- 25 Oct, 2023 40 commits
-
-
Kefeng Wang authored
Saves one compound_head() call, also in preparation for page_cpupid_xchg_last() conversion. Link: https://lkml.kernel.org/r/20231018140806.2783514-18-wangkefeng.wang@huawei.comSigned-off-by:
Kefeng Wang <wangkefeng.wang@huawei.com> Cc: David Hildenbrand <david@redhat.com> Cc: Huang Ying <ying.huang@intel.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Juri Lelli <juri.lelli@redhat.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org>
-
Kefeng Wang authored
Make finish_mkwrite_fault static since it is not used outside of memory.c. Link: https://lkml.kernel.org/r/20231018140806.2783514-17-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Convert to use folio_xchg_last_cpupid() in __split_huge_page_tail(). Link: https://lkml.kernel.org/r/20231018140806.2783514-16-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Convert to use folio_xchg_last_cpupid() in folio_migrate_flags(), also directly use folio_nid() instead of page_to_nid(&folio->page). Link: https://lkml.kernel.org/r/20231018140806.2783514-15-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Convert to use folio_xchg_last_cpupid() in should_numa_migrate_memory(). Link: https://lkml.kernel.org/r/20231018140806.2783514-14-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Add folio_xchg_last_cpupid() wrapper, which is required to convert page_cpupid_xchg_last() to folio vertion later in the series. Link: https://lkml.kernel.org/r/20231018140806.2783514-13-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Since all calls use folio_xchg_access_time(), remove xchg_page_access_time(). Link: https://lkml.kernel.org/r/20231018140806.2783514-12-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Use a folio in change_huge_pmd(), which helps to remove last xchg_page_access_time() caller. Link: https://lkml.kernel.org/r/20231018140806.2783514-11-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Use a folio in change_pte_range() to save three compound_head() calls. Since now only normal and PMD-mapped page is handled by numa balancing, it is enough to only update the entire folio's access time. Link: https://lkml.kernel.org/r/20231018140806.2783514-10-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Convert to use folio_xchg_access_time() in numa_hint_fault_latency(). Link: https://lkml.kernel.org/r/20231018140806.2783514-9-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Add folio_xchg_access_time() wrapper, which is required to convert xchg_page_access_time() to folio vertion later in the series. Link: https://lkml.kernel.org/r/20231018140806.2783514-8-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Since all calls use folio_last_cpupid(), remove page_cpupid_last(). Link: https://lkml.kernel.org/r/20231018140806.2783514-7-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Convert to use folio_last_cpupid() in __split_huge_page_tail(). Link: https://lkml.kernel.org/r/20231018140806.2783514-6-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Convert to use folio_last_cpupid() in do_huge_pmd_numa_page(). Link: https://lkml.kernel.org/r/20231018140806.2783514-5-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Convert to use folio_last_cpupid() in do_numa_page(). Link: https://lkml.kernel.org/r/20231018140806.2783514-4-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Add folio_last_cpupid() wrapper, which is required to convert page_cpupid_last() to folio vertion later in the series. Link: https://lkml.kernel.org/r/20231018140806.2783514-3-wangkefeng.wang@huawei.comSigned-off-by:
-
Kefeng Wang authored
Patch series "mm: convert page cpupid functions to folios", v3. The cpupid(or access time) used by numa balancing is stored in flags or _last_cpupid(if LAST_CPUPID_NOT_IN_PAGE_FLAGS) of page, this is to convert page cpupid to folio cpupid, a new _last_cpupid is added into folio, which make us to use folio->_last_cpupid directly, and the page cpupid functions are converted to folio ones. page_cpupid_last() -> folio_last_cpupid() xchg_page_access_time() -> folio_xchg_access_time() page_cpupid_xchg_last() -> folio_xchg_last_cpupid() This patch (of 19): If WANT_PAGE_VIRTUAL and LAST_CPUPID_NOT_IN_PAGE_FLAGS defined, the 'virtual' and '_last_cpupid' are in struct page, and since _last_cpupid is used by numa balancing feature, it is better to move it before KMSAN metadata from struct page, also add them into struct folio to make us to access them from folio directly. Link: https://lkml.kernel.org/r/20231018140806.2783514-1-wangkefeng.wang@huawei.com Link: https://lkml.kernel.org/r/20231018140806.2783514-2-wangkefeng.wang@huawei.comSigned-off-by:
