[jira] [Commented] (IGNITE-5884) Change default pageSize of page memory to 4KB

["Sergey Chugunov (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/IGNITE-5884?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16158298#comment-16158298 ] 

Sergey Chugunov commented on IGNITE-5884:
-----------------------------------------

[~ivan.glukos], the change looks good to me, TC status is acceptable (don't see any test failures related to the change). Please proceed with merging.

> Change default pageSize of page memory to 4KB
> ---------------------------------------------
>
>                 Key: IGNITE-5884
>                 URL: https://issues.apache.org/jira/browse/IGNITE-5884
>             Project: Ignite
>          Issue Type: Improvement
>          Components: persistence
>            Reporter: Ivan Rakov
>            Assignee: Ivan Rakov
>            Priority: Critical
>              Labels: usability
>             Fix For: 2.3
>
>         Attachments: CpBenchmark.java, iostat.log, ssdlab.log
>
>
> Checkpoint write speed is suboptimal with default 2K page on most UNIX-driven enviroments with SSD disk. There are several reasons for this:
> 1) Page size of linux page cache is 4k by default on most kernels (you can check yours by "getconf PAGE_SIZE" command). With 2k random writes vm.dirty_ratio threshold is reached two times faster than with 4k random writes.
> 2) Most SSD manufacturers don't expose actual disk page size, but they recommend to write at least 4k at once. Also, 4k blocks are used during benchmarking SSD random writes. 
> Related question: https://superuser.com/questions/1168014/nvme-ssd-why-is-4k-writing-faster-than-reading
> Article by Emmanuel Goossaert describing why writing less than a page is сounterproductive: http://codecapsule.com/2014/02/12/coding-for-ssds-part-3-pages-blocks-and-the-flash-translation-layer/
> I've prepared a checkpoint emulation benchmark (code and results attached). Run on production-level hardware (CentOS, 100 GB RAM, total LFS size is 100GB, vm.dirty_ratio=10) showed that checkpointing with 4k pages is much more efficient than with 2k.
> *Important: backwards compatibility must be ensured with LFS files created with old 2k default page size.*



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)