import kexec-tools-2.0.22-14.el9
This commit is contained in:
CentOS Sources
Stepan Oksanichenko
commit
7226be6b22
|
|
@ -0,0 +1,3 @@
|
|||
SOURCES/eppic-d84c354.tar.gz
|
||||
SOURCES/kexec-tools-2.0.22.tar.xz
|
||||
SOURCES/makedumpfile-1.6.9.tar.gz
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
b902add474c63fe34c4cdf2eba882d7f8675e04e SOURCES/eppic-d84c354.tar.gz
|
||||
d23d055fb98f7fa68a2888b52f11530ba3b3a206 SOURCES/kexec-tools-2.0.22.tar.xz
|
||||
f07e6ce86b1e2e20b27137c26f08cd15e5460aca SOURCES/makedumpfile-1.6.9.tar.gz
|
||||
|
|
@ -0,0 +1,36 @@
|
|||
#!/usr/bin/bash
|
||||
|
||||
COMMAND="$1"
|
||||
KERNEL_VERSION="$2"
|
||||
KDUMP_INITRD_DIR_ABS="$3"
|
||||
KERNEL_IMAGE="$4"
|
||||
|
||||
if ! [[ ${KERNEL_INSTALL_MACHINE_ID-x} ]]; then
|
||||
exit 0
|
||||
fi
|
||||
|
||||
if [[ -d "$KDUMP_INITRD_DIR_ABS" ]]; then
|
||||
KDUMP_INITRD="initrdkdump"
|
||||
else
|
||||
# If `KDUMP_BOOTDIR` is not writable, then the kdump
|
||||
# initrd must have been placed at `/var/lib/kdump`
|
||||
if [[ ! -w "/boot" ]]; then
|
||||
KDUMP_INITRD_DIR_ABS="/var/lib/kdump"
|
||||
else
|
||||
KDUMP_INITRD_DIR_ABS="/boot"
|
||||
fi
|
||||
KDUMP_INITRD="initramfs-${KERNEL_VERSION}kdump.img"
|
||||
fi
|
||||
|
||||
ret=0
|
||||
case "$COMMAND" in
|
||||
add)
|
||||
# Do nothing, kdump initramfs is strictly host only
|
||||
# and managed by kdump service
|
||||
;;
|
||||
remove)
|
||||
rm -f -- "$KDUMP_INITRD_DIR_ABS/$KDUMP_INITRD"
|
||||
ret=$?
|
||||
;;
|
||||
esac
|
||||
exit $ret
|
||||
|
|
@ -0,0 +1,143 @@
|
|||
#!/usr/bin/bash
|
||||
|
||||
COMMAND="$1"
|
||||
KERNEL_VERSION="$2"
|
||||
KDUMP_INITRD_DIR_ABS="$3"
|
||||
KERNEL_IMAGE="$4"
|
||||
|
||||
grub_etc_default="/etc/default/grub"
|
||||
|
||||
ver_lt() {
|
||||
[[ "$(echo -e "$1\n$2" | sort -V)" == $1$'\n'* ]] && [[ $1 != "$2" ]]
|
||||
}
|
||||
|
||||
# Read crashkernel= value in /etc/default/grub
|
||||
get_grub_etc_ck() {
|
||||
[[ -e $grub_etc_default ]] && \
|
||||
sed -n -e "s/^GRUB_CMDLINE_LINUX=.*\(crashkernel=[^\ \"]*\)[\ \"].*$/\1/p" $grub_etc_default
|
||||
}
|
||||
|
||||
# Read crashkernel.default value of specified kernel
|
||||
get_ck_default() {
|
||||
ck_file="/usr/lib/modules/$1/crashkernel.default"
|
||||
[[ -f "$ck_file" ]] && cat "$ck_file"
|
||||
}
|
||||
|
||||
# Iterate installed kernels, find the kernel with the highest version that has a
|
||||
# valid crashkernel.default file, exclude current installing/removing kernel
|
||||
#
|
||||
# $1: a string representing a crashkernel= cmdline. If given, will also check the
|
||||
# content of crashkernel.default, only crashkernel.default with the same value will match
|
||||
get_highest_ck_default_kver() {
|
||||
for kernel in $(find /usr/lib/modules -maxdepth 1 -mindepth 1 -printf "%f\n" | sort --version-sort -r); do
|
||||
[[ $kernel == "$KERNEL_VERSION" ]] && continue
|
||||
[[ -s "/usr/lib/modules/$kernel/crashkernel.default" ]] || continue
|
||||
|
||||
echo "$kernel"
|
||||
return 0
|
||||
done
|
||||
|
||||
return 1
|
||||
}
|
||||
|
||||
set_grub_ck() {
|
||||
sed -i -e "s/^\(GRUB_CMDLINE_LINUX=.*\)crashkernel=[^\ \"]*\([\ \"].*\)$/\1$1\2/" "$grub_etc_default"
|
||||
}
|
||||
|
||||
# Set specified kernel's crashkernel cmdline value
|
||||
set_kernel_ck() {
|
||||
kernel=$1
|
||||
ck_cmdline=$2
|
||||
|
||||
entry=$(grubby --info ALL | grep "^kernel=.*$kernel")
|
||||
entry=${entry#kernel=}
|
||||
entry=${entry#\"}
|
||||
entry=${entry%\"}
|
||||
|
||||
if [[ -z "$entry" ]]; then
|
||||
echo "$0: failed to find boot entry for kernel $kernel"
|
||||
return 1
|
||||
fi
|
||||
|
||||
[[ -f /etc/zipl.conf ]] && zipl_arg="--zipl"
|
||||
grubby --args "$ck_cmdline" --update-kernel "$entry" $zipl_arg
|
||||
[[ $zipl_arg ]] && zipl > /dev/null
|
||||
}
|
||||
|
||||
case "$COMMAND" in
|
||||
add)
|
||||
# - If current boot kernel is using default crashkernel value, update
|
||||
# installing kernel's crashkernel value to its default value,
|
||||
# - If intalling a higher version kernel, and /etc/default/grub's
|
||||
# crashkernel value is using default value, update it to installing
|
||||
# kernel's default value.
|
||||
inst_ck_default=$(get_ck_default "$KERNEL_VERSION")
|
||||
# If installing kernel doesn't have crashkernel.default, just exit.
|
||||
[[ -z "$inst_ck_default" ]] && exit 0
|
||||
|
||||
boot_kernel=$(uname -r)
|
||||
boot_ck_cmdline=$(sed -n -e "s/^.*\(crashkernel=\S*\).*$/\1/p" /proc/cmdline)
|
||||
highest_ck_default_kver=$(get_highest_ck_default_kver)
|
||||
highest_ck_default=$(get_ck_default "$highest_ck_default_kver")
|
||||
|
||||
# Try update /etc/default/grub if present, else grub2-mkconfig could
|
||||
# override crashkernel value.
|
||||
grub_etc_ck=$(get_grub_etc_ck)
|
||||
if [[ -n "$grub_etc_ck" ]]; then
|
||||
if [[ -z "$highest_ck_default_kver" ]]; then
|
||||
# None of installed kernel have a crashkernel.default,
|
||||
# check for 'crashkernel=auto' in case of legacy kernel
|
||||
[[ "$grub_etc_ck" == "crashkernel=auto" ]] && \
|
||||
set_grub_ck "$inst_ck_default"
|
||||
else
|
||||
# There is a valid crashkernel.default, check if installing kernel
|
||||
# have a higher version and grub config is using default value
|
||||
ver_lt "$highest_ck_default_kver" "$KERNEL_VERSION" && \
|
||||
[[ "$grub_etc_ck" == "$highest_ck_default" ]] && \
|
||||
[[ "$grub_etc_ck" != "$inst_ck_default" ]] && \
|
||||
set_grub_ck "$inst_ck_default"
|
||||
fi
|
||||
fi
|
||||
|
||||
# Exit if crashkernel is not used in current cmdline
|
||||
[[ -z $boot_ck_cmdline ]] && exit 0
|
||||
|
||||
# Get current boot kernel's default value
|
||||
boot_ck_default=$(get_ck_default "$boot_kernel")
|
||||
if [[ $boot_ck_cmdline == "crashkernel=auto" ]]; then
|
||||
# Legacy RHEL kernel defaults to "auto"
|
||||
boot_ck_default="$boot_ck_cmdline"
|
||||
fi
|
||||
|
||||
# If boot kernel doesn't have a crashkernel.default, check
|
||||
# if it's using any installed kernel's crashkernel.default
|
||||
if [[ -z $boot_ck_default ]]; then
|
||||
[[ $(get_highest_ck_default_kver "$boot_ck_cmdline") ]] && boot_ck_default="$boot_ck_cmdline"
|
||||
fi
|
||||
|
||||
# If boot kernel is using a default crashkernel, update
|
||||
# installing kernel's crashkernel to new default value
|
||||
if [[ "$boot_ck_cmdline" != "$inst_ck_default" ]] && [[ "$boot_ck_cmdline" == "$boot_ck_default" ]]; then
|
||||
set_kernel_ck "$KERNEL_VERSION" "$inst_ck_default"
|
||||
fi
|
||||
;;
|
||||
|
||||
remove)
|
||||
# If grub default value is upgraded when this kernel was installed, try downgrade it
|
||||
grub_etc_ck=$(get_grub_etc_ck)
|
||||
[[ $grub_etc_ck ]] || exit 0
|
||||
|
||||
removing_ck_conf=$(get_ck_default "$KERNEL_VERSION")
|
||||
[[ $removing_ck_conf ]] || exit 0
|
||||
|
||||
highest_ck_default_kver=$(get_highest_ck_default_kver) || exit 0
|
||||
highest_ck_default=$(get_ck_default "$highest_ck_default_kver")
|
||||
[[ $highest_ck_default ]] || exit 0
|
||||
|
||||
if ver_lt "$highest_ck_default_kver" "$KERNEL_VERSION"; then
|
||||
if [[ $grub_etc_ck == "$removing_ck_conf" ]] && [[ $grub_etc_ck != "$highest_ck_default" ]]; then
|
||||
set_grub_ck "$highest_ck_default"
|
||||
fi
|
||||
fi
|
||||
;;
|
||||
esac
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
SUBSYSTEM=="cpu", ACTION=="add", GOTO="kdump_reload"
|
||||
SUBSYSTEM=="cpu", ACTION=="remove", GOTO="kdump_reload"
|
||||
SUBSYSTEM=="memory", ACTION=="online", GOTO="kdump_reload"
|
||||
SUBSYSTEM=="memory", ACTION=="offline", GOTO="kdump_reload"
|
||||
|
||||
GOTO="kdump_reload_end"
|
||||
|
||||
LABEL="kdump_reload"
|
||||
|
||||
# If kdump is not loaded, calling kdump-udev-throttle will end up
|
||||
# doing nothing, but systemd-run will always generate extra logs for
|
||||
# each call, so trigger the kdump-udev-throttler only if kdump
|
||||
# service is active to avoid unnecessary logs
|
||||
RUN+="/bin/sh -c '/usr/bin/systemctl is-active kdump.service || exit 0; /usr/bin/systemd-run --quiet --no-block /usr/lib/udev/kdump-udev-throttler'"
|
||||
|
||||
LABEL="kdump_reload_end"
|
||||
|
|
@ -0,0 +1,22 @@
|
|||
SUBSYSTEM=="cpu", ACTION=="online", GOTO="kdump_reload_cpu"
|
||||
SUBSYSTEM=="memory", ACTION=="online", GOTO="kdump_reload_mem"
|
||||
SUBSYSTEM=="memory", ACTION=="offline", GOTO="kdump_reload_mem"
|
||||
|
||||
GOTO="kdump_reload_end"
|
||||
|
||||
# If kdump is not loaded, calling kdump-udev-throttle will end up
|
||||
# doing nothing, but systemd-run will always generate extra logs for
|
||||
# each call, so trigger the kdump-udev-throttler only if kdump
|
||||
# service is active to avoid unnecessary logs
|
||||
|
||||
LABEL="kdump_reload_mem"
|
||||
|
||||
RUN+="/bin/sh -c '/usr/bin/systemctl is-active kdump.service || exit 0; /usr/bin/systemd-run --quiet --no-block /usr/lib/udev/kdump-udev-throttler'"
|
||||
|
||||
GOTO="kdump_reload_end"
|
||||
|
||||
LABEL="kdump_reload_cpu"
|
||||
|
||||
RUN+="/bin/sh -c '/usr/bin/systemctl is-active kdump.service || exit 0; ! test -f /sys/kernel/fadump_enabled || cat /sys/kernel/fadump_enabled | grep 0 || exit 0; /usr/bin/systemd-run --quiet --no-block /usr/lib/udev/kdump-udev-throttler'"
|
||||
|
||||
LABEL="kdump_reload_end"
|
||||
|
|
@ -0,0 +1,204 @@
|
|||
Introduction
|
||||
============
|
||||
|
||||
This document describes features the kexec-tools package provides for setting
|
||||
and estimating the crashkernel value.
|
||||
|
||||
Kdump lives in a pre-reserved chunk of memory, and the size of the reserved
|
||||
memory is specified by the `crashkernel=` kernel parameter. It's hard to
|
||||
estimate an accurate `crashkernel=` value, so it's always recommended to test
|
||||
kdump after you updated the `crashkernel=` value or changed the dump target.
|
||||
|
||||
|
||||
Default crashkernel value
|
||||
=========================
|
||||
|
||||
Latest kernel packages includes a `crashkernel.default` file installed in kernel
|
||||
modules folder, available as:
|
||||
|
||||
/usr/lib/modules/<kernel>/crashkernel.default
|
||||
|
||||
The content of the file will be taken as the default value of 'crashkernel=', or
|
||||
take this file as a reference for setting crashkernel value manually.
|
||||
|
||||
|
||||
New installed system
|
||||
====================
|
||||
|
||||
Anaconda is the OS installer which sets all the kernel boot cmdline on a new
|
||||
installed system. If kdump is set enabled during Anaconda installation, Anaconda
|
||||
will use the `crashkernel.default` file as the default `crashkernel=` value on
|
||||
the new installed system.
|
||||
|
||||
Users can also override the value during Anaconda installation manually.
|
||||
|
||||
|
||||
Auto update of crashkernel boot parameter
|
||||
=========================================
|
||||
|
||||
Following context in this section assumes all kernel packages have a
|
||||
`crashkernel.default` file bundled, which is true for the latest official kernel
|
||||
packages. For kexec-tools behavior with a kernel that doesn't have a
|
||||
`crashkernel.default` file, please refer to the “Custom Kernel” section of this
|
||||
doc.
|
||||
|
||||
When `crashkernel=` is using the default value, kexec-tools will need to update
|
||||
the `crashkernel=` value of new installed kernels, since the default value may
|
||||
change in new kernel packages.
|
||||
|
||||
kexec-tools does so by adding a kernel installation hook, which gets triggered
|
||||
every time a new kernel is installed, so kexec-tools can do necessary checks and
|
||||
updates.
|
||||
|
||||
|
||||
Supported Bootloaders
|
||||
---------------------
|
||||
|
||||
This auto update only works with GRUB2 and ZIPL, as kexec-tools heavily depends
|
||||
on `grubby`. If other boot loaders are used, the user will have to update the
|
||||
`crashkernel=` value manually.
|
||||
|
||||
|
||||
Updating kernel package
|
||||
-----------------------
|
||||
|
||||
When a new version of package kernel is released in the official repository, the
|
||||
package will always come with a `crashkernel.default` file bundled. Kexec-tools
|
||||
will act with following rules:
|
||||
|
||||
If current boot kernel is using the default `crashkernel=` boot param value from
|
||||
its `crashkernel.default` file, then kexec-tools will update new installed
|
||||
kernel’s `crashkernel=` boot param using the value from the new installed
|
||||
kernel’s `crashkernel.default` file. This ensures `crashkernel=` is always using
|
||||
the latest default value.
|
||||
|
||||
If current boot kernel's `crashkernel=` value is set to a non-default value, the
|
||||
new installed kernel simply inherits this value.
|
||||
|
||||
On systems using GRUB2 as the bootloader, each kernel has its own boot entry,
|
||||
making it possible to set different `crashkernel=` boot param values for
|
||||
different kernels. So kexec-tools won’t touch any already installed kernel's
|
||||
boot param, only new installed kernel's `crashkernel=` boot param value will be
|
||||
updated.
|
||||
|
||||
But some utilities like `grub2-mkconfig` and `grubby` can override all boot
|
||||
entry's boot params with the boot params value from the GRUB config file
|
||||
`/etc/defaults/grub`, so kexec-tools will also update the GRUB config file in
|
||||
case old `crashkernel=` value overrides new installed kernel’s boot param.
|
||||
|
||||
|
||||
Downgrading kernel package
|
||||
--------------------------
|
||||
|
||||
When upgrading a kernel package, kexec-tools may update the `crashkernel=` value
|
||||
in GRUB2 config file to the new value. So when downgrading the kernel package,
|
||||
kexec-tools will also try to revert that update by setting GRUB2 config file’s
|
||||
`crashkernel=` value back to the default value in the older kernel package. This
|
||||
will only occur when the GRUB2 config file is using the default `crashkernel=`
|
||||
value.
|
||||
|
||||
|
||||
Custom kernel
|
||||
=============
|
||||
|
||||
To make auto crashkernel update more robust, kexec-tools will try to keep
|
||||
tracking the default 'crashkernel=` value with kernels that don’t have a
|
||||
`crashkernel.default` file, such kernels are referred to as “custom kernel” in
|
||||
this doc. This is only a best-effort support to make it easier debugging and
|
||||
testing the system.
|
||||
|
||||
When installing a custom kernel that doesn’t have a `crashkernel.default` file,
|
||||
the `crashkernel=` value will be simply inherited from the current boot kernel.
|
||||
|
||||
When installing a new official kernel package and current boot kernel is a
|
||||
custom kernel, since the boot kernel doesn’t have a `crashkernel.default` file,
|
||||
kexec-tools will iterate installed kernels and check if the boot kernel
|
||||
inherited the default value from any other existing kernels’
|
||||
`crashkernel.default` file. If a matching `crashkernel.default` file is found,
|
||||
kexec-tools will update the new installed kernel `crashkernel=` boot param using
|
||||
the value from the new installed kernel’s `crashkernel.default` file, ensures
|
||||
the auto crashkernel value update won’t break over one or two custom kernel
|
||||
installations.
|
||||
|
||||
It is possible that the auto crashkernel value update will fail when custom
|
||||
kernels are used. One example is a custom kernel inheriting the default
|
||||
`crashkernel=` value from an older official kernel package, but later that
|
||||
kernel package is uninstalled. So when booted with the custom kernel,
|
||||
kexec-tools can't determine if the boot kernel is inheriting a default
|
||||
`crashkernel=` value from any official build. In such a case, please refer to
|
||||
the "Reset crashkernel to default value" section of this doc.
|
||||
|
||||
|
||||
Reset crashkernel to default value
|
||||
==================================
|
||||
|
||||
kexec-tools only perform the auto update of crashkernel value when it can
|
||||
confirm the boot kernel's crashkernel value is using its corresponding default
|
||||
value or inherited from any installed kernel.
|
||||
|
||||
kexec-tools may fail to determine if the boot kernel is using default
|
||||
crashkernel value in some use cases:
|
||||
- kexec-tools package is absent during a kernel package upgrade, and the new
|
||||
kernel package’s `crashkernel.default` value has changed.
|
||||
- Custom kernel is used and the kernel it inherits `crashkernel=` value from is
|
||||
uninstalled.
|
||||
|
||||
So it's recommended to reset the crashkernel value if users have uninstalled
|
||||
kexec-tools or using a custom kernel.
|
||||
|
||||
Reset using kdumpctl
|
||||
--------------------
|
||||
|
||||
To make it easier to reset the `crashkernel=` kernel cmdline to this default
|
||||
value properly, `kdumpctl` also provides a sub-command:
|
||||
|
||||
`kdumpctl reset-crashkernel [<kernel version>]`
|
||||
|
||||
This command will read from the `crashkernel.default` file and reset
|
||||
bootloader's kernel cmdline to the default value. It will also update bootloader
|
||||
config if the bootloader has a standalone config file. User will have to reboot
|
||||
the machine after this command to make it take effect.
|
||||
|
||||
Reset manually
|
||||
--------------
|
||||
|
||||
To reset the crashkernel value manually, it's recommended to use utils like
|
||||
`grubby`. A one liner script for resetting `crashkernel=` value of all installed
|
||||
kernels to current boot kernel's crashkernel.default` is:
|
||||
|
||||
grubby --update-kernel ALL --args "$(cat /usr/lib/modules/$(uname -r)/crashkernel.default)"
|
||||
|
||||
Estimate crashkernel
|
||||
====================
|
||||
|
||||
The best way to estimate a usable crashkernel value is by testing kdump
|
||||
manually. And you can set crashkernel to a large value, then adjust the
|
||||
crashkernel value to an acceptable value gradually.
|
||||
|
||||
`kdumpctl` also provides a sub-command for doing rough estimating without
|
||||
triggering kdump:
|
||||
|
||||
`kdumpctl estimate`
|
||||
|
||||
The output will be like this:
|
||||
|
||||
```
|
||||
Encrypted kdump target requires extra memory, assuming using the keyslot with minimun memory requirement
|
||||
|
||||
Reserved crashkernel: 256M
|
||||
Recommended crashkernel: 655M
|
||||
|
||||
Kernel image size: 47M
|
||||
Kernel modules size: 12M
|
||||
Initramfs size: 19M
|
||||
Runtime reservation: 64M
|
||||
LUKS required size: 512M
|
||||
Large modules:
|
||||
xfs: 1892352
|
||||
nouveau: 2318336
|
||||
WARNING: Current crashkernel size is lower than recommended size 655M.
|
||||
```
|
||||
|
||||
It will generate a summary report about the estimated memory consumption
|
||||
of each component of kdump. The value may not be accurate enough, but
|
||||
would be a good start for finding a suitable crashkernel value.
|
||||
|
|
@ -0,0 +1,64 @@
|
|||
#!/bin/bash
|
||||
|
||||
. /etc/sysconfig/kdump
|
||||
|
||||
KDUMP_KERNEL=""
|
||||
KDUMP_INITRD=""
|
||||
|
||||
check() {
|
||||
if [ ! -f /etc/sysconfig/kdump ] || [ ! -f /lib/kdump/kdump-lib.sh ]\
|
||||
|| [ -n "${IN_KDUMP}" ]
|
||||
then
|
||||
return 1
|
||||
fi
|
||||
return 255
|
||||
}
|
||||
|
||||
depends() {
|
||||
echo "base shutdown"
|
||||
return 0
|
||||
}
|
||||
|
||||
prepare_kernel_initrd() {
|
||||
. /lib/kdump/kdump-lib.sh
|
||||
|
||||
prepare_kdump_bootinfo
|
||||
|
||||
# $kernel is a variable from dracut
|
||||
if [ "$KDUMP_KERNELVER" != $kernel ]; then
|
||||
dwarn "Using kernel version '$KDUMP_KERNELVER' for early kdump," \
|
||||
"but the initramfs is generated for kernel version '$kernel'"
|
||||
fi
|
||||
}
|
||||
|
||||
install() {
|
||||
prepare_kernel_initrd
|
||||
if [ ! -f "$KDUMP_KERNEL" ]; then
|
||||
derror "Could not find required kernel for earlykdump," \
|
||||
"earlykdump will not work!"
|
||||
return 1
|
||||
fi
|
||||
if [ ! -f "$KDUMP_INITRD" ]; then
|
||||
derror "Could not find required kdump initramfs for earlykdump," \
|
||||
"please ensure kdump initramfs is generated first," \
|
||||
"earlykdump will not work!"