-
Kairui Song authored
A variable is never used for swapout path (shadowp is NULL) and compiler is unable to optimize out the unneeded load since it's a function call. The was introduced by 3852f676 ("mm/swapcache: support to handle the shadow entries"). Link: https://lkml.kernel.org/r/20231017011728.37508-1-ryncsn@gmail.comSigned-off-by:
Kairui Song <kasong@tencent.com> Reviewed-by:
Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Huang Ying <ying.huang@intel.com> Signed-off-by:
-
Roman Gushchin authored
Reimplement get_obj_cgroup_from_current() using current_obj_cgroup(). get_obj_cgroup_from_current() and current_obj_cgroup() share 80% of the code, so the new implementation is almost trivial. get_obj_cgroup_from_current() is a convenient function used by the bpf subsystem, so there is no reason to get rid of it completely. Link: https://lkml.kernel.org/r/20231019225346.1822282-7-roman.gushchin@linux.devSigned-off-by:
Roman Gushchin (Cruise) <roman.gushchin@linux.dev> Reviewed-by:
Vlastimil Babka <vbabka@suse.cz> Acked-by:
Shakeel Butt <shakeelb@google.com> Cc: David Rientjes <rientjes@google.com> Cc: Dennis Zhou <dennis@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Naresh Kamboju <naresh.kamboju@linaro.org> Signed-off-by:
-
Roman Gushchin authored
Similar to slab and kmem, switch to a scope-based protection of the objcg pointer to avoid. Link: https://lkml.kernel.org/r/20231019225346.1822282-6-roman.gushchin@linux.devSigned-off-by:
Naresh Kamboju <naresh.kamboju@linaro.org> Acked-by:
-
Roman Gushchin authored
Switch to a scope-based protection of the objcg pointer on slab/kmem allocation paths. Instead of using the get_() semantics in the pre-allocation hook and put the reference afterwards, let's rely on the fact that objcg is pinned by the scope. It's possible because: 1) if the objcg is received from the current task struct, the task is keeping a reference to the objcg. 2) if the objcg is received from an active memcg (remote charging), the memcg is pinned by the scope and has a reference to the corresponding objcg. Link: https://lkml.kernel.org/r/20231019225346.1822282-5-roman.gushchin@linux.devSigned-off-by:
-
Roman Gushchin authored
Keep a reference to the original objcg object for the entire life of a memcg structure. This allows to simplify the synchronization on the kernel memory allocation paths: pinning a (live) memcg will also pin the corresponding objcg. The memory overhead of this change is minimal because object cgroups usually outlive their corresponding memory cgroups even without this change, so it's only an additional pointer per memcg. Link: https://lkml.kernel.org/r/20231019225346.1822282-4-roman.gushchin@linux.devSigned-off-by:
-
Roman Gushchin authored
To charge a freshly allocated kernel object to a memory cgroup, the kernel needs to obtain an objcg pointer. Currently it does it indirectly by obtaining the memcg pointer first and then calling to __get_obj_cgroup_from_memcg(). Usually tasks spend their entire life belonging to the same object cgroup. So it makes sense to save the objcg pointer on task_struct directly, so it can be obtained faster. It requires some work on fork, exit and cgroup migrate paths, but these paths are way colder. To avoid any costly synchronization the following rules are applied: 1) A task sets it's objcg pointer itself. 2) If a task is being migrated to another cgroup, the least significant bit of the objcg pointer is set atomically. 3) On the allocation path the objcg pointer is obtained locklessly using the READ_ONCE() macro and the least significant bit is checked. If it's set, the following procedure is used to update it locklessly: - task->objcg is zeroed using cmpxcg - new objcg pointer is obtained - task->objcg is updated using try_cmpxchg - operation is repeated if try_cmpxcg fails It guarantees that no updates will be lost if task migration is racing against objcg pointer update. It also allows to keep both read and write paths fully lockless. Because the task is keeping a reference to the objcg, it can't go away while the task is alive. This commit doesn't change the way the remote memcg charging works. Link: https://lkml.kernel.org/r/20231019225346.1822282-3-roman.gushchin@linux.devSigned-off-by:Johannes Weiner <hannes@cmpxchg.org> Acked-by:
