[kubernetes] Allow only capturing logs for certain pods

The 'podlogs' option was previously an all-or-nothing toggle, which
could result in incredibly large amounts of data collection when only a
few pod's logs were needed.

This change adds a 'podlogs-filter' option that allows users to provide
either a specific pod name or a regex to match pod names against, to
limit the amount of pod logs we collect.

Resolves: #1640

Signed-off-by: Jake Hunsaker <jhunsake@redhat.com>
Signed-off-by: Bryn M. Reeves <bmr@redhat.com>

1 files changed, 10 insertions, 0 deletions

diff --git a/sos/plugins/kubernetes.py b/sos/plugins/kubernetes.py
index 4ae51162..dc7ee278 100644
--- a/sos/plugins/kubernetes.py
+++ b/sos/plugins/kubernetes.py
@@ -10,8 +10,11 @@
 # See the LICENSE file in the source distribution for further information.
 
 from sos.plugins import Plugin, RedHatPlugin
+from fnmatch import translate
 from os import path
 
+import re
+
 
 class kubernetes(Plugin, RedHatPlugin):
 
@@ -35,6 +38,8 @@ class kubernetes(Plugin, RedHatPlugin):
         ("describe", "capture descriptions of all kube resources",
             'fast', False),
         ("podlogs", "capture logs for pods", 'slow', False),
+        ("podlogs-filter", "only capture logs for pods matching this string",
+            'fast', '')
     ]
 
     def check_is_master(self):
@@ -134,7 +139,12 @@ class kubernetes(Plugin, RedHatPlugin):
                 if r['status'] == 0:
                     pods = [p.split()[0] for p in
                             r['output'].splitlines()[1:]]
+                    # allow shell-style regex
+                    reg = (translate(self.get_option('podlogs-filter')) if
+                           self.get_option('podlogs-filter') else None)
                     for pod in pods:
+                        if reg and not re.match(reg, pod):
+                            continue
                         self.add_cmd_output('%s logs %s' % (k_cmd, pod))
 
         if not self.get_option('all'):