Introduce Data Access MONitor (DAMON)
Subsystems (4)
cover Introduce Data Access MONitor (DAMON)
From: SeongJae Park <[email protected]>
This RFC patchset introduces a new kernel module for practical monitoring of data accesses, namely DAMON.
The patches are organized in the following sequence. The first and second patch introduces the core logic and the raw level user interface of DAMON, respectively. To provide a minimal reference to the raw level interfaces and for more convenient test of the DAMON itself, the third patch implements an user space wrapper tools for the DAMON. The fourth patch adds a document for the DAMON, and finally the fifth patch provides DAMON's unit tests, which is using the kunit framework.
The patches are based on the v5.4 plus the back-ported kunit, which retrieved from v5.5-rc1. You can also clone the complete git tree by:
$ git clone git://github.com/sjp38/linux -b damon/rfc/v1
The web is also available:
https://github.com/sjp38/linux/releases/tag/damon/rfc/v1
----
DAMON is a kernel module that allows users to monitor the actual memory access pattern of specific user-space processes. It aims to be 1) accurate enough to be useful for performance-centric domains, and 2) sufficiently light-weight so that it can be applied online.
For the goals, DAMON utilizes its two core mechanisms, called region-based sampling and adaptive regions adjustment. The region-based sampling allows users to make their own trade-off between the quality and the overhead of the monitoring and set the upperbound of the monitoring overhead. Further, the adaptive regions adjustment mechanism makes DAMON to maximize the quality and minimize the overhead with its best efforts while preserving the users configured trade-off.
Background
==========
For performance-centric analysis and optimizations of memory management schemes (either that of kernel space or user space), the actual data access pattern of the workloads is highly useful. The information need to be only reasonable rather than strictly correct, because some level of incorrectness can be handled in many performance-centric domains. It also need to be taken within reasonably short time with only light-weight overhead.
Manually extracting such data is not easy and time consuming if the target workload is huge and complex, even for the developers of the programs. There are a range of tools and techniques developed for general memory access investigations, and some of those could be partially used for this purpose. However, most of those are not practical or unscalable, mainly because those are designed with no consideration about the trade-off between the accuracy of the output and the overhead.
The memory access instrumentation techniques which is applied to many tools such as Intel PIN is essential for correctness required cases such as invalid memory access bug detections. However, those usually incur high overhead which is unacceptable for many of the performance-centric domains. Periodic access checks based on H/W or S/W access counting features (e.g., the Accessed bits of PTEs or the PG_Idle flags of pages) can dramatically decrease the overhead by forgiving some of the quality, compared to the instrumentation based techniques. The reduced quality is still reasonable for many of the domains, but the overhead can arbitrarily increase as the size of the target workload grows. Miniature-like static region based sampling can set the upperbound of the overhead, but it will now decrease the quality of the output as the size of the workload grows.
Related Works
=============
There are a number of researches[1,2,3,4,5,6] optimizing memory management mechanisms based on the actual memory access patterns that shows impressive results. However, most of those has no deep consideration about the monitoring of the accesses itself. Some of those focused on the overhead of the monitoring, but does not consider the accuracy scalability[6] or has additional dependencies[7]. Indeed, one recent research[5] about the proactive reclamation has also proposed[8] to the kernel community but the monitoring overhead was considered a main problem.
[1] Subramanya R Dulloor, Amitabha Roy, Zheguang Zhao, Narayanan Sundaram, Nadathur Satish, Rajesh Sankaran, Jeff Jackson, and Karsten Schwan. 2016. Data tiering in heterogeneous memory systems. In Proceedings of the 11th European Conference on Computer Systems (EuroSys). ACM, 15.
[2] Youngjin Kwon, Hangchen Yu, Simon Peter, Christopher J Rossbach, and Emmett Witchel. 2016. Coordinated and efficient huge page management with ingens. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 705–721.
[3] Harald Servat, Antonio J Peña, Germán Llort, Estanislao Mercadal, HansChristian Hoppe, and Jesús Labarta. 2017. Automating the application data placement in hybrid memory systems. In 2017 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, 126–136.
[4] Vlad Nitu, Boris Teabe, Alain Tchana, Canturk Isci, and Daniel Hagimont. 2018. Welcome to zombieland: practical and energy-efficient memory disaggregation in a datacenter. In Proceedings of the 13th European Conference on Computer Systems (EuroSys). ACM, 16.
[5] Andres Lagar-Cavilla, Junwhan Ahn, Suleiman Souhlal, Neha Agarwal, Radoslaw Burny, Shakeel Butt, Jichuan Chang, Ashwin Chaugule, Nan Deng, Junaid Shahid, Greg Thelen, Kamil Adam Yurtsever, Yu Zhao, and Parthasarathy Ranganathan. 2019. Software-Defined Far Memory in Warehouse-Scale Computers. In Proceedings of the 24th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). ACM, New York, NY, USA, 317–330. DOI:https://doi.org/10.1145/3297858.3304053
[6] Carl Waldspurger, Trausti Saemundsson, Irfan Ahmad, and Nohhyun Park. 2017. Cache Modeling and Optimization using Miniature Simulations. In 2017 USENIX Annual Technical Conference (ATC). USENIX Association, Santa Clara, CA, 487–498.
https://www.usenix.org/conference/atc17/technical-sessions/
[7] Haojie Wang, Jidong Zhai, Xiongchao Tang, Bowen Yu, Xiaosong Ma, and Wenguang Chen. 2018. Spindle: Informed Memory Access Monitoring. In 2018 USENIX Annual Technical Conference (ATC). USENIX Association, Boston, MA, 561–574. https://www.usenix.org/conference/atc18/presentation/wang-haojie
[8] Jonathan Corbet. 2019. Proactively reclaiming idle memory. (2019).
https://lwn.net/Articles/787611/.
Expected Use-cases
==================
A straightforward usecase of DAMON would be the program behavior analysis. With the DAMON output, users can confirm whether the program is running as intended or not. This will be useful for debuggings and tests of design points.
The monitored results can also be useful for counting the dynamic working set size of workloads. For the administration of memory overcommitted systems or selection of the environments (e.g., containers providing different amount of memory) for your workloads, this will be useful.
If you are a programmer, you can optimize your program by managing the memory based on the actual data access pattern. For example, you can identify the dynamic hotness of your data using DAMON and call ``mlock()`` to keep your hot data in DRAM, or call ``madvise()`` with ``MADV_PAGEOUT`` to proactively reclaim cold data. Even though your program is guaranteed to not encounter memory pressure, you can still improve the performance by applying the DAMON outputs for call of ``MADV_HUGEPAGE`` and ``MADV_NOHUGEPAGE``. More creative optimizations would be possible. Our evaluations of DAMON includes a straightforward optimization using the ``mlock()``. Please refer to the below Evaluation section for more detail.
As DAMON incurs very low overhead, such optimizations can be applied not only offline, but also online. Also, there is no reason to limit such optimizations to the user space. Several parts of the kernel's memory management mechanisms could be also optimized using DAMON. The reclamation, the THP (de)promotion decisions, and the compaction would be such a candidates. Nevertheless, current version of DAMON is not highly optimized for the online/in-kernel uses.
Mechanisms of DAMON
===================
Basic Access Check
------------------
DAMON basically reports what pages are how frequently accessed. The report is passed to users in binary format via a ``result file`` which users can set it's path. Note that the frequency is not an absolute number of accesses, but a relative frequency among the pages of the target workloads.
Users can also control the resolution of the reports by setting two time intervals, ``sampling interval`` and ``aggregation interval``. In detail, DAMON checks access to each page per ``sampling interval``, aggregates the results (counts the number of the accesses to each page), and reports the aggregated results per ``aggregation interval``. For the access check of each page, DAMON uses the Accessed bits of PTEs.
This is thus similar to the previously mentioned periodic access checks based mechanisms, which overhead is increasing as the size of the target process grows.
Region Based Sampling
---------------------
To avoid the unbounded increase of the overhead, DAMON groups a number of adjacent pages that assumed to have same access frequencies into a region. As long as the assumption (pages in a region have same access frequencies) is kept, only one page in the region is required to be checked. Thus, for each ``sampling interval``, DAMON randomly picks one page in each region and clears its Accessed bit. After one more ``sampling interval``, DAMON reads the Accessed bit of the page and increases the access frequency of the region if the bit has set meanwhile. Therefore, the monitoring overhead is controllable by setting the number of regions. DAMON allows users to set the minimal and maximum number of regions for the trade-off.
Except the assumption, this is almost same with the above-mentioned miniature-like static region based sampling. In other words, this scheme cannot preserve the quality of the output if the assumption is not guaranteed.
Adaptive Regions Adjustment
---------------------------
At the beginning of the monitoring, DAMON constructs the initial regions by evenly splitting the memory mapped address space of the process into the user-specified minimal number of regions. In this initial state, the assumption is normally not kept and thus the quality could be low. To keep the assumption as much as possible, DAMON adaptively merges and splits each region. For each ``aggregation interval``, it compares the access frequencies of adjacent regions and merges those if the frequency difference is small. Then, after it reports and clears the aggregated access frequency of each region, it splits each region into two regions if the total number of regions is smaller than the half of the user-specified maximum number of regions.
In this way, DAMON provides its best-effort quality and minimal overhead while keeping the bounds users set for their trade-off.
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``).
Evaluations
===========
A prototype of DAMON has evaluated on an Intel Xeon E7-8837 machine using 20 benchmarks that picked from SPEC CPU 2006, NAS, Tensorflow Benchmark, SPLASH-2X, and PARSEC 3 benchmark suite. Nonethless, this section provides only summary of the results. For more detail, please refer to the slides used for the introduction of DAMON at the Linux Plumbers Conference 2019[1] or the MIDDLEWARE'19 industrial track paper[2].
Quality
-------
We first traced and visualized the data access pattern of each workload. We were able to confirm that the visualized results are reasonably accurate by manually comparing those with the source code of the workloads.
To see the usefulness of the monitoring, we optimized 9 memory intensive workloads among them for memory pressure situations using the DAMON outputs. In detail, we identified frequently accessed memory regions in each workload based on the DAMON results and protected them with ``mlock()`` system calls. The optimized versions consistently show speedup (2.55x in best case, 1.65x in average) under memory pressure situation.
Overhead
--------
We also measured the overhead of DAMON. It was not only under the upperbound we set, but was much lower (0.6 percent of the bound in best case, 13.288 percent of the bound in average). This reduction of the overhead is mainly resulted from the adaptive regions adjustment. We also compared the overhead with that of the straightforward periodic Accessed bit check-based monitoring, which checks the access of every page frame. DAMON's overhead was much smaller than the straightforward mechanism by 94,242.42x in best case, 3,159.61x in average.
References
==========
Prototypes of DAMON have introduced by an LPC kernel summit track talk[1] and two academic papers[2,3]. Please refer to those for more detailed information, especially the evaluations.
[1] SeongJae Park, Tracing Data Access Pattern with Bounded Overhead and Best-effort Accuracy. In The Linux Kernel Summit, September 2019.
https://linuxplumbersconf.org/event/4/contributions/548/
[2] SeongJae Park, Yunjae Lee, Heon Y. Yeom, Profiling Dynamic Data Access Patterns with Controlled Overhead and Quality. In 20th ACM/IFIP International Middleware Conference Industry, December 2019.
https://dl.acm.org/doi/10.1145/3366626.3368125
[3] SeongJae Park, Yunjae Lee, Yunhee Kim, Heon Y. Yeom, Profiling Dynamic Data Access Patterns with Bounded Overhead and Accuracy. In IEEE International Workshop on Foundations and Applications of Self- Systems (FAS 2019), June 2019.
SeongJae Park (5):
mm: Introduce Data Access MONitor (DAMON) mm/damon: Add debugfs interface
mm/damon: Add minimal user-space tools Documentation/admin-guide/mm: Add a document for DAMON mm/damon: Add kunit tests
.../admin-guide/mm/data_access_monitor.rst | 235 +++ Documentation/admin-guide/mm/index.rst | 1 + mm/Kconfig | 23 + mm/Makefile | 1 + mm/damon-test.h | 571 ++++++++ mm/damon.c | 1266 +++++++++++++++++ tools/damon/bin2txt.py | 64 + tools/damon/damn | 36 + tools/damon/heats.py | 358 +++++ tools/damon/nr_regions.py | 116 ++ tools/damon/record.py | 182 +++ tools/damon/report.py | 45 + tools/damon/wss.py | 121 ++ 13 files changed, 3019 insertions(+) create mode 100644 Documentation/admin-guide/mm/data_access_monitor.rst create mode 100644 mm/damon-test.h create mode 100644 mm/damon.c create mode 100644 tools/damon/bin2txt.py create mode 100644 tools/damon/damn create mode 100644 tools/damon/heats.py create mode 100644 tools/damon/nr_regions.py create mode 100644 tools/damon/record.py create mode 100644 tools/damon/report.py create mode 100644 tools/damon/wss.py
Signature · 1 line
2.17.1
RFC PATCH 1/5 mm: Introduce Data Access MONitor (DAMON)
From: SeongJae Park <[email protected]>
This commit introduces the main logic of DAMON. Because this commit is for the core logic only, it lacks an external interface to run DAMON. Following commit will add the interface.
