Comparison of branch: backports-release-1.9+RAI

Make.inc

@@ -195,7 +195,7 @@ endif
 JULIA_VERSION := $(shell cat $(JULIAHOME)/VERSION)
 JULIA_MAJOR_VERSION := $(shell echo $(JULIA_VERSION) | cut -d'-' -f 1 | cut -d'.' -f 1)
 JULIA_MINOR_VERSION := $(shell echo $(JULIA_VERSION) | cut -d'-' -f 1 | cut -d'.' -f 2)
-JULIA_PATCH_VERSION := $(shell echo $(JULIA_VERSION) | cut -d'-' -f 1 | cut -d'.' -f 3)
+JULIA_PATCH_VERSION := $(shell echo $(JULIA_VERSION) | cut -d'-' -f 1 | cut -d'+' -f 1 | cut -d'.' -f 3)
 
 # libjulia's SONAME will follow the format libjulia.so.$(SOMAJOR). Before v1.0.0,
 # SOMAJOR will be a two-decimal value, e.g. libjulia.so.0.5, whereas at and beyond

NEWS.md

@@ -38,6 +38,7 @@ Compiler/Runtime improvements
 * All uses of the `@pure` macro in `Base` have been replaced with the now-preferred `Base.@assume_effects` ([#44776]).
 * `invoke(f, invokesig, args...)` calls to a less-specific method than would normally be chosen
   for `f(args...)` are no longer spuriously invalidated when loading package precompile files ([#46010]).
+* The mark phase of the Garbage Collector is now multi-threaded ([#48600]).
 
 Command-line option changes
 ---------------------------
@@ -49,6 +50,8 @@ Command-line option changes
   number of interactive threads to create (`auto` currently means 1) ([#42302]).
 * New option `--heap-size-hint=<size>` suggests a size limit to invoke garbage collection more eagerly.
   The size may be specified in bytes, kilobytes (1000k), megabytes (300M), or gigabytes (1.5G) ([#45369]).
+* New option `--gcthreads` to set how many threads will be used by the Garbage Collector ([#48600]).
+  The default is set to `N/2` where `N` is the amount of worker threads (`--threads`) used by Julia.
 
 Multi-threading changes
 -----------------------

VERSION

@@ -1 +1 @@
-1.9.3
+1.9.4+RAI

base/options.jl

@@ -11,6 +11,7 @@ struct JLOptions
     cpu_target::Ptr{UInt8}
     nthreadpools::Int16
     nthreads::Int16
+    ngcthreads::Int16
     nthreads_per_pool::Ptr{Int16}
     nprocs::Int32
     machine_file::Ptr{UInt8}

base/partr.jl

@@ -50,7 +50,7 @@ function multiq_sift_down(heap::taskheap, idx::Int32)
             child = Int(child)
             child > length(heap.tasks) && break
             if isassigned(heap.tasks, child) &&
-                    heap.tasks[child].priority < heap.tasks[idx].priority
+                    heap.tasks[child].priority <= heap.tasks[idx].priority
                 t = heap.tasks[idx]
                 heap.tasks[idx] = heap.tasks[child]
                 heap.tasks[child] = t

base/reflection.jl

@@ -1092,6 +1092,7 @@ struct CodegenParams
     prefer_specsig::Cint
     gnu_pubnames::Cint
     debug_info_kind::Cint
+    safepoint_on_entry::Cint
 
     lookup::Ptr{Cvoid}
 
@@ -1100,12 +1101,14 @@ struct CodegenParams
     function CodegenParams(; track_allocations::Bool=true, code_coverage::Bool=true,
                    prefer_specsig::Bool=false,
                    gnu_pubnames=true, debug_info_kind::Cint = default_debug_info_kind(),
+                   safepoint_on_entry::Bool=true,
                    lookup::Ptr{Cvoid}=cglobal(:jl_rettype_inferred),
                    generic_context = nothing)
         return new(
             Cint(track_allocations), Cint(code_coverage),
             Cint(prefer_specsig),
             Cint(gnu_pubnames), debug_info_kind,
+            Cint(safepoint_on_entry),
             lookup, generic_context)
     end
 end

base/task.jl

@@ -688,7 +688,7 @@ end
 
 ## scheduler and work queue
 
-struct IntrusiveLinkedListSynchronized{T}
+mutable struct IntrusiveLinkedListSynchronized{T}
     queue::IntrusiveLinkedList{T}
     lock::Threads.SpinLock
     IntrusiveLinkedListSynchronized{T}() where {T} = new(IntrusiveLinkedList{T}(), Threads.SpinLock())

