6758c1128c
Instead of doing multiple tree walks, do one optimism range check with
lock hold, and exit if raced with another insertion. If a shadow exists,
check it with a new xas_get_order helper before releasing the lock to
avoid redundant tree walks for getting its order.
Drop the lock and do the allocation only if a split is needed.
In the best case, it only need to walk the tree once. If it needs to
alloc and split, 3 walks are issued (One for first ranged conflict check
and order retrieving, one for the second check after allocation, one for
the insert after split).
Testing with 4K pages, in an 8G cgroup, with 16G brd as block device:
echo 3 > /proc/sys/vm/drop_caches
fio -name=cached --numjobs=16 --filename=/mnt/test.img \
--buffered=1 --ioengine=mmap --rw=randread --time_based \
--ramp_time=30s --runtime=5m --group_reporting
Before:
bw ( MiB/s): min= 1027, max= 3520, per=100.00%, avg=2445.02, stdev=18.90, samples=8691
iops : min=263001, max=901288, avg=625924.36, stdev=4837.28, samples=8691
After (+7.3%):
bw ( MiB/s): min= 493, max= 3947, per=100.00%, avg=2625.56, stdev=25.74, samples=8651
iops : min=126454, max=1010681, avg=672142.61, stdev=6590.48, samples=8651
Test result with THP (do a THP randread then switch to 4K page in hope it
issues a lot of splitting):
echo 3 > /proc/sys/vm/drop_caches
fio -name=cached --numjobs=16 --filename=/mnt/test.img \
--buffered=1 --ioengine=mmap -thp=1 --readonly \
--rw=randread --time_based --ramp_time=30s --runtime=10m \
--group_reporting
fio -name=cached --numjobs=16 --filename=/mnt/test.img \
--buffered=1 --ioengine=mmap \
--rw=randread --time_based --runtime=5s --group_reporting
Before:
bw ( KiB/s): min= 4141, max=14202, per=100.00%, avg=7935.51, stdev=96.85, samples=18976
iops : min= 1029, max= 3548, avg=1979.52, stdev=24.23, samples=18976·
READ: bw=4545B/s (4545B/s), 4545B/s-4545B/s (4545B/s-4545B/s), io=64.0KiB (65.5kB), run=14419-14419msec
After (+12.5%):
bw ( KiB/s): min= 4611, max=15370, per=100.00%, avg=8928.74, stdev=105.17, samples=19146
iops : min= 1151, max= 3842, avg=2231.27, stdev=26.29, samples=19146
READ: bw=4635B/s (4635B/s), 4635B/s-4635B/s (4635B/s-4635B/s), io=64.0KiB (65.5kB), run=14137-14137msec
The performance is better for both 4K (+7.5%) and THP (+12.5%) cached read.
Link: https://lkml.kernel.org/r/20240415171857.19244-5-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
||
|---|---|---|
| .. | ||
| 842 | ||
| crypto | ||
| dim | ||
| fonts | ||
| kunit | ||
| lz4 | ||
| lzo | ||
| math | ||
| pldmfw | ||
| raid6 | ||
| reed_solomon | ||
| test_fortify | ||
| vdso | ||
| xz | ||
| zlib_deflate | ||
| zlib_dfltcc | ||
| zlib_inflate | ||
| zstd | ||
| .gitignore | ||
| alloc_tag.c | ||
| argv_split.c | ||
| ashldi3.c | ||
| ashrdi3.c | ||
| asn1_decoder.c | ||
| asn1_encoder.c | ||
| assoc_array.c | ||
| atomic64_test.c | ||
| atomic64.c | ||
| audit.c | ||
