- 08 Sep, 2021 39 commits
-
-
SeongJae Park authored
This commit adds documents for DAMON under `Documentation/admin-guide/mm/damon/` and `Documentation/vm/damon/`. Link: https://lkml.kernel.org/r/20210716081449.22187-11-sj38.park@gmail.comSigned-off-by:
SeongJae Park <sjpark@amazon.de> Reviewed-by:
Fernand Sieber <sieberf@amazon.com> Reviewed-by:
Markus Boehme <markubo@amazon.de> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Amit Shah <amit@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Brendan Higgins <brendanhiggins@google.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: David Woodhouse <dwmw@amazon.com> Cc: Fan Du <fan.du@intel.com> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Greg Thelen <gthelen@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Leonard Foerster <foersleo@amazon.de> Cc: Marco Elver <elver@google.com> Cc: Maximilian Heyne <mheyne@amazon.de> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@surriel.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Steven Rostedt (VMware) <rostedt@goodmis.org> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
SeongJae Park authored
In some use cases, users would want to run multiple monitoring context. For example, if a user wants a high precision monitoring and dedicating multiple CPUs for the job is ok, because DAMON creates one monitoring thread per one context, the user can split the monitoring target regions into multiple small regions and create one context for each region. Or, someone might want to simultaneously monitor different address spaces, e.g., both virtual address space and physical address space. The DAMON's API allows such usage, but 'damon-dbgfs' does not. Therefore, only kernel space DAMON users can do multiple contexts monitoring. This commit allows the user space DAMON users to use multiple contexts monitoring by introducing two new 'damon-dbgfs' debugfs files, 'mk_context' and 'rm_context'. Users can create a new monitoring context by writing the desired name of the new context to 'mk_context'. Then, a new directory with the name and having the files for setting of the context ('attrs', 'target_ids' and 'record') will be created under the debugfs directory. Writing the name of the context to remove to 'rm_context' will remove the related context and directory. Link: https://lkml.kernel.org/r/20210716081449.22187-10-sj38.park@gmail.comSigned-off-by: -
SeongJae Park authored
For CPU usage accounting, knowing pid of the monitoring thread could be helpful. For example, users could use cpuaccount cgroups with the pid. This commit therefore exports the pid of currently running monitoring thread to the user space via 'kdamond_pid' file in the debugfs directory. Link: https://lkml.kernel.org/r/20210716081449.22187-9-sj38.park@gmail.comSigned-off-by:
-
SeongJae Park authored
DAMON is designed to be used by kernel space code such as the memory management subsystems, and therefore it provides only kernel space API. That said, letting the user space control DAMON could provide some benefits to them. For example, it will allow user space to analyze their specific workloads and make their own special optimizations. For such cases, this commit implements a simple DAMON application kernel module, namely 'damon-dbgfs', which merely wraps the DAMON api and exports those to the user space via the debugfs. 'damon-dbgfs' exports three files, ``attrs``, ``target_ids``, and ``monitor_on`` under its debugfs directory, ``<debugfs>/damon/``. Attributes ---------- Users can read and write the ``sampling interval``, ``aggregation interval``, ``regions update interval``, and min/max number of monitoring target regions by reading from and writing to the ``attrs`` file. For example, below commands set those values to 5 ms, 100 ms, 1,000 ms, 10, 1000 and check it again:: # cd <debugfs>/damon # echo 5000 100000 1000000 10 1000 > attrs # cat attrs 5000 100000 1000000 10 1000 Target IDs ---------- Some types of address spaces supports multiple monitoring target. For example, the virtual memory address spaces monitoring can have multiple processes as the monitoring targets. Users can set the targets by writing relevant id values of the targets to, and get the ids of the current targets by reading from the ``target_ids`` file. In case of the virtual address spaces monitoring, the values should be pids of the monitoring target processes. For example, below commands set processes having pids 42 and 4242 as the monitoring targets and check it again:: # cd <debugfs>/damon # echo 42 4242 > target_ids # cat target_ids 42 4242 Note that setting the target ids doesn't start the monitoring. Turning On/Off -------------- Setting the files as described above doesn't incur effect unless you explicitly start the monitoring. You can start, stop, and check the current status of the monitoring by writing to and reading from the ``monitor_on`` file. Writing ``on`` to the file starts the monitoring of the targets with the attributes. Writing ``off`` to the file stops those. DAMON also stops if every targets are invalidated (in case of the virtual memory monitoring, target processes are invalidated when terminated). Below example commands turn on, off, and check the 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 above-mentioned debugfs files while the monitoring is turned on. If you write to the files while DAMON is running, an error code such as ``-EBUSY`` will be returned. [akpm@linux-foundation.org: remove unneeded "alloc failed" printks] [akpm@linux-foundation.org: replace macro with static inline] Link: https://lkml.kernel.org/r/20210716081449.22187-8-sj38.park@gmail.comSigned-off-by:Leonard Foerster <foersleo@amazon.de> Reviewed-by:
-
SeongJae Park authored
This commit adds a tracepoint for DAMON. It traces the monitoring results of each region for each aggregation interval. Using this, DAMON can easily integrated with tracepoints supporting tools such as perf. Link: https://lkml.kernel.org/r/20210716081449.22187-7-sj38.park@gmail.comSigned-off-by:
Steven Rostedt (VMware) <rostedt@goodmis.org> Reviewed-by:
Shakeel Butt <shakeelb@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Amit Shah <amit@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Brendan Higgins <brendanhiggins@google.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Rientjes <rientjes@google.com> Cc: David Woodhouse <dwmw@amazon.com> Cc: Fan Du <fan.du@intel.com> Cc: Greg Kroah-Hartman <greg@kroah.com> Cc: Greg Thelen <gthelen@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Joe Perches <joe@perches.com> Cc: Jonathan Cameron <Jonathan.Cameron@huawei.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Marco Elver <elver@google.com> Cc: Markus Boehme <markubo@amazon.de> Cc: Maximilian Heyne <mheyne@amazon.de> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@surriel.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by:
-
SeongJae Park authored
This commit introduces a reference implementation of the address space specific low level primitives for the virtual address space, so that users of DAMON can easily monitor the data accesses on virtual address spaces of specific processes by simply configuring the implementation to be used by DAMON. The low level primitives for the fundamental access monitoring are defined in two parts: 1. Identification of the monitoring target address range for the address space. 