----
DAMON is a kernel module that allows users to monitor the actual memory access pattern of specific user-space processes. It aims to be 1) accurate enough to be useful for performance-centric domains, and 2) sufficiently light-weight so that it can be applied online.
For the goals, DAMON utilizes its two core mechanisms, called region-based sampling and adaptive regions adjustment. The region-based sampling allows users to make their own trade-off between the quality and the overhead of the monitoring and set the upperbound of the monitoring overhead. Further, the adaptive regions adjustment mechanism makes DAMON to maximize the quality and minimize the overhead with its best efforts while preserving the users configured trade-off.
Expected Use-cases
==================
A straightforward usecase of DAMON would be the program behavior analysis. With the DAMON output, users can confirm whether the program is running as intended or not. This will be useful for debuggings and tests of design points.
The monitored results can also be useful for counting the dynamic working set size of workloads. For the administration of memory overcommitted systems or selection of the environments (e.g., containers providing different amount of memory) for your workloads, this will be useful.
If you are a programmer, you can optimize your program by managing the memory based on the actual data access pattern. For example, you can identify the dynamic hotness of your data using DAMON and call ``mlock()`` to keep your hot data in DRAM, or call ``madvise()`` with ``MADV_PAGEOUT`` to proactively reclaim cold data. Even though your program is guaranteed to not encounter memory pressure, you can still improve the performance by applying the DAMON outputs for call of ``MADV_HUGEPAGE`` and ``MADV_NOHUGEPAGE``. More creative optimizations would be possible. Our evaluations of DAMON includes a straightforward optimization using the ``mlock()``. Please refer to the below Evaluation section for more detail.
As DAMON incurs very low overhead, such optimizations can be applied not only offline, but also online. Also, there is no reason to limit such optimizations to the user space. Several parts of the kernel's memory management mechanisms could be also optimized using DAMON. The reclamation, the THP (de)promotion decisions, and the compaction would be such a candidates. Nevertheless, current version of DAMON is not highly optimized for the online/in-kernel uses.
Mechanisms of DAMON
===================
Basic Access Check
------------------
DAMON basically reports what pages are how frequently accessed. The report is passed to users in binary format via a ``result file`` which users can set it's path. Note that the frequency is not an absolute number of accesses, but a relative frequency among the pages of the target workloads.
Users can also control the resolution of the reports by setting two time intervals, ``sampling interval`` and ``aggregation interval``. In detail, DAMON checks access to each page per ``sampling interval``, aggregates the results (counts the number of the accesses to each page), and reports the aggregated results per ``aggregation interval``. For the access check of each page, DAMON uses the Accessed bits of PTEs.
This is thus similar to the previously mentioned periodic access checks based mechanisms, which overhead is increasing as the size of the target process grows.
Region Based Sampling
---------------------
To avoid the unbounded increase of the overhead, DAMON groups a number of adjacent pages that assumed to have same access frequencies into a region. As long as the assumption (pages in a region have same access frequencies) is kept, only one page in the region is required to be checked. Thus, for each ``sampling interval``, DAMON randomly picks one page in each region and clears its Accessed bit. After one more ``sampling interval``, DAMON reads the Accessed bit of the page and increases the access frequency of the region if the bit has set meanwhile. Therefore, the monitoring overhead is controllable by setting the number of regions. DAMON allows users to set the minimal and maximum number of regions for the trade-off.
Except the assumption, this is almost same with the above-mentioned miniature-like static region based sampling. In other words, this scheme cannot preserve the quality of the output if the assumption is not guaranteed.
Adaptive Regions Adjustment
---------------------------
At the beginning of the monitoring, DAMON constructs the initial regions by evenly splitting the memory mapped address space of the process into the user-specified minimal number of regions. In this initial state, the assumption is normally not kept and thus the quality could be low. To keep the assumption as much as possible, DAMON adaptively merges and splits each region. For each ``aggregation interval``, it compares the access frequencies of adjacent regions and merges those if the frequency difference is small. Then, after it reports and clears the aggregated access frequency of each region, it splits each region into two regions if the total number of regions is smaller than the half of the user-specified maximum number of regions.
In this way, DAMON provides its best-effort quality and minimal overhead while keeping the bounds users set for their trade-off.
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 a user-specified time interval (``regions update interval``).
--- mm/Kconfig | 12 + mm/Makefile | 1 + mm/damon.c | 1037 +++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 1050 insertions(+) create mode 100644 mm/damon.c
mm/Kconfig +12 -0
@@ -736,4 +736,16 @@ config ARCH_HAS_PTE_SPECIAL config ARCH_HAS_HUGEPD bool +config DAMON + bool "Data Access Monitor" + depends on MMU + default y + help + Provides data access monitoring. + + DAMON is a kernel module that allows users to monitor the actual + memory access pattern of specific user-space processes. It aims to + be 1) accurate enough to be useful for performance-centric domains, + and 2) sufficiently light-weight so that it can be applied online. + endmenu
mm/Makefile +1 -0
@@ -107,3 +107,4 @@ obj-$(CONFIG_PERCPU_STATS) += percpu-stats.o obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_HMM_MIRROR) += hmm.o obj-$(CONFIG_MEMFD_CREATE) += memfd.o +obj-$(CONFIG_DAMON) += damon.o
mm/damon.c new file +1037 -0
1,037 lines not on this page · raw message
Signature · 1 line
2.17.1
RFC PATCH 2/5 mm/damon: Add debugfs interface
In reply to SeongJae ParkFrom: SeongJae Park <[email protected]>
This commit adds a debugfs interface for DAMON.
DAMON exports three files, ``attrs``, ``pids``, and ``monitor_on`` under its debugfs directory, ``<debugfs>/damon/``.
Attributes
----------
Users can read and write the ``sampling interval``, ``aggregation interval``, ``regions update interval``, min/max number of regions, and the path to ``result file`` 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 ``/damon.data`` and check it again::
# cd <debugfs>/damon
# echo 5000 100000 1000000 10 1000 /damon.data > attrs
# cat attrs
5000 100000 1000000 10 1000 /damon.dataTarget 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 4242Note that setting the pids doesn't starts the monitoring.
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
offPlease 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.
--- mm/damon.c | 229 ++++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 228 insertions(+), 1 deletion(-)
mm/damon.c +228 -1
@@ -9,6 +9,7 @@#define pr_fmt (fmt) "damon: " fmt +#include <linux/debugfs.h> #include <linux/delay.h> #include <linux/kthread.h> #include <linux/mm.h>
@@ -1023,6 +1024,232 @@ static long damon_set_attrs(unsigned long sample_int,return 0 ; } +/* +* debugfs functions +*/ + +static ssize_t debugfs_monitor_on_read (struct file *file, +char __user *buf,size_t count,loff_t *ppos) +{ +char monitor_on_buf[5 ]; +bool monitor_on; + +spin_lock (&kdamond_lock); + monitor_on = kdamond !=NULL ; +spin_unlock (&kdamond_lock); + +snprintf (monitor_on_buf,5 , monitor_on ?"on\n" :"off\n" ); + +return simple_read_from_buffer (buf, count, ppos, monitor_on_buf, + monitor_on ?3 :4 ); +} + +static ssize_t debugfs_monitor_on_write (struct file *file, +const char __user *buf,size_t count,loff_t *ppos) +{ +ssize_t ret; +bool on = false; +char cmdbuf[5 ]; + + ret =simple_write_to_buffer (cmdbuf,5 , ppos, buf, count); +if (ret <0 ) +return ret; + +if (sscanf (cmdbuf,"%s" , cmdbuf) !=1 ) +return -EINVAL ; +if (!strncmp (cmdbuf,"on" ,5 )) + on = true; +else if (!strncmp (cmdbuf,"off" ,5 )) + on = false; +else +return -EINVAL ; + +if (damon_turn_kdamond (on)) +return -EINVAL ; + +return ret; +} + +static ssize_t damon_sprint_pids (char *buf,ssize_t len) +{ +char *cursor = buf; +struct damon_task *t; + +damon_for_each_task (t) { +snprintf (cursor, len,"%lu " , t->pid); + cursor +=strnlen (cursor, len); + } +if (cursor != buf) + cursor--; +snprintf (cursor, len,"\n" ); +return strnlen (buf, len); +} + +static ssize_t debugfs_pids_read (struct file *file, +char __user *buf,size_t count,loff_t *ppos) +{ +ssize_t len; +char pids_buf[512 ]; + + len =damon_sprint_pids (pids_buf,512 ); + +return simple_read_from_buffer (buf, count, ppos, pids_buf, len); +} + +/* +* Converts a string into an array of unsigned long integers +* +* Returns an array of unsigned long integers that converted, or NULL if the +* input is wrong. +*/ +static unsigned long *str_to_pids (const char *str,ssize_t len, +ssize_t *nr_pids) +{ +unsigned long *pids; +unsigned long pid; +int pos =0 , parsed, ret; + + *nr_pids =0 ; + pids =kmalloc_array (256 ,sizeof (unsigned long ),GFP_KERNEL ); +while (*nr_pids <256 && pos < len) { + ret =sscanf (&str[pos],"%lu%n" , &pid, &parsed); + pos += parsed; +if (ret !=1 ) +break ; + pids[*nr_pids] = pid; + *nr_pids +=1 ; + } +if (*nr_pids ==0 ) { +kfree (pids); + pids =NULL ; + } + +return pids; +} + +static ssize_t debugfs_pids_write (struct file *file, +const char __user *buf,size_t count,loff_t *ppos) +{ +ssize_t ret; +unsigned long *targets; +ssize_t nr_targets; +char pids_buf[512 ]; + + ret =simple_write_to_buffer (pids_buf,512 , ppos, buf, count); +if (ret <0 ) +return ret; + + targets =str_to_pids (pids_buf, ret, &nr_targets); + +spin_lock (&kdamond_lock); +if (kdamond) + goto monitor_running; + +damon_set_pids (targets, nr_targets); +spin_unlock (&kdamond_lock); +kfree (targets); + +return ret; + +monitor_running: +spin_unlock (&kdamond_lock); +pr_err ("%s: kdamond is running. Turn it off first.\n" , __func__); +return -EINVAL ; +} + +static ssize_t debugfs_attrs_read (struct file *file, +char __user *buf,size_t count,loff_t *ppos) +{ +char attrs_buf[512 ]; + +snprintf (attrs_buf,512 ,"%lu %lu %lu %lu %lu %s\n" , + sample_interval, aggr_interval, + regions_update_interval, min_nr_regions, + max_nr_regions, rfile_path); + +return simple_read_from_buffer (buf, count, ppos, attrs_buf, +strnlen (attrs_buf,512 )); +} + +static ssize_t debugfs_attrs_write (struct file *file, +const char __user *buf,size_t count,loff_t *ppos) +{ +unsigned long s, a, r, minr, maxr; +char attrs_buf[512 ]; +char res_file_path[LEN_RES_FILE_PATH ]; +ssize_t ret; + +if (count >512 ) { +pr_err ("attributes stream is too large: %s\n" , buf); +return -ENOMEM ; + } + + ret =simple_write_to_buffer (attrs_buf,512 , ppos, buf, count); +if (ret <0 ) +return ret; + +if (sscanf (attrs_buf,"%lu %lu %lu %lu %lu %s" , + &s, &a, &r, &minr, &maxr, res_file_path) !=6 ) +return -EINVAL ; + +spin_lock (&kdamond_lock); +if (kdamond) + goto monitor_running; + +damon_set_attrs (s, a, r, minr, maxr, res_file_path); +spin_unlock (&kdamond_lock); + +return ret; + +monitor_running: +spin_unlock (&kdamond_lock); +pr_err ("%s: kdamond is running. Turn it off first.\n" , __func__); +return -EINVAL ; +} + +static const struct file_operations monitor_on_fops = { + .owner =THIS_MODULE , + .read = debugfs_monitor_on_read, + .write = debugfs_monitor_on_write, +}; + +static const struct file_operations pids_fops = { + .owner =THIS_MODULE , + .read = debugfs_pids_read, + .write = debugfs_pids_write, +}; + +static const struct file_operations attrs_fops = { + .owner =THIS_MODULE , + .read = debugfs_attrs_read, + .write = debugfs_attrs_write, +}; + +static int __init debugfs_init (void ) +{ +struct dentry *debugfs_root; +const char *const file_names[] = {"attrs" ,"pids" ,"monitor_on" }; +const struct file_operations *fops[] = {&attrs_fops, &pids_fops, + &monitor_on_fops}; +int i; + + debugfs_root =debugfs_create_dir ("damon" ,NULL ); +if (!debugfs_root) { +pr_err ("failed to create the debugfs dir\n" ); +return -ENOMEM ; + } + +for (i =0 ; i <ARRAY_SIZE (file_names); i++) { +if (!debugfs_create_file (file_names[i],0600 , debugfs_root, +NULL , fops[i])) { +pr_err ("failed to create %s file\n" , file_names[i]); +return -ENOMEM ; + } + } + +return 0 ; +} +static int __init damon_init (void ) {pr_info ("init\n" );
@@ -1031,7 +1258,7 @@ static int __init damon_init(void)ktime_get_coarse_ts64 (&last_aggregate_time); last_regions_update_time = last_aggregate_time; -return 0 ; +return debugfs_init (); }module_init (damon_init);
Signature · 1 line
2.17.1
RFC PATCH 3/5 mm/damon: Add minimal user-space tools
In reply to SeongJae ParkFrom: SeongJae Park <[email protected]>
This commit adds a shallow wrapper python script, ``/tools/damon/damn`` that provides more convenient interface for the user space. Note that it is only aimed to be used for minimal reference of the DAMON's raw interfaces and for debuggings of DAMON itself.
