search

starpu-runtime / starpu

This is a mirror of https://gitlab.inria.fr/starpu/starpu where our development happens, but contributions are welcome here too!
https://starpu.gitlabpages.inria.fr/
GNU Lesser General Public License v2.1
58 stars 13 forks source link

FAIL: parallel_workers/parallel_workers #44

Closed ramet closed 4 months ago

ramet commented 4 months ago

Steps to reproduce

I'm using a clean Debian 12 ARM system in a virtual machine (which exposes 2 cores) under MacOS. StarPU is installed using Guix in the requested configuration for PaStiX 6.3.2.

Some tests related to parallel workers are failing. Perhaps the problem is more in HWLOC?

Obtained behavior

Here is the command line : 

guix shell gcc-toolchain coreutils pastix --pure -- /bin/bash --norc

The error occurs when installing the dependency on StarPU 1.4.4, during unit testing : "FAIL: parallel_workers/parallel_workers" (same error with : "FAIL: parallel_workers/parallel_workers_oldapi")

Configuration result

FAIL: parallel_workers/parallel_workers
=======================================

[starpu][localhost][_perf_model_add_dir] Warning: directory </gnu/store/i68nyhxx1bh1r3amzs503mcy3b02gf97-starpu-1.4.4/share/starpu/perfmodels/sampling> as set by installation directory does not exist
hwloc/linux: failed to find sysfs cpu topology directory, aborting linux discovery.
[starpu][localhost][_starpu_init_topology] Warning: The OS did not report CPU cores. Assuming there is only one hardware thread per core.
[error] `./parallel_workers/parallel_workers' killed with signal 11; test marked as failed
while looking for core file of ./parallel_workers/parallel_workers: core.102544: No such file or directory

