If the total amount of memory assigned to quarantine is less than the
amount of memory assigned to per-cpu quarantines, |new_quarantine_size|
may overflow. Instead, set it to zero.
Reported-by: Dmitry Vyukov
Fixes: 55834c59098d ("mm: kasan: initial memory quarantine
implementation")
> However, it appears that the same process, dTi-lm, is still chosen for oom
> kill
> because lowmem_deathpending_timeout has expired.
>
> So this looks like a problem if the constantly chosen process cannot exit.
> It would have been helpful to have the stack of pid 27289 in the log to see
>
> However, it appears that the same process, dTi-lm, is still chosen for oom
> kill
> because lowmem_deathpending_timeout has expired.
>
> So this looks like a problem if the constantly chosen process cannot exit.
> It would have been helpful to have the stack of pid 27289 in the log to see
>
ll hang, no process can be
> select to kill.
>
> i found the the value of "lowmem_deathpending_timeout" will be modified
> strangely, like in last killing, the value is 4296194081, but why not it
> had changed to 4296195109? so it will cause the deadloop in low memory
ll hang, no process can be
> select to kill.
>
> i found the the value of "lowmem_deathpending_timeout" will be modified
> strangely, like in last killing, the value is 4296194081, but why not it
> had changed to 4296195109? so it will cause the deadloop in low memory
> >
> > Signed-off-by: Figo Zhang
>
> As you ignored my instructions to you, I'm going to just ignore this patch,
> sorry. Now discarded.
>
I am no at intel kernel group (SSG OTC), I am at CCG CCE. I will involve the
intel open source guys if they like to help.
Hi fengguang:
Would you like
ndroid system UI will hang, no process can be
> select to kill.
>
> i found the the value of "lowmem_deathpending_timeout" will be modified
> strangely, like in last killing, the value is 4296194081, but why not it
> had changed to 4296195109? so it will cause the deadloop
will hang, no process can be
select to kill.
i found the the value of "lowmem_deathpending_timeout" will be modified
strangely, like in last killing, the value is 4296194081, but why not it
had changed to 4296195109? so it will cause the deadloop in low memory
state which will cause the an
On Sun, Dec 27, 2015 at 04:34:56PM +0800, Figo.zhang wrote:
> From: Figo
This doesn't match your signed-off-by name :(
> Signed-off-by: Figo.zhang
I doubt that you have a '.' in your name :(
Again, please consult the Intel Linux kernel group for how to do this
correctly, I will not accept
system UI will hang, no process can be
select to kill.
i found the the value of "lowmem_deathpending_timeout" will be modified
strangely, like in last killing, the value is 4296194081, but why not it
had changed to 4296195109? so it will cause the deadloop in low memory
state which wi
found the the value of "lowmem_deathpending_timeout" will be modified
strangely, like in last killing, the value is 4296194081, but why not it
had changed to 4296195109? so it will cause the deadloop in low memory
state which will cause the android system UI hang, because no process will
b
On Sun, Dec 27, 2015 at 12:19:08AM +, Zhang, Tianfei wrote:
> > Great, please use that, but why does your email address show a different
> > name? Intel has standards that you have to follow when submitting Linux
> > kernel patches, please consult them before you resend.
> >
>
> Hi greg, I
> Great, please use that, but why does your email address show a different
> name? Intel has standards that you have to follow when submitting Linux
> kernel patches, please consult them before you resend.
>
Hi greg, I should resend this patch using [PATCH RESEND v2 1/1]?
On Sat, Dec 26, 2015 at 11:24:14PM +, Zhang, Tianfei wrote:
> > > Android System UI hang when run heavy monkey stress test.
> >
> > What changed from v1 of this patch? Please describe that below the ---
> > line.
> V2,I just modify my comments.
Then say so. How am I supposed to know?
> >
On Sun, Dec 27, 2015 at 12:42:31AM +0100, Harald Arnesen wrote:
> Greg KH [2015-12-26 19:12]:
>
> > I need a "full" name here, not a "short" name, sorry, before I can do
> > anything with this patch.
