[ 
https://issues.apache.org/jira/browse/HBASE-5699?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14247143#comment-14247143
 ] 

Sean Busbey commented on HBASE-5699:
------------------------------------

bq. What would the charts look like if no disk friction at all, i.e. no a 
mocked WAL? Are we using all available i/o or are we blocked internally – 
cpu/locks/context switching?

I could run this as a baseline with the DisabledWALProvider. IIRC all it does 
is increment metric counts.

bq. Nice graphs Sean. How'd you make them/run the tests?

The tests are runs of the WALPerformanceEval tool using the command up above 
under "Overview". To alter the WAL count I made multiple conf dirs with that 
setting switched in hbase-site.xml and then exported an appropriate 
HBASE_CONF_DIR before each run. The tests I ran over the weekend (but haven't 
gotten to chart yet) are the same but with more options configured.

The chart itself is just the output from the log of the test filtered for the 
append byte counts that happen every 30 seconds, then put into a google doc to 
do deltas and avg / stddev. I was considering using the same data to plot the 
IQR instead of average +- stddev, but I wasn't sure that would be as consumable.

> Run with > 1 WAL in HRegionServer
> ---------------------------------
>
>                 Key: HBASE-5699
>                 URL: https://issues.apache.org/jira/browse/HBASE-5699
>             Project: HBase
>          Issue Type: Improvement
>          Components: Performance, wal
>            Reporter: binlijin
>            Assignee: Sean Busbey
>            Priority: Critical
>         Attachments: HBASE-5699.3.patch.txt, HBASE-5699.4.patch.txt, 
> HBASE-5699_#workers_vs_MiB_per_s_1x1col_512Bval_wal_count_1,2,4.tiff, 
> HBASE-5699_write_iops_multiwal-1_1_to_200_threads.tiff, 
> HBASE-5699_write_iops_multiwal-2_10,50,120,190,260,330,400_threads.tiff, 
> HBASE-5699_write_iops_multiwal-4_10,50,120,190,260,330,400_threads.tiff, 
> HBASE-5699_write_iops_multiwal-6_10,50,120,190,260,330,400_threads.tiff, 
> HBASE-5699_write_iops_upstream_1_to_200_threads.tiff, PerfHbase.txt, 
> hbase-5699_multiwal_400-threads_stats_sync_heavy.txt, 
> hbase-5699_total_throughput_sync_heavy.txt, 
> results-hbase5699-upstream.txt.bz2, results-hbase5699-wals-1.txt.bz2, 
> results-updated-hbase5699-wals-2.txt.bz2, 
> results-updated-hbase5699-wals-4.txt.bz2, 
> results-updated-hbase5699-wals-6.txt.bz2
>
>




--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Reply via email to