Message-ID: <20200310115755.25270-1-sjpark@amazon.com>
Date:   Tue, 10 Mar 2020 12:57:55 +0100
From:   SeongJae Park <sjpark@...zon.com>
To:     Jonathan Cameron <Jonathan.Cameron@...wei.com>
CC:     SeongJae Park <sjpark@...zon.com>, <akpm@...ux-foundation.org>,
        "SeongJae Park" <sjpark@...zon.de>, <aarcange@...hat.com>,
        <yang.shi@...ux.alibaba.com>, <acme@...nel.org>,
        <alexander.shishkin@...ux.intel.com>, <amit@...nel.org>,
        <brendan.d.gregg@...il.com>, <brendanhiggins@...gle.com>,
        <cai@....pw>, <colin.king@...onical.com>, <corbet@....net>,
        <dwmw@...zon.com>, <jolsa@...hat.com>, <kirill@...temov.name>,
        <mark.rutland@....com>, <mgorman@...e.de>, <minchan@...nel.org>,
        <mingo@...hat.com>, <namhyung@...nel.org>, <peterz@...radead.org>,
        <rdunlap@...radead.org>, <rientjes@...gle.com>,
        <rostedt@...dmis.org>, <shuah@...nel.org>, <sj38.park@...il.com>,
        <vbabka@...e.cz>, <vdavydov.dev@...il.com>, <linux-mm@...ck.org>,
        <linux-doc@...r.kernel.org>, <linux-kernel@...r.kernel.org>
Subject: Re: Re: [PATCH v6 11/14] Documentation/admin-guide/mm: Add a document for DAMON

On Tue, 10 Mar 2020 09:03:48 +0000 Jonathan Cameron <Jonathan.Cameron@...wei.com> wrote:

> On Mon, 24 Feb 2020 13:30:44 +0100
> SeongJae Park <sjpark@...zon.com> wrote:
> 
> > From: SeongJae Park <sjpark@...zon.de>
> > 
> > This commit adds a simple document for DAMON under
> > `Documentation/admin-guide/mm`.
> > 
> 
> Nice document to get people started.
> 
> Certainly worked for me doing some initial playing around.

Great to hear that :)

> 
> In general this is an interesting piece of work.   I can see there are numerous
> possible avenues to explore in making the monitoring more flexible, or potentially
> better at tracking usage whilst not breaking your fundamental 'bounded overhead'
> requirement.   Will be fun perhaps to explore some of those.
> 
> I'll do some more exploring and perhaps try some real world workloads.
> 
> Thanks,
> 
> Jonathan
> 
> 
> > Signed-off-by: SeongJae Park <sjpark@...zon.de>
> > ---
> >  .../admin-guide/mm/data_access_monitor.rst    | 414 ++++++++++++++++++
> >  Documentation/admin-guide/mm/index.rst        |   1 +
> >  2 files changed, 415 insertions(+)
> >  create mode 100644 Documentation/admin-guide/mm/data_access_monitor.rst
> > 
> > diff --git a/Documentation/admin-guide/mm/data_access_monitor.rst b/Documentation/admin-guide/mm/data_access_monitor.rst
> > new file mode 100644
> > index 000000000000..4d836c3866e2
> > --- /dev/null
> > +++ b/Documentation/admin-guide/mm/data_access_monitor.rst
> > @@ -0,0 +1,414 @@
> > +.. SPDX-License-Identifier: GPL-2.0
> > +
> > +==========================
> > +DAMON: Data Access MONitor
> > +==========================
> > +
> > +Introduction
> > +============
> > +
> > +Memory management decisions can normally be more efficient if finer data access
> > +information is available.  However, because finer information usually comes
> > +with higher overhead, most systems including Linux made a tradeoff: Forgive
> > +some wise decisions and use coarse information and/or light-weight heuristics.
> 
> I'm not sure what "Forgive some wise decisions" means...

I wanted to mean that the mechanism makes no optimal decisions.  Will wordsmith
again.

> 
> > +
> > +A number of experimental data access pattern awared memory management
> > +optimizations say the sacrifices are
> > +huge (2.55x slowdown).  
> 
> Good to have a reference.

