Please do enter a JIRA. Looking at the source it seems that we log and error, but the calling code continues. I think this is happening because the chroot c lib code is not handling znode watches separate from state change notifications.

The calling code just continues after logging an (invalid I think) error - can you try it out and see if it works, even though the error message is being displayed (with chroot I mean).



Mahadev Konar wrote:
This looks like a bug. Does this happen without doing any reads/writes using
the zookeeper handle?

Please do open a jira for this.


On 8/2/09 10:53 PM, "Michi Mutsuzaki" <> wrote:


I'm doing something like this (using zookeeper-3.2.0):

zhandle_t* zh = zookeeper_init("localhost:2818/servers", watcher,
1000, 0, 0, 0);

and getting this error:

2009-08-03 05:48:30,693:3380(0x40a04950):zoo_i...@check_events@1439:
initiated connection to server []
2009-08-03 05:48:30,705:3380(0x40a04950):zoo_i...@check_events@1484:
connected to server [] with session id=122ddb9be64016d
2009-08-03 05:48:30,705:3380(0x40c05950):zoo_er...@sub_string@730:
server path  does not include chroot path /servers

The error log doesn't appear if I use "localhost:2818" without chroot.
Is this actually an error?


Reply via email to