[
https://issues.apache.org/jira/browse/HBASE-20188?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16412942#comment-16412942
]
Anastasia Braginsky commented on HBASE-20188:
---------------------------------------------
{quote}bq. I opened HBASE-20259. Assigned you.
{quote}
Thanks [~stack]! I'll take care.
{quote}bq. Setting the table so in-memory compaction = NONE seems to make reads
worse w/ no real change to writes. See attached
YCSB_IN_MEMORY_COMPACTION=NONE.ops.png
{quote}
>From looking on YCSB_IN_MEMORY_COMPACTION=NONE.ops.png I cannot understand
>with which results should I compare. I mean where do we have reads with
>in-memory-compaction and where without...? Anyway, if you say that turning
>in-memory-compaction off doesn't improve the reads we should look for the
>source for reads degradation anywhere else.
In general I agree with Eshcar, if we want to improve reads (a little) we
should set hbase.hregion.compacting.pipeline.segments.limit to 1. However do
not expect a dramatic change there, according to my experiments it is about
1-4%.
> [TESTING] Performance
> ---------------------
>
> Key: HBASE-20188
> URL: https://issues.apache.org/jira/browse/HBASE-20188
> Project: HBase
> Issue Type: Umbrella
> Components: Performance
> Reporter: stack
> Priority: Critical
> Fix For: 2.0.0
>
> Attachments: ITBLL2.5B_1.2.7vs2.0.0_cpu.png,
> ITBLL2.5B_1.2.7vs2.0.0_gctime.png, ITBLL2.5B_1.2.7vs2.0.0_iops.png,
> ITBLL2.5B_1.2.7vs2.0.0_load.png, ITBLL2.5B_1.2.7vs2.0.0_memheap.png,
> ITBLL2.5B_1.2.7vs2.0.0_memstore.png, ITBLL2.5B_1.2.7vs2.0.0_ops.png,
> ITBLL2.5B_1.2.7vs2.0.0_ops_NOT_summing_regions.png, YCSB_CPU.png,
> YCSB_GC_TIME.png, YCSB_IN_MEMORY_COMPACTION=NONE.ops.png, YCSB_MEMSTORE.png,
> YCSB_OPs.png, YCSB_in-memory-compaction=NONE.ops.png, YCSB_load.png,
> flamegraph-1072.1.svg, flamegraph-1072.2.svg, tree.txt
>
>
> How does 2.0.0 compare to old versions? Is it faster, slower? There is rumor
> that it is much slower, that the problem is the asyncwal writing. Does
> in-memory compaction slow us down or speed us up? What happens when you
> enable offheaping?
> Keep notes here in this umbrella issue. Need to be able to say something
> about perf when 2.0.0 ships.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
