Module: check_mk Branch: master Commit: 66e6473480441a5e7b7ad6808c5f709e775bfc4c URL: http://git.mathias-kettner.de/git/?p=check_mk.git;a=commit;h=66e6473480441a… Author: Simon Betz <si(a)mathias-kettner.de> Date: Mon Jun 26 15:54:15 2017 +0200 4876 FIX mounts: Fixed wrong handling of NFS mounts on Linux which are detected as stale Such mounts are marked with '\040(deleted)' und therefore discovered as new services while the related services report {{UNKNOWN - filesystem not mounted}}. This has been fixed. The service now reports {{WARN - Mount point detected as stale}}. Please see https://utcc.utoronto.ca/~cks/space/blog/linux/NFSStaleUnmounting for more information. Change-Id: I03dd6febbaaa7495522319f36acae8e7cb498123 --- .werks/4876 | 20 ++++++++++++++++++++ checks/mounts | 29 ++++++++++++++++++----------- 2 files changed, 38 insertions(+), 11 deletions(-) diff --git a/.werks/4876 b/.werks/4876 new file mode 100644 index 0000000..44692ee --- /dev/null +++ b/.werks/4876 @@ -0,0 +1,20 @@ +Title: mounts: Fixed wrong handling of NFS mounts on Linux which are detected as stale +Level: 1 +Component: checks +Class: fix +Compatible: compat +Edition: cre +State: unknown +Version: 1.5.0i1 +Date: 1498484953 + +Such mounts are marked with '\040(deleted)' und therefore discovered +as new services while the related services report +{{UNKNOWN - filesystem not mounted}}. + +This has been fixed. The service now reports +{{WARN - Mount point detected as stale}}. + +Please see +https://utcc.utoronto.ca/~cks/space/blog/linux/NFSStaleUnmounting +for more information. diff --git a/checks/mounts b/checks/mounts index ddac74d..1d7fba4 100644 --- a/checks/mounts +++ b/checks/mounts @@ -24,6 +24,12 @@ # to the Free Software Foundation, Inc., 51 Franklin St, Fifth Floor, # Boston, MA 02110-1301 USA. +# See https://utcc.utoronto.ca/~cks/space/blog/linux/NFSStaleUnmounting +# Output changes from +# knvmsapprd:/transreorg/sap/trans /transreorg/sap/trans nfs4 rw,relatime,vers=4.0,rsize=1048576,wsize=1048576,namlen=255,hard,proto=tcp,timeo=600,retrans=2,sec=sys,clientaddr=172.24.98.63,local_lock=none,addr=172.24.98.57 0 0 +# to +# knvmsapprd:/transreorg/sap/trans /transreorg/sap/trans\040(deleted) nfs4 rw,relatime,vers=4.0,rsize=1048576,wsize=1048576,namlen=255,hard,proto=tcp,timeo=600,retrans=2,sec=sys,clientaddr=172.24.98.63,local_lock=none,addr=172.24.98.57 0 0 + def inventory_mounts(info): inventory = [] @@ -33,11 +39,11 @@ def inventory_mounts(info): devices.append(dev) opts = options.split(",") opts.sort() - inventory.append( (mp, opts) ) + inventory.append( (mp.replace("\\040(deleted)", ""), opts) ) return inventory -def check_mounts(item, targetopts, info): +def check_mounts(item, targetopts, info): # Ignore options that are allowed to change def should_ignore_option(option): for ignored_option in [ "commit=", "localalloc=", "subvol=", "subvolid=" ]: @@ -46,7 +52,10 @@ def check_mounts(item, targetopts, info): return False for dev, mp, fstype, options, dump, fsck in info: - if item == mp: + if item == mp.replace("\\040(deleted)", ""): + if mp.endswith("\\040(deleted)"): + return 1, "Mount point detected as stale" + opts = options.split(",") # Now compute the exact difference. @@ -61,24 +70,22 @@ def check_mounts(item, targetopts, info): missing.append(o) if not missing and not exceeding: - return (0, "mount options exactly as expected") + return 0, "Mount options exactly as expected" infos = [] if missing: - infos.append("missing: %s" % ",".join(missing)) + infos.append("Missing: %s" % ",".join(missing)) if exceeding: - infos.append("exceeding: %s" % ",".join(exceeding)) + infos.append("Exceeding: %s" % ",".join(exceeding)) infotext = ", ".join(infos) if "ro" in exceeding: - return (2, "filesystem has switched to read-only " - "and is probably corrupted(!!), " + infotext) + return 2, "Filesystem has switched to read-only and is probably corrupted(!!), %s" % infotext # Just warn in other cases - return (1, infotext) - - return (3, "filesystem not mounted") + return 1, infotext + return 3, "Filesystem not mounted" check_info["mounts"] = {