sonic-buildimage/files/initramfs-tools/union-mount.j2
Samuel Angebault fa95ebcaae Add optional zram compression for docker_inram
Some devices running SONiC have a small storage device (2G and 4G mainly)
The SONiC image growth over time has made it impossible to install
2 images on a single device.
Some mitigations have been implemented in the past for some devices but
there is a need to do more.

One such mitigation is `docker_inram` which creates a `tmpfs` and
extracts `dockerfs.tar.gz` in it.
This all happens in the SONiC initramfs and by ensuring the installation
process does not extract `dockerfs.tar.gz` on the flash but keep the file as is.

This mitigation does a tradeoff by using more RAM to reduce the disk footprint.
It however creates new issues for devices with 4G of system memory since
the extracted `dockerfs.tar.gz` nears the 1.6G.
Considering debian upgrades (with dual base images) and the continuous
stream of features this is only going to get bigger.

This change introduces an alternative to the `tmpfs` by allowing a system
to extract the `dockerfs.tar.gz` inside a `zram` device thus bringing
compression in play at the detriment of performance.

Introduce 2 new optional kernel parameters to be consumed by SONiC initramfs.
 - `docker_inram_size` which represent the max physical size of the
   `zram` or `tmpfs` volume (defaults to DOCKER_RAMFS_SIZE)
 - `docker_inram_algo` which is the method to use to extract the
   `dockerfs.tar.gz` (defaults to `tmpfs`)
   other values are considered to be compression algorithm for `zram`
   (e.g `zstd`, `zlo-rle`, `lz4`)

Refactored the logic to mount the docker fs in the SONiC initramfs under
the `union-mount` script.
Moved the code into a function to make it cleaner and separated the
inram volume creation and docker extraction.

On Arista platform with a flash smaller or equal to 4GB set
`docker_inram_algo` to `zstd` which produces the best compression ratio
at the detriment of a slower write performance and a similar read
performance to other `zram` compression algorithms.
2023-05-18 14:21:52 -07:00

