On Mon, 2009-02-02 at 20:06 -0800, jason hadoop wrote:
> This can be made significantly worse by your underlying host file
> system and the disks that support it.
Oh, yes, we know... It was a late-realized mistake just yesterday that
we weren't using noatime on that cluster's slaves.
The attache
On Sun, 2009-02-01 at 17:58 -0800, jason hadoop wrote:
> The Datanode's use multiple threads with locking and one of the
> assumptions is that the block report (1ce per hour by default) takes
> little time. The datanode will pause while the block report is running
> and if it happens to take a whil
We have a small test cluster, a double master (NameNode+JobTracker) plus
2 slaves, running 0.18.1. We are seeing an intermittent problem where
our application logs failures out of DFSClient, thus:
2009-01-30 01:59:42,072 WARN org.apache.hadoop.dfs.DFSClient:
DFSOutputStream ResponseProcessor exce
On Wed, 2008-12-10 at 11:52 -0800, Konstantin Shvachko wrote:
> This is probably related to HADOOP-4795.
Thanx for the observation and reference. However, my sense is that the
bug report you reference reflects NameNode going into an infloop spin,
whereas the situation we have faced concerns NameN
We have a cluster comprised of 21 nodes holding a total capacity of
about 55T where we have had a problem twice in the last couple weeks on
startup of NameNode. We are running 0.18.1. DFS space is currently
just below the halfway point of actual occupation, about 25T.
Symptom is that there is no
