- 04 Jun, 2020 40 commits
-
-
Mike Kravetz authored
With all hugetlb page processing done in a single file clean up code. - Make code match desired semantics - Update documentation with semantics - Make all warnings and errors messages start with 'HugeTLB:'. - Consistently name command line parsing routines. - Warn if !hugepages_supported() and command line parameters have been specified. - Add comments to code - Describe some of the subtle interactions - Describe semantics of command line arguments This patch also fixes issues with implicitly setting the number of gigantic huge pages to preallocate. Previously on X86 command line, hugepages=2 default_hugepagesz=1G would result in zero 1G pages being preallocated and, # grep HugePages_Total /proc/meminfo HugePages_Total: 0 # sysctl -a | grep nr_hugepages vm.nr_hugepages = 2 vm.nr_hugepages_mempolicy = 2 # cat /proc/sys/vm/nr_hugepages 2 After this patch 2 gigantic pages will be preallocated and all the proc, sysfs, sysctl and meminfo files will accurately reflect this. To address the issue with gigantic pages, a small change in behavior was made to command line processing. Previously the command line, hugepages=128 default_hugepagesz=2M hugepagesz=2M hugepages=256 would result in the allocation of 256 2M huge pages. The value 128 would be ignored without any warning. After this patch, 128 2M pages will be allocated and a warning message will be displayed indicating the value of 256 is ignored. This change in behavior is required because allocation of implicitly specified gigantic pages must be done when the default_hugepagesz= is encountered for gigantic pages. Previously the code waited until later in the boot process (hugetlb_init), to allocate pages of default size. However the bootmem allocator required for gigantic allocations is not available at this time. Signed-off-by:Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Tested-by:
Sandipan Das <sandipan@linux.ibm.com> Acked-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> [s390] Acked-by:
Will Deacon <will@kernel.org> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David S. Miller <davem@davemloft.net> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Longpeng <longpeng2@huawei.com> Cc: Mina Almasry <almasrymina@google.com> Cc: Nitesh Narayan Lal <nitesh@redhat.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Xu <peterx@redhat.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Anders Roxell <anders.roxell@linaro.org> Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Cc: Qian Cai <cai@lca.pw> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Link: http://lkml.kernel.org/r/20200417185049.275845-5-mike.kravetz@oracle.comSigned-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Mike Kravetz authored
hugetlb_add_hstate() prints a warning if the hstate already exists. This was originally done as part of kernel command line parsing. If 'hugepagesz=' was specified more than once, the warning pr_warn("hugepagesz= specified twice, ignoring\n"); would be printed. Some architectures want to enable all huge page sizes. They would call hugetlb_add_hstate for all supported sizes. However, this was done after command line processing and as a result hstates could have already been created for some sizes. To make sure no warning were printed, there would often be code like: if (!size_to_hstate(size) hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT) The only time we want to print the warning is as the result of command line processing. So, remove the warning from hugetlb_add_hstate and add it to the single arch independent routine processing "hugepagesz=". After this, calls to size_to_hstate() in arch specific code can be removed and hugetlb_add_hstate can be called without worrying about warning messages. [mike.kravetz@oracle.com: fix hugetlb initialization] Link: http://lkml.kernel.org/r/4c36c6ce-3774-78fa-abc4-b7346bf24348@oracle.com Link: http://lkml.kernel.org/r/20200428205614.246260-5-mike.kravetz@oracle.comSigned-off-by:Anders Roxell <anders.roxell@linaro.org> Acked-by:
Mina Almasry <almasrymina@google.com> Acked-by: Gerald Schaefer <gerald.schaefer@de.ibm.com> [s390] Acked-by:
-
Mike Kravetz authored
Now that architectures provide arch_hugetlb_valid_size(), parsing of "hugepagesz=" can be done in architecture independent code. Create a single routine to handle hugepagesz= parsing and remove all arch specific routines. We can also remove the interface hugetlb_bad_size() as this is no longer used outside arch independent code. This also provides consistent behavior of hugetlbfs command line options. The hugepagesz= option should only be specified once for a specific size, but some architectures allow multiple instances. This appears to be more of an oversight when code was added by some architectures to set up ALL huge pages sizes. Signed-off-by:
Peter Xu <peterx@redhat.com> Acked-by:
-
Mike Kravetz authored
Patch series "Clean up hugetlb boot command line processing", v4. Longpeng(Mike) reported a weird message from hugetlb command line processing and proposed a solution [1]. While the proposed patch does address the specific issue, there are other related issues in command line processing. As hugetlbfs evolved, updates to command line processing have been made to meet immediate needs and not necessarily in a coordinated manner. The result is that some processing is done in arch specific code, some is done in arch independent code and coordination is problematic. Semantics can vary between architectures. The patch series does the following: - Define arch specific arch_hugetlb_valid_size routine used to validate passed huge page sizes. - Move hugepagesz= command line parsing out of arch specific code and into an arch independent routine. - Clean up command line processing to follow desired semantics and document those semantics. [1] https://lore.kernel.org/linux-mm/20200305033014.1152-1-longpeng2@huawei.com This patch (of 3): The architecture independent routine hugetlb_default_setup sets up the default huge pages size. It has no way to verify if the passed value is valid, so it accepts it and attempts to validate at a later time. This requires undocumented cooperation between the arch specific and arch independent code. For architectures that support more than one huge page size, provide a routine arch_hugetlb_valid_size to validate a huge page size. hugetlb_default_setup can use this to validate passed values. arch_hugetlb_valid_size will also be used in a subsequent patch to move processing of the "hugepagesz=" in arch specific code to a common routine in arch independent code. Signed-off-by:
-
Kirill A. Shutemov authored
'max_ptes_shared' specifies how many pages can be shared across multiple processes. Exceeding the number would block the collapse:: /sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_shared A higher value may increase memory footprint for some workloads. By default, at least half of pages has to be not shared. [colin.king@canonical.com: fix several spelling mistakes] Link: http://lkml.kernel.org/r/20200420084241.65433-1-colin.king@canonical.comSigned-off-by:
Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Signed-off-by:
Colin Ian King <colin.king@canonical.com> Signed-off-by:
Zi Yan <ziy@nvidia.com> Reviewed-by:
William Kucharski <william.kucharski@oracle.com> Reviewed-by:
Yang Shi <yang.shi@linux.alibaba.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Ralph Campbell <rcampbell@nvidia.com> Link: http://lkml.kernel.org/r/20200416160026.16538-9-kirill.shutemov@linux.intel.comSigned-off-by:
-
Kirill A. Shutemov authored
Currently we have different copy-on-write semantics for anon- and file-THP. For anon-THP we try to allocate huge page on the write fault, but on file-THP we split PMD and allocate 4k page. Arguably, file-THP semantics is more desirable: we don't necessary want to unshare full PMD range from the parent on the first access. This is the primary reason THP is unusable for some workloads, like Redis. The original THP refcounting didn't allow to have PTE-mapped compound pages, so we had no options, but to allocate huge page on CoW (with fallback to 512 4k pages). The current refcounting doesn't have such limitations and we can cut a lot of complex code out of fault path. khugepaged is now able to recover THP from such ranges if the configuration allows. Signed-off-by:
-
Kirill A. Shutemov authored
We can collapse PTE-mapped compound pages. We only need to avoid handling them more than once: lock/unlock page only once if it's present in the PMD range multiple times as it handled on compound level. The same goes for LRU isolation and putback. Signed-off-by:
-
Kirill A. Shutemov authored
The page can be included into collapse as long as it doesn't have extra pins (from GUP or otherwise). Logic to check the refcount is moved to a separate function. For pages in swap cache, add compound_nr(page) to the expected refcount, in order to handle the compound page case. This is in preparation for the following patch. VM_BUG_ON_PAGE() was removed from __collapse_huge_page_copy() as the invariant it checks is no longer valid: the source can be mapped multiple times now. [yang.shi@linux.alibaba.com: remove error message when checking external pins] Link: http://lkml.kernel.org/r/1589317383-9595-1-git-send-email-yang.shi@linux.alibaba.com [cai@lca.pw: fix set-but-not-used warning] Link: http://lkml.kernel.org/r/20200521145644.GA6367@ovpn-112-192.phx2.redhat.comSigned-off-by:
John Hubbard <jhubbard@nvidia.com> Acked-by:
-
Kirill A. Shutemov authored
collapse_huge_page() tries to swap in pages that are part of the PMD range. Just swapped in page goes though LRU add cache. The cache gets extra reference on the page. The extra reference can lead to the collapse fail: the following __collapse_huge_page_isolate() would check refcount and abort collapse seeing unexpected refcount. The fix is to drain local LRU add cache in __collapse_huge_page_swapin() if we successfully swapped in any pages. Signed-off-by:
-
Kirill A. Shutemov authored
Having a page in LRU add cache offsets page refcount and gives false-negative on PageLRU(). It reduces collapse success rate. Drain all LRU add caches before scanning. It happens relatively rare and should not disturb the system too much. Signed-off-by:
-
Kirill A. Shutemov authored
__collapse_huge_page_swapin() checks the number of referenced PTE to decide if the memory range is hot enough to justify swapin. We have few problems with the approach: - It is way too late: we can do the check much earlier and safe time. khugepaged_scan_pmd() already knows if we have any pages to swap in and number of referenced page. - It stops collapse altogether if there's not enough referenced pages, not only swappingin. Fix it by making the right check early. We also can avoid additional page table scanning if khugepaged_scan_pmd() haven't found any swap entries. Fixes: 0db501f7 ("mm, thp: convert from optimistic swapin collapsing to conservative") Signed-off-by:
-
