From: SeongJae Park
PG_idle and PG_young allows the two PTE Accessed bit users,
IDLE_PAGE_TRACKING and the reclaim logic concurrently work while don't
interfere each other. That is, when they need to clear the Accessed
bit, they set PG_young and PG_idle to represent the previous state o
From: SeongJae Park
Even somehow the initial monitoring target regions are well constructed
to fulfill the assumption (pages in same region have similar access
frequencies), the data access pattern can be dynamically changed. This
will result in low monitoring quality. To keep the assumption
From: SeongJae Park
This commit introduces a reference implementation of the address space
specific low level primitives for the virtual address space, so that
users of DAMON can easily monitor the data accesses on virtual address
spaces of specific processes by simply configuring the
From: SeongJae Park
Concurrent Idle Page Tracking users can interfere each other because the
interface doesn't provide a central rule for synchronization between the
users. Users could implement their own synchronization rule, but even
in that case, applications developed by different
From: SeongJae Park
The monitoring target address range can be dynamically changed. For
example, virtual memory could be dynamically mapped and unmapped.
Physical memory could be hot-plugged.
As the changes could be quite frequent in some cases, DAMON checks the
dynamic memory mapping changes
From: SeongJae Park
DAMON is a data access monitoring framework for the Linux kernel. The
core mechanisms of DAMON make it
- accurate (the monitoring output is useful enough for DRAM level
performance-centric memory management; It might be inappropriate for
CPU Cache levels, though
From: SeongJae Park
DAMON separates its monitoring target address space independent high
level logics from the target space dependent low level primitives for
flexible support of various address spaces.
This commit implements DAMON's target address space independent high
level logics for
From: SeongJae Park
Changes from Previous Version (v20)
===
- s/snprintf()/scnprintf() (Marco Elver)
- Support multiple contexts for user space users (Shakeel Butt)
- Export pid of monitoring thread to user space (Shakeel Butt)
- Let coexistable with Idle Pages
n in < 1 sec.
>
> This is done with a one-line change that simply reduces the number of
> iterations of several tests, from 256, to 10.
Could this result in reduced test capacity? If so, how about making the number
easily tweakable?
Thanks,
SeongJae Park
> Thanks to Ralph Campb
On Tue, 29 Sep 2020 15:38:14 +0200 Marco Elver wrote:
> Add entry for KFENCE maintainers.
>
> Reviewed-by: Dmitry Vyukov
> Co-developed-by: Alexander Potapenko
> Signed-off-by: Alexander Potapenko
> Signed-off-by: Marco Elver
Reviewed-by: SeongJae Park
Thanks,
SeongJae Park
From: SeongJae Park
DAMON's reference 'primitives' internally use 'PG_Idle' flag. Because
the flag is also used by Idle Page Tracking but there was no way to
synchronize with it, the 'primitives' were configured to be exclusive
with Idle Page Tracking before.
From: SeongJae Park
Concurrent Idle Page Tracking users can interfere each other because the
interface doesn't provide a central rule for synchronization between the
users. Users could implement their own synchronization rule, but even
in that case, applications developed by different
From: SeongJae Park
DAMON passes the monitoring results to user space via two ways: 1) a
tracepoint and 2) it's recording feature. The recording feature is for
the users who want simplest use.
However, as the feature is for the user space only while the core is
fundamentally a framewor
From: SeongJae Park
DAMON-based operation schemes feature is implemented inside DAMON
'core'. Though the access pattern based schemes target region tracking
part makes sense to reside in the 'core', applying the scheme action
would better to be reside in the 'primit
From: SeongJae Park
NOTE: This is an RFC for future change of DAMON patchsets[1,2,3], which is not
merged in the mainline yet. The aim of this RFC is to show how the patchset
would be changed in the next version. So, if you have some interest in this
RFC, please consider reviewing the DAMON
On Mon, 31 Aug 2020 13:22:35 +0200 SeongJae Park wrote:
> On Thu, 20 Aug 2020 09:27:38 +0200 SeongJae Park wrote:
>
> > On Mon, 17 Aug 2020 12:51:22 +0200 SeongJae Park wrote:
> >
> > > From: SeongJae Park
> > >
[...]