2. Access check of specific address range in the target space. The reference implementation for the virtual address space does the works as below. PTE Accessed-bit Based Access Check ----------------------------------- The implementation uses PTE Accessed-bit for basic access checks. That is, it clears the bit for the next sampling target page and checks whether it is set again after one sampling period. This could disturb the reclaim logic. DAMON uses ``PG_idle`` and ``PG_young`` page flags to solve the conflict, as Idle page tracking does. VMA-based Target Address Range Construction ------------------------------------------- Only small parts in the super-huge virtual address space of the processes are mapped to physical memory and accessed. Thus, tracking the unmapped address regions is just wasteful. However, because DAMON can deal with some level of noise using the adaptive regions adjustment mechanism, tracking every mapping is not strictly required but could even incur a high overhead in some cases. That said, too huge unmapped areas inside the monitoring target should be removed to not take the time for the adaptive mechanism. For the reason, this implementation converts the complex mappings to three distinct regions that cover every mapped area of the address space. Also, the two gaps between the three regions are the two biggest unmapped areas in the given address space. The two biggest unmapped areas would be the gap between the heap and the uppermost mmap()-ed region, and the gap between the lowermost mmap()-ed region and the stack in most of the cases. Because these gaps are exceptionally huge in usual address spaces, excluding these will be sufficient to make a reasonable trade-off. Below shows this in detail:: <heap> <BIG UNMAPPED REGION 1> <uppermost mmap()-ed region> (small mmap()-ed regions and munmap()-ed regions) <lowermost mmap()-ed region> <BIG UNMAPPED REGION 2> <stack> [akpm@linux-foundation.org: mm/damon/vaddr.c needs highmem.h for kunmap_atomic()] [sjpark@amazon.de: remove unnecessary PAGE_EXTENSION setup] Link: https://lkml.kernel.org/r/20210806095153.6444-2-sj38.park@gmail.com [sjpark@amazon.de: safely walk page table] Link: https://lkml.kernel.org/r/20210831161800.29419-1-sj38.park@gmail.com Link: https://lkml.kernel.org/r/20210716081449.22187-6-sj38.park@gmail.comSigned-off-by: -
SeongJae Park authored
PG_idle and PG_young allow the two PTE Accessed bit users, Idle Page Tracking and the reclaim logic concurrently work while not interfering with each other. That is, when they need to clear the Accessed bit, they set PG_young to represent the previous state of the bit, respectively. And when they need to read the bit, if the bit is cleared, they further read the PG_young to know whether the other has cleared the bit meanwhile or not. For yet another user of the PTE Accessed bit, we could add another page flag, or extend the mechanism to use the flags. For the DAMON usecase, however, we don't need to do that just yet. IDLE_PAGE_TRACKING and DAMON are mutually exclusive, so there's only ever going to be one user of the current set of flags. In this commit, we split out the CONFIG options to allow for the use of PG_young and PG_idle outside of idle page tracking. In the next commit, DAMON's reference implementation of the virtual memory address space monitoring primitives will use it. [sjpark@amazon.de: set PAGE_EXTENSION for non-64BIT] Link: https://lkml.kernel.org/r/20210806095153.6444-1-sj38.park@gmail.com [akpm@linux-foundation.org: tweak Kconfig text] [sjpark@amazon.de: hide PAGE_IDLE_FLAG from users] Link: https://lkml.kernel.org/r/20210813081238.34705-1-sj38.park@gmail.com Link: https://lkml.kernel.org/r/20210716081449.22187-5-sj38.park@gmail.comSigned-off-by:
-
SeongJae Park authored
Even somehow the initial monitoring target regions are well constructed to fulfill the assumption (pages in same region have similar access frequencies), the data access pattern can be dynamically changed. This will result in low monitoring quality. To keep the assumption as much as possible, DAMON adaptively merges and splits each region based on their access frequency. 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 or three regions if the total number of regions will not exceed the user-specified maximum number of regions after the split. In this way, DAMON provides its best-effort quality and minimal overhead while keeping the upper-bound overhead that users set. Link: https://lkml.kernel.org/r/20210716081449.22187-4-sj38.park@gmail.comSigned-off-by:
-
SeongJae Park authored
To avoid the unbounded increase of the overhead, DAMON groups adjacent pages that are assumed to have the same access frequencies into a region. As long as the assumption (pages in a region have the same access frequencies) is kept, only one page in the region is required to be checked. Thus, for each ``sampling interval``, 1. the 'prepare_access_checks' primitive picks one page in each region, 2. waits for one ``sampling interval``, 3. checks whether the page is accessed meanwhile, and 4. increases the access count of the region if so. Therefore, the monitoring overhead is controllable by adjusting the number of regions. DAMON allows both the underlying primitives and user callbacks to adjust regions for the trade-off. In other words, this commit makes DAMON to use not only time-based sampling but also space-based sampling. This scheme, however, cannot preserve the quality of the output if the assumption is not guaranteed. Next commit will address this problem. Link: https://lkml.kernel.org/r/20210716081449.22187-3-sj38.park@gmail.comSigned-off-by:
-
SeongJae Park authored
Patch series "Introduce Data Access MONitor (DAMON)", v34. Introduction ============ DAMON is a data access monitoring framework for the Linux kernel. The core mechanisms of DAMON called 'region based sampling' and 'adaptive regions adjustment' (refer to 'mechanisms.rst' in the 11th patch of this patchset for the detail) make it - accurate (The monitored information is useful for DRAM level memory management. It might not appropriate for Cache-level accuracy, though.), - light-weight (The monitoring overhead is low enough to be applied online while making no impact on the performance of the target workloads.), and - scalable (the upper-bound of the instrumentation overhead is controllable regardless of the size of target workloads.). Using this framework, therefore, several memory management mechanisms such as reclamation and THP can be optimized to aware real data access patterns. Experimental access pattern aware memory management optimization works that incurring high instrumentation overhead will be able to have another try. Though DAMON is for kernel subsystems, it can be easily exposed to the user space by writing a DAMON-wrapper kernel subsystem. Then, user space users who have some special workloads will be able to write personalized tools or applications for deeper understanding and specialized optimizations of their systems. DAMON is also merged in two public Amazon Linux kernel trees that based on v5.4.y[1] and v5.10.y[2]. [1] https://github.com/amazonlinux/linux/tree/amazon-5.4.y/master/mm/damon [2] https://github.com/amazonlinux/linux/tree/amazon-5.10.y/master/mm/damon The userspace tool[1] is available, released under GPLv2, and actively being maintained. I am also planning to implement another basic user interface in perf[2]. Also, the basic test suite for DAMON is available under GPLv2[3]. [1] https://github.com/awslabs/damo [2] https://lore.kernel.org/linux-mm/20210107120729.22328-1-sjpark@amazon.com/ [3] https://github.com/awslabs/damon-tests Long-term Plan -------------- DAMON is a part of a project called Data Access-aware Operating System (DAOS). As the name implies, I want to improve the performance and efficiency of systems using fine-grained data access patterns. The optimizations are for both kernel and user spaces. I will therefore modify or create kernel subsystems, export some of those to user space and implement user space library / tools. Below shows the layers and components for the project. --------------------------------------------------------------------------- Primitives: PTE Accessed bit, PG_idle, rmap, (Intel CMT), ... Framework: DAMON Features: DAMOS, virtual addr, physical addr, ... Applications: DAMON-debugfs, (DARC), ... ^^^^^^^^^^^^^^^^^^^^^^^ KERNEL SPACE ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Raw Interface: debugfs, (sysfs), (damonfs), tracepoints, (sys_damon), ... vvvvvvvvvvvvvvvvvvvvvvv USER SPACE vvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvv Library: (libdamon), ... Tools: DAMO, (perf), ... --------------------------------------------------------------------------- The components in parentheses or marked as '...' are not implemented yet but in the future plan. IOW, those are the TODO tasks of DAOS project. For more detail, please refer to the plans: https://lore.kernel.org/linux-mm/20201202082731.24828-1-sjpark@amazon.com/ Evaluations =========== We evaluated DAMON's overhead, monitoring quality and usefulness using 24 realistic workloads on my QEMU/KVM based virtual machine