247 lines
8.4 KiB
Django/Jinja

#!/bin/sh -e
PREREQS="varlog"
prereqs() { echo "$PREREQS"; }
case $1 in
prereqs)
prereqs
exit 0
;;
esac
docker_inram=false
docker_inram_algo=tmpfs
docker_inram_size={{ DOCKER_RAMFS_SIZE }}
logs_inram=false
secureboot=false
bootloader=generic
in_kdump=false
varlog_size=0
# Extract kernel parameters
for x in $(cat /proc/cmdline); do
case "$x" in
Aboot=*)
bootloader=aboot
;;
docker_inram=on)
docker_inram=true
;;
docker_inram_algo=*)
docker_inram_algo="${x#docker_inram_algo=}"
;;
docker_inram_size=*)
docker_inram_size="${x#docker_inram_size=}"
;;
logs_inram=on)
logs_inram=true
;;
varlog_size=*)
varlog_size="${x#varlog_size=}"
;;
secure_boot_enable=[y1])
secureboot=true
docker_inram=true
;;
platform=*)
platform_flag="${x#platform=}"
;;
systemd.unit=kdump-tools.service)
in_kdump=true
;;
esac
done
set_tmpfs_log_partition_size()
{
if [ $varlog_size -gt 0 ]; then
# Use the varlog_size passed in from command line
varlogsize=$varlog_size
else
varlogsize=128
# set varlogsize to existing var-log.ext4 size
if [ -f ${rootmnt}/host/disk-img/var-log.ext4 ]; then
varlogsize=$(ls -l ${rootmnt}/host/disk-img/var-log.ext4 | awk '{print $5}')
varlogsize=$(($varlogsize/1024/1024))
fi
fi
# make sure varlogsize is between 5% to 10% of total memory size
memkb=$(grep MemTotal /proc/meminfo | awk '{print $2}')
memmb=$(($memkb/1024))
minsize=$(($memmb*5/100))
maxsize=$(($memmb*10/100))
if [ $minsize -ge $varlogsize ]; then
varlogsize=$minsize
fi
if [ $maxsize -le $varlogsize ]; then
varlogsize=$maxsize
fi
}
remove_not_in_allowlist_files()
{
local allowlist_file="$1"
local targeted_dir="$2"
local allowlist_pattern_file=/tmp/allowlist_paths.pattern
# Return if the allowlist file does not exist
if ! test -f "${allowlist_file}"; then
echo "The file ${allowlist_file} is missing, failed to mount rw folder." 1>&2
exit 1
fi
# Set the grep pattern file, remove the blank line in config file
awk -v rw_dir="$targeted_dir" 'NF {print rw_dir"/"$0"$"}' ${allowlist_file} > $allowlist_pattern_file
# Find the files in the rw folder, and remove the files not in the allowlist
find ${targeted_dir} -type f | grep -v -f $allowlist_pattern_file | xargs /bin/rm -f
rm -f $allowlist_pattern_file
}
mount_docker_inram()
{
if [ "$docker_inram_algo" = "tmpfs" ]; then
echo "Creating tmpfs to extract {{ FILESYSTEM_DOCKERFS }}"
mount -t tmpfs -o "rw,nodev,size=$docker_inram_size" tmpfs "${rootmnt}/var/lib/docker"
else
echo "Creating zram to extract {{ FILESYSTEM_DOCKERFS }}"
modprobe zram num_devices=0
# create new zram device
local zid="$(cat /sys/class/zram-control/hot_add)"
local zname="zram$zid"
# attempt to use desired algorithm
if ! echo $docker_inram_algo > /sys/block/$zname/comp_algorithm 2>/dev/null; then
echo "zram algorithm $docker_inram_algo is not supported"
echo "using default instead: $(cat /sys/block/$zname/comp_algorithm)"
fi
echo $docker_inram_size > /sys/block/$zname/disksize
# create filesystem on the newly created zram block device
mkfs.ext4 -m 0 -L dockerfs -O '^has_journal' -q /dev/$zname
mount -o rw,nodev /dev/$zname "${rootmnt}/var/lib/docker"
fi
}
extract_dockerfs()
{
echo "Extracting {{ FILESYSTEM_DOCKERFS }}"
if [ -f "${rootmnt}/host/$image_dir/{{ FILESYSTEM_DOCKERFS }}" ] && [ "$secureboot" = false ]; then
# Extract dockerfs.tar.gz into /var/lib/docker unless the system booted with secureboot
# In secureboot dockerfs.tar.gz cannot be trusted as it does not have a signature
tar xz --numeric-owner -f ${rootmnt}/host/$image_dir/{{ FILESYSTEM_DOCKERFS }} -C ${rootmnt}/var/lib/docker
elif [ "$bootloader" = "aboot" ] && unzip -l "$swi_path" | grep -q {{ FILESYSTEM_DOCKERFS }}; then
# Aboot swi images also support extracting dockerfs.tar.gz directly from them
unzip -qp "$swi_path" {{ FILESYSTEM_DOCKERFS }} | tar xz --numeric-owner -C ${rootmnt}/var/lib/docker
