clicx

Too many errors in log and node dead, anyone knows why?

1

Jun 21 23:43:51 WARN [gway 3486] sheep_exec_req(1184) failed No object found, remote address: 192.168.239.102:7000, op name: READ_PEER Jun 21 23:43:51 ERROR [block] __sd_read_object(512) failed to read object 207c2b25c043730f, No object...

I created 3 nodes cluster, cluster mode is zookeeper. And created some vdi, just do nothing and leaved them a few hours, then run the dog vdi check will dead....

Ways to expend nodes

1

I have running sheepdog on three node like document said: sheep /mnt/sheep/0 \ -c zookeeper:192.168.2.44:2181,192.168.2.45:2181,192.168.2.46:2181 Then how can I dynamic add the fourth node? As I see IP addresses are...

vdi setattr

4

I'm trying to use attr to internal communication, after set attr on a vdi, I can read attr from another node, but is there a way to notify other node...

After a reboot, sometimes, more than 1/2 of nodes had safety placed the log, but new leader don't set_commit_idx until a new log submitted.

Possible issues

1

I have done the following testing: 1. I applied one log item to three nodes, and persisted. 2. delete persist data from one node (not leader) and start raft (other...

in iser.c, line 333: if (pdu->indata.size smalloc_size) { it should be if (pdu->indata.size >= iscsi->smalloc_size) {

Segmentation fault in iSER discovery

6

iser discovery seems not fully implemented, I can't find an example for it. Therefor I simply modify from iscsi-ls, change iscsi:// to iser:// Then got segmentation fault after iscsi context...

iscsi_login_async callback function won't be called if some error happen, but the function return code is 0 in this condition, iscsi_service will always failed in iscsi_service_reconnect_if_loggedin. is this a known...

auto reconnect

6

How to set auto reconnect to server if connection broken? It seems not recovery iscsi connection after host is down for a period time.