>
> I don't know if that is the case here, but:
>
> You know, of course, that there are
Greg KH [2015-12-26 19:12]:
> I need a "full" name here, not a "short" name, sorry, before I can do
> anything with this patch.
I don't know if that is the case here, but:
You know, of course, that there are societies in this world where only
one name is used?
--
Hilsen Harald
--
To
> > Android System UI hang when run heavy monkey stress test.
>
> What changed from v1 of this patch? Please describe that below the ---
> line.
V2,I just modify my comments.
>
> >
> > Signed-off-by: Figo
>
> I need a "full" name here, not a "short" name, sorry, before I can do anything
>
On Sun, Dec 27, 2015 at 03:39:42AM +0800, Figo wrote:
> Android System UI hang when run heavy monkey stress test.
What changed from v1 of this patch? Please describe that below the ---
line.
>
> Signed-off-by: Figo
I need a "full" name here, not a "short" name, sorry, before I can do
fied
strangely, like in last killing, the value is 4296194081, but why not it
had changed to 4296195109? so it will cause the deadloop in low memory
state which will cause the android system UI hang, because no process will
be kill.
commit e5d7965f88a3 ("staging: android: lowmemorykiller: Don't
4296194081, but why not it
had changed to 4296195109? so it will cause the deadloop in low memory
state which will cause the android system UI hang, because no process will
be kill.
commit e5d7965f88a3 ("staging: android: lowmemorykiller: Don't wait more
than one second for a process to die"
4296194081, but why not it
had changed to 4296195109? so it will cause the deadloop in low memory
state which will cause the android system UI hang, because no process will
be kill.
commit e5d7965f88a3 ("staging: android: lowmemorykiller: Don't wait more
than one second for a process to die"
On Sun, Dec 27, 2015 at 03:39:42AM +0800, Figo wrote:
> Android System UI hang when run heavy monkey stress test.
What changed from v1 of this patch? Please describe that below the ---
line.
>
> Signed-off-by: Figo
I need a "full" name here, not a "short" name,
fied
strangely, like in last killing, the value is 4296194081, but why not it
had changed to 4296195109? so it will cause the deadloop in low memory
state which will cause the android system UI hang, because no process will
be kill.
commit e5d7965f88a3 ("staging: android: lowmemorykiller: Don't
4296194081, but why not it
had changed to 4296195109? so it will cause the deadloop in low memory
state which will cause the android system UI hang, because no process will
be kill.
commit e5d7965f88a3 ("staging: android: lowmemorykiller: Don't wait more
than one second for a process to die"
4296194081, but why not it
had changed to 4296195109? so it will cause the deadloop in low memory
state which will cause the android system UI hang, because no process will
be kill.
commit e5d7965f88a3 ("staging: android: lowmemorykiller: Don't wait more
than one second for a process to die"
> > Android System UI hang when run heavy monkey stress test.
>
> What changed from v1 of this patch? Please describe that below the ---
> line.
V2,I just modify my comments.
>
> >
> > Signed-off-by: Figo
>
> I need a "full" name here, not a "short" name, sorry,
On Sun, Dec 27, 2015 at 12:42:31AM +0100, Harald Arnesen wrote:
> Greg KH [2015-12-26 19:12]:
>
> > I need a "full" name here, not a "short" name, sorry, before I can do
> > anything with this patch.
>
> I don't know if that is the case here, but:
>
> You know, of course, that there are
On Sat, Dec 26, 2015 at 11:24:14PM +, Zhang, Tianfei wrote:
> > > Android System UI hang when run heavy monkey stress test.
> >
> > What changed from v1 of this patch? Please describe that below the ---
> > line.
> V2,I just modify my comments.
Then say so. How am I supposed to know?
> >
Greg KH [2015-12-26 19:12]:
> I need a "full" name here, not a "short" name, sorry, before I can do
> anything with this patch.
I don't know if that is the case here, but:
You know, of course, that there are societies in this world where only
one name is used?
