ab3430f891
## Motivation Since we don't need the metadata sections at runtime, we can somehow offload them from memory at runtime. Initially, I explored [debug info correlation](https://discourse.llvm.org/t/instrprofiling-lightweight-instrumentation/59113), which is used for PGO with value profiling disabled. However, it currently only works with DWARF and it's be hard to add such artificial debug info for every function in to CodeView which is used on Windows. So, offloading profile metadata sections at runtime seems to be a platform independent option. ## Design The idea is to use new section names for profile name and data sections and mark them as metadata sections. Under this mode, the new sections are non-SHF_ALLOC in ELF. So, they are not loaded into memory at runtime and can be stripped away as a post-linking step. After the process exits, the generated raw profiles will contains only headers + counters. llvm-profdata can be used correlate raw profiles with the unstripped binary to generate indexed profile. ## Data For chromium base_unittests with code coverage on linux, the binary size overhead due to instrumentation reduced from 64M to 38.8M (39.4%) and the raw profile files size reduce from 128M to 68M (46.9%) ``` $ bloaty out/cov/base_unittests.stripped -- out/no-cov/base_unittests.stripped FILE SIZE VM SIZE -------------- -------------- +121% +30.4Mi +121% +30.4Mi .text [NEW] +14.6Mi [NEW] +14.6Mi __llvm_prf_data [NEW] +10.6Mi [NEW] +10.6Mi __llvm_prf_names [NEW] +5.86Mi [NEW] +5.86Mi __llvm_prf_cnts +95% +1.75Mi +95% +1.75Mi .eh_frame +108% +400Ki +108% +400Ki .eh_frame_hdr +9.5% +211Ki +9.5% +211Ki .rela.dyn +9.2% +95.0Ki +9.2% +95.0Ki .data.rel.ro +5.0% +87.3Ki +5.0% +87.3Ki .rodata [ = ] 0 +13% +47.0Ki .bss +40% +1.78Ki +40% +1.78Ki .got +12% +1.49Ki +12% +1.49Ki .gcc_except_table [ = ] 0 +65% +1.23Ki .relro_padding +62% +1.20Ki [ = ] 0 [Unmapped] +13% +448 +19% +448 .init_array +8.8% +192 [ = ] 0 [ELF Section Headers] +0.0% +136 +0.0% +80 [7 Others] +0.1% +96 +0.1% +96 .dynsym +1.2% +96 +1.2% +96 .rela.plt +1.5% +80 +1.2% +64 .plt [ = ] 0 -99.2% -3.68Ki [LOAD #5 [RW]] +195% +64.0Mi +194% +64.0Mi TOTAL $ bloaty out/cov-cor/base_unittests.stripped -- out/no-cov/base_unittests.stripped FILE SIZE VM SIZE -------------- -------------- +121% +30.4Mi +121% +30.4Mi .text [NEW] +5.86Mi [NEW] +5.86Mi __llvm_prf_cnts +95% +1.75Mi +95% +1.75Mi .eh_frame +108% +400Ki +108% +400Ki .eh_frame_hdr +9.5% +211Ki +9.5% +211Ki .rela.dyn +9.2% +95.0Ki +9.2% +95.0Ki .data.rel.ro +5.0% +87.3Ki +5.0% +87.3Ki .rodata [ = ] 0 +13% +47.0Ki .bss +40% +1.78Ki +40% +1.78Ki .got +12% +1.49Ki +12% +1.49Ki .gcc_except_table +13% +448 +19% +448 .init_array +0.1% +96 +0.1% +96 .dynsym +1.2% +96 +1.2% +96 .rela.plt +1.2% +64 +1.2% +64 .plt +2.9% +64 [ = ] 0 [ELF Section Headers] +0.0% +40 +0.0% +40 .data +1.2% +32 +1.2% +32 .got.plt +0.0% +24 +0.0% +8 [5 Others] [ = ] 0 -22.9% -872 [LOAD #5 [RW]] -74.5% -1.44Ki [ = ] 0 [Unmapped] [ = ] 0 -76.5% -1.45Ki .relro_padding +118% +38.8Mi +117% +38.8Mi TOTAL ``` A few things to note: 1. llvm-profdata doesn't support filter raw profiles by binary id yet, so when a raw profile doesn't belongs to the binary being digested by llvm-profdata, merging will fail. Once this is implemented, llvm-profdata should be able to only merge raw profiles with the same binary id as the binary and discard the rest (with mismatched/missing binary id). The workflow I have in mind is to have scripts invoke llvm-profdata to get all binary ids for all raw profiles, and selectively choose the raw pnrofiles with matching binary id and the binary to llvm-profdata for merging. 2. Note: In COFF, currently they are still loaded into memory but not used. I didn't do it in this patch because I noticed that `.lcovmap` and `.lcovfunc` are loaded into memory. A separate patch will address it. 3. This should works with PGO when value profiling is disabled as debug info correlation currently doing, though I haven't tested this yet.