|
||||
return 1
|
||||
fi
|
||||
|
||||
inst_multiple tail find cut dirname hexdump
|
||||
inst_simple "/etc/sysconfig/kdump"
|
||||
inst_binary "/usr/sbin/kexec"
|
||||
inst_binary "/usr/bin/gawk" "/usr/bin/awk"
|
||||
inst_binary "/usr/bin/logger" "/usr/bin/logger"
|
||||
inst_binary "/usr/bin/printf" "/usr/bin/printf"
|
||||
inst_script "/lib/kdump/kdump-lib.sh" "/lib/kdump-lib.sh"
|
||||
inst_script "/lib/kdump/kdump-logger.sh" "/lib/kdump-logger.sh"
|
||||
inst_hook cmdline 00 "$moddir/early-kdump.sh"
|
||||
inst_binary "$KDUMP_KERNEL"
|
||||
inst_binary "$KDUMP_INITRD"
|
||||
|
||||
ln_r "$KDUMP_KERNEL" "/boot/kernel-earlykdump"
|
||||
ln_r "$KDUMP_INITRD" "/boot/initramfs-earlykdump"
|
||||
|
||||
chmod -x "${initdir}/$KDUMP_KERNEL"
|
||||
}
|
||||
|
|
@ -0,0 +1,88 @@
|
|||
#! /bin/sh
|
||||
|
||||
KEXEC=/sbin/kexec
|
||||
standard_kexec_args="-p"
|
||||
|
||||
EARLY_KDUMP_INITRD=""
|
||||
EARLY_KDUMP_KERNEL=""
|
||||
EARLY_KDUMP_CMDLINE=""
|
||||
EARLY_KDUMP_KERNELVER=""
|
||||
EARLY_KEXEC_ARGS=""
|
||||
|
||||
. /etc/sysconfig/kdump
|
||||
. /lib/dracut-lib.sh
|
||||
. /lib/kdump-lib.sh
|
||||
. /lib/kdump-logger.sh
|
||||
|
||||
#initiate the kdump logger
|
||||
dlog_init
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "failed to initiate the kdump logger."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
prepare_parameters()
|
||||
{
|
||||
EARLY_KDUMP_CMDLINE=$(prepare_cmdline "${KDUMP_COMMANDLINE}" "${KDUMP_COMMANDLINE_REMOVE}" "${KDUMP_COMMANDLINE_APPEND}")
|
||||
EARLY_KDUMP_KERNEL="/boot/kernel-earlykdump"
|
||||
EARLY_KDUMP_INITRD="/boot/initramfs-earlykdump"
|
||||
}
|
||||
|
||||
early_kdump_load()
|
||||
{
|
||||
check_kdump_feasibility
|
||||
if [ $? -ne 0 ]; then
|
||||
return 1
|
||||
fi
|
||||
|
||||
if is_fadump_capable; then
|
||||
dwarn "WARNING: early kdump doesn't support fadump."
|
||||
return 1
|
||||
fi
|
||||
|
||||
check_current_kdump_status
|
||||
if [ $? == 0 ]; then
|
||||
return 1
|
||||
fi
|
||||
|
||||
prepare_parameters
|
||||
|
||||
EARLY_KEXEC_ARGS=$(prepare_kexec_args "${KEXEC_ARGS}")
|
||||
|
||||
if is_secure_boot_enforced; then
|
||||
dinfo "Secure Boot is enabled. Using kexec file based syscall."
|
||||
EARLY_KEXEC_ARGS="$EARLY_KEXEC_ARGS -s"
|
||||
fi
|
||||
|
||||
# Here, only output the messages, but do not save these messages
|
||||
# to a file because the target disk may not be mounted yet, the
|
||||
# earlykdump is too early.
|
||||
ddebug "earlykdump: $KEXEC ${EARLY_KEXEC_ARGS} $standard_kexec_args \
|
||||
--command-line=$EARLY_KDUMP_CMDLINE --initrd=$EARLY_KDUMP_INITRD \
|
||||
$EARLY_KDUMP_KERNEL"
|
||||
|
||||
$KEXEC ${EARLY_KEXEC_ARGS} $standard_kexec_args \
|
||||
--command-line="$EARLY_KDUMP_CMDLINE" \
|
||||
--initrd=$EARLY_KDUMP_INITRD $EARLY_KDUMP_KERNEL
|
||||
if [ $? == 0 ]; then
|
||||
dinfo "kexec: loaded early-kdump kernel"
|
||||
return 0
|
||||
else
|
||||
derror "kexec: failed to load early-kdump kernel"
|
||||
return 1
|
||||
fi
|
||||
}
|
||||
|
||||
set_early_kdump()
|
||||
{
|
||||
if getargbool 0 rd.earlykdump; then
|
||||
dinfo "early-kdump is enabled."
|
||||
early_kdump_load
|
||||
else
|
||||
dinfo "early-kdump is disabled."
|
||||
fi
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
set_early_kdump
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
#!/bin/sh
|
||||
export PATH=/usr/bin:/usr/sbin
|
||||
export SYSTEMD_IN_INITRD=lenient
|
||||
|
||||
[ -e /proc/mounts ] ||
|
||||
(mkdir -p /proc && mount -t proc -o nosuid,noexec,nodev proc /proc)
|
||||
|
||||
grep -q '^sysfs /sys sysfs' /proc/mounts ||
|
||||
(mkdir -p /sys && mount -t sysfs -o nosuid,noexec,nodev sysfs /sys)
|
||||
|
||||
grep -q '^none / ' /proc/mounts || grep -q '^rootfs / ' /proc/mounts && ROOTFS_IS_RAMFS=1
|
||||
|
||||
if [ -f /proc/device-tree/rtas/ibm,kernel-dump ] || [ -f /proc/device-tree/ibm,opal/dump/mpipl-boot ]; then
|
||||
mkdir /newroot
|
||||
mount -t ramfs ramfs /newroot
|
||||
|
||||
if [ $ROOTFS_IS_RAMFS ]; then
|
||||
for FILE in $(ls -A /fadumproot/); do
|
||||
mv /fadumproot/$FILE /newroot/
|
||||
done
|
||||
exec switch_root /newroot /init
|
||||
else
|
||||
mkdir /newroot/sys /newroot/proc /newroot/dev /newroot/run /newroot/oldroot
|
||||
|
||||
grep -q '^devtmpfs /dev devtmpfs' /proc/mounts && mount --move /dev /newroot/dev
|
||||
grep -q '^tmpfs /run tmpfs' /proc/mounts && mount --move /run /newroot/run
|
||||
mount --move /sys /newroot/sys
|
||||
mount --move /proc /newroot/proc
|
||||
|
||||
cp --reflink=auto --sparse=auto --preserve=mode,timestamps,links -dfr /fadumproot/. /newroot/
|
||||
cd /newroot && pivot_root . oldroot
|
||||
|
||||
loop=1
|
||||
while [ $loop ]; do
|
||||
unset loop
|
||||
while read -r _ mp _; do
|
||||
case $mp in
|
||||
/oldroot/*) umount -d "$mp" && loop=1 ;;
|
||||
esac
|
||||
done </proc/mounts
|
||||
done
|
||||
umount -d -l oldroot
|
||||
|
||||
exec /init
|
||||
fi
|
||||
else
|
||||
exec /init.dracut
|
||||
fi
|
||||
|
|
@ -0,0 +1,23 @@
|
|||
#!/bin/bash
|
||||
|
||||
check() {
|
||||
return 255
|
||||
}
|
||||
|
||||
depends() {
|
||||
return 0
|
||||
}
|
||||
|
||||
install() {
|
||||
mv -f "$initdir/init" "$initdir/init.dracut"
|
||||
inst_script "$moddir/init-fadump.sh" /init
|
||||
chmod a+x "$initdir/init"
|
||||
|
||||
# Install required binaries for the init script (init-fadump.sh)
|
||||
inst_multiple sh modprobe grep mkdir mount
|
||||
if dracut_module_included "squash"; then
|
||||
inst_multiple cp pivot_root umount
|
||||
else
|
||||
inst_multiple ls mv switch_root
|
||||
fi
|
||||
}
|
||||
|
|
@ -0,0 +1,30 @@
|
|||
# This file is part of systemd.
|
||||
#
|
||||
# systemd is free software; you can redistribute it and/or modify it
|
||||
# under the terms of the GNU Lesser General Public License as published by
|
||||
# the Free Software Foundation; either version 2.1 of the License, or
|
||||
# (at your option) any later version.
|
||||
|
||||
[Unit]
|
||||
Description=Kdump Vmcore Save Service
|
||||
After=initrd.target initrd-parse-etc.service sysroot.mount
|
||||
After=dracut-initqueue.service dracut-pre-mount.service dracut-mount.service dracut-pre-pivot.service
|
||||
Before=initrd-cleanup.service
|
||||
ConditionPathExists=/etc/initrd-release
|
||||
OnFailure=emergency.target
|
||||
OnFailureJobMode=isolate
|
||||
|
||||
[Service]
|
||||
Environment=DRACUT_SYSTEMD=1
|
||||
Environment=NEWROOT=/sysroot
|
||||
Type=oneshot
|
||||
ExecStart=/bin/kdump.sh
|
||||
StandardInput=null
|
||||
StandardOutput=syslog
|
||||
StandardError=syslog+console
|
||||
KillMode=process
|
||||
RemainAfterExit=yes
|
||||
|
||||
# Bash ignores SIGTERM, so we send SIGHUP instead, to ensure that bash
|
||||
# terminates cleanly.
|
||||
KillSignal=SIGHUP
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
# This service will run the real kdump error handler code. Executing the
|
||||
# failure action configured in kdump.conf
|
||||
|
||||
[Unit]
|
||||
Description=Kdump Error Handler
|
||||
DefaultDependencies=no
|
||||
After=systemd-vconsole-setup.service
|
||||
Wants=systemd-vconsole-setup.service
|
||||
|
||||
[Service]
|
||||
Environment=HOME=/
|
||||
Environment=DRACUT_SYSTEMD=1
|
||||
Environment=NEWROOT=/sysroot
|
||||
WorkingDirectory=/
|
||||
ExecStart=/bin/kdump-error-handler.sh
|
||||
ExecStopPost=-/bin/rm -f -- /.console_lock
|
||||
Type=oneshot
|
||||
StandardInput=tty-force
|
||||
StandardOutput=inherit
|
||||
StandardError=inherit
|
||||
KillMode=process
|
||||
IgnoreSIGPIPE=no
|
||||
TasksMax=infinity
|
||||
|
||||
# Bash ignores SIGTERM, so we send SIGHUP instead, to ensure that bash
|
||||
# terminates cleanly.
|
||||
KillSignal=SIGHUP
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
# This file is part of systemd.
|
||||
#
|
||||
# systemd is free software; you can redistribute it and/or modify it
|
||||
# under the terms of the GNU Lesser General Public License as published by
|
||||
# the Free Software Foundation; either version 2.1 of the License, or
|
||||
# (at your option) any later version.
|
||||
|
||||
[Unit]
|
||||
Description=Emergency Mode
|
||||
Documentation=man:systemd.special(7)
|
||||
Requires=emergency.service
|
||||
After=emergency.service
|
||||
AllowIsolate=yes
|
||||
IgnoreOnIsolate=yes
|
||||
|
|
@ -0,0 +1,10 @@
|
|||
#!/bin/sh
|
||||
|
||||
. /lib/kdump-lib-initramfs.sh
|
||||
|
||||
set -o pipefail
|
||||
export PATH=$PATH:$KDUMP_SCRIPT_DIR
|
||||
|
||||
get_kdump_confs
|
||||
do_failure_action
|
||||
do_final_action
|
||||
|
|
@ -0,0 +1,324 @@
|
|||
#!/bin/sh
|
||||
|
||||
# continue here only if we have to save dump.
|
||||
if [ -f /etc/fadump.initramfs ] && [ ! -f /proc/device-tree/rtas/ibm,kernel-dump ] && [ ! -f /proc/device-tree/ibm,opal/dump/mpipl-boot ]; then
|
||||
exit 0
|
||||
fi
|
||||
|
||||
. /lib/dracut-lib.sh
|
||||
. /lib/kdump-lib-initramfs.sh
|
||||
|
||||
set -o pipefail
|
||||
DUMP_RETVAL=0
|
||||
|
||||
export PATH=$PATH:$KDUMP_SCRIPT_DIR
|
||||
|
||||
do_dump()
|
||||
{
|
||||
local _ret
|
||||
|
||||
eval $DUMP_INSTRUCTION
|
||||
_ret=$?
|
||||
|
||||
if [ $_ret -ne 0 ]; then
|
||||
derror "saving vmcore failed"
|
||||
fi
|
||||
|
||||
return $_ret
|
||||
}
|
||||
|
||||
do_kdump_pre()
|
||||
{
|
||||
local _ret
|
||||
|
||||
if [ -n "$KDUMP_PRE" ]; then
|
||||
"$KDUMP_PRE"
|
||||
_ret=$?
|
||||
if [ $_ret -ne 0 ]; then
|
||||
derror "$KDUMP_PRE exited with $_ret status"
|
||||
return $_ret
|
||||
fi
|
||||
fi
|
||||
|
||||
# if any script fails, it just raises warning and continues
|
||||
if [ -d /etc/kdump/pre.d ]; then
|
||||
for file in /etc/kdump/pre.d/*; do
|
||||
"$file"
|
||||
_ret=$?
|
||||
if [ $_ret -ne 0 ]; then
|
||||
derror "$file exited with $_ret status"
|
||||
fi
|
||||
done
|
||||
fi
|
||||
return 0
|
||||
}
|
||||
|
||||
do_kdump_post()
|
||||
{
|
||||
local _ret
|
||||
|
||||
if [ -d /etc/kdump/post.d ]; then
|
||||
for file in /etc/kdump/post.d/*; do
|
||||
"$file" "$1"
|
||||
_ret=$?
|
||||
if [ $_ret -ne 0 ]; then
|
||||
derror "$file exited with $_ret status"
|
||||
fi
|
||||
done
|
||||
fi
|
||||
|
||||
if [ -n "$KDUMP_POST" ]; then
|
||||
"$KDUMP_POST" "$1"
|
||||
_ret=$?
|
||||
if [ $_ret -ne 0 ]; then
|
||||
derror "$KDUMP_POST exited with $_ret status"
|
||||
fi
|
||||
fi
|
||||
}
|
||||
|
||||
add_dump_code()
|
||||
{
|
||||
DUMP_INSTRUCTION=$1
|
||||
}
|
||||
|
||||
dump_raw()
|
||||
{
|
||||
local _raw=$1
|
||||
|
||||
[ -b "$_raw" ] || return 1
|
||||
|
||||
dinfo "saving to raw disk $_raw"
|
||||
|
||||
if ! $(echo -n $CORE_COLLECTOR|grep -q makedumpfile); then
|
||||
_src_size=`ls -l /proc/vmcore | cut -d' ' -f5`
|
||||
_src_size_mb=$(($_src_size / 1048576))
|
||||
monitor_dd_progress $_src_size_mb &
|
||||
fi
|
||||
|
||||
dinfo "saving vmcore"
|
||||
$CORE_COLLECTOR /proc/vmcore | dd of=$_raw bs=$DD_BLKSIZE >> /tmp/dd_progress_file 2>&1 || return 1
|
||||
sync
|
||||
|
||||
dinfo "saving vmcore complete"
|
||||
return 0
|
||||
}
|
||||
|
||||
dump_ssh()
|
||||
{
|
||||
local _ret=0
|
||||
local _exitcode=0 _exitcode2=0
|
||||
local _opt="-i $1 -o BatchMode=yes -o StrictHostKeyChecking=yes"
|
||||
local _dir="$KDUMP_PATH/$HOST_IP-$DATEDIR"
|
||||
local _host=$2
|
||||
local _vmcore="vmcore"
|
||||
local _ipv6_addr="" _username=""
|
||||
|
||||
dinfo "saving to $_host:$_dir"
|
||||
|
||||
cat /var/lib/random-seed > /dev/urandom
|
||||
ssh -q $_opt $_host mkdir -p $_dir || return 1
|
||||
|
||||
save_vmcore_dmesg_ssh ${DMESG_COLLECTOR} ${_dir} "${_opt}" $_host
|
||||
save_opalcore_ssh ${_dir} "${_opt}" $_host
|
||||
|
||||
dinfo "saving vmcore"
|
||||
|
||||
if is_ipv6_address "$_host"; then
|
||||
_username=${_host%@*}
|
||||
_ipv6_addr="[${_host#*@}]"
|
||||
fi
|
||||
|
||||
if [ "${CORE_COLLECTOR%%[[:blank:]]*}" = "scp" ]; then
|
||||
if [ -n "$_username" ] && [ -n "$_ipv6_addr" ]; then
|
||||
scp -q $_opt /proc/vmcore "$_username@$_ipv6_addr:$_dir/vmcore-incomplete"
|
||||
else
|
||||
scp -q $_opt /proc/vmcore "$_host:$_dir/vmcore-incomplete"
|
||||
fi
|
||||
_exitcode=$?
|
||||
else
|
||||
$CORE_COLLECTOR /proc/vmcore | ssh $_opt $_host "umask 0077 && dd bs=512 of=$_dir/vmcore-incomplete"
|
||||
_exitcode=$?
|
||||
_vmcore="vmcore.flat"
|
||||
fi
|
||||
|
||||
if [ $_exitcode -eq 0 ]; then
|
||||
ssh $_opt $_host "mv $_dir/vmcore-incomplete $_dir/$_vmcore"
|
||||
_exitcode2=$?
|
||||
if [ $_exitcode2 -ne 0 ]; then
|
||||
derror "moving vmcore failed, _exitcode:$_exitcode2"
|
||||
else
|
||||
dinfo "saving vmcore complete"
|
||||
fi
|
||||
else
|
||||
derror "saving vmcore failed, _exitcode:$_exitcode"
|
||||
fi
|
||||
|
||||
dinfo "saving the $KDUMP_LOG_FILE to $_host:$_dir/"
|
||||
save_log
|
||||
if [ -n "$_username" ] && [ -n "$_ipv6_addr" ]; then
|
||||
scp -q $_opt $KDUMP_LOG_FILE "$_username@$_ipv6_addr:$_dir/"
|
||||
else
|
||||
scp -q $_opt $KDUMP_LOG_FILE "$_host:$_dir/"
|
||||
fi
|
||||
_ret=$?
|
||||
if [ $_ret -ne 0 ]; then
|
||||
derror "saving log file failed, _exitcode:$_ret"
|
||||
fi
|
||||
|
||||
if [ $_exitcode -ne 0 ] || [ $_exitcode2 -ne 0 ];then
|
||||
return 1
|
||||
fi
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
save_opalcore_ssh() {
|
||||
local _path=$1
|
||||
local _opts="$2"
|
||||
local _location=$3
|
||||
local _user_name="" _ipv6addr=""
|
||||
|
||||
ddebug "_path=$_path _opts=$_opts _location=$_location"
|
||||
|
||||
if [ ! -f $OPALCORE ]; then
|
||||
# Check if we are on an old kernel that uses a different path
|
||||
if [ -f /sys/firmware/opal/core ]; then
|
||||
OPALCORE="/sys/firmware/opal/core"
|
||||
else
|
||||
return 0
|
||||
fi
|
||||
fi
|
||||
|
||||
if is_ipv6_address "$_host"; then
|
||||
_user_name=${_location%@*}
|
||||
_ipv6addr="[${_location#*@}]"
|
||||
fi
|
||||
|
||||
dinfo "saving opalcore:$OPALCORE to $_location:$_path"
|
||||
|
||||
if [ -n "$_user_name" ] && [ -n "$_ipv6addr" ]; then
|
||||
scp $_opts $OPALCORE $_user_name@$_ipv6addr:$_path/opalcore-incomplete
|
||||
else
|
||||
scp $_opts $OPALCORE $_location:$_path/opalcore-incomplete
|
||||
fi
|
||||
if [ $? -ne 0 ]; then
|
||||
derror "saving opalcore failed"
|
||||
return 1
|
||||
fi
|
||||
|
||||
ssh $_opts $_location mv $_path/opalcore-incomplete $_path/opalcore
|
||||
dinfo "saving opalcore complete"
|
||||
return 0
|
||||
}
|
||||
|
||||
save_vmcore_dmesg_ssh() {
|
||||
local _dmesg_collector=$1
|
||||
local _path=$2
|
||||
local _opts="$3"
|
||||
local _location=$4
|
||||
|
||||
dinfo "saving vmcore-dmesg.txt to $_location:$_path"
|
||||
$_dmesg_collector /proc/vmcore | ssh $_opts $_location "umask 0077 && dd of=$_path/vmcore-dmesg-incomplete.txt"
|
||||
_exitcode=$?
|
||||
|
||||
if [ $_exitcode -eq 0 ]; then
|
||||
ssh -q $_opts $_location mv $_path/vmcore-dmesg-incomplete.txt $_path/vmcore-dmesg.txt
|
||||
dinfo "saving vmcore-dmesg.txt complete"
|
||||
else
|
||||
derror "saving vmcore-dmesg.txt failed"
|
||||
fi
|
||||
}
|
||||
|
||||
get_host_ip()
|
||||
{
|
||||
local _host
|
||||
if is_nfs_dump_target || is_ssh_dump_target
|
||||
then
|
||||
kdumpnic=$(getarg kdumpnic=)
|
||||
[ -z "$kdumpnic" ] && derror "failed to get kdumpnic!" && return 1
|
||||
_host=`ip addr show dev $kdumpnic|grep '[ ]*inet'`
|
||||
[ $? -ne 0 ] && derror "wrong kdumpnic: $kdumpnic" && return 1
|
||||
_host=`echo $_host | head -n 1 | cut -d' ' -f2`
|
||||
_host="${_host%%/*}"
|
||||
[ -z "$_host" ] && derror "wrong kdumpnic: $kdumpnic" && return 1
|
||||
HOST_IP=$_host
|
||||
fi
|
||||
return 0
|
||||
}
|
||||
|
||||
read_kdump_conf()
|
||||
{
|
||||
if [ ! -f "$KDUMP_CONF" ]; then
|
||||
derror "$KDUMP_CONF not found"
|
||||
return
|
||||
fi
|
||||
|
||||
get_kdump_confs
|
||||
|
||||
# rescan for add code for dump target
|
||||
while read config_opt config_val;
|
||||
do
|
||||
# remove inline comments after the end of a directive.
|
||||
case "$config_opt" in
|
||||
dracut_args)
|
||||
config_val=$(get_dracut_args_target "$config_val")
|
||||
if [ -n "$config_val" ]; then
|
||||
config_val=$(get_mntpoint_from_target "$config_val")
|
||||
add_dump_code "dump_fs $config_val"
|
||||
fi
|
||||
;;
|
||||
ext[234]|xfs|btrfs|minix|nfs)
|
||||
config_val=$(get_mntpoint_from_target "$config_val")
|
||||
add_dump_code "dump_fs $config_val"
|
||||
;;
|
||||
raw)
|
||||
add_dump_code "dump_raw $config_val"
|
||||
;;
|
||||
ssh)
|
||||
add_dump_code "dump_ssh $SSH_KEY_LOCATION $config_val"
|
||||
;;
|
||||
esac
|
||||
done <<< "$(read_strip_comments $KDUMP_CONF)"
|
||||
}
|
||||
|
||||
fence_kdump_notify()
|
||||
{
|
||||
if [ -n "$FENCE_KDUMP_NODES" ]; then
|
||||
$FENCE_KDUMP_SEND $FENCE_KDUMP_ARGS $FENCE_KDUMP_NODES &
|
||||
fi
|
||||
}
|
||||
|
||||
read_kdump_conf
|
||||
fence_kdump_notify
|
||||
|
||||
get_host_ip
|
||||
if [ $? -ne 0 ]; then
|
||||
derror "get_host_ip exited with non-zero status!"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [ -z "$DUMP_INSTRUCTION" ]; then
|
||||
add_dump_code "dump_fs $NEWROOT"
|
||||
fi
|
||||
|
||||
do_kdump_pre
|
||||
if [ $? -ne 0 ]; then
|
||||
derror "kdump_pre script exited with non-zero status!"
