diff mbox series

[v3,2/2] doc: Update documentation for page_idle virtual address indexing

Message ID 20190726152319.134152-2-joel@joelfernandes.org (mailing list archive)
State New, archived
Headers show
Series [v3,1/2] mm/page_idle: Add per-pid idle page tracking using virtual indexing | expand

Commit Message

Joel Fernandes July 26, 2019, 3:23 p.m. UTC
This patch updates the documentation with the new page_idle tracking
feature which uses virtual address indexing.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
---
 .../admin-guide/mm/idle_page_tracking.rst     | 43 ++++++++++++++++---
 1 file changed, 36 insertions(+), 7 deletions(-)

Comments

Sandeep Patil July 26, 2019, 8:17 p.m. UTC | #1
Thanks Joel, just a couple of nits for the doc inline below. Other than that,

Reviewed-by: Sandeep Patil <sspatil@google.com>

I'll plan on making changes to Android to use this instead of the pagemap +
page_idle. I think it will also be considerably faster.

On Fri, Jul 26, 2019 at 11:23:19AM -0400, Joel Fernandes (Google) wrote:
> This patch updates the documentation with the new page_idle tracking
> feature which uses virtual address indexing.
> 
> Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
> ---
>  .../admin-guide/mm/idle_page_tracking.rst     | 43 ++++++++++++++++---
>  1 file changed, 36 insertions(+), 7 deletions(-)
> 
> diff --git a/Documentation/admin-guide/mm/idle_page_tracking.rst b/Documentation/admin-guide/mm/idle_page_tracking.rst
> index df9394fb39c2..1eeac78c94a7 100644
> --- a/Documentation/admin-guide/mm/idle_page_tracking.rst
> +++ b/Documentation/admin-guide/mm/idle_page_tracking.rst
> @@ -19,10 +19,14 @@ It is enabled by CONFIG_IDLE_PAGE_TRACKING=y.
>  
>  User API
>  ========
> +There are 2 ways to access the idle page tracking API. One uses physical
> +address indexing, another uses a simpler virtual address indexing scheme.
>  
> -The idle page tracking API is located at ``/sys/kernel/mm/page_idle``.
> -Currently, it consists of the only read-write file,
> -``/sys/kernel/mm/page_idle/bitmap``.
> +Physical address indexing
> +-------------------------
> +The idle page tracking API for physical address indexing using page frame
> +numbers (PFN) is located at ``/sys/kernel/mm/page_idle``.  Currently, it
> +consists of the only read-write file, ``/sys/kernel/mm/page_idle/bitmap``.
>  
>  The file implements a bitmap where each bit corresponds to a memory page. The
>  bitmap is represented by an array of 8-byte integers, and the page at PFN #i is
> @@ -74,6 +78,31 @@ See :ref:`Documentation/admin-guide/mm/pagemap.rst <pagemap>` for more
>  information about ``/proc/pid/pagemap``, ``/proc/kpageflags``, and
>  ``/proc/kpagecgroup``.
>  
> +Virtual address indexing
> +------------------------
> +The idle page tracking API for virtual address indexing using virtual page
> +frame numbers (VFN) is located at ``/proc/<pid>/page_idle``. It is a bitmap
> +that follows the same semantics as ``/sys/kernel/mm/page_idle/bitmap``
> +except that it uses virtual instead of physical frame numbers.
> +
> +This idle page tracking API does not need deal with PFN so it does not require