Quick Tutorial
--------------
To test DAMON on your system,
1. Ensure your kernel is built with CONFIG_DAMON turned on, and debugfs is mounted at ``/sys/kernel/debug/``.
2. ``<your kernel source tree>/tools/damon/damn -h``
--- tools/damon/bin2txt.py | 64 +++++++ tools/damon/damn | 36 ++++ tools/damon/heats.py | 358 ++++++++++++++++++++++++++++++++++++++ tools/damon/nr_regions.py | 116 ++++++++++++ tools/damon/record.py | 182 +++++++++++++++++++ tools/damon/report.py | 45 +++++ tools/damon/wss.py | 121 +++++++++++++ 7 files changed, 922 insertions(+) create mode 100644 tools/damon/bin2txt.py create mode 100644 tools/damon/damn create mode 100644 tools/damon/heats.py create mode 100644 tools/damon/nr_regions.py create mode 100644 tools/damon/record.py create mode 100644 tools/damon/report.py create mode 100644 tools/damon/wss.py
tools/damon/bin2txt.py new file +64 -0
@@ -0,0 +1,64 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import argparse +import os +import struct +import sys + +def parse_time(bindat): + "bindat should be 16 bytes" + sec = struct.unpack('l', bindat[0:8])[0] + nsec = struct.unpack('l', bindat[8:16])[0] + return sec * 1000000000 + nsec; + +def pr_region(f): + saddr = struct.unpack('L', f.read(8))[0] + eaddr = struct.unpack('L', f.read(8))[0] + nr_accesses = struct.unpack('I', f.read(4))[0] + print("%012x-%012x(%10d):\t%d" % + (saddr, eaddr, eaddr - saddr, nr_accesses)) + +def pr_task_info(f): + pid = struct.unpack('L', f.read(8))[0] + print("pid: ", pid) + nr_regions = struct.unpack('I', f.read(4))[0] + print("nr_regions: ", nr_regions) + for r in range(nr_regions): + pr_region(f) + +def set_argparser(parser): + parser.add_argument('--input', '-i', type=str, metavar='<file>', + default='damon.data', help='input file name') + +def main(args=None): + if not args: + parser = argparse.ArgumentParser() + set_argparser(parser) + args = parser.parse_args() + + file_path = args.input + + if not os.path.isfile(file_path): + print('input file (%s) is not exist' % file_path) + exit(1) + + with open(file_path, 'rb') as f: + start_time = None + while True: + timebin = f.read(16) + if len(timebin) != 16: + break + time = parse_time(timebin) + if not start_time: + start_time = time + print("start_time: ", start_time) + print("rel time: %16d" % (time - start_time)) + nr_tasks = struct.unpack('I', f.read(4))[0] + print("nr_tasks: ", nr_tasks) + for t in range(nr_tasks): + pr_task_info(f) + print("") + +if __name__ == '__main__': + main()
tools/damon/damn new file +36 -0
@@ -0,0 +1,36 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +import argparse + +import record +import report + +class SubCmdHelpFormatter(argparse.RawDescriptionHelpFormatter): + def _format_action(self, action): + parts = super(argparse.RawDescriptionHelpFormatter, + self)._format_action(action) + # skip sub parsers help + if action.nargs == argparse.PARSER: + parts = '\n'.join(parts.split('\n')[1:]) + return parts + +parser = argparse.ArgumentParser(formatter_class=SubCmdHelpFormatter) + +subparser = parser.add_subparsers(title='command', dest='command', + metavar='<command>') +subparser.required = True + +parser_record = subparser.add_parser('record', help='record data accesses') +record.set_argparser(parser_record) + +parser_report = subparser.add_parser('report', + help='report the recorded data accesses') +report.set_argparser(parser_report) + +args = parser.parse_args() + +if args.command == 'record': + record.main(args) +elif args.command == 'report': + report.main(args)
tools/damon/heats.py new file +358 -0
358 lines not on this page · raw message
tools/damon/nr_regions.py new file +116 -0
116 lines not on this page · raw message
tools/damon/record.py new file +182 -0
182 lines not on this page · raw message
tools/damon/report.py new file +45 -0
45 lines not on this page · raw message
tools/damon/wss.py new file +121 -0
121 lines not on this page · raw message
Signature · 1 line
2.17.1
RFC PATCH 4/5 Documentation/admin-guide/mm: Add a document for DAMON
In reply to SeongJae ParkFrom: SeongJae Park <[email protected]>
This commit adds a simple document for DAMON under 'Documentation/admin-guide/mm/'.
--- .../admin-guide/mm/data_access_monitor.rst | 235 ++++++++++++++++++ Documentation/admin-guide/mm/index.rst | 1 + 2 files changed, 236 insertions(+) create mode 100644 Documentation/admin-guide/mm/data_access_monitor.rst
Documentation/admin-guide/mm/data_access_monitor.rst new file +235 -0
@@ -0,0 +1,235 @@ +.. _data_access_monitor: + +========================== +DAMON: Data Access MONitor +========================== + + +Too Long; Don't Read +==================== + +DAMON is a kernel module that allows users to monitor the actual memory access +pattern of specific user-space processes. It aims to be 1) accurate enough to +be useful for performance-centric domains, and 2) sufficiently light-weight so +that it can be applied online. + +For the goals, DAMON utilizes its two core mechanisms, called region-based +sampling and adaptive regions adjustment. The region-based sampling allows +users to make their own trade-off between the quality and the overhead of the +monitoring and set the upperbound of the monitoring overhead. Further, the +adaptive regions adjustment mechanism makes DAMON to maximize the quality and +minimize the overhead with its best efforts while preserving the users +configured trade-off. + + +Background +========== + +For performance-centric analysis and optimizations of memory management schemes +(either that of kernel space or user space), the actual data access pattern of +the workloads is highly useful. The information need to be only reasonable +rather than strictly correct, because some level of incorrectness can be +handled in many performance-centric domains. It also need to be taken within +reasonably short time with only light-weight overhead. + +Manually extracting such data is not easy and time consuming if the target +workload is huge and complex, even for the developers of the programs. There +are a range of tools and techniques developed for general memory access +investigations, and some of those could be partially used for this purpose. +However, most of those are not practical or unscalable, mainly because those +are designed with no consideration about the trade-off between the accuracy of +the output and the overhead. + +The memory access instrumentation techniques which is applied to many tools +such as Intel PIN is essential for correctness required cases such as invalid +memory access bug detections. However, those usually incur high overhead which +is unacceptable for many of the performance-centric domains. Periodic access +checks based on H/W or S/W access counting features (e.g., the Accessed bits of +PTEs or the PG_Idle flags of pages) can dramatically decrease the overhead by +forgiving some of the quality, compared to the instrumentation based +techniques. The reduced quality is still reasonable for many of the domains, +but the overhead can arbitrarily increase as the size of the target workload +grows. Miniature-like static region based sampling can set the upperbound of +the overhead, but it will now decrease the quality of the output as the size of +the workload grows. + + +Expected Use-cases +================== + +A straightforward usecase of DAMON would be the program behavior analysis. +With the DAMON output, users can confirm whether the program is running as +intended or not. This will be useful for debuggings and tests of design +points. + +The monitored results can also be useful for counting the dynamic working set +size of workloads. For the administration of memory overcommitted systems or +selection of the environments (e.g., containers providing different amount of +memory) for your workloads, this will be useful. + +If you are a programmer, you can optimize your program by managing the memory +based on the actual data access pattern. For example, you can identify the +dynamic hotness of your data using DAMON and call ``mlock()`` to keep your hot +data in DRAM, or call ``madvise()`` with ``MADV_PAGEOUT`` to proactively +reclaim cold data. Even though your program is guaranteed to not encounter +memory pressure, you can still improve the performance by applying the DAMON +outputs for call of ``MADV_HUGEPAGE`` and ``MADV_NOHUGEPAGE``. More creative +optimizations would be possible. Our evaluations of DAMON includes a +straightforward optimization using the ``mlock()``. Please refer to the below +Evaluation section for more detail. + +As DAMON incurs very low overhead, such optimizations can be applied not only +offline, but also online. Also, there is no reason to limit such optimizations +to the user space. Several parts of the kernel's memory management mechanisms +could be also optimized using DAMON. The reclamation, the THP (de)promotion +decisions, and the compaction would be such a candidates. + + +Mechanisms of DAMON +=================== + + +Basic Access Check +------------------ + +DAMON basically reports what pages are how frequently accessed. The report is +passed to users in binary format via a ``result file`` which users can set it's +path. Note that the frequency is not an absolute number of accesses, but a +relative frequency among the pages of the target workloads. + +Users can also control the resolution of the reports by setting two time +intervals, ``sampling interval`` and ``aggregation interval``. In detail, +DAMON checks access to each page per ``sampling interval``, aggregates the +results (counts the number of the accesses to each page), and reports the +aggregated results per ``aggregation interval``. For the access check of each +page, DAMON uses the Accessed bits of PTEs. + +This is thus similar to the previously mentioned periodic access checks based +mechanisms, which overhead is increasing as the size of the target process +grows. + + +Region Based Sampling +--------------------- + +To avoid the unbounded increase of the overhead, DAMON groups a number of +adjacent pages that assumed to have same access frequencies into a region. As +long as the assumption (pages in a region have same access frequencies) is +kept, only one page in the region is required to be checked. Thus, for each +``sampling interval``, DAMON randomly picks one page in each region and clears +its Accessed bit. After one more ``sampling interval``, DAMON reads the +Accessed bit of the page and increases the access frequency of the region if +the bit has set meanwhile. Therefore, the monitoring overhead is controllable +by setting the number of regions. DAMON allows users to set the minimal and +maximum number of regions for the trade-off. + +Except the assumption, this is almost same with the above-mentioned +miniature-like static region based sampling. In other words, this scheme +cannot preserve the quality of the output if the assumption is not guaranteed. + + +Adaptive Regions Adjustment +--------------------------- + +At the beginning of the monitoring, DAMON constructs the initial regions by +evenly splitting the memory mapped address space of the process into the +user-specified minimal number of regions. In this initial state, the +assumption is normally not kept and thus the quality could be low. To keep the +assumption as much as possible, DAMON adaptively merges and splits each region. +For each ``aggregation interval``, it compares the access frequencies of +adjacent regions and merges those if the frequency difference is small. Then, +after it reports and clears the aggregated access frequency of each region, it +splits each region into two regions if the total number of regions is smaller +than the half of the user-specified maximum number of regions. + +In this way, DAMON provides its best-effort quality and minimal overhead while +keeping the bounds users set for their trade-off. + + +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``). + + +User Interface +============== + +DAMON exports three files, ``attrs``, ``pids``, and ``monitor_on`` under its +debugfs directory, ``<debugfs>/damon/``. + + +Attributes +---------- + +Users can read and write the ``sampling interval``, ``aggregation interval``, +``regions update interval``, min/max number of regions, and the path to +``result file`` 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 ``/damon.data`` and check it again:: + + # cd <debugfs>/damon + # echo 5000 100000 1000000 10 1000 /damon.data > attrs + # cat attrs + 5000 100000 1000000 10 1000 /damon.data + + +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. + + +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. + + +User Space Wrapper +------------------ + +DAMON has a shallow wrapper python script, ``/tools/damon/damn`` that provides +more convenient interface. Note that it is only aimed to be used for minimal +reference of the DAMON's raw interfaces and for debugging of the DAMON itself. +Based on the debugfs interface, you can create another cool and more convenient +user space tools. + + +Quick Tutorial +-------------- + +To test DAMON on your system, + +1. Ensure your kernel is built with CONFIG_DAMON turned on, and debugfs is + mounted at ``/sys/kernel/debug/``. +2. ``<your kernel source tree>/tools/damon/damn -h``
Documentation/admin-guide/mm/index.rst +1 -0
@@ -27,6 +27,7 @@ the Linux memory management. concepts cma_debugfs + data_access_monitor hugetlbpage idle_page_tracking ksm
Signature · 1 line
2.17.1
Re: [RFC PATCH 4/5] Documentation/admin-guide/mm: Add a document for DAMON
Quoted 244 lines · SeongJae Park
From: SeongJae Park <[email protected]>
This commit adds a simple document for DAMON under '
Documentation/admin-guide/mm/'.Signed-off-by SeongJae Park <[email protected]>--- .../admin-guide/mm/data_access_monitor.rst | 235 ++++++++++++++++++ Documentation/admin-guide/mm/index.rst | 1 + 2 files changed, 236 insertions(+) create mode 100644 Documentation/admin-guide/mm/data_access_monitor.rstDocumentation/admin-guide/mm/data_access_monitor.rst new file +225
-0@@ -0,0 +1,235 @@ +.. _data_access_monitor: + +========================== +DAMON: Data Access MONitor +========================== + + +Too Long; Don't Read +==================== + +DAMON is a kernel module that allows users to monitor the actual memory access +pattern of specific user-space processes. It aims to be 1) accurate enough to +be useful for performance-centric domains, and 2) sufficiently light-weight so +that it can be applied online. + +For the goals, DAMON utilizes its two core mechanisms, called region-based +sampling and adaptive regions adjustment. The region-based sampling allows +users to make their own trade-off between the quality and the overhead of the +monitoring and set the upperbound of the monitoring overhead. Further, the +adaptive regions adjustment mechanism makes DAMON to maximize the quality and +minimize the overhead with its best efforts while preserving the users +configured trade-off. + + +Background +========== + +For performance-centric analysis and optimizations of memory management schemes +(either that of kernel space or user space), the actual data access pattern of +the workloads is highly useful. The information need to be only reasonable +rather than strictly correct, because some level of incorrectness can be +handled in many performance-centric domains. It also need to be taken within +reasonably short time with only light-weight overhead. + +Manually extracting such data is not easy and time consuming if the target +workload is huge and complex, even for the developers of the programs. There +are a range of tools and techniques developed for general memory access +investigations, and some of those could be partially used for this purpose. +However, most of those are not practical or unscalable, mainly because those +are designed with no consideration about the trade-off between the accuracy of +the output and the overhead. + +The memory access instrumentation techniques which is applied to many tools +such as Intel PIN is essential for correctness required cases such as invalid +memory access bug detections. However, those usually incur high overhead which +is unacceptable for many of the performance-centric domains. Periodic access +checks based on H/W or S/W access counting features (e.g., the Accessed bits of +PTEs or the PG_Idle flags of pages) can dramatically decrease the overhead by +forgiving some of the quality, compared to the instrumentation based +techniques. The reduced quality is still reasonable for many of the domains, +but the overhead can arbitrarily increase as the size of the target workload +grows. Miniature-like static region based sampling can set the upperbound of +the overhead, but it will now decrease the quality of the output as the size of +the workload grows. + + +Expected Use-cases +================== + +A straightforward usecase of DAMON would be the program behavior analysis. +With the DAMON output, users can confirm whether the program is running as +intended or not. This will be useful for debuggings and tests of design +points. + +The monitored results can also be useful for counting the dynamic working set +size of workloads. For the administration of memory overcommitted systems or +selection of the environments (e.g., containers providing different amount of +memory) for your workloads, this will be useful. + +If you are a programmer, you can optimize your program by managing the memory +based on the actual data access pattern. For example, you can identify the +dynamic hotness of your data using DAMON and call ``mlock()`` to keep your hot +data in DRAM, or call ``madvise()`` with ``MADV_PAGEOUT`` to proactively +reclaim cold data. Even though your program is guaranteed to not encounter +memory pressure, you can still improve the performance by applying the DAMON +outputs for call of ``MADV_HUGEPAGE`` and ``MADV_NOHUGEPAGE``. More creative +optimizations would be possible. Our evaluations of DAMON includes a +straightforward optimization using the ``mlock()``. Please refer to the below +Evaluation section for more detail. + +As DAMON incurs very low overhead, such optimizations can be applied not only +offline, but also online. Also, there is no reason to limit such optimizations +to the user space. Several parts of the kernel's memory management mechanisms +could be also optimized using DAMON. The reclamation, the THP (de)promotion +decisions, and the compaction would be such a candidates. + + +Mechanisms of DAMON +=================== + + +Basic Access Check +------------------ + +DAMON basically reports what pages are how frequently accessed. The report is +passed to users in binary format via a ``result file`` which users can set it's +path. Note that the frequency is not an absolute number of accesses, but a +relative frequency among the pages of the target workloads. + +Users can also control the resolution of the reports by setting two time +intervals, ``sampling interval`` and ``aggregation interval``. In detail, +DAMON checks access to each page per ``sampling interval``, aggregates the +results (counts the number of the accesses to each page), and reports the +aggregated results per ``aggregation interval``. For the access check of each +page, DAMON uses the Accessed bits of PTEs. + +This is thus similar to the previously mentioned periodic access checks based +mechanisms, which overhead is increasing as the size of the target process +grows. + + +Region Based Sampling +--------------------- + +To avoid the unbounded increase of the overhead, DAMON groups a number of +adjacent pages that assumed to have same access frequencies into a region. As +long as the assumption (pages in a region have same access frequencies) is +kept, only one page in the region is required to be checked. Thus, for each +``sampling interval``, DAMON randomly picks one page in each region and clears +its Accessed bit. After one more ``sampling interval``, DAMON reads the +Accessed bit of the page and increases the access frequency of the region if +the bit has set meanwhile. Therefore, the monitoring overhead is controllable +by setting the number of regions. DAMON allows users to set the minimal and +maximum number of regions for the trade-off. + +Except the assumption, this is almost same with the above-mentioned +miniature-like static region based sampling. In other words, this scheme +cannot preserve the quality of the output if the assumption is not guaranteed. + + +Adaptive Regions Adjustment +--------------------------- + +At the beginning of the monitoring, DAMON constructs the initial regions by +evenly splitting the memory mapped address space of the process into the +user-specified minimal number of regions. In this initial state, the +assumption is normally not kept and thus the quality could be low. To keep the +assumption as much as possible, DAMON adaptively merges and splits each region. +For each ``aggregation interval``, it compares the access frequencies of +adjacent regions and merges those if the frequency difference is small. Then, +after it reports and clears the aggregated access frequency of each region, it +splits each region into two regions if the total number of regions is smaller +than the half of the user-specified maximum number of regions. + +In this way, DAMON provides its best-effort quality and minimal overhead while +keeping the bounds users set for their trade-off. + + +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``). + + +User Interface +============== + +DAMON exports three files, ``attrs``, ``pids``, and ``monitor_on`` under its +debugfs directory, ``<debugfs>/damon/``. + + +Attributes +---------- + +Users can read and write the ``sampling interval``, ``aggregation interval``, +``regions update interval``, min/max number of regions, and the path to +``result file`` 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 ``/damon.data`` and check it again:: + + # cd <debugfs>/damon + # echo 5000 100000 1000000 10 1000 /damon.data > attrs + # cat attrs + 5000 100000 1000000 10 1000 /damon.data + + +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. + + +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. + + +User Space Wrapper +------------------ + +DAMON has a shallow wrapper python script, ``/tools/damon/damn`` that provides +more convenient interface. Note that it is only aimed to be used for minimal +reference of the DAMON's raw interfaces and for debugging of the DAMON itself. +Based on the debugfs interface, you can create another cool and more convenient +user space tools.
Documentation/admin-guide/mm/data_access_monitor.rst line 235
Quoted 10 lines
Documentation/admin-guide/mm/data_access_monitor.rst new file +10
-0+ + +Quick Tutorial +-------------- + +To test DAMON on your system, + +1. Ensure your kernel is built with CONFIG_DAMON turned on, and debugfs is + mounted at ``/sys/kernel/debug/``. +2. ``<your kernel source tree>/tools/damon/damn -h``
I think it would be helpful for the reader to provide an example of what they should expect to see here.
Quoted 15 lines
Documentation/admin-guide/mm/index.rst +1
-1@@ -27,6 +27,7 @@ the Linux memory management. concepts cma_debugfs + data_access_monitor hugetlbpage idle_page_tracking ksm --2.17.1
Re: Re: [RFC PATCH 4/5] Documentation/admin-guide/mm: Add a document for DAMON
Quoted 27 lines · On Thu, 23 Jan 2020 13:17:04 -0800 Brendan Higgins <[email protected]>…
Quoted 26 lines · SeongJae Park
From: SeongJae Park <[email protected]>
This commit adds a simple document for DAMON under '
Documentation/admin-guide/mm/'.Signed-off-by SeongJae Park <[email protected]>--- .../admin-guide/mm/data_access_monitor.rst | 235 ++++++++++++++++++ Documentation/admin-guide/mm/index.rst | 1 + 2 files changed, 236 insertions(+) create mode 100644 Documentation/admin-guide/mm/data_access_monitor.rstDocumentation/admin-guide/mm/data_access_monitor.rst new file +7
-0@@ -0,0 +1,235 @@ +.. _data_access_monitor: + +========================== +DAMON: Data Access MONitor +========================== + +
[...]
Quoted 4 lines
Quoted 4 lines
Documentation/admin-guide/mm/data_access_monitor.rst new file +4
-0+ +Quick Tutorial +-------------- +
Quoted 8 lines
Documentation/admin-guide/mm/data_access_monitor.rst line 235
Quoted 5 lines
Documentation/admin-guide/mm/data_access_monitor.rst new file +5
-0+To test DAMON on your system, + +1. Ensure your kernel is built with CONFIG_DAMON turned on, and debugfs is + mounted at ``/sys/kernel/debug/``. +2. ``<your kernel source tree>/tools/damon/damn -h``I think it would be helpful for the reader to provide an example of what they should expect to see here.
Totally agreed.
Will apply your suggestion by next spin.
Thanks,
SeongJae Park
Quoted 16 lines
Quoted 16 lines
Documentation/admin-guide/mm/index.rst +1
-1@@ -27,6 +27,7 @@ the Linux memory management. concepts cma_debugfs + data_access_monitor hugetlbpage idle_page_tracking ksm --2.17.1
RFC PATCH 5/5 mm/damon: Add kunit tests
In reply to SeongJae ParkFrom: SeongJae Park <[email protected]>
This commit adds kunit based unit tests for DAMON.
--- mm/Kconfig | 11 + mm/damon-test.h | 571 ++++++++++++++++++++++++++++++++++++++++++++++++ mm/damon.c | 2 + 3 files changed, 584 insertions(+) create mode 100644 mm/damon-test.h
mm/Kconfig +11 -0
@@ -748,4 +748,15 @@ config DAMON be 1) accurate enough to be useful for performance-centric domains, and 2) sufficiently light-weight so that it can be applied online. +config DAMON_TEST + bool "Test for damon" + depends on DAMON && KUNIT + help + This builds the DAMON Kunit test suite. + + For more information on KUnit and unit tests in general, please refer + to the KUnit documentation. + + If unsure, say N. + endmenu
mm/damon-test.h new file +571 -0
571 lines not on this page · raw message
mm/damon.c +2 -0
@@ -1262,3 +1262,5 @@ static int __init damon_init(void) }module_init (damon_init); + +#include "damon-test.h"
Signature · 1 line
2.17.1
Re: [RFC PATCH 5/5] mm/damon: Add kunit tests
Quoted 6 lines · SeongJae Park
From: SeongJae Park <[email protected]>
This commit adds kunit based unit tests for DAMON.
Signed-off-by SeongJae Park <[email protected]>
Sorry for the late review on this: I am still getting caught up on my vacation backlog.
Quoted 12 lines
--- mm/Kconfig | 11 + mm/damon-test.h | 571 ++++++++++++++++++++++++++++++++++++++++++++++++ mm/damon.c | 2 + 3 files changed, 584 insertions(+) create mode 100644 mm/damon-test.hmm/Kconfig +0
-0
mm/Kconfig config DAMON · line 751
Quoted 4 lines
mm/Kconfig +1
-0@@ -748,4 +748,15 @@ config DAMON be 1) accurate enough to be useful for performance-centric domains, and 2) sufficiently light-weight so that it can be applied online. +config DAMON_TEST
To be consistent with other KUnit tests, this should be "DAMON_KUNIT_TEST".
