mirror of https://github.com/torvalds/linux.git
9f44df50fe
When reading /proc/allocinfo, for each read syscall, seq_file would invoke
start/stop callbacks. In start callback, a memory is alloced to store
iterator and the iterator would start from beginning to walk linearly to
current read position.
seq_file read() takes at most 4096 bytes, even if read with a larger user
space buffer, meaning read out all of /proc/allocinfo, tens of read
syscalls are needed. For example, a 306036 bytes allocinfo files need 76
reads:
$ sudo cat /proc/allocinfo | wc
3964 16678 306036
$ sudo strace -T -e read cat /proc/allocinfo
...
read(3, " 4096 1 arch/x86/k"..., 131072) = 4063 <0.000062>
...
read(3, " 0 0 sound/core"..., 131072) = 4021 <0.000150>
...
For those n=3964 lines, each read takes about m=3964/76=52 lines,
since iterator restart from beginning for each read(),
it would move forward
m steps on 1st read
2*m steps on 2nd read
3*m steps on 3rd read
...
n steps on last read
As read() along, those linear seek steps make read() calls slower and
slower. Adding those up, codetag iterator moves about O(n*n/m) steps,
making data structure traversal take significant part of the whole
reading. Profiling when stress reading /proc/allocinfo confirms it:
vfs_read(99.959% 1677299/1677995)
proc_reg_read_iter(99.856% 1674881/1677299)
seq_read_iter(99.959% 1674191/1674881)
allocinfo_start(75.664% 1266755/1674191)
codetag_next_ct(79.217% 1003487/1266755) <---
srso_return_thunk(1.264% 16011/1266755)
__kmalloc_cache_noprof(0.102% 1296/1266755)
...
allocinfo_show(21.287% 356378/1674191)
allocinfo_next(1.530% 25621/1674191)
codetag_next_ct() takes major part.
A private data alloced at open() time can be used to carry iterator alive
across read() calls, and avoid the memory allocation and iterator reset
for each read(). This way, only O(1) memory allocation and O(n) steps
iterating, and `time` shows performance improvement from ~7ms to ~4ms.
Profiling with the change:
vfs_read(99.865% 1581073/1583214)
proc_reg_read_iter(99.485% 1572934/1581073)
seq_read_iter(99.846% 1570519/1572934)
allocinfo_show(87.428% 1373074/1570519)
seq_buf_printf(83.695% 1149196/1373074)
seq_buf_putc(1.917% 26321/1373074)
_find_next_bit(1.531% 21023/1373074)
...
codetag_to_text(0.490% 6727/1373074)
...
allocinfo_next(6.275% 98543/1570519)
...
allocinfo_start(0.369% 5790/1570519)
...
Now seq_buf_printf() takes major part.
Link: https://lkml.kernel.org/r/20250609064408.112783-1-00107082@163.com
Signed-off-by: David Wang <00107082@163.com>
Acked-by: Suren Baghdasaryan <surenb@google.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
||
|---|---|---|
| .. | ||
| 842 | ||
| crypto | ||
| dim | ||
| fonts | ||
| kunit | ||
| lz4 | ||
| lzo | ||
| math | ||
| pldmfw | ||
| raid6 | ||
| reed_solomon | ||
| test_fortify | ||
| tests | ||
| vdso | ||
| xz | ||
| zlib_deflate | ||
| zlib_dfltcc | ||
| zlib_inflate | ||
| zstd | ||
| .gitignore | ||
| Kconfig | ||
| Kconfig.debug | ||
| Kconfig.kasan | ||
| Kconfig.kcsan | ||
| Kconfig.kfence | ||
| Kconfig.kgdb | ||
| Kconfig.kmsan | ||
| Kconfig.ubsan | ||
| Makefile | ||
| alloc_tag.c | ||
| argv_split.c | ||
| ashldi3.c | ||
| ashrdi3.c | ||
| asn1_decoder.c | ||
| asn1_encoder.c | ||
| assoc_array.c | ||
| atomic64.c | ||
| atomic64_test.c | ||
| audit.c | ||
| base64.c | ||
| bcd.c | ||
