From 8d38fb72c38b69a6a91fccce10ba5372eb04be77 Mon Sep 17 00:00:00 2001
From: Klaus Aehlig <aehlig@google.com>
Date: Tue, 7 May 2013 15:21:19 +0200
Subject: [PATCH] Support online-maintenance in hroller
Make hroller take into account the nodes (redundant) instances
will be migrated to. This be behavior can be overridden by the
--offline-maintenance option which will make hroller plan under
the assumption that all instances will be shutdown before starting
with the rolling reboots.
Signed-off-by: Klaus Aehlig <aehlig@google.com>
Reviewed-by: Thomas Thrainer <thomasth@google.com>
---
man/hroller.rst | 21 ++++++++++++++-------
src/Ganeti/HTools/CLI.hs | 11 +++++++++++
src/Ganeti/HTools/Program/Hroller.hs | 6 +++++-
3 files changed, 30 insertions(+), 8 deletions(-)
diff --git a/man/hroller.rst b/man/hroller.rst
index 1caaf7be8..e39061d73 100644
--- a/man/hroller.rst
+++ b/man/hroller.rst
@@ -51,11 +51,13 @@ ALGORITHM FOR CALCULATING OFFLINE REBOOT GROUPS
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
hroller will view the nodes as vertices of an undirected graph,
-connecting by instances which have both a primary and a secondary node.
-It will then color the graph using a few different heuristics, and
-return the minimum-size color set found. Node with the same color don't
-share an edge, and as such don't have an instance with both primary and
-secondary node on them, so they are safe to be rebooted concurrently.
+with two kind of edges. Firstly, there are edges from the primary
+to the secondary node of every instance. Secondly, two nodes are connected
+by an edge if they are the primary nodes of two instances that have the
+same secondary node. It will then color the graph using a few different
+heuristics, and return the minimum-size color set found. Node with the same
+color can then simultaneously migrate all instance off to their respective
+secondary nodes, and it is safe to reboot them simultaneously.
OPTIONS
-------
@@ -69,6 +71,11 @@ For a description of the standard options check **htools**\(7) and
\--one-step-only
Restrict to the first reboot group. Output the group one node per line.
+\--offline-maintenance
+ Pretend that all instances are shutdown before the reboots are carried
+ out. I.e., only edges from the primary to the secondary node of an instance
+ are considered.
+
\--force
Do not fail, even if the master node cannot be determined.
@@ -90,8 +97,8 @@ should support them both with and without secondary node replacement.
EXAMPLE
-------
-Offline Rolling node reboot output
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+Rolling node reboot output
+~~~~~~~~~~~~~~~~~~~~~~~~~~
With the default options, the program shows one reboot group per line as
a comma-separated list.
diff --git a/src/Ganeti/HTools/CLI.hs b/src/Ganeti/HTools/CLI.hs
index c0687233d..33e241d5e 100644
--- a/src/Ganeti/HTools/CLI.hs
+++ b/src/Ganeti/HTools/CLI.hs
@@ -70,6 +70,7 @@ module Ganeti.HTools.CLI
, oNoSimulation
, oNodeSim
, oNodeTags
+ , oOfflineMaintenance
, oOfflineNode
, oOneStepOnly
, oOutputDir
@@ -139,6 +140,7 @@ data Options = Options
, optNodeSim :: [String] -- ^ Cluster simulation mode
, optNodeTags :: Maybe [String] -- ^ List of node tags to restrict to
, optOffline :: [String] -- ^ Names of offline nodes
+ , optOfflineMaintenance :: Bool -- ^ Pretend all instances are offline
, optOneStepOnly :: Bool -- ^ Only do the first step
, optOutPath :: FilePath -- ^ Path to the output directory
, optSaveCluster :: Maybe FilePath -- ^ Save cluster state to this file
@@ -188,6 +190,7 @@ defaultOptions = Options
, optNodeSim = []
, optNodeTags = Nothing
, optOffline = []
+ , optOfflineMaintenance = False
, optOneStepOnly = False
, optOutPath = "."
, optSaveCluster = Nothing
@@ -465,6 +468,14 @@ oNodeTags =
"TAG,...") "Restrict to nodes with the given tags",
OptComplString)
+oOfflineMaintenance :: OptType
+oOfflineMaintenance =
+ (Option "" ["offline-maintenance"]
+ (NoArg (\ opts -> Ok opts {optOfflineMaintenance = True}))
+ "Schedule offline maintenance, i.e., pretend that all instance are\
+ \ offline.",
+ OptComplNone)
+
oOfflineNode :: OptType
oOfflineNode =
(Option "O" ["offline"]
diff --git a/src/Ganeti/HTools/Program/Hroller.hs b/src/Ganeti/HTools/Program/Hroller.hs
index 576ffb85f..d62263b1b 100644
--- a/src/Ganeti/HTools/Program/Hroller.hs
+++ b/src/Ganeti/HTools/Program/Hroller.hs
@@ -58,6 +58,7 @@ options = do
, oDataFile
, oIAllocSrc
, oOfflineNode
+ , oOfflineMaintenance
, oVerbose
, oQuiet
, oNoHeaders
@@ -143,10 +144,13 @@ main opts args = do
, hasTag $ optNodeTags opts
, hasGroup wantedGroup ])
nlf
+ mkGraph = if optOfflineMaintenance opts
+ then Node.mkNodeGraph
+ else Node.mkRebootNodeGraph nlf
-- TODO: fail if instances are running (with option to warn only)
- nodeGraph <- case Node.mkNodeGraph nodes ilf of
+ nodeGraph <- case mkGraph nodes ilf of
Nothing -> exitErr "Cannot create node graph"
Just g -> return g
--
GitLab