> > > Introduction
&g
hetic
> benchmarks (sysbench I/O workloads) that a kernel compiled with KFENCE
> is performance-neutral compared to the non-KFENCE baseline.
>
> For more details, see Documentation/dev-tools/kfence.rst (added later in
> the series).
>
> Reviewed-by: Dmitry Vyukov
> Co-develope
On Thu, 24 Sep 2020 12:13:44 +0200 "Roger Pau Monné"
wrote:
> On Wed, Sep 23, 2020 at 04:09:30PM -0400, Konrad Rzeszutek Wilk wrote:
> > On Tue, Sep 22, 2020 at 09:01:25AM +0200, SeongJae Park wrote:
> > > From: SeongJae Park
> > >
> > > Persi
On Wed, 23 Sep 2020 10:04:57 -0700 Shakeel Butt wrote:
> On Mon, Aug 17, 2020 at 3:52 AM SeongJae Park wrote:
> >
> > From: SeongJae Park
> >
> > Changes from Previous Version
> > =
> >
> > - Place 'CREATE_TRACE_P
On Wed, 23 Sep 2020 16:09:30 -0400 Konrad Rzeszutek Wilk
wrote:
> On Tue, Sep 22, 2020 at 09:01:25AM +0200, SeongJae Park wrote:
> > From: SeongJae Park
> >
> > Persistent grants feature provides high scalability. On some small
> > systems, however, it could incu
From: SeongJae Park
The flexible interface of Idle Page Tracking can allow concurrent users
interfere each other. They could implement their own use user space
synchronization, but applications developed by different users would not
know how to synchronize with other application. To help this
From: SeongJae Park
Persistent grants feature provides high scalability. On some small
systems, however, it could incur data copy overheads[1] and thus it is
required to be disabled. It can be disabled from blkback side using a
module parameter, 'feature_persistent'. But, it is
From: SeongJae Park
Commit 14e710fe7897 ("xen-blkfront: rename indirect descriptor
parameter") changed the name of the module parameter for the maximum
amount of segments in indirect requests but missed updating the
document. This commit updates the document.
Signed-off-by: Seo
From: SeongJae Park
Persistent grants feature provides high scalability. On some small
systems, however, it could incur data copy overheads[1] and thus it is
required to be disabled. But, there is no option to disable it. For
the reason, this commit adds a module parameter for disabling of
From: SeongJae Park
Persistent grants feature provides high scalability. On some small
systems, however, it could incur data copy overheads[1] and thus it is
required to be disabled. But, there is no option to disable it. For
the reason, this commit adds module parameters for disabling of the
On Tue, 22 Sep 2020 16:44:25 +0200 "Roger Pau Monné"
wrote:
> On Tue, Sep 22, 2020 at 04:27:39PM +0200, Jürgen Groß wrote:
> > On 22.09.20 16:15, SeongJae Park wrote:
> > > From: SeongJae Park
> > >
> > > Commit 14e710fe7897 ("xen-blkfront: r
On Tue, 22 Sep 2020 16:45:56 +0200 "Roger Pau Monné"
wrote:
> On Tue, Sep 22, 2020 at 04:15:46PM +0200, SeongJae Park wrote:
> > From: SeongJae Park
> >
> > Persistent grants feature provides high scalability. On some small
> > systems, however, it could
On Tue, 22 Sep 2020 16:27:03 +0200 "Jürgen Groß" wrote:
> On 22.09.20 16:15, SeongJae Park wrote:
> > From: SeongJae Park
> >
> > Persistent grants feature provides high scalability. On some small
> > systems, however, it could incur data copy overheads
On Tue, 22 Sep 2020 16:25:57 +0200 "Jürgen Groß" wrote:
> On 22.09.20 16:15, SeongJae Park wrote:
> > From: SeongJae Park
> >
> > Persistent grants feature provides high scalability. On some small
> > systems, however, it could incur data copy overheads
From: SeongJae Park
Persistent grants feature provides high scalability. On some small
systems, however, it could incur data copy overheads[1] and thus it is
required to be disabled. But, there is no option to disable it. For
the reason, this commit adds module parameters for disabling of the
From: SeongJae Park
Persistent grants feature provides high scalability. On some small
systems, however, it could incur data copy overheads[1] and thus it is
required to be disabled. But, there is no option to disable it. For
the reason, this commit adds a module parameter for disabling of
From: SeongJae Park
Commit 14e710fe7897 ("xen-blkfront: rename indirect descriptor
parameter") changed the name of the module parameter for the maximum
amount of segments in indirect requests but missed updating the
document. This commit updates the document.