--
Hilsen Harald
--
To
On Sun, Dec 27, 2015 at 12:19:08AM +, Zhang, Tianfei wrote:
> > Great, please use that, but why does your email address show a different
> > name? Intel has standards that you have to follow when submitting Linux
> > kernel patches, please consult them before you resend.
> >
>
> Hi greg, I
On Sun, Dec 27, 2015 at 04:34:56PM +0800, Figo.zhang wrote:
> From: Figo
This doesn't match your signed-off-by name :(
> Signed-off-by: Figo.zhang
I doubt that you have a '.' in your name :(
Again, please consult the Intel Linux kernel group
will hang, no process can be
select to kill.
i found the the value of "lowmem_deathpending_timeout" will be modified
strangely, like in last killing, the value is 4296194081, but why not it
had changed to 4296195109? so it will cause the deadloop in low memory
state which will cause the an
> Great, please use that, but why does your email address show a different
> name? Intel has standards that you have to follow when submitting Linux
> kernel patches, please consult them before you resend.
>
Hi greg, I should resend this patch using [PATCH RESEND v2 1/1]?
process can be
select to kill.
i found the the value of "lowmem_deathpending_timeout" will be modified
strangely, like in last killing, the value is 4296194081, but why not it
had changed to 4296195109? so it will cause the deadloop in low memory
state which will cause the android system UI han
en this happened, the android system UI will hang, no process can be
select to kill.
i found the the value of "lowmem_deathpending_timeout" will be modified
strangely, like in last killing, the value is 4296194081, but why not it
had changed to 4296195109? so it will cause the deadloop
ndroid system UI will hang, no process can be
> select to kill.
>
> i found the the value of "lowmem_deathpending_timeout" will be modified
> strangely, like in last killing, the value is 4296194081, but why not it
> had changed to 4296195109? so it will cause the deadloop
> >
> > Signed-off-by: Figo Zhang
>
> As you ignored my instructions to you, I'm going to just ignore this patch,
> sorry. Now discarded.
>
I am no at intel kernel group (SSG OTC), I am at CCG CCE. I will involve the
intel open source guys if they like to help.
Hi
rvation of the low portion fails.
Then kexec can load the kdump kernel successfully, but booting the kdump
kernel fails as there's no low memory.
The low memory allocation for the kdump kernel can fail on large systems
for a couple of reasons. For example, the manually specified crashkernel
low
ot;low"
> portion fails. Then kexec can load kdump kernel successfully, but
> the boot of kdump kernel fails as there's no low memory. This is
> because allocation of low memory for kdump kernel can fail on large
> systems for reasons. E.g it could be manually specified cra
cceeds, but the reservation of the "low"
> portion fails. Then kexec can load kdump kernel successfully, but
> the boot of kdump kernel fails as there's no low memory. This is
> because allocation of low memory for kdump kernel can fail on large
> systems for reasons. E.g it coul
cceeds, but the reservation of the "low"
> portion fails. Then kexec can load kdump kernel successfully, but
> the boot of kdump kernel fails as there's no low memory. This is
> because allocation of low memory for kdump kernel can fail on large
> systems for reasons. E.g it coul
ot;low"
> portion fails. Then kexec can load kdump kernel successfully, but
> the boot of kdump kernel fails as there's no low memory. This is
> because allocation of low memory for kdump kernel can fail on large
> systems for reasons. E.g it could be manually specified cra
the reservation of the
high portion succeeds but the reservation of the low portion fails.
Then kexec can load the kdump kernel successfully, but booting the kdump
kernel fails as there's no low memory.
The low memory allocation for the kdump kernel can fail on large systems
for a couple of reasons. For exa
ully, but
the boot of kdump kernel fails as there's no low memory. This is
because allocation of low memory for kdump kernel can fail on large
systems for reasons. E.g it could be manually specified crashkernel
low memory is too large to find in memblock region.
