;
> On Sun, Nov 14, 2010 at 3:49 PM, Chip Salzenberg
> wrote:
> > My by-now infamous eight-node cluster running 0.7.0beta3+ dropped many
> > replication MUTATEs during load, so I decided to fix replication copies
> with
> > a "nodetool repair" on one of the n
My by-now infamous eight-node cluster running 0.7.0beta3+ dropped many
replication MUTATEs during load, so I decided to fix replication copies with
a "nodetool repair" on one of the nodes (X.21). The repair has been running
for two days, and has finally gotten itself wedged into a state where it
c
After I rebooted my 0.7.0beta3+ cluster to increase threads (read=100
write=200 ... they're beefy machines), and putting them under load again, I
find gossip reporting yoyo up-down-up-down status for the other nodes.
Anyone know what this is a symptom of, and/or how to avoid it? I haven't
seen an
On Sun, Nov 7, 2010 at 11:58 PM, Reverend Chip wrote:
> Is there an existing tool to just read everything from every node, just
> to force a read repair on everything?
>
"nodetool repair", of course. me-- for getting FAQ and mailing list out of
order.
In the below "nodetool ring" output, machine 18 was told to loadbalance over
an hour ago. It won't actually leave the ring. When I first told it to
loadbalance, the cluster was under heavy write load; I've turned off the
write load, but the node won't actually leave, still. Help?
(It also colle
