Rushabh S Shah commented on HDFS-12278:

bq. but how did you benchmark TreeSet and PriorityQueue
[~daryn] benchmarked.
He just created lease-like objects and tested renew like methods.
Basically an object with string, int member variable and a comparator.
He created 100,000 such objects and called renew on them and measured via 
Daryn: please correct me if I am wrong.

bq. Are you aware of JMH?
I wasn't aware until I read the comment as did web search.
But it is very simple to understand that priority queue is not a good data 
structure if you want to remove any object other than the top one.

> LeaseManager operations are inefficient in 2.8.
> -----------------------------------------------
>                 Key: HDFS-12278
>                 URL: https://issues.apache.org/jira/browse/HDFS-12278
>             Project: Hadoop HDFS
>          Issue Type: Bug
>          Components: namenode
>    Affects Versions: 2.8.0
>            Reporter: Rushabh S Shah
>            Assignee: Rushabh S Shah
>            Priority: Blocker
>         Attachments: HDFS-12278-branch-2.8.001.patch, HDFS-12278.patch
> After HDFS-6757, LeaseManager #removeLease became expensive. 
> HDFS-6757 changed the {{sortedLeases}} object from TreeSet to PriorityQueue. 
> Previously the {{remove(Object)}} operation from {{sortedLeases}} was {{O(log 
> n)}} but after the change it became {{O( n)}} since it has to find the object 
> first. 
> Recently we had an incident in one of our production cluster just hours after 
> we upgraded from 2.7 to 2.8 
> The {{sortledLeases}} object had approximately 100,000 items within it. 
> While removing the lease, it will acquire the LeaseManager lock and that will 
> slow down the lookup of lease also.  
> HDFS-6757 is a good improvement which replaced the path by inode id.

This message was sent by Atlassian JIRA

To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org

Reply via email to