CEPH-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: David Howells <dhowells@redhat.com>
To: linux-fsdevel@vger.kernel.org
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
	"Matthew Wilcox (Oracle)" <willy@infradead.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	Christoph Hellwig <hch@lst.de>,
	Mike Marshall <hubcap@omnibond.com>,
	linux-mm@kvack.org, linux-cachefs@redhat.com,
	linux-afs@lists.infradead.org, linux-nfs@vger.kernel.org,
	linux-cifs@vger.kernel.org, ceph-devel@vger.kernel.org,
	v9fs-developer@lists.sourceforge.net, dhowells@redhat.com,
	Trond Myklebust <trond.myklebust@hammerspace.com>,
	Anna Schumaker <anna.schumaker@netapp.com>,
	Steve French <sfrench@samba.org>,
	Dominique Martinet <asmadeus@codewreck.org>,
	Jeff Layton <jlayton@redhat.com>,
	David Wysochanski <dwysocha@redhat.com>,
	"Matthew Wilcox (Oracle)" <willy@infradead.org>,
	Alexander Viro <viro@zeniv.linux.org.uk>,
	linux-cachefs@redhat.com, linux-afs@lists.infradead.org,
	linux-nfs@vger.kernel.org, linux-cifs@vger.kernel.org,
	ceph-devel@vger.kernel.org, v9fs-developer@lists.sourceforge.net,
	linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: [PATCH v6 05/30] mm: Implement readahead_control pageset expansion
Date: Thu, 08 Apr 2021 15:04:58 +0100
Message-ID: <161789069829.6155.4295672417565512161.stgit@warthog.procyon.org.uk> (raw)
In-Reply-To: <161789062190.6155.12711584466338493050.stgit@warthog.procyon.org.uk>

Provide a function, readahead_expand(), that expands the set of pages
specified by a readahead_control object to encompass a revised area with a
proposed size and length.

The proposed area must include all of the old area and may be expanded yet
more by this function so that the edges align on (transparent huge) page
boundaries as allocated.

The expansion will be cut short if a page already exists in either of the
areas being expanded into.  Note that any expansion made in such a case is
not rolled back.

This will be used by fscache so that reads can be expanded to cache granule
boundaries, thereby allowing whole granules to be stored in the cache, but
there are other potential users also.

Changes:
v6:
- Fold in a patch from Matthew Wilcox to tell the ondemand readahead
  algorithm about the expansion so that the next readahead starts at the
  right place[2].

v4:
- Moved the declaration of readahead_expand() to a better place[1].

Suggested-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Matthew Wilcox (Oracle) <willy@infradead.org>
cc: Alexander Viro <viro@zeniv.linux.org.uk>
cc: Christoph Hellwig <hch@lst.de>
cc: Mike Marshall <hubcap@omnibond.com>
cc: linux-mm@kvack.org
cc: linux-cachefs@redhat.com
cc: linux-afs@lists.infradead.org
cc: linux-nfs@vger.kernel.org
cc: linux-cifs@vger.kernel.org
cc: ceph-devel@vger.kernel.org
cc: v9fs-developer@lists.sourceforge.net
cc: linux-fsdevel@vger.kernel.org
Link: https://lore.kernel.org/r/20210217161358.GM2858050@casper.infradead.org/ [1]
Link: https://lore.kernel.org/r/159974633888.2094769.8326206446358128373.stgit@warthog.procyon.org.uk/
Link: https://lore.kernel.org/r/160588479816.3465195.553952688795241765.stgit@warthog.procyon.org.uk/ # rfc
Link: https://lore.kernel.org/r/161118131787.1232039.4863969952441067985.stgit@warthog.procyon.org.uk/ # rfc
Link: https://lore.kernel.org/r/161161028670.2537118.13831420617039766044.stgit@warthog.procyon.org.uk/ # v2
Link: https://lore.kernel.org/r/161340389201.1303470.14353807284546854878.stgit@warthog.procyon.org.uk/ # v3
Link: https://lore.kernel.org/r/161539530488.286939.18085961677838089157.stgit@warthog.procyon.org.uk/ # v4
Link: https://lore.kernel.org/r/161653789422.2770958.2108046612147345000.stgit@warthog.procyon.org.uk/ # v5
Link: https://lore.kernel.org/r/20210407201857.3582797-4-willy@infradead.org/ [2]
---

 include/linux/pagemap.h |    2 +
 mm/readahead.c          |   75 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 9a9e558ce4c7..ef511364cc0c 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -838,6 +838,8 @@ void page_cache_ra_unbounded(struct readahead_control *,
 void page_cache_sync_ra(struct readahead_control *, unsigned long req_count);
 void page_cache_async_ra(struct readahead_control *, struct page *,
 		unsigned long req_count);
+void readahead_expand(struct readahead_control *ractl,
+		      loff_t new_start, size_t new_len);
 