|
||||
do_final_action
|
||||
# During systemd service to reboot the machine, stop this shell script running
|
||||
exit 1
|
||||
fi
|
||||
make_trace_mem "kdump saving vmcore" '1:shortmem' '2+:mem' '3+:slab'
|
||||
do_dump
|
||||
DUMP_RETVAL=$?
|
||||
|
||||
do_kdump_post $DUMP_RETVAL
|
||||
if [ $? -ne 0 ]; then
|
||||
derror "kdump_post script exited with non-zero status!"
|
||||
fi
|
||||
|
||||
if [ $DUMP_RETVAL -ne 0 ]; then
|
||||
exit 1
|
||||
fi
|
||||
|
||||
do_final_action
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,28 @@
|
|||
#!/bin/sh
|
||||
|
||||
SRC_FILE_MB=$1
|
||||
|
||||
while true
|
||||
do
|
||||
DD_PID=`pidof dd`
|
||||
if [ -n "$DD_PID" ]; then
|
||||
break
|
||||
fi
|
||||
done
|
||||
|
||||
while true
|
||||
do
|
||||
sleep 5
|
||||
if [ ! -d /proc/$DD_PID ]; then
|
||||
break
|
||||
fi
|
||||
|
||||
kill -s USR1 $DD_PID
|
||||
CURRENT_SIZE=`tail -n 1 /tmp/dd_progress_file | sed "s/[^0-9].*//g"`
|
||||
[ -n "$CURRENT_SIZE" ] && {
|
||||
CURRENT_MB=$(($CURRENT_SIZE / 1048576))
|
||||
echo -e "Copied $CURRENT_MB MB / $SRC_FILE_MB MB\r"
|
||||
}
|
||||
done
|
||||
|
||||
rm -f /tmp/dd_progress_file
|
||||
|
|
@ -0,0 +1,95 @@
|
|||
Early Kdump HOWTO
|
||||
|
||||
Introduction
|
||||
------------
|
||||
|
||||
Early kdump is a mechanism to make kdump operational earlier than normal kdump
|
||||
service. The kdump service starts early enough for general crash cases, but
|
||||
there are some cases where it has no chance to make kdump operational in boot
|
||||
sequence, such as detecting devices and starting early services. If you hit
|
||||
such a case, early kdump may allow you to get more information of it.
|
||||
|
||||
Early kdump is implemented as a dracut module. It adds a kernel (vmlinuz) and
|
||||
initramfs for kdump to your system's initramfs in order to load them as early
|
||||
as possible. After that, if you provide "rd.earlykdump" in kernel command line,
|
||||
then in the initramfs, early kdump will load those files like the normal kdump
|
||||
service. This is disabled by default.
|
||||
|
||||
For the normal kdump service, it can check whether the early kdump has loaded
|
||||
the crash kernel and initramfs. It has no conflict with the early kdump.
|
||||
|
||||
How to configure early kdump
|
||||
----------------------------
|
||||
|
||||
We assume if you're reading this document, you should already have kexec-tools
|
||||
installed.
|
||||
|
||||
You can rebuild the initramfs with earlykdump support with below steps:
|
||||
|
||||
1. start kdump service to make sure kdump initramfs is created.
|
||||
|
||||
# systemctl start kdump
|
||||
|
||||
NOTE: If a crash occurs during boot process, early kdump captures a vmcore
|
||||
and reboot the system by default, so the system might go into crash loop.
|
||||
You can avoid such a crash loop by adding the following settings, which
|
||||
power off the system after dump capturing, to kdump.conf in advance:
|
||||
|
||||
final_action poweroff
|
||||
failure_action poweroff
|
||||
|
||||
For the failure_action, you can choose anything other than "reboot".
|
||||
|
||||
2. rebuild system initramfs with earlykdump support.
|
||||
|
||||
# dracut --force --add earlykdump
|
||||
|
||||
NOTE: Recommend to backup the original system initramfs before performing
|
||||
this step to put it back if something happens during boot-up.
|
||||
|
||||
3. add rd.earlykdump in grub kernel command line.
|
||||
|
||||
After making said changes, reboot your system to take effect. Of course, if you
|
||||
want to disable early kdump, you can simply remove "rd.earlykdump" from kernel
|
||||
boot parameters in grub, and reboot system like above.
|
||||
|
||||
Once the boot is completed, you can check the status of the early kdump support
|
||||
on the command prompt:
|
||||
|
||||
# journalctl -b | grep early-kdump
|
||||
|
||||
Then, you will see some useful logs, for example:
|
||||
|
||||
- if early kdump is successful.
|
||||
|
||||
Mar 09 09:57:56 localhost dracut-cmdline[190]: early-kdump is enabled.
|
||||
Mar 09 09:57:56 localhost dracut-cmdline[190]: kexec: loaded early-kdump kernel
|
||||
|
||||
- if early kdump is disabled.
|
||||
|
||||
Mar 09 10:02:47 localhost dracut-cmdline[189]: early-kdump is disabled.
|
||||
|
||||
Notes
|
||||
-----
|
||||
|
||||
- The size of early kdump initramfs will be large because it includes vmlinuz
|
||||
and kdump initramfs.
|
||||
|
||||
- Early kdump inherits the settings of normal kdump, so any changes that
|
||||
caused normal kdump rebuilding also require rebuilding the system initramfs
|
||||
to make sure that the changes take effect for early kdump. Therefore, after
|
||||
the rebuilding of kdump initramfs is completed, provide a prompt message to
|
||||
tell the fact.
|
||||
|
||||
- If you install an updated kernel and reboot the system with it, the early
|
||||
kdump will be disabled by default. To enable it with the new kernel, you
|
||||
need to take the above steps again.
|
||||
|
||||
Limitation
|
||||
----------
|
||||
|
||||
- At present, early kdump doesn't support fadump.
|
||||
|
||||
- Early kdump loads a crash kernel and initramfs at the beginning of the
|
||||
process in system's initramfs, so a crash at earlier than that (e.g. in
|
||||
kernel initialization) cannot be captured even with the early kdump.
|
||||
|
|
@ -0,0 +1,351 @@
|
|||
Firmware assisted dump (fadump) HOWTO
|
||||
|
||||
Introduction
|
||||
|
||||
Firmware assisted dump is a new feature in the 3.4 mainline kernel supported
|
||||
only on powerpc architecture. The goal of firmware-assisted dump is to enable
|
||||
the dump of a crashed system, and to do so from a fully-reset system, and to
|
||||
minimize the total elapsed time until the system is back in production use. A
|
||||
complete documentation on implementation can be found at
|
||||
Documentation/powerpc/firmware-assisted-dump.txt in upstream linux kernel tree
|
||||
from 3.4 version and above.
|
||||
|
||||
Please note that the firmware-assisted dump feature is only available on Power6
|
||||
and above systems with recent firmware versions.
|
||||
|
||||
Overview
|
||||
|
||||
Fadump
|
||||
|
||||
Fadump is a robust kernel crash dumping mechanism to get reliable kernel crash
|
||||
dump with assistance from firmware. This approach does not use kexec, instead
|
||||
firmware assists in booting the kdump kernel while preserving memory contents.
|
||||
Unlike kdump, the system is fully reset, and loaded with a fresh copy of the
|
||||
kernel. In particular, PCI and I/O devices are reinitialized and are in a
|
||||
clean, consistent state. This second kernel, often called a capture kernel,
|
||||
boots with very little memory and captures the dump image.
|
||||
|
||||
The first kernel registers the sections of memory with the Power firmware for
|
||||
dump preservation during OS initialization. These registered sections of memory
|
||||
are reserved by the first kernel during early boot. When a system crashes, the
|
||||
Power firmware fully resets the system, preserves all the system memory
|
||||
contents, save the low memory (boot memory of size larger of 5% of system
|
||||
RAM or 256MB) of RAM to the previous registered region. It will also save
|
||||
system registers, and hardware PTE's.
|
||||
|
||||
Fadump is supported only on ppc64 platform. The standard kernel and capture
|
||||
kernel are one and the same on ppc64.
|
||||
|
||||
If you're reading this document, you should already have kexec-tools
|
||||
installed. If not, you install it via the following command:
|
||||
|
||||
# yum install kexec-tools
|
||||
|
||||
Fadump Operational Flow:
|
||||
|
||||
Like kdump, fadump also exports the ELF formatted kernel crash dump through
|
||||
/proc/vmcore. Hence existing kdump infrastructure can be used to capture fadump
|
||||
vmcore. The idea is to keep the functionality transparent to end user. From
|
||||
user perspective there is no change in the way kdump init script works.
|
||||
|
||||
However, unlike kdump, fadump does not pre-load kdump kernel and initrd into
|
||||
reserved memory, instead it always uses default OS initrd during second boot
|
||||
after crash. Hence, for fadump, we rebuild the new kdump initrd and replace it
|
||||
with default initrd. Before replacing existing default initrd we take a backup
|
||||
of original default initrd for user's reference. The dracut package has been
|
||||
enhanced to rebuild the default initrd with vmcore capture steps. The initrd
|
||||
image is rebuilt as per the configuration in /etc/kdump.conf file.
|
||||
|
||||
The control flow of fadump works as follows:
|
||||
01. System panics.
|
||||
02. At the crash, kernel informs power firmware that kernel has crashed.
|
||||
03. Firmware takes the control and reboots the entire system preserving
|
||||
only the memory (resets all other devices).
|
||||
04. The reboot follows the normal booting process (non-kexec).
|
||||
05. The boot loader loads the default kernel and initrd from /boot
|
||||
06. The default initrd loads and runs /init
|
||||
07. dracut-kdump.sh script present in fadump aware default initrd checks if
|
||||
'/proc/device-tree/rtas/ibm,kernel-dump' file exists before executing
|
||||
steps to capture vmcore.
|
||||
(This check will help to bypass the vmcore capture steps during normal boot
|
||||
process.)
|
||||
09. Captures dump according to /etc/kdump.conf
|
||||
10. Is dump capture successful (yes goto 12, no goto 11)
|
||||
11. Perform the failure action specified in /etc/kdump.conf
|
||||
(The default failure action is reboot, if unspecified)
|
||||
12. Perform the final action specified in /etc/kdump.conf
|
||||
(The default final action is reboot, if unspecified)
|
||||
|
||||
|
||||
How to configure fadump:
|
||||
|
||||
Again, we assume if you're reading this document, you should already have
|
||||
kexec-tools installed. If not, you install it via the following command:
|
||||
|
||||
# yum install kexec-tools
|
||||
|
||||
Make the kernel to be configured with FADump as the default boot entry, if
|
||||
it isn't already:
|
||||
|
||||
# grubby --set-default=/boot/vmlinuz-<kver>
|
||||
|
||||
Boot into the kernel to be configured for FADump. To be able to do much of
|
||||
anything interesting in the way of debug analysis, you'll also need to install
|
||||
the kernel-debuginfo package, of the same arch as your running kernel, and the
|
||||
crash utility:
|
||||
|
||||
# yum --enablerepo=\*debuginfo install kernel-debuginfo.$(uname -m) crash
|
||||
|
||||
Next up, we need to modify some boot parameters to enable firmware assisted
|
||||
dump. With the help of grubby, it's very easy to append "fadump=on" to the end
|
||||
of your kernel boot parameters. To reserve the appropriate amount of memory
|
||||
for boot memory preservation, pass 'crashkernel=X' kernel cmdline parameter.
|
||||
For the recommended value of X, see 'FADump Memory Requirements' section.
|
||||
|
||||
# grubby --args="fadump=on crashkernel=6G" --update-kernel=/boot/vmlinuz-`uname -r`
|
||||
|
||||
By default, FADump reserved memory will be initialized as CMA area to make the
|
||||
memory available through CMA allocator on the production kernel. We can opt out
|
||||
of this, making reserved memory unavailable to production kernel, by booting the
|
||||
linux kernel with 'fadump=nocma' instead of 'fadump=on'.
|
||||
|
||||
The term 'boot memory' means size of the low memory chunk that is required for
|
||||
a kernel to boot successfully when booted with restricted memory. By default,
|
||||
the boot memory size will be the larger of 5% of system RAM or 256MB.
|
||||
Alternatively, user can also specify boot memory size through boot parameter
|
||||
'fadump_reserve_mem=' which will override the default calculated size. Use this
|
||||
option if default boot memory size is not sufficient for second kernel to boot
|
||||
successfully.
|
||||
|
||||
After making said changes, reboot your system, so that the specified memory is
|
||||
reserved and left untouched by the normal system. Take note that the output of
|
||||
'free -m' will show X MB less memory than without this parameter, which is
|
||||
expected. If you see OOM (Out Of Memory) error messages while loading capture
|
||||
kernel, then you should bump up the memory reservation size.
|
||||
|
||||
Now that you've got that reserved memory region set up, you want to turn on
|
||||
the kdump init script:
|
||||
|
||||
# systemctl enable kdump.service
|
||||
|
||||
Then, start up kdump as well:
|
||||
|
||||
# systemctl start kdump.service
|
||||
|
||||
This should turn on the firmware assisted functionality in kernel by
|
||||
echo'ing 1 to /sys/kernel/fadump_registered, leaving the system ready
|
||||
to capture a vmcore upon crashing. For journaling filesystems like XFS an
|
||||
additional step is required to ensure bootloader does not pick the
|
||||
older initrd (without vmcore capture scripts):
|
||||
|
||||
* If /boot is a separate partition, run the below commands as the root user,
|
||||
or as a user with CAP_SYS_ADMIN rights:
|
||||
|
||||
# fsfreeze -f
|
||||
# fsfreeze -u
|
||||
|
||||
* If /boot is not a separate partition, reboot the system.
|
||||
|
||||
After reboot check if the kdump service is up and running with:
|
||||
|
||||
# systemctl status kdump.service
|
||||
|
||||
To test out whether FADump is configured properly, you can force-crash your
|
||||
system by echo'ing a 'c' into /proc/sysrq-trigger:
|
||||
|
||||
# echo c > /proc/sysrq-trigger
|
||||
|
||||
You should see some panic output, followed by the system reset and booting into
|
||||
fresh copy of kernel. When default initrd loads and runs /init, vmcore should
|
||||
be copied out to disk (by default, in /var/crash/<YYYY.MM.DD-HH:MM:SS>/vmcore),
|
||||
then the system rebooted back into your normal kernel.
|
||||
|
||||
Once back to your normal kernel, you can use the previously installed crash
|
||||
kernel in conjunction with the previously installed kernel-debuginfo to
|
||||
perform postmortem analysis:
|
||||
|
||||
# crash /usr/lib/debug/lib/modules/2.6.17-1.2621.el5/vmlinux
|
||||
/var/crash/2006-08-23-15:34/vmcore
|
||||
|
||||
crash> bt
|
||||
|
||||
and so on...
|
||||
|
||||
Saving vmcore-dmesg.txt
|
||||
-----------------------
|
||||
Kernel log bufferes are one of the most important information available
|
||||
in vmcore. Now before saving vmcore, kernel log bufferes are extracted
|
||||
from /proc/vmcore and saved into a file vmcore-dmesg.txt. After
|
||||
vmcore-dmesg.txt, vmcore is saved. Destination disk and directory for
|
||||
vmcore-dmesg.txt is same as vmcore. Note that kernel log buffers will
|
||||
not be available if dump target is raw device.
|
||||
|
||||
FADump Memory Requirements:
|
||||
|
||||
System Memory Recommended memory
|
||||
--------------------- ----------------------
|
||||
4 GB - 16 GB : 768 MB
|
||||
16 GB - 64 GB : 1024 MB
|
||||
64 GB - 128 GB : 2 GB
|
||||
128 GB - 1 TB : 4 GB
|
||||
1 TB - 2 TB : 6 GB
|
||||
2 TB - 4 TB : 12 GB
|
||||
4 TB - 8 TB : 20 GB
|
||||
8 TB - 16 TB : 36 GB
|
||||
16 TB - 32 TB : 64 GB
|
||||
32 TB - 64 TB : 128 GB
|
||||
64 TB & above : 180 GB
|
||||
|
||||
Things to remember:
|
||||
|
||||
1) The memory required to boot capture Kernel is a moving target that depends
|
||||
on many factors like hardware attached to the system, kernel and modules in
|
||||
use, packages installed and services enabled, there is no one-size-fits-all.
|
||||
But the above recommendations are based on system memory. So, the above
|
||||
recommendations for FADump come with a few assumptions, based on available
|
||||
system memory, about the resources the system could have. So, please take
|
||||
the recommendations with a pinch of salt and remember to try capturing dump
|
||||
a few times to confirm that the system is configured successfully with dump
|
||||
capturing support.
|
||||
|
||||
2) Though the memory requirements for FADump seem high, this memory is not
|
||||
completely set aside but made available for userspace applications to use,
|
||||
through the CMA allocator.
|
||||
|
||||
3) As the same initrd is used for booting production kernel as well as capture
|
||||
kernel and with dump being captured in a restricted memory environment, few
|
||||
optimizations (like not inclding network dracut module, disabling multipath
|
||||
and such) are applied while building the initrd. In case, the production
|
||||
environment needs these optimizations to be avoided, dracut_args option in
|
||||
/etc/kdump.conf file could be leveraged. For example, if a user wishes for
|
||||
network module to be included in the initrd, adding the below entry in
|
||||
/etc/kdump.conf file and restarting kdump service would take care of it.
|
||||
|
||||
dracut_args --add "network"
|
||||
|
||||
4) If FADump is configured to capture vmcore to a remote dump target using SSH
|
||||
or NFS protocol, the network interface is renamed to kdump-<interface-name>
|
||||
if <interface-name> is generic, for example, *eth#, or net#. This problem
|
||||
occurs because the vmcore capture scripts in the initial RAM disk (initrd)
|
||||
add the kdump- prefix to the network interface name to secure persistent
|
||||
naming. As the same initrd is used for production kernel boot, the interface
|
||||
name is changed for the production kernel too.
|
||||
|
||||
Dump Triggering methods:
|
||||
|
||||
This section talks about the various ways, other than a Kernel Panic, in which
|
||||
fadump can be triggered. The following methods assume that fadump is configured
|
||||
on your system, with the scripts enabled as described in the section above.
|
||||
|
||||
1) AltSysRq C
|
||||
|
||||
FAdump can be triggered with the combination of the 'Alt','SysRq' and 'C'
|
||||
keyboard keys. Please refer to the following link for more details:
|
||||
|
||||
https://fedoraproject.org/wiki/QA/Sysrq
|
||||
|
||||
In addition, on PowerPC boxes, fadump can also be triggered via Hardware
|
||||
Management Console(HMC) using 'Ctrl', 'O' and 'C' keyboard keys.
|
||||
|
||||
2) Kernel OOPs
|
||||
|
||||
If we want to generate a dump everytime the Kernel OOPses, we can achieve this
|
||||
by setting the 'Panic On OOPs' option as follows:
|
||||
|
||||
# echo 1 > /proc/sys/kernel/panic_on_oops
|
||||
|
||||
3) PowerPC specific methods:
|
||||
|
||||
On IBM PowerPC machines, issuing a soft reset invokes the XMON debugger(if
|
||||
XMON is configured). To configure XMON one needs to compile the kernel with
|
||||
the CONFIG_XMON and CONFIG_XMON_DEFAULT options, or by compiling with
|
||||
CONFIG_XMON and booting the kernel with xmon=on option.
|
||||
|
||||
Following are the ways to remotely issue a soft reset on PowerPC boxes, which
|
||||
would drop you to XMON. Pressing a 'X' (capital alphabet X) followed by an
|
||||
'Enter' here will trigger the dump.
|
||||
|
||||
3.1) HMC
|
||||
|
||||
Hardware Management Console(HMC) available on Power4 and Power5 machines allow
|
||||
partitions to be reset remotely. This is specially useful in hang situations
|
||||
where the system is not accepting any keyboard inputs.
|
||||
|
||||
Once you have HMC configured, the following steps will enable you to trigger
|
||||
fadump via a soft reset:
|
||||
|
||||
On Power4
|
||||
Using GUI
|
||||
|
||||
* In the right pane, right click on the partition you wish to dump.
|
||||
* Select "Operating System->Reset".
|
||||
* Select "Soft Reset".
|
||||
* Select "Yes".
|
||||
|
||||
Using HMC Commandline
|
||||
|
||||
# reset_partition -m <machine> -p <partition> -t soft
|
||||
|
||||
On Power5
|
||||
Using GUI
|
||||
|
||||
* In the right pane, right click on the partition you wish to dump.
|
||||
* Select "Restart Partition".
|
||||
* Select "Dump".
|
||||
* Select "OK".
|
||||
|
||||
Using HMC Commandline
|
||||
|
||||
# chsysstate -m <managed system name> -n <lpar name> -o dumprestart -r lpar
|
||||
|
||||
3.2) Blade Management Console for Blade Center
|
||||
|
||||
To initiate a dump operation, go to Power/Restart option under "Blade Tasks" in
|
||||
the Blade Management Console. Select the corresponding blade for which you want
|
||||
to initate the dump and then click "Restart blade with NMI". This issues a
|
||||
system reset and invokes xmon debugger.
|
||||
|
||||
|
||||
Advanced Setups & Failure action:
|
||||
|
||||
Kdump and fadump exhibit similar behavior in terms of setup & failure action.
|
||||
For fadump advanced setup related information see section "Advanced Setups" in
|
||||
"kexec-kdump-howto.txt" document. Refer to "Failure action" section in "kexec-
|
||||
kdump-howto.txt" document for fadump failure action related information.
|
||||
|
||||
Compression and filtering
|
||||
|
||||
Refer "Compression and filtering" section in "kexec-kdump-howto.txt" document.
|
||||
Compression and filtering are same for kdump & fadump.
|
||||
|
||||
|
||||
Notes on rootfs mount:
|
||||
Dracut is designed to mount rootfs by default. If rootfs mounting fails it
|
||||
will refuse to go on. So fadump leaves rootfs mounting to dracut currently.
|
||||
We make the assumtion that proper root= cmdline is being passed to dracut
|
||||
initramfs for the time being. If you need modify "KDUMP_COMMANDLINE=" in
|
||||
/etc/sysconfig/kdump, you will need to make sure that appropriate root=
|
||||
options are copied from /proc/cmdline. In general it is best to append
|
||||
command line options using "KDUMP_COMMANDLINE_APPEND=" instead of replacing
|
||||
the original command line completely.
|
||||
|
||||
How to disable FADump:
|
||||
|
||||
Remove "fadump=on"/"fadump=nocma" from kernel cmdline parameters OR replace
|
||||
it with "fadump=off" kernel cmdline parameter:
|
||||
|
||||
# grubby --update-kernel=/boot/vmlinuz-`uname -r` --remove-args="fadump=on"
|
||||
or
|
||||
# grubby --update-kernel=/boot/vmlinuz-`uname -r` --remove-args="fadump=nocma"
|
||||
OR
|
||||
# grubby --update-kernel=/boot/vmlinuz-`uname -r` --args="fadump=off"
|
||||
|
||||
Remove "crashkernel=" from kernel cmdline parameters:
|
||||
|
||||
# grubby --update-kernel=/boot/vmlinuz-`uname -r` --remove-args="crashkernel"
|
||||
|
||||
If KDump is to be used as the dump capturing mechanism, reset the crashkernel parameter:
|
||||
|
||||
# kdumpctl reset-crashkernel `uname -r`
|
||||
|
||||
Reboot the system for the settings to take effect.