running a kernel that v24 DAMON patchset is applied. DAMON is lightweight. It increases system memory usage by 0.39% and slows target workloads down by 1.16%. DAMON is accurate and useful for memory management optimizations. An experimental DAMON-based operation scheme for THP, namely 'ethp', removes 76.15% of THP memory overheads while preserving 51.25% of THP speedup. Another experimental DAMON-based 'proactive reclamation' implementation, 'prcl', reduces 93.38% of residential sets and 23.63% of system memory footprint while incurring only 1.22% runtime overhead in the best case (parsec3/freqmine). NOTE that the experimental THP optimization and proactive reclamation are not for production but only for proof of concepts. Please refer to the official document[1] or "Documentation/admin-guide/mm: Add a document for DAMON" patch in this patchset for detailed evaluation setup and results. [1] https://damonitor.github.io/doc/html/latest-damon/admin-guide/mm/damon/eval.html Real-world User Story ===================== In summary, DAMON has used on production systems and proved its usefulness. DAMON as a profiler ------------------- We analyzed characteristics of a large scale production systems of our customers using DAMON. The systems utilize 70GB DRAM and 36 CPUs. From this, we were able to find interesting things below. There were obviously different access pattern under idle workload and active workload. Under the idle workload, it accessed large memory regions with low frequency, while the active workload accessed small memory regions with high freuqnecy. DAMON found a 7GB memory region that showing obviously high access frequency under the active workload. We believe this is the performance-effective working set and need to be protected. There was a 4KB memory region that showing highest access frequency under not only active but also idle workloads. We think this must be a hottest code section like thing that should never be paged out. For this analysis, DAMON used only 0.3-1% of single CPU time. Because we used recording-based analysis, it consumed about 3-12 MB of disk space per 20 minutes. This is only small amount of disk space, but we can further reduce the disk usage by using non-recording-based DAMON features. I'd like to argue that only DAMON can do such detailed analysis (finding 4KB highest region in 70GB memory) with the light overhead. DAMON as a system optimization tool ----------------------------------- We also found below potential performance problems on the systems and made DAMON-based solutions. The system doesn't want to make the workload suffer from the page reclamation and thus it utilizes enough DRAM but no swap device. However, we found the system is actively reclaiming file-backed pages, because the system has intensive file IO. The file IO turned out to be not performance critical for the workload, but the customer wanted to ensure performance critical file-backed pages like code section to not mistakenly be evicted. Using direct IO should or `mlock()` would be a straightforward solution, but modifying the user space code is not easy for the customer. Alternatively, we could use DAMON-based operation scheme[1]. By using it, we can ask DAMON to track access frequency of each region and make 'process_madvise(MADV_WILLNEED)[2]' call for regions having specific size and access frequency for a time interval. We also found the system is having high number of TLB misses. We tried 'always' THP enabled policy and it greatly reduced TLB misses, but the page reclamation also been more frequent due to the THP internal fragmentation caused memory bloat. We could try another DAMON-based operation scheme that applies 'MADV_HUGEPAGE' to memory regions having >=2MB size and high access frequency, while applying 'MADV_NOHUGEPAGE' to regions having <2MB size and low access frequency. We do not own the systems so we only reported the analysis results and possible optimization solutions to the customers. The customers satisfied about the analysis results and promised to try the optimization guides. [1] https://lore.kernel.org/linux-mm/20201006123931.5847-1-sjpark@amazon.com/ [2] https://lore.kernel.org/linux-api/20200622192900.22757-4-minchan@kernel.org/ Comparison with Idle Page Tracking ================================== Idle Page Tracking allows users to set and read idleness of pages using a bitmap file which represents each page with each bit of the file. One recommended usage of it is working set size detection. Users can do that by 1. find PFN of each page for workloads in interest, 2. set all the pages as idle by doing writes to the bitmap file, 3. wait until the workload accesses its working set, and 4. read the idleness of the pages again and count pages became not idle. NOTE: While Idle Page Tracking is for user space users, DAMON is primarily designed for kernel subsystems though it can easily exposed to the user space. Hence, this section only assumes such user space use of DAMON. For what use cases Idle Page Tracking would be better? ------------------------------------------------------ 1. Flexible usecases other than hotness monitoring. Because Idle Page Tracking allows users to control the primitive (Page idleness) by themselves, Idle Page Tracking users can do anything they want. Meanwhile, DAMON is primarily designed to monitor the hotness of each memory region. For this, DAMON asks users to provide sampling interval and aggregation interval. For the reason, there could be some use case that using Idle Page Tracking is simpler. 2. Physical memory monitoring. Idle Page Tracking receives PFN range as input, so natively supports physical memory monitoring. DAMON is designed to be extensible for multiple address spaces and use cases by implementing and using primitives for the given use case. Therefore, by theory, DAMON has no limitation in the type of target address space as long as primitives for the given address space exists. However, the default primitives introduced by this patchset supports only virtual address spaces. Therefore, for physical memory monitoring, you should implement your own primitives and use it, or simply use Idle Page Tracking. Nonetheless, RFC patchsets[1] for the physical memory address space primitives is already available. It also supports user memory same to Idle Page Tracking. [1] https://lore.kernel.org/linux-mm/20200831104730.28970-1-sjpark@amazon.com/ For what use cases DAMON is better? ----------------------------------- 1. Hotness Monitoring. Idle Page Tracking let users know only if a page frame is accessed or not. For hotness check, the user should write more code and use more memory. DAMON do that by itself. 2. Low Monitoring Overhead DAMON receives user's monitoring request with one step and then provide the results. So, roughly speaking, DAMON require only O(1) user/kernel context switches. In case of Idle Page Tracking, however, because the interface receives contiguous page frames, the number of user/kernel context switches increases as the monitoring target becomes complex and huge. As a result, the context switch overhead could be not negligible. Moreover, DAMON is born to handle with the monitoring overhead. Because the core mechanism is pure logical, Idle Page Tracking users might be able to implement the mechanism on their own, but it would be time consuming and the user/kernel context switching will still more frequent than that of DAMON. Also, the kernel subsystems cannot use the logic in this case. 3. Page granularity working set size detection. Until v22 of this patchset, this was categorized as the thing Idle Page Tracking could do better, because DAMON basically maintains additional metadata for each of the monitoring target regions. So, in the page granularity working set size detection use case, DAMON would incur (number of monitoring target pages * size of metadata) memory overhead. Size of the single metadata item is about 54 bytes, so assuming 4KB pages, about 1.3% of monitoring target pages will be additionally used. All essential metadata for Idle Page Tracking are embedded in 'struct page' and page table entries. Therefore, in this use case, only one counter variable for working set size accounting is required if Idle Page Tracking is used. There