Hi Paul
> Hopefully this week or next, I will publish this patch proposal.
Great.
at that time, I will join review the patch with presure :)
- kosaki
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info
e memory. This is one of
> the memoryless nodes fixes. I THINK this is one of the areas that Paul
> and David are investigating.
this is good news for me :)
I'll wait his patch post.
Signed-off-by: KOSAKI Motohiro <[EMAIL PROTECTED]>
---
mm/mempolicy.c | 11 +++
1 file c
his patch post.
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
mm/mempolicy.c | 11 +++
1 file changed, 7 insertions(+), 4 deletions(-)
Index: b/mm/mempolicy.c
===
--- a/mm/mempolicy.c2008-02-02 17:54
Hi Paul
Hopefully this week or next, I will publish this patch proposal.
Great.
at that time, I will join review the patch with presure :)
- kosaki
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to [EMAIL PROTECTED]
More majordomo info at
Hi
The interesting thing is the use of total_vm and not the RSS which is
used as
the basis by the OOM killer. I need to read/understand the code a bit
more.
RSS makes more sense to me as well.
Andrea Arcangeli has patches pending which change this to the RSS.
Hi Lee-san
Here's a patch that addresses the problem w/o requiring change to
numactl or libnuma. It DOES have side affects, discussed in the
description.
Thank you!
but unfortunately, My machine is broken phisically today ;-)
I will test it tommorow or later.
--
To unsubscribe from this
Hi Pavel
> > > As user pages are always in highmem, this should be easy to decide:
> > > only send SIGDANGER when highmem is full. (Yes, there are
> > > inodes/dentries/file descriptors in lowmem, but I doubt apps will
> > > respond to SIGDANGER by closing files).
> >
> > Good point; for a system
Hi Jon
> I looked at this a year or two back, then ran out of time. But the thing
> I wanted to do was have libc's memory allocation routines extended to
> handle these through reservations - the kernel should send a userspace
> notification and then there should be some kind of concept of
Hi Jon
I looked at this a year or two back, then ran out of time. But the thing
I wanted to do was have libc's memory allocation routines extended to
handle these through reservations - the kernel should send a userspace
notification and then there should be some kind of concept of returning
Hi Pavel
As user pages are always in highmem, this should be easy to decide:
only send SIGDANGER when highmem is full. (Yes, there are
inodes/dentries/file descriptors in lowmem, but I doubt apps will
respond to SIGDANGER by closing files).
Good point; for a system with at least
ocess should check has_high_memory file.
but, I am not confident.
Thanks.
- kosaki
Signed-off-by: KOSAKI Motohiro <[EMAIL PROTECTED]>
---
drivers/base/node.c |7 +--
1 file changed, 1 insertion(+), 6 deletions(-)
Index: b/drivers/base/node.c
Hi
I tested numactl on 2.6.24-rc8-mm1.
and I found strange behavior.
test method and result.
$ numactl --interleave=all ls
set_mempolicy: Invalid argument
setting interleave mask: Invalid argument
numactl command download from
Hi
I tested numactl on 2.6.24-rc8-mm1.
and I found strange behavior.
test method and result.
$ numactl --interleave=all ls
set_mempolicy: Invalid argument
setting interleave mask: Invalid argument
numactl command download from
that has_high_memory exposed however CONFIG_HIGHMEM
disabled.
if CONFIG_HIGHMEM disabled, the has_high_memory file show
the same as the has_normal_memory.
may be, userland process should check has_high_memory file.
but, I am not confident.
Thanks.
- kosaki
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED
> I will integrate your fixes with my code when I
> get back from holidays. Then things should work :)
>
> Thank you for your analysis of the problem.
Thank you.
enjoy good vacation :)
-
kosaki
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a
I will integrate your fixes with my code when I
get back from holidays. Then things should work :)
Thank you for your analysis of the problem.