|
||||
|
|
@ -0,0 +1,23 @@
|
|||
#!/bin/sh
|
||||
|
||||
# More details about systemd generator:
|
||||
# http://www.freedesktop.org/wiki/Software/systemd/Generators/
|
||||
|
||||
. /usr/lib/kdump/kdump-lib.sh
|
||||
. /usr/lib/kdump/kdump-logger.sh
|
||||
|
||||
# If invokded with no arguments for testing purpose, output to /tmp to
|
||||
# avoid overriding the existing.
|
||||
dest_dir="/tmp"
|
||||
|
||||
if [ -n "$1" ]; then
|
||||
dest_dir=$1
|
||||
fi
|
||||
|
||||
systemd_dir=/usr/lib/systemd/system
|
||||
kdump_wants=$dest_dir/kdump.service.wants
|
||||
|
||||
if is_ssh_dump_target; then
|
||||
mkdir -p $kdump_wants
|
||||
ln -sf $systemd_dir/network-online.target $kdump_wants/
|
||||
fi
|
||||
|
|
@ -0,0 +1,91 @@
|
|||
Kdump-in-cluster-environment HOWTO
|
||||
|
||||
Introduction
|
||||
|
||||
Kdump is a kexec based crash dumping mechansim for Linux. This docuement
|
||||
illustrate how to configure kdump in cluster environment to allow the kdump
|
||||
crash recovery service complete without being preempted by traditional power
|
||||
fencing methods.
|
||||
|
||||
Overview
|
||||
|
||||
Kexec/Kdump
|
||||
|
||||
Details about Kexec/Kdump are available in Kexec-Kdump-howto file and will not
|
||||
be described here.
|
||||
|
||||
fence_kdump
|
||||
|
||||
fence_kdump is an I/O fencing agent to be used with the kdump crash recovery
|
||||
service. When the fence_kdump agent is invoked, it will listen for a message
|
||||
from the failed node that acknowledges that the failed node is executing the
|
||||
kdump crash kernel. Note that fence_kdump is not a replacement for traditional
|
||||
fencing methods. The fence_kdump agent can only detect that a node has entered
|
||||
the kdump crash recovery service. This allows the kdump crash recovery service
|
||||
complete without being preempted by traditional power fencing methods.
|
||||
|
||||
fence_kdump_send
|
||||
|
||||
fence_kdump_send is a utility used to send messages that acknowledge that the
|
||||
node itself has entered the kdump crash recovery service. The fence_kdump_send
|
||||
utility is typically run in the kdump kernel after a cluster node has
|
||||
encountered a kernel panic. Once the cluster node has entered the kdump crash
|
||||
recovery service, fence_kdump_send will periodically send messages to all
|
||||
cluster nodes. When the fence_kdump agent receives a valid message from the
|
||||
failed nodes, fencing is complete.
|
||||
|
||||
How to configure Pacemaker cluster environment:
|
||||
|
||||
If we want to use kdump in Pacemaker cluster environment, fence-agents-kdump
|
||||
should be installed in every nodes in the cluster. You can achieve this via
|
||||
the following command:
|
||||
|
||||
# yum install -y fence-agents-kdump
|
||||
|
||||
Next is to add kdump_fence to the cluster. Assuming that the cluster consists
|
||||
of three nodes, they are node1, node2 and node3, and use Pacemaker to perform
|
||||
resource management and pcs as cli configuration tool.
|
||||
|
||||
With pcs it is easy to add a stonith resource to the cluster. For example, add
|
||||
a stonith resource named mykdumpfence with fence type of fence_kdump via the
|
||||
following commands:
|
||||
|
||||
# pcs stonith create mykdumpfence fence_kdump \
|
||||
pcmk_host_check=static-list pcmk_host_list="node1 node2 node3"
|
||||
# pcs stonith update mykdumpfence pcmk_monitor_action=metadata --force
|
||||
# pcs stonith update mykdumpfence pcmk_status_action=metadata --force
|
||||
# pcs stonith update mykdumpfence pcmk_reboot_action=off --force
|
||||
|
||||
Then enable stonith
|
||||
# pcs property set stonith-enabled=true
|
||||
|
||||
How to configure kdump:
|
||||
|
||||
Actually there are two ways how to configure fence_kdump support:
|
||||
|
||||
1) Pacemaker based clusters
|
||||
If you have successfully configured fence_kdump in Pacemaker, there is
|
||||
no need to add some special configuration in kdump. So please refer to
|
||||
Kexec-Kdump-howto file for more information.
|
||||
|
||||
2) Generic clusters
|
||||
For other types of clusters there are two configuration options in
|
||||
kdump.conf which enables fence_kdump support:
|
||||
|
||||
fence_kdump_nodes <node(s)>
|
||||
Contains list of cluster node(s) separated by space to send
|
||||
fence_kdump notification to (this option is mandatory to enable
|
||||
fence_kdump)
|
||||
|
||||
fence_kdump_args <arg(s)>
|
||||
Command line arguments for fence_kdump_send (it can contain
|
||||
all valid arguments except hosts to send notification to)
|
||||
|
||||
These options will most probably be configured by your cluster software,
|
||||
so please refer to your cluster documentation how to enable fence_kdump
|
||||
support.
|
||||
|
||||
Please be aware that these two ways cannot be combined and 2) has precedence
|
||||
over 1). It means that if fence_kdump is configured using fence_kdump_nodes
|
||||
and fence_kdump_args options in kdump.conf, Pacemaker configuration is not
|
||||
used even if it exists.
|
||||
|
|
@ -0,0 +1,293 @@
|
|||
# These variables and functions are useful in 2nd kernel
|
||||
|
||||
. /lib/kdump-lib.sh
|
||||
. /lib/kdump-logger.sh
|
||||
|
||||
KDUMP_PATH="/var/crash"
|
||||
KDUMP_LOG_FILE="/run/initramfs/kexec-dmesg.log"
|
||||
CORE_COLLECTOR=""
|
||||
DEFAULT_CORE_COLLECTOR="makedumpfile -l --message-level 7 -d 31"
|
||||
DMESG_COLLECTOR="/sbin/vmcore-dmesg"
|
||||
FAILURE_ACTION="systemctl reboot -f"
|
||||
DATEDIR=`date +%Y-%m-%d-%T`
|
||||
HOST_IP='127.0.0.1'
|
||||
DUMP_INSTRUCTION=""
|
||||
SSH_KEY_LOCATION="/root/.ssh/kdump_id_rsa"
|
||||
KDUMP_SCRIPT_DIR="/kdumpscripts"
|
||||
DD_BLKSIZE=512
|
||||
FINAL_ACTION="systemctl reboot -f"
|
||||
KDUMP_CONF="/etc/kdump.conf"
|
||||
KDUMP_PRE=""
|
||||
KDUMP_POST=""
|
||||
NEWROOT="/sysroot"
|
||||
OPALCORE="/sys/firmware/opal/mpipl/core"
|
||||
|
||||
#initiate the kdump logger
|
||||
dlog_init
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "failed to initiate the kdump logger."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
get_kdump_confs()
|
||||
{
|
||||
local config_opt config_val
|
||||
|
||||
while read config_opt config_val;
|
||||
do
|
||||
# remove inline comments after the end of a directive.
|
||||
case "$config_opt" in
|
||||
path)
|
||||
KDUMP_PATH="$config_val"
|
||||
;;
|
||||
core_collector)
|
||||
[ -n "$config_val" ] && CORE_COLLECTOR="$config_val"
|
||||
;;
|
||||
sshkey)
|
||||
if [ -f "$config_val" ]; then
|
||||
SSH_KEY_LOCATION=$config_val
|
||||
fi
|
||||
;;
|
||||
kdump_pre)
|
||||
KDUMP_PRE="$config_val"
|
||||
;;
|
||||
kdump_post)
|
||||
KDUMP_POST="$config_val"
|
||||
;;
|
||||
fence_kdump_args)
|
||||
FENCE_KDUMP_ARGS="$config_val"
|
||||
;;
|
||||
fence_kdump_nodes)
|
||||
FENCE_KDUMP_NODES="$config_val"
|
||||
;;
|
||||
failure_action|default)
|
||||
case $config_val in
|
||||
shell)
|
||||
FAILURE_ACTION="kdump_emergency_shell"
|
||||
;;
|
||||
reboot)
|
||||
FAILURE_ACTION="systemctl reboot -f && exit"
|
||||
;;
|
||||
halt)
|
||||
FAILURE_ACTION="halt && exit"
|
||||
;;
|
||||
poweroff)
|
||||
FAILURE_ACTION="systemctl poweroff -f && exit"
|
||||
;;
|
||||
dump_to_rootfs)
|
||||
FAILURE_ACTION="dump_to_rootfs"
|
||||
;;
|
||||
esac
|
||||
;;
|
||||
final_action)
|
||||
case $config_val in
|
||||
reboot)
|
||||
FINAL_ACTION="systemctl reboot -f"
|
||||
;;
|
||||
halt)
|
||||
FINAL_ACTION="halt"
|
||||
;;
|
||||
poweroff)
|
||||
FINAL_ACTION="systemctl poweroff -f"
|
||||
;;
|
||||
esac
|
||||
;;
|
||||
esac
|
||||
done <<< "$(read_strip_comments $KDUMP_CONF)"
|
||||
|
||||
if [ -z "$CORE_COLLECTOR" ]; then
|
||||
CORE_COLLECTOR="$DEFAULT_CORE_COLLECTOR"
|
||||
if is_ssh_dump_target || is_raw_dump_target; then
|
||||
CORE_COLLECTOR="$CORE_COLLECTOR -F"
|
||||
fi
|
||||
fi
|
||||
}
|
||||
|
||||
# store the kexec kernel log to a file.
|
||||
save_log()
|
||||
{
|
||||
dmesg -T > $KDUMP_LOG_FILE
|
||||
|
||||
if command -v journalctl > /dev/null; then
|
||||
journalctl -ab >> $KDUMP_LOG_FILE
|
||||
fi
|
||||
chmod 600 $KDUMP_LOG_FILE
|
||||
}
|
||||
|
||||
# dump_fs <mount point>
|
||||
dump_fs()
|
||||
{
|
||||
local _exitcode
|
||||
local _mp=$1
|
||||
local _op=$(get_mount_info OPTIONS target $_mp -f)
|
||||
ddebug "dump_fs _mp=$_mp _opts=$_op"
|
||||
|
||||
if ! is_mounted "$_mp"; then
|
||||
dinfo "dump path \"$_mp\" is not mounted, trying to mount..."
|
||||
mount --target $_mp
|
||||
if [ $? -ne 0 ]; then
|
||||
derror "failed to dump to \"$_mp\", it's not a mount point!"
|
||||
return 1
|
||||
fi
|
||||
fi
|
||||
|
||||
# Remove -F in makedumpfile case. We don't want a flat format dump here.
|
||||
[[ $CORE_COLLECTOR = *makedumpfile* ]] && CORE_COLLECTOR=`echo $CORE_COLLECTOR | sed -e "s/-F//g"`
|
||||
|
||||
local _dump_path=$(echo "$_mp/$KDUMP_PATH/$HOST_IP-$DATEDIR/" | tr -s /)
|
||||
|
||||
dinfo "saving to $_dump_path"
|
||||
|
||||
# Only remount to read-write mode if the dump target is mounted read-only.
|
||||
if [[ "$_op" = "ro"* ]]; then
|
||||
dinfo "Remounting the dump target in rw mode."
|
||||
mount -o remount,rw $_mp || return 1
|
||||
fi
|
||||
|
||||
mkdir -p $_dump_path || return 1
|
||||
|
||||
save_vmcore_dmesg_fs ${DMESG_COLLECTOR} "$_dump_path"
|
||||
save_opalcore_fs "$_dump_path"
|
||||
|
||||
dinfo "saving vmcore"
|
||||
$CORE_COLLECTOR /proc/vmcore $_dump_path/vmcore-incomplete
|
||||
_exitcode=$?
|
||||
if [ $_exitcode -eq 0 ]; then
|
||||
mv $_dump_path/vmcore-incomplete $_dump_path/vmcore
|
||||
sync
|
||||
dinfo "saving vmcore complete"
|
||||
else
|
||||
derror "saving vmcore failed, _exitcode:$_exitcode"
|
||||
fi
|
||||
|
||||
dinfo "saving the $KDUMP_LOG_FILE to $_dump_path/"
|
||||
save_log
|
||||
mv $KDUMP_LOG_FILE $_dump_path/
|
||||
if [ $_exitcode -ne 0 ]; then
|
||||
return 1
|
||||
fi
|
||||
|
||||
# improper kernel cmdline can cause the failure of echo, we can ignore this kind of failure
|
||||
return 0
|
||||
}
|
||||
|
||||
save_vmcore_dmesg_fs() {
|
||||
local _dmesg_collector=$1
|
||||
local _path=$2
|
||||
|
||||
dinfo "saving vmcore-dmesg.txt to ${_path}"
|
||||
$_dmesg_collector /proc/vmcore > ${_path}/vmcore-dmesg-incomplete.txt
|
||||
_exitcode=$?
|
||||
if [ $_exitcode -eq 0 ]; then
|
||||
mv ${_path}/vmcore-dmesg-incomplete.txt ${_path}/vmcore-dmesg.txt
|
||||
chmod 600 ${_path}/vmcore-dmesg.txt
|
||||
|
||||
# Make sure file is on disk. There have been instances where later
|
||||
# saving vmcore failed and system rebooted without sync and there
|
||||
# was no vmcore-dmesg.txt available.
|
||||
sync
|
||||
dinfo "saving vmcore-dmesg.txt complete"
|
||||
else
|
||||
if [ -f ${_path}/vmcore-dmesg-incomplete.txt ]; then
|
||||
chmod 600 ${_path}/vmcore-dmesg-incomplete.txt
|
||||
fi
|
||||
derror "saving vmcore-dmesg.txt failed"
|
||||
fi
|
||||
}
|
||||
|
||||
save_opalcore_fs() {
|
||||
local _path=$1
|
||||
|
||||
if [ ! -f $OPALCORE ]; then
|
||||
# Check if we are on an old kernel that uses a different path
|
||||
if [ -f /sys/firmware/opal/core ]; then
|
||||
OPALCORE="/sys/firmware/opal/core"
|
||||
else
|
||||
return 0
|
||||
fi
|
||||
fi
|
||||
|
||||
dinfo "saving opalcore:$OPALCORE to ${_path}/opalcore"
|
||||
cp $OPALCORE ${_path}/opalcore
|
||||
if [ $? -ne 0 ]; then
|
||||
derror "saving opalcore failed"
|
||||
return 1
|
||||
fi
|
||||
|
||||
sync
|
||||
dinfo "saving opalcore complete"
|
||||
return 0
|
||||
}
|
||||
|
||||
dump_to_rootfs()
|
||||
{
|
||||
|
||||
if [[ $(systemctl status dracut-initqueue | sed -n "s/^\s*Active: \(\S*\)\s.*$/\1/p") == "inactive" ]]; then
|
||||
dinfo "Trying to bring up initqueue for rootfs mount"
|
||||
systemctl start dracut-initqueue
|
||||
fi
|
||||
|
||||
dinfo "Clean up dead systemd services"
|
||||
systemctl cancel
|
||||
dinfo "Waiting for rootfs mount, will timeout after 90 seconds"
|
||||
systemctl start --no-block sysroot.mount
|
||||
|
||||
_loop=0
|
||||
while [ $_loop -lt 90 ] && ! is_mounted /sysroot; do
|
||||
sleep 1
|
||||
_loop=$((_loop + 1))
|
||||
done
|
||||
|
||||
if ! is_mounted /sysroot; then
|
||||
derror "Failed to mount rootfs"
|
||||
return
|
||||
fi
|
||||
|
||||
ddebug "NEWROOT=$NEWROOT"
|
||||
dump_fs $NEWROOT
|
||||
}
|
||||
|
||||
kdump_emergency_shell()
|
||||
{
|
||||
ddebug "Switching to kdump emergency shell..."
|
||||
|
||||
[ -f /etc/profile ] && . /etc/profile
|
||||
export PS1='kdump:${PWD}# '
|
||||
|
||||
. /lib/dracut-lib.sh
|
||||
if [ -f /dracut-state.sh ]; then
|
||||
. /dracut-state.sh 2>/dev/null
|
||||
fi
|
||||
|
||||
source_conf /etc/conf.d
|
||||
|
||||
type plymouth >/dev/null 2>&1 && plymouth quit
|
||||
|
||||
source_hook "emergency"
|
||||
while read _tty rest; do
|
||||
(
|
||||
echo
|
||||
echo
|
||||
echo 'Entering kdump emergency mode.'
|
||||
echo 'Type "journalctl" to view system logs.'
|
||||
echo 'Type "rdsosreport" to generate a sosreport, you can then'
|
||||
echo 'save it elsewhere and attach it to a bug report.'
|
||||
echo
|
||||
echo
|
||||
) > /dev/$_tty
|
||||
done < /proc/consoles
|
||||
sh -i -l
|
||||
/bin/rm -f -- /.console_lock
|
||||
}
|
||||
|
||||
do_failure_action()
|
||||
{
|
||||
dinfo "Executing failure action $FAILURE_ACTION"
|
||||
eval $FAILURE_ACTION
|
||||
}
|
||||
|
||||
do_final_action()
|
||||
{
|
||||
dinfo "Executing final action $FINAL_ACTION"
|
||||
eval $FINAL_ACTION
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,348 @@
|
|||
#!/bin/bash
|
||||
#
|
||||
# This comes from the dracut-logger.sh
|
||||
#
|
||||
# The logger defined 4 logging levels:
|
||||
# - ddebug (4)
|
||||
# The DEBUG Level designates fine-grained informational events that are most
|
||||
# useful to debug an application.
|
||||
# - dinfo (3)
|
||||
# The INFO level designates informational messages that highlight the
|
||||
# progress of the application at coarse-grained level.
|
||||
# - dwarn (2)
|
||||
# The WARN level designates potentially harmful situations.
|
||||
# - derror (1)
|
||||
# The ERROR level designates error events that might still allow the
|
||||
# application to continue running.
|
||||
#
|
||||
# Logging is controlled by following global variables:
|
||||
# - @var kdump_stdloglvl - logging level to standard error (console output)
|
||||
# - @var kdump_sysloglvl - logging level to syslog (by logger command)
|
||||
# - @var kdump_kmsgloglvl - logging level to /dev/kmsg (only for boot-time)
|
||||
#
|
||||
# If any of the variables is not set, the function dlog_init() sets it to default:
|
||||
# - In the first kernel:
|
||||
# - @var kdump_stdloglvl = 3 (info)
|
||||
# - @var kdump_sysloglvl = 0 (no logging)
|
||||
# - @var kdump_kmsgloglvl = 0 (no logging)
|
||||
#
|
||||
# -In the second kernel:
|
||||
# - @var kdump_stdloglvl = 0 (no logging)
|
||||
# - @var kdump_sysloglvl = 3 (info)
|
||||
# - @var kdump_kmsgloglvl = 0 (no logging)
|
||||
#
|
||||
# First of all you have to start with dlog_init() function which initializes
|
||||
# required variables. Don't call any other logging function before that one!
|
||||
#
|
||||
|
||||
# Define vairables for the log levels in this module.
|
||||
kdump_stdloglvl=""
|
||||
kdump_sysloglvl=""
|
||||
kdump_kmsgloglvl=""
|
||||
|
||||
# The dracut-lib.sh is only available in the second kernel, and it won't
|
||||
# be used in the first kernel because the dracut-lib.sh is invisible in
|
||||
# the first kernel.
|
||||
if [ -f /lib/dracut-lib.sh ]; then
|
||||
. /lib/dracut-lib.sh
|
||||
fi
|
||||
|
||||
# @brief Get the log level from kernel command line.
|
||||
# @retval 1 if something has gone wrong
|
||||
# @retval 0 on success.
|
||||
#
|
||||
get_kdump_loglvl()
|
||||
{
|
||||
(type -p getarg) && kdump_sysloglvl=$(getarg rd.kdumploglvl)
|
||||
[ -z "$kdump_sysloglvl" ] && return 1;
|
||||
|
||||
(type -p isdigit) && isdigit $kdump_sysloglvl
|
||||
[ $? -ne 0 ] && return 1;
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
# @brief Check the log level.
|
||||
# @retval 1 if something has gone wrong
|
||||
# @retval 0 on success.
|
||||
#
|
||||
check_loglvl()
|
||||
{
|
||||
case "$1" in
|
||||
0|1|2|3|4)
|
||||
return 0
|
||||
;;
|
||||
*)
|
||||
return 1
|
||||
;;
|
||||
esac
|
||||
}
|
||||
|
||||
# @brief Initializes Logger.
|
||||
# @retval 1 if something has gone wrong
|
||||
# @retval 0 on success.
|
||||
#
|
||||
dlog_init() {
|
||||
local ret=0; local errmsg
|
||||
|
||||
if [ -s /proc/vmcore ];then
|
||||
get_kdump_loglvl
|
||||
if [ $? -ne 0 ];then
|
||||
logger -t "kdump[$$]" -p warn -- "Kdump is using the default log level(3)."