Quoted 128 lines
mm/Kconfig +10
-0+ bool "Test for damon" + depends on DAMON && KUNIT + help + This builds the DAMON Kunit test suite. + + For more information on KUnit and unit tests in general, please refer + to the KUnit documentation. + + If unsure, say N. + endmenumm/damon-test.h new file +111
-0@@ -0,0 +1,571 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* +* Data Access Monitor Unit Tests +* +* Copyright 2019 Amazon.com, Inc. or its affiliates. All rights reserved. +* +* Author: SeongJae Park <[email protected]> +*/ + +#ifdef CONFIG_DAMON_TEST + +#ifndef _DAMON_TEST_H +#define _DAMON_TEST_H + +#include <kunit/test.h> + +static void damon_test_str_to_pids(struct kunit *test) +{ + char *question; + unsigned long *answers; + unsigned long expected[] = {12, 35, 46}; + ssize_t nr_integers = 0, i; + + question = "123"; + answers = str_to_pids(question, strnlen(question, 128), &nr_integers); + KUNIT_EXPECT_EQ(test, 1l, nr_integers); + KUNIT_EXPECT_EQ(test, 123ul, answers[0]); + kfree(answers); + + question = "123abc"; + answers = str_to_pids(question, strnlen(question, 128), &nr_integers); + KUNIT_EXPECT_EQ(test, 1l, nr_integers); + KUNIT_EXPECT_EQ(test, 123ul, answers[0]); + kfree(answers); + + question = "a123"; + answers = str_to_pids(question, strnlen(question, 128), &nr_integers); + KUNIT_EXPECT_EQ(test, 0l, nr_integers); + KUNIT_EXPECT_PTR_EQ(test, answers, (unsigned long *)NULL); + + question = "12 35"; + answers = str_to_pids(question, strnlen(question, 128), &nr_integers); + KUNIT_EXPECT_EQ(test, 2l, nr_integers); + for (i = 0; i < nr_integers; i++) + KUNIT_EXPECT_EQ(test, expected[i], answers[i]); + kfree(answers); + + question = "12 35 46"; + answers = str_to_pids(question, strnlen(question, 128), &nr_integers); + KUNIT_EXPECT_EQ(test, 3l, nr_integers); + for (i = 0; i < nr_integers; i++) + KUNIT_EXPECT_EQ(test, expected[i], answers[i]); + kfree(answers); + + question = "12 35 abc 46"; + answers = str_to_pids(question, strnlen(question, 128), &nr_integers); + KUNIT_EXPECT_EQ(test, 2l, nr_integers); + for (i = 0; i < 2; i++) + KUNIT_EXPECT_EQ(test, expected[i], answers[i]); + kfree(answers); + + question = ""; + answers = str_to_pids(question, strnlen(question, 128), &nr_integers); + KUNIT_EXPECT_EQ(test, 0l, nr_integers); + KUNIT_EXPECT_PTR_EQ(test, (unsigned long *)NULL, answers); + kfree(answers); + + question = "\n"; + answers = str_to_pids(question, strnlen(question, 128), &nr_integers); + KUNIT_EXPECT_EQ(test, 0l, nr_integers); + KUNIT_EXPECT_PTR_EQ(test, (unsigned long *)NULL, answers); + kfree(answers); +} + +static void damon_test_regions(struct kunit *test) +{ + struct damon_region *r; + struct damon_task *t; + + r = damon_new_region(1, 2); + KUNIT_EXPECT_EQ(test, 1ul, r->vm_start); + KUNIT_EXPECT_EQ(test, 2ul, r->vm_end); + KUNIT_EXPECT_EQ(test, 0u, r->nr_accesses); + KUNIT_EXPECT_TRUE(test, r->sampling_addr >= r->vm_start); + KUNIT_EXPECT_TRUE(test, r->sampling_addr < r->vm_end); + + t = damon_new_task(42); + KUNIT_EXPECT_EQ(test, 0u, nr_damon_regions(t)); + + damon_add_region_tail(r, t); + KUNIT_EXPECT_EQ(test, 1u, nr_damon_regions(t)); + + damon_del_region(r); + KUNIT_EXPECT_EQ(test, 0u, nr_damon_regions(t)); + + damon_free_task(t); +} + +static void damon_test_tasks(struct kunit *test) +{ + struct damon_task *t; + + t = damon_new_task(42); + KUNIT_EXPECT_EQ(test, 42ul, t->pid); + KUNIT_EXPECT_EQ(test, 0u, nr_damon_tasks()); + + damon_add_task_tail(t); + KUNIT_EXPECT_EQ(test, 1u, nr_damon_tasks()); + + damon_destroy_task(t); + KUNIT_EXPECT_EQ(test, 0u, nr_damon_tasks());
mm/damon-test.h line 121
Quoted 10 lines
mm/damon-test.h new file +10
-0+} + +static void damon_test_set_pids (struct kunit *test) +{ +unsigned long pids[] = {1 ,2 ,3 }; +char buf[64 ]; + +damon_set_pids (pids,3 ); +damon_sprint_pids (buf,64 ); +pr_info ("buf: %s (%zu)\n" , buf,strlen (buf));
Might want to use kunit_info here so it matches the TAP test log format. Not a requirement, just an FYI.
mm/damon-test.h line 122
Quoted 1 line
mm/damon-test.h new file +1
-0+KUNIT_EXPECT_EQ (test,0 ,strncmp (buf,"1 2 3\n" ,64 ));
Here and elsewhere: This should probably use KUNIT_EXPECT_STREQ().
Quoted 35 lines
mm/damon-test.h new file +35
-0+ +damon_set_pids (NULL ,0 ); +damon_sprint_pids (buf,64 ); +KUNIT_EXPECT_EQ (test,0 ,strncmp (buf,"\n" ,64 )); + +damon_set_pids ((unsigned long []){1 ,2 },2 ); +damon_sprint_pids (buf,64 ); +KUNIT_EXPECT_EQ (test,0 ,strncmp (buf,"1 2\n" ,64 )); + +damon_set_pids ((unsigned long []){2 },1 ); +damon_sprint_pids (buf,64 ); +KUNIT_EXPECT_EQ (test,0 ,strncmp (buf,"2\n" ,64 )); + +damon_set_pids (NULL ,0 ); +damon_sprint_pids (buf,64 ); +KUNIT_EXPECT_EQ (test,0 ,strncmp (buf,"\n" ,64 )); +} + +static void damon_test_three_regions_in_vmas (struct kunit *test) +{ +struct region regions[3 ] = {0 ,}; + +struct vm_area_struct vmas[] = { + (struct vm_area_struct ) {.vm_start =10 , .vm_end =20 }, + (struct vm_area_struct ) {.vm_start =20 , .vm_end =25 }, + (struct vm_area_struct ) {.vm_start =200 , .vm_end =210 }, + (struct vm_area_struct ) {.vm_start =210 , .vm_end =220 }, + (struct vm_area_struct ) {.vm_start =300 , .vm_end =305 }, + (struct vm_area_struct ) {.vm_start =307 , .vm_end =330 }, + }; + vmas[0 ].vm_next = &vmas[1 ]; + vmas[1 ].vm_next = &vmas[2 ]; + vmas[2 ].vm_next = &vmas[3 ]; + vmas[3 ].vm_next = &vmas[4 ]; + vmas[4 ].vm_next = &vmas[5 ];
mm/damon-test.h line 167
Quoted 10 lines
mm/damon-test.h new file +10
-0+ vmas[5 ].vm_next =NULL ; + +damon_three_regions_in_vmas (&vmas[0 ], regions); + +KUNIT_EXPECT_EQ (test,10ul , regions[0 ].start); +KUNIT_EXPECT_EQ (test,25ul , regions[0 ].end); +KUNIT_EXPECT_EQ (test,200ul , regions[1 ].start); +KUNIT_EXPECT_EQ (test,220ul , regions[1 ].end); +KUNIT_EXPECT_EQ (test,300ul , regions[2 ].start); +KUNIT_EXPECT_EQ (test,330ul , regions[2 ].end);
It's not obvious to me what property you are proving here. Might want to add a comment.
Quoted 26 lines
mm/damon-test.h new file +26
-0+} + +/* Clean up global state of damon */ +static void damon_cleanup_global_state (void ) +{ +struct damon_task *t, *next; + +damon_for_each_task_safe (t, next) +damon_destroy_task (t); + + damon_rbuf_offset =0 ; +} + +static void damon_test_aggregate (struct kunit *test) +{ +unsigned long pids[] = {1 ,2 ,3 }; +unsigned long saddr[][3 ] = {{10 ,20 ,30 }, {5 ,42 ,49 }, {13 ,33 ,55 } }; +unsigned long eaddr[][3 ] = {{15 ,27 ,40 }, {31 ,45 ,55 }, {23 ,44 ,66 } }; +unsigned long accesses[][3 ] = {{42 ,95 ,84 }, {10 ,20 ,30 }, {0 ,1 ,2 } }; +struct damon_task *t; +struct damon_region *r; +int it, ir; +ssize_t sz, sr, sp; + +damon_set_pids (pids,3 ); +
mm/damon-test.h line 203
Quoted 10 lines
mm/damon-test.h new file +10
-0+ it =0 ; +damon_for_each_task (t) { +for (ir =0 ; ir <3 ; ir++) { + r =damon_new_region (saddr[it][ir], eaddr[it][ir]); + r->nr_accesses = accesses[it][ir]; +damon_add_region_tail (r, t); + } + it++; + } +kdamond_flush_aggregated ();
I think this test case is also difficult to understand. I think you probably need at least a comment on what this test case does.
Quoted 26 lines
mm/damon-test.h new file +26
-0+ it =0 ; +damon_for_each_task (t) { + ir =0 ; +damon_for_each_region (r, t) { +KUNIT_EXPECT_EQ (test,0u , r->nr_accesses); + ir++; + } +KUNIT_EXPECT_EQ (test,3 , ir); + it++; + } +KUNIT_EXPECT_EQ (test,3 , it); + + sr =sizeof (r->vm_start) +sizeof (r->vm_end) +sizeof (r->nr_accesses); + sp =sizeof (t->pid) +sizeof (unsigned int ) +3 * sr; + sz =sizeof (struct timespec64 ) +sizeof (unsigned int ) +3 * sp; +KUNIT_EXPECT_EQ (test, (unsigned int )sz, damon_rbuf_offset); + +damon_cleanup_global_state (); +} + +static void damon_test_write_rbuf (struct kunit *test) +{ +char *data; + + data ="hello" ; +damon_write_rbuf (data,strnlen (data,256 ));
mm/damon-test.h line 239
Quoted 10 lines
mm/damon-test.h new file +10
-0+KUNIT_EXPECT_EQ (test, damon_rbuf_offset,5u ); + +damon_write_rbuf (data,0 ); +KUNIT_EXPECT_EQ (test, damon_rbuf_offset,5u ); + +KUNIT_EXPECT_EQ (test,strncmp (damon_rbuf, data,5 ),0 ); +} + +static void damon_test_update_two_gaps (struct kunit *test) +{
I think this test case is also difficult to understand. I think you probably need at least a comment on what this test case does.
Quoted 39 lines
mm/damon-test.h new file +39
-0+struct damon_task *t; +struct damon_region *r, *prev =NULL ; +unsigned long regions[] = {10 ,20 ,20 ,30 , +50 ,55 ,55 ,57 ,57 ,59 , +70 ,80 ,80 ,90 ,90 ,100 };/* 10-30, 50-59, 70-100 */ +struct region new_regions[3 ] = { + (struct region ){.start =5 , .end =27 }, + (struct region ){.start =45 , .end =55 }, + (struct region ){.start =73 , .end =104 } }; +int i; +bool first_gap = true; + + t =damon_new_task (42 ); +for (i =0 ; i <ARRAY_SIZE (regions) /2 ; i++) { + r =damon_new_region (regions[i *2 ], regions[i *2 +1 ]); +damon_add_region_tail (r, t); + } +damon_add_task_tail (t); + +damon_apply_three_regions (t, new_regions); + +damon_for_each_region (r, t) { +if (prev ==NULL ) { +KUNIT_EXPECT_EQ (test, r->vm_start,5ul ); + goto next; + } + +if (prev->vm_end != r->vm_start && first_gap) { +KUNIT_EXPECT_EQ (test, prev->vm_end,27ul ); +KUNIT_EXPECT_EQ (test, r->vm_start,45ul ); + first_gap = false; + goto next; + } + +if (prev->vm_end != r->vm_start && !first_gap) { +KUNIT_EXPECT_EQ (test, prev->vm_end,55ul ); +KUNIT_EXPECT_EQ (test, r->vm_start,73ul ); + goto next; + }
mm/damon-test.h line 288
Quoted 10 lines
mm/damon-test.h new file +10
-0+ +next: + prev = r; + } + +damon_cleanup_global_state (); +} + +static void damon_test_update_two_gaps2 (struct kunit *test) +{
Same here.