base/threadingconstructs.jl

@@ -136,6 +136,13 @@ function threadpooltids(pool::Symbol)
     end
 end
 
+"""
+    Threads.ngcthreads() -> Int
+
+Returns the number of GC threads currently configured.
+"""
+ngcthreads() = Int(unsafe_load(cglobal(:jl_n_gcthreads, Cint))) + 1
+
 function threading_run(fun, static)
     ccall(:jl_enter_threaded_region, Cvoid, ())
     n = threadpoolsize()

base/timing.jl

@@ -20,10 +20,13 @@ struct GC_Num
     max_memory      ::Int64
     time_to_safepoint           ::Int64
     max_time_to_safepoint       ::Int64
+    total_time_to_safepoint     ::Int64
     sweep_time      ::Int64
     mark_time       ::Int64
     total_sweep_time  ::Int64
     total_mark_time   ::Int64
+    last_full_sweep ::Int64
+    last_incremental_sweep ::Int64
 end
 
 gc_num() = ccall(:jl_gc_num, GC_Num, ())
@@ -96,6 +99,13 @@ function gc_live_bytes()
     Int(ccall(:jl_gc_live_bytes, Int64, ())) + num.allocd + num.deferred_alloc
 end
 
+# must be kept in sync with the value from `src/julia_threads.h``
+const JL_GC_N_MAX_POOLS = 51
+function gc_page_utilization_data()
+    page_utilization_raw = cglobal(:jl_gc_page_utilization_stats, Float64)
+    return Base.unsafe_wrap(Array, page_utilization_raw, JL_GC_N_MAX_POOLS, own=false)
+end
+
 """
     Base.jit_total_bytes()
 

contrib/generate_precompile.jl

@@ -1,7 +1,7 @@
 # This file is a part of Julia. License is MIT: https://julialang.org/license
 
 if Threads.maxthreadid() != 1
-    @warn "Running this file with multiple Julia threads may lead to a build error" Base.maxthreadid()
+    @warn "Running this file with multiple Julia threads may lead to a build error" Base.Threads.maxthreadid()
 end
 
 if Base.isempty(Base.ARGS) || Base.ARGS[1] !== "0"
@@ -245,7 +245,7 @@ const HELP_PROMPT = "help?> "
 
 function generate_precompile_statements()
     start_time = time_ns()
-    debug_output = devnull # or stdout
+    debug_output = stdout
     sysimg = Base.unsafe_string(Base.JLOptions().image_file)
 
     # Extract the precompile statements from the precompile file

deps/checksums/Pkg-397c8bf20ef70a78247d4cbd3d59f28a3116c884.tar.gz/md5

@@ -0,0 +1 @@
+d9630229362baeff301c473bb3e05905

deps/checksums/Pkg-397c8bf20ef70a78247d4cbd3d59f28a3116c884.tar.gz/sha512

@@ -0,0 +1 @@
+d8d421d9cce00fddaddbe88ae02076c58f5a669064b197092ceab6051c26fb3aab42f03be3f945dc5dbf376ee0d0a29c33208121e20b3e613a92311ca171828d

doc/man/julia.1

@@ -118,6 +118,11 @@ supported (Linux and Windows). If this is not supported (macOS) or
 process affinity is not configured, it uses the number of CPU
 threads.
 
+.TP
+--gcthreads <n>
+Enable n GC threads; If unspecified is set to half of the
+compute worker threads.
+
 .TP
 -p, --procs {N|auto}
 Integer value N launches N additional local worker processes `auto` launches as many workers

