Thanks to the 3 folks who reviewed the new checksum algos. I've updated that review to address the feedback so far.
I haven't heard back on any of the other reviews after 3 weeks, so I'll reluctantly RTI these without any non-Delphix reviewers. I'm going to assume people want these changes but don't have the time or expertise to review them. If you think these changes are wrong or useless, now is the time to speak up. --matt On Sun, Jun 7, 2015 at 8:44 AM, Matthew Ahrens <[email protected]> wrote: > I have 4 outstanding ZFS code reviews; none of them trivial. I have > plenty of reviewers from Delphix but would like to get at least 1 from the > broader community. *Please send feedback* *by June 20th* or let me know > by then if you need more time to review. > > significant changes which improve performance of zfs receive, among other > things, and are foundational for resumable send/receive: > 5960 zfs recv should prefetch indirect blocks > https://reviews.csiden.org/r/221/ > > predictive prefetch rewrite (depends on above review); see detailed bug > report: > 5987 zfs prefetch code needs work > https://reviews.csiden.org/r/224 > > code restructuring for new checksum algos: > 5959 clean up per-dataset feature count code > https://reviews.csiden.org/r/222/ > > new checksum algorithms that are faster than SHA-256 (depends on the above > review): > 4185 add new cryptographic checksums to ZFS: SHA-512, Skein, Edon-R > https://reviews.csiden.org/r/223/ > > --matt >
_______________________________________________ developer mailing list [email protected] http://lists.open-zfs.org/mailman/listinfo/developer
