Add devdocs on fixing precompile hangs

base/initdefs.jl

@@ -19,14 +19,17 @@ An array of the command line arguments passed to Julia, as strings.
 const ARGS = String[]
 
 """
-    exit(code=0)
+    exit(code=0; kill_tasks=true)
 
 Stop the program with an exit code. The default exit code is zero, indicating that the
 program completed successfully. In an interactive session, `exit()` can be called with
 the keyboard shortcut `^D`.
+
+Setting `kill_tasks=false` will cause Julia to wait for running tasks (other than the
+main task) to finish before exiting.
 """
-exit(n) = ccall(:jl_exit, Cvoid, (Int32,), n)
-exit() = exit(0)
+exit(n; kill_tasks::Bool=true) = ccall(:jl_exit, Cvoid, (Int32, Int32), n, kill_tasks)
+exit(; kwargs...) = exit(0; kwargs...)
 
 const roottask = current_task()
 

doc/make.jl

@@ -157,6 +157,7 @@ DevDocs = [
         "devdocs/gc-sa.md",
         "devdocs/gc.md",
         "devdocs/jit.md",
+        "devdocs/precompile_hang.md",
     ],
     "Developing/debugging Julia's C code" => [
         "devdocs/backtraces.md",

doc/src/devdocs/precompile_hang.md

@@ -0,0 +1,89 @@
+# Fixing precompilation hangs due to open tasks or IO
+
+On Julia 1.10 or higher, you might see the following message:
+
+![Screenshot of precompilation hang](./img/precompilation_hang.png)
+
+If you follow the advice and hit `Ctrl-C`, you might see
+
+```
+^C Interrupted: Exiting precompilation...
+
+  1 dependency had warnings during precompilation:
+┌ Test1 [ac89d554-e2ba-40bc-bc5c-de68b658c982]
+│  [pid 2745] waiting for IO to finish:
+│   TYPE[FD/PID]       @UV_HANDLE_T->DATA
+│   timer              @0x55580decd1e0->0x7f94c3a4c340
+```
+
+and, depending on how long you waited, this may repeat.
+
+This message conveys two key pieces of information:
+
+- the hang is occurring during precompilation of `Test1`, a dependency of `Test2` (the package we were trying to load with `using Test2`)
+- during precompilation of `Test1`, Julia created a `Timer` object (use `?Timer` if you're unfamiliar with Timers) which is still open; until that closes, the process is hung
+
+If this is enough of a hint for you to figure out how `timer = Timer(args...)` is being created, one good solution is to add `wait(timer)` if `timer` eventually finishes on its own, or `close(timer)` if you need to force-close it, before the final `end` of the module.
+
+However, there are cases that may not be that straightforward. Usually the best option is to start by determining whether the hang is due to code in Test1 or whether it is due to one of Test1's dependencies:
+
+1. `Pkg.develop("Test1")`
+2. Comment out all the code `include`d or defined in `Test1`, *except* the `using/import` statements
+3. Try `using Test2` (or even `using Test1` assuming that hangs too) again
+
+Now we arrive at a fork in the road: either
+
+- the hang persists, indicating it is due to one of your dependencies
+- the hang disappears, indicating that it is due to something in your code
+
+## If the hang is due to a package dependency
+
+Use a binary search to identify the problematic dependency: start by commenting out half your dependencies, then when you isolate which half is responsible comment out half of that half, etc. (You don't have to remove them from the project, just comment out the `using`/`import` statements.)
+
+Once you've identified a suspect (here we'll call it `ThePackageYouThinkIsCausingTheProblem`), first try precompiling that package. If it also hangs during precompilation, continue chasing the problem backwards.
+
+However, most likely `ThePackageYouThinkIsCausingTheProblem` will precompile fine. This suggests it's in the function `ThePackageYouThinkIsCausingTheProblem.__init__`, which does not run during precompilation of `ThePackageYouThinkIsCausingTheProblem` but *does* in any package that loads `ThePackageYouThinkIsCausingTheProblem`.  To test this theory, set up a minimal working example (MWE), something like
+
+```julia
+(@v1.10) pkg> generate MWE
+  Generating  project MWE:
+    MWE\Project.toml
+    MWE\src\MWE.jl
+```
+
+where the source code of `MWE.jl` is
+
+```julia
+module MWE
+using ThePackageYouThinkIsCausingTheProblem
+end
+```
+
+and you've added `ThePackageYouThinkIsCausingTheProblem` to MWE's dependencies.
+
+If that MWE reproduces the hang, you've found your culprit:
+`ThePackageYouThinkIsCausingTheProblem.__init__` must be creating the `Timer` object. If the timer object can be safely `close`d, that's a good option. Otherwise, the most common solution is to avoid creating the timer while *any* package is being precompiled: add
+
+```julia
+ccall(:jl_generating_output, Cint, ()) == 1 && return nothing
+```
+
+as the first line of `ThePackageYouThinkIsCausingTheProblem.__init__`, and it will avoid doing any initialization in any Julia process whose purpose is to precompile packages.
+
+## If the hang is in your code
+
+Search your package for suggestive words (here like "Timer") and see if you can identify where the problem is being created. Note that a method *definition* like
+
+```julia
+maketimer() = Timer(timer -> println("hi"), 0; interval=1)
+```
+
+is not problematic in and of itself: it can cause this problem only if `maketimer` gets called while the module is being defined. This might be happening from a top-level statement such as
+
+```julia
+const GLOBAL_TIMER = maketimer()
+```
+
+or it might conceivably occur in a [precompile workload](https://github.com/JuliaLang/PrecompileTools.jl).
+
+If you struggle to identify the causative lines, then consider doing a binary search: comment out sections of your package (or `include` lines to omit entire files) until you've reduced the problem in scope.