 /**
  * page_cache_sync_readahead - generic file readahead
diff --git a/mm/readahead.c b/mm/readahead.c
index 2088569a947e..f02dbebf1cef 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -638,3 +638,78 @@ SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count)
 {
 	return ksys_readahead(fd, offset, count);
 }
+
+/**
+ * readahead_expand - Expand a readahead request
+ * @ractl: The request to be expanded
+ * @new_start: The revised start
+ * @new_len: The revised size of the request
+ *
+ * Attempt to expand a readahead request outwards from the current size to the
+ * specified size by inserting locked pages before and after the current window
+ * to increase the size to the new window.  This may involve the insertion of
+ * THPs, in which case the window may get expanded even beyond what was
+ * requested.
+ *
+ * The algorithm will stop if it encounters a conflicting page already in the
+ * pagecache and leave a smaller expansion than requested.
+ *
+ * The caller must check for this by examining the revised @ractl object for a
+ * different expansion than was requested.
+ */
+void readahead_expand(struct readahead_control *ractl,
+		      loff_t new_start, size_t new_len)
+{
+	struct address_space *mapping = ractl->mapping;
+	struct file_ra_state *ra = ractl->ra;
+	pgoff_t new_index, new_nr_pages;
+	gfp_t gfp_mask = readahead_gfp_mask(mapping);
+
+	new_index = new_start / PAGE_SIZE;
+
+	/* Expand the leading edge downwards */
+	while (ractl->_index > new_index) {
+		unsigned long index = ractl->_index - 1;
+		struct page *page = xa_load(&mapping->i_pages, index);
+
+		if (page && !xa_is_value(page))
+			return; /* Page apparently present */
+
+		page = __page_cache_alloc(gfp_mask);
+		if (!page)
+			return;
+		if (add_to_page_cache_lru(page, mapping, index, gfp_mask) < 0) {
+			put_page(page);
+			return;
+		}
+
+		ractl->_nr_pages++;
+		ractl->_index = page->index;
+	}
+
+	new_len += new_start - readahead_pos(ractl);
+	new_nr_pages = DIV_ROUND_UP(new_len, PAGE_SIZE);
+
+	/* Expand the trailing edge upwards */
+	while (ractl->_nr_pages < new_nr_pages) {
+		unsigned long index = ractl->_index + ractl->_nr_pages;
+		struct page *page = xa_load(&mapping->i_pages, index);
+
+		if (page && !xa_is_value(page))
+			return; /* Page apparently present */
+
+		page = __page_cache_alloc(gfp_mask);
+		if (!page)
+			return;
+		if (add_to_page_cache_lru(page, mapping, index, gfp_mask) < 0) {
+			put_page(page);
+			return;
+		}
+		ractl->_nr_pages++;
+		if (ra) {
+			ra->size++;
+			ra->async_size++;
+		}
+	}
+}
+EXPORT_SYMBOL(readahead_expand);



