Hi, Xiaowei
It's OK to simlify the patch just as you did. But we don't want to resend
master request to all others nodes in consideration of network traffic.
So we record those maybe down nodes in down_nodemap.
于 2013/5/28 14:12, xiaowei.hu 写道:
Hi,
I reviewed this patch , it did could fix a
On 05/31/2013 03:38 AM, Xue jiufei wrote:
Hi, Xiaowei
It's OK to simlify the patch just as you did. But we don't want to resend
master request to all others nodes in consideration of network traffic.
So we record those maybe down nodes in down_nodemap.
于 2013/5/28 14:12, xiaowei.hu 写道:
Hi,
Hi,
I reviewed this patch , it did could fix a temp lost connection problem,
but a few questions:
1. since we don't need to know the node numbers of down nodes, if simply
replace the down_nodemap[BITS_TO_LONGS(O2NM_MAX_NODES)], with a int
named for example mreq_msg_send_fail ?
2.since the
Function dlm_get_lock_resource() sends master request to all nodes in
domain_map and waits for their responses when the node(say nodeA) doesn't
known who the master is.
When nodeA sends the master request, it happened that network of
nodeB down for a while, and then restore. The master