doc/src/base/multi-threading.md

@@ -10,6 +10,7 @@ Base.Threads.nthreads
 Base.Threads.threadpool
 Base.Threads.nthreadpools
 Base.Threads.threadpoolsize
+Base.Threads.ngcthreads
 ```
 
 See also [Multi-Threading](@ref man-multithreading).

doc/src/manual/command-line-interface.md

@@ -106,8 +106,9 @@ The following is a complete list of command-line switches available when launchi
 |`-e`, `--eval <expr>`                  |Evaluate `<expr>`|
 |`-E`, `--print <expr>`                 |Evaluate `<expr>` and display the result|
 |`-L`, `--load <file>`                  |Load `<file>` immediately on all processors|
-|`-t`, `--threads {N\|auto`}            |Enable N threads; `auto` tries to infer a useful default number of threads to use but the exact behavior might change in the future.  Currently, `auto` uses the number of CPUs assigned to this julia process based on the OS-specific affinity assignment interface, if supported (Linux and Windows). If this is not supported (macOS) or process affinity is not configured, it uses the number of CPU threads.|
-|`-p`, `--procs {N\|auto`}              |Integer value N launches N additional local worker processes; `auto` launches as many workers as the number of local CPU threads (logical cores)|
+|`-t`, `--threads {N\|auto}`            |Enable N threads; `auto` tries to infer a useful default number of threads to use but the exact behavior might change in the future.  Currently, `auto` uses the number of CPUs assigned to this julia process based on the OS-specific affinity assignment interface, if supported (Linux and Windows). If this is not supported (macOS) or process affinity is not configured, it uses the number of CPU threads.|
+| `--gcthreads {N}`                     |Enable N GC threads; If unspecified is set to half of the compute worker threads.|
+|`-p`, `--procs {N\|auto}`              |Integer value N launches N additional local worker processes; `auto` launches as many workers as the number of local CPU threads (logical cores)|
 |`--machine-file <file>`                |Run processes on hosts listed in `<file>`|
 |`-i`                                   |Interactive mode; REPL runs and `isinteractive()` is true|
 |`-q`, `--quiet`                        |Quiet startup: no banner, suppress REPL warnings|

doc/src/manual/environment-variables.md

@@ -315,6 +315,14 @@ then spinning threads never sleep. Otherwise, `$JULIA_THREAD_SLEEP_THRESHOLD` is
 interpreted as an unsigned 64-bit integer (`uint64_t`) and gives, in
 nanoseconds, the amount of time after which spinning threads should sleep.
 
+### [`JULIA_NUM_GC_THREADS`](@id env-gc-threads)
+
+Sets the number of threads used by Garbage Collection. If unspecified is set to
+half of the number of worker threads.
+
+!!! compat "Julia 1.10"
+    The environment variable was added in 1.10
+
 ### `JULIA_EXCLUSIVE`
 
 If set to anything besides `0`, then Julia's thread policy is consistent with

doc/src/manual/multi-threading.md

@@ -72,6 +72,15 @@ julia> Threads.threadid()
     three processes have 2 threads enabled. For more fine grained control over worker
     threads use [`addprocs`](@ref) and pass `-t`/`--threads` as `exeflags`.
 
+### Multiple GC Threads
+
+The Garbage Collector (GC) can use multiple threads. The amount used is either half the number
+of compute worker threads or configured by either the `--gcthreads` command line argument or by using the
+[`JULIA_NUM_GC_THREADS`](@ref env-gc-threads) environment variable.
+
+!!! compat "Julia 1.10"
+    The `--gcthreads` command line argument requires at least Julia 1.10.
+
 ## [Threadpools](@id man-threadpools)
 
 When a program's threads are busy with many tasks to run, tasks may experience

doc/src/manual/profile.md

@@ -310,7 +310,122 @@ the amount of memory allocated by each line of code.
 
 ### Line-by-Line Allocation Tracking
 
-To measure allocation line-by-line, start Julia with the `--track-allocation=<setting>` command-line
+While [`@time`](@ref) logs high-level stats about memory usage and garbage collection over the course
+of evaluating an expression, it can be useful to log each garbage collection event, to get an
