On Tue, Jul 02, 2013 at 07:53:52AM +0300, Vladislav Bogdanov wrote:
> 01.07.2013 18:29, Dejan Muhamedagic wrote:
> > Hi,
> >
> > On Mon, Jul 01, 2013 at 05:29:31PM +0300, Vladislav Bogdanov wrote:
> >> Hi,
> >>
> >> I'm trying to look if it is now safe to delete non-running nodes
> >> (corosync 2.3, pacemaker HEAD, crmsh tip).
> >>
> >> # crm node delete v02-d
> >> WARNING: 2: crm_node bad format: 7 v02-c
> >> WARNING: 2: crm_node bad format: 8 v02-d
> >> WARNING: 2: crm_node bad format: 5 v02-a
> >> WARNING: 2: crm_node bad format: 6 v02-b
> >> INFO: 2: node v02-d not found by crm_node
> >> INFO: 2: node v02-d deleted
> >> #
> >>
> >> So, I expect that crmsh still doesn't follow latest changes to 'crm_node
> >> -l'. Although node seems to be deleted correctly.
> >>
> >> For reference, output of crm_node -l is:
> >> 7 v02-c
> >> 8 v02-d
> >> 5 v02-a
> >> 6 v02-b
> >
> > This time the node state was empty. Or it's missing altogether.
> > I'm not sure how's that supposed to be interpreted. We test the
> > output of crm_node -l just to make sure that the node is not
> > online. Perhaps we need to use some other command.
>
> Likely it shows everything from a corosync nodelist.
> After I deleted the node from everywhere except corosync, list is still
> the same.
OK. This patch changes the interface to crm_node to use the
"list partition" option (-p). Could you please test it?
Cheers,
Dejan
> _______________________________________________
> Linux-HA mailing list
> Linux-HA@lists.linux-ha.org
> http://lists.linux-ha.org/mailman/listinfo/linux-ha
> See also: http://linux-ha.org/ReportingProblems
# HG changeset patch
# User Dejan Muhamedagic <de...@hello-penguin.com>
# Date 1372868970 -7200
# Wed Jul 03 18:29:30 2013 +0200
# Node ID d6f915195baceb5d0e3b76297ad1c8188c767e2f
# Parent 2c70ae4d11d3744bb6917170d0216617ec3a11dd
Medium: node: update interface to crm_node (node delete)
diff -r 2c70ae4d11d3 -r d6f915195bac modules/ui.py.in
--- a/modules/ui.py.in Tue Jul 02 12:44:55 2013 +0200
+++ b/modules/ui.py.in Wed Jul 03 18:29:30 2013 +0200
@@ -1258,50 +1258,30 @@ class NodeMgmt(UserInterface):
if not is_our_node(node):
common_err("node %s not found in the CIB" % node)
return False
- rc = True
if cluster_stack() == "heartbeat":
- rc = ext_cmd(self.hb_delnode%node) == 0
+ cmd = (self.hb_delnode % node)
else:
- node_states = {}
- ec, l = stdout2list("%s -l" % self.crm_node)
- for s in l:
- a = s.split()
- if len(a) != 3:
- common_warn("%s bad format: %s" % (self.crm_node, s))
- continue
- # fmt: id uname status
- # remove only those in state "lost"
- if a[1] == node:
- node_ref_du_jour = a[0]
- if is_pcmk_118():
- node_ref_du_jour = a[1]
- node_states[a[2]] = 1
- if a[2] == "lost":
- ec = ext_cmd("%s --force -R %s" % \
- (self.crm_node, node_ref_du_jour))
- if ec != 0:
- common_warn('"%s --force -R %s" failed, rc=%d' % \
- (self.crm_node, node_ref_du_jour, ec))
- if not node_states:
- common_info("node %s not found by %s" % (node, self.crm_node))
- elif "member" in node_states:
- common_info("node %s appears to be still active" % node)
- common_info("check output of %s -l" % self.crm_node)
- rc = False
- elif not "lost" in node_states:
- common_err("node %s's state not recognized: %s" % (node, node_states.keys()))
- common_info("check output of %s -l" % self.crm_node)
- rc = False
- if rc:
- if ext_cmd(self.node_delete%node) != 0 or \
- ext_cmd(self.node_delete_status%node) != 0:
- common_err("failed to remove %s from the CIB" % node)
- rc = False
- if rc:
- common_info("node %s deleted" % node)
- else:
- common_err('failed to delete node %s' % node)
- return rc
+ ec, s = get_stdout("%s -p" % self.crm_node)
+ if not s:
+ common_err('%s -p could not list any nodes (rc=%d)' % \
+ (self.crm_node, ec))
+ return False
+ partition_l = s.split()
+ if node in partition_l:
+ common_err("according to %s, node %s is still active" % \
+ (self.crm_node, node))
+ return False
+ cmd = "%s --force -R %s" % (self.crm_node, node)
+ ec = ext_cmd(cmd)
+ if ec != 0:
+ common_warn('"%s" failed, rc=%d' % (cmd, ec))
+ return False
+ if ext_cmd(self.node_delete % node) != 0 or \
+ ext_cmd(self.node_delete_status % node) != 0:
+ common_err("%s removed from membership, but not from CIB!" % node)
+ return False
+ common_info("node %s deleted" % node)
+ return True
def attribute(self, cmd, *args):
"""usage:
attribute <node> set <rsc> <value>
_______________________________________________
Linux-HA mailing list
Linux-HA@lists.linux-ha.org
http://lists.linux-ha.org/mailman/listinfo/linux-ha
See also: http://linux-ha.org/ReportingProblems
