From: Shaokun Zhang <zhangshaokun@hisilicon.com>
To: Michal Hocko <mhocko@kernel.org>
Cc: <linux-kernel@vger.kernel.org>, yuqi jin <jinyuqi@huawei.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
Mike Rapoport <rppt@linux.ibm.com>,
"Paul Burton" <paul.burton@mips.com>,
Michael Ellerman <mpe@ellerman.id.au>,
Anshuman Khandual <anshuman.khandual@arm.com>
Subject: Re: [PATCH] lib: optimize cpumask_local_spread()
Date: Mon, 4 Nov 2019 11:37:20 +0800 [thread overview]
Message-ID: <97943c12-5704-e8a2-3736-4d0c23e2ff80@hisilicon.com> (raw)
In-Reply-To: <20191031073905.GD13102@dhcp22.suse.cz>
Hi Michal,
On 2019/10/31 15:39, Michal Hocko wrote:
> On Thu 31-10-19 14:03:33, Shaokun Zhang wrote:
>> From: yuqi jin <jinyuqi@huawei.com>
>>
>> In the multi-processor and NUMA system, A device may have many numa
>> nodes belonging to multiple cpus. When we get a local numa, it is better
>> to find the node closest to the local numa node to return instead of
>> going to the online cpu immediately.
>>
>> For example, In Huawei Kunpeng 920 system, there are 4 NUMA node(0 -3)
>> in the 2-socket system(0 - 1). If the I/O device is in socket1
>> and the local NUMA node is 2, we shall choose the non-local node3 in
>> the same socket when cpu core in NUMA node2 is less that I/O requirements.
>> If we directly pick one cpu core from all online ones, it may be in
>> the another socket and it is not friendly for performance.
>
> My previous review feedback included a request for a much better
> description of the actual problem and how much of a performance gain we
> are talking about along with a workoload description.
>
Ok, I will update both in next version.
> Besides that I do not think that the implementation is great either.
Ok, Agree, so I sent it as RFC firstly and wanted to discuss this issue,
I will fix it more reasonable.
> Relying on GFP_ATOMIC is very dubious. Is there any specific reason why
> the data structure cannot pre reallocated? The comment for
Ok, will do it.
> cpumask_local_spread says that this is not the most efficient function
> so users should better be prepared to not call it from hot paths AFAIU.
> That would imply that an internal locking should be acceptable as well
> so a preallocated data structure could be used.
Ok.
Thanks,
Shaokun
>
>> Cc: Andrew Morton <akpm@linux-foundation.org>
>> Cc: Mike Rapoport <rppt@linux.ibm.com>
>> Cc: Paul Burton <paul.burton@mips.com>
>> Cc: Michal Hocko <mhocko@suse.com>
>> Cc: Michael Ellerman <mpe@ellerman.id.au>
>> Cc: Anshuman Khandual <anshuman.khandual@arm.com>
>> Signed-off-by: yuqi jin <jinyuqi@huawei.com>
>> Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
>> ---
>> Changes from RFC:
>> Address Michal Hocko's comment: Use GFP_ATOMIC instead of GFP_KERNEL
>>
>> lib/cpumask.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++---------
>> 1 file changed, 65 insertions(+), 11 deletions(-)
>>
>> diff --git a/lib/cpumask.c b/lib/cpumask.c
>> index 0cb672eb107c..c92177b0e095 100644
>> --- a/lib/cpumask.c
>> +++ b/lib/cpumask.c
>> @@ -192,6 +192,33 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
>> }
>> #endif
>>
>> +static void calc_node_distance(int *node_dist, int node)
