[
https://issues.apache.org/jira/browse/HBASE-1177?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12714802#action_12714802
]
Jim Kellerman commented on HBASE-1177:
--------------------------------------
All I am seeing now (on trunk) is increasing times:
Read 1 row with 7 columns 100 times in 921ms
Read 1 row with 8 columns 100 times in 4,089ms
Read 1 row with 1000 columns 100 times in 16,330ms
Read 1 row with 7 columns 100 times in 875ms
Read 1 row with 8 columns 100 times in 4,025ms
Read 1 row with 1000 columns 100 times in 16,860ms
Read 1 row with 7 columns 100 times in 993ms
Read 1 row with 8 columns 100 times in 4,087ms
Read 1 row with 1000 columns 100 times in 16,530ms
Which is what I would expect, although it does not explain why sometimes the
fetch of 1000 columns is sometimes faster than fetching 8.
Trying to reproduce that case. Often I get fetching 8 columns is faster than 7
as in:
Read 1 row with 7 columns 100 times in 907ms
Read 1 row with 8 columns 100 times in 622ms
Read 1 row with 1000 columns 100 times in 15,062ms
> Delay when client is located on the same node as the regionserver
> -----------------------------------------------------------------
>
> Key: HBASE-1177
> URL: https://issues.apache.org/jira/browse/HBASE-1177
> Project: Hadoop HBase
> Issue Type: Bug
> Affects Versions: 0.19.0
> Environment: Linux 2.6.25 x86_64
> Reporter: Jonathan Gray
> Assignee: Jim Kellerman
> Priority: Blocker
> Fix For: 0.20.0
>
> Attachments: ReadDelayTest.java, screenshot-1.jpg, screenshot-2.jpg,
> screenshot-3.jpg
>
>
> During testing of HBASE-80, we uncovered a strange 40ms delay for random
> reads. We ran a series of tests and found that it only happens when the
> client is on the same node as the RS and for a certain range of payloads (not
> specifically related to number of columns or size of them, only total
> payload). It appears to be precisely 40ms every time.
> Unsure if this is particular to our architecture, but it does happen on all
> nodes we've tried. Issue completely goes away with very large payloads or
> moving the client.
> Will post a test program tomorrow if anyone can test on a different
> architecture.
> Making a blocker for 0.20. Since this happens when you have an MR task
> running local to the RS, and this is what we try to do, might also consider
> making this a blocker for 0.19.1.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