are more details to consider, but roughly speaking, this is true in most cases. However, the situation changed from v23. Now DAMON supports arbitrary types of monitoring targets, which don't use the metadata. Using that, DAMON can do the working set size detection with no additional space overhead but less user-kernel context switch. A first draft for the implementation of monitoring primitives for this usage is available in a DAMON development tree[1]. An RFC patchset for it based on this patchset will also be available soon. Since v24, the arbitrary type support is dropped from this patchset because this patchset doesn't introduce real use of the type. You can still get it from the DAMON development tree[2], though. [1] https://github.com/sjp38/linux/tree/damon/pgidle_hack [2] https://github.com/sjp38/linux/tree/damon/master 4. More future usecases While Idle Page Tracking has tight coupling with base primitives (PG_Idle and page table Accessed bits), DAMON is designed to be extensible for many use cases and address spaces. If you need some special address type or want to use special h/w access check primitives, you can write your own primitives for that and configure DAMON to use those. Therefore, if your use case could be changed a lot in future, using DAMON could be better. Can I use both Idle Page Tracking and DAMON? -------------------------------------------- Yes, though using them concurrently for overlapping memory regions could result in interference to each other. Nevertheless, such use case would be rare or makes no sense at all. Even in the case, the noise would bot be really significant. So, you can choose whatever you want depending on the characteristics of your use cases. More Information ================ We prepared a showcase web site[1] that you can get more information. There are - the official documentations[2], - the heatmap format dynamic access pattern of various realistic workloads for heap area[3], mmap()-ed area[4], and stack[5] area, - the dynamic working set size distribution[6] and chronological working set size changes[7], and - the latest performance test results[8]. [1] https://damonitor.github.io/_index [2] https://damonitor.github.io/doc/html/latest-damon [3] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.0.png.html [4] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.1.png.html [5] https://damonitor.github.io/test/result/visual/latest/rec.heatmap.2.png.html [6] https://damonitor.github.io/test/result/visual/latest/rec.wss_sz.png.html [7] https://damonitor.github.io/test/result/visual/latest/rec.wss_time.png.html [8] https://damonitor.github.io/test/result/perf/latest/html/index.html Baseline and Complete Git Trees =============================== The patches are based on the latest -mm tree, specifically v5.14-rc1-mmots-2021-07-15-18-47 of https://github.com/hnaz/linux-mm. You can also clone the complete git tree: $ git clone git://github.com/sjp38/linux -b damon/patches/v34 The web is also available: https://github.com/sjp38/linux/releases/tag/damon/patches/v34 Development Trees ----------------- There are a couple of trees for entire DAMON patchset series and features for future release. - For latest release: https://github.com/sjp38/linux/tree/damon/master - For next release: https://github.com/sjp38/linux/tree/damon/next Long-term Support Trees ----------------------- For people who want to test DAMON but using LTS kernels, there are another couple of trees based on two latest LTS kernels respectively and containing the 'damon/master' backports. - For v5.4.y: https://github.com/sjp38/linux/tree/damon/for-v5.4.y - For v5.10.y: https://github.com/sjp38/linux/tree/damon/for-v5.10.y Amazon Linux Kernel Trees ------------------------- DAMON is also merged in two public Amazon Linux kernel trees that based on v5.4.y[1] and v5.10.y[2]. [1] https://github.com/amazonlinux/linux/tree/amazon-5.4.y/master/mm/damon [2] https://github.com/amazonlinux/linux/tree/amazon-5.10.y/master/mm/damon Git Tree for Diff of Patches ============================ For easy review of diff between different versions of each patch, I prepared a git tree containing all versions of the DAMON patchset series: https://github.com/sjp38/damon-patches You can clone it and use 'diff' for easy review of changes between different versions of the patchset. For example: $ git clone https://github.com/sjp38/damon-patches && cd damon-patches $ diff -u damon/v33 damon/v34 Sequence Of Patches =================== First three patches implement the core logics of DAMON. The 1st patch introduces basic sampling based hotness monitoring for arbitrary types of targets. Following two patches implement the core mechanisms for control of overhead and accuracy, namely regions based sampling (patch 2) and adaptive regions adjustment (patch 3). Now the essential parts of DAMON is complete, but it cannot work unless someone provides monitoring primitives for a specific use case. The following two patches make it just work for virtual address spaces monitoring. The 4th patch makes 'PG_idle' can be used by DAMON and the 5th patch implements the virtual memory address space specific monitoring primitives using page table Accessed bits and the 'PG_idle' page flag. Now DAMON just works for virtual address space monitoring via the kernel space api. To let the user space users can use DAMON, following four patches add interfaces for them. The 6th patch adds a tracepoint for monitoring results. The 7th patch implements a DAMON application kernel module, namely damon-dbgfs, that simply wraps DAMON and exposes DAMON interface to the user space via the debugfs interface. The 8th patch further exports pid of monitoring thread (kdamond) to user space for easier cpu usage accounting, and the 9th patch makes the debugfs interface to support multiple contexts. Three patches for maintainability follows. The 10th patch adds documentations for both the user space and the kernel space. The 11th patch provides unit tests (based on the kunit) while the 12th patch adds user space tests (based on the kselftest). Finally, the last patch (13th) updates the MAINTAINERS file. This patch (of 13): DAMON is a data access monitoring framework for the Linux kernel. The core mechanisms of DAMON make it - accurate (the monitoring output is useful enough for DRAM level performance-centric memory management; It might be inappropriate for CPU cache levels, though), - light-weight (the monitoring overhead is normally low enough to be applied online), and - scalable (the upper-bound of the overhead is in constant range regardless of the size of target workloads). Using this framework, hence, we can easily write efficient kernel space data access monitoring applications. For example, the kernel's memory management mechanisms can make advanced decisions using this. Experimental data access aware optimization works that incurring high access monitoring overhead could again be implemented on top of this. Due to its simple and flexible interface, providing user space interface would be also easy. Then, user space users who have some special workloads can write personalized applications for better understanding and optimizations of their workloads and systems. === Nevertheless, this commit is defining and implementing only basic access check part without the overhead-accuracy handling core logic. The basic access check is as below. The output of DAMON says what memory regions are how frequently accessed for a given duration. The resolution of the access frequency is controlled by setting ``sampling interval`` and ``aggregation interval``. In detail, DAMON checks access to each page per ``sampling interval`` and aggregates the results. In other words, counts the number of the accesses to each region. After each ``aggregation interval`` passes, DAMON calls callback functions that previously registered by users so that users can read the aggregated results and then clears the results. This can be described in below simple pseudo-code:: init() while monitoring_on: for page in monitoring_target: if accessed(page): nr_accesses[page] += 1 if time() % aggregation_interval == 0: for callback in user_registered_callbacks: callback(monitoring_target, nr_accesses) for page in monitoring_target: nr_accesses[page] = 0 if time() % update_interval == 0: update() sleep(sampling interval) The target regions constructed at the beginning of the monitoring and updated after each ``regions_update_interval``, because the target regions could be dynamically changed (e.g., mmap() or memory hotplug). The monitoring overhead of this mechanism will arbitrarily increase as the size of the target workload grows. The basic monitoring primitives for actual access check and dynamic target regions construction aren't in the core part of DAMON. Instead, it allows users to implement their own primitives that are optimized for their use case and configure DAMON to use those. In other words, users cannot use current version of DAMON without some additional works. Following commits will implement the core mechanisms for the overhead-accuracy control and default primitives implementations. Link: https://lkml.kernel.org/r/20210716081449.22187-1-sj38.park@gmail.com Link: https://lkml.kernel.org/r/20210716081449.22187-2-sj38.park@gmail.comSigned-off-by:
-
Marco Elver authored
Fail kfence_test fast if KFENCE was disabled at boot, instead of each test case trying several seconds to allocate from KFENCE and failing. KUnit will fail all test cases if kunit_suite::init returns an error. Even if KFENCE was disabled, we still want the test to fail, so that CI systems that parse KUnit output will alert on KFENCE being disabled (accidentally or otherwise). Link: https://lkml.kernel.org/r/20210825105533.1247922-1-elver@google.comSigned-off-by:
Marco Elver <elver@google.com> Reported-by:
Kefeng Wang <wangkefeng.wang@huawei.com> Tested-by:
Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Signed-off-by:
-
Marco Elver authored
Record cpu and timestamp on allocations and frees, and show them in reports. Upon an error, this can help correlate earlier messages in the kernel log via allocation and free timestamps. Link: https://lkml.kernel.org/r/20210714175312.2947941-1-elver@google.comSuggested-by:
Joern Engel <joern@purestorage.com> Signed-off-by:
-
Jordy Zomer authored
When a secret memory region is active, memfd_secret disables hibernation. One of the goals is to keep the secret data from being written to persistent-storage. It accomplishes this by maintaining a reference count to `secretmem_users`. Once this reference is held your system can not be hibernated due to the check in `hibernation_available()`. However, because `secretmem_users` is of type `atomic_t`, reference counter overflows are possible. As you can see there's an `atomic_inc` for each `memfd` that is opened in the `memfd_secret` syscall. If a local attacker succeeds to open 2^32 memfd's, the counter will wrap around to 0. This implies that you may hibernate again, even though there are still regions of this secret memory, thereby bypassing the security check. In an attempt to fix this I have used `refcount_t` instead of `atomic_t` which prevents reference counter overflows. Link: https://lkml.kernel.org/r/20210820043339.2151352-1-jordy@pwning.systemsSigned-off-by:
Jordy Zomer <jordy@pwning.systems> Cc: Kees Cook <keescook@chromium.org>, Cc: Jordy Zomer <jordy@jordyzomer.github.io> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: Mike Rapoport <rppt@kernel.org> Signed-off-by:
-
Muchun Song authored
Instead of hard-coding ((1UL << NR_PAGEFLAGS) - 1) everywhere, introducing PAGEFLAGS_MASK to make the code clear to get the page flags. Link: https://lkml.kernel.org/r/20210819150712.59948-1-songmuchun@bytedance.comSigned-off-by:
Muchun Song <songmuchun@bytedance.com> Reviewed-by:
Roman Gushchin <guro@fb.com> Acked-by:
Johannes Weiner <hannes@cmpxchg.org> Reviewed-by:
-
Changbin Du authored
Replace the obsolete and ambiguos macro in_irq() with new macro in_hardirq(). Link: https://lkml.kernel.org/r/20210813145245.86070-1-changbin.du@gmail.comSigned-off-by:
Changbin Du <changbin.du@gmail.com> Acked-by: Catalin Marinas <catalin.marinas@arm.com> [kmemleak] Signed-off-by:
-
Sebastian Andrzej Siewior authored
kmap_atomic() disables preemption and pagefaults for historical reasons. The conversion to kmap_local(), which only disables migration, cannot be done wholesale because quite some call sites need to be updated to accommodate with the changed semantics. On PREEMPT_RT enabled kernels the kmap_atomic() semantics are problematic due to the implicit disabling of preemption which makes it impossible to acquire 'sleeping' spinlocks within the kmap atomic sections. PREEMPT_RT replaces the preempt_disable() with a migrate_disable() for more than a decade. It could be argued that this is a justification to do this unconditionally, but PREEMPT_RT covers only a limited number of architectures and it disables some functionality which limits the coverage further. Limit the replacement to PREEMPT_RT for now. Link: https://lkml.kernel.org/r/20210810091116.pocdmaatdcogvdso@linutronix.deSigned-off-by:
Sebastian Andrzej Siewior <bigeasy@linutronix.de> Acked-by:
Vlastimil Babka <vbabka@suse.cz> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by:
-
Weizhao Ouyang authored
early_ioremap_reset() reserved a weak function so that architectures can provide a specific cleanup. Now no architectures use it, remove this redundant function. Link: https://lkml.kernel.org/r/20210901082917.399953-1-o451686892@gmail.comSigned-off-by:
Weizhao Ouyang <o451686892@gmail.com> Reviewed-by:
David Hildenbrand <david@redhat.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by:
-
Christoph Hellwig authored
There is no need to execute from iomem (and most platforms it is impossible anyway), so add the pgprot_nx() call similar to vmap. Link: https://lkml.kernel.org/r/20210824091259.1324527-3-hch@lst.deSigned-off-by:
Christoph Hellwig <hch@lst.de> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by:
-
Christoph Hellwig authored
Patch series "small ioremap cleanups". The first patch moves a little code around the vmalloc/ioremap boundary following a bigger move by Nick earlier. The second enforces non-executable mapping on ioremap just like we do for vmap. No driver currently uses executable mappings anyway, as they should. This patch (of 2): This keeps it together with the implementation, and to remove the vmap_range wrapper. Link: https://lkml.kernel.org/r/20210824091259.1324527-1-hch@lst.de Link: https://lkml.kernel.org/r/20210824091259.1324527-2-hch@lst.deSigned-off-by:
Nicholas Piggin <npiggin@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by:
-
Christoph Hellwig authored
nommu ioremap is an inline stub in asm-generic/io.h. Link: https://lkml.kernel.org/r/20210825072036.GA29161@lst.deSigned-off-by:
-
Muchun Song authored
There is a READ_ONCE() in the macro of compound_head(), which will prevent compiler from optimizing the code when there are more than once calling of it in a function. Remove the redundant calling of compound_head() from page_to_index() and page_add_file_rmap() for better code generation. Link: https://lkml.kernel.org/r/20210811101431.83940-1-songmuchun@bytedance.comSigned-off-by:
David Howells <dhowells@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: William Kucharski <william.kucharski@oracle.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by:
-
Miaohe Lin authored
Patch series "Cleanup and fixups for memory hotplug". This series contains cleanup to use helper function to simplify the code. Also we fix some potential bugs. More details can be found in the respective changelogs. This patch (of 3): Use helper zone_is_zone_device() to simplify the code and remove some explicit CONFIG_ZONE_DEVICE codes. Link: https://lkml.kernel.org/r/20210821094246.10149-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20210821094246.10149-2-linmiaohe@huawei.comSigned-off-by:
Miaohe Lin <linmiaohe@huawei.com> Reviewed-by:
Oscar Salvador <osalvador@suse.de> Reviewed-by:
Naoya Horiguchi <naoya.horiguchi@nec.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Chris Goldsworthy <cgoldswo@codeaurora.org> Signed-off-by:
-
David Hildenbrand authored
