hbase-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Andrew Purtell <apurt...@apache.org>
Subject Re: Stress testing releases candidates
Date Fri, 06 Jan 2012 18:49:05 GMT
I have tools for testing, I guess we should call now our fork, that are similar (I think) to TestLoadAndVerify from
BigTop: a shell/ruby script like the FaceBook LoadTestTool but write side only, and another
script than runs rowcounter, also a script that writes a list over a billion rows and another
that verifies no "broken links". (I've not seen the transient availability problem you describe,
but haven't been testing 0.92 like this either.) So it sounds like we've all come up with
the same baseline techniques. Unlike the FB tool I can specify different value size distributions,
and have some settings that approximate what our applications produce. A bit crufty and use
case specific. Also, a complete canned application model that I can rehydrate up on EC2 for
smoke tests.

The FB tool is useful on its own now that it's upstream. Maybe will move testing/capabilities
to it.

Great to see Cloudera/BigTop doing this for ASF releases. Would be great to see BigTop evolve
HBase testing beyond the baseline.

> At the moment we've been manually injecting faults (killing meta, masters,
> root, random rs's, pausing them to simulate GC's) but will be likely
> injecting faults and exercising recovery paths more regularly and
> systematically. 


This is something I don't have resources to do for ASF releases, so it's great to hear it's
happening elsewhere. I'm hoping mid-year to switch over to something as close to upstream
0.94 (guessing availability) as possible, as part of a larger project involving a federated
0.23 deployment, god help us. 

I'd not enable distributed splitting for production at first, though painful, so that specifically
wouldn't be tested here right away.


Best regards,


  - Andy

Problems worthy of attack prove their worth by hitting back. - Piet Hein (via Tom White)


----- Original Message -----
> From: Jonathan Hsieh <jon@cloudera.com>
> To: dev@hbase.apache.org
> Cc: 
> Sent: Friday, January 6, 2012 9:43 AM
> Subject: Stress testing releases candidates
> 
> Hey all,
> 
> I'm curious about the kinds of testing you all do and which paths you
> exercise before +1'ing a release candidate (or putting it into production).
> Do you just simulate the expected workloads you have at your
> installations?  How much testing do you all do on error recovery paths or
> when HBase gets into a stressful place?
> 
> Jimmy and I've been doing long-running TestLoadAndVerify from Bigtop using
> different configurations including a stressful (flush/split/compact heavy,
> properties below) configuration with the recent 0.92 release
> candidates. TestLoadAndVerify basically are two sequentially executed MR
> jobs -- one that loads data that have "dependency chains" on previous
> writes, and one that verifies that all chains are satisfied (link below).
> At the moment we've been manually injecting faults (killing meta, masters,
> root, random rs's, pausing them to simulate GC's) but will be likely
> injecting faults and exercising recovery paths more regularly and
> systematically.
> 
> This approach has resulted in some of the recent dist log splitting
> deadlocks Jimmy's been working.
> 
> I've encountered a few "transient" data missing problems that 
> I'm still
> trying to duplicate and isolate.  Best I can say now is that it seems to
> happen if/when region servers have a large number of regions (roughly
> 900-2000 regions per range). More specifically, in these particular cases
> it seems that the verify job return a list of sequential rows indicating
> that a region is was temporarily unavailable or not returning data.
> Interestingly, when I run just the verify job again later on the same
> table, all rows are present.  Since the Load and Verify jobs are
> two consecutively run MR jobs, my guess is that there is a related in
> something time delayed (balancing, splitting, compaction?).
> 
> Thanks,
> Jon.
> 
> Here's how to setup bigtop:
> https://cwiki.apache.org/confluence/display/BIGTOP/Setting+up+Bigtop+to+run+HBase+system+tests
> 
> 
> Here's the patch I've been using.
> https://issues.apache.org/jira/browse/BIGTOP-321
> 
> Here's part of the stress configuration that stresses flushing, splitting,
> and balancing operations.
> 
> ----
> <!-- stress settings -->
>   <property>
>     <name>io.file.buffer.size</name>
>     <value>131072</value>
>     <description>Hadoop setting </description>
>   </property>
>    <property>
>     <name>hbase.hregion.max.filesize</name>
>     <value>4194304</value>  <!-- 4MB -->
>     <!-- <value>268435456</value> 256MB, for lots of flushes 
> without splits
> -->
>     <description>
>     Maximum HStoreFile size. If any one of a column families' HStoreFiles
> has
>     grown to exceed this value, the hosting HRegion is split in two.
>     Default: 256M.
>     </description>
>   </property>
>   <property>
>     <name>hbase.balancer.period
>     </name>
>     <value>2000</value>
>     <description>Period at which the region balancer runs in the Master.
>     </description>
>   </property>
>    <property>
>     <name>hbase.hregion.max.filesize</name>
>     <value>4194304</value>  <!-- 4MB -->
>     <!-- <value>268435456</value> 256MB, for lots of flushes 
> without splits
> -->
>     <description>
>     Maximum HStoreFile size. If any one of a column families' HStoreFiles
> has
>     grown to exceed this value, the hosting HRegion is split in two.
>     Default: 256M.
>     </description>
>   </property>
>   <property>
>     <name>hbase.balancer.period
>     </name>
>     <value>2000</value>
>     <description>Period at which the region balancer runs in the Master.
>     </description>
>   </property>
>   <property>
>     <name>hbase.hregion.memstore.flush.size</name>
>     <value>262144</value> <!-- 256KB -->
>     <description>
>     Memstore will be flushed to disk if size of the memstore
>     exceeds this number of bytes.  Value is checked by a thread that runs
>     every hbase.server.thread.wakefrequency. (normally 64 MB)
>     </description>
>   </property>
> ----
> 
> -- 
> // Jonathan Hsieh (shay)
> // Software Engineer, Cloudera
> // jon@cloudera.com
> 

Mime
View raw message