[
https://issues.apache.org/jira/browse/HBASE-16417?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15692764#comment-15692764
]
Eshcar Hillel commented on HBASE-16417:
---------------------------------------
Sorry, lost you with the acronyms ... what's IHOP?
What configuration do you suggest to test exactly?
Also wanted to re-consider again some other settings:
(1) WAL - is there a reason not to run with WAL? Obviously it is easier to
saturate the servers with no WAL, but this is not realistic, as almost 100% of
the application use WAL, and as we've seen different setting result in
different results - lets make sure there are no surprises there.
(2) #flush threads (2->10), #store files before blocking writes (10->25) - why
not use the default values? if most application use the default then we need to
test with this value, and if these values are the recommended ones then why not
change the default?
(3) memstore and blockcahce - why not just use the defaults 40%, 40%?
> In-Memory MemStore Policy for Flattening and Compactions
> --------------------------------------------------------
>
> Key: HBASE-16417
> URL: https://issues.apache.org/jira/browse/HBASE-16417
> Project: HBase
> Issue Type: Sub-task
> Reporter: Anastasia Braginsky
> Assignee: Eshcar Hillel
> Fix For: 2.0.0
>
> Attachments: HBASE-16417-benchmarkresults-20161101.pdf,
> HBASE-16417-benchmarkresults-20161110.pdf,
> HBASE-16417-benchmarkresults-20161123.pdf
>
>
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
