phoenix-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Lars Hofhansl (JIRA)" <>
Subject [jira] [Commented] (PHOENIX-2405) Improve performance and stability of server side sort for ORDER BY
Date Sat, 02 Feb 2019 21:43:00 GMT


Lars Hofhansl commented on PHOENIX-2405:

We just ran into this in production. I'm going to file a fresh issue.
My main observation here is:
# We're only spilling when the sort buffer is over some threshold, at which point we'd expect
this to get a bit slower.
# We do not need random access. The sorted part is written, than read back purely sequential.
Simple file IO would do the trick as well.

> Improve performance and stability of server side sort for ORDER BY
> ------------------------------------------------------------------
>                 Key: PHOENIX-2405
>                 URL:
>             Project: Phoenix
>          Issue Type: Bug
>            Reporter: James Taylor
>            Assignee: Haoran Zhang
>            Priority: Major
>              Labels: gsoc2016
> We currently use memory mapped files to buffer data as it's being sorted in an ORDER
BY (see MappedByteBufferQueue). The following types of exceptions have been seen to occur:
> {code}
> Caused by: java.lang.OutOfMemoryError: Map failed
>         at Method)
>         at
> {code}
> [~apurtell] has read that memory mapped files are not cleaned up after very well in Java:
> {quote}
> "Map failed" means the JVM ran out of virtual address space. If you search around stack
overflow for suggestions on what to do when your app (in this case Phoenix) encounters this
issue when using mapped buffers, the answers tend toward manually cleaning up the mapped buffers
or explicitly triggering a full GC. See
for example. There are apparently long standing JVM/JRE problems with reclamation of mapped
buffers. I think we may want to explore in Phoenix a different way to achieve what the current
code is doing.
> {quote}
> Instead of using memory mapped files, we could use heap memory, or perhaps there are
other mechanisms too.

This message was sent by Atlassian JIRA

View raw message