bug#25029: shuf generates “Bad file descriptor” error on nfs but only when run as a background process

[Alex Ryan]

fyi ...
here is the output of strace when the Bad file descriptor error is
generated ...

$nohup ./run_shuffle.sh > /tmp/run_shuffle.log 2>&1 0>&- &

execve("/usr/bin/shuf", ["shuf", "/nfs/digits/datasets/com-aosvapp"...],
[/* 54 vars */]) = 0

brk(0)                                  = 0x10dc000

access("/etc/ld.so.nohwcap", F_OK)      = -1 ENOENT (No such file or
directory)

mmap(NULL, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) =
0x7f9af2d5a000

access("/etc/ld.so.preload", R_OK)      = -1 ENOENT (No such file or
directory)

open("tls/x86_64/libc.so.6", O_RDONLY|O_CLOEXEC) = -1 ENOENT (No such file
or directory)

open("tls/libc.so.6", O_RDONLY|O_CLOEXEC) = -1 ENOENT (No such file or
directory)

open("x86_64/libc.so.6", O_RDONLY|O_CLOEXEC) = -1 ENOENT (No such file or
directory)

open("libc.so.6", O_RDONLY|O_CLOEXEC)   = -1 ENOENT (No such file or
directory)

open("/usr/local/cuda-7.5/lib64/tls/x86_64/libc.so.6", O_RDONLY|O_CLOEXEC)
= -1 ENOENT (No such file or directory)

stat("/usr/local/cuda-7.5/lib64/tls/x86_64", 0x7ffcc850b6c0) = -1 ENOENT
(No such file or directory)

open("/usr/local/cuda-7.5/lib64/tls/libc.so.6", O_RDONLY|O_CLOEXEC) = -1
ENOENT (No such file or directory)

stat("/usr/local/cuda-7.5/lib64/tls", 0x7ffcc850b6c0) = -1 ENOENT (No such
file or directory)

open("/usr/local/cuda-7.5/lib64/x86_64/libc.so.6", O_RDONLY|O_CLOEXEC) = -1
ENOENT (No such file or directory)

stat("/usr/local/cuda-7.5/lib64/x86_64", 0x7ffcc850b6c0) = -1 ENOENT (No
such file or directory)

open("/usr/local/cuda-7.5/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = -1 ENOENT
(No such file or directory)

stat("/usr/local/cuda-7.5/lib64", {st_mode=S_IFDIR|0755, st_size=4096,
...}) = 0

open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 0

fstat(0, {st_mode=S_IFREG|0644, st_size=78541, ...}) = 0

mmap(NULL, 78541, PROT_READ, MAP_PRIVATE, 0, 0) = 0x7f9af2d46000

close(0)                                = 0

access("/etc/ld.so.nohwcap", F_OK)      = -1 ENOENT (No such file or
directory)

open("/lib/x86_64-linux-gnu/libc.so.6", O_RDONLY|O_CLOEXEC) = 0

read(0, "\177ELF\2\1\1\0\0\0\0\0\0\0\0\0\3\0>\0\1\0\0\0P \2\0\0\0\0\0"...,
832) = 832

fstat(0, {st_mode=S_IFREG|0755, st_size=1840928, ...}) = 0

mmap(NULL, 3949248, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 0, 0) =
0x7f9af2775000

mprotect(0x7f9af292f000, 2097152, PROT_NONE) = 0

mmap(0x7f9af2b2f000, 24576, PROT_READ|PROT_WRITE,
MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 0, 0x1ba000) = 0x7f9af2b2f000

mmap(0x7f9af2b35000, 17088, PROT_READ|PROT_WRITE,
MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) = 0x7f9af2b35000

close(0)                                = 0

mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) =
0x7f9af2d45000

mmap(NULL, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) =
0x7f9af2d43000

arch_prctl(ARCH_SET_FS, 0x7f9af2d43740) = 0

mprotect(0x7f9af2b2f000, 16384, PROT_READ) = 0

mprotect(0x60a000, 4096, PROT_READ)     = 0

mprotect(0x7f9af2d5c000, 4096, PROT_READ) = 0

munmap(0x7f9af2d46000, 78541)           = 0

brk(0)                                  = 0x10dc000

brk(0x10fd000)                          = 0x10fd000

open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 0

fstat(0, {st_mode=S_IFREG|0644, st_size=1607664, ...}) = 0

mmap(NULL, 1607664, PROT_READ, MAP_PRIVATE, 0, 0) = 0x7f9af2bba000

close(0)                                = 0

open("/nfs/digits/datasets/com-aosvapps-distracted-driving3/databases/TrainImagePathsAndLabels_AlpineTest1.csv",
O_RDONLY) = 0

dup3(0, 0, 0)                           = -1 EINVAL (Invalid argument)

dup2(0, 0)                              = 0

close(0)                                = 0

fadvise64(0, 0, 0, POSIX_FADV_SEQUENTIAL) = -1 EBADF (Bad file descriptor)

fstat(0, 0x7ffcc850be10)                = -1 EBADF (Bad file descriptor)

fstat(0, 0x7ffcc850bcd0)                = -1 EBADF (Bad file descriptor)