Quoted 26 lines
mm/damon-test.h new file +26
-0+struct damon_task *t; +struct damon_region *r; +/* 10-20-30, 50-55-57-59, 70-80-90-100 */ +unsigned long regions[] = {10 ,20 ,20 ,30 , +50 ,55 ,55 ,57 ,57 ,59 , +70 ,80 ,80 ,90 ,90 ,100 }; +struct region new_regions[3 ] = { + (struct region ){.start =5 , .end =27 }, + (struct region ){.start =56 , .end =57 }, + (struct region ){.start =65 , .end =104 } }; +/* expect 5-27, 56-57, 65-80-90-104 */ +unsigned long answers[] = {5 ,20 ,20 ,27 , +56 ,57 , +65 ,80 ,80 ,90 ,90 ,104 }; +int i; + + t =damon_new_task (42 ); +for (i =0 ; i <ARRAY_SIZE (regions) /2 ; i++) { + r =damon_new_region (regions[i *2 ], regions[i *2 +1 ]); +damon_add_region_tail (r, t); + } +damon_add_task_tail (t); + +damon_apply_three_regions (t, new_regions); + +for (i =0 ; i <ARRAY_SIZE (answers) /2 ; i++) {
mm/damon-test.h line 324
Quoted 10 lines
mm/damon-test.h new file +10
-0+ r =damon_nth_region_of (t, i); +KUNIT_EXPECT_EQ (test, r->vm_start, answers[i *2 ]); +KUNIT_EXPECT_EQ (test, r->vm_end, answers[i++ *2 +1 ]); + } + +damon_cleanup_global_state (); +} + +static void damon_test_update_two_gaps3 (struct kunit *test) +{
Same here.
Quoted 26 lines
mm/damon-test.h new file +26
-0+struct damon_task *t; +struct damon_region *r; +/* 10-20-30, 50-55-57-59, 70-80-90-100 */ +unsigned long regions[] = {10 ,20 ,20 ,30 , +50 ,55 ,55 ,57 ,57 ,59 , +70 ,80 ,80 ,90 ,90 ,100 }; +struct region new_regions[3 ] = { + (struct region ){.start =5 , .end =27 }, + (struct region ){.start =61 , .end =63 }, + (struct region ){.start =65 , .end =104 } }; +/* expect 5-27, 56-57, 65-80-90-104 */ +unsigned long answers[] = {5 ,20 ,20 ,27 , +61 ,63 , +65 ,80 ,80 ,90 ,90 ,104 }; +int i; + + t =damon_new_task (42 ); +for (i =0 ; i <ARRAY_SIZE (regions) /2 ; i++) { + r =damon_new_region (regions[i *2 ], regions[i *2 +1 ]); +damon_add_region_tail (r, t); + } +damon_add_task_tail (t); + +damon_apply_three_regions (t, new_regions); + +for (i =0 ; i <ARRAY_SIZE (answers) /2 ; i++) {
mm/damon-test.h line 360
Quoted 10 lines
mm/damon-test.h new file +10
-0+ r =damon_nth_region_of (t, i); +KUNIT_EXPECT_EQ (test, r->vm_start, answers[i *2 ]); +KUNIT_EXPECT_EQ (test, r->vm_end, answers[i++ *2 +1 ]); + } + +damon_cleanup_global_state (); +} + +static void damon_test_update_two_gaps4 (struct kunit *test) +{
Ditto.
Quoted 224 lines
mm/damon-test.h new file +211
-0+struct damon_task *t; +struct damon_region *r; +/* 10-20-30, 50-55-57-59, 70-80-90-100 */ +unsigned long regions[] = {10 ,20 ,20 ,30 , +50 ,55 ,55 ,57 ,57 ,59 , +70 ,80 ,80 ,90 ,90 ,100 }; +struct region new_regions[3 ] = { + (struct region ){.start =5 , .end =7 }, + (struct region ){.start =30 , .end =32 }, + (struct region ){.start =65 , .end =68 } }; +/* expect 5-27, 56-57, 65-80-90-104 */ +unsigned long answers[] = {5 ,7 ,30 ,32 ,65 ,68 }; +int i; + + t =damon_new_task (42 ); +for (i =0 ; i <ARRAY_SIZE (regions) /2 ; i++) { + r =damon_new_region (regions[i *2 ], regions[i *2 +1 ]); +damon_add_region_tail (r, t); + } +damon_add_task_tail (t); + +damon_apply_three_regions (t, new_regions); + +for (i =0 ; i <ARRAY_SIZE (answers) /2 ; i++) { + r =damon_nth_region_of (t, i); +KUNIT_EXPECT_EQ (test, r->vm_start, answers[i *2 ]); +KUNIT_EXPECT_EQ (test, r->vm_end, answers[i++ *2 +1 ]); + } + +damon_cleanup_global_state (); +} + +static void damon_test_split_evenly (struct kunit *test) +{ +struct damon_task *t; +struct damon_region *r; +unsigned long i; + +KUNIT_EXPECT_EQ (test,damon_split_region_evenly (NULL ,5 ), -EINVAL ); + + t =damon_new_task (42 ); + r =damon_new_region (0 ,100 ); +KUNIT_EXPECT_EQ (test,damon_split_region_evenly (r,0 ), -EINVAL ); + +damon_add_region_tail (r, t); +KUNIT_EXPECT_EQ (test,damon_split_region_evenly (r,10 ),0 ); +KUNIT_EXPECT_EQ (test,nr_damon_regions (t),10u ); + + i =0 ; +damon_for_each_region (r, t) { +KUNIT_EXPECT_EQ (test, r->vm_start, i++ *10 ); +KUNIT_EXPECT_EQ (test, r->vm_end, i *10 ); + } +damon_free_task (t); + + t =damon_new_task (42 ); + r =damon_new_region (5 ,59 ); +damon_add_region_tail (r, t); +KUNIT_EXPECT_EQ (test,damon_split_region_evenly (r,5 ),0 ); +KUNIT_EXPECT_EQ (test,nr_damon_regions (t),5u ); + + i =0 ; +damon_for_each_region (r, t) { +if (i ==4 ) +break ; +KUNIT_EXPECT_EQ (test, r->vm_start,5 +10 * i++); +KUNIT_EXPECT_EQ (test, r->vm_end,5 +10 * i); + } +KUNIT_EXPECT_EQ (test, r->vm_start,5 +10 * i); +KUNIT_EXPECT_EQ (test, r->vm_end,59ul ); +damon_free_task (t); + + t =damon_new_task (42 ); + r =damon_new_region (5 ,6 ); +damon_add_region_tail (r, t); +KUNIT_EXPECT_EQ (test,damon_split_region_evenly (r,2 ), -EINVAL ); +KUNIT_EXPECT_EQ (test,nr_damon_regions (t),1u ); + +damon_for_each_region (r, t) { +KUNIT_EXPECT_EQ (test, r->vm_start,5ul ); +KUNIT_EXPECT_EQ (test, r->vm_end,6ul ); + } +damon_free_task (t); +} + +static void damon_test_split_at (struct kunit *test) +{ +struct damon_task *t; +struct damon_region *r; + + t =damon_new_task (42 ); + r =damon_new_region (0 ,100 ); +damon_add_region_tail (r, t); +damon_split_region_at (r,25 ); +KUNIT_EXPECT_EQ (test, r->vm_start,0ul ); +KUNIT_EXPECT_EQ (test, r->vm_end,25ul ); + + r =damon_next_region (r); +KUNIT_EXPECT_EQ (test, r->vm_start,25ul ); +KUNIT_EXPECT_EQ (test, r->vm_end,100ul ); + +damon_free_task (t); +} + +static void damon_test_merge_two (struct kunit *test) +{ +struct damon_task *t; +struct damon_region *r, *r2, *r3; +int i; + + t =damon_new_task (42 ); + r =damon_new_region (0 ,100 ); + r->nr_accesses =10 ; +damon_add_region_tail (r, t); + r2 =damon_new_region (100 ,300 ); + r2->nr_accesses =20 ; +damon_add_region_tail (r2, t); + +damon_merge_two_regions (r, r2); +KUNIT_EXPECT_EQ (test, r->vm_start,0ul ); +KUNIT_EXPECT_EQ (test, r->vm_end,300ul ); +KUNIT_EXPECT_EQ (test, r->nr_accesses,16u ); + + i =0 ; +damon_for_each_region (r3, t) { +KUNIT_EXPECT_PTR_EQ (test, r, r3); + i++; + } +KUNIT_EXPECT_EQ (test, i,1 ); + +damon_free_task (t); +} + +static void damon_test_merge_regions_of (struct kunit *test) +{ +struct damon_task *t; +struct damon_region *r; +unsigned long sa[] = {0 ,100 ,114 ,122 ,130 ,156 ,170 ,184 }; +unsigned long ea[] = {100 ,112 ,122 ,130 ,156 ,170 ,184 ,230 }; +unsigned int nrs[] = {0 ,0 ,10 ,10 ,20 ,30 ,1 ,2 }; + +unsigned long saddrs[] = {0 ,114 ,130 ,156 ,170 }; +unsigned long eaddrs[] = {112 ,130 ,156 ,170 ,230 }; +int i; + + t =damon_new_task (42 ); +for (i =0 ; i <ARRAY_SIZE (sa); i++) { + r =damon_new_region (sa[i], ea[i]); + r->nr_accesses = nrs[i]; +damon_add_region_tail (r, t); + } + +damon_merge_regions_of (t,9 ); +/* 0-112, 114-130, 130-156, 156-170 */ +KUNIT_EXPECT_EQ (test,nr_damon_regions (t),5u ); +for (i =0 ; i <5 ; i++) { + r =damon_nth_region_of (t, i); +KUNIT_EXPECT_EQ (test, r->vm_start, saddrs[i]); +KUNIT_EXPECT_EQ (test, r->vm_end, eaddrs[i]); + } +damon_free_task (t); +} + +static void damon_test_split_regions_of (struct kunit *test) +{ +struct damon_task *t; +struct damon_region *r; + + t =damon_new_task (42 ); + r =damon_new_region (0 ,22 ); +damon_add_region_tail (r, t); +damon_split_regions_of (t); +KUNIT_EXPECT_EQ (test,nr_damon_regions (t),2u ); +damon_free_task (t); +} + +static void damon_test_kdamond_need_stop (struct kunit *test) +{ +KUNIT_EXPECT_TRUE (test,kdamond_need_stop ()); +} + +static struct kunit_case damon_test_cases[] = { +KUNIT_CASE (damon_test_str_to_pids), +KUNIT_CASE (damon_test_tasks), +KUNIT_CASE (damon_test_regions), +KUNIT_CASE (damon_test_set_pids), +KUNIT_CASE (damon_test_three_regions_in_vmas), +KUNIT_CASE (damon_test_aggregate), +KUNIT_CASE (damon_test_write_rbuf), +KUNIT_CASE (damon_test_update_two_gaps), +KUNIT_CASE (damon_test_update_two_gaps2), +KUNIT_CASE (damon_test_update_two_gaps3), +KUNIT_CASE (damon_test_update_two_gaps4), +KUNIT_CASE (damon_test_split_evenly), +KUNIT_CASE (damon_test_split_at), +KUNIT_CASE (damon_test_merge_two), +KUNIT_CASE (damon_test_merge_regions_of), +KUNIT_CASE (damon_test_split_regions_of), +KUNIT_CASE (damon_test_kdamond_need_stop), + {}, +}; + +static struct kunit_suite damon_test_suite = { + .name ="damon" , + .test_cases = damon_test_cases, +}; +kunit_test_suite (damon_test_suite); + +#endif /* _DAMON_TEST_H */ + +#endif /* CONFIG_DAMON_TEST */ mm/damon.c +2
-1@@ -1262,3 +1262,5 @@ static int __init damon_init(void) }module_init (damon_init); + +#include "damon-test.h" --2.17.1
Re: Re: [RFC PATCH 5/5] mm/damon: Add kunit tests
Quoted 10 lines · On Thu, 23 Jan 2020 13:12:55 -0800 Brendan Higgins <[email protected]>…
Quoted 6 lines · SeongJae Park
From: SeongJae Park <[email protected]>
This commit adds kunit based unit tests for DAMON.
Signed-off-by SeongJae Park <[email protected]>Sorry for the late review on this: I am still getting caught up on my vacation backlog.
Thank you so much for this review, Brendan :)
BTW, I posted 'PATCH v1' of this [1] meanwhile and I forgot adding you as recipients, sorry. That said, the kunit related part has no change with the next spin, so your reviews will applied. Will not miss you from 'v2'.
[1] https://lore.kernel.org/linux-mm/[email protected]/
Quoted 16 lines
Quoted 16 lines
--- mm/Kconfig | 11 + mm/damon-test.h | 571 ++++++++++++++++++++++++++++++++++++++++++++++++ mm/damon.c | 2 + 3 files changed, 584 insertions(+) create mode 100644 mm/damon-test.hmm/Kconfig +0
-0@@ -748,4 +748,15 @@ config DAMON be 1) accurate enough to be useful for performance-centric domains, and 2) sufficiently light-weight so that it can be applied online.
Quoted 3 lines
mm/Kconfig config DAMON · line 751
Quoted 1 line
mm/Kconfig +1
-0+config DAMON_TESTTo be consistent with other KUnit tests, this should be "
DAMON_KUNIT_TEST".
