OK, I have figured out that this was happening due to double free. Sorry for the false alarm and 3 emails.
On Thu, Jan 1, 2015 at 1:47 PM, Marcin Zalewski <marcin.zalew...@gmail.com> wrote: > I just got a stack trace on this assertion fail (below), and it seem that > second assertion is triggered in error processing. > > #0 0x00007fffbf9ff3f8 in pthread_once () from > /lib/x86_64-linux-gnu/libpthread.so.0 > #1 0x00007fffbf73e074 in backtrace () from /lib/x86_64-linux-gnu/libc.so.6 > #2 0x00007fff7a99b0f0 in ipath_sighdlr (sig=<optimized out>, > p1=<optimized out>, ucv=0x7fff78558380) at ipath_debug.c:116 > #3 <signal handler called> > #4 0x00007fffbf6690d5 in raise () from /lib/x86_64-linux-gnu/libc.so.6 > #5 0x00007fffbf66c83b in abort () from /lib/x86_64-linux-gnu/libc.so.6 > #6 0x00007fffbfc4d9ec in je_tcache_event (tcache=0x7fffbe81a000) at > include/jemalloc/internal/tcache.h:212 > #7 0x00007fffbfc4dd03 in je_tcache_alloc_small (tcache=0x7fffbe81a000, > size=36, zero=false) at include/jemalloc/internal/tcache.h:273 > #8 0x00007fffbfc1c7ad in je_arena_malloc (tsd=0x7fffc17e5708, arena=0x0, > size=36, zero=false, try_tcache=true) at > include/jemalloc/internal/arena.h:931 > #9 0x00007fffbfc1378c in je_imalloct (tsd=0x7fffc17e5708, size=36, > try_tcache=true, arena=0x0) at > include/jemalloc/internal/jemalloc_internal.h:816 > #10 0x00007fffbfc137da in je_imalloc (tsd=0x7fffc17e5708, size=36) at > include/jemalloc/internal/jemalloc_internal.h:825 > #11 0x00007fffbfc172a8 in imalloc_body (size=36, tsd=0x7fff78558bc0, > usize=0x7fff78558bb8) at src/jemalloc.c:1331 > #12 0x00007fffbfc172e4 in malloc (size=36) at src/jemalloc.c:1344 > #13 0x00007fffc15e294e in ?? () from /lib64/ld-linux-x86-64.so.2 > #14 0x00007fffc15ed84b in ?? () from /lib64/ld-linux-x86-64.so.2 > #15 0x00007fffc15e9176 in ?? () from /lib64/ld-linux-x86-64.so.2 > #16 0x00007fffc15ed31a in ?? () from /lib64/ld-linux-x86-64.so.2 > #17 0x00007fffbf763c62 in ?? () from /lib/x86_64-linux-gnu/libc.so.6 > #18 0x00007fffc15e9176 in ?? () from /lib64/ld-linux-x86-64.so.2 > #19 0x00007fffbf763d24 in __libc_dlopen_mode () from > /lib/x86_64-linux-gnu/libc.so.6 > #20 0x00007fffbf73df55 in ?? () from /lib/x86_64-linux-gnu/libc.so.6 > #21 0x00007fffbf9ff400 in pthread_once () from > /lib/x86_64-linux-gnu/libpthread.so.0 > #22 0x00007fffbf73e074 in backtrace () from /lib/x86_64-linux-gnu/libc.so.6 > #23 0x00007fff7a99b0f0 in ipath_sighdlr (sig=<optimized out>, > p1=<optimized out>, ucv=0x7fff785594c0) at ipath_debug.c:116 > #24 <signal handler called> > #25 0x00007fffbf6690d5 in raise () from /lib/x86_64-linux-gnu/libc.so.6 > #26 0x00007fffbf66c83b in abort () from /lib/x86_64-linux-gnu/libc.so.6 > #27 0x00007fffbfc21acf in arena_run_reg_dalloc (run=0x7fffbe8039e8, > ptr=0x7fffbe8644d0) at src/arena.c:182 > #28 0x00007fffbfc2711f in arena_dalloc_bin_locked_impl > (arena=0x7fffbf010140, chunk=0x7fffbe800000, ptr=0x7fffbe8644d0, > bitselm=0x7fffbe800258, junked=true) at src/arena.c:1854 > #29 0x00007fffbfc27209 in je_arena_dalloc_bin_junked_locked > (arena=0x7fffbf010140, chunk=0x7fffbe800000, ptr=0x7fffbe8644d0, > bitselm=0x7fffbe800258) at src/arena.c:1872 > #30 0x00007fffbfc4e842 in je_tcache_bin_flush_small (tbin=0x7fffbe81a0c8, > binind=5, rem=0, tcache=0x7fffbe81a000) at src/tcache.c:120 > #31 0x00007fffbfc4e40c in je_tcache_event_hard (tcache=0x7fffbe81a000) at > src/tcache.c:36 > #32 0x00007fffbfc4da0f in je_tcache_event (tcache=0x7fffbe81a000) at > include/jemalloc/internal/tcache.h:214 > #33 0x00007fffbfc4dd03 in je_tcache_alloc_small (tcache=0x7fffbe81a000, > size=24, zero=false) at include/jemalloc/internal/tcache.h:273 > #34 0x00007fffbfc1c7ad in je_arena_malloc (tsd=0x7fffc17e5708, arena=0x0, > size=24, zero=false, try_tcache=true) at > include/jemalloc/internal/arena.h:931 > #35 0x00007fffbfc1378c in je_imalloct (tsd=0x7fffc17e5708, size=24, > try_tcache=true, arena=0x0) at > include/jemalloc/internal/jemalloc_internal.h:816 > #36 0x00007fffbfc137da in je_imalloc (tsd=0x7fffc17e5708, size=24) at > include/jemalloc/internal/jemalloc_internal.h:825 > #37 0x00007fffbfc172a8 in imalloc_body (size=24, tsd=0x7fff78559ef0, > usize=0x7fff78559ee8) at src/jemalloc.c:1331 > #38 0x00007fffbfc172e4 in malloc (size=24) at src/jemalloc.c:1344 > #39 0x00000000004082be in sssp_queue_push (q=0x7fffbe865420, > v=140729942941792, d=5032) at ./include/libpxgl/unlocked_pqueue_wrapper.h:75 > #40 0x0000000000408511 in _sssp_dc_process_vertex_action > (distance=0x7ffc848478c0) at src/sssp_dc1.c:74 > #41 0x000000000042d751 in _thread_enter (parcel=0x7ffc84847880) at > worker.c:95 > #42 0x0000000000000000 in ?? () > > On Thu, Jan 1, 2015 at 1:44 PM, Marcin Zalewski <marcin.zalew...@gmail.com > > wrote: > >> I am using the latest jemalloc dev (9c6a8d) compiled only with >> --enable-debug. I am getting the following two assertions fail in my >> program (16 threads): >> >> src/arena.c:182: Failed assertion: "bitmap_get(run->bitmap, >> &bin_info->bitmap_info, regind)" >> include/jemalloc/internal/tcache.h:212: Failed assertion: "tcache->ev_cnt >> <= TCACHE_GC_INCR" >> >> Is there something obvious that I am doing wrong? I would appreciate any >> help. >> >> Thank you, >> Marcin >> > >
_______________________________________________ jemalloc-discuss mailing list jemalloc-discuss@canonware.com http://www.canonware.com/mailman/listinfo/jemalloc-discuss