src/init.c

@@ -202,8 +202,10 @@ static void jl_close_item_atexit(uv_handle_t *handle)
 void jl_task_frame_noreturn(jl_task_t *ct) JL_NOTSAFEPOINT;
 
 // cause this process to exit with WEXITSTATUS(signo), after waiting to finish all julia, C, and C++ cleanup
-JL_DLLEXPORT void jl_exit(int exitcode)
+JL_DLLEXPORT void jl_exit(int exitcode, int kill_tasks)
 {
+    if (!kill_tasks)
+        jl_task_wait_empty();
     jl_atexit_hook(exitcode);
     exit(exitcode);
 }

src/julia.h

@@ -1852,7 +1852,7 @@ JL_DLLEXPORT int jl_is_initialized(void);
 JL_DLLEXPORT void jl_atexit_hook(int status);
 JL_DLLEXPORT void jl_task_wait_empty(void);
 JL_DLLEXPORT void jl_postoutput_hook(void);
-JL_DLLEXPORT void JL_NORETURN jl_exit(int status);
+JL_DLLEXPORT void JL_NORETURN jl_exit(int status, int kill_tasks);
 JL_DLLEXPORT void JL_NORETURN jl_raise(int signo);
 JL_DLLEXPORT const char *jl_pathname_for_handle(void *handle);
 JL_DLLEXPORT jl_gcframe_t **jl_adopt_thread(void);

src/rtutils.c

@@ -34,7 +34,7 @@ JL_DLLEXPORT void JL_NORETURN jl_error(const char *str)
 {
     if (jl_errorexception_type == NULL) {
         jl_printf(JL_STDERR, "ERROR: %s\n", str);
-        jl_exit(1);
+        jl_exit(1, 1);
     }
     jl_value_t *msg = jl_pchar_to_string((char*)str, strlen(str));
     JL_GC_PUSH1(&msg);
@@ -50,7 +50,7 @@ jl_value_t *jl_vexceptionf(jl_datatype_t *exception_type,
         jl_printf(JL_STDERR, "ERROR: ");
         jl_vprintf(JL_STDERR, fmt, args);
         jl_printf(JL_STDERR, "\n");
-        jl_exit(1);
+        jl_exit(1, 1);
     }
     char *str = NULL;
     int ok = vasprintf(&str, fmt, args);

src/signals-win.c

@@ -81,7 +81,7 @@ void __cdecl crt_sig_handler(int sig, int num)
         signal(SIGINT, (void (__cdecl *)(int))crt_sig_handler);
         if (!jl_ignore_sigint()) {
             if (exit_on_sigint)
-                jl_exit(130); // 128 + SIGINT
+                jl_exit(130, 1); // 128 + SIGINT
             jl_try_throw_sigint();
         }
         break;
@@ -220,7 +220,7 @@ static BOOL WINAPI sigint_handler(DWORD wsig) //This needs winapi types to guara
     }
     if (!jl_ignore_sigint()) {
         if (exit_on_sigint)
-            jl_exit(128 + sig); // 128 + SIGINT
+            jl_exit(128 + sig, 1); // 128 + SIGINT
         jl_try_deliver_sigint();
     }
     return 1;
@@ -334,7 +334,7 @@ LONG WINAPI jl_exception_handler(struct _EXCEPTION_POINTERS *ExceptionInfo)
     if (recursion++)
         exit(1);
     else
-        jl_exit(1);
+        jl_exit(1, 1);
 }
 
 JL_DLLEXPORT void jl_install_sigint_handler(void)

src/staticdata.c

@@ -2537,7 +2537,7 @@ static void jl_save_system_image_to_stream(ios_t *f, jl_array_t *mod_array,
             (intmax_t)sysimg.size,
             ((uintptr_t)1 << RELOC_TAG_OFFSET)
         );
-        jl_exit(1);
+        jl_exit(1, 1);
     }
     if (const_data.size / sizeof(void*) > ((uintptr_t)1 << RELOC_TAG_OFFSET)) {
         jl_printf(
@@ -2546,7 +2546,7 @@ static void jl_save_system_image_to_stream(ios_t *f, jl_array_t *mod_array,
             (intmax_t)const_data.size,
             ((uintptr_t)1 << RELOC_TAG_OFFSET)*sizeof(void*)
         );
-        jl_exit(1);
+        jl_exit(1, 1);
     }
     htable_free(&s.callers_with_edges);
 

src/task.c

@@ -696,7 +696,7 @@ JL_DLLEXPORT JL_NORETURN void jl_no_exc_handler(jl_value_t *e, jl_task_t *ct)
     jlbacktrace(); // written to STDERR_FILENO
     if (ct == NULL)
         jl_raise(6);
-    jl_exit(1);
+    jl_exit(1, 1);
 }
 
 /* throw_internal - yield to exception handler */

test/atexit.jl

@@ -260,4 +260,12 @@ using Test
         end
     end
     rm(atexit_temp_dir; force = true, recursive = true)
+
+    @testset "block exit with unfinished tasks" begin
+        t = @elapsed run(`$(Base.julia_cmd()) --startup=no -e 't=Timer(0.1; interval=1); exit()'`; wait=true)
+        p =          run(`$(Base.julia_cmd()) --startup=no -e 't=Timer(0.1; interval=1); exit(; kill_tasks=false)'`; wait=false)
+        sleep(10*t)
+        @test process_running(p)
+        kill(p)
+    end
 end