[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <f0e640c9-2eff-ffc5-8558-4bc1b374eb2a@arm.com>
Date: Wed, 15 May 2019 12:44:16 +0530
From: Anshuman Khandual <anshuman.khandual@....com>
To: Roman Gushchin <guro@...com>,
Andrew Morton <akpm@...ux-foundation.org>
Cc: linux-mm@...ck.org, linux-kernel@...r.kernel.org,
kernel-team@...com, Johannes Weiner <hannes@...xchg.org>
Subject: Re: [PATCH RESEND] mm: show number of vmalloc pages in /proc/meminfo
On 05/15/2019 05:21 AM, Roman Gushchin wrote:
> Vmalloc() is getting more and more used these days (kernel stacks,
> bpf and percpu allocator are new top users), and the total %
> of memory consumed by vmalloc() can be pretty significant
> and changes dynamically.
>
> /proc/meminfo is the best place to display this information:
> its top goal is to show top consumers of the memory.
>
> Since the VmallocUsed field in /proc/meminfo is not in use
> for quite a long time (it has been defined to 0 by the
> commit a5ad88ce8c7f ("mm: get rid of 'vmalloc_info' from
> /proc/meminfo")), let's reuse it for showing the actual
> physical memory consumption of vmalloc().
The primary concern which got addressed with a5ad88ce8c7f was that computing
get_vmalloc_info() was taking long time. But here its reads an already updated
value which gets added or subtracted during __vmalloc_area_node/__vunmap cycle.
Hence this should not cost much (like get_vmalloc_info). But is not this similar
to the caching solution Linus mentioned.
Powered by blists - more mailing lists