Thank you.
enjoy good vacation :)
-
kosaki
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to
Hi Lee-san
> Rik is currently out on holiday and I've been traveling. Just getting
> back to rebasing to 24-rc8-mm1. Thank you for your efforts in testing
> and tracking down the regressions. I will add your fixes into my tree
> and try them out and let you know. Rik mentioned to me that he
- kosaki
Signed-off-by: KOSAKI Motohiro <[EMAIL PROTECTED]>
---
mm/vmscan.c | 11 ---
1 file changed, 8 insertions(+), 3 deletions(-)
Index: b/mm/vmscan.c
===
--- a/mm/vmscan.c 2008-01-30 15:22:10.00
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
mm/vmscan.c | 11 ---
1 file changed, 8 insertions(+), 3 deletions(-)
Index: b/mm/vmscan.c
===
--- a/mm/vmscan.c 2008-01-30 15:22:10.0 +0900
+++ b/mm/vmscan.c
Hi Lee-san
Rik is currently out on holiday and I've been traveling. Just getting
back to rebasing to 24-rc8-mm1. Thank you for your efforts in testing
and tracking down the regressions. I will add your fixes into my tree
and try them out and let you know. Rik mentioned to me that he has a
eed reintroduce this portion after new page LRU
(aka LRU for used only page).
but now is too early.
I hope this patch series merge to -mm ASAP.
therefore, I hope remove any corner case regression.
Thanks!
- kosaki
Signed-off-by: KOSAKI Motohiro <[EMAIL PROTECTED]>
---
mm/vmscan
> here's a QuickStart:
>
>http://redhat.com/~mingo/x86.git/README
Thanks!
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at
here's a QuickStart:
http://redhat.com/~mingo/x86.git/README
Thanks!
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at
> Add a new fops entry point to allow fasync without BKL. While it's arguably
> unclear this entry point is called often enough for it really matters
> it was still relatively easy to do. And there are far less async users
> in the tree than ioctls so it's likely they can be all converted
>
Hi Mel
> > my patch stack is
> > 2.6.24-rc7 +
> > http://lkml.org/lkml/2007/8/24/220 +
>
> Can you replace this patch with the patch below instead and try again
> please? This is the patch that is actually in git-x86. Out of
> curiousity, have you tried the latest mm branch from git-x86?
to
> 1. if sparce_mem on, build failture
after fix compile error, no panic and bad-page happened both highmem
off and 64G.
I guess discontigmem numa is premature yet ;-)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More
Hi Al
> > the mem_notify patch can realize "just before starting swapping"
> > notification :)
> >
> > to be honest, I don't know fs guys requirement.
> > if lacking feature of fs guys needed, I implement it with presure if
> > you tell me it.
>
> These notifications are really useful, but it may
Hi Mel
>To rule it out, can you also try with the patch below applied please? It
>should only make a difference on sparsemem so if discontigmem is still
>crashing, there is likely another problem. Assuming it crashes, please
>post the full dmesg output with loglevel=8 on the command line. Thanks
> > And from a performance point of view letting applications voluntarily
> > free some memory is better even than starting to swap.
>
> Absolutely.
the mem_notify patch can realize "just before starting swapping" notification :)
to be honest, I don't know fs guys requirement.
if lacking feature
> The commentary on the mem_notify threads claimed that the signal is
> easily provided by setting up the file handle for SIGIO.
BTW:
Of cource, you can receive any signal instead SIGIO by use fcntl(F_SETSIG) :-)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the
The commentary on the mem_notify threads claimed that the signal is
easily provided by setting up the file handle for SIGIO.
BTW:
Of cource, you can receive any signal instead SIGIO by use fcntl(F_SETSIG) :-)
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body
And from a performance point of view letting applications voluntarily
free some memory is better even than starting to swap.
Absolutely.
the mem_notify patch can realize just before starting swapping notification :)
to be honest, I don't know fs guys requirement.
if lacking feature of fs
Hi Mel
To rule it out, can you also try with the patch below applied please? It
should only make a difference on sparsemem so if discontigmem is still
crashing, there is likely another problem. Assuming it crashes, please
post the full dmesg output with loglevel=8 on the command line. Thanks
I
Hi Al
the mem_notify patch can realize just before starting swapping
notification :)
to be honest, I don't know fs guys requirement.
if lacking feature of fs guys needed, I implement it with presure if
you tell me it.
These notifications are really useful, but it may be much wiser
1. if sparce_mem on, build failture
after fix compile error, no panic and bad-page happened both highmem
off and 64G.
I guess discontigmem numa is premature yet ;-)
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to [EMAIL PROTECTED]
More
Hi Daniel
> > +#define PROC_WAKEUP_GUARD (10*HZ)
> [...]
> > + timeout = info->last_proc_notify + PROC_WAKEUP_GUARD;
>
> If only one or a few processes are using the system I think 10 seconds
> is a little long time to wait before they get the notification again.
> Can we decrease this
Hi Daniel
+#define PROC_WAKEUP_GUARD (10*HZ)
[...]
+ timeout = info-last_proc_notify + PROC_WAKEUP_GUARD;
If only one or a few processes are using the system I think 10 seconds
is a little long time to wait before they get the notification again.
