I am going to have to make numerous fields in struct vattr much larger
to accomodate HAMMER. I'm fairly sure the changes will not be exposed
to userland too badly but I can't guarentee it.
va_nlink, va_fsid, va_fileid, and va_gen will be expanded from 32 to 64
bits.
va_uid and va_gid will be expanded from a uid_t/gid_t to a full
16-byte uuid_t. The kernel will convert to and from the standard
32 bit uid_t and gid_t.
I will not be changing the ucred structure, that would be a bit too big
of bite for the moment.
The statvfs structure will also have to be changed in order to properly
export the 16 byte fsid. That will be user-visible, but fortunately
we have some spare fields we can use for it and I'll name the fields
f_fsid_uuid and f_owner_uuid and leave the original f_fsid and f_owner
fields intact.
We're stuck with the stat structure as-is, changing that would be a huge
mess. Fortunately we made the change to 64 bit inodes a long time ago
(st_ino is the one field we wouldn't be able to fake).
There may also be an issue with directory cookies, but I don't know
yet.
-Matt
Matthew Dillon
<dillon@backplane.com>
| Alexandre Oliva | Re: Dual-Licensing Linux Kernel with GPL V2 and GPL V3 |
| Bart Van Assche | Re: [Scst-devel] Integration of SCST in the mainstream Linux kernel |
| Thomas Meyer | Re: [PATCH] clockevents: Fix suspend/resume to disk hangs |
| S.Çağlar | Rescheduling interrupts |
git: | |
| Chris Ortman | [FEATURE REQUEST] git-svn format-patch |
| Sverre Rabbelier | Git vs Monotone |
| Linus Torvalds | People unaware of the importance of "git gc"? |
| Johannes Schindelin | Re: VCS comparison table |
| Alexey Dobriyan | [PATCH 01/53] xfrm: initialise xfrm_policy_gc_work statically |
| KOSAKI Motohiro | [bug?] tg3: Failed to load firmware "tigon/tg3_tso.bin" |
| Jarek Poplawski | Re: Data corruption issue with splice() on 2.6.27.10 |
| David Miller | [GIT]: Networking |
| Nick Holland | Re: keyboard lockup, KVM, dual-boot |
| Richard Stallman | Real men don't attack straw men |
| Anders Langworthy | Re: OpenBSD/i386 won't boot on Transmeta Efficeon CPU |
| Matthew Dempsky | hoststated/relayd and Linux's tcp_tw_recycle option |
