hbase-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Ryan Rawson <ryano...@gmail.com>
Subject Re: block cache
Date Sun, 19 Sep 2010 08:22:58 GMT
I'd love to see a GC log, and yes it can be possible for ParNew to
take a long long time.

Thanks,
-ryan

On Sun, Sep 19, 2010 at 1:20 AM, Tao Xie <xietao.mailbox@gmail.com> wrote:
> At first when I running the test, one of my regionserver shuts down. I found
> the gc has problems on that node. Then I enabled the jvm options listed in
> http://wiki.apache.org/hadoop/PerformanceTuning. After that, the test runs
> well. I checked the log and I do not know if it's normal for ParNew  to take
> as long as 500 ms. I will attach a snippet of that if necessary.
>
> Thanks.
>
>
> 2010/9/19 Ryan Rawson <ryanobjc@gmail.com>
>
>> What does your GC situation look like?
>>
>>
>>
>> On Sun, Sep 19, 2010 at 1:05 AM, Tao Xie <xietao.mailbox@gmail.com> wrote:
>> > Now my scenario is running ycsb doing heavy read. I compared the results
>> of
>> > setting hfile.block.cache.size to 0.2 with 0.  I found with the factor 0
>> the
>> > hbase metric 'get_avg_time' is even smaller. Maybe I should turn off
>> block
>> > cache in such scenario. I wonder if there are performance tests show the
>> > benefits of block cache?  Or there are other configurations for me to pay
>> > attention to?
>> >
>> > Btw, I give hbase 18G memory.
>> >
>>
>

Mime
View raw message