Regression: sockets for 3.0.9pre1 ?

grarpamp grarpamp at gmail.com
Fri Jun 24 19:43:05 MDT 2011


Hi.

rsync 3.0.8
FreeBSD RELENG_4 i386.

rsync -Haxi --delete /.../ /.../

The first pathspec above (residing on zz, a full filesystem) is:
/vvvv/wwww/xxxx/zz/
The second pathspec above (residing on yyy, an empty filesystem) is:
/vvvv/wwww/xxxx/yyy/zz/

It's obviously a 'copy everything over' operation.

I've had to obfuscate the pathnames, however the exact pathlength
throughout the hierarchy, including the sockname, has been preserved
in the error. The destination socket is not created:

rsync: mknod "/vvvv/wwww/xxxx/yyy/zz/..../............../........../..../..........................?????????????/...../......./.../.../sockname.ctl
" failed: No such file or directory (2)
rsync error: some files/attrs were not transferred (see previous
errors) (code 23) at main.c(1052) [sender=3.0.8]

The rest of the hier at that depth and below was created.
I have not yet rerun the sync to see if it picks up the missing
socket.
I have not yet checked to see what it did with any other sockets
that may exist in zz.
The filesystem passes fsck, no media issues.
I am root.
I have no problem rsync'ing between existing exact copies.
  from
 filesystem zz: /vvvv/wwww/xxxx/zz/
  to
 filesystem aa: /vvvv/wwww/xxxx/aa/
I have no problem rsync'ing the source socket into /tmp/yyy/ .
I have no problem rsync'ing the source socket's hier into /tmp/yyy/ .
The sockname is hardlinked once in the source filesystem.
I have noted those path variants with ?'s above and A/B below.
Neither the A nor B hardlink made it into the yyy filesystem above.

mkdir /tmp/foo

rsync -Haxi --delete /vvvv/wwww/xxxx/zz/.../sockname.ctl /tmp/foo/sockname.ctl

ls -aliTos /vvvv/wwww/xxxx/zz/.../sockname.ctl /tmp/foo/sockname.ctl
1234567 0 srwxr-xr-x  2 1001  1001  - 0 Jun  1 12:00:00 2005 /...A/sockname.ctl
1234567 0 srwxr-xr-x  2 1001  1001  - 0 Jun  1 12:00:00 2005 /...B/sockname.ctl
    123 0 srwxr-xr-x  1 1001  1001  - 0 Jun  1 12:00:00 2005
/tmp/foo/sockname.ctl

What is it we might be seeing with this?


More information about the rsync mailing list