<div dir="ltr">Thanks Jason</div><div class="gmail_extra"><br><div class="gmail_quote">On Wed, Jan 27, 2016 at 4:48 PM, Jason Evans <span dir="ltr"><<a href="mailto:jasone@canonware.com" target="_blank">jasone@canonware.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div class="HOEnZb"><div class="h5">On Jan 26, 2016, at 8:08 PM, Roel Van de Paar <<a href="mailto:roel.vandepaar@percona.com">roel.vandepaar@percona.com</a>> wrote:<br>
> Crashing mysqld:<br>
><br>
> +bt<br>
> #0  0x00007f01cabf5741 in __pthread_kill (threadid=<optimized out>, signo=11) at ../nptl/sysdeps/unix/sysv/linux/pthread_kill.c:61<br>
> #1  0x0000000000793555 in handle_fatal_signal (sig=11) at /git/PS-5.7_opt/sql/signal_handler.cc:223<br>
> #2  <signal handler called><br>
> #3  je_bitmap_set (bit=18446744073709551615, binfo=0x7f01cb037a28 <je_arena_bin_info+456>, bitmap=0x7f016b423010) at include/jemalloc/internal/bitmap.h:105<br>
> #4  je_bitmap_sfu (binfo=0x7f01cb037a28 <je_arena_bin_info+456>, bitmap=0x7f016b423010) at include/jemalloc/internal/bitmap.h:140<br>
> #5  arena_run_reg_alloc (bin_info=0x7f01cb037a00 <je_arena_bin_info+416>, run=0x7f016b423000) at src/arena.c:291<br>
> #6  je_arena_tcache_fill_small (arena=0x7f01c721f1c0, tbin=tbin@entry=0x7f016b4060a8, binind=binind@entry=4, prof_accumbytes=prof_accumbytes@entry=0) at src/arena.c:1479<br>
> #7  0x00007f01cae2b6ff in je_tcache_alloc_small_hard (tcache=tcache@entry=0x7f016b406000, tbin=tbin@entry=0x7f016b4060a8, binind=binind@entry=4) at src/tcache.c:72<br>
> #8  0x00007f01cae0b14f in je_tcache_alloc_small (zero=false, size=64, tcache=0x7f016b406000) at include/jemalloc/internal/tcache.h:303<br>
> #9  je_arena_malloc (try_tcache=true, zero=false, size=<optimized out>, arena=0x0) at include/jemalloc/internal/arena.h:957<br>
> #10 je_imalloct (arena=0x0, try_tcache=true, size=<optimized out>) at include/jemalloc/internal/jemalloc_internal.h:771<br>
> #11 je_imalloc (size=<optimized out>) at include/jemalloc/internal/jemalloc_internal.h:780<br>
> #12 malloc (size=<optimized out>) at src/jemalloc.c:929<br>
> #13 0x00000000011ce169 in ut_allocator<unsigned char>::allocate (this=this@entry=0x7f01977f7930, n_elements=32, file=file@entry=0x159f298 "/git/PS-5.7_opt/storage/innobase/fil/fil0fil.cc", throw_on_error=false, set_to_zero=false, hint=0x0) at /git/PS-5.7_opt/storage/innobase/include/ut0new.h:349<br>
> #14 0x00000000011d9e2d in fil_flush_file_spaces (purpose=purpose@entry=FIL_TYPE_TABLESPACE) at /git/PS-5.7_opt/storage/innobase/fil/fil0fil.cc:5946<br>
> #15 0x00000000011685d9 in buf_dblwr_update (bpage=bpage@entry=0x7f019cd07740, flush_type=flush_type@entry=BUF_FLUSH_LIST) at /git/PS-5.7_opt/storage/innobase/buf/buf0dblwr.cc:750<br>
> #16 0x0000000001177506 in buf_flush_write_complete (bpage=bpage@entry=0x7f019cd07740) at /git/PS-5.7_opt/storage/innobase/buf/buf0flu.cc:809<br>
> #17 0x000000000115f511 in buf_page_io_complete (bpage=0x7f019cd07740, evict=evict@entry=false) at /git/PS-5.7_opt/storage/innobase/buf/buf0buf.cc:6030<br>
> #18 0x00000000011d24af in fil_aio_wait (segment=segment@entry=7) at /git/PS-5.7_opt/storage/innobase/fil/fil0fil.cc:5754<br>
> #19 0x00000000010c07b0 in io_handler_thread (arg=<optimized out>) at /git/PS-5.7_opt/storage/innobase/srv/srv0start.cc:330<br>
> #20 0x00007f01cabf0dc5 in start_thread (arg=0x7f01977f8700) at pthread_create.c:308<br>
> #21 0x00007f01c904f21d in clone () at ../sysdeps/unix/sysv/linux/x86_64/clone.S:113<br>
><br>
> This looks highly like to be jemalloc bug - agreed?<br>
><br>
> Can I provide any other info to report this? Is this list notification sufficient?<br>
<br>
</div></div>No, this is more likely to be an application bug than a jemalloc bug.  The application probably corrupted jemalloc data structures, e.g. by freeing the same object twice.  If you do determine that it's a jemalloc bug, please provide full reproduction steps or a diagnosis/patch so we can get the problem fixed.<br>
<br>
Thanks,<br>
Jason</blockquote></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature"><div dir="ltr"><div><div dir="ltr"><br><font face="arial,helvetica,sans-serif">Kind Regards,<br>God Bless,<br>-- <br>Roel Van de Paar, </font><font face="arial,helvetica,sans-serif">CMDBA/CMDEV Senior QA Lead, </font>Percona<div><font face="arial,helvetica,sans-serif">Tel: +61 2 8004 1288 (UTC+10)<br>Mob: +61 427 141 635 (UTC+10)<br>Skype: percona.rvandepaar<br></font><font face="arial,helvetica,sans-serif"><a href="http://www.percona.com/services.html" target="_blank">http://www.percona.com/services.html</a></font><br></div><div><br></div><div><div>Looking for Replication with Data Consistency?</div><div>Try <a href="http://www.percona.com/software/percona-xtradb-cluster" target="_blank">Percona XtraDB Cluster</a>!</div></div></div></div></div></div>
</div>