Mailing-List: contact user-help@zookeeper.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@zookeeper.apache.org
MIME-Version: 1.0
In-Reply-To: <C982CE5E.16851%rash@fb.com>
References: <C982CE5E.16851%rash@fb.com>
Date: Thu, 17 Feb 2011 13:29:36 -0800
Message-ID: <AANLkTikuUUuHLhiv017xUa7YXUMP6n5cWOFeGD_ZVvKr@mail.gmail.com>
Subject: Re: ephemeral node problem
From: Mahadev Konar <mahadev@apache.org>
To: user@zookeeper.apache.org
Cc: Samuel Rash <rash@fb.com>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

You probably ran into

https://issues.apache.org/jira/browse/ZOOKEEPER-919
?

If yes, 3.3.3 has the fix! It is due to be released next week.

thanks
mahadev
On Thu, Feb 17, 2011 at 1:08 PM, Samuel Rash <rash@fb.com> wrote:
> Hi,
>
> We are running zookeeper 3.3.2 and have seen what appears to be a problem=
 with ephemeral nodes. =A0We create about 2000 persistent nodes (leaves) in=
 a hierarchy. =A0Under each of these, we run a leader
> election with ephemeral nodes (~40). =A0This results in about 80,000 tota=
l ephemeral nodes. =A0During restart of our system, the leader elections ca=
n churn a bit as hosts remove themselves, electing new leaders, which then =
themselves may withdraw from the election. =A0In one such restart, we saw a=
n election get 'stuck'. =A0Upon investigating, one node had it's session ex=
pired (indicated in the zk logs), but one of its ephemeral nodes was still =
left. =A0We took down the processes holdilng ephemeral nodes and this node =
remained.
>
> Are there any known bugs in zookeeper that might result in this? =A0it do=
es not appear to happen under our normal laod.
>
> thx,
> -sr
>
>
>
> Sam Rash
> rash@fb.com
>