Currently, the "auto-movable" online policy does not allow for hotplugged KERNEL (ZONE_NORMAL) memory to increase the amount of MOVABLE memory we can have, primarily, because there is no coordiantion across memory devices and we don't want to create zone-imbalances accidentially when unplugging memory. However, within a single memory device it's different. Let's allow for KERNEL memory within a dynamic memory group to allow for more MOVABLE within the same memory group. The only thing we have to take care of is that the managing driver avoids zone imbalances by unplugging MOVABLE memory first, otherwise there can be corner cases where unplug of memory could result in (accidential) zone imbalances. virtio-mem is the only user of dynamic memory groups and recently added support for prioritizing unplug of ZONE_MOVABLE over ZONE_NORMAL, so we don't need a new toggle to enable it for dynamic memory groups. We limit this handling to dynamic memory groups, because: * We want to keep the runtime overhead for collecting stats when onlining a single memory block small. We tend to have only a handful of dynamic memory groups, but we can have quite some static memory groups (e.g., 256 DIMMs). * It doesn't make too much sense for static memory groups, as we try onlining all applicable memory blocks either completely to ZONE_MOVABLE or not. In ordinary operation, we won't have a mixture of zones within a static memory group. When adding memory to a dynamic memory group, we'll first online memory to ZONE_MOVABLE as long as early KERNEL memory allows for it. Then, we'll online the next unit(s) to ZONE_NORMAL, until we can online the next unit(s) to ZONE_MOVABLE. For a simple virtio-mem device with a MOVABLE:KERNEL ratio of 3:1, it will result in a layout like: [M][M][M][M][M][M][M][M][N][M][M][M][N][M][M][M]... ^ movable memory due to early kernel memory ^ allows for more movable memory ... ^-----^ ... here ^ allows for more movable memory ... ^-----^ ... here While the created layout is sub-optimal when it comes to contiguous zones, it gives us the maximum flexibility when dynamically growing/shrinking a device; we can grow small VMs really big in small steps, and still shrink reliably to e.g., 1/4 of the maximum VM size in this example, removing full memory blocks along with meta data more reliably. Mark dynamic memory groups in the xarray such that we can efficiently iterate over them when collecting stats. In usual setups, we have one virtio-mem device per NUMA node, and usually only a small number of NUMA nodes. Note: for now, there seems to be no compelling reason to make this behavior configurable. Link: https://lkml.kernel.org/r/20210806124715.17090-10-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
Use memory groups to improve our "auto-movable" onlining policy: 1. For static memory groups (e.g., a DIMM), online a memory block MOVABLE only if all other memory blocks in the group are either MOVABLE or could be onlined MOVABLE. A DIMM will either be MOVABLE or not, not a mixture. 2. For dynamic memory groups (e.g., a virtio-mem device), online a memory block MOVABLE only if all other memory blocks inside the current unit are either MOVABLE or could be onlined MOVABLE. For a virtio-mem device with a device block size with 512 MiB, all 128 MiB memory blocks wihin a 512 MiB unit will either be MOVABLE or not, not a mixture. We have to pass the memory group to zone_for_pfn_range() to take the memory group into account. Note: for now, there seems to be no compelling reason to make this behavior configurable. Link: https://lkml.kernel.org/r/20210806124715.17090-9-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
Let's use a single dynamic memory group. Link: https://lkml.kernel.org/r/20210806124715.17090-8-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
Although dax/kmem users often disable auto-onlining and instead online memory manually (usually to ZONE_MOVABLE), there is still value in having auto-onlining be aware of the relationship of memory blocks. Let's treat one probed unit as a single static memory device, similar to a single ACPI memory device. Link: https://lkml.kernel.org/r/20210806124715.17090-7-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
Let's group all memory we add for a single memory device - we want a single node for that (which also seems to be the sane thing to do). We won't care for now about memory that was already added to the system (e.g., via e820) -- usually *all* memory of a memory device was already added and we'll fail acpi_memory_enable_device(). Link: https://lkml.kernel.org/r/20210806124715.17090-6-david@redhat.comSigned-off-by:
Rafael J. Wysocki <rafael.j.wysocki@intel.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Hui Zhu <teawater@gmail.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Marek Kedzierski <mkedzier@redhat.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Mike Rapoport <rppt@kernel.org> Cc: Oscar Salvador <osalvador@suse.de> Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Signed-off-by:
-
David Hildenbrand authored
Let's track all present pages in each memory group. Especially, track memory present in ZONE_MOVABLE and memory present in one of the kernel zones (which really only is ZONE_NORMAL right now as memory groups only apply to hotplugged memory) separately within a memory group, to prepare for making smart auto-online decision for individual memory blocks within a memory group based on group statistics. Link: https://lkml.kernel.org/r/20210806124715.17090-5-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
In our "auto-movable" memory onlining policy, we want to make decisions across memory blocks of a single memory device. Examples of memory devices include ACPI memory devices (in the simplest case a single DIMM) and virtio-mem. For now, we don't have a connection between a single memory block device and the real memory device. Each memory device consists of 1..X memory block devices. Let's logically group memory blocks belonging to the same memory device in "memory groups". Memory groups can span multiple physical ranges and a memory group itself does not contain any information regarding physical ranges, only properties (e.g., "max_pages") necessary for improved memory onlining. Introduce two memory group types: 1) Static memory group: E.g., a single ACPI memory device, consisting of 1..X memory resources. A memory group consists of 1..Y memory blocks. The whole group is added/removed in one go. If any part cannot get offlined, the whole group cannot be removed. 2) Dynamic memory group: E.g., a single virtio-mem device. Memory is dynamically added/removed in a fixed granularity, called a "unit", consisting of 1..X memory blocks. A unit is added/removed in one go. If any part of a unit cannot get offlined, the whole unit cannot be removed. In case of 1) we usually want either all memory managed by ZONE_MOVABLE or none. In case of 2) we usually want to have as many units as possible managed by ZONE_MOVABLE. We want a single unit to be of the same type. For now, memory groups are an internal concept that is not exposed to user space; we might want to change that in the future, though. add_memory() users can specify a mgid instead of a nid when passing the MHP_NID_IS_MGID flag. Link: https://lkml.kernel.org/r/20210806124715.17090-4-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
