Did you do some heavy inserting during that time? I assume you use 0.90.x(?)
Might be HBASE-4387.
-- Lars
- Original Message -
From: Stuti Awasthi
To: "user@hbase.apache.org"
Cc:
Sent: Thursday, October 13, 2011 9:44 PM
Subject: FATAL org.apache.hadoop.hbase.regionserver.wal.HLog: C
Hi Friends
I am using a mini distributed cluster of 3 nodes. Regionservers are running on
all of 3 nodes. This cluster is operational from 2 weeks now without any issue.
Today morning I saw one of the region servers are down.
I restarted the regionserver dynamically and it started fine and master
Most of the benchmarks I've seen are about what you're seeing 4-5x
overhead reading from HBase vs straight DFS files.
Makes sense as we have a whole extra layer involved, plus locking
overhead, etc. We can probably do some more optimization and get down
to a 2x difference, but we'll never be as fa
On Thu, Oct 13, 2011 at 1:47 PM, Norbert Burger wrote:
>
> > BTW, can your app support the semantics of having auto flush off? What's
> > your use case like?
> >
>
> By semantics, do you mean the possibility that unflushed data might be lost
> if the client goes away?
Yep, or if the Thrift serve
On Thu, Oct 13, 2011 at 1:05 PM, Jean-Daniel Cryans wrote:
> On Thu, Oct 13, 2011 at 8:17 AM, Norbert Burger >wrote:
>
> > In the ticket, I mentioned setting hbase.client.write.buffer as a
> > workaround, but unfortunately it doesn't seem that autoflush (which I
> > imagine has a bigger impact on
Have you done what the exception message tells you to do? It's related to
ZooKeeper, not HDFS.
J-D
On Wed, Oct 12, 2011 at 2:58 PM, Jignesh Patel wrote:
> I have following setup in my hbase-site.xml
>
>
> hbase.rootdir
> hdfs://localhost:9000/hbase
>
>
> dfs.replication
> 1
>
>
>
> but whe
Your question is more basic than that, it's actually how much slower is it
to sequentially read in HBase compared to HDFS. I'm not sure anyone
quantified that, and there's probably a bunch of factors that can influence
it, but at least you should try to get the same level of distribution eg
since y
On Thu, Oct 13, 2011 at 8:17 AM, Norbert Burger wrote:
> Thanks Ted, I created https://issues.apache.org/jira/browse/HBASE-4586.
>
> In the ticket, I mentioned setting hbase.client.write.buffer as a
> workaround, but unfortunately it doesn't seem that autoflush (which I
> imagine has a bigger impa
Thanks Ted, I created https://issues.apache.org/jira/browse/HBASE-4586.
In the ticket, I mentioned setting hbase.client.write.buffer as a
workaround, but unfortunately it doesn't seem that autoflush (which I
imagine has a bigger impact on write performance) isn't exposed.
Norbert
On Wed, Oct 12,
After set this argument to 1000, I get a result: hive/hbase is 4X
slower than hive/hdfs.
how much X is the expected slowdown for hive/hbase vs hive/hdfs?
Thanks
Weihua
2011/10/12 Akash Ashok :
> Hi,
> To set this parameter you could use "set hbase.client.scanner.caching=500;"
> before the execut
10 matches
Mail list logo