Signed-off-by: Seo
From: SeongJae Park
Persistent grants feature provides high scalability. On some small
systems, however, it could incur data copy overheads[1] and thus it is
required to be disabled. It can be disabled from blkback side using a
module parameter, 'feature_persistent'. But, it is
On Tue, 22 Sep 2020 14:11:32 +0200 "Jürgen Groß" wrote:
> On 22.09.20 12:52, SeongJae Park wrote:
> > From: SeongJae Park
> >
> > Persistent grants feature provides high scalability. On some small
> > systems, however, it could incur data copy overheads
On Tue, 22 Sep 2020 13:35:30 +0200 "Jürgen Groß" wrote:
> On 22.09.20 13:26, SeongJae Park wrote:
> > On Tue, 22 Sep 2020 13:12:59 +0200 "Roger Pau Monné"
> > wrote:
> >
> >> On Tue, Sep 22, 2020 at 12:52:07PM +0200, SeongJae Park wrote:
On Tue, 22 Sep 2020 13:35:11 +0200 "Roger Pau Monné"
wrote:
> On Tue, Sep 22, 2020 at 01:26:38PM +0200, SeongJae Park wrote:
> > On Tue, 22 Sep 2020 13:12:59 +0200 "Roger Pau Monné"
> > wrote:
> >
> > > On Tue, Sep 22, 2020 at 12:52:07PM
On Tue, 22 Sep 2020 13:12:59 +0200 "Roger Pau Monné"
wrote:
> On Tue, Sep 22, 2020 at 12:52:07PM +0200, SeongJae Park wrote:
> > From: SeongJae Park
> >
> > Persistent grants feature provides high scalability. On some small
> > systems, however, it could
From: SeongJae Park
Commit 14e710fe7897 ("xen-blkfront: rename indirect descriptor
parameter") changed the name of the module parameter for the maximum
amount of segments in indirect requests but missed updating the
document. This commit updates the document.
Signed-off-by: Seo
From: SeongJae Park
Persistent grants feature provides high scalability. On some small
systems, however, it could incur data copy overheads[1] and thus it is
required to be disabled. It can be disabled from blkback side using a
module parameter, 'feature_persistent'. But, it is
From: SeongJae Park
Persistent grants feature provides high scalability. On some small
systems, however, it could incur data copy overheads[1] and thus it is
required to be disabled. But, there is no option to disable it. For
the reason, this commit adds a module parameter for disabling of
From: SeongJae Park
Persistent grants feature provides high scalability. On some small
systems, however, it could incur data copy overheads[1] and thus it is
required to be disabled. But, there is no option to disable it. For
the reason, this commit adds module parameters for disabling of the
On Tue, 22 Sep 2020 09:32:02 +0200 "Roger Pau Monné"
wrote:
> On Tue, Sep 22, 2020 at 09:01:25AM +0200, SeongJae Park wrote:
> > From: SeongJae Park
> >
> > Persistent grants feature provides high scalability. On some small
> > systems, however, it could
On Tue, 22 Sep 2020 09:18:05 +0200 "Jürgen Groß" wrote:
> On 22.09.20 09:01, SeongJae Park wrote:
> > From: SeongJae Park
> >
> > Persistent grants feature provides high scalability. On some small
> > systems, however, it could incur data copy overhead
From: SeongJae Park
Persistent grants feature provides high scalability. On some small
systems, however, it could incur data copy overhead[1] and thus it is
required to be disabled. But, there is no option to disable it. For
the reason, this commit adds a module parameter for disabling of the
On Wed, 16 Sep 2020 09:11:18 -0700 Shakeel Butt wrote:
> On Tue, Sep 15, 2020 at 11:03 AM SeongJae Park wrote:
> >
> > From: SeongJae Park
> >
> > DAMON allows the programming interface users to run monitoring with
> > multiple contexts. This could be usefu
/report.c b/mm/kfence/report.c
> new file mode 100644
> index ..8c28200e7433
> --- /dev/null
> +++ b/mm/kfence/report.c
> @@ -0,0 +1,201 @@
> +// SPDX-License-Identifier: GPL-2.0
[...]