|
||||
kdump_sysloglvl=3
|
||||
fi
|
||||
kdump_stdloglvl=0
|
||||
kdump_kmsgloglvl=0
|
||||
else
|
||||
kdump_stdloglvl=$KDUMP_STDLOGLVL
|
||||
kdump_sysloglvl=$KDUMP_SYSLOGLVL
|
||||
kdump_kmsgloglvl=$KDUMP_KMSGLOGLVL
|
||||
fi
|
||||
|
||||
[ -z "$kdump_stdloglvl" ] && kdump_stdloglvl=3
|
||||
[ -z "$kdump_sysloglvl" ] && kdump_sysloglvl=0
|
||||
[ -z "$kdump_kmsgloglvl" ] && kdump_kmsgloglvl=0
|
||||
|
||||
for loglvl in "$kdump_stdloglvl" "$kdump_kmsgloglvl" "$kdump_sysloglvl"; do
|
||||
check_loglvl "$loglvl"
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "Illegal log level: $kdump_stdloglvl $kdump_kmsgloglvl $kdump_sysloglvl"
|
||||
return 1
|
||||
fi
|
||||
done
|
||||
|
||||
# Skip initialization if it's already done.
|
||||
[ -n "$kdump_maxloglvl" ] && return 0
|
||||
|
||||
if [[ $UID -ne 0 ]]; then
|
||||
kdump_kmsgloglvl=0
|
||||
kdump_sysloglvl=0
|
||||
fi
|
||||
|
||||
if [[ $kdump_sysloglvl -gt 0 ]]; then
|
||||
if [[ -d /run/systemd/journal ]] \
|
||||
&& type -P systemd-cat &>/dev/null \
|
||||
&& systemctl --quiet is-active systemd-journald.socket &>/dev/null; then
|
||||
readonly _systemdcatfile="/var/tmp/systemd-cat"
|
||||
mkfifo "$_systemdcatfile" &>/dev/null
|
||||
readonly _dlogfd=15
|
||||
systemd-cat -t 'kdump' --level-prefix=true <"$_systemdcatfile" &
|
||||
exec 15>"$_systemdcatfile"
|
||||
elif ! [ -S /dev/log -a -w /dev/log ] || ! command -v logger >/dev/null; then
|
||||
# We cannot log to syslog, so turn this facility off.
|
||||
kdump_kmsgloglvl=$kdump_sysloglvl
|
||||
kdump_sysloglvl=0
|
||||
ret=1
|
||||
errmsg="No '/dev/log' or 'logger' included for syslog logging"
|
||||
fi
|
||||
fi
|
||||
|
||||
local lvl; local maxloglvl_l=0
|
||||
for lvl in $kdump_stdloglvl $kdump_sysloglvl $kdump_kmsgloglvl; do
|
||||
[[ $lvl -gt $maxloglvl_l ]] && maxloglvl_l=$lvl
|
||||
done
|
||||
readonly kdump_maxloglvl=$maxloglvl_l
|
||||
export kdump_maxloglvl
|
||||
|
||||
if [[ $kdump_stdloglvl -lt 4 ]] && [[ $kdump_kmsgloglvl -lt 4 ]] && [[ $kdump_sysloglvl -lt 4 ]]; then
|
||||
unset ddebug
|
||||
ddebug() { :; };
|
||||
fi
|
||||
|
||||
if [[ $kdump_stdloglvl -lt 3 ]] && [[ $kdump_kmsgloglvl -lt 3 ]] && [[ $kdump_sysloglvl -lt 3 ]]; then
|
||||
unset dinfo
|
||||
dinfo() { :; };
|
||||
fi
|
||||
|
||||
if [[ $kdump_stdloglvl -lt 2 ]] && [[ $kdump_kmsgloglvl -lt 2 ]] && [[ $kdump_sysloglvl -lt 2 ]]; then
|
||||
unset dwarn
|
||||
dwarn() { :; };
|
||||
unset dwarning
|
||||
dwarning() { :; };
|
||||
fi
|
||||
|
||||
if [[ $kdump_stdloglvl -lt 1 ]] && [[ $kdump_kmsgloglvl -lt 1 ]] && [[ $kdump_sysloglvl -lt 1 ]]; then
|
||||
unset derror
|
||||
derror() { :; };
|
||||
fi
|
||||
|
||||
[ -n "$errmsg" ] && derror "$errmsg"
|
||||
|
||||
return $ret
|
||||
}
|
||||
|
||||
## @brief Converts numeric level to logger priority defined by POSIX.2.
|
||||
#
|
||||
# @param lvl Numeric logging level in range from 1 to 4.
|
||||
# @retval 1 if @a lvl is out of range.
|
||||
# @retval 0 if @a lvl is correct.
|
||||
# @result Echoes logger priority.
|
||||
_lvl2syspri() {
|
||||
case "$1" in
|
||||
1) echo error;;
|
||||
2) echo warning;;
|
||||
3) echo info;;
|
||||
4) echo debug;;
|
||||
*) return 1;;
|
||||
esac
|
||||
}
|
||||
|
||||
## @brief Converts logger numeric level to syslog log level
|
||||
#
|
||||
# @param lvl Numeric logging level in range from 1 to 4.
|
||||
# @retval 1 if @a lvl is out of range.
|
||||
# @retval 0 if @a lvl is correct.
|
||||
# @result Echoes kernel console numeric log level
|
||||
#
|
||||
# Conversion is done as follows:
|
||||
#
|
||||
# <tt>
|
||||
# none -> LOG_EMERG (0)
|
||||
# none -> LOG_ALERT (1)
|
||||
# none -> LOG_CRIT (2)
|
||||
# ERROR(1) -> LOG_ERR (3)
|
||||
# WARN(2) -> LOG_WARNING (4)
|
||||
# none -> LOG_NOTICE (5)
|
||||
# INFO(3) -> LOG_INFO (6)
|
||||
# DEBUG(4) -> LOG_DEBUG (7)
|
||||
# </tt>
|
||||
#
|
||||
# @see /usr/include/sys/syslog.h
|
||||
_dlvl2syslvl() {
|
||||
local lvl
|
||||
|
||||
case "$1" in
|
||||
1) lvl=3;;
|
||||
2) lvl=4;;
|
||||
3) lvl=6;;
|
||||
4) lvl=7;;
|
||||
*) return 1;;
|
||||
esac
|
||||
|
||||
# The number is constructed by multiplying the facility by 8 and then
|
||||
# adding the level.
|
||||
# About The Syslog Protocol, please refer to the RFC5424 for more details.
|
||||
echo $((24+$lvl))
|
||||
}
|
||||
|
||||
## @brief Prints to stderr, to syslog and/or /dev/kmsg given message with
|
||||
# given level (priority).
|
||||
#
|
||||
# @param lvl Numeric logging level.
|
||||
# @param msg Message.
|
||||
# @retval 0 It's always returned, even if logging failed.
|
||||
#
|
||||
# @note This function is not supposed to be called manually. Please use
|
||||
# dinfo(), ddebug(), or others instead which wrap this one.
|
||||
#
|
||||
# This is core logging function which logs given message to standard error
|
||||
# and/or syslog (with POSIX shell command <tt>logger</tt>) and/or to /dev/kmsg.
|
||||
# The format is following:
|
||||
#
|
||||
# <tt>X: some message</tt>
|
||||
#
|
||||
# where @c X is the first letter of logging level. See module description for
|
||||
# details on that.
|
||||
#
|
||||
# Message to syslog is sent with tag @c kdump. Priorities are mapped as
|
||||
# following:
|
||||
# - @c ERROR to @c error
|
||||
# - @c WARN to @c warning
|
||||
# - @c INFO to @c info
|
||||
# - @c DEBUG to @c debug
|
||||
_do_dlog() {
|
||||
local lvl="$1"; shift
|
||||
local msg="$*"
|
||||
|
||||
[[ $lvl -le $kdump_stdloglvl ]] && printf -- 'kdump: %s\n' "$msg" >&2
|
||||
|
||||
if [[ $lvl -le $kdump_sysloglvl ]]; then
|
||||
if [[ "$_dlogfd" ]]; then
|
||||
printf -- "<%s>%s\n" "$(($(_dlvl2syslvl $lvl) & 7))" "$msg" >&$_dlogfd
|
||||
else
|
||||
logger -t "kdump[$$]" -p $(_lvl2syspri $lvl) -- "$msg"
|
||||
fi
|
||||
fi
|
||||
|
||||
[[ $lvl -le $kdump_kmsgloglvl ]] && \
|
||||
echo "<$(_dlvl2syslvl $lvl)>kdump[$$] $msg" >/dev/kmsg
|
||||
}
|
||||
|
||||
## @brief Internal helper function for _do_dlog()
|
||||
#
|
||||
# @param lvl Numeric logging level.
|
||||
# @param msg Message.
|
||||
# @retval 0 It's always returned, even if logging failed.
|
||||
#
|
||||
# @note This function is not supposed to be called manually. Please use
|
||||
# dinfo(), ddebug(), or others instead which wrap this one.
|
||||
#
|
||||
# This function calls _do_dlog() either with parameter msg, or if
|
||||
# none is given, it will read standard input and will use every line as
|
||||
# a message.
|
||||
#
|
||||
# This enables:
|
||||
# dwarn "This is a warning"
|
||||
# echo "This is a warning" | dwarn
|
||||
dlog() {
|
||||
[ -z "$kdump_maxloglvl" ] && return 0
|
||||
[[ $1 -le $kdump_maxloglvl ]] || return 0
|
||||
|
||||
if [[ $# -gt 1 ]]; then
|
||||
_do_dlog "$@"
|
||||
else
|
||||
while read line || [ -n "$line" ]; do
|
||||
_do_dlog "$1" "$line"
|
||||
done
|
||||
fi
|
||||
}
|
||||
|
||||
## @brief Logs message at DEBUG level (4)
|
||||
#
|
||||
# @param msg Message.
|
||||
# @retval 0 It's always returned, even if logging failed.
|
||||
ddebug() {
|
||||
set +x
|
||||
dlog 4 "$@"
|
||||
[ -n "$debug" ] && set -x || :
|
||||
}
|
||||
|
||||
## @brief Logs message at INFO level (3)
|
||||
#
|
||||
# @param msg Message.
|
||||
# @retval 0 It's always returned, even if logging failed.
|
||||
dinfo() {
|
||||
set +x
|
||||
dlog 3 "$@"
|
||||
[ -n "$debug" ] && set -x || :
|
||||
}
|
||||
|
||||
## @brief Logs message at WARN level (2)
|
||||
#
|
||||
# @param msg Message.
|
||||
# @retval 0 It's always returned, even if logging failed.
|
||||
dwarn() {
|
||||
set +x
|
||||
dlog 2 "$@"
|
||||
[ -n "$debug" ] && set -x || :
|
||||
}
|
||||
|
||||
## @brief It's an alias to dwarn() function.
|
||||
#
|
||||
# @param msg Message.
|
||||
# @retval 0 It's always returned, even if logging failed.
|
||||
dwarning() {
|
||||
set +x
|
||||
dwarn "$@"
|
||||
[ -n "$debug" ] && set -x || :
|
||||
}
|
||||
|
||||
## @brief Logs message at ERROR level (1)
|
||||
#
|
||||
# @param msg Message.
|
||||
# @retval 0 It's always returned, even if logging failed.
|
||||
derror() {
|
||||
set +x
|
||||
dlog 1 "$@"
|
||||
[ -n "$debug" ] && set -x || :
|
||||
}
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
#!/bin/bash
|
||||
# This util helps to reduce the workload of kdump service restarting
|
||||
# on udev event. When hotplugging memory / CPU, multiple udev
|
||||
# events may be triggered concurrently, and obviously, we don't want
|
||||
# to restart kdump service for each event.
|
||||
|
||||
# This script will be called by udev, and make sure kdump service is
|
||||
# restart after all events we are watching are settled.
|
||||
|
||||
# On each call, this script will update try to aquire the $throttle_lock
|
||||
# The first instance acquired the file lock will keep waiting for events
|
||||
# to settle and then reload kdump. Other instances will just exit
|
||||
# In this way, we can make sure kdump service is restarted immediately
|
||||
# and for exactly once after udev events are settled.
|
||||
|
||||
throttle_lock="/var/lock/kdump-udev-throttle"
|
||||
|
||||
exec 9>$throttle_lock
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "Failed to create the lock file! Fallback to non-throttled kdump service restart"
|
||||
/bin/kdumpctl reload
|
||||
exit 1
|
||||
fi
|
||||
|
||||
flock -n 9
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "Throttling kdump restart for concurrent udev event"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# Wait for at least 1 second, at most 4 seconds for udev to settle
|
||||
# Idealy we will have a less than 1 second lag between udev events settle
|
||||
# and kdump reload
|
||||
sleep 1 && udevadm settle --timeout 3
|
||||
|
||||
# Release the lock, /bin/kdumpctl will block and make the process
|
||||
# holding two locks at the same time and we might miss some events
|
||||
exec 9>&-
|
||||
|
||||
/bin/kdumpctl reload
|
||||
|
||||
exit 0
|
||||
|
|
@ -0,0 +1,185 @@
|
|||
# This file contains a series of commands to perform (in order) in the kdump
|
||||
# kernel after a kernel crash in the crash kernel(1st kernel) has happened.
|
||||
#
|
||||
# Directives in this file are only applicable to the kdump initramfs, and have
|
||||
# no effect once the root filesystem is mounted and the normal init scripts are
|
||||
# processed.
|
||||
#
|
||||
# Currently, only one dump target and path can be specified. If the dumping to
|
||||
# the configured target fails, the failure action which can be configured via
|
||||
# the "failure_action" directive will be performed.
|
||||
#
|
||||
# Supported options:
|
||||
#
|
||||
# raw <partition>
|
||||
# - Will dd /proc/vmcore into <partition>.
|
||||
# Use persistent device names for partition devices,
|
||||
# such as /dev/vg/<devname>.
|
||||
#
|
||||
# nfs <nfs mount>
|
||||
# - Will mount nfs to <mnt>, and copy /proc/vmcore to
|
||||
# <mnt>/<path>/%HOST-%DATE/, supports DNS.
|
||||
#
|
||||
# ssh <user@server>
|
||||
# - Will save /proc/vmcore to <user@server>:<path>/%HOST-%DATE/,
|
||||
# supports DNS.
|
||||
# NOTE: make sure the user has write permissions on the server.
|
||||
#
|
||||
# sshkey <path>
|
||||
# - Will use the sshkey to do ssh dump.
|
||||
# Specify the path of the ssh key to use when dumping
|
||||
# via ssh. The default value is /root/.ssh/kdump_id_rsa.
|
||||
#
|
||||
# <fs type> <partition>
|
||||
# - Will mount -t <fs type> <partition> <mnt>, and copy
|
||||
# /proc/vmcore to <mnt>/<path>/%HOST_IP-%DATE/.
|
||||
# NOTE: <partition> can be a device node, label or uuid.
|
||||
# It's recommended to use persistent device names
|
||||
# such as /dev/vg/<devname>.
|
||||
# Otherwise it's suggested to use label or uuid.
|
||||
#
|
||||
# path <path>
|
||||
# - "path" represents the file system path in which vmcore
|
||||
# will be saved. If a dump target is specified in
|
||||
# kdump.conf, then "path" is relative to the specified
|
||||
# dump target.
|
||||
#
|
||||
# Interpretation of "path" changes a bit if the user didn't
|
||||
# specify any dump target explicitly in kdump.conf. In this
|
||||
# case, "path" represents the absolute path from root. The
|
||||
# dump target and adjusted path are arrived at automatically
|
||||
# depending on what's mounted in the current system.
|
||||
#
|
||||
# Ignored for raw device dumps. If unset, will use the default
|
||||
# "/var/crash".
|
||||
#
|
||||
# core_collector <command> <options>
|
||||
# - This allows you to specify the command to copy
|
||||
# the vmcore. The default is makedumpfile, which on
|
||||
# some architectures can drastically reduce vmcore size.
|
||||
# See /sbin/makedumpfile --help for a list of options.
|
||||
# Note that the -i and -g options are not needed here,
|
||||
# as the initrd will automatically be populated with a
|
||||
# config file appropriate for the running kernel.
|
||||
# The default core_collector for raw/ssh dump is:
|
||||
# "makedumpfile -F -l --message-level 7 -d 31".
|
||||
# The default core_collector for other targets is:
|
||||
# "makedumpfile -l --message-level 7 -d 31".
|
||||
#
|
||||
# "makedumpfile -F" will create a flattened vmcore.
|
||||
# You need to use "makedumpfile -R" to rearrange the dump data to
|
||||
# a normal dumpfile readable with analysis tools. For example:
|
||||
# "makedumpfile -R vmcore < vmcore.flat".
|
||||
#
|
||||
# For core_collector format details, you can refer to
|
||||
# kexec-kdump-howto.txt or kdump.conf manpage.
|
||||
#
|
||||
# kdump_post <binary | script>
|
||||
# - This directive allows you to run a executable binary
|
||||
# or script after the vmcore dump process terminates.
|
||||
# The exit status of the current dump process is fed to
|
||||
# the executable binary or script as its first argument.
|
||||
# All files under /etc/kdump/post.d are collectively sorted
|
||||
# and executed in lexical order, before binary or script
|
||||
# specified kdump_post parameter is executed.
|
||||
#
|
||||
# kdump_pre <binary | script>
|
||||
# - Works like the "kdump_post" directive, but instead of running
|
||||
# after the dump process, runs immediately before it.
|
||||
# Exit status of this binary is interpreted as follows:
|
||||
# 0 - continue with dump process as usual
|
||||
# non 0 - run the final action (reboot/poweroff/halt)
|
||||
# All files under /etc/kdump/pre.d are collectively sorted and
|
||||
# executed in lexical order, after binary or script specified
|
||||
# kdump_pre parameter is executed.
|
||||
# Even if the binary or script in /etc/kdump/pre.d directory
|
||||
# returns non 0 exit status, the processing is continued.
|
||||
#
|
||||
# extra_bins <binaries | shell scripts>
|
||||
# - This directive allows you to specify additional binaries or
|
||||
# shell scripts to be included in the kdump initrd.
|
||||
# Generally they are useful in conjunction with a kdump_post
|
||||
# or kdump_pre binary or script which depends on these extra_bins.
|
||||
#
|
||||
# extra_modules <module(s)>
|
||||
# - This directive allows you to specify extra kernel modules
|
||||
# that you want to be loaded in the kdump initrd.
|
||||
# Multiple modules can be listed, separated by spaces, and any
|
||||
# dependent modules will automatically be included.
|
||||
#
|
||||
# failure_action <reboot | halt | poweroff | shell | dump_to_rootfs>
|
||||
# - Action to perform in case dumping fails.
|
||||
# reboot: Reboot the system.
|
||||
# halt: Halt the system.
|
||||
# poweroff: Power down the system.
|
||||
# shell: Drop to a bash shell.
|
||||
# Exiting the shell reboots the system by default,
|
||||
# or perform "final_action".
|
||||
# dump_to_rootfs: Dump vmcore to rootfs from initramfs context and
|
||||
# reboot by default or perform "final_action".
|
||||
# Useful when non-root dump target is specified.
|
||||
# The default option is "reboot".
|
||||
#
|
||||
# default <reboot | halt | poweroff | shell | dump_to_rootfs>
|
||||
# - Same as the "failure_action" directive above, but this directive
|
||||
# is obsolete and will be removed in the future.
|
||||
#
|
||||
# final_action <reboot | halt | poweroff>
|
||||
# - Action to perform in case dumping succeeds. Also performed
|
||||
# when "shell" or "dump_to_rootfs" failure action finishes.
|
||||
# Each action is same as the "failure_action" directive above.
|
||||
# The default is "reboot".
|
||||
#
|
||||
# force_rebuild <0 | 1>
|
||||
# - By default, kdump initrd will only be rebuilt when necessary.
|
||||
# Specify 1 to force rebuilding kdump initrd every time when kdump
|
||||
# service starts.
|
||||
#
|
||||
# force_no_rebuild <0 | 1>
|
||||
# - By default, kdump initrd will be rebuilt when necessary.
|
||||
# Specify 1 to bypass rebuilding of kdump initrd.
|
||||
#
|
||||
# force_no_rebuild and force_rebuild options are mutually
|
||||
# exclusive and they should not be set to 1 simultaneously.
|
||||
#
|
||||
# override_resettable <0 | 1>
|
||||
# - Usually an unresettable block device can't be a dump target.
|
||||
# Specifying 1 when you want to dump even though the block
|
||||
# target is unresettable
|
||||
# By default, it is 0, which will not try dumping destined to fail.
|
||||
#
|
||||
# dracut_args <arg(s)>
|
||||
# - Pass extra dracut options when rebuilding kdump initrd.
|
||||
#
|
||||
# fence_kdump_args <arg(s)>
|
||||
# - Command line arguments for fence_kdump_send (it can contain
|
||||
# all valid arguments except hosts to send notification to).
|
||||
#
|
||||
# fence_kdump_nodes <node(s)>
|
||||
# - List of cluster node(s) except localhost, separated by spaces,
|
||||
# to send fence_kdump notifications to.
|
||||
# (this option is mandatory to enable fence_kdump).
|
||||
#
|
||||
|
||||
#raw /dev/vg/lv_kdump
|
||||
#ext4 /dev/vg/lv_kdump
|
||||
#ext4 LABEL=/boot
|
||||
#ext4 UUID=03138356-5e61-4ab3-b58e-27507ac41937
|
||||
#nfs my.server.com:/export/tmp
|
||||
#nfs [2001:db8::1:2:3:4]:/export/tmp
|
||||
#ssh user@my.server.com
|
||||
#ssh user@2001:db8::1:2:3:4
|
||||
#sshkey /root/.ssh/kdump_id_rsa
|
||||
path /var/crash
|
||||
core_collector makedumpfile -l --message-level 7 -d 31
|
||||
#core_collector scp
|
||||
#kdump_post /var/crash/scripts/kdump-post.sh
|
||||
#kdump_pre /var/crash/scripts/kdump-pre.sh
|
||||
#extra_bins /usr/bin/lftp
|
||||
#extra_modules gfs2
|
||||
#failure_action shell
|
||||
#force_rebuild 1
|
||||
#force_no_rebuild 1
|
||||
#dracut_args --omit-drivers "cfg80211 snd" --add-drivers "ext2 ext3"
|
||||
#fence_kdump_args -p 7410 -f auto -c 0 -i 10
|
||||
#fence_kdump_nodes node1 node2
|
||||
|
|
@ -0,0 +1,375 @@
|
|||
.TH KDUMP.CONF 5 "07/23/2008" "kexec-tools"
|
||||
|
||||
.SH NAME
|
||||
kdump.conf \- configuration file for kdump kernel.
|
||||
|
||||
.SH DESCRIPTION
|
||||
|
||||
kdump.conf is a configuration file for the kdump kernel crash
|
||||
collection service.
|
||||
|
||||
kdump.conf provides post-kexec instructions to the kdump kernel. It is
|
||||
stored in the initrd file managed by the kdump service. If you change
|
||||
this file and do not want to reboot in order for the changes to take
|
||||
effect, restart the kdump service to rebuild the initrd.
|
||||
|
||||
For most configurations, you can simply review the examples provided
|
||||
in the stock /etc/kdump.conf.
|
||||
|
||||
.B NOTE:
|
||||
For filesystem dumps the dump target must be mounted before building
|
||||
kdump initramfs.
|
||||
|
||||
kdump.conf only affects the behavior of the initramfs. Please read the
|
||||
kdump operational flow section of kexec-kdump-howto.txt in the docs to better
|
||||
understand how this configuration file affects the behavior of kdump.
|
||||
|
||||
.SH OPTIONS
|
||||
|
||||
.B raw <partition>
|
||||
.RS
|
||||
Will dd /proc/vmcore into <partition>. Use persistent device names for
|
||||
partition devices, such as /dev/vg/<devname>.
|
||||
.RE
|
||||
|
||||
.B nfs <nfs mount>
|
||||
.RS
|
||||
Will mount nfs to <mnt>, and copy /proc/vmcore to <mnt>/<path>/%HOST-%DATE/,
|
||||
supports DNS. Note that a fqdn should be used as the server name in the
|
||||
mount point.
|
||||
.RE
|
||||
|
||||
.B ssh <user@server>
|
||||
.RS
|
||||
Will save /proc/vmcore through ssh pipe to <user@server>:<path>/%HOST-%DATE/,
|
||||
supports DNS. NOTE: make sure user has necessary write permissions on
|
||||
server and that a fqdn is used as the server name.
|
||||
.RE
|
||||
|
||||
.B sshkey <path>
|
||||
.RS
|
||||
Specify the path of the ssh key to use when dumping via ssh.
|
||||
The default value is /root/.ssh/kdump_id_rsa.
|
||||
.RE
|
||||
|
||||
.B <fs type> <partition>
|
||||
.RS
|
||||
Will mount -t <fs type> <partition> <mnt>, and copy /proc/vmcore to
|
||||
<mnt>/<path>/%HOST_IP-%DATE/. NOTE: <partition> can be a device node, label
|
||||
or uuid. It's recommended to use persistent device names such as
|
||||
/dev/vg/<devname>. Otherwise it's suggested to use label or uuid.
|
||||
.RE
|
||||
|
||||
.B path <path>
|
||||
.RS
|
||||
"path" represents the file system path in which vmcore will be saved.
|
||||
If a dump target is specified in kdump.conf, then "path" is relative to the
|
||||
specified dump target.
|
||||
.PP
|
||||
Interpretation of "path" changes a bit if the user didn't specify any dump
|
||||
target explicitly in kdump.conf. In this case, "path" represents the
|
||||
absolute path from root. The dump target and adjusted path are arrived
|
||||
at automatically depending on what's mounted in the current system.
|
||||
.PP
|
||||
Ignored for raw device dumps. If unset, will use the default "/var/crash".
|
||||
.RE
|
||||
|
||||
.B core_collector <command> <options>
|
||||
.RS
|
||||
This allows you to specify the command to copy the vmcore.
|
||||
The default is makedumpfile, which on some architectures can drastically reduce
|
||||
core file size. See /sbin/makedumpfile --help for a list of options.
|
||||
Note that the -i and -g options are not needed here, as the initrd
|
||||
will automatically be populated with a config file appropriate
|
||||
for the running kernel.
