From 0ff1a185620460a84042b4e99a1376ba2cf6de10 Mon Sep 17 00:00:00 2001 From: Neil Brown Date: Mon, 5 Dec 2005 05:56:42 +0000 Subject: [PATCH] Guides on how to use mdadm with initramfs Signed-off-by: Neil Brown --- ChangeLog | 2 + Makefile | 3 +- README.initramfs | 123 +++++++++++++++++++++++++++++++++++++++++++++++ inventory | 2 + mkinitramfs | 57 ++++++++++++++++++++++ 5 files changed, 186 insertions(+), 1 deletion(-) create mode 100644 README.initramfs create mode 100644 mkinitramfs diff --git a/ChangeLog b/ChangeLog index 9c9b4f9..4390e4c 100644 --- a/ChangeLog +++ b/ChangeLog @@ -19,6 +19,8 @@ Changes Prior to this release isn't needed, and is a problem if the crash was while the metadata was being updated. - Support --update==uuid + - Added README.initramfs and mkinitramfs to help people use an + initram for starting md arrays at boot. Changes Prior to 2.1 release - Fix assembling of raid10 array when devices are missing. diff --git a/Makefile b/Makefile index 81102ea..0ff1adf 100644 --- a/Makefile +++ b/Makefile @@ -131,7 +131,8 @@ install : mdadm mdadm.8 md.4 mdadm.conf.5 clean : rm -f mdadm $(OBJS) core *.man mdadm.tcc mdadm.uclibc mdadm.static *.orig *.porig *.rej *.alt \ - mdassemble mdassemble.static mdassemble.uclibc mdassemble.klibc swap_super + mdassemble mdassemble.static mdassemble.uclibc mdassemble.klibc swap_super \ + init.cpio.gz dist : clean ./makedist diff --git a/README.initramfs b/README.initramfs new file mode 100644 index 0000000..8f9b8dd --- /dev/null +++ b/README.initramfs @@ -0,0 +1,123 @@ +Assembling md arrays at boot time. +--------------------------------- +December 2005 + +These notes apply to 2.6 kernels only and, in some cases, +to 2.6.15 or later. + +Md arrays can be assembled at boot time using the 'autodetect' functionality +which is triggered by storing components of an array in partitions of type +'fd' - Linux Raid Autodetect. +They can also be assembled by specifying the component devices in a +kernel parameter such as + md=0,/dev/sda,/dev/sdb +In this case, /dev/md0 will be assembled (because of the 0) from the listed +devices. + +These mechanisms, while useful, do not provide complete functionality +and are unlikely to be extended. The preferred way to assemble md +arrays at boot time is using 'mdadm' or 'mdassemble' (which is a +trimmed-down mdadm). To assemble an array which contains the root +filesystem, mdadm needs to be run before that filesystem is mounted, +and so needs to be run from an initial-ram-fs. It is how this can +work that is the primary focus of this document. + +It should be noted up front that only the array containing the root +filesystem should be assembled from the initramfs. Any other arrays +should be assembled under the control of files on the main filesystem +as this enhanced flexibility and maintainability. + +A minimal initramfs for assembling md arrays can be created using 3 +files and one directory. These are: + +/bin Directory +/bin/mdadm statically linked mdadm binary +/bin/busybox statically linked busybox binary +/bin/sh hard link to /bin/busybox +/init a shell script which call mdadm appropriately. + +An example init script is: + +============================================== +#!/bin/sh + +echo 'Auto-assembling boot md array' +mkdir /proc +mount -t proc proc /proc +if [ -n "$rootuuid" ] +then arg=--uuid=$rootuuid +elif [ -n "$mdminor" ] +then arg=--super-minor=$mdminor +else arg=--super-minor=0 +fi +echo "Using $arg" +mdadm -Acpartitions $arg --auto=part /dev/mda +cd / +mount /dev/mda1 /root || mount /dev/mda /root +umount /proc +cd /root +exec chroot . /sbin/init < /dev/console > /dev/console 2>&1 +============================================= + +This could certainly be extended, or merged into a larger init script. +Though tested and in production use, it is not presented here as +"The Right Way" to do it, but as a useful example. +Some key points are: + + /proc needs to be mounted so that /proc/partitions can be accessed + by mdadm, and so that /proc/filesystems can be accessed by mount. + + The uuid of the array