warning: core file may not match specified executable file.
[New LWP 102544]
[New LWP 102560]
[New LWP 102558]
[New LWP 102559]
[New LWP 102561]
[Thread debugging using libthread_db enabled]
Using host libthread_db library "/gnu/store/a19xbynxc3sg25xpkwmx7g0mdl7g31hx-glibc-2.35/lib/libthread_db.so.1".
Core was generated by `/tmp/guix-build-starpu-1.4.4.drv-0/source/examples/parallel_workers/.libs/paral'.
Program terminated with signal SIGSEGV, Segmentation fault.
#0  starpu_sched_ctx_create (workerids=0x0, nworkers=1, sched_ctx_name=sched_ctx_name@entry=0xfffff7ec0b48 "parallel_workers") at core/sched_ctx.c:793
793         if (workerids[i] < 0 || workerids[i] >= num_workers)
[Current thread is 1 (Thread 0xfffff7ff1020 (LWP 102544))]
warning: File "/gnu/store/vwkiblwq7y8xiflg51cnk2a3x1wwiysj-gcc-11.3.0-lib/lib/libstdc++.so.6.0.29-gdb.py" auto-loading has been declined by your `auto-load safe-path' set to "$debugdir:$datadir/auto-load".
To enable execution of this file add
    add-auto-load-safe-path /gnu/store/vwkiblwq7y8xiflg51cnk2a3x1wwiysj-gcc-11.3.0-lib/lib/libstdc++.so.6.0.29-gdb.py
line to your configuration file "/tmp/guix-build-starpu-1.4.4.drv-0/source/.config/gdb/gdbinit".
To completely disable this security protection add
    set auto-load safe-path /
line to your configuration file "/tmp/guix-build-starpu-1.4.4.drv-0/source/.config/gdb/gdbinit".
For more information about this security protection see the
"Auto-loading safe path" section in the GDB manual.  E.g., run from the shell:
    info "(gdb)Auto-loading safe path"
Undefined command: "py-list".  Try "help".
Undefined command: "starpu-tasks".  Try "help".
Undefined command: "starpu-workers".  Try "help".
Undefined command: "starpu-print-datas-summary".  Try "help".
Undefined command: "starpu-memusage".  Try "help".
Undefined command: "starpu-print-archs".  Try "help".
Undefined command: "starpu-print-registered-models".  Try "help".
#0  starpu_sched_ctx_create (workerids=0x0, nworkers=1, sched_ctx_name=sched_ctx_name@entry=0xfffff7ec0b48 "parallel_workers") at core/sched_ctx.c:793
        __func__ = "starpu_sched_ctx_create"
        varg_list = {__stack = 0xfffffffebbd0, __gr_top = 0xfffffffebbd0, __vr_top = 0xfffffffebba0, __gr_offs = -32, __vr_offs = 0}
        arg_type = -135262208
        min_prio_set = 0
        max_prio_set = 0
        min_prio = 0
        max_prio = 0
        nsms = 0
        sub_ctxs = 0x0
        nsub_ctxs = 0
        user_data = 0x0
        sched_policy = 0x0
        hierarchy_level = 0
        nesting_sched_ctx = 10
        awake_workers = 0
        init_sched = 0x0
        num_workers = 4
        i = 0
        sched_ctx = <optimized out>
        added_workerids = 0x42e070
        nw_ctx = <optimized out>
        p_ret = <optimized out>
        __ptrs = <optimized out>
        __n = <optimized out>
#1  0x0000fffff7e8c214 in _starpu_parallel_worker_create (parallel_worker=parallel_worker@entry=0x42c3b0) at parallel_worker/starpu_parallel_worker_create.c:333
        config = <optimized out>
#2  0x0000fffff7e8c3f4 in _starpu_parallel_worker_group_create (group=group@entry=0x42c2f0) at parallel_worker/starpu_parallel_worker_create.c:350
        c = 0x42c3b0
#3  0x0000fffff7e8d590 in _starpu_parallel_worker_config (parallel_worker_level=<optimized out>, machine=0x42c270) at parallel_worker/starpu_parallel_worker_create.c:553
        g = 0x42c2f0
        ret = 0
        config = <optimized out>
        sched_policy = <optimized out>
        global_ctx = <optimized out>
#4  0x0000fffff7e8d7ec in _starpu_parallel_worker_init_varg (parallel_worker_level=parallel_worker_level@entry=HWLOC_OBJ_PACKAGE, varg_list=...) at parallel_worker/starpu_parallel_worker_create.c:241
        arg_type = 0
        machine = 0x42c270
        __func__ = "_starpu_parallel_worker_init_varg"
        __PRETTY_FUNCTION__ = "_starpu_parallel_worker_init_varg"
#5  0x0000fffff7e8e058 in starpu_parallel_worker_init (parallel_worker_level=parallel_worker_level@entry=HWLOC_OBJ_PACKAGE) at parallel_worker/starpu_parallel_worker_create.c:255
        config = <optimized out>
