child process of varnishd restarts automatically

[Vincent]

Hi All

We are running varnish on a 32-bit centos 5 box and we have noticed that
sometimes the child process of varnishd will restart automatically.

/var/log/messages shows the following error message:

varnishd[12707]: Child (12708) died signal=6
varnishd[12707]: Child (12708) Panic message: Missing errorhandling code in
sma_alloc(), storage_malloc.c line 81:   Condition((sma->s.ptr) != 0) not
true.errno = 12 (Cannot allocate memory) thread = (cache-worker) ident =
Linux,2.6.18-194.8.1.el5PAE,i686,-smalloc,-hcritbit,epoll Backtrace:
0x806cb6c: varnishd [0x806cb6c]   0x8088047: varnishd [0x8088047]
0x8085b3a: varnishd(STV_alloc+0xda) [0x8085b3a]   0x8063a91:
varnishd(FetchBody+0x7c1) [0x8063a91]   0x8059f87: varnishd [0x8059f87]
0x805b93a: varnishd(CNT_Session+0x44a) [0x805b93a]   0x806f5ef: varnishd
[0x806f5ef]   0x806e671: varnishd [0x806e671]   0x806eb6f: varnishd
[0x806eb6f]   0xc65832: /lib/libpthread.so.0 [0xc65832] sp = 0xb7ec5004 {
fd = 15, id = 15, xid = 608646521,   client = 127.0.0.1:57125,   step =
STP_FETCH,   handling = deliver,   err_code = 200, err_reason = (null),
restarts = 0, esis = 0   ws = 0xb7ec504c {      id = "sess",     {s,f,r,e} =
{0xb7ec57dc,+956,(nil),+16384},   },   http[req] = {     ws = 0x
varnishd[12707]: child (32242) Started
varnishd[12707]: Child (32242) said
varnishd[12707]: Child (32242) said Child starts


Varnishd was started with option "malloc,1.5G" and it runs without any
problem for hours before the child process restarts. When the child process
restarts, the system still have about 1.5G free memory so this is not a out
of memory issue.

Does anybody know how to solve this?

Thanks,

Vincent
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.varnish-cache.org/lists/pipermail/varnish-misc/attachments/20101220/c5526c3f/attachment.html>