[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <55496C8F.606@hp.com>
Date: Tue, 05 May 2015 21:21:19 -0400
From: Waiman Long <waiman.long@...com>
To: Andrew Morton <akpm@...ux-foundation.org>
CC: Mel Gorman <mgorman@...e.de>, Nathan Zimmer <nzimmer@....com>,
Dave Hansen <dave.hansen@...el.com>,
Scott Norton <scott.norton@...com>,
Daniel J Blueman <daniel@...ascale.com>,
Linux-MM <linux-mm@...ck.org>,
LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH 0/13] Parallel struct page initialisation v4
On 05/05/2015 04:02 PM, Andrew Morton wrote:
> On Tue, 5 May 2015 11:45:14 +0100 Mel Gorman<mgorman@...e.de> wrote:
>
>> On Mon, May 04, 2015 at 02:30:46PM -0700, Andrew Morton wrote:
>>>> Before the patch, the boot time from elilo prompt to ssh login was 694s.
>>>> After the patch, the boot up time was 346s, a saving of 348s (about 50%).
>>> Having to guesstimate the amount of memory which is needed for a
>>> successful boot will be painful. Any number we choose will be wrong
>>> 99% of the time.
>>>
>>> If the kswapd threads have started, all we need to do is to wait: take
>>> a little nap in the allocator's page==NULL slowpath.
>>>
>>> I'm not seeing any reason why we can't start kswapd much earlier -
>>> right at the start of do_basic_setup()?
>> It doesn't even have to be kswapd, it just should be a thread pinned to
>> a done. The difficulty is that dealing with the system hashes means the
>> initialisation has to happen before vfs_caches_init_early() when there is
>> no scheduler.
> I bet we can run vfs_caches_init_early() after sched_init(). Might
> need a few little fixups.
>
>> Those allocations could be delayed further but then there is
>> the possibility that the allocations would not be contiguous and they'd
>> have to rely on CMA to make the attempt. That potentially alters the
>> performance of the large system hashes at run time.
> hm, why. If the kswapd threads are running and busily creating free
> pages then alloc_pages(order=10) can detect this situation and stall
> for a while, waiting for kswapd to create an order-10 page.
>
> Alternatively, the page allocator can go off and synchronously
> initialize some pageframes itself. Keep doing that until the
> allocation attempt succeeds.
>
> Such an approach is much more robust than trying to predict how much
> memory will be needed.
>
Most of those hash tables are allocated before smp_boot. In UP mode, you
can't have another thread initializing memory. So we really need to
preallocate enough for those tables.
Cheers,
Longman
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists