[llvm-dev] Making LLD PDB generation faster

Mon Feb 25 10:33:06 PST 2019

Someone at the office was telling of a different approach for the
densemap, don't store the hash in there at all, just a 32bit index
into the SeenHashes. To get the actual hash you need an indirection,
but it should keep the hashmap so much smaller that all other
operations on it fit better in the caches. Might be worth a try. I
have some code laying around for it, might try it latter.

On Mon, Feb 25, 2019 at 5:23 PM Leonardo Santagada <santagada at gmail.com> wrote:
>
> I have to change it on llvm-objcopy, which is doing most of the hash
> generation, just to make the hashes actually collide if they are
> pointing to the same thing :)
>
> On Mon, Feb 25, 2019 at 5:08 PM Alexandre Ganea
> <alexandre.ganea at ubisoft.com> wrote:
> >
> > For enabling large memory pages, see this link: https://support.sisoftware.co.uk/knowledgebase.php?article=52
> >
> > Meow hash isn't in the patch I posted, but you can use xxHash, it is good enough. Just add /hasher:xxhash to the LLD cmd-line.
> >
> >
> > -----Original Message-----
> > From: Leonardo Santagada <santagada at gmail.com>
> > Sent: Monday, February 25, 2019 11:05 AM
> > To: Alexandre Ganea <alexandre.ganea at ubisoft.com>
> > Cc: Zachary Turner <zturner at google.com>; Reid Kleckner <rnk at google.com>; llvm-dev <llvm-dev at lists.llvm.org>
> > Subject: Re: [llvm-dev] Making LLD PDB generation faster
> >
> > Times for lld compiled with LTO:
> >
> >   Input File Reading:          1430 ms (  3.3%)
> >   Code Layout:                  486 ms (  1.1%)
> >   PDB Emission (Cumulative):  41042 ms ( 94.6%)
> >     Add Objects:              33117 ms ( 76.4%)
> >       Type Merging:           25861 ms ( 59.6%)
> >       Symbol Merging:          7011 ms ( 16.2%)
> >     TPI Stream Layout:          996 ms (  2.3%)
> >     Globals Stream Layout:      513 ms (  1.2%)
> >     Commit to Disk:            5175 ms ( 11.9%)
> >   Commit Output File:            37 ms (  0.1%)
> > -------------------------------------------------
> > Total Link Time:              43366 ms (100.0%)
> >
> > LTO didn't help much :(
> >
> > Now I will try Alexandre patches and switch fo xxHash64 or meow hashing. I need to discover how to enable huge pages on my windows
> > (1809)
> >
> > ps: Need to figure out how to limit the number of link jobs in ninja as that almost used the whole 128GB of ram on my machine. On our distributed build system we can limit linking jobs (which are the only strict local jobs) to 8.
> >
> > On Mon, Feb 25, 2019 at 4:47 PM Alexandre Ganea <alexandre.ganea at ubisoft.com> wrote:
> > >
> > > …however it is very slow to compile, because /MP isn’t currently supported by clang-cl. So each CPP is compiled sequentially, one after another. Thus my patch for adding /MP.
> > >
> > >
> > >
> > > From: Alexandre Ganea
> > > Sent: Monday, February 25, 2019 10:42 AM
> > > To: Zachary Turner <zturner at google.com>; Leonardo Santagada
> > > <santagada at gmail.com>
> > > Cc: Reid Kleckner <rnk at google.com>; llvm-dev <llvm-dev at lists.llvm.org>
> > > Subject: RE: [llvm-dev] Making LLD PDB generation faster
> > >
> > >
> > >
> > > Yes, -Tllvm works.
> > >
> > >
> > >
> > >
> > >
> > > From: Zachary Turner <zturner at google.com>
> > > Sent: Monday, February 25, 2019 10:36 AM
> > > To: Leonardo Santagada <santagada at gmail.com>
> > > Cc: Alexandre Ganea <alexandre.ganea at ubisoft.com>; Reid Kleckner
> > > <rnk at google.com>; llvm-dev <llvm-dev at lists.llvm.org>
> > > Subject: Re: [llvm-dev] Making LLD PDB generation faster
> > >
> > >
> > >
> > > Is -Tllvm even supported? I thought the only thing you could pass for
> > > -T was -Thost=x64
> > >
> > > On Mon, Feb 25, 2019 at 6:52 AM Leonardo Santagada <santagada at gmail.com> wrote:
> > >
> > > I think its a huge bug that it doesn't raise any errors or warnings
> > > about it. But I will open a ticket on cmake, they should be using
> > > clang-cl.exe and lld-link.exe if T="llvm" probably set host to 64 bit
> > > as well.
> > >
> > > On Mon, Feb 25, 2019 at 3:34 PM Zachary Turner <zturner at google.com> wrote:
> > > >
> > > > I don’t think changing the compiler or linker is supported with the
> > > > vs generator, but I also don’t think it’s a bug On Mon, Feb 25, 2019 at 6:31 AM Alexandre Ganea <alexandre.ganea at ubisoft.com> wrote:
> > > >>
> > > >> Can you please try using Ninja instead?
> > > >>
> > > >> cmake -G Ninja f:/svn/llvm -DCMAKE_BUILD_TYPE=Release
> > > >> -DLLVM_OPTIMIZED_TABLEGEN=true
> > > >> -DLLVM_EXTERNAL_LLD_SOURCE_DIR=f:/svn/lld
> > > >> -DLLVM_TOOL_LLD_BUILD=true -DLLVM_ENABLE_LLD=true
> > > >> -DCMAKE_C_COMPILER="C:/Program Files/LLVM/bin/clang-cl.exe"
> > > >> -DCMAKE_CXX_COMPILER="C:/Program Files/LLVM/bin/clang-cl.exe"
> > > >> -DCMAKE_LINKER="C:/Program Files/LLVM/bin/lld-link.exe"
> > > >> -DLLVM_ENABLE_PDB=true
> > > >>
> > > >> It will be faster to compile. The setup I use is the above Ninja cmd-line for compiling optimized builds; and in addition, I keep the Visual Studio generator, as you do, but only for having a .sln to debug. It is a bit annoying to cmake twice, in two different build folders, but you can write a batch script.
> > > >>
> > > >> If the above works, maybe you should log the bug on https://bugs.llvm.org/ so it is not forgotten.
> > > >>
> > > >> Alex.
> > > >>
> > > >> -----Original Message-----
> > > >> From: Leonardo Santagada <santagada at gmail.com>
> > > >> Sent: Monday, February 25, 2019 9:04 AM
> > > >> To: Alexandre Ganea <alexandre.ganea at ubisoft.com>
> > > >> Cc: Zachary Turner <zturner at google.com>; Reid Kleckner
> > > >> <rnk at google.com>; llvm-dev <llvm-dev at lists.llvm.org>
> > > >> Subject: Re: [llvm-dev] Making LLD PDB generation faster
> > > >>
> > > >> Ok so there's a lot of confusion on cmake regarding using llvm as a toolset. It still does all its checks against cl.exe (not clang-cl) and somehow overriders CMAKE_LINKER to be link.exe. I tried a couple of places including:
> > > >>
> > > >> cmake -G "Visual Studio 15 2017" -A x64 -T"llvm",host=x64 -DCMAKE_LINKER="C:/Program Files/LLVM/bin/lld-link.exe"
> > > >> -DCMAKE_CXX_COMPILER="C:/Program Files/LLVM/bin/clang-cl.exe"
> > > >> -DCMAKE_C_COMPILER="C:/Program Files/LLVM/bin/clang-cl.exe"
> > > >> -DLLVM_ENABLE_LTO=true -DLLVM_ENABLE_PDB=true
> > > >> -DLLVM_ENABLE_PROJECTS=lld  ../llvm
> > > >>
> > > >> but it seems like the generator overrides it.
> > > >>
> > > >>
> > > >> ps: Created a phabricator account
> > > >>
> > > >> On Mon, Feb 25, 2019 at 2:48 PM Alexandre Ganea <alexandre.ganea at ubisoft.com> wrote:
> > > >> >
> > > >> > That's good news. For having debug info, you could try adding /Z7 on the cmake cmd-line, such as -DCMAKE_CXX_FLAGS="/Z7". Or use the 'RelWithDebInfo' target instead of 'Release' and add -DCMAKE_CXX_FLAGS="/Ob2" (because that target uses /Ob1 as a default).
> > > >> >
> > > >> > Can you please send a patch on Phabricator if you fix the LLVM_ENABLE_PDB issue with Clang? The goal is to have performance out-of-the-box.
> > > >> >
> > > >> > Alex.
> > > >> >
> > > >> > -----Original Message-----
> > > >> > From: Leonardo Santagada <santagada at gmail.com>
> > > >> > Sent: Monday, February 25, 2019 7:36 AM
> > > >> > To: Alexandre Ganea <alexandre.ganea at ubisoft.com>
> > > >> > Cc: Zachary Turner <zturner at google.com>; Reid Kleckner
> > > >> > <rnk at google.com>; llvm-dev <llvm-dev at lists.llvm.org>
> > > >> > Subject: Re: [llvm-dev] Making LLD PDB generation faster
> > > >> >
> > > >> > With your patch for cmake and reconfiguring it with "cmake -G "Visual Studio 15 2017" -A x64 -T"llvm",host=x64 -DLLVM_ENABLE_PDB=true -DLLVM_ENABLE_PROJECTS=lld  ../llvm" we get these results:
> > > >> >
> > > >> >   Input File Reading:          1602 ms (  3.5%)
> > > >> >   Code Layout:                  493 ms (  1.1%)
> > > >> >   PDB Emission (Cumulative):  43127 ms ( 94.5%)
> > > >> >     Add Objects:              34577 ms ( 75.8%)
> > > >> >       Type Merging:           26709 ms ( 58.5%)
> > > >> >       Symbol Merging:          7598 ms ( 16.7%)
> > > >> >     TPI Stream Layout:         1107 ms (  2.4%)
> > > >> >     Globals Stream Layout:      602 ms (  1.3%)
> > > >> >     Commit to Disk:            5636 ms ( 12.4%)
> > > >> >   Commit Output File:            16 ms (  0.0%)
> > > >> > -------------------------------------------------
> > > >> > Total Link Time:              45626 ms (100.0%)
> > > >> >
> > > >> > Unfortunately there were no pdb generated with lld.exe (or any
> > > >> > other
> > > >> > binaries) so I can't debug them. It seems like LLVM_ENABLE_PDB is not made to support using clang to complie itself as it tries to att /Zi to the targets instead of /Z7 and global hashes. I can patch it over here, but we probably want to fix this in cmake and on the docs, as its not clear at all how to compile lld in a performance 64bit way.
> > > >> >
> > > >> > On Mon, Feb 25, 2019 at 2:38 AM Alexandre Ganea <alexandre.ganea at ubisoft.com> wrote:
> > > >> > >
> > > >> > > How do you compile LLD? There's a big difference between when
> > > >> > > using MSVC vs Clang. The parallel ghash patch I was mentioning
> > > >> > > is almost 2x as fast when using Clang 7.0+ vs. MSVC 15.9+, I
> > > >> > > don't know exactly why. I also suggest you use the Release target. You should also grab this patch:
> > > >> > > https://reviews.llvm.org/D55056 - I had to revert it because it
> > > >> > > was causing issues with LLDB. But it will give an improvement for LLD.
> > > >> > > Please let me know if that improves your timings.
> > > >> > >
> > > >> > > The page faults are probably the OS loading from disk: most, if
> > > >> > > not all the files are accessed by LLD by mmap'ing them.
> > > >> > >
> > > >> > > The lockless DenseHash I was talking about will be published in
> > > >> > > an upcoming patch. As for reproducibility, this can be an issue
> > > >> > > on build systems. But on local machines, we could explicitly
> > > >> > > state that we want non-deterministic builds, through some cmd-line flag. If your 57sec for "Type Merging"
> > > >> > > transforms into 5sec when non-deterministic, I think that's worth it.
> > > >> > >
> > > >> > > Alex.
> > > >> > >
> > > >> > > -----Original Message-----
> > > >> > > From: Leonardo Santagada <santagada at gmail.com>
> > > >> > > Sent: Sunday, February 24, 2019 6:43 PM
> > > >> > > To: Alexandre Ganea <alexandre.ganea at ubisoft.com>
> > > >> > > Cc: Zachary Turner <zturner at google.com>; Reid Kleckner
> > > >> > > <rnk at google.com>; llvm-dev <llvm-dev at lists.llvm.org>
> > > >> > > Subject: Re: [llvm-dev] Making LLD PDB generation faster
> > > >> > >
> > > >> > > More info inline, I think there is a couple of misconceptions on what I'm doing:
> > > >> > >
> > > >> > > 1) I already patch all my .obj files to contain .debug$H
> > > >> > > entries so it is all ghashed already
> > > >> > > 2) All the 35s is spent adding to the DenseMap
> > > >> > >
> > > >> > > Here is my current times (lld-link.exe compiled with -O2 so no lto/pgo), lld generates a 141 MB binary and 1.2GB pdb file:
> > > >> > >
> > > >> > >   Input File Reading:          1724 ms (  2.1%)
> > > >> > >   Code Layout:                  482 ms (  0.6%)
> > > >> > >   PDB Emission (Cumulative):  79261 ms ( 96.8%)
> > > >> > >     Add Objects:              68650 ms ( 83.8%)
> > > >> > >       Type Merging:           57534 ms ( 70.2%)
> > > >> > >       Symbol Merging:         10822 ms ( 13.2%)
> > > >> > >     TPI Stream Layout:         1501 ms (  1.8%)
> > > >> > >     Globals Stream Layout:      770 ms (  0.9%)
> > > >> > >     Commit to Disk:            7007 ms (  8.6%)
> > > >> > >   Commit Output File:            19 ms (  0.0%)
> > > >> > > -------------------------------------------------
> > > >> > > Total Link Time:              81900 ms (100.0%)
> > > >> > >
> > > >> > > Our target is for < 20 seconds linking, anything bellow 40 seconds would be ok. Ideal times would be around 8s (in which it will mostly beat link.exe incremental linking).
> > > >> > >
> > > >> > > My tip for profiling is using superluminal
> > > >> > > (https://www.superluminal.eu/) its the easiest way to see everything your code is doing.
> > > >> > >
> > > >> > > On Sun, Feb 24, 2019 at 5:18 PM Alexandre Ganea <alexandre.ganea at ubisoft.com> wrote:
> > > >> > > >
> > > >> > > > Leonardo, to answer to your questions, yes to all of them J
> > > >> > > > You can take a
> > > >> > > >
> > > >> > > > look at this prototype/proposal:
> > > >> > > > https://reviews.llvm.org/D55585
> > > >> > > >
> > > >> > > >
> > > >> > > >
> > > >> > > > Overall, computing ghashes in parallel at link-time and
> > > >> > > > merging Types with them
> > > >> > > >
> > > >> > > > is less costly that the current approach to merging. The
> > > >> > > > 35sec you’re seeing
> > > >> > > >
> > > >> > > > for merging should go down to about 15sec.
> > > >> > >
> > > >> > > I don't do much computing of ghashes as we already preprocess all .obj files from msvc to add a .debug$H to them. The whole 35 seconds is spent in just densehash findbucket function. The rest of the time is mostly pagefaults (I guess to load in obj data and to grow the final pdb?).
> > > >> > >
> > > >> > > > The patch doesn’t parallelize
> > > >> > > >
> > > >> > > > (yet) the Type merging itself, but we have an alternate
> > > >> > > > multithread-suitable
> > > >> > > >
> > > >> > > > implementation of DenseHash which already supports lockless,
> > > >> > > > wait-free,
> > > >> > > >
> > > >> > > > insert/fetch/resize.
> > > >> > >
> > > >> > > Where is this lockless densehash? This is the part were I would love to help, but if there is a densehash it is probably just creating the threads and letting them merge the results. I'm a bit afraid of reproduceability of builds, but as we already don't have that with link.exe we are not really loosing anything.
> > > >> > >
> > > >> > > >
> > > >> > > >
> > > >> > > > The prototype allows for testing different hashing
> > > >> > > > algorithms, and indeed
> > > >> > > >
> > > >> > > > xxHash seems to be the best general-purpose choice. I’ve also
> > > >> > > > added support
> > > >> > > >
> > > >> > > > for more specialized hardware-based hashes, like Casey
> > > >> > > > Muratori’s Meow Hash
> > > >> > > >
> > > >> > > > (uses hardware AES SSE 4.2 instructions), which brings the figures down a bit.
> > > >> > > >
> > > >> > >
> > > >> > > I remembered Meow hashes needing at least k bytes of data, but looking at their website right now there is no mention of it. Hashing performance isn't much of an impact as we do it per .obj file distributed through our company so the time to calculate those are completely distributed.
> > > >> > >
> > > >> > > >
> > > >> > > >
> > > >> > > > Future changes could write back the computed ghash stream
> > > >> > > > back to OBJs if
> > > >> > > >
> > > >> > > > /INCREMENTAL is specified (just an idea). Incrementally
> > > >> > > > linking will be faster
> > > >> > > >
> > > >> > > > that way when working with MSVC OBJs.