s/need//

> +prior lookups of ``pagemap`` in order to find if page is idle or not. This is

s/in order to find if page is idle or not//

> +an advantage on some systems where looking up PFN is considered a security
> +issue.  Also in some cases, this interface could be slightly more reliable to
> +use than physical address indexing, since in physical address indexing, address
> +space changes can occur between reading the ``pagemap`` and reading the
> +``bitmap``, while in virtual address indexing, the process's ``mmap_sem`` is
> +held for the duration of the access.
> +
> +To estimate the amount of pages that are not used by a workload one should:
> +
> + 1. Mark all the workload's pages as idle by setting corresponding bits in
> +    ``/proc/<pid>/page_idle``.
> +
> + 2. Wait until the workload accesses its working set.
> +
> + 3. Read ``/proc/<pid>/page_idle`` and count the number of bits set.
> +
>  .. _impl_details:
>  
>  Implementation Details
> @@ -99,10 +128,10 @@ When a dirty page is written to swap or disk as a result of memory reclaim or
>  exceeding the dirty memory limit, it is not marked referenced.
>  
>  The idle memory tracking feature adds a new page flag, the Idle flag. This flag
> -is set manually, by writing to ``/sys/kernel/mm/page_idle/bitmap`` (see the
> -:ref:`User API <user_api>`
> -section), and cleared automatically whenever a page is referenced as defined
> -above.
> +is set manually, by writing to ``/sys/kernel/mm/page_idle/bitmap`` for physical
> +addressing or by writing to ``/proc/<pid>/page_idle`` for virtual
> +addressing (see the :ref:`User API <user_api>` section), and cleared
> +automatically whenever a page is referenced as defined above.
>  
>  When a page is marked idle, the Accessed bit must be cleared in all PTEs it is
>  mapped to, otherwise we will not be able to detect accesses to the page coming
> -- 
> 2.22.0.709.g102302147b-goog
> 
> -- 
> To unsubscribe from this group and stop receiving emails from it, send an email to kernel-team+unsubscribe@android.com.
>
Joel Fernandes July 26, 2019, 8:26 p.m. UTC | #2
On Fri, Jul 26, 2019 at 01:17:10PM -0700, sspatil@google.com wrote:
> Thanks Joel, just a couple of nits for the doc inline below. Other than that,
> 
> Reviewed-by: Sandeep Patil <sspatil@google.com>

Thanks!

> I'll plan on making changes to Android to use this instead of the pagemap +
> page_idle. I think it will also be considerably faster.

Cool, glad to know.

> On Fri, Jul 26, 2019 at 11:23:19AM -0400, Joel Fernandes (Google) wrote:
> > This patch updates the documentation with the new page_idle tracking
> > feature which uses virtual address indexing.
> > 
> > Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
> > ---
> >  .../admin-guide/mm/idle_page_tracking.rst     | 43 ++++++++++++++++---
> >  1 file changed, 36 insertions(+), 7 deletions(-)
> > 
> > diff --git a/Documentation/admin-guide/mm/idle_page_tracking.rst b/Documentation/admin-guide/mm/idle_page_tracking.rst
> > index df9394fb39c2..1eeac78c94a7 100644
> > --- a/Documentation/admin-guide/mm/idle_page_tracking.rst
> > +++ b/Documentation/admin-guide/mm/idle_page_tracking.rst
> > @@ -19,10 +19,14 @@ It is enabled by CONFIG_IDLE_PAGE_TRACKING=y.
> >  
> >  User API
> >  ========
> > +There are 2 ways to access the idle page tracking API. One uses physical
> > +address indexing, another uses a simpler virtual address indexing scheme.
> >  
> > -The idle page tracking API is located at ``/sys/kernel/mm/page_idle``.
> > -Currently, it consists of the only read-write file,
> > -``/sys/kernel/mm/page_idle/bitmap``.
> > +Physical address indexing
> > +-------------------------
> > +The idle page tracking API for physical address indexing using page frame
> > +numbers (PFN) is located at ``/sys/kernel/mm/page_idle``.  Currently, it
> > +consists of the only read-write file, ``/sys/kernel/mm/page_idle/bitmap``.
> >  
> >  The file implements a bitmap where each bit corresponds to a memory page. The
> >  bitmap is represented by an array of 8-byte integers, and the page at PFN #i is
> > @@ -74,6 +78,31 @@ See :ref:`Documentation/admin-guide/mm/pagemap.rst <pagemap>` for more
> >  information about ``/proc/pid/pagemap``, ``/proc/kpageflags``, and
> >  ``/proc/kpagecgroup``.
> >  
> > +Virtual address indexing
> > +------------------------
> > +The idle page tracking API for virtual address indexing using virtual page
> > +frame numbers (VFN) is located at ``/proc/<pid>/page_idle``. It is a bitmap
> > +that follows the same semantics as ``/sys/kernel/mm/page_idle/bitmap``
> > +except that it uses virtual instead of physical frame numbers.
> > +
> > +This idle page tracking API does not need deal with PFN so it does not require
> 
> s/need//
> 
> > +prior lookups of ``pagemap`` in order to find if page is idle or not. This is
> 
> s/in order to find if page is idle or not//