        varg_list = {__stack = 0xfffffffebea0, __gr_top = 0xfffffffebea0, __vr_top = 0xfffffffebe60, __gr_offs = -56, __vr_offs = -128}
#6  0x0000000000400ff8 in main () at parallel_workers/parallel_workers.c:79
        ntasks = 8
        ret = 0
        i = <optimized out>
        parallel_workers = <optimized out>
        __PRETTY_FUNCTION__ = <optimized out>
        __func__ = "main"
        array1 = {0 <repeats 4000 times>}
        array2 = {0 <repeats 3000 times>, 1.3906711614409153e-309, 1.3906704974653626e-309, 1.3906711614411525e-309, 1.3906704983826054e-309, 0, 0, 1.3906711614613894e-309, 1.3906704975785234e-309, 1.3906704984230793e-309, 1.3906704983826054e-309, 1.3906704984275061e-309, 0, 1.0239368235597433e+200, 5.0130396337438505e-90, 8.3365299802249716e-72, 3.6195066075658384e+262, 1.1146009660511128e+171, 2.2120874227700783e+214, 1.1746884519525608e+214, 3.7879995910192795e+209, 1.1711897052348906e+166, 1.9108618774865702e+214, 3.5591190367735002e+180, 1.46016160971922e-319, 0 <repeats 377 times>, 7.7305068220971491e-318, 7.7112580245351742e-318, 7.7112580245351742e-318, 3.2379086165851934e-319, 0, 2.4703282292062327e-323, 8.034060754902011e-318, 8.1554823280239558e-318, 8.1439409545371042e-318, 8.3982464237645107e-318, 3.2379086165851934e-319, 7.7102698932434917e-318, 1.4821969375237396e-323, 0 <repeats 15 times>, 1.2142157312194475e-318, 1.2024767314742595e-318, 1.2024767314742595e-318, 0, 4.0473857707314917e-319, 3.860826582861837e-319, 3.860826582861837e-319, 1.3906711614580693e-309, 1.390670497321886e-309, 1.3906711614586226e-309, 1.3906704983969926e-309, 1.3906711614593341e-309, 1.3906704973289412e-309, 1.3906711614586226e-309, 4.9406564584124654e-323, 1.3906711614584645e-309, 1.3906704974401455e-309, 1.3906704982485357e-309, 2.3221085354538588e-322, 1.3906711614593341e-309, 1.3906704973293563e-309, 1.390671161459255e-309, 1.3906704973530912e-309, 1.390671161459255e-309, 1.3906704973666879e-309, 0, 0, 2.0733533996918329e-317, 1.3906711614622194e-309, 1.390671161459255e-309, 1.3906704973663124e-309, 1.3906704566746112e-309, 1.3906704983969926e-309, 0, 1.3906704982545041e-309, 1.3906704650931736e-309, 1.3906704983969926e-309, 0, 1.3906704982475476e-309, 1.3906704660645462e-309, 1.3906704983969926e-309, 1.3906711614611522e-309, 1.3906704973779723e-309, 2.0733533996918329e-317, 0, 1.3906704984275061e-309, 0, 4.9406564584124654e-324, 1.3906711614622194e-309, 1.3906704984028423e-309, 1.3906704983826054e-309, 0, 1.390670497266353e-309, 1.3906704983623685e-309, 1.3906711614622589e-309, 1.3906704650725415e-309, 1.3906711614622589e-309, 1.3906704650725415e-309, 9.8813129168249309e-324, 1.3906711614622589e-309, 1.3906711614590179e-309, 9.8813129168249309e-324, 0, 1.4821969375237396e-323, 1.3906704984253717e-309, 1.3906711614625751e-309, 0, 1.3906704984028423e-309, 2.9643938750474793e-323, 3.2127112686472898e-319, 5.2917543283166305e-318, 3.2127112686472898e-319, 5.2917543283166305e-318, 4.2440079518075883e-314, 0, 0, 0, 9.7773615049399326e-318, 2.0236928853657458e-320, 1.3906711614609941e-309, 1.3906704973765889e-309, 1.3906704572715759e-309, 0, 0, 8.4617375499254853e-315, 1.3906711614662115e-309, 1.3906704972666494e-309, 1.390671161470994e-309, 1.3906704984230793e-309, 1.390670464783849e-309, 1.3906704984275061e-309, 1.3906704982485357e-309, 4.9406564584124654e-324, 0, 1.3906711614712707e-309, 0, 1.390670497266353e-309, 0, 0, 0, 1.390670497266353e-309, 0, 1.3906704984324467e-309, 0, 0, 0, 4.9406564584124654e-323, 0, 0, 0, 6.9169190417774516e-323, 0, 0, 1.3906704982481405e-309, 1.3906711614820216e-309, 0, 4.1106261733991712e-321, 3.3280039514459023e-294, 0, 2.1279211652158202e-314, 7.9595951807608183e-319, 3.1620201333839779e-322, 9.7564921720595984e-318, 1.3350986381965695e-307, 1.8914248227666973e-307, 8.4879831668254831e-314, 3.1620201333839779e-322, 3.1620201333839779e-322, 3.1620201333839779e-322, 2.7667676167109806e-321, 2.7667676167109806e-321, 3.9525251667299724e-323, 8.4879831653432862e-314...}
        handle1 = 0x0
        handle2 = 0x0
        size = 0
        out = <optimized out>
Undefined command: "py-bt".  Try "help".

Thread 5 (Thread 0xfffff5fbf080 (LWP 102561)):
#0  0x0000fffff786ebe8 in __pthread_mutex_unlock_usercnt () from /gnu/store/a19xbynxc3sg25xpkwmx7g0mdl7g31hx-glibc-2.35/lib/libc.so.6
No symbol table info available.
#1  0x0000fffff7e15b98 in _starpu_worker_relax_on () at ./core/workers.h:1118
        p_ret = <optimized out>
        worker = 0xfffff7f05308 <_starpu_config+15960>
        __func__ = "_starpu_worker_relax_on"
        __PRETTY_FUNCTION__ = "_starpu_worker_relax_on"
#2  0x0000fffff7e16594 in ws_pop_task (sched_ctx_id=0) at sched_policies/work_stealing_policy.c:601
        ws = 0x428c30
        task = <optimized out>
        workerid = 3
        victim = <optimized out>
#3  0x0000fffff7e04f88 in _starpu_pop_task (worker=worker@entry=0xfffff7f05308 <_starpu_config+15960>) at core/sched_policy.c:1020
        sched_ctx = 0xfffff7fa1600 <_starpu_config+655696>
        task = 0x0
        worker_id = <optimized out>
        node = <optimized out>
        profiling = 0
        pop_start_time = {tv_sec = 281474841465896, tv_nsec = 0}
        pick = <optimized out>
        i = <optimized out>
        nbuffers = <optimized out>
#4  0x0000fffff7e2ab30 in _starpu_get_worker_task (worker=worker@entry=0xfffff7f05308 <_starpu_config+15960>, workerid=workerid@entry=3, memnode=memnode@entry=0) at drivers/driver_common/driver_common.c:431
        task = <optimized out>
        keep_awake = <optimized out>
        __func__ = "_starpu_get_worker_task"
#5  0x0000fffff7e8a1bc in _starpu_cpu_driver_run_once (cpu_worker=cpu_worker@entry=0xfffff7f05308 <_starpu_config+15960>) at drivers/cpu/driver_cpu.c:608
        memnode = 0
        workerid = 3
        pi = {conf = 0x0, event_type = starpu_prof_tool_event_driver_init_end, starpu_version = {1, 4126926560, 65535}, thread_id = -135748100, worker_id = 65535, device_number = -135245048, driver_type = 65535, memnode = 4160361648, bytes_to_transfer = 65535, bytes_transfered = 0, fun_ptr = 0x0}
        res = <optimized out>
        j = <optimized out>
        task = 0x0
        pending_task = 0x0
        rank = 0
        __func__ = "_starpu_cpu_driver_run_once"
        continuation_wake_up = <optimized out>
        __PRETTY_FUNCTION__ = "_starpu_cpu_driver_run_once"
#6  0x0000fffff7e8a604 in _starpu_cpu_worker (arg=0xfffff7f05308 <_starpu_config+15960>) at drivers/cpu/driver_cpu.c:714
        worker = 0xfffff7f05308 <_starpu_config+15960>
        pi = {conf = 0x0, event_type = starpu_prof_tool_event_start_transfer, starpu_version = {1, 4, 4}, thread_id = -168038272, worker_id = 3, device_number = 3, driver_type = starpu_prof_tool_driver_cpu, memnode = 0, bytes_to_transfer = 0, bytes_transfered = 0, fun_ptr = 0x0}
#7  0x0000fffff786a394 in start_thread () from /gnu/store/a19xbynxc3sg25xpkwmx7g0mdl7g31hx-glibc-2.35/lib/libc.so.6
No symbol table info available.
#8  0x0000fffff78cefdc in thread_start () from /gnu/store/a19xbynxc3sg25xpkwmx7g0mdl7g31hx-glibc-2.35/lib/libc.so.6
No symbol table info available.

