Hi all, I am not a developer, but I have a background in engineering and a strong interest in performance and optimization. A recent Slashdot reference really piqued my interest. The reference is to an ACM Queue article that challenges some conventional wisdom regarding algorithm performance when memory paging is taken into consideration. As file systems and ZFS in particular deal with block hierarchies, I was curious if some of the principles discussed in the article might have substantial performance implications for ZFS or de-dup (e.g. in reducing the DDT memory thrashing and performance hit that can take place when deleting large datasets from a de-duped pool).
The ACM Queue article URL is below: http://queue.acm.org/detail.cfm?id=1814327 Any thoughts? Thanks in advance. Richard Bruce -- This message posted from opensolaris.org _______________________________________________ zfs-discuss mailing list zfs-discuss@opensolaris.org http://mail.opensolaris.org/mailman/listinfo/zfs-discuss