In this patch add return value for rese
ully, but
the boot of kdump kernel fails as there's no low memory. This is
because allocation of low memory for kdump kernel can fail on large
systems for reasons. E.g it could be manually specified crashkernel
low memory is too large to find in memblock region.
In this patch add return value for rese
On 09/22/15 at 05:08pm, Andrew Morton wrote:
> On Wed, 23 Sep 2015 08:02:55 +0800 Baoquan He wrote:
>
> > >
> > > > }
> > > >
> > > > low_base = memblock_find_in_range(low_size, (1ULL<<32),
> > > > low_size, alignment);
> > > >
> > > >
On Wed, 23 Sep 2015 08:02:55 +0800 Baoquan He wrote:
> >
> > > }
> > >
> > > low_base = memblock_find_in_range(low_size, (1ULL<<32),
> > > low_size, alignment);
> > >
> > > if (!low_base) {
> > > - if (!auto_set)
> > > -
@ -522,17 +522,15 @@ static void __init reserve_crashkernel_low(void)
> > } else {
> > /* passed with crashkernel=0,low ? */
> > if (!low_size)
> > - return;
> > + return 0;
>
> What's happening here? It's returning &q
"
> portion fails. Then kexec can load kdump kernel successfully, but
> the boot of kdump kernel fails as there's no low memory. This is
> because allocation of low memory for kdump kernel can fail on large
> systems for reasons. E.g it could be manually specified cra
e "low"
> portion fails. Then kexec can load kdump kernel successfully, but
> the boot of kdump kernel fails as there's no low memory. This is
> because allocation of low memory for kdump kernel can fail on large
> systems for reasons. E.g it could be manually specified cra
ully, but
the boot of kdump kernel fails as there's no low memory. This is
because allocation of low memory for kdump kernel can fail on large
systems for reasons. E.g it could be manually specified crashkernel
low memory is too large to find in memblock region.
In this patch add return value for rese
tion of the "low"
> portion fails. Then kexec can load kdump kernel successfully, but
> the boot of kdump kernel fails as there's no low memory. This is
> because allocation of low memory for kdump kernel can fail on large
> systems for reasons. E.g it could be manually specifi
On Wed, 23 Sep 2015 08:02:55 +0800 Baoquan He wrote:
> >
> > > }
> > >
> > > low_base = memblock_find_in_range(low_size, (1ULL<<32),
> > > low_size, alignment);
> > >
> > > if (!low_base) {
> > > - if (!auto_set)
> > > -
On 09/22/15 at 05:08pm, Andrew Morton wrote:
> On Wed, 23 Sep 2015 08:02:55 +0800 Baoquan He wrote:
>
> > >
> > > > }
> > > >
> > > > low_base = memblock_find_in_range(low_size, (1ULL<<32),
> > > > low_size, alignment);
@ -522,17 +522,15 @@ static void __init reserve_crashkernel_low(void)
> > } else {
> > /* passed with crashkernel=0,low ? */
> > if (!low_size)
> > - return;
> > + return 0;
>
> What's happening here? It's returning &q
e "low"
> portion fails. Then kexec can load kdump kernel successfully, but
> the boot of kdump kernel fails as there's no low memory. This is
> because allocation of low memory for kdump kernel can fail on large
> systems for reasons. E.g it could be manually specified cra
ully, but
the boot of kdump kernel fails as there's no low memory. This is
because allocation of low memory for kdump kernel can fail on large
systems for reasons. E.g it could be manually specified crashkernel
low memory is too large to find in memblock region.
In this patch add return value for rese
On Wed, Jul 29, 2015 at 01:54:12PM +0200, Michal Hocko wrote:
> On Tue 21-07-15 10:58:59, Michal Hocko wrote:
> > [CCing more people from a potentially affected fs - the reference to the
> > email thread is: http://marc.info/?l=linux-mm=143744398020147=2]
...