Fixed both, thank you! Will send out update soon.

thanks,

 - Joel
Mike Rapoport July 31, 2019, 6:44 a.m. UTC | #3
On Fri, Jul 26, 2019 at 11:23:19AM -0400, Joel Fernandes (Google) wrote:
> This patch updates the documentation with the new page_idle tracking
> feature which uses virtual address indexing.
> 
> Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>

One nit below, otherwise

Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>

> ---
>  .../admin-guide/mm/idle_page_tracking.rst     | 43 ++++++++++++++++---
>  1 file changed, 36 insertions(+), 7 deletions(-)
> 
> diff --git a/Documentation/admin-guide/mm/idle_page_tracking.rst b/Documentation/admin-guide/mm/idle_page_tracking.rst
> index df9394fb39c2..1eeac78c94a7 100644
> --- a/Documentation/admin-guide/mm/idle_page_tracking.rst
> +++ b/Documentation/admin-guide/mm/idle_page_tracking.rst
> @@ -19,10 +19,14 @@ It is enabled by CONFIG_IDLE_PAGE_TRACKING=y.
>  
>  User API
>  ========
> +There are 2 ways to access the idle page tracking API. One uses physical
> +address indexing, another uses a simpler virtual address indexing scheme.
>  
> -The idle page tracking API is located at ``/sys/kernel/mm/page_idle``.
> -Currently, it consists of the only read-write file,
> -``/sys/kernel/mm/page_idle/bitmap``.
> +Physical address indexing
> +-------------------------
> +The idle page tracking API for physical address indexing using page frame
> +numbers (PFN) is located at ``/sys/kernel/mm/page_idle``.  Currently, it
> +consists of the only read-write file, ``/sys/kernel/mm/page_idle/bitmap``.
>  
>  The file implements a bitmap where each bit corresponds to a memory page. The
>  bitmap is represented by an array of 8-byte integers, and the page at PFN #i is
> @@ -74,6 +78,31 @@ See :ref:`Documentation/admin-guide/mm/pagemap.rst <pagemap>` for more
>  information about ``/proc/pid/pagemap``, ``/proc/kpageflags``, and
>  ``/proc/kpagecgroup``.
>  
> +Virtual address indexing
> +------------------------
> +The idle page tracking API for virtual address indexing using virtual page
> +frame numbers (VFN) is located at ``/proc/<pid>/page_idle``. It is a bitmap
> +that follows the same semantics as ``/sys/kernel/mm/page_idle/bitmap``
> +except that it uses virtual instead of physical frame numbers.

Can you please make it more explicit that VFNs are in the <pid>'s address
space?

> +
> +This idle page tracking API does not need deal with PFN so it does not require
> +prior lookups of ``pagemap`` in order to find if page is idle or not. This is
> +an advantage on some systems where looking up PFN is considered a security
> +issue.  Also in some cases, this interface could be slightly more reliable to
> +use than physical address indexing, since in physical address indexing, address
> +space changes can occur between reading the ``pagemap`` and reading the
> +``bitmap``, while in virtual address indexing, the process's ``mmap_sem`` is
> +held for the duration of the access.
> +
> +To estimate the amount of pages that are not used by a workload one should:
> +
> + 1. Mark all the workload's pages as idle by setting corresponding bits in
> +    ``/proc/<pid>/page_idle``.
> +
> + 2. Wait until the workload accesses its working set.
> +
> + 3. Read ``/proc/<pid>/page_idle`` and count the number of bits set.
> +
>  .. _impl_details:
>  
>  Implementation Details
> @@ -99,10 +128,10 @@ When a dirty page is written to swap or disk as a result of memory reclaim or
>  exceeding the dirty memory limit, it is not marked referenced.
>  
>  The idle memory tracking feature adds a new page flag, the Idle flag. This flag
> -is set manually, by writing to ``/sys/kernel/mm/page_idle/bitmap`` (see the
> -:ref:`User API <user_api>`
> -section), and cleared automatically whenever a page is referenced as defined
> -above.
> +is set manually, by writing to ``/sys/kernel/mm/page_idle/bitmap`` for physical
> +addressing or by writing to ``/proc/<pid>/page_idle`` for virtual
> +addressing (see the :ref:`User API <user_api>` section), and cleared
> +automatically whenever a page is referenced as defined above.
>  
>  When a page is marked idle, the Accessed bit must be cleared in all PTEs it is
>  mapped to, otherwise we will not be able to detect accesses to the page coming
> -- 
> 2.22.0.709.g102302147b-goog
>
diff mbox series