-
Roman Gushchin authored
Patch series "mm: improve performance of accounted kernel memory allocations", v5. This patchset improves the performance of accounted kernel memory allocations by ~30% as measured by a micro-benchmark [1]. The benchmark is very straightforward: 1M of 64 bytes-large kmalloc() allocations. Below are results with the disabled kernel memory accounting, the original state and with this patchset applied. | | Kmem disabled | Original | Patched | Delta | |-------------+---------------+----------+---------+--------| | User cgroup | 29764 | 84548 | 59078 | -30.0% | | Root cgroup | 29742 | 48342 | 31501 | -34.8% | As we can see, the patchset removes the majority of the overhead when there is no actual accounting (a task belongs to the root memory cgroup) and almost halves the accounting overhead otherwise. The main idea is to get rid of unnecessary memcg to objcg conversions and switch to a scope-based protection of objcgs, which eliminates extra operations with objcg reference counters under a rcu read lock. More details are provided in individual commit descriptions. This patch (of 5): Manually inline memcg_kmem_bypass() and active_memcg() to speed up get_obj_cgroup_from_current() by avoiding duplicate in_task() checks and active_memcg() readings. Also add a likely() macro to __get_obj_cgroup_from_memcg(): obj_cgroup_tryget() should succeed at almost all times except a very unlikely race with the memcg deletion path. Link: https://lkml.kernel.org/r/20231019225346.1822282-1-roman.gushchin@linux.dev Link: https://lkml.kernel.org/r/20231019225346.1822282-2-roman.gushchin@linux.devSigned-off-by:
-
Huang Ying authored
In current PCP auto-tuning design, if the number of pages allocated is much more than that of pages freed on a CPU, the PCP high may become the maximal value even if the allocating/freeing depth is small, for example, in the sender of network workloads. If a CPU was used as sender originally, then it is used as receiver after context switching, we need to fill the whole PCP with maximal high before triggering PCP draining for consecutive high order freeing. This will hurt the performance of some network workloads. To solve the issue, in this patch, we will track the consecutive page freeing with a counter in stead of relying on PCP draining. So, we can detect consecutive page freeing much earlier. On a 2-socket Intel server with 128 logical CPU, we tested SCTP_STREAM_MANY test case of netperf test suite with 64-pair processes. With the patch, the network bandwidth improves 5.0%. This restores the performance drop caused by PCP auto-tuning. Link: https://lkml.kernel.org/r/20231016053002.756205-10-ying.huang@intel.comSigned-off-by:
"Huang, Ying" <ying.huang@intel.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: David Hildenbrand <david@redhat.com> Cc: Johannes Weiner <jweiner@redhat.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Sudeep Holla <sudeep.holla@arm.com> Signed-off-by:
-
Huang Ying authored
One target of PCP is to minimize pages in PCP if the system free pages is too few. To reach that target, when page reclaiming is active for the zone (ZONE_RECLAIM_ACTIVE), we will stop increasing PCP high in allocating path, decrease PCP high and free some pages in freeing path. But this may be too late because the background page reclaiming may introduce latency for some workloads. So, in this patch, during page allocation we will detect whether the number of free pages of the zone is below high watermark. If so, we will stop increasing PCP high in allocating path, decrease PCP high and free some pages in freeing path. With this, we can reduce the possibility of the premature background page reclaiming caused by too large PCP. The high watermark checking is done in allocating path to reduce the overhead in hotter freeing path. Link: https://lkml.kernel.org/r/20231016053002.756205-9-ying.huang@intel.comSigned-off-by:
-
Huang Ying authored