Good point, will do so.
Quoted 18 lines
Quoted 18 lines
mm/Kconfig +10
-0+ bool "Test for damon" + depends on DAMON && KUNIT + help + This builds the DAMON Kunit test suite. + + For more information on KUnit and unit tests in general, please refer + to the KUnit documentation. + + If unsure, say N. + endmenumm/damon-test.h new file +0
-0@@ -0,0 +1,571 @@
[...]
Quoted 4 lines
Quoted 4 lines
mm/damon-test.h new file +4
-0+ +static void damon_test_set_pids (struct kunit *test) +{ +unsigned long pids[] = {1 ,2 ,3 };
Quoted 8 lines
mm/damon-test.h line 121
Quoted 5 lines
mm/damon-test.h new file +5
-0+char buf[64 ]; + +damon_set_pids (pids,3 ); +damon_sprint_pids (buf,64 ); +pr_info ("buf: %s (%zu)\n" , buf,strlen (buf));Might want to use
kunit_infohere so it matches the TAP test log format. Not a requirement, just an FYI.
Oh, this is a debugging code I missed to delete. Will delete from next spin. Also, will use 'kunit_info()' like things if I need any log, either.
Quoted 4 lines
Quoted 2 lines
+
KUNIT_EXPECT_EQ(test, 0, strncmp(buf, "1 2 3\n", 64));Here and elsewhere: This should probably use
KUNIT_EXPECT_STREQ().
Good point, will fix with the next spin.
Quoted 1 line
[...]
Quoted 23 lines
Quoted 23 lines
mm/damon-test.h new file +23
-0+ +static void damon_test_three_regions_in_vmas (struct kunit *test) +{ +struct region regions[3 ] = {0 ,}; + +struct vm_area_struct vmas[] = { + (struct vm_area_struct ) {.vm_start =10 , .vm_end =20 }, + (struct vm_area_struct ) {.vm_start =20 , .vm_end =25 }, + (struct vm_area_struct ) {.vm_start =200 , .vm_end =210 }, + (struct vm_area_struct ) {.vm_start =210 , .vm_end =220 }, + (struct vm_area_struct ) {.vm_start =300 , .vm_end =305 }, + (struct vm_area_struct ) {.vm_start =307 , .vm_end =330 }, + }; + vmas[0 ].vm_next = &vmas[1 ]; + vmas[1 ].vm_next = &vmas[2 ]; + vmas[2 ].vm_next = &vmas[3 ]; + vmas[3 ].vm_next = &vmas[4 ]; + vmas[4 ].vm_next = &vmas[5 ]; + vmas[5 ].vm_next =NULL ; + +damon_three_regions_in_vmas (&vmas[0 ], regions); + +KUNIT_EXPECT_EQ (test,10ul , regions[0 ].start);
Quoted 8 lines
mm/damon-test.h line 167
Quoted 5 lines
mm/damon-test.h new file +5
-0+KUNIT_EXPECT_EQ (test,25ul , regions[0 ].end); +KUNIT_EXPECT_EQ (test,200ul , regions[1 ].start); +KUNIT_EXPECT_EQ (test,220ul , regions[1 ].end); +KUNIT_EXPECT_EQ (test,300ul , regions[2 ].start); +KUNIT_EXPECT_EQ (test,330ul , regions[2 ].end);It's not obvious to me what property you are proving here. Might want to add a comment.
It's closely related with DAMON internal logic. Will add a reference to a document for the internal logic and what I'm checking, as you suggested. Same for other ambiguous test code fragments you pointed out below.
Quoted 1 line
[...]
Quoted 48 lines
Quoted 14 lines
mm/damon-test.h new file +14
-0+ +static void damon_test_aggregate (struct kunit *test) +{ +unsigned long pids[] = {1 ,2 ,3 }; +unsigned long saddr[][3 ] = {{10 ,20 ,30 }, {5 ,42 ,49 }, {13 ,33 ,55 } }; +unsigned long eaddr[][3 ] = {{15 ,27 ,40 }, {31 ,45 ,55 }, {23 ,44 ,66 } }; +unsigned long accesses[][3 ] = {{42 ,95 ,84 }, {10 ,20 ,30 }, {0 ,1 ,2 } }; +struct damon_task *t; +struct damon_region *r; +int it, ir; +ssize_t sz, sr, sp; + +damon_set_pids (pids,3 ); +mm/damon-test.h line 203
Quoted 10 lines
mm/damon-test.h new file +10
-0+ it =0 ; +damon_for_each_task (t) { +for (ir =0 ; ir <3 ; ir++) { + r =damon_new_region (saddr[it][ir], eaddr[it][ir]); + r->nr_accesses = accesses[it][ir]; +damon_add_region_tail (r, t); + } + it++; + } +kdamond_flush_aggregated ();I think this test case is also difficult to understand. I think you probably need at least a comment on what this test case does.
Quoted 20 lines
mm/damon-test.h new file +20
-0+ it =0 ; +damon_for_each_task (t) { + ir =0 ; +damon_for_each_region (r, t) { +KUNIT_EXPECT_EQ (test,0u , r->nr_accesses); + ir++; + } +KUNIT_EXPECT_EQ (test,3 , ir); + it++; + } +KUNIT_EXPECT_EQ (test,3 , it); + + sr =sizeof (r->vm_start) +sizeof (r->vm_end) +sizeof (r->nr_accesses); + sp =sizeof (t->pid) +sizeof (unsigned int ) +3 * sr; + sz =sizeof (struct timespec64 ) +sizeof (unsigned int ) +3 * sp; +KUNIT_EXPECT_EQ (test, (unsigned int )sz, damon_rbuf_offset); + +damon_cleanup_global_state (); +} +
[...]
Quoted 161 lines
mm/damon-test.h line 239
Quoted 3 lines
mm/damon-test.h new file +3
-0+ +static void damon_test_update_two_gaps (struct kunit *test) +{I think this test case is also difficult to understand. I think you probably need at least a comment on what this test case does.
Quoted 39 lines
mm/damon-test.h new file +39
-0+struct damon_task *t; +struct damon_region *r, *prev =NULL ; +unsigned long regions[] = {10 ,20 ,20 ,30 , +50 ,55 ,55 ,57 ,57 ,59 , +70 ,80 ,80 ,90 ,90 ,100 };/* 10-30, 50-59, 70-100 */ +struct region new_regions[3 ] = { + (struct region ){.start =5 , .end =27 }, + (struct region ){.start =45 , .end =55 }, + (struct region ){.start =73 , .end =104 } }; +int i; +bool first_gap = true; + + t =damon_new_task (42 ); +for (i =0 ; i <ARRAY_SIZE (regions) /2 ; i++) { + r =damon_new_region (regions[i *2 ], regions[i *2 +1 ]); +damon_add_region_tail (r, t); + } +damon_add_task_tail (t); + +damon_apply_three_regions (t, new_regions); + +damon_for_each_region (r, t) { +if (prev ==NULL ) { +KUNIT_EXPECT_EQ (test, r->vm_start,5ul ); + goto next; + } + +if (prev->vm_end != r->vm_start && first_gap) { +KUNIT_EXPECT_EQ (test, prev->vm_end,27ul ); +KUNIT_EXPECT_EQ (test, r->vm_start,45ul ); + first_gap = false; + goto next; + } + +if (prev->vm_end != r->vm_start && !first_gap) { +KUNIT_EXPECT_EQ (test, prev->vm_end,55ul ); +KUNIT_EXPECT_EQ (test, r->vm_start,73ul ); + goto next; + }mm/damon-test.h line 288
Quoted 10 lines
mm/damon-test.h new file +10
-0+ +next: + prev = r; + } + +damon_cleanup_global_state (); +} + +static void damon_test_update_two_gaps2 (struct kunit *test) +{Same here.
Quoted 26 lines
mm/damon-test.h new file +26
-0+struct damon_task *t; +struct damon_region *r; +/* 10-20-30, 50-55-57-59, 70-80-90-100 */ +unsigned long regions[] = {10 ,20 ,20 ,30 , +50 ,55 ,55 ,57 ,57 ,59 , +70 ,80 ,80 ,90 ,90 ,100 }; +struct region new_regions[3 ] = { + (struct region ){.start =5 , .end =27 }, + (struct region ){.start =56 , .end =57 }, + (struct region ){.start =65 , .end =104 } }; +/* expect 5-27, 56-57, 65-80-90-104 */ +unsigned long answers[] = {5 ,20 ,20 ,27 , +56 ,57 , +65 ,80 ,80 ,90 ,90 ,104 }; +int i; + + t =damon_new_task (42 ); +for (i =0 ; i <ARRAY_SIZE (regions) /2 ; i++) { + r =damon_new_region (regions[i *2 ], regions[i *2 +1 ]); +damon_add_region_tail (r, t); + } +damon_add_task_tail (t); + +damon_apply_three_regions (t, new_regions); + +for (i =0 ; i <ARRAY_SIZE (answers) /2 ; i++) {mm/damon-test.h line 324
Quoted 10 lines
mm/damon-test.h new file +10
-0+ r =damon_nth_region_of (t, i); +KUNIT_EXPECT_EQ (test, r->vm_start, answers[i *2 ]); +KUNIT_EXPECT_EQ (test, r->vm_end, answers[i++ *2 +1 ]); + } + +damon_cleanup_global_state (); +} + +static void damon_test_update_two_gaps3 (struct kunit *test) +{Same here.
Quoted 26 lines
mm/damon-test.h new file +26
-0+struct damon_task *t; +struct damon_region *r; +/* 10-20-30, 50-55-57-59, 70-80-90-100 */ +unsigned long regions[] = {10 ,20 ,20 ,30 , +50 ,55 ,55 ,57 ,57 ,59 , +70 ,80 ,80 ,90 ,90 ,100 }; +struct region new_regions[3 ] = { + (struct region ){.start =5 , .end =27 }, + (struct region ){.start =61 , .end =63 }, + (struct region ){.start =65 , .end =104 } }; +/* expect 5-27, 56-57, 65-80-90-104 */ +unsigned long answers[] = {5 ,20 ,20 ,27 , +61 ,63 , +65 ,80 ,80 ,90 ,90 ,104 }; +int i; + + t =damon_new_task (42 ); +for (i =0 ; i <ARRAY_SIZE (regions) /2 ; i++) { + r =damon_new_region (regions[i *2 ], regions[i *2 +1 ]); +damon_add_region_tail (r, t); + } +damon_add_task_tail (t); + +damon_apply_three_regions (t, new_regions); + +for (i =0 ; i <ARRAY_SIZE (answers) /2 ; i++) {mm/damon-test.h line 360
Quoted 10 lines
mm/damon-test.h new file +10
-0+ r =damon_nth_region_of (t, i); +KUNIT_EXPECT_EQ (test, r->vm_start, answers[i *2 ]); +KUNIT_EXPECT_EQ (test, r->vm_end, answers[i++ *2 +1 ]); + } + +damon_cleanup_global_state (); +} + +static void damon_test_update_two_gaps4 (struct kunit *test) +{Ditto.
Quoted 24 lines
mm/damon-test.h new file +24
-0+struct damon_task *t; +struct damon_region *r; +/* 10-20-30, 50-55-57-59, 70-80-90-100 */ +unsigned long regions[] = {10 ,20 ,20 ,30 , +50 ,55 ,55 ,57 ,57 ,59 , +70 ,80 ,80 ,90 ,90 ,100 }; +struct region new_regions[3 ] = { + (struct region ){.start =5 , .end =7 }, + (struct region ){.start =30 , .end =32 }, + (struct region ){.start =65 , .end =68 } }; +/* expect 5-27, 56-57, 65-80-90-104 */ +unsigned long answers[] = {5 ,7 ,30 ,32 ,65 ,68 }; +int i; + + t =damon_new_task (42 ); +for (i =0 ; i <ARRAY_SIZE (regions) /2 ; i++) { + r =damon_new_region (regions[i *2 ], regions[i *2 +1 ]); +damon_add_region_tail (r, t); + } +damon_add_task_tail (t); + +damon_apply_three_regions (t, new_regions); + +for (i =0 ; i <ARRAY_SIZE (answers) /2 ; i++) {
Quoted 8 lines
mm/damon-test.h line 322
Quoted 8 lines
mm/damon-test.h new file +8
-0+ r =damon_nth_region_of (t, i); +KUNIT_EXPECT_EQ (test, r->vm_start, answers[i *2 ]); +KUNIT_EXPECT_EQ (test, r->vm_end, answers[i++ *2 +1 ]); + } + +damon_cleanup_global_state (); +} +
[...]
Will apply all of your suggestions, soon.
Thanks,
SeongJae Park
Adding more recipients for comments. The original RFC mail is available at:
https://lore.kernel.org/linux-mm/[email protected]/
Thanks,
SeongJae Park
Quoted 316 lines · On Fri, 10 Jan 2020 14:15:17 +0100 SeongJae Park <[email protected]> wrote:
From: SeongJae Park <[email protected]>
This RFC patchset introduces a new kernel module for practical monitoring of data accesses, namely DAMON.
