[ https://issues.apache.org/jira/browse/IGNITE-8873?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16663690#comment-16663690 ]
Alexey Goncharuk commented on IGNITE-8873: ------------------------------------------ [~ascherbakov], a few comments: 1) From the change I see that the method {{preloadPartition()}} is supposed to be cluster-wide, however {{affinityRun}} will send the runnable only to one node, instead of primary and backups. Is it how it is supposed to work? I think it makes sense to preload both primary and backups. Also, should we add {{preloadPartitionLocal()}} method which will not broadcast any jobs but preload partition only if it exists locally? 2) Please add a proper javadoc to public API methods so a user understands what they do and what drawbacks it may have on page memory and performance 3) I think the methods should throw/return failed future with an {{IgniteException}} if the method is called on a non-persistent cache. > Optimize cache scans with enabled persistence. > ---------------------------------------------- > > Key: IGNITE-8873 > URL: https://issues.apache.org/jira/browse/IGNITE-8873 > Project: Ignite > Issue Type: Improvement > Reporter: Alexei Scherbakov > Assignee: Alexei Scherbakov > Priority: Major > Fix For: 2.8 > > > Currently cache scans with enabled persistence involve link resolution, which > can lead to radom disk access resulting in bad performace on SAS disks. > One possibility is to preload cache data pages to remove slow random disk > access. -- This message was sent by Atlassian JIRA (v7.6.3#76005)