The target to tune PCP high automatically is as follows, - Minimize allocation/freeing from/to shared zone - Minimize idle pages in PCP - Minimize pages in PCP if the system free pages is too few To reach these target, a tuning algorithm as follows is designed, - When we refill PCP via allocating from the zone, increase PCP high. Because if we had larger PCP, we could avoid to allocate from the zone. - In periodic vmstat updating kworker (via refresh_cpu_vm_stats()), decrease PCP high to try to free possible idle PCP pages. - When page reclaiming is active for the zone, stop increasing PCP high in allocating path, decrease PCP high and free some pages in freeing path. So, the PCP high can be tuned to the page allocating/freeing depth of workloads eventually. One issue of the algorithm is that if the number of pages allocated is much more than that of pages freed on a CPU, the PCP high may become the maximal value even if the allocating/freeing depth is small. But this isn't a severe issue, because there are no idle pages in this case. One alternative choice is to increase PCP high when we drain PCP via trying to free pages to the zone, but don't increase PCP high during PCP refilling. This can avoid the issue above. But if the number of pages allocated is much less than that of pages freed on a CPU, there will be many idle pages in PCP and it is hard to free these idle pages. 1/8 (>> 3) of PCP high will be decreased periodically. The value 1/8 is kind of arbitrary. Just to make sure that the idle PCP pages will be freed eventually. On a 2-socket Intel server with 224 logical CPU, we run 8 kbuild instances in parallel (each with `make -j 28`) in 8 cgroup. This simulates the kbuild server that is used by 0-Day kbuild service. With the patch, the build time decreases 3.5%. The cycles% of the spinlock contention (mostly for zone lock) decreases from 11.0% to 0.5%. The number of PCP draining for high order pages freeing (free_high) decreases 65.6%. The number of pages allocated from zone (instead of from PCP) decreases 83.9%. Link: https://lkml.kernel.org/r/20231016053002.756205-8-ying.huang@intel.comSigned-off-by:
Mel Gorman <mgorman@techsingularity.net> Suggested-by:
Michal Hocko <mhocko@suse.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: David Hildenbrand <david@redhat.com> Cc: Johannes Weiner <jweiner@redhat.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Christoph Lameter <cl@linux.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: Sudeep Holla <sudeep.holla@arm.com> Signed-off-by:
-
Huang Ying authored
The page allocation performance requirements of different workloads are usually different. So, we need to tune PCP (per-CPU pageset) high to optimize the workload page allocation performance. Now, we have a system wide sysctl knob (percpu_pagelist_high_fraction) to tune PCP high by hand. But, it's hard to find out the best value by hand. And one global configuration may not work best for the different workloads that run on the same system. One solution to these issues is to tune PCP high of each CPU automatically. This patch adds the framework for PCP high auto-tuning. With it, pcp->high of each CPU will be changed automatically by tuning algorithm at runtime. The minimal high (pcp->high_min) is the original PCP high value calculated based on the low watermark pages. While the maximal high (pcp->high_max) is the PCP high value when percpu_pagelist_high_fraction sysctl knob is set to MIN_PERCPU_PAGELIST_HIGH_FRACTION. That is, the maximal pcp->high that can be set via sysctl knob by hand. It's possible that PCP high auto-tuning doesn't work well for some workloads. So, when PCP high is tuned by hand via the sysctl knob, the auto-tuning will be disabled. The PCP high set by hand will be used instead. This patch only adds the framework, so pcp->high will be set to pcp->high_min (original default) always. We will add actual auto-tuning algorithm in the following patches in the series. Link: https://lkml.kernel.org/r/20231016053002.756205-7-ying.huang@intel.comSigned-off-by:
-
Huang Ying authored
When a task is allocating a large number of order-0 pages, it may acquire the zone->lock multiple times allocating pages in batches. This may unnecessarily contend on the zone lock when allocating very large number of pages. This patch adapts the size of the batch based on the recent pattern to scale the batch size for subsequent allocations. On a 2-socket Intel server with 224 logical CPU, we run 8 kbuild instances in parallel (each with `make -j 28`) in 8 cgroup. This simulates the kbuild server that is used by 0-Day kbuild service. With the patch, the cycles% of the spinlock contention (mostly for zone lock) decreases from 12.6% to 11.0% (with PCP size == 367). Link: https://lkml.kernel.org/r/20231016053002.756205-6-ying.huang@intel.comSigned-off-by:
