Whilst running VPP on multiple cores, the entire process hangs with a backtrace
a little something like this:
(gdb) backtrace -full
#0 internal_mallinfo (m=0x7fffadf18040) at
/home/vpp/vpp/src/vppinfra/dlmalloc.c:2099
q = 0x7fffadf185e0
nfree = 2
mfree = 31846400
sum = 31847744
s = 0x7fffadf183b8
nm = {arena = 0, ordblks = 0, smblks = 0, hblks = 0, hblkhd = 0, usmblks = 0,
fsmblks = 0, uordblks = 0, fordblks = 0, keepcost = 0}
#1 0x00007ffff6d155fb in mspace_mallinfo (msp=0x7fffadf18040) at
/home/vpp/vpp/src/vppinfra/dlmalloc.c:4803
ms = 0x7fffadf18040
#2 0x00007ffff6d551f1 in clib_mem_get_heap_usage (heap=0x7fffadf18000,
usage=0x7fffadb44e80) at /home/vpp/vpp/src/vppinfra/mem_dlmalloc.c:475
mi = {arena = 0, ordblks = 0, smblks = 0, hblks = 0, hblkhd = 0, usmblks = 0,
fsmblks = 0, uordblks = 0, fordblks = 0, keepcost = 0}
#3 0x00007ffff6ed5731 in stat_provider_mem_usage_update_fn (d=0x7fffadb44f10)
at /home/vpp/vpp/src/vlib/stats/provider_mem.c:34
usage = {object_count = 3171228624, bytes_total = 0, bytes_used =
140736107663024, bytes_free = 0, bytes_overhead = 0, bytes_free_reclaimed = 0,
bytes_used_sbrk = 140736107663056, bytes_used_mmap = 140737336117493, bytes_max
= 140736364616624}
heap = 0x7fffadf18000
counters = 0x7fffadf18440
cb = 0x7ffff6ed0d18 <vec_header+40>
#4 0x00007ffff6ecf8c9 in do_stat_segment_updates (vm=0x7fffb68b7740,
sm=0x7ffff6f6e5a8 <vlib_stats_main>) at
/home/vpp/vpp/src/vlib/stats/collector.c:167
data = {entry_index = 7, vector_index = 0, private_data = 0, entry =
0x7fffae00df30}
c = 0x7fffbd051bd0
#5 0x00007ffff6ecf79a in stat_segment_collector_process (vm=0x7fffb68b7740,
rt=0x7fffb7140440, f=0x0) at /home/vpp/vpp/src/vlib/stats/collector.c:182
sm = 0x7ffff6f6e5a8 <vlib_stats_main>
#6 0x00007ffff6ea426d in vlib_process_bootstrap (_a=140736147323080) at
/home/vpp/vpp/src/vlib/main.c:1220
a = 0x7fffb01178c8
vm = 0x7fffb68b7740
node = 0x7fffb7140440
f = 0x0
p = 0x7fffb7140440
n = 0
#7 0x00007ffff6d4be78 in clib_calljmp () at
/home/vpp/vpp/src/vppinfra/longjmp.S:123
No locals.
#8 0x00007fffb01178c0 in ?? ()
No symbol table info available.
#9 0x00007ffff6ea3b3f in vlib_process_startup (vm=0x2a800000001,
p=0x7099405b988, f=0xbd055100) at /home/vpp/vpp/src/vlib/main.c:1245
a = {vm = 0x4268a0 <__libc_csu_init>, process = 0x7ffff7fc6f50, frame =
0x7fffbd017800}
r = 140736147323184
#10 0x0000002ff7f757c3 in ?? ()
No symbol table info available.
#11 0x000000000000002e in ?? ()
No symbol table info available.
#12 0x00000032b68b7c38 in ?? ()
No symbol table info available.
#13 0x0000000000000031 in ?? ()
No symbol table info available.
#14 0x00007ffff7f73b4b in memclnt_queue_callback (vm=<error reading variable:
Cannot access memory at address 0xfffffffffffffff8>) at
/home/vpp/vpp/src/vlibmemory/memory_api.c:90
i = <error reading variable i (Cannot access memory at address
0xfffffffffffffff4)>
am = <error reading variable am (Cannot access memory at address
0xffffffffffffffe8)>
have_pending_rpcs = <error reading variable have_pending_rpcs (Cannot access
memory at address 0xffffffffffffffe4)>
Looks like a memory underflow to my novice eyes - struggling to diagnose it
though! Does anyone have any thoughts on this?
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.
View/Reply Online (#21091): https://lists.fd.io/g/vpp-dev/message/21091
Mute This Topic: https://lists.fd.io/mt/89947053/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-