:)

> 
> > However, none of those has successfully adopted to
> 
> adopted into the 

Thanks for correcting.

> 
[...]
> > +Applying Dynamic Memory Mappings
> > +--------------------------------
> > +
> > +Only a number of small parts in the super-huge virtual address space of the
> > +processes is mapped to physical memory and accessed.  Thus, tracking the
> > +unmapped address regions is just wasteful.  However, tracking every memory
> > +mapping change might incur an overhead.  For the reason, DAMON applies the
> > +dynamic memory mapping changes to the tracking regions only for each of an
> > +user-specified time interval (``regions update interval``).
> 
> One key part of the approach is the 3 region bit.  Perhaps talk about that here
> somewhere?

I was afraid if it is too implementation detail, as this document is for admin
users.  Will add it in next spin, though.

> 
> > +
> > +
> > +``debugfs`` Interface
> > +=====================
> > +
> > +DAMON exports four files, ``attrs``, ``pids``, ``record``, and ``monitor_on``
> > +under its debugfs directory, ``<debugfs>/damon/``.
> > +
> > +Attributes
> > +----------
> > +
> > +Users can read and write the ``sampling interval``, ``aggregation interval``,
> > +``regions update interval``, and min/max number of monitoring target regions by
> > +reading from and writing to the ``attrs`` file.  For example, below commands
> > +set those values to 5 ms, 100 ms, 1,000 ms, 10, 1000 and check it again::
> > +
> > +    # cd <debugfs>/damon
> > +    # echo 5000 100000 1000000 10 1000 > attrs
> 
> I'm personally a great fan of human readable interfaces.  Could we just
> split this into one file per interval?  That way the file naming would
> make it self describing.

I was worried if it makes too many files.  Do you think it's ok?

> 
> > +    # cat attrs
> > +    5000 100000 1000000 10 1000
> > +
> > +Target PIDs
> > +-----------
> > +
> > +Users can read and write the pids of current monitoring target processes by
> > +reading from and writing to the ``pids`` file.  For example, below commands set
> > +processes having pids 42 and 4242 as the processes to be monitored and check it
> > +again::
> > +
> > +    # cd <debugfs>/damon
> > +    # echo 42 4242 > pids
> > +    # cat pids
> > +    42 4242
> > +
> > +Note that setting the pids doesn't starts the monitoring.
> > +
> > +Record
> > +------
> > +
> > +DAMON support direct monitoring result record feature.  The recorded results
> > +are first written to a buffer and flushed to a file in batch.  Users can set
> > +the size of the buffer and the path to the result file by reading from and
> > +writing to the ``record`` file.  For example, below commands set the buffer to
> > +be 4 KiB and the result to be saved in ``/damon.data``.
> > +
> > +    # cd <debugfs>/damon
> > +    # echo "4096 /damon.data" > pids
> 
> write it to record, not pids.

Ah, good eye!

> 
> > +    # cat record
> > +    4096 /damon.data
> > +
> > +Turning On/Off
> > +--------------
> > +
> > +You can check current status, start and stop the monitoring by reading from and
> > +writing to the ``monitor_on`` file.  Writing ``on`` to the file starts DAMON to
> > +monitor the target processes with the attributes.  Writing ``off`` to the file
> > +stops DAMON.  DAMON also stops if every target processes is be terminated.
> > +Below example commands turn on, off, and check status of DAMON::
> > +
> > +    # cd <debugfs>/damon
> > +    # echo on > monitor_on
> > +    # echo off > monitor_on
> > +    # cat monitor_on
> > +    off
> > +
> > +Please note that you cannot write to the ``attrs`` and ``pids`` files while the
> > +monitoring is turned on.  If you write to the files while DAMON is running,
> > +``-EINVAL`` will be returned.
> 
> Perhaps -EBUSY would be more informative?  Implies values might be fine, but
> the issue is 'not now'.

Agreed, will change so!


Thanks,
SeongJae Park

[...]

Powered by blists - more mailing lists