-
Huang Ying authored
In page allocator, PCP (Per-CPU Pageset) is refilled and drained in batches to increase page allocation throughput, reduce page allocation/freeing latency per page, and reduce zone lock contention. But too large batch size will cause too long maximal allocation/freeing latency, which may punish arbitrary users. So the default batch size is chosen carefully (in zone_batchsize(), the value is 63 for zone > 1GB) to avoid that. In commit 3b12e7e9 ("mm/page_alloc: scale the number of pages that are batch freed"), the batch size will be scaled for large number of page freeing to improve page freeing performance and reduce zone lock contention. Similar optimization can be used for large number of pages allocation too. To find out a suitable max batch scale factor (that is, max effective batch size), some tests and measurement on some machines were done as follows. A set of debug patches are implemented as follows, - Set PCP high to be 2 * batch to reduce the effect of PCP high - Disable free batch size scaling to get the raw performance. - The code with zone lock held is extracted from rmqueue_bulk() and free_pcppages_bulk() to 2 separate functions to make it easy to measure the function run time with ftrace function_graph tracer. - The batch size is hard coded to be 63 (default), 127, 255, 511, 1023, 2047, 4095. Then will-it-scale/page_fault1 is used to generate the page allocation/freeing workload. The page allocation/freeing throughput (page/s) is measured via will-it-scale. The page allocation/freeing average latency (alloc/free latency avg, in us) and allocation/freeing latency at 99 percentile (alloc/free latency 99%, in us) are measured with ftrace function_graph tracer. The test results are as follows, Sapphire Rapids Server ====================== Batch throughput free latency free latency alloc latency alloc latency page/s avg / us 99% / us avg / us 99% / us ----- ---------- ------------ ------------ ------------- ------------- 63 513633.4 2.33 3.57 2.67 6.83 127 517616.7 4.35 6.65 4.22 13.03 255 520822.8 8.29 13.32 7.52 25.24 511 524122.0 15.79 23.42 14.02 49.35 1023 525980.5 30.25 44.19 25.36 94.88 2047 526793.6 59.39 84.50 45.22 140.81 Ice Lake Server =============== Batch throughput free latency free latency alloc latency alloc latency page/s avg / us 99% / us avg / us 99% / us ----- ---------- ------------ ------------ ------------- ------------- 63 620210.3 2.21 3.68 2.02 4.35 127 627003.0 4.09 6.86 3.51 8.28 255 630777.5 7.70 13.50 6.17 15.97 511 633651.5 14.85 22.62 11.66 31.08 1023 637071.1 28.55 42.02 20.81 54.36 2047 638089.7 56.54 84.06 39.28 91.68 Cascade Lake Server =================== Batch throughput free latency free latency alloc latency alloc latency page/s avg / us 99% / us avg / us 99% / us ----- ---------- ------------ ------------ ------------- ------------- 63 404706.7 3.29 5.03 3.53 4.75 127 422475.2 6.12 9.09 6.36 8.76 255 411522.2 11.68 16.97 10.90 16.39 511 428124.1 22.54 31.28 19.86 32.25 1023 414718.4 43.39 62.52 40.00 66.33 2047 429848.7 86.64 120.34 71.14 106.08 Commet Lake Desktop =================== Batch throughput free latency free latency alloc latency alloc latency page/s avg / us 99% / us avg / us 99% / us ----- ---------- ------------ ------------ ------------- ------------- 63 795183.13 2.18 3.55 2.03 3.05 127 803067.85 3.91 6.56 3.85 5.52 255 812771.10 7.35 10.80 7.14 10.20 511 817723.48 14.17 27.54 13.43 30.31 1023 818870.19 27.72 40.10 27.89 46.28 Coffee Lake Desktop =================== Batch throughput free latency free latency alloc latency alloc latency page/s avg / us 99% / us avg / us 99% / us ----- ---------- ------------ ------------ ------------- ------------- 63 510542.8 3.13 4.40 2.48 3.43 127 514288.6 5.97 7.89 4.65 6.04 255 516889.7 11.86 15.58 8.96 12.55 511 519802.4 23.10 28.81 16.95 26.19 1023 520802.7 45.30 52.51 33.19 45.95 2047 519997.1 90.63 104.00 65.26 81.74 From the above data, to restrict the allocation/freeing latency to be less than 100 us in most times, the max batch scale factor needs to be less than or equal to 5. Although it is reasonable to use 5 as max batch scale factor for the systems tested, there are also slower systems. Where smaller value should be used to constrain the page allocation/freeing latency. So, in this patch, a new kconfig option (PCP_BATCH_SCALE_MAX) is added to set the max batch scale factor. Whose default value is 5, and users can reduce it when necessary. Link: https://lkml.kernel.org/r/20231016053002.756205-5-ying.huang@intel.comSigned-off-by:
