Broken pipe @parallel #7927 Closed arnim opened this Issue on Aug 8, 2014 · 3 comments Projects None yet Labels bug I/O parallel regression Milestone No milestone Assignees @JeffBezanson JeffBezanson 2 participants @arnim @JeffBezanson Notifications You’re not receiving notifications from this thread. @arnim arnim commented on Aug 8, 2014 The code addprocs(1) versioninfo() @parallel (+) for i=1:2 ones(10^6) end seems to have very different behavior dependent on the platform. machine 1: julia _ _ _ _(_)_ | A fresh approach to technical computing (_) | (_) (_) | Documentation: http://docs.julialang.org _ _ _| |_ __ _ | Type "help()" to list help topics | | | | | | |/ _` | | | | |_| | | | (_| | | Version 0.3.0-rc1+40 (2014-07-16 04:30 UTC) _/ |\__'_|_|_|\__'_| | |__/ | x86_64-apple-darwin13.2.0 julia> addprocs(1) 1-element Array{Any,1}: 2 julia> versioninfo() Julia Version 0.3.0-rc1+40 Commit d57e5fa* (2014-07-16 04:30 UTC) Platform Info: System: Darwin (x86_64-apple-darwin13.2.0) CPU: Intel(R) Core(TM) i5-3210M CPU @ 2.50GHz WORD_SIZE: 64 BLAS: libopenblas (NO_AFFINITY) LAPACK: libopenblas LIBM: libopenlibm julia> @parallel (+) for i=1:2 ones(10^6) end 1000000-element Array{Float64,1}: 2.0 2.0 2.0 2.0 2.0 2.0 as I would expect. machine 2: julia _ _ _ _(_)_ | A fresh approach to technical computing (_) | (_) (_) | Documentation: http://docs.julialang.org _ _ _| |_ __ _ | Type "help()" for help. | | | | | | |/ _` | | | | |_| | | | (_| | | Version 0.3.0-rc2+65 (2014-08-08 18:04 UTC) _/ |\__'_|_|_|\__'_| | Commit 10117ca (0 days old master) |__/ | x86_64-linux-gnu julia> addprocs(1) 1-element Array{Any,1}: 2 julia> versioninfo() Julia Version 0.3.0-rc2+65 Commit 10117ca (2014-08-08 18:04 UTC) Platform Info: System: Linux (x86_64-linux-gnu) CPU: Intel(R) Xeon(R) CPU E5-2670 0 @ 2.60GHz WORD_SIZE: 64 BLAS: libopenblas (USE64BITINT DYNAMIC_ARCH NO_AFFINITY Sandybridge) LAPACK: libopenblas LIBM: libopenlibm LLVM: libLLVM-3.3 julia> julia> @parallel (+) for i=1:2 ones(10^6) end Worker 2 terminated. signal (13): Broken pipe write at /lib/x86_64-linux-gnu/libpthread.so.0 (unknown line) uv__write at /home/arnim/julia/deps/libuv/src/unix/stream.c:798 uv__stream_io at /home/arnim/julia/deps/libuv/src/unix/stream.c:1224 uv__io_poll at /home/arnim/julia/deps/libuv/src/unix/linux-core.c:237 uv_run at /home/arnim/julia/deps/libuv/src/unix/core.c:295 process_events at ./stream.jl:537 wait at ./task.jl:273 stream_wait at ./stream.jl:263 write at stream.jl:788 send_msg_ at multi.jl:178 jlcall_send_msg_;19727 at (unknown line) jl_apply at /home/arnim/julia/src/gf.c:1429 send_msg_now at multi.jl:137 jl_apply at /home/arnim/julia/src/gf.c:1429 jl_apply at /home/arnim/julia/src/builtins.c:332 send_msg_now at multi.jl:83 jl_apply at /home/arnim/julia/src/gf.c:1429 deliver_result at multi.jl:794 jlcall_deliver_result;19724 at (unknown line) jl_apply at /home/arnim/julia/src/gf.c:1429 anonymous at task.jl:856 start_task at /home/arnim/julia/src/task.c:427 switch_stack at /home/arnim/julia/src/task.c:207 switch_stack at /home/arnim/julia/src/task.c:207 julia_trampoline at /home/arnim/julia/src/init.c:1005 unknown function (ip: 4199789) __libc_start_main at /lib/x86_64-linux-gnu/libc.so.6 (unknown line) unknown function (ip: 4199845) ERROR: ProcessExitedException() in wait at ./task.jl:284 in wait at ./task.jl:194 in wait_full at ./multi.jl:602 in remotecall_fetch at multi.jl:704 in call_on_owner at ./multi.jl:751 in fetch at multi.jl:759 in _mapreduce at reduce.jl:156 in mapreduce at reduce.jl:176 in preduce at multi.jl:1418 (ones(10^6) still works). @JeffBezanson JeffBezanson added I/O bug parallel regression labels on Aug 8, 2014 @JeffBezanson The Julia Language member JeffBezanson commented on Aug 8, 2014 Bisect blames my fc56f24 @JeffBezanson JeffBezanson self-assigned this on Aug 8, 2014 @JeffBezanson JeffBezanson added a commit that closed this issue on Aug 8, 2014 @JeffBezanson fix #7927 a58babf @JeffBezanson JeffBezanson closed this in a58babf on Aug 8, 2014 @JeffBezanson The Julia Language member JeffBezanson commented on Aug 8, 2014 My new use of read! exposed another bug. @arnim arnim commented on Aug 8, 2014 @JeffBezanson THX :+1: