Volker Lendecke [Fri, 12 Nov 2004 15:49:47 +0000 (15:49 +0000)]
r3705: Nobody has commented, so I'll take this as an ack...
abartlet, I'd like to ask you to take a severe look at this!
We have solved the problem to find the global groups a user is in twice: Once
in auth_util.c and another time for the corresponding samr call. The attached
patch unifies these and sends them through the passdb backend (new function
pdb_enum_group_memberships). Thus it gives pdb_ldap.c the chance to further
optimize the corresponding call if the samba and posix accounts are unified by
issuing a specialized ldap query.
The parameter to activate this ldapsam behaviour is
Volker Lendecke [Fri, 12 Nov 2004 15:30:51 +0000 (15:30 +0000)]
r3704: Implement a cache get saves the result of a pdb_getsampwnam for later
retrieval by pdb_getsampwsid. This solves our problem that we do lots of calls
to LDAP during a typical XP login. XP does a lookupnames, then an openuser and
some queryinfo stuff. Lookupnames triggers the initial getsampwnam, and all
the subsequent ones make us call getsampwsid. This patch gets this down to one
call to LDAP.
Yes, a more "correct" way would be to stick the information to the open user
handle, but this one is simpler and saves the LDAP roundtrip for the openuser
call.
Jeremy Allison [Wed, 10 Nov 2004 23:43:52 +0000 (23:43 +0000)]
r3674: Stefan Esser <s.esser@e-matters.de> pointed out that the max data
value is only valid on the initial trans/trans2/nttrans request,
so if there are secondary requests we can't read it from them. Read
it from the initial request and pass as a parameter for those functions
that need it.
Jeremy.
Jeremy Allison [Tue, 9 Nov 2004 22:49:28 +0000 (22:49 +0000)]
r3642: Extend vfs to add seekdir/telldir/rewinddir. Yes I know I have to
fix the modules too... First step in fixing out large directories
problem.
Jeremy.
Volker Lendecke [Fri, 5 Nov 2004 23:34:00 +0000 (23:34 +0000)]
r3566: Completely replace the queryuseraliases call. The previous implementation does
not exactly match what you would expect.
XP workstations during login actually do this, so we should better become a
bit more correct. The LDAP query issued is not really fully optimal, but it is
a lot faster and more correct than what was there before. The change in
passdb.h makes it possible that queryuseraliases is done with a single ldap
query.
Volker Lendecke [Fri, 5 Nov 2004 22:53:35 +0000 (22:53 +0000)]
r3563: During a typical logon a modern workstation makes a lot of anonymous session
setups on its way to open a pipe. This gets rid of many round-trips to the
LDAP server during logon by setting up the server_info_guest once and not
asking the LDAP server and nss every time. Make sure that the ldap connection
is reopened in the child. (I did not look at the sql backends.)
Volker Lendecke [Fri, 5 Nov 2004 21:55:21 +0000 (21:55 +0000)]
r3561: Since we have tdb_reopen_all() after all forks, the local_pid logic is not
correct anymore. If we actually open the tdb before the fork, we end up
opening the tdb twice. Jerry, jra, this also happens in the locking and
printing subsystems. You might want to check it there (not that it actually
happens right now, but this gave me some confusion lately...).
Jeremy Allison [Thu, 4 Nov 2004 23:56:23 +0000 (23:56 +0000)]
r3535: Tidy up error reporting. Memory leak with MIT krb5 1.3.5 turns
out to be in the kerberos libraries, not in Samba. Now to test
with Heimdal.
Jeremy
Jeremy Allison [Sat, 30 Oct 2004 01:32:05 +0000 (01:32 +0000)]
r3381: More merging of the #1717 patch. Fixup some erroneous assumptions about
memcpy's into fqdn names. I think the original intent was to create
MYNAME.fqdn.tail.part.
Will need testing to see I haven't broken keytab support.
Jeremy.
Jeremy Allison [Fri, 29 Oct 2004 22:38:10 +0000 (22:38 +0000)]
r3377: Merge in first part of modified patch from Nalin Dahyabhai <nalin@redhat.com>
for bug #1717.The rest of the code needed to call this patch has not yet been
checked in (that's my next task). This has not yet been tested - I'll do this
once the rest of the patch is integrated.
Jeremy.
Tim Potter [Tue, 26 Oct 2004 01:37:19 +0000 (01:37 +0000)]
r3228: Fix for bugzilla #1884 from Brett Funderburg. Use the value of
desired_access passed in to the lsa open policy routine. Use a default
value that netapps and windows likes as well.
Günther Deschner [Sat, 23 Oct 2004 15:16:10 +0000 (15:16 +0000)]
r3146: Some cleanup for idmap_rid:
- fix several memleaks found by valgrind
- turn off support for trusted domains (can be reenabled with
#define IDMAP_RID_SUPPORT_TRUSTED_DOMAINS 1)
- improve readability
Günther Deschner [Sat, 23 Oct 2004 13:23:54 +0000 (13:23 +0000)]
r3145: Add experimental idmap_rid-Plugin.
Written by Sumit Bose <sbose@suse.de> and myself a while ago.
idmap_rid does a direct, static mapping between RIDs and UIDs/GIDs using
the idmap-range as offset. It does thus allow to have a unified mapping
over several winbindd-systems without having the need of a central
LDAP-Server (and all related dependencies and problems this solution can
bring).
idmp_rid does even allow you to have multiple mappings (for trusted
domains). This is a rather problemtic feature and will be turned off by
default rather soon. The problem is that ranges can quickly overlap when
not measured with caution.
Gerald Carter [Fri, 22 Oct 2004 20:15:24 +0000 (20:15 +0000)]
r3140: * try to ensure consistent usage of the username map.
Use the fully qualified DOMAIN\user format for 'security = domain|ads'
and apply after authentication has succeeded.
* also change fill_domain_username() to only lowercase the username
and not the domain+username. This was a cosmetic fix only.
makes the output more consistent with %D and %U.
Gerald Carter [Tue, 19 Oct 2004 14:45:48 +0000 (14:45 +0000)]
r3065: BUG 1519 (more): apparently the server_name notify request is used to fill in the title bar of the port monitor window and unless we get it right, you cannot open the printer properties from the port monitor window
Gerald Carter [Mon, 18 Oct 2004 19:57:03 +0000 (19:57 +0000)]
r3049: fixing some calls in the printing code to stanard_sub_basic(); fix standard_sub_snum() to use the current user's gid; add some (snum == -1) checks to standard_sub_advanced()
Andrew Tridgell [Sun, 17 Oct 2004 00:22:11 +0000 (00:22 +0000)]
r3008: when checking for the existance of a lock we are only doing a single
tdb call, so there is no need to get the chainlock. This reduces the
number of tdb locking calls made on file IO
Jeremy Allison [Sat, 16 Oct 2004 03:04:40 +0000 (03:04 +0000)]
r3002: Fix for bug #1886 - prevent delete on close being set
for readonly files (and return the correct error code).
We now pass the Samba4 test suite on this.
Jeremy.
projects / thirdparty / samba.git / log