> +/* Get the number of stack entries to skip get out of MM internals. */
> +static int get_stack_skipnr(const unsigned long stack_entries[], int
> num_entries,
> + enum kfence_error_type type)
> +{
> + char buf[64];
> + int skipnr, fallback = 0;
> +
> + for (skipnr = 0; skipnr < num_entries; skipnr++) {
> + int len = scnprintf(buf, sizeof(buf), "%ps", (void
> *)stack_entries[skipnr]);
> +
> + /* Depending on error type, find different stack entries. */
> + switch (type) {
> + case KFENCE_ERROR_UAF:
> + case KFENCE_ERROR_OOB:
> + case KFENCE_ERROR_INVALID:
> + if (!strncmp(buf, KFENCE_SKIP_ARCH_FAULT_HANDLER, len))
Seems KFENCE_SKIP_ARCH_FAULT_HANDLER not defined yet?
> + goto found;
> + break;
[...]
Thanks,
SeongJae Park
On Tue, 15 Sep 2020 16:14:49 +0200 Marco Elver wrote:
> On Tue, Sep 15, 2020 at 03:57PM +0200, SeongJae Park wrote:
> [...]
> >
> > So interesting feature! I left some tirvial comments below.
>
> Thank you!
[...]
> > > +
> > > + /* Only call with a p
From: SeongJae Park
NOTE: This is only an RFC for future features of DAMON patchset[1], which is
not merged in the mainline yet. The aim of this RFC is to show how DAMON would
be evolved once it is merged in. So, if you have some interest in this RFC,
please consider reviewing the DAMON
From: SeongJae Park
Seems lore.kernel.org missed original posting of this mail. Resending.
NOTE: This is only an RFC for future features of DAMON patchset[1], which is
not merged in the mainline yet. The aim of this RFC is to show how DAMON would
be evolved once it is merged in. So, if you
From: SeongJae Park
While multiple kdamond threads can run, it is hard to distinguish each
thread as all kdamond threads has same name, 'kdamond'. This commit
puts more information including if it is spawned from the user context
(via the debugfs interface) and for what context it
From: SeongJae Park
DAMON allows the programming interface users to run monitoring with
multiple contexts. This could be useful in some cases. For example, if
someone want to do highly accurate monitoring and lots of CPUs are
available, splitting the monitoring target regions into multiple
> On Wed, Sep 9, 2020 at 11:37 PM SeongJae Park wrote:
> >
> > On 2020-09-09T14:57:52-07:00 Shakeel Butt wrote:
> >
> > > Introduce an memcg interface to trigger memory reclaim on a memory cgroup.
> > >
> > > Use cases:
> > > --
if (signal_pending(current))
> + break;
> +
> + reclaimed = try_to_free_mem_cgroup_pages(memcg,
> + nr_to_reclaim - nr_reclaimed,
> + GFP_KERNEL, true);
> +
> + if (!reclaimed && !nr_retries--)
> + break;
Shouldn't the if condition use '||' instead of '&&'? I think it could be
easier to read if we put the 'nr_retires' condition in the while condition as
below (just my personal preference, though).
while (nr_reclaimed < nr_to_reclaim && nr_retires--)
Thanks,
SeongJae Park
This is just a reminder ping to let you know I'm still waiting more reviews!
Any comments will be appreciated!
Thanks,
SeongJae Park
On Mon, 31 Aug 2020 12:47:20 +0200 SeongJae Park wrote:
> From: SeongJae Park
>
> Changes from Previous Version
> =
>
> - Add missed 'put_page()' calls
> - Support unmapped LRU pages
Forgot mentioning the people who suggested the ch
On Mon, 31 Aug 2020 20:08:44 +0200 Marco Elver wrote:
> On Mon, Aug 31, 2020 at 12:47PM +0200, SeongJae Park wrote:
> [...]
