[jira] [Commented] (HBASE-27867) Close the L1 victim handler race

["Hudson (Jira)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/HBASE-27867?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17726553#comment-17726553 ] 

Hudson commented on HBASE-27867:
--------------------------------

Results for branch master
	[build #848 on builds.a.o|https://ci-hbase.apache.org/job/HBase%20Nightly/job/master/848/]: (x) *{color:red}-1 overall{color}*
----
details (if available):

(x) {color:red}-1 general checks{color}
-- For more information [see general report|https://ci-hbase.apache.org/job/HBase%20Nightly/job/master/848/General_20Nightly_20Build_20Report/]




(x) {color:red}-1 jdk8 hadoop3 checks{color}
-- For more information [see jdk8 (hadoop3) report|https://ci-hbase.apache.org/job/HBase%20Nightly/job/master/848/JDK8_20Nightly_20Build_20Report_20_28Hadoop3_29/]


(x) {color:red}-1 jdk11 hadoop3 checks{color}
-- For more information [see jdk11 report|https://ci-hbase.apache.org/job/HBase%20Nightly/job/master/848/JDK11_20Nightly_20Build_20Report_20_28Hadoop3_29/]


(/) {color:green}+1 source release artifact{color}
-- See build output for details.


(/) {color:green}+1 client integration test{color}


> Close the L1 victim handler race
> --------------------------------
>
>                 Key: HBASE-27867
>                 URL: https://issues.apache.org/jira/browse/HBASE-27867
>             Project: HBase
>          Issue Type: Bug
>          Components: BlockCache
>    Affects Versions: 2.5.4
>            Reporter: Andrew Kyle Purtell
>            Assignee: Andrew Kyle Purtell
>            Priority: Minor
>             Fix For: 2.6.0, 3.0.0-alpha-4, 2.5.5
>
>
> When we evict a block from L1 and move it to L2 there is a brief window of time where we have removed the block from the L1 map and yet the victim handler has not completed execution. Some read-your-write use cases can be significantly impacted even though the window is small. Imagine a use case where PRELOAD_DATA_ON_OPEN and CACHE_DATA_ON_WRITE are both enabled to warm cache ahead of access and any miss can be problematic. Perhaps a particularly latency sensitive case with HFiles backed by S3. 
> Victim handling can be made atomic with respect to the unmapping operation with ConcurrentHashMap#computeIfPresent. The upside is there will be no L1+L2 misses during the transition. The downside is if the victim handler takes a long time to execute -- currently they are all very fast, so only a theoretical risk -- then other removals or insertions in L1 can block until it completes. 



--
This message was sent by Atlassian Jira
(v8.20.10#820010)