Can we decrease this value? Or
Signed-off-by: KOSAKI Motohiro <[EMAIL PROTECTED]>
---
mm/mem_notify.c | 95 +---
1 file changed, 90 insertions(+), 5 deletions(-)
Index: b/mm/mem_notify.c
===
--- a/mm/mem
on X86, ZONE_DMA is very very small.
It is often no used at all.
Unfortunately,
when NR_ACTIVE==0, NR_INACTIVE==0, shrink_zone() try to reclaim 1 page.
because
zone->nr_scan_active +=
(zone_page_state(zone, NR_ACTIVE) >> priority) + 1;
-by: KOSAKI Motohiro <[EMAIL PROTECTED]>
---
include/linux/mem_notify.h |3 +++
mm/page_alloc.c|6 +-
2 files changed, 8 insertions(+), 1 deletion(-)
Index: b/include/linux/mem_notify.h
===
--- a/include
show new member of zone struct by /proc/zoneinfo.
ChangeLog:
v5: change display order to at last.
Signed-off-by: Marcelo Tosatti <[EMAIL PROTECTED]>
Signed-off-by: KOSAKI Motohiro <[EMAIL PROTECTED]>
---
mm/vmstat.c |8 +---
1 file changed, 5 insertions(+),
pressure decrease and stop moves an anonymous page to the inactive
list.
o free pages increase than (pages_high+lowmem_reserve)*2.
ChangeLog:
v5: add out of trouble notify to exit of balance_pgdat().
Signed-off-by: Marcelo Tosatti <[EMAIL PROTECTED]>
Signed-off-by: KOSAKI Motohiro &
s.revents = 0;
err = poll(, 1, -1); // wake up at low memory
...
Signed-off-by: Marcelo Tosatti <[EMAIL PROTECTED]>
Signed-off-by: KOSAKI Motohiro <[EMAIL PROTECTED]>
---
Documentation/devices.txt |1
drivers/char/mem.c |6 ++
include/
introduce new API wake_up_locked_nr() and wake_up_locked_all().
it it similar as wake_up_nr() and wake_up_all(), but it doesn't lock.
Signed-off-by: Marcelo Tosatti <[EMAIL PROTECTED]>
Signed-off-by: KOSAKI Motohiro <[EMAIL PROTECTED]>
---
include/linux/wait.h |7 +--
ke
, _wait_queue, wait);
if (data_exist)
return POLLIN | POLLRDNORM;
return 0;
}
Signed-off-by: Marcelo Tosatti <[EMAIL PROTECTED]>
Signed-off-by: KOSAKI Motohiro <[EMAIL PROTECTED]>
---
fs/eventpoll.c |7 +--
fs/select.c |9 ++---
i
[kosaki]
http://marc.info/?l=linux-mm=120035840523718=2
Changelog
-
v4 -> v5 (by KOSAKI Motohiro)
o rebase to 2.6.24-rc8-mm1
o change display order of /proc/zoneinfo
o ignore very small zone
o support fcntl(F_SETFL, FAS
Hi
> To rule it out, can you also try with the patch below applied please? It
> should only make a difference on sparsemem so if discontigmem is still
> crashing, there is likely another problem. Assuming it crashes,
Aaah, sorry.
I can't test again until next week.
I repost at that time...
>
Hi
To rule it out, can you also try with the patch below applied please? It
should only make a difference on sparsemem so if discontigmem is still
crashing, there is likely another problem. Assuming it crashes,
Aaah, sorry.
I can't test again until next week.
I repost at that time...
notification v4 [kosaki]
http://marc.info/?l=linux-mmm=120035840523718w=2
Changelog
-
v4 - v5 (by KOSAKI Motohiro)
o rebase to 2.6.24-rc8-mm1
o change display order of /proc/zoneinfo
o ignore very small zone
o support fcntl(F_SETFL
)
{
poll_wait_exclusive(file, kosaki_wait_queue, wait);
if (data_exist)
return POLLIN | POLLRDNORM;
return 0;
}
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
fs/eventpoll.c |7 +--
fs/select.c |9
introduce new API wake_up_locked_nr() and wake_up_locked_all().
it it similar as wake_up_nr() and wake_up_all(), but it doesn't lock.
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
include/linux/wait.h |7 +--
kernel/sched.c
;
pollfds.revents = 0;
err = poll(pollfds, 1, -1); // wake up at low memory
...
