Re: squashfs performance regression and readahea

[Hsin-Yi Wang <hsinyi@chromium.org>]

[-- Attachment #1: Type: text/plain, Size: 4189 bytes --]

On Mon, May 9, 2022 at 3:05 PM Hsin-Yi Wang <hsinyi@chromium.org> wrote:
>
> On Mon, May 9, 2022 at 12:45 AM Matthew Wilcox <willy@infradead.org> wrote:
> >
> > On Sun, May 08, 2022 at 02:46:40PM +0000, Song, Xiongwei wrote:
> > > I am facing a performance regression on squashfs.  There are many squashfs
> > > partitions on our board. I am doing the operations below on 90 squashfs
> > > partitions:
> >
> > Hi Xiongwei.  Thanks for the report.  Hsin-Ye and I have been working on
> > this problem off-list.  Hsin-Ye, could you send the latest version?
>
> Hi Matthew,
>
> This is the patch of the latest version. Since it's just being
> reviewed halfway done, I posted the patch here, or should I send it to
> the list directly?
>
The indent seems broken when I pasted it here. Resend in the attachment.

> Thanks
>
> From 03558dcaab93ed3c32498eb70c7f2b1382b218d6 Mon Sep 17 00:00:00 2001
> From: Hsin-Yi Wang <hsinyi@chromium.org>
> Date: Sun, 10 Oct 2021 21:22:25 +0800
> Subject: [PATCH] squashfs: implement readahead
>
> Implement readahead callback for squashfs. It will read datablocks
> which cover pages in readahead request. For a few cases it will
> not mark page as uptodate, including:
> - file end is 0.
> - current batch of pages isn't in the same datablock or not enough in a
>   datablock.
> Otherwise pages will be marked as uptodate. The unhandled pages will be
> updated by readpage later.
>
> Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
> ---
>  fs/squashfs/file.c | 72 +++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 71 insertions(+), 1 deletion(-)
>
> diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
> index 89d492916dea..20ec48cf97c5 100644
> --- a/fs/squashfs/file.c
> +++ b/fs/squashfs/file.c
> @@ -39,6 +39,7 @@
>  #include "squashfs_fs_sb.h"
>  #include "squashfs_fs_i.h"
>  #include "squashfs.h"
> +#include "page_actor.h"
>
>  /*
>   * Locate cache slot in range [offset, index] for specified inode.  If
> @@ -494,7 +495,76 @@ static int squashfs_readpage(struct file *file,
> struct page *page)
>   return 0;
>  }
>
> +static void squashfs_readahead(struct readahead_control *ractl)
> +{
> + struct inode *inode = ractl->mapping->host;
> + struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
> + size_t mask = (1UL << msblk->block_log) - 1;
> + size_t shift = msblk->block_log - PAGE_SHIFT;
> + loff_t req_end = readahead_pos(ractl) + readahead_length(ractl);
> + loff_t start = readahead_pos(ractl) &~ mask;
> + size_t len = readahead_length(ractl) + readahead_pos(ractl) - start;
> + struct squashfs_page_actor *actor;
> + unsigned int nr_pages = 0;
> + struct page **pages;
> + u64 block = 0;
> + int bsize, res, i, index;
> + int file_end = i_size_read(inode) >> msblk->block_log;
> + int max_pages = 1UL << shift;
> +
> + readahead_expand(ractl, start, (len | mask) + 1);
> +
> + if (readahead_pos(ractl) + readahead_length(ractl) < req_end)
> + return;
> +
> + nr_pages = readahead_count(ractl);
> + pages = kmalloc_array(nr_pages, sizeof(void *), GFP_KERNEL);
> + if (!pages)
> + return;
> +
> + actor = squashfs_page_actor_init_special(pages, nr_pages, 0);
> + if (!actor)
> + goto out;
> +
> + for (;;) {
> + nr_pages = __readahead_batch(ractl, pages, max_pages);
> + if (!nr_pages)
> + break;
> +
> + if (readahead_pos(ractl) >= i_size_read(inode) ||
> +     file_end == 0 || nr_pages < max_pages)
> + goto skip_pages;
> +
> + index = pages[0]->index >> shift;
> + bsize = read_blocklist(inode, index, &block);
> + res = squashfs_read_data(inode->i_sb, block, bsize, NULL,
> + actor);
> +
> + if (res >=0 && (pages[nr_pages - 1]->index >> shift) == index)
> + for (i = 0; i < nr_pages; i++)
> + SetPageUptodate(pages[i]);
> +
> + for (i = 0; i < nr_pages; i++) {
> + unlock_page(pages[i]);
> + put_page(pages[i]);
> + }
> + }
> +
> + kfree(actor);
> + return;
> +
> +skip_pages:
> + for (i = 0; i < nr_pages; i++) {
> + unlock_page(pages[i]);
> + put_page(pages[i]);
> + }
> +
> + kfree(actor);
> +out:
> + kfree(pages);
> +}
>
>  const struct address_space_operations squashfs_aops = {
> - .readpage = squashfs_readpage
> + .readpage = squashfs_readpage,
> + .readahead = squashfs_readahead
>  };
> --
> 2.31.0

