石头盘VPS改造2: LVM + Bcache + ZSwap + Zram

转为LVM + Bcache

• 安装dracut

• 配置好分区相关的工具，通过rd.break选项进入initramfs shell

转为LVM + Bcache

• /usr/lib/dracut/modules.d/99misty-utils/module-setup.sh

#!/bin/bash
check() {
    return 0
}

depends() {
    echo bash
    echo busybox_post
    return 0
}

install() {
    for cmd in lsblk blkid fdisk sfdisk cfdisk parted wipefs \
               mkfs mkfs.ext4 mkfs.xfs mkfs.vfat mkfs.btrfs \
               mount umount losetup dd hexdump \
               xfs_admin xfs_copy xfs_estimate xfs_fsr xfs_info xfs_logprint xfs_metadump xfs_ncheck xfs_repair xfs_scrub xfs_spaceman xfs_bmap xfs_db xfs_freeze xfs_growfs xfs_io xfs_mdrestore xfs_mkfile xfs_quota xfs_rtcp xfs_scrub_all \
               nilfs-clean nilfs_cleanerd nilfs-resize nilfs-tune \
               reiserfsck reiserfstune tune2fs tunefs.reiserfs \
               resize2fs \
               lvm pvcreate pvscan vgcreate vgscan vgchange lvcreate lvremove lvs vgs pvs \
               grub-bios-setup grub-fstest grub-kbdcomp grub-mkconfig grub-mkimage grub-mkpasswd-pbkdf2 grub-mkstandalone grub-probe grub-script-check \
               grub-editenv grub-glue-efi grub-macbless grub-mkdevicemap grub-mklayout grub-mkrelpath grub-mount grub-reboot grub-set-default \
               grub-file grub-install grub-menulst2cfg grub-mkfont grub-mknetdir grub-mkrescue grub-ntldr-img grub-render-label grub-syslinux2cfg \
                           tee wc sort uniq grep find xargs \
                           vim nano awk \
                           pv \
                           ; do
        inst $(command -v $cmd) || true
    done
}

• /usr/lib/dracut/modules.d/90python3/module-setup.sh

#!/bin/bash

check() { return 0; }
depends() { echo bash; return 0; }

install() {
  export UV=/usr/local/bin/uv
  export UV_DIR=/opt/uv
  export UV_TOOL_DIR=$UV_DIR/tools
  export UV_TOOL_BIN_DIR=$UV_DIR/tools
  export UV_PYTHON_INSTALL_DIR=$UV_DIR/python
  $UV python install 3.9
  inst "$UV"
  #inst_dir "$UV_DIR"

    src=$UV_DIR
    # 先确保根目录存在
    inst_dir "$src"

    # 递归遍历：目录 -> inst_dir；文件/链接 -> inst
    # -L 跟随软链接把目标也带进去（你想“全拷贝”一般需要这个）
    while IFS= read -r -d '' p; do
        # 跳过根本身（已经 inst_dir 过）
        [[ "$p" == "$src" ]] && continue

        if [[ -d "$p" ]]; then
            inst_dir "$p"
        else
            # inst 会把文件放到同路径；若是 ELF，dracut 会自动拉依赖
            inst "$p"
        fi
    done < <(find -L "$src" -print0)
}

• 先转为LVM

# 挂载boot分区，用来存日志
mkdir boot
mount /dev/sda2 boot

# 转换为LVM
/opt/uv/tools/bin/blocks --debug to-lvm --vg-name vg0 /dev/sda1 2>&1 | tee -a boot/blocks.log

• 然后是bcache

# 确保我们的vg里，只有目标LV是active的
lvchange -an
lvchange -ay /dev/vg0/Root

# 转换为Bcache（需要重启后再来一次）
/opt/uv/tools/bin/blocks --debug to-bcache /dev/vg0/Root 2>&1 | tee -a boot/blocks2.log

用Zram作为bcache caching device

• 如果backing device没挂到caching device上，那会自动出现/dev/bcacheX
• 有两种情况，一种是你从来没挂过，这个时候state显示为no cache
• 另一种是你非writeback模式时在cache device丢了之后手动echo 1 > /sys/block/bcacheX/bcache/running，这时候state为clean

