Transparent hugepages are on by default. Disable it in kdump kernel by adding parameter transparent_hugepage=never. This might help us with some of the memory issues we are facing.
Signed-off-by: Li Wang liwang@redhat.com --- kdump.sysconfig.x86_64 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kdump.sysconfig.x86_64 b/kdump.sysconfig.x86_64 index d9ad9b5..7991d68 100644 --- a/kdump.sysconfig.x86_64 +++ b/kdump.sysconfig.x86_64 @@ -16,7 +16,7 @@ KDUMP_COMMANDLINE=""
# This variable lets us append arguments to the current kdump commandline # As taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline -KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices cgroup_disable=memory mce=off numa=off udev.children-max=2 panic=10 rootflags=nofail acpi_no_memhotplug" +KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices cgroup_disable=memory mce=off numa=off udev.children-max=2 panic=10 rootflags=nofail acpi_no_memhotplug transparent_hugepage=never"
# Any additional kexec arguments required. In most situations, this should # be left empty
On 05/18/15 at 04:32pm, Li Wang wrote:
Transparent hugepages are on by default. Disable it in kdump kernel by adding parameter transparent_hugepage=never. This might help us with some of the memory issues we are facing.
Signed-off-by: Li Wang liwang@redhat.com
kdump.sysconfig.x86_64 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kdump.sysconfig.x86_64 b/kdump.sysconfig.x86_64 index d9ad9b5..7991d68 100644 --- a/kdump.sysconfig.x86_64 +++ b/kdump.sysconfig.x86_64 @@ -16,7 +16,7 @@ KDUMP_COMMANDLINE=""
# This variable lets us append arguments to the current kdump commandline # As taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline -KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices cgroup_disable=memory mce=off numa=off udev.children-max=2 panic=10 rootflags=nofail acpi_no_memhotplug" +KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices cgroup_disable=memory mce=off numa=off udev.children-max=2 panic=10 rootflags=nofail acpi_no_memhotplug transparent_hugepage=never"
Hi, Li Wang.
Does it work for other arch? if so, it is better to fix all of the arch.
Thanks Minfei
# Any additional kexec arguments required. In most situations, this should
# be left empty
1.8.3.1
kexec mailing list kexec@lists.fedoraproject.org https://lists.fedoraproject.org/mailman/listinfo/kexec
----- Original Message -----
On 05/18/15 at 04:32pm, Li Wang wrote:
Transparent hugepages are on by default. Disable it in kdump kernel by adding parameter transparent_hugepage=never. This might help us with some of the memory issues we are facing.
Signed-off-by: Li Wang liwang@redhat.com
kdump.sysconfig.x86_64 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kdump.sysconfig.x86_64 b/kdump.sysconfig.x86_64 index d9ad9b5..7991d68 100644 --- a/kdump.sysconfig.x86_64 +++ b/kdump.sysconfig.x86_64 @@ -16,7 +16,7 @@ KDUMP_COMMANDLINE=""
# This variable lets us append arguments to the current kdump commandline # As taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline -KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices cgroup_disable=memory mce=off numa=off udev.children-max=2 panic=10 rootflags=nofail acpi_no_memhotplug" +KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices cgroup_disable=memory mce=off numa=off udev.children-max=2 panic=10 rootflags=nofail acpi_no_memhotplug transparent_hugepage=never"
Hi, Li Wang.
Does it work for other arch? if so, it is better to fix all of the arch.
Yeah, it does. I will post V2 patch.
Thanks for review.
Li Wang
Thanks Minfei
# Any additional kexec arguments required. In most situations, this should
# be left empty
1.8.3.1
kexec mailing list kexec@lists.fedoraproject.org https://lists.fedoraproject.org/mailman/listinfo/kexec
On 05/18/15 at 04:32pm, Li Wang wrote:
Transparent hugepages are on by default. Disable it in kdump kernel by adding parameter transparent_hugepage=never. This might help us with some of the memory issues we are facing.
Signed-off-by: Li Wang liwang@redhat.com
Hi Wang,
It's not the same issue as this commit 12b86202b58e117504f7beda3207b8c7efd5a785, is it?
Thanks Baoquan
kdump.sysconfig.x86_64 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kdump.sysconfig.x86_64 b/kdump.sysconfig.x86_64 index d9ad9b5..7991d68 100644 --- a/kdump.sysconfig.x86_64 +++ b/kdump.sysconfig.x86_64 @@ -16,7 +16,7 @@ KDUMP_COMMANDLINE=""
# This variable lets us append arguments to the current kdump commandline # As taken from either KDUMP_COMMANDLINE above, or from /proc/cmdline -KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices cgroup_disable=memory mce=off numa=off udev.children-max=2 panic=10 rootflags=nofail acpi_no_memhotplug" +KDUMP_COMMANDLINE_APPEND="irqpoll nr_cpus=1 reset_devices cgroup_disable=memory mce=off numa=off udev.children-max=2 panic=10 rootflags=nofail acpi_no_memhotplug transparent_hugepage=never"
# Any additional kexec arguments required. In most situations, this should
# be left empty
1.8.3.1
kexec mailing list kexec@lists.fedoraproject.org https://lists.fedoraproject.org/mailman/listinfo/kexec
----- Original Message -----
On 05/18/15 at 04:32pm, Li Wang wrote:
Transparent hugepages are on by default. Disable it in kdump kernel by adding parameter transparent_hugepage=never. This might help us with some of the memory issues we are facing.
Signed-off-by: Li Wang liwang@redhat.com
Hi Wang,
It's not the same issue as this commit 12b86202b58e117504f7beda3207b8c7efd5a785, is it?
Hi Baoquan,
Yes, it's not the same issue. The commit 12b8620... is about hugepage allocations, But this patch is fix the THP(transparent hugepage) issue. They are not the same things :)
Regards, Li Wang
On 05/18/15 at 05:14am, Li Wang wrote:
----- Original Message -----
On 05/18/15 at 04:32pm, Li Wang wrote:
Transparent hugepages are on by default. Disable it in kdump kernel by adding parameter transparent_hugepage=never. This might help us with some of the memory issues we are facing.
Signed-off-by: Li Wang liwang@redhat.com
Hi Wang,
It's not the same issue as this commit 12b86202b58e117504f7beda3207b8c7efd5a785, is it?
Hi Baoquan,
Yes, it's not the same issue. The commit 12b8620... is about hugepage allocations, But this patch is fix the THP(transparent hugepage) issue. They are not the same things :)
OK, I got it. Chao Wang's patch only takes care of hugeTLB. So you add this to disable transparent hugepage. This makes sense.
Will ack it when patch is updated.
Thanks Baoquan
Regards, Li Wang _______________________________________________ kexec mailing list kexec@lists.fedoraproject.org https://lists.fedoraproject.org/mailman/listinfo/kexec