| bch.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.c | ||
| closure.c | ||
| clz_ctz.c | ||
| clz_tab.c | ||
| cmdline.c | ||
| cmpdi2.c | ||
| cmpxchg-emu.c | ||
| codetag.c | ||
| compat_audit.c | ||
| cpu_rmap.c | ||
| cpumask.c | ||
| crc-ccitt.c | ||
| crc-itu-t.c | ||
| crc-t10dif.c | ||
| crc4.c | ||
| crc7.c | ||
| crc8.c | ||
| crc16.c | ||
| crc32.c | ||
| crc64.c | ||
| ctype.c | ||
| debug_info.c | ||
| debug_locks.c | ||
| debugobjects.c | ||
| dec_and_lock.c | ||
| decompress.c | ||
| decompress_bunzip2.c | ||
| decompress_inflate.c | ||
| decompress_unlz4.c | ||
| decompress_unlzma.c | ||
| decompress_unlzo.c | ||
| decompress_unxz.c | ||
| decompress_unzstd.c | ||
| devmem_is_allowed.c | ||
| devres.c | ||
| dhry.h | ||
| dhry_1.c | ||
| dhry_2.c | ||
| dhry_run.c | ||
| 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.c | ||
| fdt_addresses.c | ||
| fdt_empty_tree.c | ||
| fdt_ro.c | ||
| fdt_rw.c | ||
| fdt_strerror.c | ||
| fdt_sw.c | ||
| fdt_wip.c | ||
| find_bit.c | ||
| find_bit_benchmark.c | ||
| flex_proportions.c | ||
| fw_table.c | ||
| gen_crc32table.c | ||
| gen_crc64table.c | ||
| genalloc.c | ||
| generic-radix-tree.c | ||
| glob.c | ||
| globtest.c | ||
| group_cpus.c | ||
| hexdump.c | ||
| hweight.c | ||
| idr.c | ||
| inflate.c | ||
| interval_tree.c | ||
| interval_tree_test.c | ||
| iomap.c | ||
| iomap_copy.c | ||
| iomem_copy.c | ||
| iommu-helper.c | ||
| iov_iter.c | ||
| irq_poll.c | ||
| irq_regs.c | ||
| is_single_threaded.c | ||
| kasprintf.c | ||
| kfifo.c | ||
| klist.c | ||
| kobject.c | ||
| kobject_uevent.c | ||
| kstrtox.c | ||
| kstrtox.h | ||
| linear_ranges.c | ||
| list_debug.c | ||
| list_sort.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 | ||
| maple_tree.c | ||
| memcat_p.c | ||
| memory-notifier-error-inject.c | ||
| memregion.c | ||
| memweight.c | ||
| min_heap.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 | ||
| packing.c | ||
| packing_test.c | ||
| parman.c | ||
| parser.c | ||
| percpu-refcount.c | ||
| percpu_counter.c | ||
| percpu_test.c | ||
| plist.c | ||
| pm-notifier-error-inject.c | ||
| polynomial.c | ||
| radix-tree.c | ||
| radix-tree.h | ||
| random32.c | ||
| ratelimit.c | ||
| rbtree.c | ||
| rbtree_test.c | ||
| rcuref.c | ||
| ref_tracker.c | ||
| refcount.c | ||
| rhashtable.c | ||
| sbitmap.c | ||
| scatterlist.c | ||
| seq_buf.c | ||
| sg_pool.c | ||
| sg_split.c | ||
| siphash.c | ||
| smp_processor_id.c | ||
| sort.c | ||
| stackdepot.c | ||
| stmp_device.c | ||
| string.c | ||
| string_helpers.c | ||
| strncpy_from_user.c | ||
| strnlen_user.c | ||
| syscall.c | ||
| test-kstrtox.c | ||
| test_bitmap.c | ||
| test_bitops.c | ||
| test_bpf.c | ||
| test_debug_virtual.c | ||
| test_dynamic_debug.c | ||
| test_firmware.c | ||
| test_fpu.h | ||
| test_fpu_glue.c | ||
| test_fpu_impl.c | ||
| test_free_pages.c | ||
| test_hexdump.c | ||
| test_hmm.c | ||
| test_hmm_uapi.h | ||
| test_ida.c | ||
| test_kmod.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_ref_tracker.c | ||
| test_rhashtable.c | ||
| test_static_key_base.c | ||
| test_static_keys.c | ||
| test_sysctl.c | ||
| test_ubsan.c | ||
| test_uuid.c | ||
| test_vmalloc.c | ||
| test_xarray.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 | ||
| union_find.c | ||
| usercopy.c | ||
| uuid.c | ||
| vsprintf.c | ||
| win_minmax.c | ||
| xarray.c | ||
| xxhash.c | ||