summaryrefslogtreecommitdiff
path: root/testsuite/build_farm/torture-TORTURE.test
diff options
context:
space:
mode:
authorJean-François Micouleau <jfm@samba.org>2001-12-21 22:34:49 +0000
committerJean-François Micouleau <jfm@samba.org>2001-12-21 22:34:49 +0000
commit0e550b2c11bde9a05167b237fb9910e2beccd14c (patch)
tree3567569d59bca94f542cf13b7c33c30f026b05fd /testsuite/build_farm/torture-TORTURE.test
parent5829284a07463aa560527b38b69570444160e019 (diff)
downloadsamba-0e550b2c11bde9a05167b237fb9910e2beccd14c.tar.gz
samba-0e550b2c11bde9a05167b237fb9910e2beccd14c.tar.bz2
samba-0e550b2c11bde9a05167b237fb9910e2beccd14c.zip
doesn't keep track of the struct's size we enumerate. W2K doesn't
calculate them and always reply a size of 32 bytes whereas NT4 did the maths. Anyway, it looks like the clients don't complain. in query_dom_info() at level 2, return the real number of users and groups. That's the fix to the W95/98 userlist bug ! as W95/98 does a query_dom_info(2) followed by a query_disp_info(4) on the SAME context handle (err we call it an lsa policy handle ! plain wrong name), I was tempted to keep the snapshoot in memory, to prevent 2 full user db enumerations in a row and just have one shared. But if some client does the 2 calls on two different handles, we would have 2 copies in memory not free'ed before the samr_close(). We still have too many fixed constant and too many magic values in that code. And btw, I really hates how the sequence number is generated ! J.F. (This used to be commit c0178e1a03f8225e5b350feb8fcbfb02f43327b4)
Diffstat (limited to 'testsuite/build_farm/torture-TORTURE.test')
0 files changed, 0 insertions, 0 deletions