• 否则他会注册到/sys/block/XXX/bcache下面，需要你自己手动echo到running才会激活/dev节点

• cache device 需要register才能生效，register之后，会自动attach到相同的cache set uuid的backing device上并生效

• 如果是writeback模式
• 如果cache device丢了，state会显示inconsistent，直接echo到running不会改变这个状态，只会让他无cache启动
• 此时detach后state会回到no cache状态
• 再attach后会进入dirty状态（dirty只有writeback模式的时候才会出现）

• 如何判断是否启用了cache？
• state其实并不能正确给出是否启用，只能给出一个状态
• 可以通过看/sys/block/bcacheX/bcache下是否存在cache目录来判断是否启用
• 同时cache也会指向/sys/fs/bcache/XXXX的cache set文件夹

• /usr/lib/dracut/modules.d/70zram/module-setup.sh

#!/bin/bash

check() { return 0; }
depends() { echo bcache; return 0; }

installkernel() {
  # 需要 zram、loop，bcache相关的东西由bcache dracut模块提供
  instmods zram loop
}

install() {
  # 工具：含 losetup、zramctl 和 LVM 全家桶
  echo "PATH during install: $PATH" >>/tmp/dracut-debug.log
  ls -al /usr/sbin/losetup >>/tmp/dracut-debug.log 2>&1
  command -v losetup >>/tmp/dracut-debug.log 2>&1 || echo "losetup not found" >>/tmp/dracut-debug.log
  inst_multiple zramctl losetup \
               make-bcache bcache-super-show \
               dmsetup wipefs blockdev awk sed tee grep udevadm

  # 挂载 root 之前执行
  inst_hook initqueue/finished 99 "$moddir/zram-bcache.sh"
}

• /usr/lib/dracut/modules.d/70zram/zram-bcache.sh

#!/bin/sh
# 阶段：initqueue/finished(00)
# 策略：一次触发只检查一次；成功或放弃时写锁

set -eu

# ===== 日志 =====
LOG_DIR=/run/initramfs
LOG_FILE=$LOG_DIR/70zram.log
LOCK_DONE=$LOG_DIR/70zram.done
mkdir -p "$LOG_DIR"
exec > >(tee -a "$LOG_FILE") 2>&1
set -x

ts() { date +%H:%M:%S 2>/dev/null || echo time; }
log() { echo "[70zram $(ts)] $*"; }

# ===== 参数 =====
CSET_UUID="${CSET_UUID:-2ffef9c2-b4ff-493f-8f65-7e899231dbcd}"
for tok in $(cat /proc/cmdline); do
  case "$tok" in
    rd.zram.csetuuid=*) CSET_UUID="${tok#rd.zram.csetuuid=}";;
  esac
done

CACHE_SZ="${CACHE_SZ:-2G}"

log "Bcache cset-uuid: ${CSET_UUID}, zram cache size: ${CACHE_SZ}"

activate_all_bcache() {
  : "${CSET_UUID:?CSET_UUID is not set}"

  for d in /sys/block/*; do
    [ -d "$d" ] || continue

    run="$d/bcache/running"
    [ -w "$run" ] || continue

    cur="$(cat "$run" 2>/dev/null | tr -d ' \t\r\n' || true)"
    if [ "$cur" = "0" ]; then
      # 仅在 running=0 时才置为 1
      echo 1 > "$run"
      sleep 2 # wait for bcache to init
    fi
    detach="$d/bcache/detach"
    attach="$d/bcache/attach"

    state="$(cat "$d/bcache/state" || true)"
    if [ "$state" = "no cache" ]; then
      # 先 detach（不存在/不可写就跳过）
      if [ -w "$detach" ]; then
        echo 1 | tee "$detach" 2>/dev/null || true
      fi
    fi