/usage example
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
Documentation/devices.txt |1
drivers/char/mem.c |6 ++
include/linux
pressure decrease and stop moves an anonymous page to the inactive
list.
o free pages increase than (pages_high+lowmem_reserve)*2.
ChangeLog:
v5: add out of trouble notify to exit of balance_pgdat().
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Signed-off-by: KOSAKI Motohiro [EMAIL
show new member of zone struct by /proc/zoneinfo.
ChangeLog:
v5: change display order to at last.
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
mm/vmstat.c |8 +---
1 file changed, 5 insertions(+), 3 deletions(-)
Index
on X86, ZONE_DMA is very very small.
It is often no used at all.
Unfortunately,
when NR_ACTIVE==0, NR_INACTIVE==0, shrink_zone() try to reclaim 1 page.
because
zone-nr_scan_active +=
(zone_page_state(zone, NR_ACTIVE) priority) + 1;
-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
include/linux/mem_notify.h |3 +++
mm/page_alloc.c|6 +-
2 files changed, 8 insertions(+), 1 deletion(-)
Index: b/include/linux/mem_notify.h
===
--- a/include/linux
v5: new
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
mm/mem_notify.c | 95 +---
1 file changed, 90 insertions(+), 5 deletions(-)
Index: b/mm/mem_notify.c
Hi mel
> Hi
>
> > A fix[1] was merged to the x86.git tree that allowed NUMA kernels to boot
> > on normal x86 machines (and not just NUMA-Q, Summit etc.). I took a look
> > at the restrictions on setting NUMA on x86 to see if they could be lifted.
>
> Interesting!
>
> I will test tomorrow.
Hi mel
Hi
A fix[1] was merged to the x86.git tree that allowed NUMA kernels to boot
on normal x86 machines (and not just NUMA-Q, Summit etc.). I took a look
at the restrictions on setting NUMA on x86 to see if they could be lifted.
Interesting!
I will test tomorrow.
Hmm...
It
Hi
> +static void __sched
> +account_global_scheduler_latency(struct task_struct *tsk, int usecs)
> +{
> + int i;
> + int firstnonnull = MAXLR + 1;
> +
> + if (!tsk->latency_reason.reason)
> + return;
> +
> + /* skip kernel threads for now */
> + if (!tsk->mm)
> +
Hi
+static void __sched
+account_global_scheduler_latency(struct task_struct *tsk, int usecs)
+{
+ int i;
+ int firstnonnull = MAXLR + 1;
+
+ if (!tsk-latency_reason.reason)
+ return;
+
+ /* skip kernel threads for now */
+ if (!tsk-mm)
+
Hi
> The Intel Open Source Technology Center is pleased to announce the
> release of version 0.1 of LatencyTOP, a tool for developers to visualize
> system latencies.
Interesting.
at least, I will use for fixed page lock contension :)
if possible, I want some /proc/lock_stat feature.
i.e.
Hi
> A fix[1] was merged to the x86.git tree that allowed NUMA kernels to boot
> on normal x86 machines (and not just NUMA-Q, Summit etc.). I took a look
> at the restrictions on setting NUMA on x86 to see if they could be lifted.
Interesting!
I will test tomorrow.
I think this patch become
Hi
The Intel Open Source Technology Center is pleased to announce the
release of version 0.1 of LatencyTOP, a tool for developers to visualize
system latencies.
Interesting.
at least, I will use for fixed page lock contension :)
if possible, I want some /proc/lock_stat feature.
i.e.
Hi
A fix[1] was merged to the x86.git tree that allowed NUMA kernels to boot
on normal x86 machines (and not just NUMA-Q, Summit etc.). I took a look
at the restrictions on setting NUMA on x86 to see if they could be lifted.
Interesting!
I will test tomorrow.
I think this patch become easy
Hi Andrew,
> > > on X86, ZONE_DMA is very very small.
> > > It is often no used at all.
> >
> > In that case page-reclaim is supposed to set all_unreclaimable and
> > basically ignores the zone altogether until it looks like something might
> > have changed.
> >
> > Is that code not working?
Hi!
> > 1. I doubt ZONE_DMA, please shipment ignore zone_dma patch(below).
>
> Your patch above solves the problem I had with early notification.
really!?
I am really happy!!
Thanks you.
- kosaki
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a
Hi!
1. I doubt ZONE_DMA, please shipment ignore zone_dma patch(below).
Your patch above solves the problem I had with early notification.
really!?
I am really happy!!
Thanks you.