When onlining without specifying a zone (using "online" instead of "online_kernel" or "online_movable"), we currently select a zone such that existing zones are kept contiguous. This online policy made sense in the past, where contiguous zones where required. We'd like to implement smarter policies, however: * User space has little insight. As one example, it has no idea which memory blocks logically belong together (e.g., to a DIMM or to a virtio-mem device). * Drivers that add memory in separate memory blocks, especially virtio-mem, want memory to get onlined right from the kernel when adding. So we really want to have onlining to differing zones managed in the kernel, configured by user space. We see more and more cases where we might eventually hotplug a lot of memory in the future (e.g., eventually grow a 2 GiB VM to 64 GiB), however: * Resizing happens dynamically, in smaller steps in both directions (e.g., 2 GiB -> 8 GiB -> 4 GiB -> 16 GiB ...) * We still want as much flexibility as possible, especially, hotunplugging as much memory as possible later. We can really only use "online_movable" if we know that the amount of memory we are going to hotplug upfront, and we know that it won't result in a zone imbalance. So in our example, a 2 GiB VM that could grow to 64 GiB could currently not use "online_movable", and instead, "online_kernel" would have to be used, resulting in worse (no) memory hotunplug reliability. Let's add a new "auto-movable" online policy that considers the current zone ratios (global, per-node) to determine, whether we a memory block can be onlined to ZONE_MOVABLE: MOVABLE : KERNEL However, internally we'll only consider the following ratio for now: MOVABLE : KERNEL_EARLY For now, we don't allow for hotplugged KERNEL memory to allow for more MOVABLE memory, because there is no coordination across memory devices. In follow-up patches, we will allow for more KERNEL memory within a memory device to allow for more MOVABLE memory within the same memory device -- which only makes sense for special memory device types. We base our calculation on "present pages", see the code comments for details. Hotplugged memory will get online to ZONE_MOVABLE if the configured ratio allows for it. Depending on the setup, this can result in fragmented zones, which can make compaction slower and dynamic allocation of gigantic pages when not using CMA less reliable (... which is already pretty unreliable). The old policy will be the default and called "contig-zones". In follow-up patches, our new policy will use additional information, such as memory groups, to make even smarter decisions across memory blocks. Configuration: * memory_hotplug.online_policy is used to switch between both polices and defaults to "contig-zones". * memory_hotplug.auto_movable_ratio defines the maximum ratio is in percent and defaults to "301" -- allowing e.g., most 8 GiB machines to grow to 32 GiB and have all hotplugged memory in ZONE_MOVABLE. The additional percent accounts for a handful of lost present pages (e.g., firmware allocations). User space is expected to adjust this ratio when enabling the new "auto-movable" policy, though. * memory_hotplug.auto_movable_numa_aware considers numa node stats in addition to global stats, and defaults to "true". Note: just like the old policy, the new policy won't take things like unmovable huge pages or memory ballooning that doesn't support balloon compaction into account. User space has to configure onlining accordingly. Link: https://lkml.kernel.org/r/20210806124715.17090-3-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
Patch series "mm/memory_hotplug: "auto-movable" online policy and memory groups", v3. I. Goal The goal of this series is improving in-kernel auto-online support. It tackles the fundamental problems that: 1) We can create zone imbalances when onlining all memory blindly to ZONE_MOVABLE, in the worst case crashing the system. We have to know upfront how much memory we are going to hotplug such that we can safely enable auto-onlining of all hotplugged memory to ZONE_MOVABLE via "online_movable". This is far from practical and only applicable in limited setups -- like inside VMs under the RHV/oVirt hypervisor which will never hotplug more than 3 times the boot memory (and the limitation is only in place due to the Linux limitation). 2) We see more setups that implement dynamic VM resizing, hot(un)plugging memory to resize VM memory. In these setups, we might hotplug a lot of memory, but it might happen in various small steps in both directions (e.g., 2 GiB -> 8 GiB -> 4 GiB -> 16 GiB ...). virtio-mem is the primary driver of this upstream right now, performing such dynamic resizing NUMA-aware via multiple virtio-mem devices. Onlining all hotplugged memory to ZONE_NORMAL means we basically have no hotunplug guarantees. Onlining all to ZONE_MOVABLE means we can easily run into zone imbalances when growing a VM. We want a mixture, and we want as much memory as reasonable/configured in ZONE_MOVABLE. Details regarding zone imbalances can be found at [1]. 3) Memory devices consist of 1..X memory block devices, however, the kernel doesn't really track the relationship. Consequently, also user space has no idea. We want to make per-device decisions. As one example, for memory hotunplug it doesn't make sense to use a mixture of zones within a single DIMM: we want all MOVABLE if possible, otherwise all !MOVABLE, because any !MOVABLE part will easily block the whole DIMM from getting hotunplugged. As another example, virtio-mem operates on individual units that span 1..X memory blocks. Similar to a DIMM, we want a unit to either be all MOVABLE or !MOVABLE. A "unit" can be thought of like a DIMM, however, all units of a virtio-mem device logically belong together and are managed (added/removed) by a single driver. We want as much memory of a virtio-mem device to be MOVABLE as possible. 4) We want memory onlining to be done right from the kernel while adding memory, not triggered by user space via udev rules; for example, this is reqired for fast memory hotplug for drivers that add individual memory blocks, like virito-mem. We want a way to configure a policy in the kernel and avoid implementing advanced policies in user space. The auto-onlining support we have in the kernel is not sufficient. All we have is a) online everything MOVABLE (online_movable) b) online everything !MOVABLE (online_kernel) c) keep zones contiguous (online). This series allows configuring c) to mean instead "online movable if possible according to the coniguration, driven by a maximum MOVABLE:KERNEL ratio" -- a new onlining policy. II. Approach This series does 3 things: 1) Introduces the "auto-movable" online policy that initially operates on individual memory blocks only. It uses a maximum MOVABLE:KERNEL ratio to make a decision whether a memory block will be onlined to ZONE_MOVABLE or not. However, in the basic form, hotplugged KERNEL memory does not allow for more MOVABLE memory (details in the patches). CMA memory is treated like MOVABLE memory. 2) Introduces static (e.g., DIMM) and dynamic (e.g., virtio-mem) memory groups and uses group information to make decisions in the "auto-movable" online policy across memory blocks of a single memory device (modeled as memory group). More details can be found in patch #3 or in the DIMM example below. 3) Maximizes ZONE_MOVABLE memory within dynamic memory groups, by allowing ZONE_NORMAL memory within a dynamic memory group to allow for more ZONE_MOVABLE memory within the same memory group. The target use case is dynamic VM resizing using virtio-mem. See the virtio-mem example below. I remember that the basic idea of using a ratio to implement a policy in the kernel was once mentioned by Vitaly Kuznetsov, but I might be wrong (I lost the pointer to that discussion). For me, the main use case is using it along with virtio-mem (and DIMMs / ppc64 dlpar where necessary) for dynamic resizing of VMs, increasing the amount of memory we can hotunplug reliably again if we might eventually hotplug a lot of memory to a VM. III. Target Usage The target usage will be: 1) Linux boots with "mhp_default_online_type=offline" 2) User space (e.g., systemd unit) configures memory onlining (according to a config file and system properties), for example: * Setting memory_hotplug.online_policy=auto-movable * Setting memory_hotplug.auto_movable_ratio=301 * Setting memory_hotplug.auto_movable_numa_aware=true 3) User space enabled auto onlining via "echo online > /sys/devices/system/memory/auto_online_blocks" 4) User space triggers manual onlining of all already-offline memory blocks (go over offline memory blocks and set them to "online") IV. Example For DIMMs, hotplugging 4 GiB DIMMs to a 4 GiB VM with a configured ratio of 301% results in the following layout: Memory block 0-15: DMA32 (early) Memory block 32-47: Normal (early) Memory block 48-79: Movable (DIMM 0) Memory block 80-111: Movable (DIMM 1) Memory block 112-143: Movable (DIMM 2) Memory block 144-275: Normal (DIMM 3) Memory block 176-207: Normal (DIMM 4) ... all Normal (-> hotplugged Normal memory does not allow for more Movable memory) For virtio-mem, using a simple, single virtio-mem device with a 4 GiB VM will result in the following layout: Memory block 0-15: DMA32 (early) Memory block 32-47: Normal (early) Memory block 48-143: Movable (virtio-mem, first 12 GiB) Memory block 144: Normal (virtio-mem, next 128 MiB) Memory block 145-147: Movable (virtio-mem, next 384 MiB) Memory block 148: Normal (virtio-mem, next 128 MiB) Memory block 149-151: Movable (virtio-mem, next 384 MiB) ... Normal/Movable mixture as above (-> hotplugged Normal memory allows for more Movable memory within the same device) Which gives us maximum flexibility when dynamically growing/shrinking a VM in smaller steps. V. Doc Update I'll update the memory-hotplug.rst documentation, once the overhaul [1] is usptream. Until then, details can be found in patch #2. VI. Future Work 1) Use memory groups for ppc64 dlpar 2) Being able to specify a portion of (early) kernel memory that will be excluded from the ratio. Like "128 MiB globally/per node" are excluded. This might be helpful when starting VMs with extremely small memory footprint (e.g., 128 MiB) and hotplugging memory later -- not wanting the first hotplugged units getting onlined to ZONE_MOVABLE. One alternative would be a trigger to not consider ZONE_DMA memory in the ratio. We'll have to see if this is really rrequired. 3) Indicate to user space that MOVABLE might be a bad idea -- especially relevant when memory ballooning without support for balloon compaction is active. This patch (of 9): For implementing a new memory onlining policy, which determines when to online memory blocks to ZONE_MOVABLE semi-automatically, we need the number of present early (boot) pages -- present pages excluding hotplugged pages. Let's track these pages per zone. Pass a page instead of the zone to adjust_present_page_count(), similar as adjust_managed_page_count() and derive the zone from the page. It's worth noting that a memory block to be offlined/onlined is either completely "early" or "not early". add_memory() and friends can only add complete memory blocks and we only online/offline complete (individual) memory blocks. Link: https://lkml.kernel.org/r/20210806124715.17090-1-david@redhat.com Link: https://lkml.kernel.org/r/20210806124715.17090-2-david@redhat.comSigned-off-by: -
David Hildenbrand authored
We allocate + initialize everything from scratch. In case enabling the device fails, we free all memory resourcs. Link: https://lkml.kernel.org/r/20210712124052.26491-5-david@redhat.comSigned-off-by:
Pankaj Gupta <pankaj.gupta@ionos.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Anton Blanchard <anton@ozlabs.org> Cc: Ard Biesheuvel <ardb@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jason Wang <jasowang@redhat.com> Cc: Jia He <justin.he@arm.com> Cc: Joe Perches <joe@perches.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Cc: Laurent Dufour <ldufour@linux.ibm.com> Cc: Len Brown <lenb@kernel.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Michel Lespinasse <michel@lespinasse.org> Cc: Mike Rapoport <rppt@kernel.org> Cc: Nathan Lynch <nathanl@linux.ibm.com> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Pankaj Gupta <pankaj.gupta.linux@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Pierre Morel <pmorel@linux.ibm.com> Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net> Cc: Rich Felker <dalias@libc.org> Cc: Scott Cheloha <cheloha@linux.ibm.com> Cc: Sergei Trofimovich <slyfox@gentoo.org> Cc: Thiago Jung Bauermann <bauerman@linux.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: Vitaly Kuznetsov <vkuznets@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Wei Yang <richard.weiyang@linux.alibaba.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by:
-
David Hildenbrand authored
There is only a single user remaining. We can simply lookup the nid only used for node offlining purposes when walking our memory blocks. We don't expect to remove multi-nid ranges; and if we'd ever do, we most probably don't care about removing multi-nid ranges that actually result in empty nodes. If ever required, we can detect the "multi-nid" scenario and simply try offlining all online nodes. Link: https://lkml.kernel.org/r/20210712124052.26491-4-david@redhat.comSigned-off-by:
-
David Hildenbrand authored
The parameter is unused, let's remove it. Link: https://lkml.kernel.org/r/20210712124052.26491-3-david@redhat.comSigned-off-by:
Catalin Marinas <catalin.marinas@arm.com> Acked-by: Michael Ellerman <mpe@ellerman.id.au> [powerpc] Acked-by: Heiko Carstens <hca@linux.ibm.com> [s390] Reviewed-by:
-
David Hildenbrand authored
Patch series "mm/memory_hotplug: preparatory patches for new online policy and memory" These are all cleanups and one fix previously sent as part of [1]: [PATCH v1 00/12] mm/memory_hotplug: "auto-movable" online policy and memory groups. These patches make sense even without the other series, therefore I pulled them out to make the other series easier to digest. [1] https://lkml.kernel.org/r/20210607195430.48228-1-david@redhat.com This patch (of 4): Checkpatch complained on a follow-up patch that we are using "unsigned" here, which defaults to "unsigned int" and checkpatch is correct. As we will search for a fitting zone using the wrong pfn, we might end up onlining memory to one of the special kernel zones, such as ZONE_DMA, which can end badly as the onlined memory does not satisfy properties of these zones. Use "unsigned long" instead, just as we do in other places when handling PFNs. This can bite us once we have physical addresses in the range of multiple TB. Link: https://lkml.kernel.org/r/20210712124052.26491-2-david@redhat.com Fixes: e5e68930 ("mm, memory_hotplug: display allowed zones in the preferred ordering") Signed-off-by:
-
Mike Rapoport authored
When test_pages_in_a_zone() used pfn_valid_within() is has some logic surrounding pfn_valid_within() checks. Since pfn_valid_within() is gone, this logic can be removed. Link: https://lkml.kernel.org/r/20210713080035.7464-3-rppt@kernel.orgSigned-off-by:
Mike Rapoport <rppt@linux.ibm.com> Acked-by:
-
Mike Rapoport authored
Patch series "mm: remove pfn_valid_within() and CONFIG_HOLES_IN_ZONE". After recent updates to freeing unused parts of the memory map, no architecture can have holes in the memory map within a pageblock. This makes pfn_valid_within() check and CONFIG_HOLES_IN_ZONE configuration option redundant. The first patch removes them both in a mechanical way and the second patch simplifies memory_hotplug::test_pages_in_a_zone() that had pfn_valid_within() surrounded by more logic than simple if. This patch (of 2): After recent changes in freeing of the unused parts of the memory map and rework of pfn_valid() in arm and arm64 there are no architectures that can have holes in the memory map within a pageblock and so nothing can enable CONFIG_HOLES_IN_ZONE which guards non trivial implementation of pfn_valid_within(). With that, pfn_valid_within() is always hardwired to 1 and can be completely removed. Remove calls to pfn_valid_within() and CONFIG_HOLES_IN_ZONE. Link: https://lkml.kernel.org/r/20210713080035.7464-1-rppt@kernel.org Link: https://lkml.kernel.org/r/20210713080035.7464-2-rppt@kernel.orgSigned-off-by:
-
David Hildenbrand authored
The memory hot(un)plug documentation is outdated and incomplete. Most of the content dates back to 2007, so it's time for a major overhaul. Let's rewrite, reorganize and update most parts of the documentation. In addition to memory hot(un)plug, also add some details regarding ZONE_MOVABLE, with memory hotunplug being one of its main consumers. Drop the file history, that information can more reliably be had from the git log. The style of the document is also properly fixed that e.g., "restview" renders it cleanly now. In the future, we might add some more details about virt users like virtio-mem, the XEN balloon, the Hyper-V balloon and ppc64 dlpar. Link: https://lkml.kernel.org/r/20210707073205.3835-3-david@redhat.comSigned-off-by:
Michal Hocko <mhocko@suse.com> Reviewed-by:
-
David Hildenbrand authored
Patch series "memory-hotplug.rst: complete admin-guide overhaul", v3. This patch (of 2): We have the same content at Documentation/core-api/memory-hotplug.rst and it doesn't fit into the admin-guide. The documentation was accidentially duplicated when merging. Link: https://lkml.kernel.org/r/20210707073205.3835-1-david@redhat.com Link: https://lkml.kernel.org/r/20210707073205.3835-2-david@redhat.comSigned-off-by:
-
- 29 Aug, 2021 1 commit
-
-
Linus Torvalds authored
-