    # 再 attach 到指定 CSET_UUID（不存在/不可写就跳过）
    if [ -w "$attach" ]; then
      echo "$CSET_UUID" | tee "$attach" || true
    fi

  done
}

# 已完成就直接返回
[ -f "$LOCK_DONE" ] && {
    activate_all_bcache
    log "already done; skip";
    exit 0;
}

# “完成并激活”帮助函数
finish_and_activate() {
  touch "$LOCK_DONE"
  activate_all_bcache
}

# ===== B) zram -> loop(512B) =====
modprobe zram || true
sleep 2
command -v zramctl 2>&1 || { log "zramctl missing; done & activate without cache."; finish_and_activate; exit 0; }

ZDEV="$(zramctl -f -s "$CACHE_SZ" -a lz4)" || { log "zramctl failed; done & activate without cache."; finish_and_activate; exit 0; }
log "zram: ${ZDEV}"

modprobe loop || true
command -v losetup >/dev/null 2>&1 || { log "losetup missing; done & activate without cache."; finish_and_activate; exit 0; }

LOOPDEV="$(losetup --sector-size=512 -fP --show "$ZDEV" 2>/dev/null)" || { log "losetup failed; done & activate without cache."; finish_and_activate; exit 0; }
log "loop on zram: ${LOOPDEV}"
ln -sf "$(basename "$LOOPDEV")" /dev/cachebrd

[ -b "$LOOPDEV" ] || { log "loop not block; done & activate without cache."; finish_and_activate; exit 0; }
SZ="$(blockdev --getsize64 "$LOOPDEV" 2>/dev/null || echo 0)"
[ "$SZ" -gt 0 ] || { log "loop size=0; done & activate without cache."; finish_and_activate; exit 0; }
log "loop size: $SZ bytes"

# ===== C) 创建bcache cache dev =====
modprobe bcache || true
sleep 2

wipefs -a "$LOOPDEV" || true

make-bcache -C "$LOOPDEV" --cset-uuid "$CSET_UUID"

echo "$LOOPDEV" | tee /sys/fs/bcache/register 2>&1 || { log "failed to register bcache cache device"; finish_and_activate; exit 0; }

finish_and_activate
exit 0

在initramfs里面启用网络

其实直接用这个项目就可以了：

dracut-sshd

Github

dracut-sshd

Owner

gsauthof

Updated

Jan 2, 2026

• 首先安装dracut-network包

• 然后安装这个项目

• 然后按照这个文档配置网络，我是这么配到/etc/default/grub里面的 https://man7.org/linux/man-pages/man7/dracut.cmdline.7.html

GRUB_CMDLINE_LINUX_DEFAULT="rd.shell rd.debug rd.timeout=90 rd.neednet=1 ifname=bootnet:00:01:02:12:23:45 ip=192.168.1.112::192.168.1.1:255.255.255.0:box:bootnet:none nameserver=1.1.1.1"

• 这样就可以在initramfs里面上网了！
• 记得include一些curl之类的命令（

• 不过这样打出来的镜像虽然可以上网，并且开了ssh，但是登陆不上去，因为root用户在/etc/shadow中没有密码，导致sshd认为root用户locked了
• 可以自己手动在initramfs里面用vim来随便写一个密码，比如$1$salt$123456789012345678901/
• 也可以改镜像

关机自动回写writeback buffer

• /etc/systemd/system/detach_writeback_bcache.service
• 又被gpt坑了

[Unit]
Description=bcache: detach (flush writeback) then attach back at shutdown
After=local-fs.target boot.mount boot.automount
Wants=local-fs.target

[Service]
Type=oneshot
RemainAfterExit=yes
ExecStart=/bin/true
ExecStop=/usr/local/bin/detach_writeback_bcache
TimeoutStopSec=infinity