>> +{
>> + int i;
>> +
>> + for (i = 0; i < nr_node_ids; i++)
>> + node_dist[i] = node_distance(node, i);
>> +}
>> +
>> +static int find_nearest_node(int *node_dist, bool *used_flag)
>> +{
>> + int i, min_dist = node_dist[0], node_id = -1;
>> +
>> + for (i = 0; i < nr_node_ids; i++)
>> + if (used_flag[i] == 0) {
>> + min_dist = node_dist[i];
>> + node_id = i;
>> + break;
>> + }
>> + for (i = 0; i < nr_node_ids; i++)
>> + if (node_dist[i] < min_dist && used_flag[i] == 0) {
>> + min_dist = node_dist[i];
>> + node_id = i;
>> + }
>> +
>> + return node_id;
>> +}
>> +
>> /**
>> * cpumask_local_spread - select the i'th cpu with local numa cpu's first
>> * @i: index number
>> @@ -205,7 +232,8 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask)
>> */
>> unsigned int cpumask_local_spread(unsigned int i, int node)
>> {
>> - int cpu;
>> + int cpu, j, id, *node_dist;
>> + bool *used_flag;
>>
>> /* Wrap: we always want a cpu. */
>> i %= num_online_cpus();
>> @@ -215,19 +243,45 @@ unsigned int cpumask_local_spread(unsigned int i, int node)
>> if (i-- == 0)
>> return cpu;
>> } else {
>> - /* NUMA first. */
>> - for_each_cpu_and(cpu, cpumask_of_node(node), cpu_online_mask)
>> - if (i-- == 0)
>> - return cpu;
>> + node_dist = kmalloc_array(nr_node_ids, sizeof(int), GFP_ATOMIC);
>> + if (!node_dist)
>> + for_each_cpu(cpu, cpu_online_mask)
>> + if (i-- == 0)
>> + return cpu;
>>
>> - for_each_cpu(cpu, cpu_online_mask) {
>> - /* Skip NUMA nodes, done above. */
>> - if (cpumask_test_cpu(cpu, cpumask_of_node(node)))
>> - continue;
>> + used_flag = kmalloc_array(nr_node_ids, sizeof(bool), GFP_ATOMIC);
>> + if (!used_flag)
>> + for_each_cpu(cpu, cpu_online_mask)
>> + if (i-- == 0) {
>> + kfree(node_dist);
>> + return cpu;
>> + }
>> + memset(used_flag, 0, nr_node_ids * sizeof(bool));
>>
>> - if (i-- == 0)
>> - return cpu;
>> + calc_node_distance(node_dist, node);
>> + for (j = 0; j < nr_node_ids; j++) {
>> + id = find_nearest_node(node_dist, used_flag);
>> + if (id < 0)
>> + break;
>> + for_each_cpu_and(cpu,
>> + cpumask_of_node(id), cpu_online_mask)
>> + if (i-- == 0) {
>> + kfree(node_dist);
>> + kfree(used_flag);
>> + return cpu;
>> + }
>> + used_flag[id] = 1;
>> }
>> +
>> + for_each_cpu(cpu, cpu_online_mask)
>> + if (i-- == 0) {
>> + kfree(node_dist);
>> + kfree(used_flag);
>> + return cpu;
>> + }
>> +
>> + kfree(node_dist);
>> + kfree(used_flag);
>> }
>> BUG();
>> }
>> --
>> 2.7.4
>
next prev parent reply other threads:[~2019-11-04 3:37 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-31 6:03 [PATCH] lib: optimize cpumask_local_spread() Shaokun Zhang
2019-10-31 7:39 ` Michal Hocko
2019-11-04 3:37 ` Shaokun Zhang [this message]
2019-11-01 0:37 ` Andrew Morton
2019-11-04 6:02 ` Shaokun Zhang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=97943c12-5704-e8a2-3736-4d0c23e2ff80@hisilicon.com \
--to=zhangshaokun@hisilicon.com \
--cc=akpm@linux-foundation.org \
--cc=anshuman.khandual@arm.com \
--cc=jinyuqi@huawei.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mhocko@kernel.org \
--cc=mpe@ellerman.id.au \
--cc=paul.burton@mips.com \
--cc=rppt@linux.ibm.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).