Kirill A. Shutemov authored
Patch series "thp/khugepaged improvements and CoW semantics", v4. The patchset adds khugepaged selftest (anon-THP only for now), expands cases khugepaged can handle and switches anon-THP copy-on-write handling to 4k. This patch (of 8): The test checks if khugepaged is able to recover huge page where we expect to do so. It only covers anon-THP for now. Currently the test shows few failures. They are going to be addressed by the following patches. [colin.king@canonical.com: fix several spelling mistakes] Link: http://lkml.kernel.org/r/20200420084241.65433-1-colin.king@canonical.com [aneesh.kumar@linux.ibm.com: replace the usage of system(3) in the test] Link: http://lkml.kernel.org/r/20200429110727.89388-1-aneesh.kumar@linux.ibm.com [kirill@shutemov.name: fixup for issues I've noticed] Link: http://lkml.kernel.org/r/20200429124816.jp272trghrzxx5j5@box [jhubbard@nvidia.com: add khugepaged to .gitignore] Link: http://lkml.kernel.org/r/20200517002509.362401-1-jhubbard@nvidia.comSigned-off-by:
Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Signed-off-by:
-
Chen Tao authored
Add missing line breaks on pr_warn(). Signed-off-by:
Chen Tao <chentao107@huawei.com> Signed-off-by:
-
Daniel Jordan authored
Add Documentation for multithreaded jobs. Signed-off-by:
Daniel Jordan <daniel.m.jordan@oracle.com> Signed-off-by:
Josh Triplett <josh@joshtriplett.org> Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Robert Elliott <elliott@hpe.com> Cc: Shile Zhang <shile.zhang@linux.alibaba.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Steven Sistare <steven.sistare@oracle.com> Cc: Tejun Heo <tj@kernel.org> Cc: Zi Yan <ziy@nvidia.com> Link: http://lkml.kernel.org/r/20200527173608.2885243-9-daniel.m.jordan@oracle.comSigned-off-by:
-
Daniel Jordan authored
Using padata during deferred init has only been tested on x86, so for now limit it to this architecture. If another arch wants this, it can find the max thread limit that's best for it and override deferred_page_init_max_threads(). Signed-off-by:
-
Daniel Jordan authored
Deferred struct page init is a significant bottleneck in kernel boot. Optimizing it maximizes availability for large-memory systems and allows spinning up short-lived VMs as needed without having to leave them running. It also benefits bare metal machines hosting VMs that are sensitive to downtime. In projects such as VMM Fast Restart[1], where guest state is preserved across kexec reboot, it helps prevent application and network timeouts in the guests. Multithread to take full advantage of system memory bandwidth. The maximum number of threads is capped at the number of CPUs on the node because speedups always improve with additional threads on every system tested, and at this phase of boot, the system is otherwise idle and waiting on page init to finish. Helper threads operate on section-aligned ranges to both avoid false sharing when setting the pageblock's migrate type and to avoid accessing uninitialized buddy pages, though max order alignment is enough for the latter. The minimum chunk size is also a section. There was benefit to using multiple threads even on relatively small memory (1G) systems, and this is the smallest size that the alignment allows. The time (milliseconds) is the slowest node to initialize since boot blocks until all nodes finish. intel_pstate is loaded in active mode without hwp and with turbo enabled, and intel_idle is active as well. Intel(R) Xeon(R) Platinum 8167M CPU @ 2.00GHz (Skylake, bare metal) 2 nodes * 26 cores * 2 threads = 104 CPUs 384G/node = 768G memory kernel boot deferred init ------------------------ ------------------------ node% (thr) speedup time_ms (stdev) speedup time_ms (stdev) ( 0) -- 4089.7 ( 8.1) -- 1785.7 ( 7.6) 2% ( 1) 1.7% 4019.3 ( 1.5) 3.8% 1717.7 ( 11.8) 12% ( 6) 34.9% 2662.7 ( 2.9) 79.9% 359.3 ( 0.6) 25% ( 13) 39.9% 2459.0 ( 3.6) 91.2% 157.0 ( 0.0) 37% ( 19) 39.2% 2485.0 ( 29.7) 90.4% 172.0 ( 28.6) 50% ( 26) 39.3% 2482.7 ( 25.7) 90.3% 173.7 ( 30.0) 75% ( 39) 39.0% 2495.7 ( 5.5) 89.4% 190.0 ( 1.0) 100% ( 52) 40.2% 2443.7 ( 3.8) 92.3% 138.0 ( 1.0) Intel(R) Xeon(R) CPU E5-2699C v4 @ 2.20GHz (Broadwell, kvm guest) 1 node * 16 cores * 2 threads = 32 CPUs 192G/node = 192G memory kernel boot deferred init ------------------------ ------------------------ node% (thr) speedup time_ms (stdev) speedup time_ms (stdev) ( 0) -- 1988.7 ( 9.6) -- 1096.0 ( 11.5) 3% ( 1) 1.1% 1967.0 ( 17.6) 0.3% 1092.7 ( 11.0) 12% ( 4) 41.1% 1170.3 ( 14.2) 73.8% 287.0 ( 3.6) 25% ( 8) 47.1% 1052.7 ( 21.9) 83.9% 177.0 ( 13.5) 38% ( 12) 48.9% 1016.3 ( 12.1) 86.8% 144.7 ( 1.5) 50% ( 16) 48.9% 1015.7 ( 8.1) 87.8% 134.0 ( 4.4) 75% ( 24) 49.1% 1012.3 ( 3.1) 88.1% 130.3 ( 2.3) 100% ( 32) 49.5% 1004.0 ( 5.3) 88.5% 125.7 ( 2.1) Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz (Haswell, bare metal) 2 nodes * 18 cores * 2 threads = 72 CPUs 128G/node = 256G memory kernel boot deferred init ------------------------ ------------------------ node% (thr) speedup time_ms (stdev) speedup time_ms (stdev) ( 0) -- 1680.0 ( 4.6) -- 627.0 ( 4.0) 3% ( 1) 0.3% 1675.7 ( 4.5) -0.2% 628.0 ( 3.6) 11% ( 4) 25.6% 1250.7 ( 2.1) 67.9% 201.0 ( 0.0) 25% ( 9) 30.7% 1164.0 ( 17.3) 81.8% 114.3 ( 17.7) 36% ( 13) 31.4% 1152.7 ( 10.8) 84.0% 100.3 ( 17.9) 50% ( 18) 31.5% 1150.7 ( 9.3) 83.9% 101.0 ( 14.1) 75% ( 27) 31.7% 1148.0 ( 5.6) 84.5% 97.3 ( 6.4) 100% ( 36) 32.0% 1142.3 ( 4.0) 85.6% 90.0 ( 1.0) AMD EPYC 7551 32-Core