[Install]
WantedBy=sysinit.target

• /usr/local/bin/detach_writeback_bcache

#!/usr/bin/env bash
set -euo pipefail

LOG_FILE=/boot/detach_writeback_bcache.log
exec > >(tee -a "$LOG_FILE") 2>&1

log() { echo "[bcache-shutdown] $*"; }

# 可调：轮询间隔/打印间隔（秒）
POLL_INTERVAL="${BCACHE_POLL_INTERVAL:-1}"

human_to_bytes() {
  # 输入如：0.0k / 12.3M / 4.0G / 1024
  # 输出近似 bytes（用于判断是否为 0）
  awk '
    function mul(u) {
      if (u=="k" || u=="K") return 1024
      if (u=="M") return 1024*1024
      if (u=="G") return 1024*1024*1024
      if (u=="T") return 1024*1024*1024*1024
      if (u=="P") return 1024*1024*1024*1024*1024
      if (u=="E") return 1024*1024*1024*1024*1024*1024
      return 1
    }
    {
      v=$1
      # 末尾单位
      u=substr(v, length(v), 1)
      if (u ~ /[0-9]/) { printf "%.0f\n", v+0; exit }
      n=substr(v, 1, length(v)-1) + 0
      printf "%.0f\n", n * mul(u)
    }
  '
}

main() {
  shopt -s nullglob

  for bcdir in /sys/class/block/bcache*/bcache; do
    [[ -d "$bcdir" ]] || continue

    dev="$(basename "$(dirname "$bcdir")")"

    # 你要求：没有 cache => 实际上没 cache，无需处理
    if [[ ! -e "$bcdir/cache" ]]; then
      log "$dev: no cache link; skip"
      continue
    fi

    state="$(cat "$bcdir/state" 2>/dev/null || echo "")"
    if [[ "$state" != "dirty" ]]; then
      log "$dev: state=$state (not dirty); skip"
      continue
    fi

    # 从 cache symlink 解析 cacheset uuid（detach 前先记下来）
    cache_path="$(readlink -f "$bcdir/cache" || true)"
    if [[ -z "$cache_path" || ! -d "$cache_path" ]]; then
      log "$dev: cache link resolved to '$cache_path' (missing); skip"
      continue
    fi
    uuid="$(basename "$cache_path")"

    if [[ ! -w "$bcdir/detach" || ! -w "$bcdir/attach" ]]; then
      log "$dev: detach/attach not writable; skip"
      continue
    fi

    mode="$(cat "$bcdir/cache_mode" 2>/dev/null || echo "?")"
    dirty_data="$(cat "$bcdir/dirty_data" 2>/dev/null || echo "?")"
    log "$dev: begin flush via detach; cache_mode=$mode dirty_data=$dirty_data cacheset=$uuid"

    sync || true

    # 触发 detach（有些实现不阻塞，所以后面要循环确认）
    if ! (echo 1 | tee "$bcdir/detach" >/dev/null); then
      log "$dev: detach with '1' failed; retry with uuid"
      echo "$uuid" | tee "$bcdir/detach" >/dev/null
    fi

    # 循环检查：直到 dirty_data 归零 且 已经 no cache（或 cache 链接消失）
    t=0
    last_log=0
    while :; do
      # cache 是否还在（detach 完成后通常会消失）
      has_cache=0
      [[ -e "$bcdir/cache" ]] && has_cache=1

      state_now="$(cat "$bcdir/state" 2>/dev/null || echo "")"
      dirty_now="$(cat "$bcdir/dirty_data" 2>/dev/null || echo "0")"
      dirty_bytes="$(printf "%s\n" "$dirty_now" | human_to_bytes)"

      # 完成条件：脏数据为 0，且 detach 完成（cache symlink 消失或 state=no cache）
      if [[ "$dirty_bytes" -le 0 ]] && { [[ "$has_cache" -eq 0 ]] && [[ "$state_now" == "no cache" ]]; }; then
        log "$dev: flush complete after detach (state=$state_now dirty_data=$dirty_now)"
        break
      fi

      # 周期性打印进度
      log "$dev: waiting... state=$state_now dirty_data=$dirty_now has_cache=$has_cache"
      last_log=$t

      sleep "$POLL_INTERVAL"
      t=$((t + POLL_INTERVAL))
    done

    if false; then
      # attach 回去（前提：cacheset 目录还在）
      if [[ -d "/sys/fs/bcache/$uuid" ]]; then
        log "$dev: attach back to $uuid"
        echo "$uuid" | tee "$bcdir/attach" >/dev/null
        log "$dev: attach done"
      else
        log "$dev: cacheset $uuid missing; leave detached"
      fi
    fi
    sync || true
  done
}

main "$@"

剩余的配置