We don't attempt to optimize region placement with hdfs locations yet. A
reason why is because on a long lived cluster compactions create the
locality you are looking for. Furthermore, in the old master such an
optimization was really hard to do. The new master should make it easier to
write such 1
Yes this is spot on. When hbase scans we read a block, iterate through the
keys in the block then goes to the next block. We try to be as efficient as
possible, but the inescapable fact remains we must read all the intervening
data. We can do tricks (in 0.90) to use the block index to skip some blo
I would like to tune region server to increase throughput..On a 10 node
cluster,
I'm getting 5 sec per put. (this is unbatched/unbuffered). Other than
region server handler count property is there anything else I can tune
to increase throughput? ( this operation i can't use buffered write wit
hi, all
I set hdfs replica=1 when running hbase. And DN and RS co-exists on each
slave node. So the data in the regions managed by RS will be stored on its
local data node, rite?
But when I restart hbase and hbase client does gets on RS, datanode will
read data from remote data nodes. Does that mea
Another potential "problem" of incremental bulk loader is that the number of
reducers (for the bulk loading process) needs to be equal to the existing
regions -- this seems to be unfeasible for very large table, say with 2000
regions.
Any comment on this? Thanks.
Sean
On Fri, Oct 8, 2010 at 9:03
On Sun, Oct 10, 2010 at 12:28 PM, Abhijit Pol wrote:
> Thanks Stack.
>
> I think we have GC under control. We have CMS tunned to start early and
> don't see slept x longer y in logs anymore. We also have higher zk timeout
> (150 seconds), guess can bump that up a bit.
>
> I was able to point to s
Can someone give me a detailed look at the HLog mechanism for 0.90
durablity?
I recall that HBase committers claim that data will be truly durable in 0.90
after the client gets 'ok' acknowledgement from server, while it was not
true in 0.20 (i.e., HBase may have the chance to lose the data even it
I think this is a good suggestion too.
HBase linearly scans through the 64KB that is bring to memory. If big data
payload (yet unused in a query/scan) is mixed with small data payload, it
will be rather ineffective, I think?
On Mon, Oct 11, 2010 at 9:43 AM, Ryan Rawson wrote:
> The reason I tal
That is correct. But we are confident with the new durability changes and
other things 0.90 will be safer and faster than 0.20.6.
On Oct 11, 2010 4:51 PM, "Sean Bigdatafun"
wrote:
> Thanks for clarifying this.
>
> But on the other hand, wow... that means that even I like the consistency
> enhance
Thanks for clarifying this.
But on the other hand, wow... that means that even I like the consistency
enhancement in 0.90, I can not enjoy it if I have started using HBase 0.20
on a production?
On Thu, Sep 16, 2010 at 10:49 PM, Stack wrote:
> On Thu, Sep 16, 2010 at 10:22 PM, Todd Lipcon w
We're using a pre-existing zookeeper cluster (HBASE_MANAGES_ZK=false),
and trying to port some code from 0.20 to 0.89, but hbase fails
to start with
Couldnt start ZK at requested address of 2181 [..blah..] 2182
(from ./src/main/java/org/apache/hadoop/hbase/master/HMaster.java)
Because port
BTW..get this exception while trying a new put..& Also, get this exception on
gets on some region servers
org.apache.hadoop.hbase.client.RetriesExhaustedException: Trying to contact
region server Some server, retryOnlyOne=true, index=0, islastrow=true, tries=9,
numtries=10, i=0, listsize=1
HBase was seamless for first couple of weeks..now all kinds of issues in
production :) fun fun..
Curious ..does this property have to match up on "hbase client side" & region
server side..
I've this number set to 0 on region server side & default on client side..
I can't do any put (new)
t
The reason I talk about value size is one area where multiple families
are good is when you have really large values in one column and
smaller values in different columns. So if you want to just read the
small values without scanning through the big values you can use
separate column families.
-ry
This smells of garbage and low memory.
See for ref a similar problem report here -
http://kr.forums.oracle.com/forums/thread.jspa?messageID=2146733
How many rest servers do you have loading all of that data? AFAIK they're
stateless and loadbalancable
#
"Gang worker#0 (Parallel GC Threads)" pr
> Yes. I agree. OOME unlikely. I misinterpreted my current problem.
> I found, that this (gc timeout) on my 0.89-stumpbleupon hbase occurs
> only if writeToWAL=false. My RS eats all available memory (5GB), but
> don't get OOME. I try ti figure out what is going on.
Long GC pauses happens for many
2010/10/11 Jean-Daniel Cryans :
> On Mon, Oct 11, 2010 at 4:20 AM, Andrey Stepachev wrote:
>> Hi.
>>
Yes. I agree. OOME unlikely. I misinterpreted my current problem.
I found, that this (gc timeout) on my 0.89-stumpbleupon hbase occurs
only if writeToWAL=false. My RS eats all available memory (5G
No idea, the reason it died is higher in the log. Look for a message
like "Dumping metrics" and the reason should be just a few lines
higher than that.
J-D
On Sun, Oct 10, 2010 at 5:13 PM, Venkatesh wrote:
>
> Some of the region servers suddenly dying..I've pasted relevant log lines..I
> don't
Section 5.1 of the Bigtable paper gives a pretty good explanation:
http://labs.google.com/papers/bigtable.html
In HBase, Chubby is replaced by ZooKeeper, root tablet by the -ROOT-
table, and METADATA tablets by the .META. table.
J-D
On Sun, Oct 10, 2010 at 10:54 PM, William Kang wrote:
> Hi,
>
On Mon, Oct 11, 2010 at 4:20 AM, Andrey Stepachev wrote:
> Hi.
>
> One additional issue with column families: number of memstores. Each
> family on insert utilizies
> one memstory. If you'll write in several memstores at onces you get
> more memstores and more
> memory will be used by you region s
Hi Fleming,
First, Sanel is correct, whatever you are attempting to use is not Stargate.
Kindly follow the rest of the advice.
> HBase 20.2
You should be using HBase 0.20.6. We can't help muchwith problems with 0.20.2
any more -- in just about all cases the first advice will be to upgrade to
0.
Actually, this is not Stargate, but older REST service that was deprecated.
To activate Stargate, copy $HBASE_HOME/contrib/stargate/* and
$HBASE_HOME/contrib/stargate/lib/* to hbase lib directory ($HBASE_HOME/lib)
and start it with:
$HBASE_HOME/bin/hbase org.apache.hadoop.hbase.stargate.Main
Now
Hi.
One additional issue with column families: number of memstores. Each
family on insert utilizies
one memstory. If you'll write in several memstores at onces you get
more memstores and more
memory will be used by you region server. Especially with random
inserts you can easy get
gc timeouts or O
23 matches
Mail list logo