+intuitive sense of how often the garbage collector is running, how long it's running each time,
+and how much garbage it collects each time. This can be enabled with
+[`GC.enable_logging(true)`](@ref), which causes Julia to log to stderr every time
+a garbage collection happens.
+
+### [Allocation Profiler](@id allocation-profiler)
+
+!!! compat "Julia 1.8"
+    This functionality requires at least Julia 1.8.
+
+The allocation profiler records the stack trace, type, and size of each
+allocation while it is running. It can be invoked with
+[`Profile.Allocs.@profile`](@ref).
+
+This information about the allocations is returned as an array of `Alloc`
+objects, wrapped in an `AllocResults` object. The best way to visualize these is
+currently with the [PProf.jl](https://github.com/JuliaPerf/PProf.jl) and
+[ProfileCanvas.jl](https://github.com/pfitzseb/ProfileCanvas.jl) packages, which
+can visualize the call stacks which are making the most allocations.
+
+The allocation profiler does have significant overhead, so a `sample_rate`
+argument can be passed to speed it up by making it skip some allocations.
+Passing `sample_rate=1.0` will make it record everything (which is slow);
+`sample_rate=0.1` will record only 10% of the allocations (faster), etc.
+
+!!! compat "Julia 1.11"
+
+    Older versions of Julia could not capture types in all cases. In older versions of
+    Julia, if you see an allocation of type `Profile.Allocs.UnknownType`, it means that
+    the profiler doesn't know what type of object was allocated. This mainly happened when
+    the allocation was coming from generated code produced by the compiler. See
+    [issue #43688](https://github.com/JuliaLang/julia/issues/43688) for more info.
+
+    Since Julia 1.11, all allocations should have a type reported.
+
+For more details on how to use this tool, please see the following talk from JuliaCon 2022:
+https://www.youtube.com/watch?v=BFvpwC8hEWQ
+
+##### Allocation Profiler Example
+
+In this simple example, we use PProf to visualize the alloc profile. You could use another
+visualization tool instead. We collect the profile (specifying a sample rate), then we visualize it.
+```julia
+using Profile, PProf
+Profile.Allocs.clear()
+Profile.Allocs.@profile sample_rate=0.0001 my_function()
+PProf.Allocs.pprof()
+```
+
+Here is a more in-depth example, showing how we can tune the sample rate. A
+good number of samples to aim for is around 1 - 10 thousand. Too many, and the
+profile visualizer can get overwhelmed, and profiling will be slow. Too few,
+and you don't have a representative sample.
+
+
+```julia-repl
+julia> import Profile
+
+julia> @time my_function()  # Estimate allocations from a (second-run) of the function
+  0.110018 seconds (1.50 M allocations: 58.725 MiB, 17.17% gc time)
+500000
+
+julia> Profile.Allocs.clear()
+
+julia> Profile.Allocs.@profile sample_rate=0.001 begin   # 1.5 M * 0.001 = ~1.5K allocs.
+           my_function()
+       end
+500000
+
+julia> prof = Profile.Allocs.fetch();  # If you want, you can also manually inspect the results.
+
+julia> length(prof.allocs)  # Confirm we have expected number of allocations.
+1515
+
+julia> using PProf  # Now, visualize with an external tool, like PProf or ProfileCanvas.
+
+julia> PProf.Allocs.pprof(prof; from_c=false)  # You can optionally pass in a previously fetched profile result.
+Analyzing 1515 allocation samples... 100%|████████████████████████████████| Time: 0:00:00
+Main binary filename not available.
+Serving web UI on http://localhost:62261
+"alloc-profile.pb.gz"
+```
+Then you can view the profile by navigating to http://localhost:62261, and the profile is saved to disk.
+See PProf package for more options.
+
+##### Allocation Profiling Tips
+
+As stated above, aim for around 1-10 thousand samples in your profile.
+
+Note that we are uniformly sampling in the space of _all allocations_, and are not weighting
+our samples by the size of the allocation. So a given allocation profile may not give a
+representative profile of where most bytes are allocated in your program, unless you had set
+`sample_rate=1`.
+
+Allocations can come from users directly constructing objects, but can also come from inside
