Transient storage killing memory

[Niall Murphy]

Hi all,

Occasionally I encounter the following crash:

Nov 13 19:44:03 vc-varnish-02 kernel: [4029833.862916] apt-get[30000]: segfault at ffffffffffffffff ip 00007f3acce7456a sp 00007fffa93b00a0 error 5 in libapt-pkg.so.4.12.0[7f3acce1d000+168000]
Nov 13 19:45:33 vc-varnish-02 varnishd[12731]: Child (12732) died signal=6
Nov 13 19:45:33 vc-varnish-02 varnishd[12731]: Child (12732) Panic at: Sun, 13 Nov 2016 18:45:32 GMT#012"Assert error in mpl_alloc(), cache/cache_mempool.c line 79:#012  Condition((mi) != 0) not true.#012errno = 12 (Cannot allocate memory)#012thread = (cache-worker)#012version = varnish-5.0.0 revision 99d036f#012ident = Linux,3.16.0-4-amd64,x86_64,-junix,-smalloc,-smalloc,-hcritbit,epoll#012Backtrace:#012#012"

I've included the apt-get segfault in case it's relevant.

SMA.s0.c_bytes                      1598929523     11755.71 Bytes allocated
SMA.s0.c_freed                      1473918175     10836.60 Bytes freed
SMA.s0.g_bytes                       125011348          .   Bytes outstanding
SMA.s0.g_space                       948730476          .   Bytes available
SMA.Transient.c_bytes               4731618771     34787.99 Bytes allocated
SMA.Transient.c_freed               3838779376     28223.62 Bytes freed
SMA.Transient.g_bytes                892839395          .   Bytes outstanding
SMA.Transient.g_space                        0          .   Bytes available

I'm wondering if someone could put me in the right direction in how
to further investigate the content of transient storage, and why it's
larger than the regular cache.

The parameter itself is the default of 10 seconds, and I set a ttl of 5
minutes. It's Varnish 5.0.0-1 on Debian jessie. Never experienced it
with 4.13, but there were probably conf changes since we upgraded.

Regards,

-- 
Niall Murphy