[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20230421122504.pq76pj6hka2xdbpu@techsingularity.net>
Date: Fri, 21 Apr 2023 13:25:04 +0100
From: Mel Gorman <mgorman@...hsingularity.net>
To: Johannes Weiner <hannes@...xchg.org>
Cc: linux-mm@...ck.org, Kaiyang Zhao <kaiyang2@...cmu.edu>,
Vlastimil Babka <vbabka@...e.cz>,
David Rientjes <rientjes@...gle.com>,
linux-kernel@...r.kernel.org, kernel-team@...com
Subject: Re: [RFC PATCH 01/26] block: bdev: blockdev page cache is movable
On Tue, Apr 18, 2023 at 03:12:48PM -0400, Johannes Weiner wrote:
> While inspecting page blocks for the type of pages in them, I noticed
> a large number of blockdev cache in unmovable blocks. However, these
> pages are actually on the LRU, and their mapping has a .migrate_folio
> callback; they can be reclaimed and compacted as necessary.
>
> Put them into movable blocks, so they don't cause pollution, and
> subsequent proliferation, of unmovable blocks.
>
> Signed-off-by: Johannes Weiner <hannes@...xchg.org>
Deserves to be split out and needs careful treatment. I don't recall exactly
but I believe I encountered a problem with these allocations in the very
distant past. Some of the allocations were movable and others weren't
or had very long lifetimes. Something like being superblock-related or
directory inodes being pinned for very long lengths of time. This is a
*long* time ago and the picture almost certainly has changed but it's
very possible that a high percentage, but not 100% of these allocations
are not movable in practice.
--
Mel Gorman
SUSE Labs
Powered by blists - more mailing lists