[
https://issues.apache.org/jira/browse/HBASE-15619?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
stack updated HBASE-15619:
--------------------------
Attachment: flamegraph-108588.098.svg
flamegraph-1221.branch-1.svg
flamegraph-135684.1.1.svg
Flame graphs from when were were doing the C` workload where we were mostly
random reading values with about 40% of the time reading nothing from hbase.
I don't think these help much. The shape of the server has changed too much.
Would be more useful if they'd been for the empty table. Then we might see
where they are spending the extra time... though flight recording might give
better detail. I didn't do this. Let me know if you want me to (you'd probably
be better-off doing it yourself [~carp84] if bad performance reading an empty
table is important for you).
> Performance regression observed: Empty random read(get) performance of
> branch-1 worse than 0.98
> -----------------------------------------------------------------------------------------------
>
> Key: HBASE-15619
> URL: https://issues.apache.org/jira/browse/HBASE-15619
> Project: HBase
> Issue Type: Bug
> Reporter: Yu Li
> Assignee: Yu Li
> Attachments: compare.png, flamegraph-108588.098.svg,
> flamegraph-1221.branch-1.svg, flamegraph-135684.1.1.svg
>
>
> As titled, I observed the perf regression in the final stress testing before
> upgrading our online cluster to 1.x. More details as follows:
> 1. HBase version in the comparison test:
> * 0.98: based on 0.98.12 with some backports, among which HBASE-11297 is
> the most important perf-related one (especially under high stress)
> * 1.x: checked 3 releases in total
> 1) 1.1.2 with important perf fixes/improvements including HBASE-15031
> and HBASE-14465
> 2) 1.1.4 release
> 3) 1.2.1RC1
> 2. Test environment
> * YCSB: 0.7.0 with
> [YCSB-651|https://github.com/brianfrankcooper/YCSB/pull/651] applied
> * Client: 4 physical nodes, each with 8 YCSB instance, each instance with
> 100 threads
> * Server: 1 Master with 3 RS, each RS with 256 handlers and 64G heap
> * Hardware: 64-core CPU, 256GB Mem, 10Gb Net, 1 PCIe-SSD and 11 HDD, same
> hardware for client and server
> 3. Test cases
> * -p fieldcount=1 -p fieldlength=128 -p readproportion=1
> * case #1: read against empty table
> * -case #2: lrucache 100% hit-
> * -case #3: BLOCKCACHE=>false-
> 4. Test result
> * 1.1.4 and 1.2.1 have a similar perf (less than 2% deviation) as 1.1.2+, so
> will only paste comparison data of 0.98.12+ and 1.1.2+
> * per-RS Throughput(ops/s)
> ||HBaseVersion||case#1||-case#2-||-case#3-||
> |0.98.12+|383562|-257493-|-47594-|
> |1.1.2+|363050|-232757-|-35872-|
> * AverageLatency(us)
> ||HBaseVersion||case#1||-case#2-||-case#3-||
> |0.98.12+|2774|-4134-|-22371-|
> |1.1.2+|2930|-4572-|-29690-|
> It seems there's perf regression on RPCServer (we tried 0.98 client against
> 1.x server and observed a similar perf to 1.x client)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
