Add descriptions of parallel dumping and how to use it.
Signed-off-by: Zhou Wenjian zhouwj-fnst@cn.fujitsu.com --- v2->v3: 1.address Baoquan He's comment on disable_cpu_apicid v1->v2: 1.fix some inappropriate description 2.delete some unnecessary description
kexec-kdump-howto.txt | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+)
diff --git a/kexec-kdump-howto.txt b/kexec-kdump-howto.txt index 05b497f..6e49f35 100644 --- a/kexec-kdump-howto.txt +++ b/kexec-kdump-howto.txt @@ -616,6 +616,37 @@ 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.
+Parallel Dumping Operation +========================== +Kexec allows kdump using multiple cpus. So parallel feature can accelerate +dumping substantially, especially in executing compress and filter. +For example: + + 1."makedumpfile -c --num-threads [THREAD_NUM] /proc/vmcore dumpfile" + 2."makedumpfile -c /proc/vmcore dumpfile", + + 1 has better performance than 2, if THREAD_NUM is larger than two + and the usable cpus number is larger than THREAD_NUM. + +Notes on how to use multiple cpus on a capture kernel on x86 system: + +Make sure that you are using a kernel that supports disable_cpu_apicid +kernel option as a capture kernel, which is needed to avoid x86 specific +hardware issue (*). The disable_cpu_apicid kernel option is automatically +appended by kdumpctl script and is ignored if the kernel doesn't support it. + +You need to specify how many cpus to be used in a capture kernel by specifying +the number of cpus in nr_cpus kernel option in /etc/sysconfig/kdump. nr_cpus +is 1 at default. + +You should use necessary and suffcient number of cpus on a capture kernel. +IOW, don't use too many cpus on a capture kernel, or the capture kernel may +lead to panic due to Out Of Memory(each cpu uses about 1MB). + +(*) Without disable_cpu_apicid kernel option, capture kernel may lead to +hang, system reset or power-off at boot, depending on your system and runtime +situation at the time of crash. + Debugging Tips -------------- - One can drop into a shell before/after saving vmcore with the help of
On 16/09/2015:03:50:52 PM, Zhou Wenjian wrote:
Add descriptions of parallel dumping and how to use it.
Signed-off-by: Zhou Wenjian zhouwj-fnst@cn.fujitsu.com
Reviewed-by: Pratyush Anand panand@redhat.com
Hi,
On 09/16/15 at 03:50pm, Zhou Wenjian wrote:
Add descriptions of parallel dumping and how to use it.
Signed-off-by: Zhou Wenjian zhouwj-fnst@cn.fujitsu.com
v2->v3: 1.address Baoquan He's comment on disable_cpu_apicid v1->v2: 1.fix some inappropriate description 2.delete some unnecessary description
kexec-kdump-howto.txt | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+)
diff --git a/kexec-kdump-howto.txt b/kexec-kdump-howto.txt index 05b497f..6e49f35 100644 --- a/kexec-kdump-howto.txt +++ b/kexec-kdump-howto.txt @@ -616,6 +616,37 @@ 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.
+Parallel Dumping Operation +========================== +Kexec allows kdump using multiple cpus. So parallel feature can accelerate +dumping substantially, especially in executing compress and filter.
s/compress/compression
+For example:
- 1."makedumpfile -c --num-threads [THREAD_NUM] /proc/vmcore dumpfile"
- 2."makedumpfile -c /proc/vmcore dumpfile",
- 1 has better performance than 2, if THREAD_NUM is larger than two
- and the usable cpus number is larger than THREAD_NUM.
+Notes on how to use multiple cpus on a capture kernel on x86 system:
+Make sure that you are using a kernel that supports disable_cpu_apicid +kernel option as a capture kernel, which is needed to avoid x86 specific +hardware issue (*). The disable_cpu_apicid kernel option is automatically +appended by kdumpctl script and is ignored if the kernel doesn't support it.
+You need to specify how many cpus to be used in a capture kernel by specifying +the number of cpus in nr_cpus kernel option in /etc/sysconfig/kdump. nr_cpus +is 1 at default.
+You should use necessary and suffcient number of cpus on a capture kernel.
s/suffcient/sufficient
+IOW, don't use too many cpus on a capture kernel, or the capture kernel may +lead to panic due to Out Of Memory(each cpu uses about 1MB).
Each cpu uses about 1MB may be not precise, it will depends on kernel, who knows it use how much in the future. It will use much more on powerpc architecture per our testing.
So remove the (each cpu uses about 1MB) and change 'IOW,' to 'Warning: ' sounds better.
+(*) Without disable_cpu_apicid kernel option, capture kernel may lead to +hang, system reset or power-off at boot, depending on your system and runtime +situation at the time of crash.
Debugging Tips
- One can drop into a shell before/after saving vmcore with the help of
-- 1.8.3.1
kexec mailing list kexec@lists.fedoraproject.org https://lists.fedoraproject.org/mailman/listinfo/kexec
BTW, if you need a RHEL fix please file a bug again proper version.
THanks Dave
Hello Dave,
I have fixed the words.
But I have a question about the following.
BTW, if you need a RHEL fix please file a bug again proper version.
Do you mean that I need to file a bug report in https://bugzilla.redhat.com?
On 09/25/15 at 04:32pm, "Zhou, Wenjian/周文剑" wrote:
Hello Dave,
I have fixed the words.
But I have a question about the following.
BTW, if you need a RHEL fix please file a bug again proper version.
Do you mean that I need to file a bug report in https://bugzilla.redhat.com?
Yes if you need a RHEL fix.
Thanks Dave
On 09/25/2015 04:57 PM, Dave Young wrote:
On 09/25/15 at 04:32pm, "Zhou, Wenjian/周文剑" wrote:
Hello Dave,
I have fixed the words.
But I have a question about the following.
BTW, if you need a RHEL fix please file a bug again proper version.
Do you mean that I need to file a bug report in https://bugzilla.redhat.com?
Yes if you need a RHEL fix.
Thank you for telling me that.