> > diff --git a/mm/damon.c b/mm/damon.c
> > index 7e3c8c82a010..9815d22fc4de 100644
> > --- a/mm/damon.c
> > +++ b/mm/damon.c
> > @@
On Thu, 20 Aug 2020 09:27:38 +0200 SeongJae Park wrote:
> On Mon, 17 Aug 2020 12:51:22 +0200 SeongJae Park wrote:
>
> > From: SeongJae Park
> >
> > Changes from Previous Version
> > =
> >
> > - Place 'CREATE_TR
From: SeongJae Park
This commit updates the DAMON documents for the physical memory
monitoring support.
Signed-off-by: SeongJae Park
---
Documentation/admin-guide/mm/damon/usage.rst | 42
Documentation/vm/damon/design.rst| 29 +-
Documentation/vm
From: SeongJae Park
This commit makes the debugfs interface to support the physical memory
monitoring, in addition to the virtual memory monitoring.
Users can do the physical memory monitoring by writing a special
keyword, 'paddr\n' to the 'pids' debugfs file. Then,
From: SeongJae Park
This commit updates the DAMON user space tool (damo-record) for NUMA
specific physical memory monitoring. With this change, users can
monitor accesses to physical memory of specific NUMA node.
Signed-off-by: SeongJae Park
---
tools/damon/_paddr_layout.py | 147
From: SeongJae Park
This commit allows users to record the data accesses on physical memory
address space by passing 'paddr' as target to 'damo-record'. If the
init regions are given, the regions will be monitored. Else, it will
monitor biggest conitguous 'System RA
From: SeongJae Park
This commit adds description of the 'init_regions' feature in the DAMON
usage document.
Signed-off-by: SeongJae Park
---
Documentation/admin-guide/mm/damon/usage.rst | 41 +++-
1 file changed, 39 insertions(+), 2 deletions(-)
diff --git a/Doc
From: SeongJae Park
This commit implements the four callbacks (->init_target_regions,
->update_target_regions, ->prepare_access_check, and ->check_accesses)
for the basic access monitoring of the physical memory address space.
By setting the callback pointers to point those, user
From: SeongJae Park
Now the regions can be explicitly set as users want. Therefore checking
the number of gaps doesn't make sense. Remove the condition.
Signed-off-by: SeongJae Park
---
tools/testing/selftests/damon/_chk_record.py | 6 --
1 file changed, 6 deletions(-)
diff --
From: SeongJae Park
Some users would want to monitor only a part of the entire virtual
memory address space. The '->init_target_regions' callback is therefore
provided, but only programming interface can use it.
For the reason, this commit introduces a new debugfs file,
'in
From: SeongJae Park
This commit adds more test cases for the new feature, 'init_regions'.
Signed-off-by: SeongJae Park
Reviewed-by: Brendan Higgins
---
mm/damon-test.h | 53 +
1 file changed, 53 insertions(+)
diff --git a/mm/damon-t
From: SeongJae Park
This commit updates the damon user space tool to support the initial
monitoring target regions specification.
Signed-off-by: SeongJae Park
---
tools/damon/_damon.py | 39 +++
tools/damon/record.py | 12 +++-
tools/damon
From: SeongJae Park
Changes from Previous Version
=
- Add missed 'put_page()' calls
- Support unmapped LRU pages
Introduction
NOTE: This is only an RFC for future features of DAMON patchset[1], which is
not merged in the mainline yet. The a
From: SeongJae Park
Translate this commit to Korean:
3e79f082ebfc ("libnvdimm/nvdimm/flush: Allow architecture to override the
flush barrier")
Signed-off-by: SeongJae Park
Reviewed-by: Yunjae Lee
---
.../translations/ko_KR/memory-barriers.txt | 13 +
1 fi
Ah, why I always see the typo only after posting it... The title should start
with 'docs/', not 'dics/'. Sorry, I will send a fixed patch as reply to this.
If you want full v3 patchset, just let me know, please.
Thanks,
SeongJae Park
On Sat, 29 Aug 2020 10:26:07 +0200
From: SeongJae Park
Commit 985098a05eee ("docs: fix references for DMA*.txt files") missed
fixing memory-barriers.txt file. This commit applies the change to the
file.