> > > The didn't used to happen,
On Tue 21-07-15 10:58:59, Michal Hocko wrote:
> [CCing more people from a potentially affected fs - the reference to the
> email thread is: http://marc.info/?l=linux-mm=143744398020147=2]
>
> On Tue 21-07-15 11:59:34, Dave Chinner wrote:
> > Hi Ming,
> >
> > With the recent merge of the loop
On Wed, Jul 29, 2015 at 01:54:12PM +0200, Michal Hocko wrote:
On Tue 21-07-15 10:58:59, Michal Hocko wrote:
[CCing more people from a potentially affected fs - the reference to the
email thread is: http://marc.info/?l=linux-mmm=143744398020147w=2]
...
The didn't used to happen, because
On Tue 21-07-15 10:58:59, Michal Hocko wrote:
[CCing more people from a potentially affected fs - the reference to the
email thread is: http://marc.info/?l=linux-mmm=143744398020147w=2]
On Tue 21-07-15 11:59:34, Dave Chinner wrote:
Hi Ming,
With the recent merge of the loop device
itialized successfully. There's possibility that hw iommu
> > initialization will fail, in this case kdump kernel will fail to boot
> > if no any low memory is given. So we can't make assumption that system
> > can boot always well without low memory.
>
> When we had crashk
initialization will fail, in this case kdump kernel will fail to boot
if no any low memory is given. So we can't make assumption that system
can boot always well without low memory.
When we had crashkernel=,high working with auto low=40M.
all system with crashkernel=,high worked.
Now come one
case kdump kernel will fail to boot
> if no any low memory is given. So we can't make assumption that system
> can boot always well without low memory.
When we had crashkernel=,high working with auto low=40M.
all system with crashkernel=,high worked.
Now come one model (assume it is 16 socket syst
ill can
> > enable swiotlb suport. Then low memory is needed.
>
> Do you have whole bootlog? I don't understand why those system can not use
> full iommu. BIOS problem or HW/silicon limitation?
Sorry for late reply. This problem is reported by customers. They usulay
don't like to m
On 07/27/15 at 11:31am, Yinghai Lu wrote:
> >> #else
> >> static void __init reserve_crashkernel(void)
>
> No, you can not move the calling position for reserve_crashkernel_low().
>
> old sequence:
>
> memblock_find_in_range for high
> memblock_reserve for high
> memblock_find_in_range for
On Tue, Jul 21, 2015 at 12:31 AM, Dave Young wrote:
>> diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
>> index 80f874b..36aeac3 100644
>> --- a/arch/x86/kernel/setup.c
>> +++ b/arch/x86/kernel/setup.c
>> @@ -513,7 +513,7 @@ static void __init
>>
On Tue, Jul 21, 2015 at 09:38:14AM +0200, Ingo Molnar wrote:
> Also, why was this syntax introduced in the first place? Why should the user
> care??
>
> We should only have a single crashkernel option, to enable it - and
> everything
> else should be figured out by the kernel, automatically.
>
cceeds, but the reservation of the "low"
> portion fails. Then kexec can load kdump kernel successfully, but
> the boot of kdump kernel fails as there's no low memory. This is
> because allocation of low memory for kdump kernel can fail on large
> systems for reasons. E.g it coul
On Wed, Jul 22, 2015 at 04:41:00PM -0700, Yinghai Lu wrote:
> Do you mean BIOS have that disabled with not exposing DMAR table ?
>
> kernel for RHEL 6 and RHEL7 have them enabled.
> Also opensuse kernel have that enabled too.
You still need to pass intel_iommu=on in the kernel command line to
On Wed, Jul 22, 2015 at 04:41:00PM -0700, Yinghai Lu wrote:
Do you mean BIOS have that disabled with not exposing DMAR table ?
kernel for RHEL 6 and RHEL7 have them enabled.
Also opensuse kernel have that enabled too.
You still need to pass intel_iommu=on in the kernel command line to
enable
On Tue, Jul 21, 2015 at 09:38:14AM +0200, Ingo Molnar wrote:
Also, why was this syntax introduced in the first place? Why should the user
care??
We should only have a single crashkernel option, to enable it - and
everything
else should be figured out by the kernel, automatically.