can be passed in as a kernel parameter + (rootuuid). As the kernel doesn't use this value, it is made available + in the environment for /init + + If no uuid is given, we default to md0, (--super-minor=0) which is a + commonly used to store the root filesystem. This may not work in + all situations. + + We assemble the array as a partitionable array (/dev/mda) even if we + end up using the whole array. There is no cost in using the partitionable + interface, and in this context it is simpler. + + We try mounting both /dev/mda1 and /dev/mda as they are the most like + part of the array to contain the root filesystem. + + The --auto flag is given to mdadm so that it will create /dev/md* + files automatically. This is needed as /dev will not contain + and md files, and udev will not create them (as udev only created device + files after the device exists, and mdadm need the device file to create + the device). Note that the created md files may not exist in /dev + of the mounted root filesystem. This needs to be deal with separately + from mdadm - possibly using udev. + + We do not need to create device files for the components which will + be assembled into /dev/mda. mdadm finds the major/minor numbers from + /proc/partitions and creates a temporary /dev file if one doesn't already + exist. + +The script "mkinitramfs" which is included with the mdadm distribution +can be used to create a minimal initramfs. It creates a file called +'init.cpio.gz' which can be specified as an 'initrd' to lilo or grub +(or whatever boot loader is being used). + + + + +Resume from an md array +----------------------- + +If you want to make use of the suspend-to-disk/resume functionality in Linux, +and want to have swap on an md array, you will need to assemble the array +before resume is possible. +However, because the array is active in the resumed image, you do not want +anything written to any drives during the resume process, such as superblock +updates or array resync. + +This can be achieved in 2.6.15-rc1 and later kernels using the +'start_readonly' module parameter. +Simply include the command + echo 1 > /sys/module/md_mod/parameters/start_ro +before assembling the array with 'mdadm'. +You can then echo + 9:0 +or whatever is appropriate to /sys/power/resume to trigger the resume. diff --git a/inventory b/inventory index 0d6cac7..1617b08 100644 --- a/inventory +++ b/inventory @@ -15,6 +15,7 @@ Makefile Manage.c Monitor.c Query.c +README.initramfs ReadMe.c TODO bitmap.c @@ -39,6 +40,7 @@ mdopen.c mdstat.c misc/ misc/syslog-events +mkinitramfs raid5extend.c super0.c super1.c diff --git a/mkinitramfs b/mkinitramfs new file mode 100644 index 0000000..fdb15c9 --- /dev/null +++ b/mkinitramfs @@ -0,0 +1,57 @@ +#!/bin/sh + +# make sure we are being run in the right directory... +if [ -f mkinitramfs ] +then : +else + echo >&2 mkinitramfs must be run from the mdadm source directory. + exit 1 +fi +if [ -f /bin/busybox ] +then : good, it exists + case `file /bin/busybox` in + *statically* ) : good ;; + * ) echo >&2 mkinitramfs: /bin/busybox is not statically linked: cannot proceed. + exit 1 + esac +else + echo >&2 "mkinitramfs: /bin/busybox doesn't exist - please install it statically linked." + exit 1 +fi + +rm -rf initramfs +mkdir initramfs +mkdir initramfs/bin +make mdadm.static +cp mdadm.static initramfs/bin/mdadm +cp /bin/busybox initramfs/bin/busybox +ln initramfs/bin/busybox initramfs/bin/sh +cat <<- END > initramfs/init + #!/bin/sh + + echo 'Auto-assembling boot md array' + mkdir /proc + mount -t proc proc /proc + if [ -n "$rootuuid" ] + then arg=--uuid=$rootuuid + elif [ -n "$mdminor" ] + then arg=--super-minor=$mdminor + else arg=--super-minor=0 + fi + echo "Using $arg" + mdadm -Acpartitions $arg --auto=part /dev/mda + cd / + mount /dev/mda1 /root || mount /dev/mda /root + umount /proc + cd /root + exec chroot . /sbin/init < /dev/console > /dev/console 2>&1 +END +chmod +x initramfs/init + +(cd initramfs + find init bin | cpio -o -H newc | gzip --best +) > init.cpio.gz +rm -rf initramfs +ls -l init.cpio.gz + +