| base64.c | ||
| bcd.c | ||
| bch.c | ||
| bitfield_kunit.c | ||
| bitmap-str.c | ||
| bitmap.c | ||
| bitrev.c | ||
| bootconfig-data.S | ||
| bootconfig.c | ||
| bsearch.c | ||
| btree.c | ||
| bucket_locks.c | ||
| bug.c | ||
| build_OID_registry | ||
| buildid.c | ||
| bust_spinlocks.c | ||
| check_signature.c | ||
| checksum_kunit.c | ||
| checksum.c | ||
| closure.c | ||
| clz_ctz.c | ||
| clz_tab.c | ||
| cmdline_kunit.c | ||
| cmdline.c | ||
| cmpdi2.c | ||
| codetag.c | ||
| compat_audit.c | ||
| cpu_rmap.c | ||
| cpumask_kunit.c | ||
| cpumask.c | ||
| crc4.c | ||
| crc7.c | ||
| crc8.c | ||
| crc16.c | ||
| crc32.c | ||
| crc32defs.h | ||
| crc32test.c | ||
| crc64-rocksoft.c | ||
| crc64.c | ||
| crc-ccitt.c | ||
| crc-itu-t.c | ||
| crc-t10dif.c | ||
| ctype.c | ||
| debug_info.c | ||
| debug_locks.c | ||
| debugobjects.c | ||
| dec_and_lock.c | ||
| decompress_bunzip2.c | ||
| decompress_inflate.c | ||
| decompress_unlz4.c | ||
| decompress_unlzma.c | ||
| decompress_unlzo.c | ||
| decompress_unxz.c | ||
| decompress_unzstd.c | ||
| decompress.c | ||
| devmem_is_allowed.c | ||
| devres.c | ||
| dhry_1.c | ||
| dhry_2.c | ||
| dhry_run.c | ||
| dhry.h | ||
| digsig.c | ||
| dump_stack.c | ||
| dynamic_debug.c | ||
| dynamic_queue_limits.c | ||
| earlycpio.c | ||
| errname.c | ||
| error-inject.c | ||
| errseq.c | ||
| extable.c | ||
| fault-inject-usercopy.c | ||
| fault-inject.c | ||
| fdt_addresses.c | ||
| fdt_empty_tree.c | ||
| fdt_ro.c | ||
| fdt_rw.c | ||
| fdt_strerror.c | ||
| fdt_sw.c | ||
| fdt_wip.c | ||
| fdt.c | ||
| find_bit_benchmark.c | ||
| find_bit.c | ||
| flex_proportions.c | ||
| fortify_kunit.c | ||
| fw_table.c | ||
| gen_crc32table.c | ||
| gen_crc64table.c | ||
| genalloc.c | ||
| generic-radix-tree.c | ||
| glob.c | ||
| globtest.c | ||
| group_cpus.c | ||
| hashtable_test.c | ||
| hexdump.c | ||
| hweight.c | ||
| idr.c | ||
| inflate.c | ||
| interval_tree_test.c | ||
| interval_tree.c | ||
| iomap_copy.c | ||
| iomap.c | ||
| iommu-helper.c | ||
| iov_iter.c | ||
| irq_poll.c | ||
| irq_regs.c | ||
| is_signed_type_kunit.c | ||
| is_single_threaded.c | ||
| kasprintf.c | ||
| Kconfig | ||
| Kconfig.debug | ||
| Kconfig.kasan | ||
| Kconfig.kcsan | ||
| Kconfig.kfence | ||
| Kconfig.kgdb | ||
| Kconfig.kmsan | ||
| Kconfig.ubsan | ||
| kfifo.c | ||
| klist.c | ||
| kobject_uevent.c | ||
| kobject.c | ||
| kstrtox.c | ||
| kstrtox.h | ||
| kunit_iov_iter.c | ||
| libcrc32c.c | ||
| linear_ranges.c | ||
| list_debug.c | ||
| list_sort.c | ||
| list-test.c | ||
| llist.c | ||
| locking-selftest-hardirq.h | ||
| locking-selftest-mutex.h | ||
| locking-selftest-rlock-hardirq.h | ||
| locking-selftest-rlock-softirq.h | ||
| locking-selftest-rlock.h | ||
| locking-selftest-rsem.h | ||
| locking-selftest-rtmutex.h | ||
| locking-selftest-softirq.h | ||
| locking-selftest-spin-hardirq.h | ||