Patch

diff --git a/Documentation/admin-guide/mm/idle_page_tracking.rst b/Documentation/admin-guide/mm/idle_page_tracking.rst
index df9394fb39c2..1eeac78c94a7 100644
--- a/Documentation/admin-guide/mm/idle_page_tracking.rst
+++ b/Documentation/admin-guide/mm/idle_page_tracking.rst
@@ -19,10 +19,14 @@  It is enabled by CONFIG_IDLE_PAGE_TRACKING=y.
 
 User API
 ========
+There are 2 ways to access the idle page tracking API. One uses physical
+address indexing, another uses a simpler virtual address indexing scheme.
 
-The idle page tracking API is located at ``/sys/kernel/mm/page_idle``.
-Currently, it consists of the only read-write file,
-``/sys/kernel/mm/page_idle/bitmap``.
+Physical address indexing
+-------------------------
+The idle page tracking API for physical address indexing using page frame
+numbers (PFN) is located at ``/sys/kernel/mm/page_idle``.  Currently, it
+consists of the only read-write file, ``/sys/kernel/mm/page_idle/bitmap``.
 
 The file implements a bitmap where each bit corresponds to a memory page. The
 bitmap is represented by an array of 8-byte integers, and the page at PFN #i is
@@ -74,6 +78,31 @@  See :ref:`Documentation/admin-guide/mm/pagemap.rst <pagemap>` for more
 information about ``/proc/pid/pagemap``, ``/proc/kpageflags``, and
 ``/proc/kpagecgroup``.
 
+Virtual address indexing
+------------------------
+The idle page tracking API for virtual address indexing using virtual page
+frame numbers (VFN) is located at ``/proc/<pid>/page_idle``. It is a bitmap
+that follows the same semantics as ``/sys/kernel/mm/page_idle/bitmap``
+except that it uses virtual instead of physical frame numbers.
+
+This idle page tracking API does not need deal with PFN so it does not require
+prior lookups of ``pagemap`` in order to find if page is idle or not. This is
+an advantage on some systems where looking up PFN is considered a security
+issue.  Also in some cases, this interface could be slightly more reliable to
+use than physical address indexing, since in physical address indexing, address
+space changes can occur between reading the ``pagemap`` and reading the
+``bitmap``, while in virtual address indexing, the process's ``mmap_sem`` is
+held for the duration of the access.
+
+To estimate the amount of pages that are not used by a workload one should:
+
+ 1. Mark all the workload's pages as idle by setting corresponding bits in
+    ``/proc/<pid>/page_idle``.
+
+ 2. Wait until the workload accesses its working set.
+
+ 3. Read ``/proc/<pid>/page_idle`` and count the number of bits set.
+
 .. _impl_details:
 
 Implementation Details
@@ -99,10 +128,10 @@  When a dirty page is written to swap or disk as a result of memory reclaim or
 exceeding the dirty memory limit, it is not marked referenced.
 
 The idle memory tracking feature adds a new page flag, the Idle flag. This flag
-is set manually, by writing to ``/sys/kernel/mm/page_idle/bitmap`` (see the
-:ref:`User API <user_api>`
-section), and cleared automatically whenever a page is referenced as defined
-above.
+is set manually, by writing to ``/sys/kernel/mm/page_idle/bitmap`` for physical
+addressing or by writing to ``/proc/<pid>/page_idle`` for virtual
+addressing (see the :ref:`User API <user_api>` section), and cleared
+automatically whenever a page is referenced as defined above.
 
 When a page is marked idle, the Accessed bit must be cleared in all PTEs it is
 mapped to, otherwise we will not be able to detect accesses to the page coming