Any
. Then kexec can load kdump kernel successfully, but
the boot of kdump kernel fails as there's no low memory. This is
because allocation of low memory for kdump kernel can fail on large
systems for reasons. E.g it could be manually specified crashkernel
low memory is too large to find in memblock
On Tue, Jul 21, 2015 at 12:31 AM, Dave Young dyo...@redhat.com wrote:
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 80f874b..36aeac3 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -513,7 +513,7 @@ static void __init
On 07/27/15 at 11:31am, Yinghai Lu wrote:
#else
static void __init reserve_crashkernel(void)
No, you can not move the calling position for reserve_crashkernel_low().
old sequence:
memblock_find_in_range for high
memblock_reserve for high
memblock_find_in_range for low
. Then low memory is needed.
Do you have whole bootlog? I don't understand why those system can not use
full iommu. BIOS problem or HW/silicon limitation?
Sorry for late reply. This problem is reported by customers. They usulay
don't like to make these things public. While for those systems
to boot
if no any low memory is given. So we can't make assumption that system
can boot always well without low memory.
When we had crashkernel=,high working with auto low=40M.
all system with crashkernel=,high worked.
Now come one model (assume it is 16 socket system), and it
could use
On Tue, Jul 21, 2015 at 5:59 PM, Baoquan He wrote:
>> That commit should only be used to workaround some systems that
>> have partial iommu support.
>
> Those big servers mostly has hardware iommu. But they still can
> enable swiotlb suport. Then low memory is needed.
Do y
On Tue, Jul 21, 2015 at 9:47 PM, Minfei Huang wrote:
>
> Since low memory does not need for some machines, how about kexec does
> not allocate low memory automatically, if cmdline does not specify the
> option ",low". User shall know well, if they specify the cmdlin
On Wed, Jul 22, 2015 at 3:11 AM, Joerg Roedel wrote:
> On Tue, Jul 21, 2015 at 12:22:53PM -0700, Yinghai Lu wrote:
>> On Tue, Jul 21, 2015 at 1:58 AM, Baoquan He wrote:
>>
>> > Maybe system which don't need low memory is rare, only for testing?
>>
>> No, it
On Tue, Jul 21, 2015 at 12:22:53PM -0700, Yinghai Lu wrote:
> On Tue, Jul 21, 2015 at 1:58 AM, Baoquan He wrote:
>
> > Maybe system which don't need low memory is rare, only for testing?
>
> No, it is not rare.
>
> All recent intel based systems with iommu support does
On Tue, Jul 21, 2015 at 12:22:53PM -0700, Yinghai Lu wrote:
On Tue, Jul 21, 2015 at 1:58 AM, Baoquan He b...@redhat.com wrote:
Maybe system which don't need low memory is rare, only for testing?
No, it is not rare.
All recent intel based systems with iommu support does not need low
On Tue, Jul 21, 2015 at 9:47 PM, Minfei Huang mhu...@redhat.com wrote:
Since low memory does not need for some machines, how about kexec does
not allocate low memory automatically, if cmdline does not specify the
option ,low. User shall know well, if they specify the cmdline with
option ,high
On Wed, Jul 22, 2015 at 3:11 AM, Joerg Roedel j...@8bytes.org wrote:
On Tue, Jul 21, 2015 at 12:22:53PM -0700, Yinghai Lu wrote:
On Tue, Jul 21, 2015 at 1:58 AM, Baoquan He b...@redhat.com wrote:
Maybe system which don't need low memory is rare, only for testing?
No, it is not rare.
All
On Tue, Jul 21, 2015 at 5:59 PM, Baoquan He b...@redhat.com wrote:
That commit should only be used to workaround some systems that
have partial iommu support.
Those big servers mostly has hardware iommu. But they still can
enable swiotlb suport. Then low memory is needed.
Do you have whole
On 07/21/15 at 12:22pm, Yinghai Lu wrote:
> On Tue, Jul 21, 2015 at 1:58 AM, Baoquan He wrote:
>
> > Maybe system which don't need low memory is rare, only for testing?
