed reasonable?

To me, 64k lock hold times seems like a giant number, entirely outside
of reasonable.

I actually had similar question before, but having the capability of
changing the default with boot time parameter alleviate some of my
concern. I will certainly like to see actual data on how different
values will affect the performance of the code.

Cheers,
Longman


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel