> > I finally finished the testing w/o and with your above improvement > patch. Testing is done on a system with 128 cpus. The system with 288 > cpus is not available because of some console connection. Attach the log > here. In some testing after rebooting, I found it could take more than 30 > minutes, I am not sure if it's caused by my messy code change. I finally > cleaned up all of them and take a clean linux-next to test, then apply > your above draft code. > [root@dell-per6515-03 linux]# nproc > 128 > [root@dell-per6515-03 linux]# free -h > total used free shared buff/cache available > Mem: 124Gi 2.6Gi 122Gi 21Mi 402Mi 122Gi > Swap: 4.0Gi 0B 4.0Gi > > 1)linux-next kernel w/o improving code from Uladzislau > ------------------------------------------------------- > [root@dell-per6515-03 linux]# time tools/testing/selftests/mm/test_vmalloc.sh run_test_mask=127 nr_threads=64 > Run the test with following parameters: run_test_mask=127 nr_threads=64 > Done. > Check the kernel ring buffer to see the summary. > > real 4m28.018s > user 0m0.015s > sys 0m4.712s > [root@dell-per6515-03 ~]# sort -h /proc/allocinfo | tail -10 > 21405696 5226 mm/memory.c:1122 func:folio_prealloc > 26199936 7980 kernel/fork.c:309 func:alloc_thread_stack_node > 29822976 7281 mm/readahead.c:247 func:page_cache_ra_unbounded > 99090432 96768 drivers/iommu/iova.c:604 func:iova_magazine_alloc > 107638784 6320 mm/readahead.c:468 func:ra_alloc_folio > 120560528 29439 mm/mm_init.c:2521 func:alloc_large_system_hash > 134742016 32896 mm/percpu-vm.c:95 func:pcpu_alloc_pages > 263192576 64256 mm/page_ext.c:270 func:alloc_page_ext > 266797056 65136 include/linux/mm.h:2848 func:pagetable_alloc > 507617280 32796 mm/slub.c:2305 func:alloc_slab_page > [root@dell-per6515-03 ~]# > [root@dell-per6515-03 ~]# > [root@dell-per6515-03 linux]# time tools/testing/selftests/mm/test_vmalloc.sh run_test_mask=127 nr_threads=128 > Run the test with following parameters: run_test_mask=127 nr_threads=128 > Done. > Check the kernel ring buffer to see the summary. > > real 6m19.328s > user 0m0.005s > sys 0m9.476s > [root@dell-per6515-03 ~]# sort -h /proc/allocinfo | tail -10 > 21405696 5226 mm/memory.c:1122 func:folio_prealloc > 26889408 8190 kernel/fork.c:309 func:alloc_thread_stack_node > 29822976 7281 mm/readahead.c:247 func:page_cache_ra_unbounded > 99090432 96768 drivers/iommu/iova.c:604 func:iova_magazine_alloc > 107638784 6320 mm/readahead.c:468 func:ra_alloc_folio > 120560528 29439 mm/mm_init.c:2521 func:alloc_large_system_hash > 134742016 32896 mm/percpu-vm.c:95 func:pcpu_alloc_pages > 263192576 64256 mm/page_ext.c:270 func:alloc_page_ext > 550068224 34086 mm/slub.c:2305 func:alloc_slab_page > 664535040 162240 include/linux/mm.h:2848 func:pagetable_alloc > [root@dell-per6515-03 ~]# > [root@dell-per6515-03 ~]# > [root@dell-per6515-03 linux]# time tools/testing/selftests/mm/test_vmalloc.sh run_test_mask=127 nr_threads=256 > Run the test with following parameters: run_test_mask=127 nr_threads=256 > Done. > Check the kernel ring buffer to see the summary. > > real 19m10.657s > user 0m0.015s > sys 0m20.959s > [root@dell-per6515-03 ~]# sort -h /proc/allocinfo | tail -10 > 22441984 5479 mm/shmem.c:1634 func:shmem_alloc_folio > 26758080 8150 kernel/fork.c:309 func:alloc_thread_stack_node > 35880960 8760 mm/readahead.c:247 func:page_cache_ra_unbounded > 99090432 96768 drivers/iommu/iova.c:604 func:iova_magazine_alloc > 120560528 29439 mm/mm_init.c:2521 func:alloc_large_system_hash > 122355712 7852 mm/readahead.c:468 func:ra_alloc_folio > 134742016 32896 mm/percpu-vm.c:95 func:pcpu_alloc_pages > 263192576 64256 mm/page_ext.c:270 func:alloc_page_ext > 708231168 50309 mm/slub.c:2305 func:alloc_slab_page > 1107296256 270336 include/linux/mm.h:2848 func:pagetable_alloc > [root@dell-per6515-03 ~]# > > 2)linux-next kernel with improving code from Uladzislau > ----------------------------------------------------- > [root@dell-per6515-03 linux]# time tools/testing/selftests/mm/test_vmalloc.sh run_test_mask=127 nr_threads=64 > Run the test with following parameters: run_test_mask=127 nr_threads=64 > Done. > Check the kernel ring buffer to see the summary. > > real 4m27.226s > user 0m0.006s > sys 0m4.709s > [root@dell-per6515-03 linux]# sort -h /proc/allocinfo | tail -10 > 38023168 9283 mm/readahead.c:247 func:page_cache_ra_unbounded > 72228864 17634 fs/xfs/xfs_buf.c:390 [xfs] func:xfs_buf_alloc_pages > 99090432 96768 drivers/iommu/iova.c:604 func:iova_magazine_alloc > 99863552 97523 fs/xfs/xfs_icache.c:81 [xfs] func:xfs_inode_alloc > 120560528 29439 mm/mm_init.c:2521 func:alloc_large_system_hash > 136314880 33280 mm/percpu-vm.c:95 func:pcpu_alloc_pages > 184176640 10684 mm/readahead.c:468 func:ra_alloc_folio > 263192576 64256 mm/page_ext.c:270 func:alloc_page_ext > 284700672 69507 include/linux/mm.h:2848 func:pagetable_alloc > 601427968 36377 mm/slub.c:2305 func:alloc_slab_page > [root@dell-per6515-03 linux]# time tools/testing/selftests/mm/test_vmalloc.sh run_test_mask=127 nr_threads=128 > Run the test with following parameters: run_test_mask=127 nr_threads=128 > Done. > Check the kernel ring buffer to see the summary. > > real 6m16.960s > user 0m0.007s > sys 0m9.465s > [root@dell-per6515-03 linux]# sort -h /proc/allocinfo | tail -10 > 38158336 9316 mm/readahead.c:247 func:page_cache_ra_unbounded > 72220672 17632 fs/xfs/xfs_buf.c:390 [xfs] func:xfs_buf_alloc_pages > 99090432 96768 drivers/iommu/iova.c:604 func:iova_magazine_alloc > 99863552 97523 fs/xfs/xfs_icache.c:81 [xfs] func:xfs_inode_alloc > 120560528 29439 mm/mm_init.c:2521 func:alloc_large_system_hash > 136314880 33280 mm/percpu-vm.c:95 func:pcpu_alloc_pages > 184504320 10710 mm/readahead.c:468 func:ra_alloc_folio > 263192576 64256 mm/page_ext.c:270 func:alloc_page_ext > 427884544 104464 include/linux/mm.h:2848 func:pagetable_alloc > 697311232 45159 mm/slub.c:2305 func:alloc_slab_page > [root@dell-per6515-03 linux]# time tools/testing/selftests/mm/test_vmalloc.sh run_test_mask=127 nr_threads=256 > Run the test with following parameters: run_test_mask=127 nr_threads=256 > Done. > Check the kernel ring buffer to see the summary. > > real 21m15.673s > user 0m0.008s > sys 0m20.259s > [root@dell-per6515-03 linux]# sort -h /proc/allocinfo | tail -10 > 38158336 9316 mm/readahead.c:247 func:page_cache_ra_unbounded > 72224768 17633 fs/xfs/xfs_buf.c:390 [xfs] func:xfs_buf_alloc_pages > 99090432 96768 drivers/iommu/iova.c:604 func:iova_magazine_alloc > 99863552 97523 fs/xfs/xfs_icache.c:81 [xfs] func:xfs_inode_alloc > 120560528 29439 mm/mm_init.c:2521 func:alloc_large_system_hash > 136314880 33280 mm/percpu-vm.c:95 func:pcpu_alloc_pages > 184504320 10710 mm/readahead.c:468 func:ra_alloc_folio > 263192576 64256 mm/page_ext.c:270 func:alloc_page_ext > 506974208 123773 include/linux/mm.h:2848 func:pagetable_alloc > 809504768 53621 mm/slub.c:2305 func:alloc_slab_page > [root@dell-per6515-03 linux]# time tools/testing/selftests/mm/test_vmalloc.sh run_test_mask=127 nr_threads=256 > Run the test with following parameters: run_test_mask=127 nr_threads=256 > Done. > Check the kernel ring buffer to see the summary. > > real 21m36.580s > user 0m0.012s > sys 0m19.912s > [root@dell-per6515-03 linux]# sort -h /proc/allocinfo | tail -10 > 38977536 9516 mm/readahead.c:247 func:page_cache_ra_unbounded > 72273920 17645 fs/xfs/xfs_buf.c:390 [xfs] func:xfs_buf_alloc_pages > 99090432 96768 drivers/iommu/iova.c:604 func:iova_magazine_alloc > 99895296 97554 fs/xfs/xfs_icache.c:81 [xfs] func:xfs_inode_alloc > 120560528 29439 mm/mm_init.c:2521 func:alloc_large_system_hash > 141033472 34432 mm/percpu-vm.c:95 func:pcpu_alloc_pages > 186064896 10841 mm/readahead.c:468 func:ra_alloc_folio > 263192576 64256 mm/page_ext.c:270 func:alloc_page_ext > 541237248 132138 include/linux/mm.h:2848 func:pagetable_alloc > 694718464 41216 mm/slub.c:2305 func:alloc_slab_page > > Thank you for testing this. So ~132mb with a patch. I think it looks good but i might change the draft version and send out a new version. Thank you again! -- Uladzislau Rezki
