On Wednesday, June 27, 2018 5:38:31 PM CEST Pavel Stehule wrote:
> 2018-06-27 17:19 GMT+02:00 Tomas Vondra <tomas.von...@2ndquadrant.com>:
> > On 06/26/2018 09:25 PM, Pavel Stehule wrote:
> >> Hi
> >>
> >> ...
> >>
> >> So I am able to see effect of jit_tuple_deforming, and very well, but
> >> only if optimization is active. When optimization is not active then
> >> jit_tuple_deforming does slowdown.
> >>
> >> So maybe a usage of jit_tuple_deforming can be conditioned by
> >> jit_optimization?
> >
> > Can you share the test case and some detail about the hardware and
> > PostgreSQL configuration?
>
> I did very simple test
>
>
> 0.
>
> master branch without asserts, shared buffer to 1GB
> tested on Lenovo T520 8GB RAM 8CPU, i7
> Fedora 28, gcc CFLAGS="-ggdb -Og -g3 -fno-omit-frame-pointer" --with-llvm
>
> 1.
>
> select 'create table wt(' || string_agg(format('%I int', 'c' || i),',') ||
> ')' from generate_series(1,100) g(i) \gexec
>
>
> 2.
>
> begin;
> select 'insert into wt values(' || (select
> string_agg((random()*10000)::int::text,',') from generate_series(1,j - j +
> 100) g(i)) || ')' from generate_series(1,1000000) gg(j) \gexec
> insert into wt select * from wt;
> commit;
>
> 3.
>
> set max_paralel_workers to 0; -- the effect of JIT will be more visible
>
> analyze wt;
> \timing
>
> select sum(c99) from wt;
>
> I tested some combination of:
>
> jit: off on
> jit_inline_above_cost: 0, 10000000000000
> jit_optimize_above_cost: 0, 10000000000000
> jit_tuple_deforming: on, off
>
>
> My primitive tests shows nice possitive effect of jit_tuple_deforming if
> jit optimization is active. When jit optimization is not active, then
> jit_tuple_deforming did slowdown in my test.
>
> So there is range of costs between 100000 and 500000 where
> jit_tuple_deforming didn't work well (without optimization)
>
> I am limmited by small memory of my notebook - when I created table larger
> than 3GB, then I got IO waits on my crypted disc, and any effect of JIT was
> eliminated.
>
> Regards
>
> Pavel
Hi
I have studied this case a bit, and I think too that there is something wrong
here.
Right now, jit_optimize is a -O3. It's really expensive, and triggering it
here is not the right solution. In the attached patch, I force a -O1 for tuple
deforming. With your test case, on my computer, the results are :
- no jit : 850ms
- jit with tuple deforming without optimizations : 1650 ms (1.5ms spent
optimizing)
- jit without tuple deforming : 820ms (0.2ms)
- jit with tuple deforming with optimization (-O3) : 770ms (105ms)
- jit with tuple deforming with patch (-O1) : 725ms (54ms)
I will look at the generated code for tuple deforming, but I think we should
pre-optimize the LLVM bytecode if we do not want to involve the LLVM
optimization passes.
Regards
Pierre
>From c2e70c8fbb7715283d3d53bdf5a70e4db18c99a9 Mon Sep 17 00:00:00 2001
From: Pierre Ducroquet <p.p...@pinaraf.info>
Date: Mon, 2 Jul 2018 13:44:10 +0200
Subject: [PATCH] Introduce opt1 in LLVM/JIT, and force it with deforming
---
src/backend/jit/llvm/llvmjit.c | 30 ++++++++++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/src/backend/jit/llvm/llvmjit.c b/src/backend/jit/llvm/llvmjit.c
index 5d0cdab1fc..025319e9c1 100644
--- a/src/backend/jit/llvm/llvmjit.c
+++ b/src/backend/jit/llvm/llvmjit.c
@@ -91,10 +91,12 @@ static const char *llvm_layout = NULL;
static LLVMTargetMachineRef llvm_opt0_targetmachine;
+static LLVMTargetMachineRef llvm_opt1_targetmachine;
static LLVMTargetMachineRef llvm_opt3_targetmachine;
static LLVMTargetRef llvm_targetref;
static LLVMOrcJITStackRef llvm_opt0_orc;
+static LLVMOrcJITStackRef llvm_opt1_orc;
static LLVMOrcJITStackRef llvm_opt3_orc;
@@ -277,6 +279,8 @@ llvm_get_function(LLVMJitContext *context, const char *funcname)
#if LLVM_VERSION_MAJOR < 5
if ((addr = LLVMOrcGetSymbolAddress(llvm_opt0_orc, funcname)))
return (void *) (uintptr_t) addr;
+ if ((addr = LLVMOrcGetSymbolAddress(llvm_opt1_orc, funcname)))
+ return (void *) (uintptr_t) addr;
if ((addr = LLVMOrcGetSymbolAddress(llvm_opt3_orc, funcname)))
return (void *) (uintptr_t) addr;
#else
@@ -284,6 +288,10 @@ llvm_get_function(LLVMJitContext *context, const char *funcname)
elog(ERROR, "failed to look up symbol \"%s\"", funcname);
if (addr)
return (void *) (uintptr_t) addr;
+ if (LLVMOrcGetSymbolAddress(llvm_opt1_orc, &addr, funcname))
+ elog(ERROR, "failed to look up symbol \"%s\"", funcname);
+ if (addr)
+ return (void *) (uintptr_t) addr;
if (LLVMOrcGetSymbolAddress(llvm_opt3_orc, &addr, funcname))
elog(ERROR, "failed to look up symbol \"%s\"", funcname);
if (addr)
@@ -420,6 +428,8 @@ llvm_optimize_module(LLVMJitContext *context, LLVMModuleRef module)
if (context->base.flags & PGJIT_OPT3)
compile_optlevel = 3;
+ else if (context->base.flags & PGJIT_DEFORM)
+ compile_optlevel = 1;
else
compile_optlevel = 0;
@@ -491,6 +501,8 @@ llvm_compile_module(LLVMJitContext *context)
if (context->base.flags & PGJIT_OPT3)
compile_orc = llvm_opt3_orc;
+ else if (context->base.flags & PGJIT_DEFORM)
+ compile_orc = llvm_opt1_orc;
else
compile_orc = llvm_opt0_orc;
@@ -646,6 +658,11 @@ llvm_session_initialize(void)
LLVMCodeGenLevelNone,
LLVMRelocDefault,
LLVMCodeModelJITDefault);
+ llvm_opt1_targetmachine =
+ LLVMCreateTargetMachine(llvm_targetref, llvm_triple, cpu, features,
+ LLVMCodeGenLevelLess,
+ LLVMRelocDefault,
+ LLVMCodeModelJITDefault);
llvm_opt3_targetmachine =
LLVMCreateTargetMachine(llvm_targetref, llvm_triple, cpu, features,
LLVMCodeGenLevelAggressive,
@@ -661,12 +678,14 @@ llvm_session_initialize(void)
LLVMLoadLibraryPermanently(NULL);
llvm_opt0_orc = LLVMOrcCreateInstance(llvm_opt0_targetmachine);
+ llvm_opt1_orc = LLVMOrcCreateInstance(llvm_opt1_targetmachine);
llvm_opt3_orc = LLVMOrcCreateInstance(llvm_opt3_targetmachine);
#if defined(HAVE_DECL_LLVMORCREGISTERGDB) && HAVE_DECL_LLVMORCREGISTERGDB
if (jit_debugging_support)
{
LLVMOrcRegisterGDB(llvm_opt0_orc);
+ LLVMOrcRegisterGDB(llvm_opt1_orc);
LLVMOrcRegisterGDB(llvm_opt3_orc);
}
#endif
@@ -674,6 +693,7 @@ llvm_session_initialize(void)
if (jit_profiling_support)
{
LLVMOrcRegisterPerf(llvm_opt0_orc);
+ LLVMOrcRegisterPerf(llvm_opt1_orc);
LLVMOrcRegisterPerf(llvm_opt3_orc);
}
#endif
@@ -700,6 +720,16 @@ llvm_shutdown(int code, Datum arg)
llvm_opt3_orc = NULL;
}
+ if (llvm_opt1_orc)
+ {
+#if defined(HAVE_DECL_LLVMORCREGISTERPERF) && HAVE_DECL_LLVMORCREGISTERPERF
+ if (jit_profiling_support)
+ LLVMOrcUnregisterPerf(llvm_opt1_orc);
+#endif
+ LLVMOrcDisposeInstance(llvm_opt1_orc);
+ llvm_opt1_orc = NULL;
+ }
+
if (llvm_opt0_orc)
{
#if defined(HAVE_DECL_LLVMORCREGISTERPERF) && HAVE_DECL_LLVMORCREGISTERPERF
--
2.18.0