else
# Warn but allow the system to boot to at least have ssh access
echo "No {{ FILESYSTEM_DOCKERFS }} to extract, SONiC will be broken"
fi
}
mount_docker()
{
if [ "$in_kdump" = true ]; then
# There is no point in mounting the docker filesystem in kdump environment
# Especially when there is some space mitigation in place
return
fi
if [ "$docker_inram" = true ]; then
# Create an in memory filesystem (tmpfs, zram) and extract dockerfs.tar.gz
mount_docker_inram
extract_dockerfs
else
# Mount the working directory of docker engine in the raw partition, bypass the overlay
mount --bind ${rootmnt}/host/$image_dir/{{ DOCKERFS_DIR }} ${rootmnt}/var/lib/docker
fi
}
## Mount the overlay file system: rw layer over squashfs
image_dir=$(cat /proc/cmdline | sed -e 's/.*loop=\(\S*\)\/.*/\1/')
rw_dir=${rootmnt}/host/$image_dir/rw
work_dir=${rootmnt}/host/$image_dir/work
mkdir -p "$rw_dir"
mkdir -p "$work_dir"
## Remove the files not in allowlist in the rw folder
if [ "$secureboot" = true ] && [ "$in_kdump" = false ]; then
if [ "$bootloader" = "aboot" ]; then
swi_path="${rootmnt}/host/$(sed -E 's/.*loop=([^ ]+).*/\1/' /proc/cmdline)"
unzip -q "$swi_path" allowlist_paths.conf -d /tmp
allowlist_file=/tmp/allowlist_paths.conf
else
allowlist_file=${rootmnt}/host/$image_dir/allowlist_paths.conf
fi
remove_not_in_allowlist_files "$allowlist_file" "$rw_dir"
## Remove the executable permission for all the files in rw folder except home folder
find ${rw_dir} -type f -not -path ${rw_dir}/home -exec chmod a-x {} +
fi
mount -n -o lowerdir=${rootmnt},upperdir=${rw_dir},workdir=${work_dir} -t overlay root-overlay ${rootmnt}
## Check if the root block device is still there
[ -b ${ROOT} ] || mdev -s
case "${ROOT}" in
ubi*)
mtd=$(cat /proc/cmdline | sed -e 's/.*ubi.mtd=\([0-9]\) .*/\1/')
if [ ! -f /dev/${ROOT}_0 ]; then
ubiattach /dev/ubi_ctrl -m $mtd 2>dev/null || true
fi
mount -t ubifs /dev/${ROOT}_0 ${rootmnt}/host
;;
*)
## Mount the raw partition again
mount -t ext4 ${ROOT} ${rootmnt}/host
tune2fs -m 0 -r 0 ${ROOT}
;;
esac
## Mount the docker storage path
mkdir -p ${rootmnt}/var/lib/docker
mount_docker
## Mount the boot directory in the raw partition, bypass the overlay
mkdir -p ${rootmnt}/boot
# make sure that the boot folder exists before attempting a mount
mkdir -p ${rootmnt}/host/$image_dir/boot
mount --bind ${rootmnt}/host/$image_dir/boot ${rootmnt}/boot
## Mount loop device or tmpfs for /var/log
if $logs_inram; then
# NOTE: some platforms, when reaching initramfs stage, have a small
# limit of mounting tmpfs partition, potentially due to amount
# of RAM available in this stage. Therefore limiting the size
# set for tmpfs partitions.
#
# Another reason for using tmpfs /var/log partition is:
# Some platforms have a small flash and therefore the log partition takes valuable space.
# To improve the longevity of these devices storing the logs in memory will permit more
# SONiC image growth before being bottlenecked.
set_tmpfs_log_partition_size
mount -t tmpfs -o rw,nosuid,nodev,size=${varlogsize}M tmpfs ${rootmnt}/var/log
if [ -f ${rootmnt}/host/disk-img/var-log.ext4 ]; then
rm -rf ${rootmnt}/host/disk-img/var-log.ext4
fi
else
if [ -f ${rootmnt}/host/disk-img/var-log.ext4 ]; then
fsck.ext4 -v -p ${rootmnt}/host/disk-img/var-log.ext4 2>&1 | gzip -c >> /tmp/fsck.log.gz
mount -t ext4 -o loop,rw ${rootmnt}/host/disk-img/var-log.ext4 ${rootmnt}/var/log
fi
fi
## fscklog file: /tmp will be lost when overlayfs is mounted
if [ -f /tmp/fsck.log.gz ]; then
mv /tmp/fsck.log.gz ${rootmnt}/var/log
fi
## ssd-fw-upgrade log file: /tmp will be lost when overlayfs is mounted
if [ -f /tmp/ssd-fw-upgrade.log.gz ]; then
mv /tmp/ssd-fw-upgrade.log.gz ${rootmnt}/var/log
fi