Re: [PATCH] reduce the time of finding symbols for module
From: zhouchengming
Date: Tue Mar 28 2017 - 07:00:46 EST
On 2017/3/28 17:00, Miroslav Benes wrote:
Hi,
On Tue, 28 Mar 2017, Zhou Chengming wrote:
It's reported that the time of insmoding a klp.ko for one of our
out-tree modules is too long.
~ time sudo insmod klp.ko
real 0m23.799s
user 0m0.036s
sys 0m21.256s
Is this stable through several (>=10) runs? 23 seconds are really
suspicious. Yes, there is a linear search through all the kallsyms in
kallsyms_on_each_symbol(), but there are something like 70k symbols on my
machine (that is, way less than 1M). 23 seconds are somewhat unexpected.
Yes, it's stable through several runs.
I think the big reason is that our out-tree module used a lot of static local
variables. We can see '.rela.kpatch.dynrelas' contains many entries, so it will
waste a lot of time if we use kallsyms_on_each_symbol() to find these symbols of module.
Relocation section '.rela.kpatch.funcs' at offset 0x382e0 contains 3 entries:
Offset Info Type Sym. Value Sym. Name + Addend
000000000000 003300000101 R_AARCH64_ABS64 0000000000000000 value_show + 0
000000000020 000b00000101 R_AARCH64_ABS64 0000000000000000 .kpatch.strings + 8
000000000028 000b00000101 R_AARCH64_ABS64 0000000000000000 .kpatch.strings + 0
Relocation section '.rela.kpatch.dynrelas' at offset 0x38328 contains 2562 entries:
Offset Info Type Sym. Value Sym. Name + Addend
000000000000 003300000101 R_AARCH64_ABS64 0000000000000000 value_show + 14
000000000018 000b00000101 R_AARCH64_ABS64 0000000000000000 .kpatch.strings + 13
000000000020 000b00000101 R_AARCH64_ABS64 0000000000000000 .kpatch.strings + 0
000000000040 003300000101 R_AARCH64_ABS64 0000000000000000 value_show + 20
000000000058 000b00000101 R_AARCH64_ABS64 0000000000000000 .kpatch.strings + 13
000000000060 000b00000101 R_AARCH64_ABS64 0000000000000000 .kpatch.strings + 0
If it is a problem, can we fix kallsyms_on_each_symbol() and replace the
linear search with something better? All users would benefit...
Yes, it's better if we can improve the linear search, but I can't think of that...
Thanks.
Thanks,
Miroslav
.