[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <65b32f11-6c83-3497-3cbf-3d3688195291@huawei.com>
Date: Thu, 31 May 2018 22:00:51 +0800
From: Hanjun Guo <guohanjun@...wei.com>
To: Xie XiuQi <xiexiuqi@...wei.com>, <catalin.marinas@....com>,
<will.deacon@....com>, <bhelgaas@...gle.com>,
<gregkh@...uxfoundation.org>, <rafael.j.wysocki@...el.com>,
<jarkko.sakkinen@...ux.intel.com>
CC: <linux-arm-kernel@...ts.infradead.org>,
<linux-kernel@...r.kernel.org>, <wanghuiqiang@...wei.com>,
<tnowicki@...iumnetworks.com>
Subject: Re: [PATCH 0/2] arm64/drivers: avoid alloc memory on offline node
Hi Xiuqi,
On 2018/5/31 20:14, Xie XiuQi wrote:
> A numa system may return node which is not online.
> For example, a numa node:
> 1) without memory
> 2) NR_CPUS is very small, and the cpus on the node are not brought up
I think adding detail info will be easy to be understood:
- NUMA node will be built if CPUs and (or) memory are valid on this NUMA node;
- But if we boot the system with memory-less node and also with CONFIG_NR_CPUS
less than CPUs in SRAT, for example, 64 CPUs total with 4 NUMA nodes, 16 CPUs
on each NUMA node, if we boot with CONFIG_NR_CPUS=48, then we will not built
numa node for node 3, but with devices on that numa node, alloc memory will
be panic because NUMA node 3 is not a valid node.
>
> In this situation, we use NUMA_NO_NODE to avoid oops.
[snip]
>
> Xie XiuQi (2):
> arm64: avoid alloc memory on offline node
> drivers: check numa node's online status in dev_to_node
I think we still missing devices like SMMU, ITS, so how about check
the numa node online in the core memory allocation such as kmalloc_node()?
Thanks
Hanjun
Powered by blists - more mailing lists