|
||||
.PP
|
||||
Note 1: About default core collector:
|
||||
The default core_collector for raw/ssh dump is:
|
||||
"makedumpfile -F -l --message-level 7 -d 31".
|
||||
The default core_collector for other targets is:
|
||||
"makedumpfile -l --message-level 7 -d 31".
|
||||
Even if core_collector option is commented out in kdump.conf, makedumpfile
|
||||
is the default core collector and kdump uses it internally.
|
||||
If one does not want makedumpfile as default core_collector, then they
|
||||
need to specify one using core_collector option to change the behavior.
|
||||
.PP
|
||||
Note 2: If "makedumpfile -F" is used then you will get a flattened format
|
||||
vmcore.flat, you will need to use "makedumpfile -R" to rearrange the
|
||||
dump data from standard input to a normal dumpfile (readable with analysis
|
||||
tools).
|
||||
ie. "makedumpfile -R vmcore < vmcore.flat"
|
||||
.PP
|
||||
Note 3: If specified core_collector simply copy the vmcore file to the
|
||||
dump target (eg: cp, scp), the vmcore could be significantly large.
|
||||
Please make sure the dump target has enough space, at leaset larger
|
||||
than the system's RAM.
|
||||
|
||||
.RE
|
||||
|
||||
.B kdump_post <binary | script>
|
||||
.RS
|
||||
This directive allows you to run a specified executable
|
||||
just after the vmcore dump process terminates. The exit
|
||||
status of the current dump process is fed to the kdump_post
|
||||
executable as its first argument($1). Executable can modify
|
||||
it to indicate the new exit status of succeeding dump process,
|
||||
.PP
|
||||
All files under /etc/kdump/post.d are collectively sorted
|
||||
and executed in lexical order, before binary or script
|
||||
specified kdump_post parameter is executed.
|
||||
.PP
|
||||
Note that scripts written for use with this directive must use
|
||||
the /bin/bash interpreter.
|
||||
.RE
|
||||
|
||||
.B kdump_pre <binary | script>
|
||||
.RS
|
||||
Works just like the "kdump_post" directive, but instead
|
||||
of running after the dump process, runs immediately
|
||||
before. Exit status of this binary is interpreted
|
||||
as follows:
|
||||
.PP
|
||||
0 - continue with dump process as usual
|
||||
.PP
|
||||
non 0 - run the final action (reboot/poweroff/halt)
|
||||
.PP
|
||||
All files under /etc/kdump/pre.d are collectively sorted and
|
||||
executed in lexical order, after binary or script specified
|
||||
kdump_pre parameter is executed.
|
||||
Even if the binary or script in /etc/kdump/pre.d directory
|
||||
returns non 0 exit status, the processing is continued.
|
||||
.PP
|
||||
Note that scripts written for this directive must use
|
||||
the /bin/bash interpreter.
|
||||
.RE
|
||||
|
||||
.B extra_bins <binaries | shell scripts>
|
||||
.RS
|
||||
This directive allows you to specify additional
|
||||
binaries or shell scripts you'd like to include in
|
||||
your kdump initrd. Generally only useful in
|
||||
conjunction with a kdump_post binary or script that
|
||||
relies on other binaries or scripts.
|
||||
.RE
|
||||
|
||||
.B extra_modules <module(s)>
|
||||
.RS
|
||||
This directive allows you to specify extra kernel
|
||||
modules that you want to be loaded in the kdump
|
||||
initrd, typically used to set up access to
|
||||
non-boot-path dump targets that might otherwise
|
||||
not be accessible in the kdump environment. Multiple
|
||||
modules can be listed, separated by spaces, and any
|
||||
dependent modules will automatically be included.
|
||||
.RE
|
||||
|
||||
.B failure_action <reboot | halt | poweroff | shell | dump_to_rootfs>
|
||||
.RS
|
||||
Action to perform in case dumping to the intended target fails. The default is "reboot".
|
||||
reboot: Reboot the system (this is what most people will want, as it returns the system
|
||||
to a normal state). halt: Halt the system and lose the vmcore. poweroff: The system
|
||||
will be powered down. shell: Drop to a shell session inside the initramfs, from which
|
||||
you can manually perform additional recovery actions. Exiting this shell reboots the
|
||||
system by default or performs "final_action".
|
||||
Note: kdump uses bash as the default shell. dump_to_rootfs: If non-root dump
|
||||
target is specified, the failure action can be set as dump_to_rootfs. That means when
|
||||
dumping to target fails, dump vmcore to rootfs from initramfs context and reboot
|
||||
by default or perform "final_action".
|
||||
.RE
|
||||
|
||||
.B default <reboot | halt | poweroff | shell | dump_to_rootfs>
|
||||
.RS
|
||||
Same as the "failure_action" directive above, but this directive is obsolete
|
||||
and will be removed in the future.
|
||||
.RE
|
||||
|
||||
.B final_action <reboot | halt | poweroff>
|
||||
.RS
|
||||
Action to perform in case dumping to the intended target succeeds.
|
||||
Also performed when "shell" or "dump_to_rootfs" failure action finishes.
|
||||
Each action is same as the "failure_action" directive above.
|
||||
The default is "reboot".
|
||||
.RE
|
||||
|
||||
.B force_rebuild <0 | 1>
|
||||
.RS
|
||||
By default, kdump initrd will only be rebuilt when necessary.
|
||||
Specify 1 to force rebuilding kdump initrd every time when kdump service starts.
|
||||
.RE
|
||||
|
||||
.B force_no_rebuild <0 | 1>
|
||||
.RS
|
||||
By default, kdump initrd will be rebuilt when necessary.
|
||||
Specify 1 to bypass rebuilding of kdump initrd.
|
||||
|
||||
.PP
|
||||
force_no_rebuild and force_rebuild options are mutually exclusive and
|
||||
they should not be set to 1 simultaneously.
|
||||
.RE
|
||||
|
||||
.B override_resettable <0 | 1>
|
||||
.RS
|
||||
Usually an unresettable block device can't be a dump target. Specifying 1 means
|
||||
that even though the block target is unresettable, the user wants to try dumping anyway.
|
||||
By default, it's set to 0, which will not try something destined to fail.
|
||||
.RE
|
||||
|
||||
|
||||
.B dracut_args <arg(s)>
|
||||
.RS
|
||||
Kdump uses dracut to generate initramfs for second kernel. This option
|
||||
allows a user to pass arguments to dracut directly.
|
||||
.RE
|
||||
|
||||
|
||||
.B fence_kdump_args <arg(s)>
|
||||
.RS
|
||||
Command line arguments for fence_kdump_send (it can contain all valid
|
||||
arguments except hosts to send notification to).
|
||||
.RE
|
||||
|
||||
|
||||
.B fence_kdump_nodes <node(s)>
|
||||
.RS
|
||||
List of cluster node(s) except localhost, separated by spaces, to send fence_kdump notification
|
||||
to (this option is mandatory to enable fence_kdump).
|
||||
.RE
|
||||
|
||||
|
||||
.SH DEPRECATED OPTIONS
|
||||
|
||||
.B net <nfs mount>|<user@server>
|
||||
.RS
|
||||
net option is replaced by nfs and ssh options. Use nfs or ssh options
|
||||
directly.
|
||||
.RE
|
||||
|
||||
.B options <module> <option list>
|
||||
.RS
|
||||
Use KDUMP_COMMANDLINE_APPEND in /etc/sysconfig/kdump to add module options as
|
||||
kernel command line parameters. For example, specify 'loop.max_loop=1' to limit
|
||||
maximum loop devices to 1.
|
||||
.RE
|
||||
|
||||
.B link_delay <seconds>
|
||||
.RS
|
||||
link_delay was used to wait for a network device to initialize before using it.
|
||||
Now dracut network module takes care of this issue automatically.
|
||||
.RE
|
||||
|
||||
.B disk_timeout <seconds>
|
||||
.RS
|
||||
Similar to link_delay, dracut ensures disks are ready before kdump uses them.
|
||||
.RE
|
||||
|
||||
.B debug_mem_level <0-3>
|
||||
.RS
|
||||
Turn on verbose debug output of kdump scripts regarding free/used memory at
|
||||
various points of execution. This feature has been
|
||||
moved to dracut now.
|
||||
Use KDUMP_COMMANDLINE_APPEND in /etc/sysconfig/kdump and
|
||||
append dracut cmdline param rd.memdebug=[0-3] to enable the debug output.
|
||||
|
||||
Higher level means more debugging output.
|
||||
.PP
|
||||
0 - no output
|
||||
.PP
|
||||
1 - partial /proc/meminfo
|
||||
.PP
|
||||
2 - /proc/meminfo
|
||||
.PP
|
||||
3 - /proc/meminfo + /proc/slabinfo
|
||||
.RE
|
||||
|
||||
.B blacklist <list of kernel modules>
|
||||
.RS
|
||||
blacklist option was recently being used to prevent loading modules in
|
||||
initramfs. General terminology for blacklist has been that module is
|
||||
present in initramfs but it is not actually loaded in kernel. Hence
|
||||
retaining blacklist option creates more confusing behavior. It has been
|
||||
deprecated.
|
||||
.PP
|
||||
Instead, use rd.driver.blacklist option on second kernel to blacklist
|
||||
a certain module. One can edit /etc/sysconfig/kdump.conf and edit
|
||||
KDUMP_COMMANDLINE_APPEND to pass kernel command line options. Refer
|
||||
to dracut.cmdline man page for more details on module blacklist option.
|
||||
.RE
|
||||
|
||||
.RE
|
||||
|
||||
.SH EXAMPLES
|
||||
Here are some examples for core_collector option:
|
||||
.PP
|
||||
Core collector command format depends on dump target type. Typically for
|
||||
filesystem (local/remote), core_collector should accept two arguments.
|
||||
First one is source file and second one is target file. For ex.
|
||||
.TP
|
||||
ex1.
|
||||
core_collector "cp --sparse=always"
|
||||
|
||||
Above will effectively be translated to:
|
||||
|
||||
cp --sparse=always /proc/vmcore <dest-path>/vmcore
|
||||
.TP
|
||||
ex2.
|
||||
core_collector "makedumpfile -l --message-level 7 -d 31"
|
||||
|
||||
Above will effectively be translated to:
|
||||
|
||||
makedumpfile -l --message-level 7 -d 31 /proc/vmcore <dest-path>/vmcore
|
||||
.PP
|
||||
For dump targets like raw and ssh, in general, core collector should expect
|
||||
one argument (source file) and should output the processed core on standard
|
||||
output (There is one exception of "scp", discussed later). This standard
|
||||
output will be saved to destination using appropriate commands.
|
||||
|
||||
raw dumps examples:
|
||||
.TP
|
||||
ex3.
|
||||
core_collector "cat"
|
||||
|
||||
Above will effectively be translated to.
|
||||
|
||||
cat /proc/vmcore | dd of=<target-device>
|
||||
.TP
|
||||
ex4.
|
||||
core_collector "makedumpfile -F -l --message-level 7 -d 31"
|
||||
|
||||
Above will effectively be translated to.
|
||||
|
||||
makedumpfile -F -l --message-level 7 -d 31 | dd of=<target-device>
|
||||
.PP
|
||||
ssh dumps examples
|
||||
.TP
|
||||
ex5.
|
||||
core_collector "cat"
|
||||
|
||||
Above will effectively be translated to.
|
||||
|
||||
cat /proc/vmcore | ssh <options> <remote-location> "dd of=path/vmcore"
|
||||
.TP
|
||||
ex6.
|
||||
core_collector "makedumpfile -F -l --message-level 7 -d 31"
|
||||
|
||||
Above will effectively be translated to.
|
||||
|
||||
makedumpfile -F -l --message-level 7 -d 31 | ssh <options> <remote-location> "dd of=path/vmcore"
|
||||
|
||||
There is one exception to standard output rule for ssh dumps. And that is
|
||||
scp. As scp can handle ssh destinations for file transfers, one can
|
||||
specify "scp" as core collector for ssh targets (no output on stdout).
|
||||
.TP
|
||||
ex7.
|
||||
core_collector "scp"
|
||||
|
||||
Above will effectively be translated to.
|
||||
|
||||
scp /proc/vmcore <user@host>:path/vmcore
|
||||
|
||||
.PP
|
||||
examples for other options please see
|
||||
.I /etc/kdump.conf
|
||||
|
||||
.SH SEE ALSO
|
||||
|
||||
kexec(8) mkdumprd(8) dracut.cmdline(7)
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
[Unit]
|
||||
Description=Crash recovery kernel arming
|
||||
After=network.target network-online.target remote-fs.target basic.target
|
||||
DefaultDependencies=no
|
||||
ConditionKernelCommandLine=crashkernel
|
||||
|
||||
[Service]
|
||||
Type=oneshot
|
||||
ExecStart=/usr/bin/kdumpctl start
|
||||
ExecStop=/usr/bin/kdumpctl stop
|
||||
ExecReload=/usr/bin/kdumpctl reload
|
||||
RemainAfterExit=yes
|
||||
StartLimitInterval=0
|
||||
|
||||
[Install]
|
||||
WantedBy=multi-user.target
|
||||
|
|
@ -0,0 +1,53 @@
|
|||
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
|
||||
# If no version is specified, then the init script will try to find a
|
||||
# kdump kernel with the same version number as the running kernel.
|
||||
KDUMP_KERNELVER=""
|
||||
|
||||
# The kdump commandline is the command line that needs to be passed off to
|
||||
# the kdump kernel. This will likely match the contents of the grub kernel
|
||||
# line. For example:
|
||||
# KDUMP_COMMANDLINE="ro root=LABEL=/"
|
||||
# Dracut depends on proper root= options, so please make sure that appropriate
|
||||
# root= options are copied from /proc/cmdline. In general it is best to append
|
||||
# command line options using "KDUMP_COMMANDLINE_APPEND=".
|
||||
# If a command line is not specified, the default will be taken from
|
||||
# /proc/cmdline
|
||||
KDUMP_COMMANDLINE=""
|
||||
|
||||
# This variable lets us remove arguments from the current kdump commandline
|
||||
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
|
||||
# NOTE: some arguments such as crashkernel will always be removed
|
||||
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len swiotlb cma hugetlb_cma"
|
||||
|
||||
# This variable lets us append arguments to the current kdump commandline
|
||||
# after processed by KDUMP_COMMANDLINE_REMOVE
|
||||
KDUMP_COMMANDLINE_APPEND="irqpoll maxcpus=1 reset_devices novmcoredd cma=0 hugetlb_cma=0"
|
||||
|
||||
# Any additional kexec arguments required. In most situations, this should
|
||||
# be left empty
|
||||
#
|
||||
# Example:
|
||||
# KEXEC_ARGS="--elf32-core-headers"
|
||||
KEXEC_ARGS=""
|
||||
|
||||
#Where to find the boot image
|
||||
#KDUMP_BOOTDIR="/boot"
|
||||
|
||||
#What is the image type used for kdump
|
||||
KDUMP_IMG="vmlinuz"
|
||||
|
||||
# Logging is controlled by following variables in the first kernel:
|
||||
# - @var KDUMP_STDLOGLVL - logging level to standard error (console output)
|
||||
# - @var KDUMP_SYSLOGLVL - logging level to syslog (by logger command)
|
||||
# - @var KDUMP_KMSGLOGLVL - logging level to /dev/kmsg (only for boot-time)
|
||||
#
|
||||
# In the second kernel, kdump will use the rd.kdumploglvl option to set the
|
||||
# log level in the above KDUMP_COMMANDLINE_APPEND.
|
||||
# - @var rd.kdumploglvl - logging level to syslog (by logger command)
|
||||
# - for example: add the rd.kdumploglvl=3 option to KDUMP_COMMANDLINE_APPEND
|
||||
#
|
||||
# Logging levels: no logging(0), error(1),warn(2),info(3),debug(4)
|
||||
#
|
||||
# KDUMP_STDLOGLVL=3
|
||||
# KDUMP_SYSLOGLVL=0
|
||||
# KDUMP_KMSGLOGLVL=0
|
||||
|
|
@ -0,0 +1,53 @@
|
|||
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
|
||||
# If no version is specified, then the init script will try to find a
|
||||
# kdump kernel with the same version number as the running kernel.
|
||||
KDUMP_KERNELVER=""
|
||||
|
||||
# The kdump commandline is the command line that needs to be passed off to
|
||||
# the kdump kernel. This will likely match the contents of the grub kernel
|
||||
# line. For example:
|
||||
# KDUMP_COMMANDLINE="ro root=LABEL=/"
|
||||
# Dracut depends on proper root= options, so please make sure that appropriate
|
||||
# root= options are copied from /proc/cmdline. In general it is best to append
|
||||
# command line options using "KDUMP_COMMANDLINE_APPEND=".
|
||||
# If a command line is not specified, the default will be taken from
|
||||
# /proc/cmdline
|
||||
KDUMP_COMMANDLINE=""
|
||||
|
||||
# This variable lets us remove arguments from the current kdump commandline
|
||||
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
|
||||
# NOTE: some arguments such as crashkernel will always be removed
|
||||
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len swiotlb cma hugetlb_cma"
|
||||
|
||||
# This variable lets us append arguments to the current kdump commandline
|
||||
# after processed by KDUMP_COMMANDLINE_REMOVE
|
||||
KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices cgroup_disable=memory udev.children-max=2 panic=10 swiotlb=noforce novmcoredd cma=0 hugetlb_cma=0"
|
||||
|
||||
# Any additional kexec arguments required. In most situations, this should
|
||||
# be left empty
|
||||
#
|
||||
# Example:
|
||||
# KEXEC_ARGS="--elf32-core-headers"
|
||||
KEXEC_ARGS=""
|
||||
|
||||
#Where to find the boot image
|
||||
#KDUMP_BOOTDIR="/boot"
|
||||
|
||||
#What is the image type used for kdump
|
||||
KDUMP_IMG="vmlinuz"
|
||||
|
||||
# Logging is controlled by following variables in the first kernel:
|
||||
# - @var KDUMP_STDLOGLVL - logging level to standard error (console output)
|
||||
# - @var KDUMP_SYSLOGLVL - logging level to syslog (by logger command)
|
||||
# - @var KDUMP_KMSGLOGLVL - logging level to /dev/kmsg (only for boot-time)
|
||||
#
|
||||
# In the second kernel, kdump will use the rd.kdumploglvl option to set the
|
||||
# log level in the above KDUMP_COMMANDLINE_APPEND.
|
||||
# - @var rd.kdumploglvl - logging level to syslog (by logger command)
|
||||
# - for example: add the rd.kdumploglvl=3 option to KDUMP_COMMANDLINE_APPEND
|
||||
#
|
||||
# Logging levels: no logging(0), error(1),warn(2),info(3),debug(4)
|
||||
#
|
||||
# KDUMP_STDLOGLVL=3
|
||||
# KDUMP_SYSLOGLVL=0
|
||||
# KDUMP_KMSGLOGLVL=0
|
||||
|
|
@ -0,0 +1,56 @@
|
|||
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
|
||||
# If no version is specified, then the init script will try to find a
|
||||
# kdump kernel with the same version number as the running kernel.
|
||||
KDUMP_KERNELVER=""
|
||||
|
||||
# The kdump commandline is the command line that needs to be passed off to
|
||||
# the kdump kernel. This will likely match the contents of the grub kernel
|
||||
# line. For example:
|
||||
# KDUMP_COMMANDLINE="ro root=LABEL=/"
|
||||
# Dracut depends on proper root= options, so please make sure that appropriate
|
||||
# root= options are copied from /proc/cmdline. In general it is best to append
|
||||
# command line options using "KDUMP_COMMANDLINE_APPEND=".
|
||||
# If a command line is not specified, the default will be taken from
|
||||
# /proc/cmdline
|
||||
KDUMP_COMMANDLINE=""
|
||||
|
||||
# This variable lets us remove arguments from the current kdump commandline
|
||||
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
|
||||
# NOTE: some arguments such as crashkernel will always be removed
|
||||
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len swiotlb cma hugetlb_cma"
|
||||
|
||||
# This variable lets us append arguments to the current kdump commandline
|
||||
# after processed by KDUMP_COMMANDLINE_REMOVE
|
||||
KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices numa=off udev.children-max=2 panic=10 transparent_hugepage=never novmcoredd cma=0 hugetlb_cma=0"
|
||||
|
||||
# Any additional kexec arguments required. In most situations, this should
|
||||
# be left empty
|
||||
#
|
||||
# Example:
|
||||
# KEXEC_ARGS="--elf32-core-headers"
|
||||
KEXEC_ARGS=""
|
||||
|
||||
#Where to find the boot image
|
||||
#KDUMP_BOOTDIR="/boot"
|
||||
|
||||
#What is the image type used for kdump
|
||||
KDUMP_IMG="vmlinuz"
|
||||
|
||||
#What is the images extension. Relocatable kernels don't have one
|
||||
KDUMP_IMG_EXT=""
|
||||
|
||||
# Logging is controlled by following variables in the first kernel:
|
||||
# - @var KDUMP_STDLOGLVL - logging level to standard error (console output)
|
||||
# - @var KDUMP_SYSLOGLVL - logging level to syslog (by logger command)
|
||||
# - @var KDUMP_KMSGLOGLVL - logging level to /dev/kmsg (only for boot-time)
|
||||
#
|
||||
# In the second kernel, kdump will use the rd.kdumploglvl option to set the
|
||||
# log level in the above KDUMP_COMMANDLINE_APPEND.
|
||||
# - @var rd.kdumploglvl - logging level to syslog (by logger command)
|
||||
# - for example: add the rd.kdumploglvl=3 option to KDUMP_COMMANDLINE_APPEND
|
||||
#
|
||||
# Logging levels: no logging(0), error(1),warn(2),info(3),debug(4)
|
||||
#
|
||||
# KDUMP_STDLOGLVL=3
|
||||
# KDUMP_SYSLOGLVL=0
|
||||
# KDUMP_KMSGLOGLVL=0
|
||||
|
|
@ -0,0 +1,58 @@
|
|||
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
|
||||
# If no version is specified, then the init script will try to find a
|
||||
# kdump kernel with the same version number as the running kernel.
|
||||
KDUMP_KERNELVER=""
|
||||
|
||||
# The kdump commandline is the command line that needs to be passed off to
|
||||
# the kdump kernel. This will likely match the contents of the grub kernel
|
||||
# line. For example:
|
||||
# KDUMP_COMMANDLINE="ro root=LABEL=/"
|
||||
# Dracut depends on proper root= options, so please make sure that appropriate
|
||||
# root= options are copied from /proc/cmdline. In general it is best to append
|
||||
# command line options using "KDUMP_COMMANDLINE_APPEND=".
|
||||
# If a command line is not specified, the default will be taken from
|
||||
# /proc/cmdline
|
||||
KDUMP_COMMANDLINE=""
|
||||
|
||||
# This variable lets us remove arguments from the current kdump commandline
|
||||
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
|
||||
# NOTE: some arguments such as crashkernel will always be removed
|
||||
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len swiotlb hugetlb_cma"
|
||||
|
||||
# This variable lets us append arguments to the current kdump commandline
|
||||
# after processed by KDUMP_COMMANDLINE_REMOVE
|
||||
KDUMP_COMMANDLINE_APPEND="irqpoll maxcpus=1 noirqdistrib reset_devices cgroup_disable=memory numa=off udev.children-max=2 ehea.use_mcs=0 panic=10 kvm_cma_resv_ratio=0 transparent_hugepage=never novmcoredd hugetlb_cma=0"
|
||||
|
||||
# Any additional kexec arguments required. In most situations, this should
|
||||
# be left empty
|
||||
#
|
||||
# Example:
|
||||
# KEXEC_ARGS="--elf32-core-headers"
|
||||
KEXEC_ARGS="--dt-no-old-root"
|
||||
|
||||
#Where to find the boot image
|
||||
#KDUMP_BOOTDIR="/boot"
|
||||
|
||||
#What is the image type used for kdump
|
||||
KDUMP_IMG="vmlinuz"
|
||||
|
||||
#What is the images extension. Relocatable kernels don't have one
|
||||
KDUMP_IMG_EXT=""