Processor (Zen, kvm guest) 1 node * 8 cores * 2 threads = 16 CPUs 64G/node = 64G memory kernel boot deferred init ------------------------ ------------------------ node% (thr) speedup time_ms (stdev) speedup time_ms (stdev) ( 0) -- 1029.3 ( 25.1) -- 240.7 ( 1.5) 6% ( 1) -0.6% 1036.0 ( 7.8) -2.2% 246.0 ( 0.0) 12% ( 2) 11.8% 907.7 ( 8.6) 44.7% 133.0 ( 1.0) 25% ( 4) 13.9% 886.0 ( 10.6) 62.6% 90.0 ( 6.0) 38% ( 6) 17.8% 845.7 ( 14.2) 69.1% 74.3 ( 3.8) 50% ( 8) 16.8% 856.0 ( 22.1) 72.9% 65.3 ( 5.7) 75% ( 12) 15.4% 871.0 ( 29.2) 79.8% 48.7 ( 7.4) 100% ( 16) 21.0% 813.7 ( 21.0) 80.5% 47.0 ( 5.2) Server-oriented distros that enable deferred page init sometimes run in small VMs, and they still benefit even though the fraction of boot time saved is smaller: AMD EPYC 7551 32-Core Processor (Zen, kvm guest) 1 node * 2 cores * 2 threads = 4 CPUs 16G/node = 16G memory kernel boot deferred init ------------------------ ------------------------ node% (thr) speedup time_ms (stdev) speedup time_ms (stdev) ( 0) -- 716.0 ( 14.0) -- 49.7 ( 0.6) 25% ( 1) 1.8% 703.0 ( 5.3) -4.0% 51.7 ( 0.6) 50% ( 2) 1.6% 704.7 ( 1.2) 43.0% 28.3 ( 0.6) 75% ( 3) 2.7% 696.7 ( 13.1) 49.7% 25.0 ( 0.0) 100% ( 4) 4.1% 687.0 ( 10.4) 55.7% 22.0 ( 0.0) Intel(R) Xeon(R) CPU E5-2699 v3 @ 2.30GHz (Haswell, kvm guest) 1 node * 2 cores * 2 threads = 4 CPUs 14G/node = 14G memory kernel boot deferred init ------------------------ ------------------------ node% (thr) speedup time_ms (stdev) speedup time_ms (stdev) ( 0) -- 787.7 ( 6.4) -- 122.3 ( 0.6) 25% ( 1) 0.2% 786.3 ( 10.8) -2.5% 125.3 ( 2.1) 50% ( 2) 5.9% 741.0 ( 13.9) 37.6% 76.3 ( 19.7) 75% ( 3) 8.3% 722.0 ( 19.0) 49.9% 61.3 ( 3.2) 100% ( 4) 9.3% 714.7 ( 9.5) 56.4% 53.3 ( 1.5) On Josh's 96-CPU and 192G memory system: Without this patch series: [ 0.487132] node 0 initialised, 23398907 pages in 292ms [ 0.499132] node 1 initialised, 24189223 pages in 304ms ... [ 0.629376] Run /sbin/init as init process With this patch series: [ 0.231435] node 1 initialised, 24189223 pages in 32ms [ 0.236718] node 0 initialised, 23398907 pages in 36ms [1] https://static.sched.com/hosted_files/kvmforum2019/66/VMM-fast-restart_kvmforum2019.pdfSigned-off-by:Alexander Duyck <alexander.h.duyck@linux.intel.com> Cc: Alex Williamson <alex.williamson@redhat.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Pavel Machek <pavel@ucw.cz> Cc: Pavel Tatashin <pasha.tatashin@soleen.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Robert Elliott <elliott@hpe.com> Cc: Shile Zhang <shile.zhang@linux.alibaba.com> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Steven Sistare <steven.sistare@oracle.com> Cc: Tejun Heo <tj@kernel.org> Cc: Zi Yan <ziy@nvidia.com> Link: http://lkml.kernel.org/r/20200527173608.2885243-7-daniel.m.jordan@oracle.comSigned-off-by:
-
Daniel Jordan authored
Deferred page init used to report the number of pages initialized: node 0 initialised, 32439114 pages in 97ms Tracking this makes the code more complicated when using multiple threads. Given that the statistic probably has limited value, especially since a zone grows on demand so that the page count can vary, just remove it. The boot message now looks like node 0 deferred pages initialised in 97ms Suggested-by:
-
Daniel Jordan authored
Sometimes the kernel doesn't take full advantage of system memory bandwidth, leading to a single CPU spending excessive time in initialization paths where the data scales with memory size. Multithreading naturally addresses this problem. Extend padata, a framework that handles many parallel yet singlethreaded jobs, to also handle multithreaded jobs by adding support for splitting up the work evenly, specifying a minimum amount of work that's appropriate for one helper thread to do, load balancing between helpers, and coordinating them. This is inspired by work from Pavel Tatashin and Steve Sistare. Signed-off-by:
-
Daniel Jordan authored
padata allocates per-CPU, per-instance work structs for parallel jobs. A do_parallel call assigns a job to a sequence number and hashes the number to a CPU, where the job will eventually run using the corresponding work. This approach fit with how padata used to bind a job to each CPU round-robin, makes less sense after commit bfde23ce ("padata: unbind parallel jobs from specific CPUs") because a work isn't bound to a particular CPU anymore, and isn't needed at all for multithreaded jobs because they don't have sequence numbers. Replace the per-CPU works with a preallocated pool, which allows sharing them between existing padata users and the upcoming multithreaded user. The pool will also facilitate setting NUMA-aware concurrency limits with later users. The pool is sized according to the number of possible CPUs. With this limit, MAX_OBJ_NUM no longer makes sense, so remove it. If the global pool is exhausted, a parallel job is run in the current task instead to throttle a system trying to do too much in parallel. Signed-off-by:
-
Daniel Jordan authored
padata will soon initialize the system's struct pages in parallel, so it needs to be ready by page_alloc_init_late(). The error return from padata_driver_init() triggers an initcall warning, so add a warning to padata_init() to avoid silent failure. Signed-off-by:
-
Daniel Jordan authored
Patch series "padata: parallelize deferred page init", v3. Deferred struct page init is a bottleneck in kernel boot--the biggest for us and probably others. Optimizing it maximizes availability for large-memory systems and allows spinning up short-lived VMs as needed without having to leave them running. It also benefits bare metal machines hosting VMs that are sensitive to downtime. In projects such as VMM Fast Restart[1], where guest state is preserved across kexec reboot, it helps prevent application and network timeouts in the guests. So, multithread deferred init to take full advantage of system memory bandwidth. Extend padata, a framework that handles many parallel singlethreaded jobs, to handle multithreaded jobs as well by adding support for splitting up the work evenly, specifying a minimum amount of work that's appropriate for one helper thread to do, load balancing between helpers, and coordinating them. More documentation in patches 4 and 8. This series is the first step in a project to address other memory proportional bottlenecks in the kernel such as pmem struct page init, vfio page pinning, hugetlb fallocate, and munmap. Deferred page init doesn't require concurrency limits, resource control, or priority adjustments like these other users will because it happens during boot when the system is otherwise idle and waiting for page init to finish. This has been run on a variety of x86 systems and speeds up kernel boot by 4% to 49%, saving up to 1.6 out of 4 seconds. Patch 6 has more numbers. This patch (of 8): padata_driver_exit() is unnecessary because padata isn't built as a module and doesn't exit. padata's init routine will soon allocate memory, so getting rid of the exit function now avoids pointless code to free it. Signed-off-by:
-
Pavel Tatashin authored
Now that deferred pages are initialized with interrupts enabled we can replace touch_nmi_watchdog() with cond_resched(), as it was before 3a2d7fa8. For now, we cannot do the same in deferred_grow_zone() as it is still initializes pages with interrupts disabled. This change fixes RCU problem described in https://lkml.kernel.org/r/20200401104156.11564-2-david@redhat.com [ 60.474005] rcu: INFO: rcu_sched detected stalls on CPUs/tasks: [ 60.475000] rcu: 1-...0: (0 ticks this GP) idle=02a/1/0x4000000000000000 softirq=1/1 fqs=15000 [ 60.475000] rcu: (detected by 0, t=60002 jiffies, g=-1199, q=1) [ 60.475000] Sending NMI from CPU 0 to CPUs 1: [ 1.760091] NMI backtrace for cpu 1 [ 1.760091] CPU: 1 PID: 20 Comm: pgdatinit0 Not tainted 4.18.0-147.9.1.el8_1.x86_64 #1 [ 1.760091] Hardware name: Red Hat KVM, BIOS 1.13.0-1.module+el8.2.0+5520+4e5817f3 04/01/2014 [ 1.760091] RIP: 0010:__init_single_page.isra.65+0x10/0x4f [ 1.760091] Code: 48 83 cf 63 48 89 f8 0f 1f 40 00 48 89 c6 48 89 d7 e8 6b 18 80 ff 66 90 5b c3 31 c0 b9 10 00 00 00 49 89 f8 48 c1 e6 33 f3 ab <b8> 07 00 00 00 48 c1 e2 36 41 c7 40 34 01 00 00 00 48 c1 e0 33 41 [ 1.760091] RSP: 0000:ffffba783123be40 EFLAGS: 00000006 [ 1.760091] RAX: 0000000000000000 RBX: fffffad34405e300 RCX: 0000000000000000 [ 1.760091] RDX: 0000000000000000 RSI: 0010000000000000 RDI: fffffad34405e340 [ 1.760091] RBP: 0000000033f3177e R08: fffffad34405e300 R09: 0000000000000002 [ 1.760091] R10: 000000000000002b R11: ffff98afb691a500 R12: 0000000000000002 [ 1.760091] R13: 0000000000000000 R14: 000000003f03ea00 R15: 000000003e10178c [ 1.760091] FS: 0000000000000000(0000) GS:ffff9c9ebeb00000(0000) knlGS:0000000000000000 [ 1.760091] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1.760091] CR2: 00000000ffffffff CR3: 000000a1cf20a001 CR4: 00000000003606e0 [ 1.760091] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 1.760091] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 1.760091] Call Trace: [ 1.760091] deferred_init_pages+0x8f/0xbf [ 1.760091] deferred_init_memmap+0x184/0x29d [ 1.760091] ? deferred_free_pages.isra.97+0xba/0xba [ 1.760091] kthread+0x112/0x130 [ 1.760091] ? kthread_flush_work_fn+0x10/0x10 [ 1.760091] ret_from_fork+0x35/0x40 [ 89.123011] node 0 initialised, 1055935372 pages in 88650ms Fixes: 3a2d7fa8 ("mm: disable interrupts while initializing deferred pages") Reported-by:
Yiqian Wei <yiwei@redhat.com> Signed-off-by:
Pavel Tatashin <pasha.tatashin@soleen.com> Signed-off-by:
David Hildenbrand <david@redhat.com> Reviewed-by:
Pankaj Gupta <pankaj.gupta.linux@gmail.com> Acked-by:
Michal Hocko <mhocko@suse.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: James Morris <jmorris@namei.org> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Sasha Levin <sashal@kernel.org> Cc: Shile Zhang <shile.zhang@linux.alibaba.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: <stable@vger.kernel.org> [4.17+] Link: http://lkml.kernel.org/r/20200403140952.17177-4-pasha.tatashin@soleen.comSigned-off-by:
-
Pavel Tatashin authored
Initializing struct pages is a long task and keeping interrupts disabled for the duration of this operation introduces a number of problems. 1. jiffies are not updated for long period of time, and thus incorrect time is reported. See proposed solution and discussion here: lkml/20200311123848.118638-1-shile.zhang@linux.alibaba.com 2. It prevents farther improving deferred page initialization by allowing intra-node multi-threading. We are keeping interrupts disabled to solve a rather theoretical problem that was never observed in real world (See 3a2d7fa8). Let's keep interrupts enabled. In case we ever encounter a scenario where an interrupt thread wants to allocate large amount of memory this early in boot we can deal with that by growing zone (see deferred_grow_zone()) by the needed amount before starting deferred_init_memmap() threads. Before: [ 1.232459] node 0 initialised, 12058412 pages in 1ms After: [ 1.632580] node 0 initialised, 12051227 pages in 436ms Fixes: 3a2d7fa8 ("mm: disable interrupts while initializing deferred pages") Reported-by:
Shile Zhang <shile.zhang@linux.alibaba.com> Signed-off-by:
Vlastimil Babka <vbabka@suse.cz> Cc: Dan Williams <dan.j.williams@intel.com> Cc: James Morris <jmorris@namei.org> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Sasha Levin <sashal@kernel.org> Cc: Yiqian Wei <yiwei@redhat.com> Cc: <stable@vger.kernel.org> [4.17+] Link: http://lkml.kernel.org/r/20200403140952.17177-3-pasha.tatashin@soleen.comSigned-off-by:
-
Daniel Jordan authored
Patch series "initialize deferred pages with interrupts enabled", v4. Keep interrupts enabled during deferred page initialization in order to make code more modular and allow jiffies to update. Original approach, and discussion can be found here: http://lkml.kernel.org/r/20200311123848.118638-1-shile.zhang@linux.alibaba.com This patch (of 3): deferred_init_memmap() disables interrupts the entire time, so it calls touch_nmi_watchdog() periodically to avoid soft lockup splats. Soon it will run with interrupts enabled, at which point cond_resched() should be used instead. deferred_grow_zone() makes the same watchdog calls through code shared with deferred init but will continue to run with interrupts disabled, so it can't call cond_resched(). Pull the watchdog calls up to these two places to allow the first to be changed later, independently of the second. The frequency reduces from twice per pageblock (init and free) to once per max order block. Fixes: 3a2d7fa8 ("mm: disable interrupts while initializing deferred pages") Signed-off-by:
-
Anshuman Khandual authored
Restrict elements in compound_page_dtors[] array per NR_COMPOUND_DTORS and explicitly position them according to enum compound_dtor_id. This improves protection against possible misalignment between compound_page_dtors[] and enum compound_dtor_id later on. Signed-off-by:
Anshuman Khandual <anshuman.khandual@arm.com> Signed-off-by:
-
Charan Teja Reddy authored
Updating the zone watermarks by any means, like min_free_kbytes, water_mark_scale_factor etc, when ->watermark_boost is set will result in higher low and high watermarks than the user asked. Below are the steps to reproduce the problem on system setup of Android kernel running on Snapdragon hardware. 1) Default settings of the system are as below: #cat /proc/sys/vm/min_free_kbytes = 5162 #cat /proc/zoneinfo | grep -e boost -e low -e "high " -e min -e Node Node 0, zone Normal min 797 low 8340 high 8539 2) Monitor the zone->watermark_boost(by adding a debug print in the kernel) and whenever it is greater than zero value, write the same value of min_free_kbytes obtained from step 1. #echo 5162 > /proc/sys/vm/min_free_kbytes 3) Then read the zone watermarks in the system while the ->watermark_boost is zero. This should show the same values of watermarks as step 1 but shown a higher values than asked. #cat /proc/zoneinfo | grep -e boost -e low -e "high " -e min -e Node Node 0, zone Normal min 797 low 21148 high 21347 These higher values are because of updating the zone watermarks using the macro min_wmark_pages(zone) which also adds the zone->watermark_boost. #define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost) So the steps that lead to the issue are: 1) On the extfrag event, watermarks are boosted by storing the required value in ->watermark_boost. 2) User tries to update the zone watermarks level in the system through min_free_kbytes or watermark_scale_factor. 3) Later, when kswapd woke up, it resets the zone->watermark_boost to zero. In step 2), we use the min_wmark_pages() macro to store the watermarks in the zone structure thus the values are always offsetted by ->watermark_boost value. This can be avoided by resetting the ->watermark_boost to zero before it is used. Signed-off-by:
Charan Teja Reddy <charante@codeaurora.org> Signed-off-by:
Baoquan He <bhe@redhat.com> Cc: Vinayak Menon <vinmenon@codeaurora.org> Link: http://lkml.kernel.org/r/1589457511-4255-1-git-send-email-charante@codeaurora.orgSigned-off-by:
-
Sandipan Das authored
Initially, the per-cpu pagesets of each zone are set to the boot pagesets. The real pagesets are allocated later but before that happens, page allocations do occur and the numa stats for the boot pagesets get incremented since they are common to all zones at that point. The real pagesets, however, are allocated for the populated zones only. Unpopulated zones, like those associated with memory-less nodes, continue using the boot pageset and end up skewing the numa stats of the corresponding node. E.g. $ numactl -H available: 2 nodes (0-1) node 0 cpus: 0 1 2 3 node 0 size: 0 MB node 0 free: 0 MB node 1 cpus: 4 5 6 7 node 1 size: 8131 MB node 1 free: 6980 MB node distances: node 0 1 0: 10 40 1: 40 10 $ numastat node0 node1 numa_hit 108 56495 numa_miss 0 0 numa_foreign 0 0 interleave_hit 0 4537 local_node 108 31547 other_node 0 24948 Hence, the boot pageset stats need to be cleared after the real pagesets are allocated. After this point, the stats of the boot pagesets do not change as page allocations requested for a memory-less node will either fail (if __GFP_THISNODE is used) or get fulfilled by a preferred zone of a different node based on the fallback zonelist. [sandipan@linux.ibm.com: v3] Link: http://lkml.kernel.org/r/20200511170356.162531-1-sandipan@linux.ibm.comSigned-off-by: -
Wei Yang authored
Pageblock migrate type is encoded in GFP flags, just as zone_type and zonelist. Currently we use gfp_zone() and gfp_zonelist() to extract related information, it would be proper to use the same naming convention for migrate type. Signed-off-by:
Wei Yang <richard.weiyang@gmail.com> Signed-off-by:
-
Wei Yang authored
Slightly simplify the code by initializing user_mask with NODE_MASK_NONE, instead of later calling nodes_clear(). This saves a line of code. Signed-off-by:
-
Joonsoo Kim authored
classzone_idx is just different name for high_zoneidx now. So, integrate them and add some comment to struct alloc_context in order to reduce future confusion about the meaning of this variable. The accessor, ac_classzone_idx() is also removed since it isn't needed after integration. In addition to integration, this patch also renames high_zoneidx to highest_zoneidx since it represents more precise meaning. Signed-off-by:
Joonsoo Kim <iamjoonsoo.kim@lge.com> Signed-off-by:
David Rientjes <rientjes@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Michal Hocko <mhocko@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Ye Xiaolong <xiaolong.ye@intel.com> Link: http://lkml.kernel.org/r/1587095923-7515-3-git-send-email-iamjoonsoo.kim@lge.comSigned-off-by:
-
Joonsoo Kim authored
Patch series "integrate classzone_idx and high_zoneidx", v5. This patchset is followup of the problem reported and discussed two years ago [1, 2]. The problem this patchset solves is related to the classzone_idx on the NUMA system. It causes a problem when the lowmem reserve protection exists for some zones on a node that do not exist on other nodes. This problem was reported two years ago, and, at that time, the solution got general agreements [2]. But it was not upstreamed. [1]: http://lkml.kernel.org/r/20180102063528.GG30397@yexl-desktop [2]: http://lkml.kernel.org/r/1525408246-14768-1-git-send-email-iamjoonsoo.kim@lge.com This patch (of 2): Currently, we use classzone_idx to calculate lowmem reserve proetection for an allocation request. This classzone_idx causes a problem on NUMA systems when the lowmem reserve protection exists for some zones on a node that do not exist on other nodes. Before further explanation, I should first clarify how to compute the classzone_idx and the high_zoneidx. - ac->high_zoneidx is computed via the arcane gfp_zone(gfp_mask) and represents the index of the highest zone the allocation can use - classzone_idx was supposed to be the index of the highest zone on the local node that the allocation can use, that is actually available in the system Think about following example. Node 0 has 4 populated zone, DMA/DMA32/NORMAL/MOVABLE. Node 1 has 1 populated zone, NORMAL. Some zones, such as MOVABLE, doesn't exist on node 1 and this makes following difference. Assume that there is an allocation request whose gfp_zone(gfp_mask) is the zone, MOVABLE. Then, it's high_zoneidx is 3. If this allocation is initiated on node 0, it's classzone_idx is 3 since actually available/usable zone on local (node 0) is MOVABLE. If this allocation is initiated on node 1, it's classzone_idx is 2 since actually available/usable zone on local (node 1) is NORMAL. You can see that classzone_idx of the allocation request are different according to their starting node, even if their high_zoneidx is the same. Think more about these two allocation requests. If they are processed on local, there is no problem. However, if allocation is initiated on node 1 are processed on remote, in this example, at the NORMAL zone on node 0, due to memory shortage, problem occurs. Their different classzone_idx leads to different lowmem reserve and then different min watermark. See the following example. root@ubuntu:/sys/devices/system/memory# cat /proc/zoneinfo Node 0, zone DMA per-node stats ... pages free 3965 min 5 low 8 high 11 spanned 4095 present 3998 managed 3977 protection: (0, 2961, 4928, 5440) ... Node 0, zone DMA32 pages free 757955 min 1129 low 1887 high 2645 spanned 1044480 present 782303 managed 758116 protection: (0, 0, 1967, 2479) ... Node 0, zone Normal pages free 459806 min 750 low 1253 high 1756 spanned 524288 present 524288 managed 503620 protection: (0, 0, 0, 4096) ... Node 0, zone Movable pages free 130759 min 195 low 326 high 457 spanned 1966079 present 131072 managed 131072 protection: (0, 0, 0, 0) ... Node 1, zone DMA pages free 0 min 0 low 0 high 0 spanned 0 present 0 managed 0 protection: (0, 0, 1006, 1006) Node 1, zone DMA32 pages free 0 min 0 low 0 high 0 spanned 0 present 0 managed 0 protection: (0, 0, 1006, 1006) Node 1, zone Normal per-node stats ... pages free 233277 min 383 low 640 high 897 spanned 262144 present 262144 managed 257744 protection: (0, 0, 0, 0) ... Node 1, zone Movable pages free 0 min 0 low 0 high 0 spanned 262144 present 0 managed 0 protection: (0, 0, 0, 0) - static min watermark for the NORMAL zone on node 0 is 750. - lowmem reserve for the request with classzone idx 3 at the NORMAL on node 0 is 4096. - lowmem reserve for the request with classzone idx 2 at the NORMAL on node 0 is 0. So, overall min watermark is: allocation initiated on node 0 (classzone_idx 3): 750 + 4096 = 4846 allocation initiated on node 1 (classzone_idx 2): 750 + 0 = 750 Allocation initiated on node 1 will have some precedence than allocation initiated on node 0 because min watermark of the former allocation is lower than the other. So, allocation initiated on node 1 could succeed on node 0 when allocation initiated on node 0 could not, and, this could cause too many numa_miss allocation. Then, performance