-
Huang Ying authored
In commit f26b3fa0 ("mm/page_alloc: limit number of high-order pages on PCP during bulk free"), the PCP (Per-CPU Pageset) will be drained when PCP is mostly used for high-order pages freeing to improve the cache-hot pages reusing between page allocating and freeing CPUs. On system with small per-CPU data cache slice, pages shouldn't be cached before draining to guarantee cache-hot. But on a system with large per-CPU data cache slice, some pages can be cached before draining to reduce zone lock contention. So, in this patch, instead of draining without any caching, "pcp->batch" pages will be cached in PCP before draining if the size of the per-CPU data cache slice is more than "3 * batch". In theory, if the size of per-CPU data cache slice is more than "2 * batch", we can reuse cache-hot pages between CPUs. But considering the other usage of cache (code, other data accessing, etc.), "3 * batch" is used. Note: "3 * batch" is chosen to make sure the optimization works on recent x86_64 server CPUs. If you want to increase it, please check whether it breaks the optimization. On a 2-socket Intel server with 128 logical CPU, with the patch, the network bandwidth of the UNIX (AF_UNIX) test case of lmbench test suite with 16-pair processes increase 70.5%. The cycles% of the spinlock contention (mostly for zone lock) decreases from 46.1% to 21.3%. The number of PCP draining for high order pages freeing (free_high) decreases 89.9%. The cache miss rate keeps 0.2%. Link: https://lkml.kernel.org/r/20231016053002.756205-4-ying.huang@intel.comSigned-off-by:
-
Huang Ying authored
This can be used to estimate the size of the data cache slice that can be used by one CPU under ideal circumstances. Both DATA caches and UNIFIED caches are used in calculation. So, the users need to consider the impact of the code cache usage. Because the cache inclusive/non-inclusive information isn't available now, we just use the size of the per-CPU slice of LLC to make the result more predictable across architectures. This may be improved when more cache information is available in the future. A brute-force algorithm to iterate all online CPUs is used to avoid to allocate an extra cpumask, especially in offline callback. Link: https://lkml.kernel.org/r/20231016053002.756205-3-ying.huang@intel.comSigned-off-by:
-
Huang Ying authored
Patch series "mm: PCP high auto-tuning", v3. The page allocation performance requirements of different workloads are often different. So, we need to tune the PCP (Per-CPU Pageset) high on each CPU automatically to optimize the page allocation performance. The list of patches in series is as follows, [1/9] mm, pcp: avoid to drain PCP when process exit [2/9] cacheinfo: calculate per-CPU data cache size [3/9] mm, pcp: reduce lock contention for draining high-order pages [4/9] mm: restrict the pcp batch scale factor to avoid too long latency [5/9] mm, page_alloc: scale the number of pages that are batch allocated [6/9] mm: add framework for PCP high auto-tuning [7/9] mm: tune PCP high automatically [8/9] mm, pcp: decrease PCP high if free pages < high watermark [9/9] mm, pcp: reduce detecting time of consecutive high order page freeing Patch [1/9], [2/9], [3/9] optimize the PCP draining for consecutive high-order pages freeing. Patch [4/9], [5/9] optimize batch freeing and allocating. Patch [6/9], [7/9], [8/9] implement and optimize a PCP high auto-tuning method. Patch [9/9] optimize the PCP draining for consecutive high order page freeing based on PCP high auto-tuning. The test results for patches with performance impact are as follows, kbuild ====== On a 2-socket Intel server with 224 logical CPU, we run 8 kbuild instances in parallel (each with `make -j 28`) in 8 cgroup. This simulates the kbuild server that is used by 0-Day kbuild service. build time lock contend% free_high alloc_zone ---------- ---------- --------- ---------- base 100.0 14.0 100.0 100.0 patch1 99.5 12.8 19.5 95.6 patch3 99.4 12.6 7.1 95.6 patch5 98.6 11.0 8.1 97.1 patch7 95.1 0.5 2.8 15.6 patch9 95.0 1.0 8.8 20.0 The PCP draining optimization (patch [1/9], [3/9]) and PCP batch