|
||||
|
||||
#Specify the action after failure
|
||||
|
||||
# Logging is controlled by following variables in the first kernel:
|
||||
# - @var KDUMP_STDLOGLVL - logging level to standard error (console output)
|
||||
# - @var KDUMP_SYSLOGLVL - logging level to syslog (by logger command)
|
||||
# - @var KDUMP_KMSGLOGLVL - logging level to /dev/kmsg (only for boot-time)
|
||||
#
|
||||
# In the second kernel, kdump will use the rd.kdumploglvl option to set the
|
||||
# log level in the above KDUMP_COMMANDLINE_APPEND.
|
||||
# - @var rd.kdumploglvl - logging level to syslog (by logger command)
|
||||
# - for example: add the rd.kdumploglvl=3 option to KDUMP_COMMANDLINE_APPEND
|
||||
#
|
||||
# Logging levels: no logging(0), error(1),warn(2),info(3),debug(4)
|
||||
#
|
||||
# KDUMP_STDLOGLVL=3
|
||||
# KDUMP_SYSLOGLVL=0
|
||||
# KDUMP_KMSGLOGLVL=0
|
||||
|
|
@ -0,0 +1,58 @@
|
|||
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
|
||||
# If no version is specified, then the init script will try to find a
|
||||
# kdump kernel with the same version number as the running kernel.
|
||||
KDUMP_KERNELVER=""
|
||||
|
||||
# The kdump commandline is the command line that needs to be passed off to
|
||||
# the kdump kernel. This will likely match the contents of the grub kernel
|
||||
# line. For example:
|
||||
# KDUMP_COMMANDLINE="ro root=LABEL=/"
|
||||
# Dracut depends on proper root= options, so please make sure that appropriate
|
||||
# root= options are copied from /proc/cmdline. In general it is best to append
|
||||
# command line options using "KDUMP_COMMANDLINE_APPEND=".
|
||||
# If a command line is not specified, the default will be taken from
|
||||
# /proc/cmdline
|
||||
KDUMP_COMMANDLINE=""
|
||||
|
||||
# This variable lets us remove arguments from the current kdump commandline
|
||||
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
|
||||
# NOTE: some arguments such as crashkernel will always be removed
|
||||
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len swiotlb hugetlb_cma"
|
||||
|
||||
# This variable lets us append arguments to the current kdump commandline
|
||||
# after processed by KDUMP_COMMANDLINE_REMOVE
|
||||
KDUMP_COMMANDLINE_APPEND="irqpoll maxcpus=1 noirqdistrib reset_devices cgroup_disable=memory numa=off udev.children-max=2 ehea.use_mcs=0 panic=10 kvm_cma_resv_ratio=0 transparent_hugepage=never novmcoredd hugetlb_cma=0"
|
||||
|
||||
# Any additional kexec arguments required. In most situations, this should
|
||||
# be left empty
|
||||
#
|
||||
# Example:
|
||||
# KEXEC_ARGS="--elf32-core-headers"
|
||||
KEXEC_ARGS="--dt-no-old-root"
|
||||
|
||||
#Where to find the boot image
|
||||
#KDUMP_BOOTDIR="/boot"
|
||||
|
||||
#What is the image type used for kdump
|
||||
KDUMP_IMG="vmlinuz"
|
||||
|
||||
#What is the images extension. Relocatable kernels don't have one
|
||||
KDUMP_IMG_EXT=""
|
||||
|
||||
#Specify the action after failure
|
||||
|
||||
# Logging is controlled by following variables in the first kernel:
|
||||
# - @var KDUMP_STDLOGLVL - logging level to standard error (console output)
|
||||
# - @var KDUMP_SYSLOGLVL - logging level to syslog (by logger command)
|
||||
# - @var KDUMP_KMSGLOGLVL - logging level to /dev/kmsg (only for boot-time)
|
||||
#
|
||||
# In the second kernel, kdump will use the rd.kdumploglvl option to set the
|
||||
# log level in the above KDUMP_COMMANDLINE_APPEND.
|
||||
# - @var rd.kdumploglvl - logging level to syslog (by logger command)
|
||||
# - for example: add the rd.kdumploglvl=3 option to KDUMP_COMMANDLINE_APPEND
|
||||
#
|
||||
# Logging levels: no logging(0), error(1),warn(2),info(3),debug(4)
|
||||
#
|
||||
# KDUMP_STDLOGLVL=3
|
||||
# KDUMP_SYSLOGLVL=0
|
||||
# KDUMP_KMSGLOGLVL=0
|
||||
|
|
@ -0,0 +1,59 @@
|
|||
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
|
||||
# If no version is specified, then the init script will try to find a
|
||||
# kdump kernel with the same version number as the running kernel.
|
||||
KDUMP_KERNELVER=""
|
||||
|
||||
# The kdump commandline is the command line that needs to be passed off to
|
||||
# the kdump kernel. This will likely match the contents of the grub kernel
|
||||
# line. For example:
|
||||
# KDUMP_COMMANDLINE="ro root=LABEL=/"
|
||||
# Dracut depends on proper root= options, so please make sure that appropriate
|
||||
# root= options are copied from /proc/cmdline. In general it is best to append
|
||||
# command line options using "KDUMP_COMMANDLINE_APPEND=".
|
||||
# If a command line is not specified, the default will be taken from
|
||||
# /proc/cmdline
|
||||
KDUMP_COMMANDLINE=""
|
||||
|
||||
# This variable lets us remove arguments from the current kdump commandline
|
||||
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
|
||||
# NOTE: some arguments such as crashkernel will always be removed
|
||||
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len swiotlb vmcp_cma cma hugetlb_cma prot_virt"
|
||||
|
||||
# This variable lets us append arguments to the current kdump commandline
|
||||
# after processed by KDUMP_COMMANDLINE_REMOVE
|
||||
KDUMP_COMMANDLINE_APPEND="nr_cpus=1 cgroup_disable=memory numa=off udev.children-max=2 panic=10 transparent_hugepage=never novmcoredd vmcp_cma=0 cma=0 hugetlb_cma=0"
|
||||
|
||||
# Any additional /sbin/mkdumprd arguments required.
|
||||
MKDUMPRD_ARGS=""
|
||||
|
||||
# Any additional kexec arguments required. In most situations, this should
|
||||
# be left empty
|
||||
#
|
||||
# Example:
|
||||
# KEXEC_ARGS="--elf32-core-headers"
|
||||
KEXEC_ARGS="-s"
|
||||
|
||||
#Where to find the boot image
|
||||
#KDUMP_BOOTDIR="/boot"
|
||||
|
||||
#What is the image type used for kdump
|
||||
KDUMP_IMG="vmlinuz"
|
||||
|
||||
#What is the images extension. Relocatable kernels don't have one
|
||||
KDUMP_IMG_EXT=""
|
||||
|
||||
# Logging is controlled by following variables in the first kernel:
|
||||
# - @var KDUMP_STDLOGLVL - logging level to standard error (console output)
|
||||
# - @var KDUMP_SYSLOGLVL - logging level to syslog (by logger command)
|
||||
# - @var KDUMP_KMSGLOGLVL - logging level to /dev/kmsg (only for boot-time)
|
||||
#
|
||||
# In the second kernel, kdump will use the rd.kdumploglvl option to set the
|
||||
# log level in the above KDUMP_COMMANDLINE_APPEND.
|
||||
# - @var rd.kdumploglvl - logging level to syslog (by logger command)
|
||||
# - for example: add the rd.kdumploglvl=3 option to KDUMP_COMMANDLINE_APPEND
|
||||
#
|
||||
# Logging levels: no logging(0), error(1),warn(2),info(3),debug(4)
|
||||
#
|
||||
# KDUMP_STDLOGLVL=3
|
||||
# KDUMP_SYSLOGLVL=0
|
||||
# KDUMP_KMSGLOGLVL=0
|
||||
|
|
@ -0,0 +1,56 @@
|
|||
# Kernel Version string for the -kdump kernel, such as 2.6.13-1544.FC5kdump
|
||||
# If no version is specified, then the init script will try to find a
|
||||
# kdump kernel with the same version number as the running kernel.
|
||||
KDUMP_KERNELVER=""
|
||||
|
||||
# The kdump commandline is the command line that needs to be passed off to
|
||||
# the kdump kernel. This will likely match the contents of the grub kernel
|
||||
# line. For example:
|
||||
# KDUMP_COMMANDLINE="ro root=LABEL=/"
|
||||
# Dracut depends on proper root= options, so please make sure that appropriate
|
||||
# root= options are copied from /proc/cmdline. In general it is best to append
|
||||
# command line options using "KDUMP_COMMANDLINE_APPEND=".
|
||||
# If a command line is not specified, the default will be taken from
|
||||
# /proc/cmdline
|
||||
KDUMP_COMMANDLINE=""
|
||||
|
||||
# This variable lets us remove arguments from the current kdump commandline
|
||||
# as taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline
|
||||
# NOTE: some arguments such as crashkernel will always be removed
|
||||
KDUMP_COMMANDLINE_REMOVE="hugepages hugepagesz slub_debug quiet log_buf_len swiotlb cma hugetlb_cma"
|
||||
|
||||
# This variable lets us append arguments to the current kdump commandline
|
||||
# after processed by KDUMP_COMMANDLINE_REMOVE
|
||||
KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices cgroup_disable=memory mce=off numa=off udev.children-max=2 panic=10 acpi_no_memhotplug transparent_hugepage=never nokaslr hest_disable novmcoredd cma=0 hugetlb_cma=0"
|
||||
|
||||
# Any additional kexec arguments required. In most situations, this should
|
||||
# be left empty
|
||||
#
|
||||
# Example:
|
||||
# KEXEC_ARGS="--elf32-core-headers"
|
||||
KEXEC_ARGS="-s"
|
||||
|
||||
#Where to find the boot image
|
||||
#KDUMP_BOOTDIR="/boot"
|
||||
|
||||
#What is the image type used for kdump
|
||||
KDUMP_IMG="vmlinuz"
|
||||
|
||||
#What is the images extension. Relocatable kernels don't have one
|
||||
KDUMP_IMG_EXT=""
|
||||
|
||||
# Logging is controlled by following variables in the first kernel:
|
||||
# - @var KDUMP_STDLOGLVL - logging level to standard error (console output)
|
||||
# - @var KDUMP_SYSLOGLVL - logging level to syslog (by logger command)
|
||||
# - @var KDUMP_KMSGLOGLVL - logging level to /dev/kmsg (only for boot-time)
|
||||
#
|
||||
# In the second kernel, kdump will use the rd.kdumploglvl option to set the
|
||||
# log level in the above KDUMP_COMMANDLINE_APPEND.
|
||||
# - @var rd.kdumploglvl - logging level to syslog (by logger command)
|
||||
# - for example: add the rd.kdumploglvl=3 option to KDUMP_COMMANDLINE_APPEND
|
||||
#
|
||||
# Logging levels: no logging(0), error(1),warn(2),info(3),debug(4)
|
||||
#
|
||||
# KDUMP_STDLOGLVL=3
|
||||
# KDUMP_SYSLOGLVL=0
|
||||
# KDUMP_KMSGLOGLVL=0
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,64 @@
|
|||
.TH KDUMPCTL 8 2015-07-13 kexec-tools
|
||||
|
||||
.SH NAME
|
||||
kdumpctl \- control interface for kdump
|
||||
|
||||
.SH SYNOPSIS
|
||||
.B kdumpctl
|
||||
.I COMMAND
|
||||
|
||||
.SH DESCRIPTION
|
||||
.B kdumpctl
|
||||
is used to check or control the kdump service.
|
||||
In most cases, you should use
|
||||
.B systemctl
|
||||
to start / stop / enable kdump service instead. However,
|
||||
.B kdumpctl
|
||||
provides more details for debug and a helper to setup ssh key authentication.
|
||||
|
||||
.SH COMMANDS
|
||||
.TP
|
||||
.I start
|
||||
Start the service.
|
||||
.TP
|
||||
.I stop
|
||||
Stop the service.
|
||||
.TP
|
||||
.I status
|
||||
Prints the current status of kdump service.
|
||||
It returns non-zero value if kdump is not operational.
|
||||
.TP
|
||||
.I restart
|
||||
Is equal to
|
||||
.I start; stop
|
||||
.TP
|
||||
.I reload
|
||||
reload crash kernel image and initramfs without triggering a rebuild.
|
||||
.TP
|
||||
.I rebuild
|
||||
rebuild the crash kernel initramfs.
|
||||
.TP
|
||||
.I propagate
|
||||
Helps to setup key authentication for ssh storage since it's
|
||||
impossible to use password authentication during kdump.
|
||||
.TP
|
||||
.I showmem
|
||||
Prints the size of reserved memory for crash kernel in megabytes.
|
||||
.TP
|
||||
.I estimate
|
||||
Estimate a suitable crashkernel value for current machine. This is a
|
||||
best-effort estimate. It will print a recommanded crashkernel value
|
||||
based on current kdump setup, and list some details of memory usage.
|
||||
.TP
|
||||
.I reset-crashkernel [KERNEL]
|
||||
Reset crashkernel value to default value. kdumpctl will try to read
|
||||
from /usr/lib/modules/<KERNEL>/crashkernel.default and reset specified
|
||||
kernel's crashkernel cmdline value. If no kernel is
|
||||
specified, will reset current running kernel's crashkernel value.
|
||||
If /usr/lib/modules/<KERNEL>/crashkernel.default doesn't exist, will
|
||||
simply exit return 1.
|
||||
|
||||
|
||||
.SH "SEE ALSO"
|
||||
.BR kdump.conf (5),
|
||||
.BR mkdumprd (8)
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,36 @@
|
|||
From 2837fb1f5f8362976c188b30ebe50dc8b0377f64 Mon Sep 17 00:00:00 2001
|
||||
From: Kairui Song <kasong@redhat.com>
|
||||
Date: Wed, 29 Jan 2020 11:33:18 +0800
|
||||
Subject: [PATCH] Remove duplicated variable declaration
|
||||
|
||||
When building on Fedora 32, following error is observed:
|
||||
|
||||
...
|
||||
/usr/bin/ld: ../eppic/libeppic/libeppic.a(eppic_stat.o):/builddir/build/BUILD/kexec-tools-2.0.20/eppic/libeppic/eppic.h:474: multiple definition of `lastv';
|
||||
../eppic/libeppic/libeppic.a(eppic_func.o):/builddir/build/BUILD/kexec-tools-2.0.20/eppic/libeppic/eppic.h:474: first defined here
|
||||
...
|
||||
|
||||
And apparently, the variable is wrongly declared multiple times. So
|
||||
remove duplicated declaration.
|
||||
|
||||
Signed-off-by: Kairui Song <kasong@redhat.com>
|
||||
---
|
||||
libeppic/eppic.h | 2 +-
|
||||
1 file changed, 1 insertion(+), 1 deletion(-)
|
||||
|
||||
diff --git a/libeppic/eppic.h b/libeppic/eppic.h
|
||||
index 5664583..836b475 100644
|
||||
--- a/eppic-d84c3541035d95077aa8571f5d5c3e07c6ef510b/libeppic/eppic.h
|
||||
+++ b/eppic-d84c3541035d95077aa8571f5d5c3e07c6ef510b/libeppic/eppic.h
|
||||
@@ -471,7 +471,7 @@ type_t *eppic_addstorage(type_t *t1, type_t *t2);
|
||||
type_t *eppic_getvoidstruct(int ctype);
|
||||
|
||||
extern int lineno, needvar, instruct, nomacs, eppic_legacy;
|
||||
-node_t *lastv;
|
||||
+extern node_t *lastv;
|
||||
|
||||
#define NULLNODE ((node_t*)0)
|
||||
|
||||
--
|
||||
2.24.1
|
||||
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
From 646456862df8926ba10dd7330abf3bf0f887e1b6 Mon Sep 17 00:00:00 2001
|
||||
From: Kazuhito Hagio <k-hagio-ab@nec.com>
|
||||
Date: Wed, 26 May 2021 14:31:26 +0900
|
||||
Subject: [PATCH] Increase SECTION_MAP_LAST_BIT to 5
|
||||
|
||||
* Required for kernel 5.12
|
||||
|
||||
Kernel commit 1f90a3477df3 ("mm: teach pfn_to_online_page() about
|
||||
ZONE_DEVICE section collisions") added a section flag
|
||||
(SECTION_TAINT_ZONE_DEVICE) and causes makedumpfile an error on
|
||||
some machines like this:
|
||||
|
||||
__vtop4_x86_64: Can't get a valid pmd_pte.
|
||||
readmem: Can't convert a virtual address(ffffe2bdc2000000) to physical address.
|
||||
readmem: type_addr: 0, addr:ffffe2bdc2000000, size:32768
|
||||
__exclude_unnecessary_pages: Can't read the buffer of struct page.
|
||||
create_2nd_bitmap: Can't exclude unnecessary pages.
|
||||
|
||||
Increase SECTION_MAP_LAST_BIT to 5 to fix this. The bit had not
|
||||
been used until the change, so we can just increase the value.
|
||||
|
||||
Signed-off-by: Kazuhito Hagio <k-hagio-ab@nec.com>
|
||||
---
|
||||
makedumpfile.h | 2 +-
|
||||
1 file changed, 1 insertion(+), 1 deletion(-)
|
||||
|
||||
diff --git a/makedumpfile-1.6.9/makedumpfile.h b/makedumpfile-1.6.9/makedumpfile.h
|
||||
index 93aa774..79046f2 100644
|
||||
--- a/makedumpfile-1.6.9/makedumpfile.h
|
||||
+++ b/makedumpfile-1.6.9/makedumpfile.h
|
||||
@@ -195,7 +195,7 @@ isAnon(unsigned long mapping)
|
||||
* 2. it has been verified that (1UL<<2) was never set, so it is
|
||||
* safe to mask that bit off even in old kernels.
|
||||
*/
|
||||
-#define SECTION_MAP_LAST_BIT (1UL<<4)
|
||||
+#define SECTION_MAP_LAST_BIT (1UL<<5)
|
||||
#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1))
|
||||
#define NR_SECTION_ROOTS() divideup(num_section, SECTIONS_PER_ROOT())
|
||||
#define SECTION_NR_TO_PFN(sec) ((sec) << PFN_SECTION_SHIFT())
|
||||
--
|
||||
2.29.2
|
||||
|
||||
|
|
@ -0,0 +1,43 @@
|
|||
From 9a6f589d99dcef114c89fde992157f5467028c8f Mon Sep 17 00:00:00 2001
|
||||
From: Tao Liu <ltao@redhat.com>
|
||||
Date: Fri, 18 Jun 2021 18:28:04 +0800
|
||||
Subject: [PATCH] check for invalid physical address of /proc/kcore
|
||||
when making ELF dumpfile
|
||||
|
||||
Previously when executing makedumpfile with -E option against
|
||||
/proc/kcore, makedumpfile will fail:
|
||||
|
||||
# makedumpfile -E -d 31 /proc/kcore kcore.dump
|
||||
...
|
||||
write_elf_load_segment: Can't convert physaddr(ffffffffffffffff) to an offset.
|
||||
|
||||
makedumpfile Failed.
|
||||
|
||||
It's because /proc/kcore contains PT_LOAD program headers which have
|
||||
physaddr (0xffffffffffffffff). With -E option, makedumpfile will
|
||||
try to convert the physaddr to an offset and fails.
|
||||
|
||||
Skip the PT_LOAD program headers which have such physaddr.
|
||||
|
||||
Signed-off-by: Tao Liu <ltao@redhat.com>
|
||||
Signed-off-by: Kazuhito Hagio <k-hagio-ab@nec.com>
|
||||
---
|
||||
makedumpfile.c | 2 +-
|
||||
1 file changed, 1 insertion(+), 1 deletion(-)
|
||||
|
||||
diff --git a/makedumpfile-1.6.9/makedumpfile.c b/makedumpfile-1.6.9/makedumpfile.c
|
||||
index 894c88e..fcb571f 100644
|
||||
--- a/makedumpfile-1.6.9/makedumpfile.c
|
||||
+++ b/makedumpfile-1.6.9/makedumpfile.c
|
||||
@@ -7764,7 +7764,7 @@ write_elf_pages_cyclic(struct cache_data *cd_header, struct cache_data *cd_page)
|
||||
if (!get_phdr_memory(i, &load))
|
||||
return FALSE;
|
||||
|
||||
- if (load.p_type != PT_LOAD)
|
||||
+ if (load.p_type != PT_LOAD || load.p_paddr == NOT_PADDR)
|
||||
continue;
|
||||
|
||||
off_memory= load.p_offset;
|
||||
--
|
||||
2.29.2
|
||||
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
Kdump now works on live images with some manual configurations. Here is the step
|
||||
by step guide.
|
||||
|
||||
1. Enable crashkernel reservation
|
||||
|
||||
Since there isn't any config file that can be used to configure kernel
|
||||
parameters for live images before booting them, we have to append 'crashkernel'
|
||||
argument in boot menu every time we boot a live image.
|
||||
|
||||
2. Change dump target in /etc/kdump.conf
|
||||
|
||||
When kdump kernel boots in a live environment, the default target /var/crash is
|
||||
in RAM so you need to change the dump target to an external disk or a network
|
||||
dump target.
|
||||
|
||||
Besides, make sure that "default dump_to_rootfs" is not specified.
|
||||
|
||||
3. Start kdump service
|
||||
|
||||
$ kdumpctl start
|
||||
|
||||
4. Trigger a kdump test
|
||||
|
||||
$ echo 1 > /proc/sys/kernel/sysrq
|
||||
$ echo c > /proc/sysrq-trigger
|
||||
|
|
@ -0,0 +1,452 @@
|
|||
#!/bin/bash --norc
|
||||
# New mkdumprd
|
||||
#
|
||||
# Copyright 2011 Red Hat, Inc.
|
||||
#
|
||||
# Written by Cong Wang <amwang@redhat.com>
|
||||
#
|
||||
|
||||
if [ -f /etc/sysconfig/kdump ]; then
|
||||
. /etc/sysconfig/kdump
|
||||
fi
|
||||
|
||||
[[ $dracutbasedir ]] || dracutbasedir=/usr/lib/dracut
|
||||
. $dracutbasedir/dracut-functions.sh
|
||||
. /lib/kdump/kdump-lib.sh
|
||||
. /lib/kdump/kdump-logger.sh
|
||||
export IN_KDUMP=1
|
||||
|
||||
#initiate the kdump logger
|
||||
dlog_init
|
||||
if [ $? -ne 0 ]; then
|
||||
echo "failed to initiate the kdump logger."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
conf_file="/etc/kdump.conf"
|
||||
SSH_KEY_LOCATION="/root/.ssh/kdump_id_rsa"
|
||||
SAVE_PATH=$(get_save_path)
|
||||
OVERRIDE_RESETTABLE=0
|
||||
|
||||
extra_modules=""
|
||||
dracut_args="--add kdumpbase --quiet --hostonly --hostonly-cmdline --hostonly-i18n --hostonly-mode strict -o \"plymouth dash resume ifcfg earlykdump\""
|
||||
|
||||
readonly MKDUMPRD_TMPDIR="$(mktemp -d -t mkdumprd.XXXXXX)"
|
||||
[ -d "$MKDUMPRD_TMPDIR" ] || perror_exit "dracut: mktemp -p -d -t dracut.XXXXXX failed."
