linux-kernel - [RFC Patch 2/3] mm/slub: double per-cpu partial number for large systems

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue,  5 Sep 2023 22:13:47 +0800
From:   Feng Tang <feng.tang@...el.com>
To:     Vlastimil Babka <vbabka@...e.cz>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Christoph Lameter <cl@...ux.com>,
        Pekka Enberg <penberg@...nel.org>,
        David Rientjes <rientjes@...gle.com>,
        Joonsoo Kim <iamjoonsoo.kim@....com>,
        Roman Gushchin <roman.gushchin@...ux.dev>,
        Hyeonggon Yoo <42.hyeyoo@...il.com>, linux-mm@...ck.org,
        linux-kernel@...r.kernel.org
Cc:     Feng Tang <feng.tang@...el.com>
Subject: [RFC Patch 2/3] mm/slub: double per-cpu partial number for large systems

There are reports about severe lock contention for slub's per-node
'list_lock' in 'hackbench' test, [1][2], on server systems. And
similar contention is also seen when running 'mmap1' case of
will-it-scale on big systems. As the trend is one processor (socket)
will have more and more CPUs (100+, 200+), the contention could be
much more severe and becomes a scalability issue.

One way to help reducing the contention is to double the per-cpu
partial number for large systems.

Following is some performance data, where it shows big improvment
in will-it-scale/mmap1 case, but no ovbious change for the 'hackbench'
test.

The patch itself only makes the per-cpu partial number 2X, and for
better analysis, the 4X case is also profiled

will-it-scale/mmap1
-------------------
Run will-it-scale benchmark's 'mmap1' test case on a 2 socket Sapphire
Rapids server (112 cores / 224 threads) with 256 GB DRAM, run 3
configurations with parallel test threads of 25%, 50% and 100% of
number of CPUs, and the data is (base is vanilla v6.5 kernel):

		  base             base + 2X patch        base + 4X patch
wis-mmap1-25	 223670    +12.7%     251999     +34.9%     301749    per_process_ops
wis-mmap1-50	 186020    +28.0%     238067     +55.6%     289521    per_process_ops
wis-mmap1-100	  89200    +40.7%     125478     +62.4%     144858    per_process_ops

Take the perf-profile comparasion of 50% test case, the lock contention
is greatly reduced:

     43.80           -11.5       32.27           -27.9       15.91   pp.self.native_queued_spin_lock_slowpath

hackbench
---------

Run same hackbench testcase  mentioned in [1], use same HW/SW as will-it-scale:

		  base             base + 2X patch        base + 4X patch
hackbench	759951      +0.2%    761506      +0.5%     763972     hackbench.throughput

[1]. https://lore.kernel.org/all/202307172140.3b34825a-oliver.sang@intel.com/
[2]. ttps://lore.kernel.org/lkml/ZORaUsd+So+tnyMV@...nyu5-mobl2/

Signed-off-by: Feng Tang <feng.tang@...el.com>
---
 mm/slub.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/mm/slub.c b/mm/slub.c
index f7940048138c..51ca6dbaad09 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4361,6 +4361,13 @@ static void set_cpu_partial(struct kmem_cache *s)
 	else
 		nr_objects = 120;
 
+	/*
+	 * Give larger system more per-cpu partial slabs to reduce/postpone
+	 * contending per-node partial list.
+	 */
+	if (num_cpus() >= 32)
+		nr_objects *= 2;
+
 	slub_set_cpu_partial(s, nr_objects);
 #endif
 }
-- 
2.27.0