32 lines
1.7 KiB
LLVM
32 lines
1.7 KiB
LLVM
; RUN: opt < %s -passes=instrprof -S | FileCheck %s
|
|
; RUN: opt < %s -passes=instrprof -profile-correlate=binary -S | FileCheck %s --check-prefix=BINARY
|
|
|
|
target triple = "aarch64-unknown-linux-gnu"
|
|
|
|
@__profn_foo = private constant [3 x i8] c"foo"
|
|
; CHECK: @__profc_foo = private global [1 x i8] c"\FF", section "__llvm_prf_cnts", comdat, align 1
|
|
; CHECK: @__profd_foo = private global { i64, i64, i64, i64, ptr, ptr, i32, [2 x i16], i32 } { i64 {{.*}}, i64 {{.*}}, i64 sub (i64 ptrtoint (ptr @__profc_foo to i64)
|
|
; BINARY: @__profd_foo = private global { i64, i64, i64, i64, ptr, ptr, i32, [2 x i16], i32 } { i64 {{.*}}, i64 {{.*}}, i64 ptrtoint (ptr @__profc_foo to i64),
|
|
@__profn_bar = private constant [3 x i8] c"bar"
|
|
; CHECK: @__profc_bar = private global [1 x i8] c"\FF", section "__llvm_prf_cnts", comdat, align 1
|
|
; CHECK: @__profd_bar = private global { i64, i64, i64, i64, ptr, ptr, i32, [2 x i16], i32 } { i64 {{.*}}, i64 {{.*}}, i64 sub (i64 ptrtoint (ptr @__profc_bar to i64)
|
|
; BINARY: @__profd_bar = private global { i64, i64, i64, i64, ptr, ptr, i32, [2 x i16], i32 } { i64 {{.*}}, i64 {{.*}}, i64 ptrtoint (ptr @__profc_bar to i64),
|
|
|
|
; CHECK: @__llvm_prf_nm = {{.*}} section "__llvm_prf_names"
|
|
; BINARY: @__llvm_prf_nm ={{.*}} section "__llvm_covnames"
|
|
|
|
define void @_Z3foov() {
|
|
call void @llvm.instrprof.cover(ptr @__profn_foo, i64 12345678, i32 1, i32 0)
|
|
; CHECK: store i8 0, ptr @__profc_foo, align 1
|
|
ret void
|
|
}
|
|
|
|
%class.A = type { ptr }
|
|
define dso_local void @_Z3barv(ptr nocapture nonnull align 8 %0) unnamed_addr #0 align 2 {
|
|
call void @llvm.instrprof.cover(ptr @__profn_bar, i64 87654321, i32 1, i32 0)
|
|
; CHECK: store i8 0, ptr @__profc_bar, align 1
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.instrprof.cover(ptr, i64, i32, i32)
|