|
||||
readonly MKDUMPRD_TMPMNT="$MKDUMPRD_TMPDIR/target"
|
||||
|
||||
trap '
|
||||
ret=$?;
|
||||
is_mounted $MKDUMPRD_TMPMNT && umount -f $MKDUMPRD_TMPMNT;
|
||||
[[ -d $MKDUMPRD_TMPDIR ]] && rm --one-file-system -rf -- "$MKDUMPRD_TMPDIR";
|
||||
exit $ret;
|
||||
' EXIT
|
||||
|
||||
# clean up after ourselves no matter how we die.
|
||||
trap 'exit 1;' SIGINT
|
||||
|
||||
add_dracut_arg() {
|
||||
dracut_args="$dracut_args $@"
|
||||
}
|
||||
|
||||
add_dracut_mount() {
|
||||
add_dracut_arg "--mount" "\"$1\""
|
||||
}
|
||||
|
||||
add_dracut_sshkey() {
|
||||
add_dracut_arg "--sshkey" "\"$1\""
|
||||
}
|
||||
|
||||
# caller should ensure $1 is valid and mounted in 1st kernel
|
||||
to_mount() {
|
||||
local _target=$1 _fstype=$2 _options=$3 _new_mntpoint _pdev
|
||||
|
||||
_new_mntpoint=$(get_kdump_mntpoint_from_target $_target)
|
||||
_fstype="${_fstype:-$(get_fs_type_from_target $_target)}"
|
||||
_options="${_options:-$(get_mntopt_from_target $_target)}"
|
||||
_options="${_options:-defaults}"
|
||||
|
||||
if [[ "$_fstype" == "nfs"* ]]; then
|
||||
_pdev=$_target
|
||||
_options=$(echo $_options | sed 's/,addr=[^,]*//')
|
||||
_options=$(echo $_options | sed 's/,proto=[^,]*//')
|
||||
_options=$(echo $_options | sed 's/,clientaddr=[^,]*//')
|
||||
else
|
||||
# for non-nfs _target converting to use udev persistent name
|
||||
_pdev="$(kdump_get_persistent_dev $_target)"
|
||||
if [ -z "$_pdev" ]; then
|
||||
return 1
|
||||
fi
|
||||
fi
|
||||
|
||||
# mount fs target as rw in 2nd kernel
|
||||
_options=$(echo $_options | sed 's/\(^\|,\)ro\($\|,\)/\1rw\2/g')
|
||||
# with 'noauto' in fstab nfs and non-root disk mount will fail in 2nd
|
||||
# kernel, filter it out here.
|
||||
_options=$(echo $_options | sed 's/\(^\|,\)noauto\($\|,\)/\1/g')
|
||||
# drop nofail or nobootwait
|
||||
_options=$(echo $_options | sed 's/\(^\|,\)nofail\($\|,\)/\1/g')
|
||||
_options=$(echo $_options | sed 's/\(^\|,\)nobootwait\($\|,\)/\1/g')
|
||||
|
||||
echo "$_pdev $_new_mntpoint $_fstype $_options"
|
||||
}
|
||||
|
||||
#Function: get_ssh_size
|
||||
#$1=dump target
|
||||
#called from while loop and shouldn't read from stdin, so we're using "ssh -n"
|
||||
get_ssh_size() {
|
||||
local _opt _out _size
|
||||
_opt="-i $SSH_KEY_LOCATION -o BatchMode=yes -o StrictHostKeyChecking=yes"
|
||||
_out=$(ssh -q -n $_opt $1 "df -P $SAVE_PATH")
|
||||
[ $? -ne 0 ] && {
|
||||
perror_exit "checking remote ssh server available size failed."
|
||||
}
|
||||
|
||||
#ssh output removed the line break, so print field NF-2
|
||||
_size=$(echo -n $_out| awk '{avail=NF-2; print $avail}')
|
||||
echo -n $_size
|
||||
}
|
||||
|
||||
#mkdir if save path does not exist on ssh dump target
|
||||
#$1=ssh dump target
|
||||
#caller should ensure write permission on $1:$SAVE_PATH
|
||||
#called from while loop and shouldn't read from stdin, so we're using "ssh -n"
|
||||
mkdir_save_path_ssh()
|
||||
{
|
||||
local _opt _dir
|
||||
_opt="-i $SSH_KEY_LOCATION -o BatchMode=yes -o StrictHostKeyChecking=yes"
|
||||
ssh -qn $_opt $1 mkdir -p $SAVE_PATH 2>&1 > /dev/null
|
||||
_ret=$?
|
||||
if [ $_ret -ne 0 ]; then
|
||||
perror_exit "mkdir failed on $1:$SAVE_PATH"
|
||||
fi
|
||||
|
||||
#check whether user has write permission on $1:$SAVE_PATH
|
||||
_dir=$(ssh -qn $_opt $1 mktemp -dqp $SAVE_PATH 2>/dev/null)
|
||||
_ret=$?
|
||||
if [ $_ret -ne 0 ]; then
|
||||
perror_exit "Could not create temporary directory on $1:$SAVE_PATH. Make sure user has write permission on destination"
|
||||
fi
|
||||
ssh -qn $_opt $1 rmdir $_dir
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
#Function: get_fs_size
|
||||
#$1=dump target
|
||||
get_fs_size() {
|
||||
local _mnt=$(get_mntpoint_from_target $1)
|
||||
echo -n $(df -P "${_mnt}/$SAVE_PATH"|tail -1|awk '{print $4}')
|
||||
}
|
||||
|
||||
#Function: get_raw_size
|
||||
#$1=dump target
|
||||
get_raw_size() {
|
||||
echo -n $(fdisk -s "$1")
|
||||
}
|
||||
|
||||
#Function: check_size
|
||||
#$1: dump type string ('raw', 'fs', 'ssh')
|
||||
#$2: dump target
|
||||
check_size() {
|
||||
local avail memtotal
|
||||
|
||||
memtotal=$(awk '/MemTotal/{print $2}' /proc/meminfo)
|
||||
case "$1" in
|
||||
raw)
|
||||
avail=$(get_raw_size "$2")
|
||||
;;
|
||||
ssh)
|
||||
avail=$(get_ssh_size "$2")
|
||||
;;
|
||||
fs)
|
||||
avail=$(get_fs_size "$2")
|
||||
;;
|
||||
*)
|
||||
return
|
||||
esac
|
||||
|
||||
if [ $? -ne 0 ]; then
|
||||
perror_exit "Check dump target size failed"
|
||||
fi
|
||||
|
||||
if [ $avail -lt $memtotal ]; then
|
||||
dwarn "Warning: There might not be enough space to save a vmcore."
|
||||
dwarn " The size of $2 should be greater than $memtotal kilo bytes."
|
||||
fi
|
||||
}
|
||||
|
||||
check_save_path_fs()
|
||||
{
|
||||
local _path=$1
|
||||
|
||||
if [ ! -d $_path ]; then
|
||||
perror_exit "Dump path $_path does not exist."
|
||||
fi
|
||||
}
|
||||
|
||||
check_user_configured_target()
|
||||
{
|
||||
local _target=$1 _cfg_fs_type=$2 _mounted
|
||||
local _mnt=$(get_mntpoint_from_target $_target)
|
||||
local _opt=$(get_mntopt_from_target $_target)
|
||||
local _fstype=$(get_fs_type_from_target $_target)
|
||||
|
||||
if [ -n "$_fstype" ]; then
|
||||
# In case of nfs4, nfs should be used instead, nfs* options is deprecated in kdump.conf
|
||||
[[ $_fstype = "nfs"* ]] && _fstype=nfs
|
||||
|
||||
if [ -n "$_cfg_fs_type" ] && [ "$_fstype" != "$_cfg_fs_type" ]; then
|
||||
perror_exit "\"$_target\" have a wrong type config \"$_cfg_fs_type\", expected \"$_fstype\""
|
||||
fi
|
||||
else
|
||||
_fstype="$_cfg_fs_type"
|
||||
_fstype="$_cfg_fs_type"
|
||||
fi
|
||||
|
||||
# For noauto mount, mount it inplace with default value.
|
||||
# Else use the temporary target directory
|
||||
if [ -n "$_mnt" ]; then
|
||||
if ! is_mounted "$_mnt"; then
|
||||
if [[ $_opt = *",noauto"* ]]; then
|
||||
mount $_mnt
|
||||
[ $? -ne 0 ] && perror_exit "Failed to mount $_target on $_mnt for kdump preflight check."
|
||||
_mounted=$_mnt
|
||||
else
|
||||
perror_exit "Dump target \"$_target\" is neither mounted nor configured as \"noauto\""
|
||||
fi
|
||||
fi
|
||||
else
|
||||
_mnt=$MKDUMPRD_TMPMNT
|
||||
mkdir -p $_mnt
|
||||
mount $_target $_mnt -t $_fstype -o defaults
|
||||
[ $? -ne 0 ] && perror_exit "Failed to mount $_target for kdump preflight check."
|
||||
_mounted=$_mnt
|
||||
fi
|
||||
|
||||
# For user configured target, use $SAVE_PATH as the dump path within the target
|
||||
if [ ! -d "$_mnt/$SAVE_PATH" ]; then
|
||||
perror_exit "Dump path \"$SAVE_PATH\" does not exist in dump target \"$_target\""
|
||||
fi
|
||||
|
||||
check_size fs "$_target"
|
||||
|
||||
# Unmount it early, if function is interrupted and didn't reach here, the shell trap will clear it up anyway
|
||||
if [ -n "$_mounted" ]; then
|
||||
umount -f -- $_mounted
|
||||
fi
|
||||
}
|
||||
|
||||
# $1: core_collector config value
|
||||
verify_core_collector() {
|
||||
local _cmd="${1%% *}"
|
||||
local _params="${1#* }"
|
||||
|
||||
if [ "$_cmd" != "makedumpfile" ]; then
|
||||
if is_raw_dump_target; then
|
||||
dwarn "Warning: specifying a non-makedumpfile core collector, you will have to recover the vmcore manually."
|
||||
fi
|
||||
return
|
||||
fi
|
||||
|
||||
if is_ssh_dump_target || is_raw_dump_target; then
|
||||
if ! strstr "$_params" "-F"; then
|
||||
perror_exit "The specified dump target needs makedumpfile \"-F\" option."
|
||||
fi
|
||||
_params="$_params vmcore"
|
||||
else
|
||||
_params="$_params vmcore dumpfile"
|
||||
fi
|
||||
|
||||
if ! $_cmd --check-params $_params; then
|
||||
perror_exit "makedumpfile parameter check failed."
|
||||
fi
|
||||
}
|
||||
|
||||
add_mount() {
|
||||
local _mnt=$(to_mount $@)
|
||||
|
||||
if [ $? -ne 0 ]; then
|
||||
exit 1
|
||||
fi
|
||||
|
||||
add_dracut_mount "$_mnt"
|
||||
}
|
||||
|
||||
#handle the case user does not specify the dump target explicitly
|
||||
handle_default_dump_target()
|
||||
{
|
||||
local _target
|
||||
local _mntpoint
|
||||
|
||||
is_user_configured_dump_target && return
|
||||
|
||||
check_save_path_fs $SAVE_PATH
|
||||
|
||||
_save_path=$(get_bind_mount_source $SAVE_PATH)
|
||||
_target=$(get_target_from_path $_save_path)
|
||||
_mntpoint=$(get_mntpoint_from_target $_target)
|
||||
|
||||
SAVE_PATH=${_save_path##"$_mntpoint"}
|
||||
add_mount "$_target"
|
||||
check_size fs $_target
|
||||
}
|
||||
|
||||
get_override_resettable()
|
||||
{
|
||||
local override_resettable
|
||||
|
||||
override_resettable=$(grep "^override_resettable" $conf_file)
|
||||
if [ -n "$override_resettable" ]; then
|
||||
OVERRIDE_RESETTABLE=$(echo $override_resettable | cut -d' ' -f2)
|
||||
if [ "$OVERRIDE_RESETTABLE" != "0" ] && [ "$OVERRIDE_RESETTABLE" != "1" ];then
|
||||
perror_exit "override_resettable value $OVERRIDE_RESETTABLE is invalid"
|
||||
fi
|
||||
fi
|
||||
}
|
||||
|
||||
# $1: function name
|
||||
for_each_block_target()
|
||||
{
|
||||
local dev majmin
|
||||
|
||||
for dev in $(get_kdump_targets); do
|
||||
[ -b "$dev" ] || continue
|
||||
majmin=$(get_maj_min $dev)
|
||||
check_block_and_slaves $1 $majmin && return 1
|
||||
done
|
||||
|
||||
return 0
|
||||
}
|
||||
|
||||
#judge if a specific device with $1 is unresettable
|
||||
#return false if unresettable.
|
||||
is_unresettable()
|
||||
{
|
||||
local path="/sys/$(udevadm info --query=all --path=/sys/dev/block/$1 | awk '/^P:/ {print $2}' | sed -e 's/\(cciss[0-9]\+\/\).*/\1/g' -e 's/\/block\/.*$//')/resettable"
|
||||
local resettable=1
|
||||
|
||||
if [ -f "$path" ]
|
||||
then
|
||||
resettable="$(cat $path)"
|
||||
[ $resettable -eq 0 -a "$OVERRIDE_RESETTABLE" -eq 0 ] && {
|
||||
local device=$(udevadm info --query=all --path=/sys/dev/block/$1 | awk -F= '/DEVNAME/{print $2}')
|
||||
derror "Error: Can not save vmcore because device $device is unresettable"
|
||||
return 0
|
||||
}
|
||||
fi
|
||||
|
||||
return 1
|
||||
}
|
||||
|
||||
#check if machine is resettable.
|
||||
#return true if resettable
|
||||
check_resettable()
|
||||
{
|
||||
local _ret _target
|
||||
|
||||
get_override_resettable
|
||||
|
||||
for_each_block_target is_unresettable
|
||||
_ret=$?
|
||||
|
||||
[ $_ret -eq 0 ] && return
|
||||
|
||||
return 1
|
||||
}
|
||||
|
||||
check_crypt()
|
||||
{
|
||||
local _dev
|
||||
|
||||
for _dev in $(get_kdump_targets); do
|
||||
if [[ -n $(get_luks_crypt_dev "$(get_maj_min "$_dev")") ]]; then
|
||||
derror "Device $_dev is encrypted." && return 1
|
||||
fi
|
||||
done
|
||||
}
|
||||
|
||||
if ! check_resettable; then
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if ! check_crypt; then
|
||||
dwarn "Warning: Encrypted device is in dump path, which is not recommended, see kexec-kdump-howto.txt for more details."
|
||||
fi
|
||||
|
||||
# firstly get right SSH_KEY_LOCATION
|
||||
keyfile=$(awk '/^sshkey/ {print $2}' $conf_file)
|
||||
if [ -f "$keyfile" ]; then
|
||||
# canonicalize the path
|
||||
SSH_KEY_LOCATION=$(/usr/bin/readlink -m $keyfile)
|
||||
fi
|
||||
|
||||
while read config_opt config_val;
|
||||
do
|
||||
# remove inline comments after the end of a directive.
|
||||
case "$config_opt" in
|
||||
extra_modules)
|
||||
extra_modules="$extra_modules $config_val"
|
||||
;;
|
||||
ext[234]|xfs|btrfs|minix|nfs)
|
||||
check_user_configured_target "$config_val" "$config_opt"
|
||||
add_mount "$config_val" "$config_opt"
|
||||
;;
|
||||
raw)
|
||||
# checking raw disk writable
|
||||
dd if=$config_val count=1 of=/dev/null > /dev/null 2>&1 || {
|
||||
perror_exit "Bad raw disk $config_val"
|
||||
}
|
||||
_praw=$(persistent_policy="by-id" kdump_get_persistent_dev $config_val)
|
||||
if [ -z "$_praw" ]; then
|
||||
exit 1
|
||||
fi
|
||||
add_dracut_arg "--device" "$_praw"
|
||||
check_size raw $config_val
|
||||
;;
|
||||
ssh)
|
||||
if strstr "$config_val" "@";
|
||||
then
|
||||
mkdir_save_path_ssh $config_val
|
||||
check_size ssh $config_val
|
||||
add_dracut_sshkey "$SSH_KEY_LOCATION"
|
||||
else
|
||||
perror_exit "Bad ssh dump target $config_val"
|
||||
fi
|
||||
;;
|
||||
core_collector)
|
||||
verify_core_collector "$config_val"
|
||||
;;
|
||||
dracut_args)
|
||||
add_dracut_arg $config_val
|
||||
;;
|
||||
*)
|
||||
;;
|
||||
esac
|
||||
done <<< "$(read_strip_comments $conf_file)"
|
||||
|
||||
handle_default_dump_target
|
||||
|
||||
if [ -n "$extra_modules" ]
|
||||
then
|
||||
add_dracut_arg "--add-drivers" \"$extra_modules\"
|
||||
fi
|
||||
|
||||
# TODO: The below check is not needed anymore with the introduction of
|
||||
# 'zz-fadumpinit' module, that isolates fadump's capture kernel initrd,
|
||||
# but still sysroot.mount unit gets generated based on 'root=' kernel
|
||||
# parameter available in fadump case. So, find a way to fix that first
|
||||
# before removing this check.
|
||||
if ! is_fadump_capable; then
|
||||
# The 2nd rootfs mount stays behind the normal dump target mount,
|
||||
# so it doesn't affect the logic of check_dump_fs_modified().
|
||||
is_dump_to_rootfs && add_mount "$(to_dev_name $(get_root_fs_device))"
|
||||
|
||||
add_dracut_arg "--no-hostonly-default-device"
|
||||
fi
|
||||
|
||||
echo "$dracut_args $@" | xargs dracut
|
||||
|
||||
_rc=$?
|
||||
sync
|
||||
exit $_rc
|
||||
|
|
@ -0,0 +1,39 @@
|
|||
.TH MKDUMRD 8 "Fri Feb 9 2007"
|
||||
.SH NAME
|
||||
mkdumprd \- creates initial ramdisk images for kdump crash recovery
|
||||
.SH SYNOPSIS
|
||||
\fBmkdumprd\fR [OPTION]
|
||||
|
||||
.SH DESCRIPTION
|
||||
\fBmkdumprd\fR creates an initial ram file system for use in conjunction with
|
||||
the booting of a kernel within the kdump framework for crash recovery.
|
||||
\fBmkdumprds\fR purpose is to create an initial ram filesystem capable of copying
|
||||
the crashed systems vmcore image to a location specified in \fI/etc/kdump.conf
|
||||
|
||||
\fBmkdumprd\fR interrogates the running system to understand what modules need to
|
||||
be loaded in the initramfs (based on configuration retrieved from
|
||||
\fI/etc/kdump.conf)\fR
|
||||
|
||||
\fBmkdumprd\fR add a new \fBdracut\fR module 99kdumpbase and use \fBdracut\fR
|
||||
utility to generate the initramfs. When generating a kdump initramfs, \fBmkdumprd\fR
|
||||
will determine how much disk space is available, if the dump target's available
|
||||
space is not greater than the total system memory, \fBmkdumprd\fR will print a
|
||||
warning to remind that there might not be enough space to save a vmcore. The
|
||||
warning covers extreme scenarios such as the slab explodes with non-zero data or
|
||||
a full vmcore, etc. Therefore, need to prevent users from having minimum disk
|
||||
space for crash dump.
|
||||
|
||||
\fBmkdumprd\fR was not intended for casual use outside of the service
|
||||
initialization script for the kdump utility, and should not be run manually. If
|
||||
you require a custom kdump initramfs image, it is suggested that you use the
|
||||
kdump service infrastructure to create one, and then manually unpack, modify and
|
||||
repack the image.
|
||||
|
||||
|
||||
.SH OPTIONS
|
||||
.TP
|
||||
All options here are passed to dracut directly, please refer \fBdracut\fR docs
|
||||
for the info.
|
||||
|
||||
.SH "SEE ALSO"
|
||||
.BR dracut (8)
|
||||
|
|
@ -0,0 +1,64 @@
|
|||
#!/bin/bash --norc
|
||||
# Generate an initramfs image that isolates dump capture capability within
|
||||
# the default initramfs using zz-fadumpinit dracut module.
|
||||
|
||||
if [ -f /etc/sysconfig/kdump ]; then
|
||||
. /etc/sysconfig/kdump
|
||||
fi
|
||||
|
||||
[[ $dracutbasedir ]] || dracutbasedir=/usr/lib/dracut
|
||||
. $dracutbasedir/dracut-functions.sh
|
||||
. /lib/kdump/kdump-lib.sh
|
||||
. /lib/kdump/kdump-logger.sh
|
||||
|
||||
#initiate the kdump logger
|
||||
if ! dlog_init; then
|
||||
echo "mkfadumprd: failed to initiate the kdump logger."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
readonly MKFADUMPRD_TMPDIR="$(mktemp -d -t mkfadumprd.XXXXXX)"
|
||||
[ -d "$MKFADUMPRD_TMPDIR" ] || perror_exit "mkfadumprd: mktemp -d -t mkfadumprd.XXXXXX failed."
|
||||
trap '
|
||||
ret=$?;
|
||||
[[ -d $MKFADUMPRD_TMPDIR ]] && rm --one-file-system -rf -- "$MKFADUMPRD_TMPDIR";
|
||||
exit $ret;
|
||||
' EXIT
|
||||
|
||||
# clean up after ourselves no matter how we die.
|
||||
trap 'exit 1;' SIGINT
|
||||
|
||||
MKDUMPRD="/sbin/mkdumprd -f"
|
||||
# Default boot initramfs to be rebuilt
|
||||
REBUILD_INITRD="$1" && shift
|
||||
TARGET_INITRD="$1" && shift
|
||||
FADUMP_INITRD="$MKFADUMPRD_TMPDIR/fadump.img"
|
||||
|
||||
### First build an initramfs with dump capture capability
|
||||
# this file tells the initrd is fadump enabled
|
||||
touch "$MKFADUMPRD_TMPDIR/fadump.initramfs"
|
||||
ddebug "rebuild fadump initrd: $FADUMP_INITRD $DEFAULT_INITRD $KDUMP_KERNELVER"
|
||||
if ! $MKDUMPRD "$FADUMP_INITRD" -i "$MKFADUMPRD_TMPDIR/fadump.initramfs" /etc/fadump.initramfs; then
|
||||
perror_exit "mkfadumprd: failed to build image with dump capture support"
|
||||
fi
|
||||
|
||||
### Unpack the initramfs having dump capture capability
|
||||
mkdir -p "$MKFADUMPRD_TMPDIR/fadumproot"
|
||||
if ! (pushd "$MKFADUMPRD_TMPDIR/fadumproot" > /dev/null && lsinitrd --unpack "$FADUMP_INITRD" && \
|
||||
popd > /dev/null); then
|
||||
derror "mkfadumprd: failed to unpack '$MKFADUMPRD_TMPDIR'"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
### Pack it into the normal boot initramfs with zz-fadumpinit module
|
||||
_dracut_isolate_args="--rebuild $REBUILD_INITRD --add zz-fadumpinit \
|
||||
-i $MKFADUMPRD_TMPDIR/fadumproot /fadumproot \
|
||||
-i $MKFADUMPRD_TMPDIR/fadumproot/usr/lib/dracut/hostonly-kernel-modules.txt
|
||||
/usr/lib/dracut/fadump-kernel-modules.txt"
|
||||
|
||||
if is_squash_available; then
|
||||
_dracut_isolate_args="$_dracut_isolate_args --add squash"
|
||||
fi
|
||||
if ! dracut --force --quiet $_dracut_isolate_args $@ "$TARGET_INITRD"; then
|
||||
perror_exit "mkfadumprd: failed to setup '$TARGET_INITRD' with dump capture capability"
|
||||
fi
|
||||
File diff suppressed because it is too large
Load Diff
Loading…
Reference in New Issue