  parent reply index

Thread overview: 60+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-08 14:03 [PATCH v6 00/30] Network fs helper library & fscache kiocb API David Howells
2021-04-08 14:04 ` [PATCH v6 01/30] iov_iter: Add ITER_XARRAY David Howells
2021-04-09  1:24   ` Al Viro
2021-04-09 18:10     ` [RFC PATCH 1/2] iov_iter: Remove iov_iter_for_each_range() David Howells
2021-04-09 18:11     ` [RFC PATCH 2/2] iov_iter: Drop the X argument from iterate_all_kinds() and use B instead David Howells
2021-04-09  9:09   ` [PATCH v6 01/30] iov_iter: Add ITER_XARRAY David Howells
2021-04-09 11:44     ` Matthew Wilcox
2021-04-22 13:35   ` Jeff Layton
2021-04-22 13:51   ` David Howells
2021-04-22 14:51     ` Jeff Layton
2021-04-08 14:04 ` [PATCH v6 02/30] mm: Add set/end/wait functions for PG_private_2 David Howells
2021-04-08 14:50   ` Matthew Wilcox
2021-04-08 15:25   ` David Howells
2021-04-08 15:57   ` David Howells
2021-04-08 21:15   ` [RFC][PATCH] mm: Split page_has_private() in two to better handle PG_private_2 David Howells
2021-04-08 23:50     ` Linus Torvalds
2021-04-09 10:59       ` [RFC PATCH 1/3] Make the generic bitops return bool David Howells
2021-04-09 10:59       ` [RFC PATCH 2/3] mm: Return bool from pagebit test functions David Howells
2021-04-09 11:16         ` Matthew Wilcox
2021-04-09 12:00         ` David Howells
2021-04-09 12:35         ` David Howells
2021-04-09 16:03         ` David Howells
2021-04-09 10:59       ` [RFC PATCH 3/3] mm: Split page_has_private() in two to better handle PG_private_2 David Howells
2021-04-09 11:24         ` Matthew Wilcox
2021-04-09  8:14     ` [RFC][PATCH] " David Howells
2021-04-13 15:11   ` [PATCH v7] mm: Add set/end/wait functions for PG_private_2 David Howells
2021-04-13 15:22     ` Matthew Wilcox
2021-04-08 14:04 ` [PATCH v6 03/30] mm/filemap: Pass the file_ra_state in the ractl David Howells
2021-04-08 14:04 ` [PATCH v6 04/30] fs: Document file_ra_state David Howells
2021-04-08 14:04 ` David Howells [this message]
2021-04-08 14:55   ` [PATCH v6 05/30] mm: Implement readahead_control pageset expansion Matthew Wilcox
2021-04-08 14:05 ` [PATCH v6 06/30] netfs: Make a netfs helper module David Howells
2021-04-08 14:05 ` [PATCH v6 07/30] netfs: Documentation for helper library David Howells
2021-04-08 14:05 ` [PATCH v6 08/30] netfs, mm: Move PG_fscache helper funcs to linux/netfs.h David Howells
2021-04-08 14:05 ` [PATCH v6 09/30] netfs, mm: Add set/end/wait_on_page_fscache() aliases David Howells
2021-04-08 14:06 ` [PATCH v6 10/30] netfs: Provide readahead and readpage netfs helpers David Howells
2021-04-08 14:06 ` [PATCH v6 11/30] netfs: Add tracepoints David Howells
2021-04-08 14:06 ` [PATCH v6 12/30] netfs: Gather stats David Howells
2021-04-08 14:06 ` [PATCH v6 13/30] netfs: Add write_begin helper David Howells
2021-04-08 14:06 ` [PATCH v6 14/30] netfs: Define an interface to talk to a cache David Howells
2021-04-08 14:07 ` [PATCH v6 15/30] netfs: Add a tracepoint to log failures that would be otherwise unseen David Howells
2021-04-08 14:07 ` [PATCH v6 16/30] fscache, cachefiles: Add alternate API to use kiocb for read/write to cache David Howells
2021-04-08 14:07 ` [PATCH v6 17/30] afs: Disable use of the fscache I/O routines David Howells
2021-04-08 14:07 ` [PATCH v6 18/30] afs: Pass page into dirty region helpers to provide THP size David Howells
2021-04-08 14:08 ` [PATCH v6 19/30] afs: Print the operation debug_id when logging an unexpected data version David Howells
2021-04-08 14:08 ` [PATCH v6 20/30] afs: Move key to afs_read struct David Howells
2021-04-08 14:08 ` [PATCH v6 21/30] afs: Don't truncate iter during data fetch David Howells
2021-04-08 14:08 ` [PATCH v6 22/30] afs: Log remote unmarshalling errors David Howells
2021-04-08 14:08 ` [PATCH v6 23/30] afs: Set up the iov_iter before calling afs_extract_data() David Howells
2021-04-08 14:09 ` [PATCH v6 24/30] afs: Use ITER_XARRAY for writing David Howells
2021-04-08 14:09 ` [PATCH v6 25/30] afs: Wait on PG_fscache before modifying/releasing a page David Howells
2021-04-08 14:09 ` [PATCH v6 26/30] afs: Extract writeback extension into its own function David Howells
2021-04-08 14:09 ` [PATCH v6 27/30] afs: Prepare for use of THPs David Howells
2021-04-08 14:09 ` [PATCH v6 28/30] afs: Use the fs operation ops to handle FetchData completion David Howells
2021-04-08 14:10 ` [PATCH v6 29/30] afs: Use new netfs lib read helper API David Howells
2021-04-08 14:10 ` [PATCH v6 30/30] afs: Use the netfs_write_begin() helper David Howells
2021-04-08 15:40 ` [PATCH v6 00/30] Network fs helper library & fscache kiocb API Jeff Layton
2021-04-09 12:04 ` David Wysochanski
2021-04-13 14:56   ` David Wysochanski
2021-04-13 16:21 ` Marc Dionne

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=161789069829.6155.4295672417565512161.stgit@warthog.procyon.org.uk \
    --to=dhowells@redhat.com \
    --cc=anna.schumaker@netapp.com \
    --cc=asmadeus@codewreck.org \
    --cc=ceph-devel@vger.kernel.org \
    --cc=dwysocha@redhat.com \
    --cc=hch@lst.de \
    --cc=hubcap@omnibond.com \
    --cc=jlayton@redhat.com \
    --cc=linux-afs@lists.infradead.org \
    --cc=linux-cachefs@redhat.com \
    --cc=linux-cifs@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=sfrench@samba.org \
    --cc=trond.myklebust@hammerspace.com \
    --cc=v9fs-developer@lists.sourceforge.net \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    /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

CEPH-Devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/ceph-devel/0 ceph-devel/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 ceph-devel ceph-devel/ https://lore.kernel.org/ceph-devel \
		ceph-devel@vger.kernel.org
	public-inbox-index ceph-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.ceph-devel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git