+the runtime or be inserted into compiled code to handle type instability. Looking at the
+"source code" view can be helpful to isolate them, and then other external tools such as
+[`Cthulhu.jl`](https://github.com/JuliaDebug/Cthulhu.jl) can be useful for identifying the
+cause of the allocation.
+
+##### Allocation Profile Visualization Tools
+
+There are several profiling visualization tools now that can all display Allocation
+Profiles. Here is a small list of some of the main ones we know about:
+- [PProf.jl](https://github.com/JuliaPerf/PProf.jl)
+- [ProfileCanvas.jl](https://github.com/pfitzseb/ProfileCanvas.jl)
+- VSCode's built-in profile visualizer (`@profview_allocs`) [docs needed]
+- Viewing the results directly in the REPL
+  - You can inspect the results in the REPL via [`Profile.Allocs.fetch()`](@ref), to view
+    the stacktrace and type of each allocation.
+
+#### Line-by-Line Allocation Tracking
+
+An alternative way to measure allocations is to start Julia with the `--track-allocation=<setting>` command-line
 option, for which you can choose `none` (the default, do not measure allocation), `user` (measure
 memory allocation everywhere except Julia's core code), or `all` (measure memory allocation at
 each line of Julia code). Allocation gets measured for each line of compiled code. When you quit

src/Makefile

@@ -43,8 +43,8 @@ endif
 SRCS := \
 	jltypes gf typemap smallintset ast builtins module interpreter symbol \
 	dlload sys init task array staticdata toplevel jl_uv datatype \
-	simplevector runtime_intrinsics precompile jloptions \
-	threading partr stackwalk gc gc-debug gc-pages gc-stacks gc-alloc-profiler method \
+	simplevector runtime_intrinsics precompile jloptions mtarraylist \
+	threading partr stackwalk gc gc-debug gc-pages gc-stacks gc-alloc-profiler gc-page-profiler method \
 	jlapi signal-handling safepoint timing subtype rtutils gc-heap-snapshot \
 	crc32c APInt-C processor ircode opaque_closure codegen-stubs coverage runtime_ccall
 
@@ -99,7 +99,7 @@ ifeq ($(USE_SYSTEM_LIBUV),0)
 UV_HEADERS += uv.h
 UV_HEADERS += uv/*.h
 endif
-PUBLIC_HEADERS := $(BUILDDIR)/julia_version.h $(wildcard $(SRCDIR)/support/*.h) $(addprefix $(SRCDIR)/,julia.h julia_assert.h julia_threads.h julia_fasttls.h julia_locks.h julia_atomics.h jloptions.h)
+PUBLIC_HEADERS := $(BUILDDIR)/julia_version.h $(wildcard $(SRCDIR)/support/*.h) $(addprefix $(SRCDIR)/,work-stealing-queue.h julia.h julia_assert.h julia_threads.h julia_fasttls.h julia_locks.h julia_atomics.h jloptions.h)
 ifeq ($(OS),WINNT)
 PUBLIC_HEADERS += $(addprefix $(SRCDIR)/,win32_ucontext.h)
 endif
@@ -353,7 +353,7 @@ $(BUILDDIR)/julia_version.h: $(JULIAHOME)/VERSION
 	@echo "#ifndef JL_VERSION_H" >> $@.$(JULIA_BUILD_MODE).tmp
 	@echo "#define JL_VERSION_H" >> $@.$(JULIA_BUILD_MODE).tmp
 	@echo "#define JULIA_VERSION_STRING" \"$(JULIA_VERSION)\" >> $@.$(JULIA_BUILD_MODE).tmp
-	@echo $(JULIA_VERSION) | awk 'BEGIN {FS="[.,-]"} \
+	@echo $(JULIA_VERSION) | awk 'BEGIN {FS="[.,+-]"} \
 	{print "#define JULIA_VERSION_MAJOR " $$1 "\n" \
 	"#define JULIA_VERSION_MINOR " $$2 "\n" \
 	"#define JULIA_VERSION_PATCH " $$3 ; \

src/cgutils.cpp

@@ -3933,7 +3933,6 @@ static Value *emit_defer_signal(jl_codectx_t &ctx)
     return ctx.builder.CreateInBoundsGEP(ctx.types().T_sigatomic, ptls, ArrayRef<Value*>(offset), "jl_defer_signal");
 }
 
-
 #ifndef JL_NDEBUG
 static int compare_cgparams(const jl_cgparams_t *a, const jl_cgparams_t *b)
 {

src/codegen.cpp

@@ -1279,6 +1279,7 @@ extern "C" {
         1,
 #endif
         (int) DICompileUnit::DebugEmissionKind::FullDebug,
+        1,
         jl_rettype_inferred, NULL };
 }
 
@@ -7805,7 +7806,11 @@ static jl_llvm_functions_t
         ctx.builder.CreateAlignedStore(load_world, world_age_field, Align(sizeof(size_t)));
     }
 
-    // step 11b. Do codegen in control flow order
+    // step 11b. Emit the entry safepoint
+    if (JL_FEAT_TEST(ctx, safepoint_on_entry))
+        emit_gc_safepoint(ctx.builder, get_current_ptls(ctx), ctx.tbaa().tbaa_const);
+
+    // step 11c. Do codegen in control flow order
     std::vector<int> workstack;
     std::map<int, BasicBlock*> BB;
     std::map<size_t, BasicBlock*> come_from_bb;