The patches are organized in the following sequence. The first and second patch introduces the core logic and the raw level user interface of DAMON, respectively. To provide a minimal reference to the raw level interfaces and for more convenient test of the DAMON itself, the third patch implements an user space wrapper tools for the DAMON. The fourth patch adds a document for the DAMON, and finally the fifth patch provides DAMON's unit tests, which is using the kunit framework.
The patches are based on the v5.4 plus the back-ported kunit, which retrieved from v5.5-rc1. You can also clone the complete git tree by:
$ git clone git://github.com/sjp38/linux -b damon/rfc/v1The web is also available:
https://github.com/sjp38/linux/releases/tag/damon/rfc/v1----
DAMON is a kernel module that allows users to monitor the actual memory access pattern of specific user-space processes. It aims to be 1) accurate enough to be useful for performance-centric domains, and 2) sufficiently light-weight so that it can be applied online.
For the goals, DAMON utilizes its two core mechanisms, called region-based sampling and adaptive regions adjustment. The region-based sampling allows users to make their own trade-off between the quality and the overhead of the monitoring and set the upperbound of the monitoring overhead. Further, the adaptive regions adjustment mechanism makes DAMON to maximize the quality and minimize the overhead with its best efforts while preserving the users configured trade-off.
Background
==========For performance-centric analysis and optimizations of memory management schemes (either that of kernel space or user space), the actual data access pattern of the workloads is highly useful. The information need to be only reasonable rather than strictly correct, because some level of incorrectness can be handled in many performance-centric domains. It also need to be taken within reasonably short time with only light-weight overhead.
Manually extracting such data is not easy and time consuming if the target workload is huge and complex, even for the developers of the programs. There are a range of tools and techniques developed for general memory access investigations, and some of those could be partially used for this purpose. However, most of those are not practical or unscalable, mainly because those are designed with no consideration about the trade-off between the accuracy of the output and the overhead.
The memory access instrumentation techniques which is applied to many tools such as Intel PIN is essential for correctness required cases such as invalid memory access bug detections. However, those usually incur high overhead which is unacceptable for many of the performance-centric domains. Periodic access checks based on H/W or S/W access counting features (e.g., the Accessed bits of PTEs or the
PG_Idleflags of pages) can dramatically decrease the overhead by forgiving some of the quality, compared to the instrumentation based techniques. The reduced quality is still reasonable for many of the domains, but the overhead can arbitrarily increase as the size of the target workload grows. Miniature-like static region based sampling can set the upperbound of the overhead, but it will now decrease the quality of the output as the size of the workload grows.Related Works
=============There are a number of researches[1,2,3,4,5,6] optimizing memory management mechanisms based on the actual memory access patterns that shows impressive results. However, most of those has no deep consideration about the monitoring of the accesses itself. Some of those focused on the overhead of the monitoring, but does not consider the accuracy scalability[6] or has additional dependencies[7]. Indeed, one recent research[5] about the proactive reclamation has also proposed[8] to the kernel community but the monitoring overhead was considered a main problem.
[1] Subramanya R Dulloor, Amitabha Roy, Zheguang Zhao, Narayanan Sundaram, Nadathur Satish, Rajesh Sankaran, Jeff Jackson, and Karsten Schwan. 2016. Data tiering in heterogeneous memory systems. In Proceedings of the 11th European Conference on Computer Systems (EuroSys). ACM, 15.
[2] Youngjin Kwon, Hangchen Yu, Simon Peter, Christopher J Rossbach, and Emmett Witchel. 2016. Coordinated and efficient huge page management with ingens. In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI). 705–721.
[3] Harald Servat, Antonio J Peña, Germán Llort, Estanislao Mercadal, HansChristian Hoppe, and Jesús Labarta. 2017. Automating the application data placement in hybrid memory systems. In 2017 IEEE International Conference on Cluster Computing (CLUSTER). IEEE, 126–136.
[4] Vlad Nitu, Boris Teabe, Alain Tchana, Canturk Isci, and Daniel Hagimont. 2018. Welcome to zombieland: practical and energy-efficient memory disaggregation in a datacenter. In Proceedings of the 13th European Conference on Computer Systems (EuroSys). ACM, 16.
[5] Andres Lagar-Cavilla, Junwhan Ahn, Suleiman Souhlal, Neha Agarwal, Radoslaw Burny, Shakeel Butt, Jichuan Chang, Ashwin Chaugule, Nan Deng, Junaid Shahid, Greg Thelen, Kamil Adam Yurtsever, Yu Zhao, and Parthasarathy Ranganathan. 2019. Software-Defined Far Memory in Warehouse-Scale Computers. In Proceedings of the 24th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS). ACM, New York, NY, USA, 317–330. DOI:https://doi.org/10.1145/3297858.3304053
[6] Carl Waldspurger, Trausti Saemundsson, Irfan Ahmad, and Nohhyun Park. 2017. Cache Modeling and Optimization using Miniature Simulations. In 2017 USENIX Annual Technical Conference (ATC). USENIX Association, Santa Clara, CA, 487–498.
https://www.usenix.org/conference/atc17/technical-sessions/
[7] Haojie Wang, Jidong Zhai, Xiongchao Tang, Bowen Yu, Xiaosong Ma, and Wenguang Chen. 2018. Spindle: Informed Memory Access Monitoring. In 2018 USENIX Annual Technical Conference (ATC). USENIX Association, Boston, MA, 561–574. https://www.usenix.org/conference/atc18/presentation/wang-haojie
[8] Jonathan Corbet. 2019. Proactively reclaiming idle memory. (2019).https://lwn.net/Articles/787611/.Expected Use-cases
==================A straightforward usecase of DAMON would be the program behavior analysis. With the DAMON output, users can confirm whether the program is running as intended or not. This will be useful for debuggings and tests of design points.
The monitored results can also be useful for counting the dynamic working set size of workloads. For the administration of memory overcommitted systems or selection of the environments (e.g., containers providing different amount of memory) for your workloads, this will be useful.
If you are a programmer, you can optimize your program by managing the memory based on the actual data access pattern. For example, you can identify the dynamic hotness of your data using DAMON and call ``mlock()`` to keep your hot data in DRAM, or call ``madvise()`` with ``MADV_PAGEOUT`` to proactively reclaim cold data. Even though your program is guaranteed to not encounter memory pressure, you can still improve the performance by applying the DAMON outputs for call of ``MADV_HUGEPAGE`` and ``MADV_NOHUGEPAGE``. More creative optimizations would be possible. Our evaluations of DAMON includes a straightforward optimization using the ``mlock()``. Please refer to the below Evaluation section for more detail.
As DAMON incurs very low overhead, such optimizations can be applied not only offline, but also online. Also, there is no reason to limit such optimizations to the user space. Several parts of the kernel's memory management mechanisms could be also optimized using DAMON. The reclamation, the THP (de)promotion decisions, and the compaction would be such a candidates. Nevertheless, current version of DAMON is not highly optimized for the online/in-kernel uses.
Mechanisms of DAMON
===================Basic Access Check
------------------DAMON basically reports what pages are how frequently accessed. The report is passed to users in binary format via a ``result file`` which users can set it's path. Note that the frequency is not an absolute number of accesses, but a relative frequency among the pages of the target workloads.
Users can also control the resolution of the reports by setting two time intervals, ``sampling interval`` and ``aggregation interval``. In detail, DAMON checks access to each page per ``sampling interval``, aggregates the results (counts the number of the accesses to each page), and reports the aggregated results per ``aggregation interval``. For the access check of each page, DAMON uses the Accessed bits of PTEs.
This is thus similar to the previously mentioned periodic access checks based mechanisms, which overhead is increasing as the size of the target process grows.
Region Based Sampling
---------------------To avoid the unbounded increase of the overhead, DAMON groups a number of adjacent pages that assumed to have same access frequencies into a region. As long as the assumption (pages in a region have same access frequencies) is kept, only one page in the region is required to be checked. Thus, for each ``sampling interval``, DAMON randomly picks one page in each region and clears its Accessed bit. After one more ``sampling interval``, DAMON reads the Accessed bit of the page and increases the access frequency of the region if the bit has set meanwhile. Therefore, the monitoring overhead is controllable by setting the number of regions. DAMON allows users to set the minimal and maximum number of regions for the trade-off.
Except the assumption, this is almost same with the above-mentioned miniature-like static region based sampling. In other words, this scheme cannot preserve the quality of the output if the assumption is not guaranteed.
Adaptive Regions Adjustment
---------------------------At the beginning of the monitoring, DAMON constructs the initial regions by evenly splitting the memory mapped address space of the process into the user-specified minimal number of regions. In this initial state, the assumption is normally not kept and thus the quality could be low. To keep the assumption as much as possible, DAMON adaptively merges and splits each region. For each ``aggregation interval``, it compares the access frequencies of adjacent regions and merges those if the frequency difference is small. Then, after it reports and clears the aggregated access frequency of each region, it splits each region into two regions if the total number of regions is smaller than the half of the user-specified maximum number of regions.
In this way, DAMON provides its best-effort quality and minimal overhead while keeping the bounds users set for their trade-off.
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``).
Evaluations
===========A prototype of DAMON has evaluated on an Intel Xeon E7-8837 machine using 20 benchmarks that picked from SPEC CPU 2006, NAS, Tensorflow Benchmark, SPLASH-2X, and PARSEC 3 benchmark suite. Nonethless, this section provides only summary of the results. For more detail, please refer to the slides used for the introduction of DAMON at the Linux Plumbers Conference 2019[1] or the MIDDLEWARE'19 industrial track paper[2].
Quality
-------We first traced and visualized the data access pattern of each workload. We were able to confirm that the visualized results are reasonably accurate by manually comparing those with the source code of the workloads.
To see the usefulness of the monitoring, we optimized 9 memory intensive workloads among them for memory pressure situations using the DAMON outputs. In detail, we identified frequently accessed memory regions in each workload based on the DAMON results and protected them with ``mlock()`` system calls. The optimized versions consistently show speedup (2.55x in best case, 1.65x in average) under memory pressure situation.
Overhead
--------We also measured the overhead of DAMON. It was not only under the upperbound we set, but was much lower (0.6 percent of the bound in best case, 13.288 percent of the bound in average). This reduction of the overhead is mainly resulted from the adaptive regions adjustment. We also compared the overhead with that of the straightforward periodic Accessed bit check-based monitoring, which checks the access of every page frame. DAMON's overhead was much smaller than the straightforward mechanism by 94,242.42x in best case, 3,159.61x in average.
References
==========Prototypes of DAMON have introduced by an LPC kernel summit track talk[1] and two academic papers[2,3]. Please refer to those for more detailed information, especially the evaluations.
[1] SeongJae Park, Tracing Data Access Pattern with Bounded Overhead and Best-effort Accuracy. In The Linux Kernel Summit, September 2019.
https://linuxplumbersconf.org/event/4/contributions/548/
[2] SeongJae Park, Yunjae Lee, Heon Y. Yeom, Profiling Dynamic Data Access Patterns with Controlled Overhead and Quality. In 20th ACM/IFIP International Middleware Conference Industry, December 2019.
https://dl.acm.org/doi/10.1145/3366626.3368125
[3] SeongJae Park, Yunjae Lee, Yunhee Kim, Heon Y. Yeom, Profiling Dynamic Data Access Patterns with Bounded Overhead and Accuracy. In IEEE International Workshop on Foundations and Applications of Self- Systems (FAS 2019), June 2019.SeongJae Park (5):
mm: Introduce Data Access MONitor (DAMON) mm/damon: Add debugfs interface
mm/damon: Add minimal user-space toolsDocumentation/admin-guide/mm: Add a document for DAMON mm/damon: Add kunit tests.../admin-guide/mm/data_access_monitor.rst | 235 +++ Documentation/admin-guide/mm/index.rst | 1 + mm/Kconfig | 23 + mm/Makefile | 1 + mm/damon-test.h | 571 ++++++++ mm/damon.c | 1266 +++++++++++++++++ tools/damon/bin2txt.py | 64 + tools/damon/damn | 36 + tools/damon/heats.py | 358 +++++ tools/damon/nr_regions.py | 116 ++ tools/damon/record.py | 182 +++ tools/damon/report.py | 45 + tools/damon/wss.py | 121 ++ 13 files changed, 3019 insertions(+) create mode 100644 Documentation/admin-guide/mm/data_access_monitor.rst create mode 100644 mm/damon-test.h create mode 100644 mm/damon.c create mode 100644 tools/damon/bin2txt.py create mode 100644 tools/damon/damn create mode 100644 tools/damon/heats.py create mode 100644 tools/damon/nr_regions.py create mode 100644 tools/damon/record.py create mode 100644 tools/damon/report.py create mode 100644 tools/damon/wss.pySignature · 1 line
2.17.1