[
https://issues.apache.org/jira/browse/HBASE-21874?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16770101#comment-16770101
]
ramkrishna.s.vasudevan commented on HBASE-21874:
------------------------------------------------
bq.Thus, main goal of setting "Direct Mode" here for now is not to use the
persistence capabilities (although it's probably already working), but just
have a mean to guarantee we use space from PMem device for caching (and not
DRAM at all, which can't be guaranteed with "Memory Mode")
Right.
bq.So theoretically, we can already do this with the current FileMmapEngine, no?
Yes. Theoretically correct provided the file is on the pmem engine. But
FileMmapEngine's assumes that if at all mmap is not able to fit the file in the
DRAM then the block has to be copied onheap. So the entire block wil be copied
to onheap. Our recent tests show that if we try to use as a mmap based file but
on AEP the copy is costlier because we copy from the AEP a 64K block to onheap.
So perf is on the lower side rather than doing what the pmem IOEngine does.
Thanks [~wchevreuil].
> Bucket cache on Persistent memory
> ---------------------------------
>
> Key: HBASE-21874
> URL: https://issues.apache.org/jira/browse/HBASE-21874
> Project: HBase
> Issue Type: New Feature
> Components: BucketCache
> Affects Versions: 3.0.0
> Reporter: ramkrishna.s.vasudevan
> Assignee: ramkrishna.s.vasudevan
> Priority: Major
> Fix For: 3.0.0
>
> Attachments: HBASE-21874.patch, HBASE-21874.patch,
> HBASE-21874_V2.patch, Pmem_BC.png
>
>
> Non volatile persistent memory devices are byte addressable like DRAM (for
> eg. Intel DCPMM). Bucket cache implementation can take advantage of this new
> memory type and can make use of the existing offheap data structures to serve
> data directly from this memory area without having to bring the data to
> onheap.
> The patch is a new IOEngine implementation that works with the persistent
> memory.
> Note : Here we don't make use of the persistence nature of the device and
> just make use of the big memory it provides.
> Performance numbers to follow.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
