708a507af0
Refresh kernel patches for generic kernel 5.15 due to new backport version of MGLRU patchset. Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
126 lines
4.5 KiB
Diff
126 lines
4.5 KiB
Diff
From 686c3d4f71de9e0e7a27f03a5617a712385f90cd Mon Sep 17 00:00:00 2001
|
|
From: Yu Zhao <yuzhao@google.com>
|
|
Date: Fri, 30 Dec 2022 14:52:52 -0700
|
|
Subject: [PATCH 20/29] mm: support POSIX_FADV_NOREUSE
|
|
|
|
This patch adds POSIX_FADV_NOREUSE to vma_has_recency() so that the LRU
|
|
algorithm can ignore access to mapped files marked by this flag.
|
|
|
|
The advantages of POSIX_FADV_NOREUSE are:
|
|
1. Unlike MADV_SEQUENTIAL and MADV_RANDOM, it does not alter the
|
|
default readahead behavior.
|
|
2. Unlike MADV_SEQUENTIAL and MADV_RANDOM, it does not split VMAs and
|
|
therefore does not take mmap_lock.
|
|
3. Unlike MADV_COLD, setting it has a negligible cost, regardless of
|
|
how many pages it affects.
|
|
|
|
Its limitations are:
|
|
1. Like POSIX_FADV_RANDOM and POSIX_FADV_SEQUENTIAL, it currently does
|
|
not support range. IOW, its scope is the entire file.
|
|
2. It currently does not ignore access through file descriptors.
|
|
Specifically, for the active/inactive LRU, given a file page shared
|
|
by two users and one of them having set POSIX_FADV_NOREUSE on the
|
|
file, this page will be activated upon the second user accessing
|
|
it. This corner case can be covered by checking POSIX_FADV_NOREUSE
|
|
before calling mark_page_accessed() on the read path. But it is
|
|
considered not worth the effort.
|
|
|
|
There have been a few attempts to support POSIX_FADV_NOREUSE, e.g., [1].
|
|
This time the goal is to fill a niche: a few desktop applications, e.g.,
|
|
large file transferring and video encoding/decoding, want fast file
|
|
streaming with mmap() rather than direct IO. Among those applications, an
|
|
SVT-AV1 regression was reported when running with MGLRU [2]. The
|
|
following test can reproduce that regression.
|
|
|
|
kb=$(awk '/MemTotal/ { print $2 }' /proc/meminfo)
|
|
kb=$((kb - 8*1024*1024))
|
|
|
|
modprobe brd rd_nr=1 rd_size=$kb
|
|
dd if=/dev/zero of=/dev/ram0 bs=1M
|
|
|
|
mkfs.ext4 /dev/ram0
|
|
mount /dev/ram0 /mnt/
|
|
swapoff -a
|
|
|
|
fallocate -l 8G /mnt/swapfile
|
|
mkswap /mnt/swapfile
|
|
swapon /mnt/swapfile
|
|
|
|
wget http://ultravideo.cs.tut.fi/video/Bosphorus_3840x2160_120fps_420_8bit_YUV_Y4M.7z
|
|
7z e -o/mnt/ Bosphorus_3840x2160_120fps_420_8bit_YUV_Y4M.7z
|
|
SvtAv1EncApp --preset 12 -w 3840 -h 2160 \
|
|
-i /mnt/Bosphorus_3840x2160.y4m
|
|
|
|
For MGLRU, the following change showed a [9-11]% increase in FPS,
|
|
which makes it on par with the active/inactive LRU.
|
|
|
|
patch Source/App/EncApp/EbAppMain.c <<EOF
|
|
31a32
|
|
> #include <fcntl.h>
|
|
35d35
|
|
< #include <fcntl.h> /* _O_BINARY */
|
|
117a118
|
|
> posix_fadvise(config->mmap.fd, 0, 0, POSIX_FADV_NOREUSE);
|
|
EOF
|
|
|
|
[1] https://lore.kernel.org/r/1308923350-7932-1-git-send-email-andrea@betterlinux.com/
|
|
[2] https://openbenchmarking.org/result/2209259-PTS-MGLRU8GB57
|
|
|
|
Link: https://lkml.kernel.org/r/20221230215252.2628425-2-yuzhao@google.com
|
|
Signed-off-by: Yu Zhao <yuzhao@google.com>
|
|
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
|
|
Cc: Andrea Righi <andrea.righi@canonical.com>
|
|
Cc: Johannes Weiner <hannes@cmpxchg.org>
|
|
Cc: Michael Larabel <Michael@MichaelLarabel.com>
|
|
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
|
---
|
|
include/linux/fs.h | 2 ++
|
|
include/linux/mm_inline.h | 3 +++
|
|
mm/fadvise.c | 5 ++++-
|
|
3 files changed, 9 insertions(+), 1 deletion(-)
|
|
|
|
--- a/include/linux/fs.h
|
|
+++ b/include/linux/fs.h
|
|
@@ -167,6 +167,8 @@ typedef int (dio_iodone_t)(struct kiocb
|
|
/* File is stream-like */
|
|
#define FMODE_STREAM ((__force fmode_t)0x200000)
|
|
|
|
+#define FMODE_NOREUSE ((__force fmode_t)0x400000)
|
|
+
|
|
/* File was opened by fanotify and shouldn't generate fanotify events */
|
|
#define FMODE_NONOTIFY ((__force fmode_t)0x4000000)
|
|
|
|
--- a/include/linux/mm_inline.h
|
|
+++ b/include/linux/mm_inline.h
|
|
@@ -339,6 +339,9 @@ static inline bool vma_has_recency(struc
|
|
if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))
|
|
return false;
|
|
|
|
+ if (vma->vm_file && (vma->vm_file->f_mode & FMODE_NOREUSE))
|
|
+ return false;
|
|
+
|
|
return true;
|
|
}
|
|
|
|
--- a/mm/fadvise.c
|
|
+++ b/mm/fadvise.c
|
|
@@ -80,7 +80,7 @@ int generic_fadvise(struct file *file, l
|
|
case POSIX_FADV_NORMAL:
|
|
file->f_ra.ra_pages = bdi->ra_pages;
|
|
spin_lock(&file->f_lock);
|
|
- file->f_mode &= ~FMODE_RANDOM;
|
|
+ file->f_mode &= ~(FMODE_RANDOM | FMODE_NOREUSE);
|
|
spin_unlock(&file->f_lock);
|
|
break;
|
|
case POSIX_FADV_RANDOM:
|
|
@@ -107,6 +107,9 @@ int generic_fadvise(struct file *file, l
|
|
force_page_cache_readahead(mapping, file, start_index, nrpages);
|
|
break;
|
|
case POSIX_FADV_NOREUSE:
|
|
+ spin_lock(&file->f_lock);
|
|
+ file->f_mode |= FMODE_NOREUSE;
|
|
+ spin_unlock(&file->f_lock);
|
|
break;
|
|
case POSIX_FADV_DONTNEED:
|
|
if (!inode_write_congested(mapping->host))
|