[-- Attachment #2: 0001-WIP-squashfs-implement-readahead.patch --]
[-- Type: text/x-patch, Size: 3190 bytes --]

From 03558dcaab93ed3c32498eb70c7f2b1382b218d6 Mon Sep 17 00:00:00 2001
From: Hsin-Yi Wang <hsinyi@chromium.org>
Date: Sun, 10 Oct 2021 21:22:25 +0800
Subject: [PATCH] squashfs: implement readahead

Implement readahead callback for squashfs. It will read datablocks
which cover pages in readahead request. For a few cases it will
not mark page as uptodate, including:
- file end is 0.
- current batch of pages isn't in the same datablock or not enough in a
  datablock.
Otherwise pages will be marked as uptodate. The unhandled pages will be
updated by readpage later.

Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
---
 fs/squashfs/file.c | 72 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 71 insertions(+), 1 deletion(-)

diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index 89d492916dea..20ec48cf97c5 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -39,6 +39,7 @@
 #include "squashfs_fs_sb.h"
 #include "squashfs_fs_i.h"
 #include "squashfs.h"
+#include "page_actor.h"
 
 /*
  * Locate cache slot in range [offset, index] for specified inode.  If
@@ -494,7 +495,76 @@ static int squashfs_readpage(struct file *file, struct page *page)
 	return 0;
 }
 
+static void squashfs_readahead(struct readahead_control *ractl)
+{
+	struct inode *inode = ractl->mapping->host;
+	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+	size_t mask = (1UL << msblk->block_log) - 1;
+	size_t shift = msblk->block_log - PAGE_SHIFT;
+	loff_t req_end = readahead_pos(ractl) + readahead_length(ractl);
+	loff_t start = readahead_pos(ractl) &~ mask;
+	size_t len = readahead_length(ractl) + readahead_pos(ractl) - start;
+	struct squashfs_page_actor *actor;
+	unsigned int nr_pages = 0;
+	struct page **pages;
+	u64 block = 0;
+	int bsize, res, i, index;
+	int file_end = i_size_read(inode) >> msblk->block_log;
+	int max_pages = 1UL << shift;
+
+	readahead_expand(ractl, start, (len | mask) + 1);
+
+	if (readahead_pos(ractl) + readahead_length(ractl) < req_end)
+		return;
+
+	nr_pages = readahead_count(ractl);
+	pages = kmalloc_array(nr_pages, sizeof(void *), GFP_KERNEL);
+	if (!pages)
+		return;
+
+	actor = squashfs_page_actor_init_special(pages, nr_pages, 0);
+	if (!actor)
+		goto out;
+
+	for (;;) {
+		nr_pages = __readahead_batch(ractl, pages, max_pages);
+		if (!nr_pages)
+			break;
+
+		if (readahead_pos(ractl) >= i_size_read(inode) ||
+		    file_end == 0 || nr_pages < max_pages)
+			goto skip_pages;
+
+		index = pages[0]->index >> shift;
+		bsize = read_blocklist(inode, index, &block);
+		res = squashfs_read_data(inode->i_sb, block, bsize, NULL,
+					 actor);
+
+		if (res >=0 && (pages[nr_pages - 1]->index >> shift) == index)
+			for (i = 0; i < nr_pages; i++)
+				SetPageUptodate(pages[i]);
+
+		for (i = 0; i < nr_pages; i++) {
+			unlock_page(pages[i]);
+			put_page(pages[i]);
+		}
+	}
+
+	kfree(actor);
+	return;
+
+skip_pages:
+	for (i = 0; i < nr_pages; i++) {
+		unlock_page(pages[i]);
+		put_page(pages[i]);
+	}
+
+	kfree(actor);
+out:
+	kfree(pages);
+}
 
 const struct address_space_operations squashfs_aops = {
-	.readpage = squashfs_readpage
+	.readpage = squashfs_readpage,
+	.readahead = squashfs_readahead
 };
-- 
2.31.0