- kosaki
--
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message
Hi Andrew,
on X86, ZONE_DMA is very very small.
It is often no used at all.
In that case page-reclaim is supposed to set all_unreclaimable and
basically ignores the zone altogether until it looks like something might
have changed.
Is that code not working? (quite possible).
Hi Andrew
> > on X86, ZONE_DMA is very very small.
> > It is often no used at all.
>
> In that case page-reclaim is supposed to set all_unreclaimable and
> basically ignores the zone altogether until it looks like something might
> have changed.
>
> Is that code not working? (quite possible).
this patch against: 2.6.24-rc6-mm1
Signed-off-by: KOSAKI Motohiro <[EMAIL PROTECTED]>
---
mm/vmscan.c | 21 -
1 file changed, 16 insertions(+), 5 deletions(-)
Index: b/mm/vmscan.c
===
--- a/mm/vmscan.c
Hi
> > > Should all this cache usage not be counted towards the
> > > 'Cached' entry in meminfo rather then getting counted as part of used
> > > ram.
> >
> > Cached is only the page-cache, not all the other caches we have..
> > This someones confuses people, but one gets used to it. slabinfo
Hi
Should all this cache usage not be counted towards the
'Cached' entry in meminfo rather then getting counted as part of used
ram.
Cached is only the page-cache, not all the other caches we have..
This someones confuses people, but one gets used to it. slabinfo allows
one to
against: 2.6.24-rc6-mm1
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
mm/vmscan.c | 21 -
1 file changed, 16 insertions(+), 5 deletions(-)
Index: b/mm/vmscan.c
===
--- a/mm/vmscan.c 2008-01-18 14:18
Hi Andrew
on X86, ZONE_DMA is very very small.
It is often no used at all.
In that case page-reclaim is supposed to set all_unreclaimable and
basically ignores the zone altogether until it looks like something might
have changed.
Is that code not working? (quite possible).
please
Hi
> If that is indeed the source of your change_bit function then there is
> a problem. However in my kernel tree there is a LOCK_PREFIX in the
> definition of the atomic version. I don't have your exact source tree
> handy, but on a local RHEL4 system, the LOCK_PREFIX is still there:
>
>
challenge.
thanks.
- kosaki
Signed-off-by: KOSAKI Motohiro <[EMAIL PROTECTED]>
---
include/linux/mem_notify.h |3 +++
mm/page_alloc.c|6 +-
2 files changed, 8 insertions(+), 1 deletion(-)
Index: linux-2.6.24-rc6-mm1-
Hi
> > One thing you could also try is to pass MAP_POPULATE to mmap so that the
> > page tables are filled in at the time of the mmap, avoiding a lot of
> > page faults later.
> >
>
> OK, I will test your idea and report about tomorrow.
> but I don't think page fault is major performance
Hi
> > I'd read mem_notify as "tell me when new memory is unplugged" or
> > something. /dev/oom_notify? Plus, /dev/ names usually do not have "_"
> > in them.
>
> I don't think we should use oom in the name, since the notification is
> sent long before oom.
OK, I don't change name.
Of cource, I
Hi
I'd read mem_notify as tell me when new memory is unplugged or
something. /dev/oom_notify? Plus, /dev/ names usually do not have _
in them.
I don't think we should use oom in the name, since the notification is
sent long before oom.
OK, I don't change name.
Of cource, I will change
Hi
One thing you could also try is to pass MAP_POPULATE to mmap so that the
page tables are filled in at the time of the mmap, avoiding a lot of
page faults later.
OK, I will test your idea and report about tomorrow.
but I don't think page fault is major performance impact.
I got
-by: KOSAKI Motohiro [EMAIL PROTECTED]
---
include/linux/mem_notify.h |3 +++
mm/page_alloc.c|6 +-
2 files changed, 8 insertions(+), 1 deletion(-)
Index: linux-2.6.24-rc6-mm1-memnotify/include/linux/mem_notify.h
Hi
If that is indeed the source of your change_bit function then there is
a problem. However in my kernel tree there is a LOCK_PREFIX in the
definition of the atomic version. I don't have your exact source tree
handy, but on a local RHEL4 system, the LOCK_PREFIX is still there:
static
Hi Clifford,
> +static inline char *task_rlim(struct task_struct *p, char *buffer)
> +{
> + unsigned long flags;
> + struct rlimit rlim[RLIM_NLIMITS];
> + int i;
> +
> + rcu_read_lock();
> + if (lock_task_sighand(p, )) {
> + for (i=0; i +
Hi Rik
I tested new hackbench on rvr split LRU patch.
new hackbench URL is
http://people.redhat.com/mingo/cfs-scheduler/tools/hackbench.c
method of test
(1) $ ./hackbench 150 process 1000
(2) # sync; echo 3 > /proc/sys/vm/drop_caches
$ dd if=tmp10G of=/dev/null
$ ./hackbench 150
Hi Alan
> > > It also appears there is no way to wait for memory shortages (processes
> > > that can free memory easily) only for memory to start appearing.
