Hi there Bing,
Please refer to this document. It describes the internal overhead for Geode.
https://geode.apache.org/docs/guide/10/reference/topics/memory_requirements_for_cache_data.html
--Udo
On 5/8/17 22:23, Bing Jiang wrote:
Thanks, Barry.
Can anyone point me a document or blog to describe how Geode allocate
memory internally?
2017-05-06 5:24 GMT+08:00 Barry Oglesby <[email protected]
<mailto:[email protected]>>:
Bing,
The gfsh gc command is reporting incorrect results. I filed
https://issues.apache.org/jira/browse/GEODE-2883
<https://issues.apache.org/jira/browse/GEODE-2883>.
Thanks for finding this.
Thanks,
Barry Oglesby
On Fri, May 5, 2017 at 1:03 AM, Bing Jiang
<[email protected] <mailto:[email protected]>> wrote:
hi, All.
We launch a geode locator and 7 geode servers (max heap size
is 20GB).
Experiments:
insert 1000,000 row (Kay-Value) into one PARTITION_PERSISTEN
region, and pulse web ui shows that the it uses about 66MB
memory. I believe it is expected.
But after executing gc via gfsh shell, each geode server show
about 700MB increase in heap.
Can anyone tell the why the extra heap memory has used?
Any possible solution to decrease the heap memory usage?
Thanks
Bing
--
Bing Jiang
Tel：(86)134-2619-1361
weibo: http://weibo.com/jiangbinglover
BLOG: www.binospace.com <http://www.binospace.com>
BLOG: http://blog.sina.com.cn/jiangbinglover
Focus on distributed computing, HDFS/HBase