allocation optimization (patch [5/9]) reduces zone lock contention a little. The PCP high auto-tuning (patch [7/9], [9/9]) reduces build time visibly. Where the tuning target: the number of pages allocated from zone reduces greatly. So, the zone contention cycles% reduces greatly. With PCP tuning patches (patch [7/9], [9/9]), the average used memory during test increases up to 18.4% because more pages are cached in PCP. But at the end of the test, the number of the used memory decreases to the same level as that of the base patch. That is, the pages cached in PCP will be released to zone after not being used actively. netperf SCTP_STREAM_MANY ======================== On a 2-socket Intel server with 128 logical CPU, we tested SCTP_STREAM_MANY test case of netperf test suite with 64-pair processes. score lock contend% free_high alloc_zone cache miss rate% ----- ---------- --------- ---------- ---------------- base 100.0 2.1 100.0 100.0 1.3 patch1 99.4 2.1 99.4 99.4 1.3 patch3 106.4 1.3 13.3 106.3 1.3 patch5 106.0 1.2 13.2 105.9 1.3 patch7 103.4 1.9 6.7 90.3 7.6 patch9 108.6 1.3 13.7 108.6 1.3 The PCP draining optimization (patch [1/9]+[3/9]) improves performance. The PCP high auto-tuning (patch [7/9]) reduces performance a little because PCP draining cannot be triggered in time sometimes. So, the cache miss rate% increases. The further PCP draining optimization (patch [9/9]) based on PCP tuning restore the performance. lmbench3 UNIX (AF_UNIX) ======================= On a 2-socket Intel server with 128 logical CPU, we tested UNIX (AF_UNIX socket) test case of lmbench3 test suite with 16-pair processes. score lock contend% free_high alloc_zone cache miss rate% ----- ---------- --------- ---------- ---------------- base 100.0 51.4 100.0 100.0 0.2 patch1 116.8 46.1 69.5 104.3 0.2 patch3 199.1 21.3 7.0 104.9 0.2 patch5 200.0 20.8 7.1 106.9 0.3 patch7 191.6 19.9 6.8 103.8 2.8 patch9 193.4 21.7 7.0 104.7 2.1 The PCP draining optimization (patch [1/9], [3/9]) improves performance much. The PCP tuning (patch [7/9]) reduces performance a little because PCP draining cannot be triggered in time sometimes. The further PCP draining optimization (patch [9/9]) based on PCP tuning restores the performance partly. The patchset adds several fields in struct per_cpu_pages. The struct layout before/after the patchset is as follows, base ==== struct per_cpu_pages { spinlock_t lock; /* 0 4 */ int count; /* 4 4 */ int high; /* 8 4 */ int batch; /* 12 4 */ short int free_factor; /* 16 2 */ short int expire; /* 18 2 */ /* XXX 4 bytes hole, try to pack */ struct list_head lists[13]; /* 24 208 */ /* size: 256, cachelines: 4, members: 7 */ /* sum members: 228, holes: 1, sum holes: 4 */ /* padding: 24 */ } __attribute__((__aligned__(64))); patched ======= struct per_cpu_pages { spinlock_t lock; /* 0 4 */ int count; /* 4 4 */ int high; /* 8 4 */ int high_min; /* 12 4 */ int high_max; /* 16 4 */ int batch; /* 20 4 */ u8 flags; /* 24 1 */ u8 alloc_factor; /* 25 1 */ u8 expire; /* 26 1 */ /* XXX 1 byte hole, try to pack */ short int free_count; /* 28 2 */ /* XXX 2 bytes hole, try to pack */ struct list_head lists[13]; /* 32 208 */ /* size: 256, cachelines: 4, members: 11 */ /* sum members: 237, holes: 2, sum holes: 3 */ /* padding: 16 */ } __attribute__((__aligned__(64))); The size of the struct doesn't changed with the patchset. This patch (of 9): In commit f26b3fa0 ("mm/page_alloc: limit number of high-order pages on PCP during bulk free"), the PCP (Per-CPU Pageset) will be drained when PCP is mostly used for high-order pages freeing to improve the cache-hot pages reusing between page allocation and freeing CPUs. But, the PCP draining mechanism may be triggered unexpectedly when process exits. With some customized trace point, it was found that PCP draining (free_high == true) was triggered with the order-1 page freeing with the following call stack, => free_unref_page_commit => free_unref_page => __mmdrop => exit_mm => do_exit => do_group_exit => __x64_sys_exit_group => do_syscall_64 Checking the source code, this is the page table PGD freeing (mm_free_pgd()). It's a order-1 page freeing if CONFIG_PAGE_TABLE_ISOLATION=y. Which is a common configuration for security. Just before that, page freeing with the following call stack was found, => free_unref_page_commit => free_unref_page_list => release_pages => tlb_batch_pages_flush => tlb_finish_mmu => exit_mmap => __mmput => exit_mm => do_exit => do_group_exit => __x64_sys_exit_group => do_syscall_64 So, when a process exits, - a large number of user pages of the process will be freed without page allocation, it's highly possible that pcp->free_factor becomes > 0. In fact, this is expected behavior to improve process exit performance. - after freeing all user pages, the PGD will be freed, which is a order-1 page freeing, PCP will be drained. All in all, when a process exits, it's high possible that the PCP will be drained. This is an unexpected behavior. To avoid this, in the patch, the PCP draining will only be triggered for 2 consecutive high-order page freeing. On a 2-socket Intel server with 224 logical CPU, we run 8 kbuild instances in parallel (each with `make -j 28`) in 8 cgroup. This simulates the kbuild server that is used by 0-Day kbuild service. With the patch, the cycles% of the spinlock contention (mostly for zone lock) decreases from 14.0% to 12.8% (with PCP size == 367). The number of PCP draining for high order pages freeing (free_high) decreases 80.5%. This helps network workload too for reduced zone lock contention. On a 2-socket Intel server with 128 logical CPU, with the patch, the network bandwidth of the UNIX (AF_UNIX) test case of lmbench test suite with 16-pair processes increase 16.8%. The cycles% of the spinlock contention (mostly for zone lock) decreases from 51.4% to 46.1%. The number of PCP draining for high order pages freeing (free_high) decreases 30.5%. The cache miss rate keeps 0.2%. Link: https://lkml.kernel.org/r/20231016053002.756205-1-ying.huang@intel.com Link: https://lkml.kernel.org/r/20231016053002.756205-2-ying.huang@intel.comSigned-off-by: -
Kairui Song authored
There is only one caller wants to dump the kill victim info, so just let it call the standalone helper, no need to make the generic info dump helper take an extra argument for that. Result of bloat-o-meter: ./scripts/bloat-o-meter ./mm/oom_kill.old.o ./mm/oom_kill.o add/remove: 0/0 grow/shrink: 1/2 up/down: 131/-142 (-11) Function old new delta oom_kill_process 412 543 +131 out_of_memory 1422 1418 -4 dump_header 562 424 -138 Total: Before=21514, After=21503, chg -0.05% Link: https://lkml.kernel.org/r/20231016113103.86477-1-ryncsn@gmail.comSigned-off-by:
-
Pedro Falcato authored
Given large enough allocations and a machine with low enough memory (i.e a default QEMU VM), it's entirely possible that kmsan_init_alloc_meta_for_range's shadow+origin allocation fails. Instead of eating a NULL deref kernel oops, check explicitly for memblock_alloc() failure and panic with a nice error message. Alexander Potapenko said: For posterity, it is generally quite important for the allocated shadow and origin to be contiguous, otherwise an unaligned memory write may result in memory corruption (the corresponding unaligned shadow write will be assuming that shadow pages are adjacent). So instead of panicking we could have split the range into smaller ones until the allocation succeeds, but that would've led to hard-to-debug problems in the future. Link: https://lkml.kernel.org/r/20231016153446.132763-1-pedro.falcato@gmail.comSigned-off-by:
Pedro Falcato <pedro.falcato@gmail.com> Reviewed-by:
Alexander Potapenko <glider@google.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Marco Elver <elver@google.com> Signed-off-by:
-
Matthew Wilcox (Oracle) authored
With all users converted, remove the old create_empty_buffers() and rename folio_create_empty_buffers() to create_empty_buffers(). Link: https://lkml.kernel.org/r/20231016201114.1928083-28-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Both callers are now converted to ufs_get_locked_folio(). Link: https://lkml.kernel.org/r/20231016201114.1928083-27-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Convert the locked_page argument to a folio, then use folios throughout. Saves three hidden calls to compound_head(). Link: https://lkml.kernel.org/r/20231016201114.1928083-26-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Switch to the folio APIs, saving one folio->page->folio conversion. Link: https://lkml.kernel.org/r/20231016201114.1928083-25-willy@infradead.orgSigned-off-by:
-
Matthew Wilcox (Oracle) authored
Convert the _page variants to call them. Saves a few hidden calls to compound_head(). Link: https://lkml.kernel.org/r/20231016201114.1928083-24-willy@infradead.orgSigned-off-by:
-