>
> No, it is not rare.
>
> All recent intel based systems with iommu support does not need low.
&g
mory user prefers crashkernel memory
resereved above 4G since memory space above 4G could be huge while
memory under 4G is very limited. So system with more than 1T physical
memory should take high memory and with a very few low memory
reservation, e.g about 100M. This is very cost-effective for those
sy
On 07/21/15 at 12:22pm, Yinghai Lu wrote:
> On Tue, Jul 21, 2015 at 1:58 AM, Baoquan He wrote:
>
> > Maybe system which don't need low memory is rare, only for testing?
>
> No, it is not rare.
>
> All recent intel based systems with iommu support does not need l
On Tue, Jul 21, 2015 at 1:58 AM, Baoquan He wrote:
> Maybe system which don't need low memory is rare, only for testing?
No, it is not rare.
All recent intel based systems with iommu support does not need low.
And those systems get punished by following patch:
| com
[CCing more people from a potentially affected fs - the reference to the
email thread is: http://marc.info/?l=linux-mm=143744398020147=2]
On Tue 21-07-15 11:59:34, Dave Chinner wrote:
> Hi Ming,
>
> With the recent merge of the loop device changes, I'm now seeing
> XFS deadlock on my single
On 07/21/15 at 04:23pm, Dave Young wrote:
> > I think so. the reason why ,low is introduced is swiotlb or pci device
> > need low memory when crashkernel is reserved above 4G. Low memory is
> > necessary when ,high is specified unless user can make sure their
> > machin
ed that when allocating crashkernel memory using
> > > ",high" and ",low" syntax, there were cases where the reservation
> > > of the "high" portion succeeds, but the reservation of the "low"
> > > portion fails. Then kexec can load
d
> everything
> else should be figured out by the kernel, automatically.
Presonally I do not current complicated params either, I hope we can have an
elegant interface, but seems there's no better way to resolve the low memory
only requirement for software tlb.
>
> Any other sub-
",low" syntax, there were cases where the reservation
> > of the "high" portion succeeds, but the reservation of the "low"
> > portion fails. Then kexec can load kdump kernel successfully, but
> > the boot of kdump kernel fails as there's no low memory. This i
* Dave Young wrote:
> Hi, Baoquan
>
> The interface was introduced by Yinghai, ccing him.
Also, why was this syntax introduced in the first place? Why should the user
care??
We should only have a single crashkernel option, to enable it - and everything
else should be figured out by the
; portion succeeds, but the reservation of the "low"
> portion fails. Then kexec can load kdump kernel successfully, but
> the boot of kdump kernel fails as there's no low memory. This is
> because allocation of low memory for kdump kernel can fail on large
> systems for reasons
On 07/21/15 at 12:22pm, Yinghai Lu wrote:
On Tue, Jul 21, 2015 at 1:58 AM, Baoquan He b...@redhat.com wrote:
Maybe system which don't need low memory is rare, only for testing?
No, it is not rare.
All recent intel based systems with iommu support does not need low.
And those systems
resereved above 4G since memory space above 4G could be huge while
memory under 4G is very limited. So system with more than 1T physical
memory should take high memory and with a very few low memory
reservation, e.g about 100M. This is very cost-effective for those
systems where pci memory space
On Tue, Jul 21, 2015 at 1:58 AM, Baoquan He b...@redhat.com wrote:
Maybe system which don't need low memory is rare, only for testing?
No, it is not rare.
All recent intel based systems with iommu support does not need low.
And those systems get punished by following patch:
| commit
On 07/21/15 at 12:22pm, Yinghai Lu wrote:
On Tue, Jul 21, 2015 at 1:58 AM, Baoquan He b...@redhat.com wrote:
Maybe system which don't need low memory is rare, only for testing?
No, it is not rare.
All recent intel based systems with iommu support does not need low.
Yeah, you are right
301 - 400 of 637 matches
Mail list logo