> > > >> > > >
> > > >> > >
> > > >> > > I already have a patch for llvm-objcopy that adds a
> > > >> > > -add-ghashes option that does this, I will be cleaning it up
> > > >> > > this week and sending a PR for it
> > > >> > >
> > > >> > > >
> > > >> > > >
> > > >> > > > As for creating PDBs for independent projects, that would help most likely.
> > > >> > > >
> > > >> > > > However the ghash stream would need to be stored in the PDB
> > > >> > > > in that case
> > > >> > > >
> > > >> > > > (currently, ghashes are dropped after merging). That could
> > > >> > > > help when using
> > > >> > > >
> > > >> > > > rarely compiled projects, used along with network caches.
> > > >> > >
> > > >> > > I meant actually a .lib, with all the obj files inside plus a merged .debug$H entry. No pdb generation or changes necessary, we just run the same code that merges types in lld and do that a the librarian level.
> > > >> > >
> > > >> > > >
> > > >> > > > I will start sending smaller patches to converge towards the
> > > >> > > > functionally of
> > > >> > > >
> > > >> > > > the prototype above.
> > > >> > > >
> > > >> > > >
> > > >> > > >
> > > >> > > > Best,
> > > >> > > >
> > > >> > > > Alex.
> > > >> > > >
> > > >> > > >
> > > >> > > >
> > > >> > > > From: Zachary Turner <zturner at google.com>
> > > >> > > > Sent: Sunday, February 24, 2019 1:20 AM
> > > >> > > > To: Leonardo Santagada <santagada at gmail.com>
> > > >> > > > Cc: Alexandre Ganea <alexandre.ganea at ubisoft.com>; Reid
> > > >> > > > Kleckner <rnk at google.com>; llvm-dev <llvm-dev at lists.llvm.org>
> > > >> > > > Subject: Re: [llvm-dev] Making LLD PDB generation faster
> > > >> > > >
> > > >> > > >
> > > >> > > >
> > > >> > > > +Reid and Alexandre, who have been doing work in this area
> > > >> > > > +recently
> > > >> > > >
> > > >> > > >
> > > >> > > >
> > > >> > > > On Sat, Feb 23, 2019 at 4:07 AM Leonardo Santagada via llvm-dev <llvm-dev at lists.llvm.org> wrote:
> > > >> > > >
> > > >> > > > Hi,
> > > >> > > >
> > > >> > > > Is anyone working on making the PDB generation on LLD faster?
> > > >> > > > Looking of a trace for linking one of our binaries (it takes
> > > >> > > > 1min6s-1min20s) I see two things:
> > > >> > > >
> > > >> > > > 1) LookupBucketFor(Val, ConstFoundBucket); takes 35s so
> > > >> > > > almost half of the time of linking, mostly finding duplicates
> > > >> > > > 2) There is no parallelization inside of addObjectsToPDB
> > > >> > > >
> > > >> > > > Is anyone working on those? Also has anyone thought about
> > > >> > > > merging .obj files to deduplicate type infomation so we can
> > > >> > > > do the linking on projects to generate something like a lib
> > > >> > > > file, but deduplicated debug information (as far as I know
> > > >> > > > actual .lib just put all pdbs or
> > > >> > > > /Z7 debug info inside a file without dedup).
> > > >> > > >
> > > >> > > > Just looking at the code it seems it is much more mature and
> > > >> > > > also the choice of SHA1_8 seems interesting (still don't know
> > > >> > > > why not use xxHash64).
> > > >> > > >
> > > >> > > > ps: My code to add ghashes to msvc compiled .obj files is
> > > >> > > > almost ready to be pushed as an option for llvm-objcopy.
> > > >> > > >
> > > >> > > > --
> > > >> > > >
> > > >> > > > Leonardo Santagada
> > > >> > > > _______________________________________________
> > > >> > > > LLVM Developers mailing list
> > > >> > > > llvm-dev at lists.llvm.org
> > > >> > > > https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-dev
> > > >> > >
> > > >> > >
> > > >> > >
> > > >> > > --
> > > >> > >
> > > >> > > Leonardo Santagada
> > > >> >
> > > >> >
> > > >> >
> > > >> > --
> > > >> >
> > > >> > Leonardo Santagada
> > > >>
> > > >>
> > > >>
> > > >> --
> > > >>
> > > >> Leonardo Santagada
> > >
> > >
> > >
> > > --
> > >
> > > Leonardo Santagada
> >
> >
> >
> > --
> >
> > Leonardo Santagada
>
>
>
> --
>
> Leonardo Santagada

-- 

Leonardo Santagada