Thread 4 (Thread 0xfffff6fdf080 (LWP 102559)):
#0  0x0000fffff7868a88 in pthread_cond_broadcast@@GLIBC_2.17 () from /gnu/store/a19xbynxc3sg25xpkwmx7g0mdl7g31hx-glibc-2.35/lib/libc.so.6
No symbol table info available.
#1  0x0000fffff7e15b8c in _starpu_worker_relax_on () at ./core/workers.h:1117
        p_ret = <optimized out>
        worker = 0xfffff7f03cf8 <_starpu_config+10312>
        __func__ = "_starpu_worker_relax_on"
        __PRETTY_FUNCTION__ = "_starpu_worker_relax_on"
#2  0x0000fffff7e16594 in ws_pop_task (sched_ctx_id=0) at sched_policies/work_stealing_policy.c:601
        ws = 0x428c30
        task = <optimized out>
        workerid = 1
        victim = <optimized out>
#3  0x0000fffff7e04f88 in _starpu_pop_task (worker=worker@entry=0xfffff7f03cf8 <_starpu_config+10312>) at core/sched_policy.c:1020
        sched_ctx = 0xfffff7fa1600 <_starpu_config+655696>
        task = 0x0
        worker_id = <optimized out>
        node = <optimized out>
        profiling = 0
        pop_start_time = {tv_sec = 281474841460248, tv_nsec = 0}
        pick = <optimized out>
        i = <optimized out>
        nbuffers = <optimized out>
#4  0x0000fffff7e2ab30 in _starpu_get_worker_task (worker=worker@entry=0xfffff7f03cf8 <_starpu_config+10312>, workerid=workerid@entry=1, memnode=memnode@entry=0) at drivers/driver_common/driver_common.c:431
        task = <optimized out>
        keep_awake = <optimized out>
        __func__ = "_starpu_get_worker_task"
#5  0x0000fffff7e8a1bc in _starpu_cpu_driver_run_once (cpu_worker=cpu_worker@entry=0xfffff7f03cf8 <_starpu_config+10312>) at drivers/cpu/driver_cpu.c:608
        memnode = 0
        workerid = 1
        pi = {conf = 0xfffff6fde760, event_type = 4143834912, starpu_version = {65535, 4143834848, 65535}, thread_id = -135748100, worker_id = 65535, device_number = -135250696, driver_type = 65535, memnode = 4160361648, bytes_to_transfer = 65535, bytes_transfered = 0, fun_ptr = 0xfffff7d9b0a8}
        res = <optimized out>
        j = <optimized out>
        task = 0x0
        pending_task = 0x0
        rank = 0
        __func__ = "_starpu_cpu_driver_run_once"
        continuation_wake_up = <optimized out>
        __PRETTY_FUNCTION__ = "_starpu_cpu_driver_run_once"
#6  0x0000fffff7e8a604 in _starpu_cpu_worker (arg=0xfffff7f03cf8 <_starpu_config+10312>) at drivers/cpu/driver_cpu.c:714
        worker = 0xfffff7f03cf8 <_starpu_config+10312>
        pi = {conf = 0x0, event_type = starpu_prof_tool_event_start_transfer, starpu_version = {1, 4, 4}, thread_id = -151129984, worker_id = 1, device_number = 1, driver_type = starpu_prof_tool_driver_cpu, memnode = 0, bytes_to_transfer = 0, bytes_transfered = 0, fun_ptr = 0x0}
#7  0x0000fffff786a394 in start_thread () from /gnu/store/a19xbynxc3sg25xpkwmx7g0mdl7g31hx-glibc-2.35/lib/libc.so.6
No symbol table info available.
#8  0x0000fffff78cefdc in thread_start () from /gnu/store/a19xbynxc3sg25xpkwmx7g0mdl7g31hx-glibc-2.35/lib/libc.so.6
No symbol table info available.

Thread 3 (Thread 0xfffff77ef080 (LWP 102558)):
#0  0x0000fffff7e165a8 in ws_pop_task (sched_ctx_id=0) at sched_policies/work_stealing_policy.c:602
        ws = 0x428c30
        task = <optimized out>
        workerid = 0
        victim = <optimized out>
#1  0x0000fffff7e04f88 in _starpu_pop_task (worker=worker@entry=0xfffff7f031f0 <_starpu_config+7488>) at core/sched_policy.c:1020
        sched_ctx = 0xfffff7fa1600 <_starpu_config+655696>
        task = 0x0
        worker_id = <optimized out>
        node = <optimized out>
        profiling = 0
        pop_start_time = {tv_sec = 281474841457424, tv_nsec = 0}
        pick = <optimized out>
        i = <optimized out>
        nbuffers = <optimized out>
#2  0x0000fffff7e2ab30 in _starpu_get_worker_task (worker=worker@entry=0xfffff7f031f0 <_starpu_config+7488>, workerid=workerid@entry=0, memnode=memnode@entry=0) at drivers/driver_common/driver_common.c:431
        task = <optimized out>
        keep_awake = <optimized out>
        __func__ = "_starpu_get_worker_task"
#3  0x0000fffff7e8a1bc in _starpu_cpu_driver_run_once (cpu_worker=cpu_worker@entry=0xfffff7f031f0 <_starpu_config+7488>) at drivers/cpu/driver_cpu.c:608
        memnode = 0
        workerid = 0
        pi = {conf = 0x0, event_type = starpu_prof_tool_event_driver_init_end, starpu_version = {1, 4152288992, 65535}, thread_id = -135748100, worker_id = 65535, device_number = -135253520, driver_type = 65535, memnode = 4160361648, bytes_to_transfer = 65535, bytes_transfered = 0, fun_ptr = 0x0}
        res = <optimized out>
        j = <optimized out>
        task = 0x0
        pending_task = 0x0
        rank = 0
        __func__ = "_starpu_cpu_driver_run_once"
        continuation_wake_up = <optimized out>
        __PRETTY_FUNCTION__ = "_starpu_cpu_driver_run_once"
#4  0x0000fffff7e8a604 in _starpu_cpu_worker (arg=0xfffff7f031f0 <_starpu_config+7488>) at drivers/cpu/driver_cpu.c:714
        worker = 0xfffff7f031f0 <_starpu_config+7488>
        pi = {conf = 0x0, event_type = starpu_prof_tool_event_start_transfer, starpu_version = {1, 4, 4}, thread_id = -142675840, worker_id = 0, device_number = 0, driver_type = starpu_prof_tool_driver_cpu, memnode = 0, bytes_to_transfer = 0, bytes_transfered = 0, fun_ptr = 0x0}
#5  0x0000fffff786a394 in start_thread () from /gnu/store/a19xbynxc3sg25xpkwmx7g0mdl7g31hx-glibc-2.35/lib/libc.so.6
No symbol table info available.
#6  0x0000fffff78cefdc in thread_start () from /gnu/store/a19xbynxc3sg25xpkwmx7g0mdl7g31hx-glibc-2.35/lib/libc.so.6
No symbol table info available.

Thread 2 (Thread 0xfffff67cf080 (LWP 102560)):
#0  _starpu_machine_is_running () at ./core/workers.h:588
        ret = <optimized out>
        ret = <optimized out>
#1  _starpu_get_worker_task (worker=worker@entry=0xfffff7f04800 <_starpu_config+13136>, workerid=workerid@entry=2, memnode=memnode@entry=0) at drivers/driver_common/driver_common.c:506
        task = <optimized out>
        keep_awake = <optimized out>
        __func__ = "_starpu_get_worker_task"
#2  0x0000fffff7e8a1bc in _starpu_cpu_driver_run_once (cpu_worker=cpu_worker@entry=0xfffff7f04800 <_starpu_config+13136>) at drivers/cpu/driver_cpu.c:608
        memnode = 0
        workerid = 2
        pi = {conf = 0x0, event_type = starpu_prof_tool_event_driver_init_end, starpu_version = {1, 4135380704, 65535}, thread_id = -135748100, worker_id = 65535, device_number = -135247872, driver_type = 65535, memnode = 4160361648, bytes_to_transfer = 65535, bytes_transfered = 0, fun_ptr = 0x0}
        res = <optimized out>
        j = <optimized out>
        task = 0x0
        pending_task = 0x0
        rank = 0
        __func__ = "_starpu_cpu_driver_run_once"
        continuation_wake_up = <optimized out>
        __PRETTY_FUNCTION__ = "_starpu_cpu_driver_run_once"
#3  0x0000fffff7e8a604 in _starpu_cpu_worker (arg=0xfffff7f04800 <_starpu_config+13136>) at drivers/cpu/driver_cpu.c:714
        worker = 0xfffff7f04800 <_starpu_config+13136>
        pi = {conf = 0x0, event_type = starpu_prof_tool_event_start_transfer, starpu_version = {1, 4, 4}, thread_id = -159584128, worker_id = 2, device_number = 2, driver_type = starpu_prof_tool_driver_cpu, memnode = 0, bytes_to_transfer = 0, bytes_transfered = 0, fun_ptr = 0x0}
#4  0x0000fffff786a394 in start_thread () from /gnu/store/a19xbynxc3sg25xpkwmx7g0mdl7g31hx-glibc-2.35/lib/libc.so.6
No symbol table info available.
#5  0x0000fffff78cefdc in thread_start () from /gnu/store/a19xbynxc3sg25xpkwmx7g0mdl7g31hx-glibc-2.35/lib/libc.so.6
No symbol table info available.

Thread 1 (Thread 0xfffff7ff1020 (LWP 102544)):
#0  starpu_sched_ctx_create (workerids=0x0, nworkers=1, sched_ctx_name=sched_ctx_name@entry=0xfffff7ec0b48 "parallel_workers") at core/sched_ctx.c:793
        __func__ = "starpu_sched_ctx_create"
        varg_list = {__stack = 0xfffffffebbd0, __gr_top = 0xfffffffebbd0, __vr_top = 0xfffffffebba0, __gr_offs = -32, __vr_offs = 0}
        arg_type = -135262208
        min_prio_set = 0
        max_prio_set = 0
        min_prio = 0
        max_prio = 0
        nsms = 0
        sub_ctxs = 0x0
        nsub_ctxs = 0
        user_data = 0x0
        sched_policy = 0x0
        hierarchy_level = 0
        nesting_sched_ctx = 10
        awake_workers = 0
        init_sched = 0x0
        num_workers = 4
        i = 0
        sched_ctx = <optimized out>
        added_workerids = 0x42e070
        nw_ctx = <optimized out>
        p_ret = <optimized out>
        __ptrs = <optimized out>
        __n = <optimized out>
#1  0x0000fffff7e8c214 in _starpu_parallel_worker_create (parallel_worker=parallel_worker@entry=0x42c3b0) at parallel_worker/starpu_parallel_worker_create.c:333
        config = <optimized out>
#2  0x0000fffff7e8c3f4 in _starpu_parallel_worker_group_create (group=group@entry=0x42c2f0) at parallel_worker/starpu_parallel_worker_create.c:350
        c = 0x42c3b0
#3  0x0000fffff7e8d590 in _starpu_parallel_worker_config (parallel_worker_level=<optimized out>, machine=0x42c270) at parallel_worker/starpu_parallel_worker_create.c:553
        g = 0x42c2f0
        ret = 0
        config = <optimized out>
        sched_policy = <optimized out>
        global_ctx = <optimized out>
#4  0x0000fffff7e8d7ec in _starpu_parallel_worker_init_varg (parallel_worker_level=parallel_worker_level@entry=HWLOC_OBJ_PACKAGE, varg_list=...) at parallel_worker/starpu_parallel_worker_create.c:241
        arg_type = 0
        machine = 0x42c270
        __func__ = "_starpu_parallel_worker_init_varg"
        __PRETTY_FUNCTION__ = "_starpu_parallel_worker_init_varg"
#5  0x0000fffff7e8e058 in starpu_parallel_worker_init (parallel_worker_level=parallel_worker_level@entry=HWLOC_OBJ_PACKAGE) at parallel_worker/starpu_parallel_worker_create.c:255
        config = <optimized out>
        varg_list = {__stack = 0xfffffffebea0, __gr_top = 0xfffffffebea0, __vr_top = 0xfffffffebe60, __gr_offs = -56, __vr_offs = -128}
#6  0x0000000000400ff8 in main () at parallel_workers/parallel_workers.c:79
        ntasks = 8
        ret = 0
        i = <optimized out>
        parallel_workers = <optimized out>
        __PRETTY_FUNCTION__ = <optimized out>
        __func__ = "main"
        array1 = {0 <repeats 4000 times>}
        array2 = {0 <repeats 3000 times>, 1.3906711614409153e-309, 1.3906704974653626e-309, 1.3906711614411525e-309, 1.3906704983826054e-309, 0, 0, 1.3906711614613894e-309, 1.3906704975785234e-309, 1.3906704984230793e-309, 1.3906704983826054e-309, 1.3906704984275061e-309, 0, 1.0239368235597433e+200, 5.0130396337438505e-90, 8.3365299802249716e-72, 3.6195066075658384e+262, 1.1146009660511128e+171, 2.2120874227700783e+214, 1.1746884519525608e+214, 3.7879995910192795e+209, 1.1711897052348906e+166, 1.9108618774865702e+214, 3.5591190367735002e+180, 1.46016160971922e-319, 0 <repeats 377 times>, 7.7305068220971491e-318, 7.7112580245351742e-318, 7.7112580245351742e-318, 3.2379086165851934e-319, 0, 2.4703282292062327e-323, 8.034060754902011e-318, 8.1554823280239558e-318, 8.1439409545371042e-318, 8.3982464237645107e-318, 3.2379086165851934e-319, 7.7102698932434917e-318, 1.4821969375237396e-323, 0 <repeats 15 times>, 1.2142157312194475e-318, 1.2024767314742595e-318, 1.2024767314742595e-318, 0, 4.0473857707314917e-319, 3.860826582861837e-319, 3.860826582861837e-319, 1.3906711614580693e-309, 1.390670497321886e-309, 1.3906711614586226e-309, 1.3906704983969926e-309, 1.3906711614593341e-309, 1.3906704973289412e-309, 1.3906711614586226e-309, 4.9406564584124654e-323, 1.3906711614584645e-309, 1.3906704974401455e-309, 1.3906704982485357e-309, 2.3221085354538588e-322, 1.3906711614593341e-309, 1.3906704973293563e-309, 1.390671161459255e-309, 1.3906704973530912e-309, 1.390671161459255e-309, 1.3906704973666879e-309, 0, 0, 2.0733533996918329e-317, 1.3906711614622194e-309, 1.390671161459255e-309, 1.3906704973663124e-309, 1.3906704566746112e-309, 1.3906704983969926e-309, 0, 1.3906704982545041e-309, 1.3906704650931736e-309, 1.3906704983969926e-309, 0, 1.3906704982475476e-309, 1.3906704660645462e-309, 1.3906704983969926e-309, 1.3906711614611522e-309, 1.3906704973779723e-309, 2.0733533996918329e-317, 0, 1.3906704984275061e-309, 0, 4.9406564584124654e-324, 1.3906711614622194e-309, 1.3906704984028423e-309, 1.3906704983826054e-309, 0, 1.390670497266353e-309, 1.3906704983623685e-309, 1.3906711614622589e-309, 1.3906704650725415e-309, 1.3906711614622589e-309, 1.3906704650725415e-309, 9.8813129168249309e-324, 1.3906711614622589e-309, 1.3906711614590179e-309, 9.8813129168249309e-324, 0, 1.4821969375237396e-323, 1.3906704984253717e-309, 1.3906711614625751e-309, 0, 1.3906704984028423e-309, 2.9643938750474793e-323, 3.2127112686472898e-319, 5.2917543283166305e-318, 3.2127112686472898e-319, 5.2917543283166305e-318, 4.2440079518075883e-314, 0, 0, 0, 9.7773615049399326e-318, 2.0236928853657458e-320, 1.3906711614609941e-309, 1.3906704973765889e-309, 1.3906704572715759e-309, 0, 0, 8.4617375499254853e-315, 1.3906711614662115e-309, 1.3906704972666494e-309, 1.390671161470994e-309, 1.3906704984230793e-309, 1.390670464783849e-309, 1.3906704984275061e-309, 1.3906704982485357e-309, 4.9406564584124654e-324, 0, 1.3906711614712707e-309, 0, 1.390670497266353e-309, 0, 0, 0, 1.390670497266353e-309, 0, 1.3906704984324467e-309, 0, 0, 0, 4.9406564584124654e-323, 0, 0, 0, 6.9169190417774516e-323, 0, 0, 1.3906704982481405e-309, 1.3906711614820216e-309, 0, 4.1106261733991712e-321, 3.3280039514459023e-294, 0, 2.1279211652158202e-314, 7.9595951807608183e-319, 3.1620201333839779e-322, 9.7564921720595984e-318, 1.3350986381965695e-307, 1.8914248227666973e-307, 8.4879831668254831e-314, 3.1620201333839779e-322, 3.1620201333839779e-322, 3.1620201333839779e-322, 2.7667676167109806e-321, 2.7667676167109806e-321, 3.9525251667299724e-323, 8.4879831653432862e-314...}
        handle1 = 0x0
        handle2 = 0x0
        size = 0
        out = <optimized out>

Thread 5 (Thread 0xfffff5fbf080 (LWP 102561)):
Undefined command: "py-bt".  Try "help".
#Execution_time_in_seconds 0.286683 ./parallel_workers/parallel_workers
FAIL parallel_workers/parallel_workers (exit status: 1)

Distribution

Debian 12 ARM

Version of StarPU

Release 1.4.4 of StarPU available with Guix

sthibaul commented 4 months ago

Indeed, the test is looking for sockets, which macos doesn't expose to hwloc. I have added the error handling in https://gitlab.inria.fr/starpu/starpu/-/commit/b2b4f414ab9f916d3fa57328617fefc8a94d4a77 , that should be "fixing" the test by making it skip