[
https://issues.apache.org/jira/browse/CASSANDRA-6916?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13976585#comment-13976585
]
Benedict commented on CASSANDRA-6916:
-------------------------------------
[~enigmacurry]: 6916v3 should crash if you set the preheat_kernel_page_cache
property to true (just tested this locally). Setting the
populate_io_cache_on_flush property of the CF would probably work but simply
have no effect. Are you sure you were running the correct branch?
bq. Furthermore, I hadn't realized when testing CASSANDRA-6746 that we could
actually fare well with the existing options like this
The problem is that we consider the default to be better at preventing dramatic
page cache churn during compaction, which this should continue to deliver but
without the downsides.
The errors look plausible - but could we confirm we're running the correct (v3)
branch given it didn't crash with the preheat setting in the yaml?
> Preemptive opening of compaction result
> ---------------------------------------
>
> Key: CASSANDRA-6916
> URL: https://issues.apache.org/jira/browse/CASSANDRA-6916
> Project: Cassandra
> Issue Type: Bug
> Components: Core
> Reporter: Benedict
> Assignee: Benedict
> Priority: Minor
> Labels: performance
> Fix For: 2.1
>
> Attachments: 6916-stock2_1.mixed.cache_tweaks.tar.gz,
> 6916-stock2_1.mixed.logs.tar.gz, 6916v3-preempive-open-compact.logs.gz,
> 6916v3-preempive-open-compact.mixed.2.logs.tar.gz,
> 6916v3-premptive-open-compact.mixed.cache_tweaks.2.tar.gz
>
>
> Related to CASSANDRA-6812, but a little simpler: when compacting, we mess
> quite badly with the page cache. One thing we can do to mitigate this problem
> is to use the sstable we're writing before we've finished writing it, and to
> drop the regions from the old sstables from the page cache as soon as the new
> sstables have them (even if they're only written to the page cache). This
> should minimise any page cache churn, as the old sstables must be larger than
> the new sstable, and since both will be in memory, dropping the old sstables
> is at least as good as dropping the new.
> The approach is quite straight-forward. Every X MB written:
> # grab flushed length of index file;
> # grab second to last index summary record, after excluding those that point
> to positions after the flushed length;
> # open index file, and check that our last record doesn't occur outside of
> the flushed length of the data file (pretty unlikely)
> # Open the sstable with the calculated upper bound
> Some complications:
> # must keep running copy of compression metadata for reopening with
> # we need to be able to replace an sstable with itself but a different lower
> bound
> # we need to drop the old page cache only when readers have finished
--
This message was sent by Atlassian JIRA
(v6.2#6252)