> >
> > poll() with never timeout don't fill your requirement?
> > to be honest, maybe I don't understand your afraid yet. sorry.
>
> My
Hi Paulo
> One thing you could also try is to pass MAP_POPULATE to mmap so that the
> page tables are filled in at the time of the mmap, avoiding a lot of
> page faults later.
>
> Just my 2 cents,
OK, I will test your idea and report about tomorrow.
but I don't think page fault is major
Hi Pavel
> > err = poll(, 1, -1); // wake up at low memory
> >
> > ...
> >
>
> Nice, this is really needed for openmoko, zaurus, etc
>
> But this changelog needs to go into Documentation/...
>
> ...and /dev/mem_notify is really a bad name. /dev/memory_low?
> /dev/oom?
thank
Hi Daniel
> > > The notification fires after only ~100 MB allocated, i.e., when page
> > > reclaim is beginning to nag from page cache. Isn't this a bit early?
> > > Repeating the test with swap enabled results in a notification after
> > > ~600 MB allocated, which is more reasonable and just
Hi Alan
thank you for kindfull explain.
> > > > the core of this patch series.
> > > > add /dev/mem_notify device for notification low memory to user process.
> > >
> > > As you only wake one process how would you use this API from processes
> > > which want to monitor and can free memory under
> > the core of this patch series.
> > add /dev/mem_notify device for notification low memory to user process.
>
> As you only wake one process how would you use this API from processes
> which want to monitor and can free memory under load. Also what fairness
> guarantees are there...
Sorry, I
Hi alan
> > show new member of zone struct by /proc/zoneinfo.
> >
> > Signed-off-by: Marcelo Tosatti <[EMAIL PROTECTED]>
> > Signed-off-by: KOSAKI Motohiro <[EMAIL PROTECTED]>
>
> Minor NAK - Please put new fields at the end - it makes it less likely to
Hi
sound good for me.
a few question please.
> + for (i=0; i + if (rlim_names[i])
> + buffer += sprintf(buffer, "Rlim%s:\t", rlim_names[i]);
> + else
> + buffer += sprintf(buffer, "Rlim%d:\t", i);
this else is really necessary?
Hi Peter,
> > > While being able to deal with used-once mappings in page reclaim
> > > could be a good idea, this would require us to be able to determine
> > > the difference between a page that was accessed once since it was
> > > faulted in and a page that got accessed several times.
> >
> >
Hi Peter,
While being able to deal with used-once mappings in page reclaim
could be a good idea, this would require us to be able to determine
the difference between a page that was accessed once since it was
faulted in and a page that got accessed several times.
it makes sense
Hi
sound good for me.
a few question please.
+ for (i=0; iRLIM_NLIMITS; i++) {
+ if (rlim_names[i])
+ buffer += sprintf(buffer, Rlim%s:\t, rlim_names[i]);
+ else
+ buffer += sprintf(buffer, Rlim%d:\t, i);
this else is
Hi alan
show new member of zone struct by /proc/zoneinfo.
Signed-off-by: Marcelo Tosatti [EMAIL PROTECTED]
Signed-off-by: KOSAKI Motohiro [EMAIL PROTECTED]
Minor NAK - Please put new fields at the end - it makes it less likely to
break badly written tools.
Oh I see.
I applied your
the core of this patch series.
add /dev/mem_notify device for notification low memory to user process.
As you only wake one process how would you use this API from processes
which want to monitor and can free memory under load. Also what fairness
guarantees are there...
Sorry, I don't
Hi Alan
thank you for kindfull explain.
the core of this patch series.
add /dev/mem_notify device for notification low memory to user process.
As you only wake one process how would you use this API from processes
which want to monitor and can free memory under load. Also what
Hi Daniel
The notification fires after only ~100 MB allocated, i.e., when page
reclaim is beginning to nag from page cache. Isn't this a bit early?
Repeating the test with swap enabled results in a notification after
~600 MB allocated, which is more reasonable and just before the
801 - 900 of 949 matches
Mail list logo