could be downgraded. Recently, there was a regression report about this problem on CMA patches since CMA memory are placed in ZONE_MOVABLE by those patches. I checked that problem is disappeared with this fix that uses high_zoneidx for classzone_idx. http://lkml.kernel.org/r/20180102063528.GG30397@yexl-desktop Using high_zoneidx for classzone_idx is more consistent way than previous approach because system's memory layout doesn't affect anything to it. With this patch, both classzone_idx on above example will be 3 so will have the same min watermark. allocation initiated on node 0: 750 + 4096 = 4846 allocation initiated on node 1: 750 + 4096 = 4846 One could wonder if there is a side effect that allocation initiated on node 1 will use higher bar when allocation is handled on local since classzone_idx could be higher than before. It will not happen because the zone without managed page doesn't contributes lowmem_reserve at all. Reported-by:
Ye Xiaolong <xiaolong.ye@intel.com> Signed-off-by:
-
Baoquan He authored
Because the lowmem reserve protection of a zone can't tell anything if the zone is empty, except of adding one more line in /proc/zoneinfo. Let's remove it from that zone's showing. Signed-off-by:
-
Baoquan He authored
When requesting memory allocation from a specific zone is not satisfied, it will fall to lower zone to try allocating memory. In this case, lower zone's ->lowmem_reserve[] will help protect its own memory resource. The higher the relevant ->lowmem_reserve[] is, the harder the upper zone can get memory from this lower zone. However, this protection mechanism should be applied to populated zone, but not an empty zone. So filling ->lowmem_reserve[] for empty zone is not necessary, and may mislead people that it's valid data in that zone. Node 2, zone DMA pages free 0 min 0 low 0 high 0 spanned 0 present 0 managed 0 protection: (0, 0, 1024, 1024) Node 2, zone DMA32 pages free 0 min 0 low 0 high 0 spanned 0 present 0 managed 0 protection: (0, 0, 1024, 1024) Node 2, zone Normal per-node stats nr_inactive_anon 0 nr_active_anon 143 nr_inactive_file 0 nr_active_file 0 nr_unevictable 0 nr_slab_reclaimable 45 nr_slab_unreclaimable 254 Here clear out zone->lowmem_reserve[] if zone is empty. Signed-off-by: -
Baoquan He authored
Patch series "improvements about lowmem_reserve and /proc/zoneinfo", v2. This patch (of 3): When people write to /proc/sys/vm/lowmem_reserve_ratio to change sysctl_lowmem_reserve_ratio[], setup_per_zone_lowmem_reserve() is called to recalculate all ->lowmem_reserve[] for each zone of all nodes as below: static void setup_per_zone_lowmem_reserve(void) { ... for_each_online_pgdat(pgdat) { for (j = 0; j < MAX_NR_ZONES; j++) { ... while (idx) { ... if (sysctl_lowmem_reserve_ratio[idx] < 1) { sysctl_lowmem_reserve_ratio[idx] = 0; lower_zone->lowmem_reserve[j] = 0; } else { ... } } } } Meanwhile, here, sysctl_lowmem_reserve_ratio[idx] will be tuned if its value is smaller than '1'. As we know, sysctl_lowmem_reserve_ratio[] is set for zone without regarding to which node it belongs to. That means the tuning will be done on all nodes, even though it has been done in the first node. And the tuning will be done too even when init_per_zone_wmark_min() calls setup_per_zone_lowmem_reserve(), where actually nobody tries to change sysctl_lowmem_reserve_ratio[]. So now move the tuning into lowmem_reserve_ratio_sysctl_handler(), to make code logic more reasonable. Signed-off-by: -
Baoquan He authored
Since commit 397dc00e ("mips: sgi-ip27: switch from DISCONTIGMEM to SPARSEMEM"), the last caller of free_bootmem_with_active_regions() was gone. Now no user calls it any more. Let's remove it. Signed-off-by:
-
Roman Gushchin authored
Currently a cma area is barely used by the page allocator because it's used only as a fallback from movable, however kswapd tries hard to make sure that the fallback path isn't used. This results in a system evicting memory and pushing data into swap, while lots of CMA memory is still available. This happens despite the fact that alloc_contig_range is perfectly capable of moving any movable allocations out of the way of an allocation. To effectively use the cma area let's alter the rules: if the zone has more free cma pages than the half of total free pages in the zone, use cma pageblocks first and fallback to movable blocks in the case of failure. [guro@fb.com: ifdef the cma-specific code] Link: http://lkml.kernel.org/r/20200311225832.GA178154@carbon.DHCP.thefacebook.comCo-developed-by:
Rik van Riel <riel@surriel.com> Signed-off-by:
Roman Gushchin <guro@fb.com> Signed-off-by:
Minchan Kim <minchan@kernel.org> Cc: Qian Cai <cai@lca.pw> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Joonsoo Kim <js1304@gmail.com> Link: http://lkml.kernel.org/r/20200306150102.3e77354b@imladris.surriel.comSigned-off-by:
-
Wei Yang authored
We share similar code in check_[new|free]_page_bad() to get the page's bad reason. Let's extract it and reduce code duplication. Signed-off-by:
-
Wei Yang authored
free_pages_check() is the counterpart of check_new_page(). Rename it to use the same naming convention. Signed-off-by:
-
Wei Yang authored
free_pages_check_bad() is the counterpart of check_new_page_bad(). Rename it to use the same naming convention. Signed-off-by:
-
Wei Yang authored
After commit 5b57b8f2 ("mm/debug.c: always print flags in dump_page()"), page->flags is always printed for a bad page. It is not necessary to have bad_flags any more. Suggested-by:
-