mmap(NULL, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) =
0x7f9af2d58000

read(0, 0x10dd030, 8192)                = -1 EBADF (Bad file descriptor)

open("/usr/share/locale/locale.alias", O_RDONLY|O_CLOEXEC) = 0

fstat(0, {st_mode=S_IFREG|0644, st_size=2570, ...}) = 0

mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) =
0x7f9af2d57000

read(0, "# Locale name alias data base.\n#"..., 4096) = 2570

read(0, "", 4096)                       = 0

close(0)                                = 0

munmap(0x7f9af2d57000, 4096)            = 0

open("/usr/share/locale/en_US.UTF-8/LC_MESSAGES/coreutils.mo", O_RDONLY) =
-1 ENOENT (No such file or directory)

open("/usr/share/locale/en_US.utf8/LC_MESSAGES/coreutils.mo", O_RDONLY) =
-1 ENOENT (No such file or directory)

open("/usr/share/locale/en_US/LC_MESSAGES/coreutils.mo", O_RDONLY) = -1
ENOENT (No such file or directory)

open("/usr/share/locale/en.UTF-8/LC_MESSAGES/coreutils.mo", O_RDONLY) = -1
ENOENT (No such file or directory)

open("/usr/share/locale/en.utf8/LC_MESSAGES/coreutils.mo", O_RDONLY) = -1
ENOENT (No such file or directory)

open("/usr/share/locale/en/LC_MESSAGES/coreutils.mo", O_RDONLY) = -1 ENOENT
(No such file or directory)

open("/usr/share/locale-langpack/en_US.UTF-8/LC_MESSAGES/coreutils.mo",
O_RDONLY) = -1 ENOENT (No such file or directory)

open("/usr/share/locale-langpack/en_US.utf8/LC_MESSAGES/coreutils.mo",
O_RDONLY) = -1 ENOENT (No such file or directory)

open("/usr/share/locale-langpack/en_US/LC_MESSAGES/coreutils.mo", O_RDONLY)
= -1 ENOENT (No such file or directory)

open("/usr/share/locale-langpack/en.UTF-8/LC_MESSAGES/coreutils.mo",
O_RDONLY) = -1 ENOENT (No such file or directory)

open("/usr/share/locale-langpack/en.utf8/LC_MESSAGES/coreutils.mo",
O_RDONLY) = -1 ENOENT (No such file or directory)

open("/usr/share/locale-langpack/en/LC_MESSAGES/coreutils.mo", O_RDONLY) =
-1 ENOENT (No such file or directory)

write(2, "shuf: ", 6shuf: )                   = 6

write(2, "read error", 10read error)              = 10

open("/usr/share/locale/en_US.UTF-8/LC_MESSAGES/libc.mo", O_RDONLY) = -1
ENOENT (No such file or directory)

open("/usr/share/locale/en_US.utf8/LC_MESSAGES/libc.mo", O_RDONLY) = -1
ENOENT (No such file or directory)

open("/usr/share/locale/en_US/LC_MESSAGES/libc.mo", O_RDONLY) = -1 ENOENT
(No such file or directory)

open("/usr/share/locale/en.UTF-8/LC_MESSAGES/libc.mo", O_RDONLY) = -1
ENOENT (No such file or directory)

open("/usr/share/locale/en.utf8/LC_MESSAGES/libc.mo", O_RDONLY) = -1 ENOENT
(No such file or directory)

open("/usr/share/locale/en/LC_MESSAGES/libc.mo", O_RDONLY) = -1 ENOENT (No
such file or directory)

open("/usr/share/locale-langpack/en_US.UTF-8/LC_MESSAGES/libc.mo",
O_RDONLY) = -1 ENOENT (No such file or directory)

open("/usr/share/locale-langpack/en_US.utf8/LC_MESSAGES/libc.mo", O_RDONLY)
= -1 ENOENT (No such file or directory)

open("/usr/share/locale-langpack/en_US/LC_MESSAGES/libc.mo", O_RDONLY) = -1
ENOENT (No such file or directory)

open("/usr/share/locale-langpack/en.UTF-8/LC_MESSAGES/libc.mo", O_RDONLY) =
-1 ENOENT (No such file or directory)

open("/usr/share/locale-langpack/en.utf8/LC_MESSAGES/libc.mo", O_RDONLY) =
-1 ENOENT (No such file or directory)

open("/usr/share/locale-langpack/en/LC_MESSAGES/libc.mo", O_RDONLY) = -1
ENOENT (No such file or directory)

write(2, ": Bad file descriptor", 21: Bad file descriptor)   = 21

write(2, "\n", 1

)                       = 1

close(1)                                = 0

close(2)                                = 0

exit_group(1)                           = ?
+++ exited with 1 +++



On Fri, Nov 25, 2016 at 3:20 PM, Paul Eggert <address@hidden> wrote:

> I see no real evidence that this is a bug in 'shuf'. It looks like a bug
> in the program that calls 'shuf'. You can verify this by using 'strace
> shuf' instead of plain 'shuf'.
>



-- 
Alex Ryan
https://www.linkedin.com/in/alexryan