Signed-off-by: SeongJae Park
---
Documentation/memory-barriers.txt | 8
1 file changed, 4 insert
From: SeongJae Park
Translate this commit to Korean:
3e79f082ebfc ("libnvdimm/nvdimm/flush: Allow architecture to override the
flush barrier")
Signed-off-by: SeongJae Park
Reviewed-by: Yunjae Lee
---
.../translations/ko_KR/memory-barriers.txt | 13 +
1 fi
From: SeongJae Park
Translate this commit to Korean:
a897b13d1b77 ("docs/memory-barriers.txt: Remove remaining references to
mmiowb()")
Signed-off-by: SeongJae Park
Reviewed-by: Yunjae Lee
---
.../translations/ko_KR/memory-barriers.txt| 19 +++
1 file
From: SeongJae Park
This patchset applies missed changes that should land in the
memory-barriers.txt and its Korean translation.
The patches are based on v5.9-rc2.
Changes from v1
- Fix mismatch between author and Signed-off-by:
SeongJae Park (3):
docs/memory-barriers.txt: Fix references
From: SeongJae Park
The sentence regarding version numbers of '-stable' kernels is quite
ambiguous. This commit makes the sentence more clear and fix
inconsistent uses of the terms for 'version'.
Signed-off-by: SeongJae Park
---
Documentation/translations/ko_KR/howto.rs
From: SeongJae Park
This patchset syncs howto.rst for recent changes to the original doc and
fix some trivial nits in the translation itself.
The patches are based on v5.9-rc2.
Changes from v1
- Fix mismatch between author and Signed-off-by:
SeongJae Park (2):
Documentation/kokr: bring
From: SeongJae Park
Translate this commit to Korean:
fb0e0ffe7fc8 ("Documentation: bring process docs up to date")
Signed-off-by: SeongJae Park
---
Documentation/translations/ko_KR/howto.rst | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/Documentation/tr
Oops, I forgot adding 'From:' line in the body. This will make author and
signed-off-by mismatch. Sorry, I will send v2 soon.
Thanks,
SeongJae Park
On Sat, 29 Aug 2020 10:08:13 +0200 SeongJae Park wrote:
> This patchset applies missed changes that should land in the
> mem
Oops, I forgot adding 'From:' line in the body. This will make author and
signed-off-by mismatch. Sorry, I will send v2 soon.
Thanks,
SeongJae Park
On Sat, 29 Aug 2020 10:04:26 +0200 SeongJae Park wrote:
> This patchset syncs howto.rst for recent changes to the original doc a
Translate this commit to Korean:
3e79f082ebfc ("libnvdimm/nvdimm/flush: Allow architecture to override the
flush barrier")
Signed-off-by: SeongJae Park
Reviewed-by: Yunjae Lee
---
.../translations/ko_KR/memory-barriers.txt | 13 +
1 file changed, 13
Commit 985098a05eee ("docs: fix references for DMA*.txt files") missed
fixing memory-barriers.txt file. This commit applies the change to the
file.
Signed-off-by: SeongJae Park
---
Documentation/memory-barriers.txt | 8
1 file changed, 4 insertions(+), 4 deletions(-)
di
Translate this commit to Korean:
a897b13d1b77 ("docs/memory-barriers.txt: Remove remaining references to
mmiowb()")
Signed-off-by: SeongJae Park
Reviewed-by: Yunjae Lee
---
.../translations/ko_KR/memory-barriers.txt| 19 +++
1 file changed, 7 inserti
This patchset applies missed changes that should land in the
memory-barriers.txt and its Korean translation.
The patches are based on v5.9-rc2.
SeongJae Park (3):
docs/memory-barriers.txt: Fix references for DMA*.txt files
docs/memory-barriers.txt/kokr: Remove remaining references to mmiowb
This patchset syncs howto.rst for recent changes to the original doc and
fix some trivial nits in the translation itself.
The patches are based on v5.9-rc2.
SeongJae Park (2):
Documentation/kokr: bring process docs up to date
Documentation/kokr/howto: Wordsmith
Documentation/translations
The sentence regarding version numbers of '-stable' kernels is quite
ambiguous. This commit makes the sentence more clear and fix
inconsistent uses of the terms for 'version'.
