In message <[email protected]>, "Michael S. Fis cher" writes: >On Jan 18, 2010, at 1:52 PM, Poul-Henning Kamp wrote:
>Can you describe in more detail your comparative analysis and plans? =20 First of all, the major player in this are the 'stevedores' like "malloc", "file" and "persistent". I'm trying to apply what I have learned so far to the persistent stevedore and it has much more VM-hintable behaviour than the "file" stevedore, and hopefully a much more disk-scheduling friendly (ie: sequential) layout policy. In particular, I'm trying to make the "persistent" stevedore as "cheap-SSD" friendly as possible, by optmising for sequential writes where at all possile. Exactly how much help this will be, depends on everything in your world, including what your kernel does for madvise(), and if you have a usable sendfile() syscall, and therefore giving any specific promises is pretty impossible for me. Poul-Henning -- Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 [email protected] | TCP/IP since RFC 956 FreeBSD committer | BSD since 4.3-tahoe Never attribute to malice what can adequately be explained by incompetence. _______________________________________________ varnish-misc mailing list [email protected] http://projects.linpro.no/mailman/listinfo/varnish-misc