| locking-selftest-spin-softirq.h | ||
| locking-selftest-spin.h | ||
| locking-selftest-wlock-hardirq.h | ||
| locking-selftest-wlock-softirq.h | ||
| locking-selftest-wlock.h | ||
| locking-selftest-wsem.h | ||
| locking-selftest.c | ||
| lockref.c | ||
| logic_iomem.c | ||
| logic_pio.c | ||
| lru_cache.c | ||
| lshrdi3.c | ||
| lwq.c | ||
| Makefile | ||
| maple_tree.c | ||
| memcat_p.c | ||
| memcpy_kunit.c | ||
| memory-notifier-error-inject.c | ||
| memregion.c | ||
| memweight.c | ||
| muldi3.c | ||
| net_utils.c | ||
| netdev-notifier-error-inject.c | ||
| nlattr.c | ||
| nmi_backtrace.c | ||
| notifier-error-inject.c | ||
| notifier-error-inject.h | ||
| objagg.c | ||
| objpool.c | ||
| of-reconfig-notifier-error-inject.c | ||
| oid_registry.c | ||
| once.c | ||
| overflow_kunit.c | ||
| packing.c | ||
| parman.c | ||
| parser.c | ||
| percpu_counter.c | ||
| percpu_test.c | ||
| percpu-refcount.c | ||
| plist.c | ||
| pm-notifier-error-inject.c | ||
| polynomial.c | ||
| radix-tree.c | ||
| radix-tree.h | ||
| random32.c | ||
| ratelimit.c | ||
| rbtree_test.c | ||
| rbtree.c | ||
| rcuref.c | ||
| ref_tracker.c | ||
| refcount.c | ||
| rhashtable.c | ||
| sbitmap.c | ||
| scatterlist.c | ||
| seq_buf.c | ||
| sg_pool.c | ||
| sg_split.c | ||
| siphash_kunit.c | ||
| siphash.c | ||
| slub_kunit.c | ||
| smp_processor_id.c | ||
| sort.c | ||
| stackdepot.c | ||
| stackinit_kunit.c | ||
| stmp_device.c | ||
| strcat_kunit.c | ||
| string_helpers_kunit.c | ||
| string_helpers.c | ||
| string_kunit.c | ||
| string.c | ||
| strncpy_from_user.c | ||
| strnlen_user.c | ||
| strscpy_kunit.c | ||
| syscall.c | ||
| test_bitmap.c | ||
| test_bitops.c | ||
| test_bits.c | ||
| test_blackhole_dev.c | ||
| test_bpf.c | ||
| test_debug_virtual.c | ||
| test_dynamic_debug.c | ||
| test_firmware.c | ||
| test_fprobe.c | ||
| test_fpu.c | ||
| test_free_pages.c | ||
| test_hash.c | ||
| test_hexdump.c | ||
| test_hmm_uapi.h | ||
| test_hmm.c | ||
| test_ida.c | ||
| test_kmod.c | ||
| test_kprobes.c | ||
| test_linear_ranges.c | ||
| test_list_sort.c | ||
| test_lockup.c | ||
| test_maple_tree.c | ||
| test_memcat_p.c | ||
| test_meminit.c | ||
| test_min_heap.c | ||
| test_module.c | ||
| test_objagg.c | ||
| test_objpool.c | ||
| test_parman.c | ||
| test_printf.c | ||
| test_ref_tracker.c | ||
| test_rhashtable.c | ||
| test_scanf.c | ||
| test_sort.c | ||
| test_static_key_base.c | ||
| test_static_keys.c | ||
| test_sysctl.c | ||
| test_ubsan.c | ||
| test_user_copy.c | ||
| test_uuid.c | ||
| test_vmalloc.c | ||
| test_xarray.c | ||
| test-kstrtox.c | ||
| textsearch.c | ||
| timerqueue.c | ||
| trace_readwrite.c | ||
| ts_bm.c | ||
| ts_fsm.c | ||
| ts_kmp.c | ||
| ubsan.c | ||
| ubsan.h | ||
| ucmpdi2.c | ||
| ucs2_string.c | ||
| usercopy.c | ||
| uuid.c | ||
| vsprintf.c | ||
| win_minmax.c | ||
| xarray.c | ||
| xxhash.c | ||