Signed-off-by: SeongJae Park
---
Documentation/translations/ko_KR/howto.rst | 10 +
Translate this commit to Korean:
fb0e0ffe7fc8 ("Documentation: bring process docs up to date")
Signed-off-by: SeongJae Park
---
Documentation/translations/ko_KR/howto.rst | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/Documentation/translations/ko_KR/ho
On Fri, 28 Aug 2020 11:53:15 +0200 SeongJae Park wrote:
> On Fri, 28 Aug 2020 04:11:56 -0400 Alkaid wrote:
>
> >
> > [-- Attachment #1: Type: text/plain, Size: 2677 bytes --]
> >
> > Hi SeongJae,
> >
> > I think there are potential memory leaks in
this! I
will post a patch for this soon.
Thanks,
SeongJae Park
[...]
On Thu, 20 Aug 2020 08:44:33 -0700 Shakeel Butt wrote:
> On Thu, Aug 20, 2020 at 12:11 AM SeongJae Park wrote:
> >
> > On Wed, 19 Aug 2020 18:21:44 -0700 Shakeel Butt wrote:
> >
> > > On Tue, Aug 18, 2020 at 12:25 AM SeongJae Park wrote:
>
On Thu, 20 Aug 2020 06:26:49 -0700 Shakeel Butt wrote:
> On Thu, Aug 20, 2020 at 12:17 AM SeongJae Park wrote:
> >
> > On Wed, 19 Aug 2020 17:26:15 -0700 Shakeel Butt wrote:
> >
> > > On Tue, Aug 18, 2020 at 12:27 AM SeongJae Park wrote:
>
On Mon, 17 Aug 2020 12:51:22 +0200 SeongJae Park wrote:
> From: SeongJae Park
>
> Changes from Previous Version
> =
>
> - Place 'CREATE_TRACE_POINTS' after '#include' statements (Steven Rostedt)
> - Support large reco
On Wed, 19 Aug 2020 17:26:15 -0700 Shakeel Butt wrote:
> On Tue, Aug 18, 2020 at 12:27 AM SeongJae Park wrote:
> >
> > From: SeongJae Park
> >
> > This commit implements the four callbacks (->init_target_regions,
> > ->update_target_regions, ->
On Wed, 19 Aug 2020 18:21:44 -0700 Shakeel Butt wrote:
> On Tue, Aug 18, 2020 at 12:25 AM SeongJae Park wrote:
> >
> > From: SeongJae Park
> >
> > Changes from Previous Version
> > =
> >
> > - Use 42 as the fake targe
From: SeongJae Park
This commit updates the DAMON documents for the physical memory
monitoring support.
Signed-off-by: SeongJae Park
---
Documentation/admin-guide/mm/damon/usage.rst | 42
Documentation/vm/damon/design.rst| 29 +-
Documentation/vm
From: SeongJae Park
This commit updates the DAMON user space tool (damo-record) for NUMA
specific physical memory monitoring. With this change, users can
monitor accesses to physical memory of specific NUMA node.
Signed-off-by: SeongJae Park
---
tools/damon/_paddr_layout.py | 147
From: SeongJae Park
This commit allows users to record the data accesses on physical memory
address space by passing 'paddr' as target to 'damo-record'. If the
init regions are given, the regions will be monitored. Else, it will
monitor biggest conitguous 'System RA
From: SeongJae Park
This commit makes the debugfs interface to support the physical memory
monitoring, in addition to the virtual memory monitoring.
Users can do the physical memory monitoring by writing a special
keyword, 'paddr\n' to the 'pids' debugfs file. Then,
From: SeongJae Park
This commit adds description of the 'init_regions' feature in the DAMON
usage document.
Signed-off-by: SeongJae Park
---
Documentation/admin-guide/mm/damon/usage.rst | 41 +++-
1 file changed, 39 insertions(+), 2 deletions(-)
diff --git a/Doc
From: SeongJae Park
This commit implements the four callbacks (->init_target_regions,
->update_target_regions, ->prepare_access_check, and ->check_accesses)
for the basic access monitoring of the physical memory address space.
By setting the callback pointers to point those, user
From: SeongJae Park
This commit adds more test cases for the new feature, 'init_regions'.
Signed-off-by: SeongJae Park
---
mm/damon-test.h | 53 +
1 file changed, 53 insertions(+)
diff --git a/mm/damon-test.h b/mm/damon-te
301 - 400 of 1001 matches
Mail list logo