From d1eb4f520b35c1057c7cb3427a51dd6ae75cc61f Mon Sep 17 00:00:00 2001 From: Pranith Kumar K Date: Thu, 8 Jan 2015 15:39:40 +0530 Subject: cluster/ec: Handle CHILD UP/DOWN in all cases Backport of http://review.gluster.org/9396 Problem: When all the bricks are down at the time of mounting the volume, then mount command hangs. Fix: 1. Ignore all CHILD_CONNECTING events comming from subvolumes. 2. On timer expiration (without enough up or down childs) send CHILD_DOWN. 3. Once enough up or down subvolumes are detected, send the appropriate event. When rest of the subvols go up/down without changing the overall ec-up/ec-down send CHILD_MODIFIED to parent subvols. BUG: 1188471 Change-Id: If92bd84107d49495cd104deb34601afe7f9b155c Signed-off-by: Pranith Kumar K Reviewed-on: http://review.gluster.org/9551 Reviewed-by: Xavier Hernandez Tested-by: Gluster Build System Reviewed-by: Raghavendra Bhat --- tests/basic/ec/ec-notify.t | 79 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 79 insertions(+) create mode 100644 tests/basic/ec/ec-notify.t (limited to 'tests/basic') diff --git a/tests/basic/ec/ec-notify.t b/tests/basic/ec/ec-notify.t new file mode 100644 index 00000000000..586be91bdbe --- /dev/null +++ b/tests/basic/ec/ec-notify.t @@ -0,0 +1,79 @@ +#!/bin/bash + +. $(dirname $0)/../../include.rc +. $(dirname $0)/../../volume.rc + +# This test checks notify part of ec + +cleanup +TEST glusterd +TEST pidof glusterd +TEST $CLI volume create $V0 disperse 3 redundancy 1 $H0:$B0/${V0}{0..2} +TEST $CLI volume start $V0 + +#First time mount tests. +# When all the bricks are up, mount should succeed and up-children +# count should be 3 +TEST $GFS --volfile-id=/$V0 --volfile-server=$H0 $M0; +EXPECT_WITHIN $CHILD_UP_TIMEOUT "3" ec_child_up_count $V0 0 +TEST stat $M0 +EXPECT_WITHIN $UMOUNT_TIMEOUT "Y" force_umount $M0 + +# When the volume is stopped mount succeeds and up-children will be 0 +TEST $CLI volume stop $V0 +TEST $GFS --volfile-id=/$V0 --volfile-server=$H0 $M0; +# Wait for 5 seconds even after that up_count should show 0 +sleep 5; +EXPECT_WITHIN $CHILD_UP_TIMEOUT "0" ec_child_up_count $V0 0 +TEST ! stat $M0 +EXPECT_WITHIN $UMOUNT_TIMEOUT "Y" force_umount $M0 + +# When 2 bricks are up, mount should succeed and up-children +# count should be 2 + +TEST $CLI volume start $V0 +TEST kill_brick $V0 $H0 $B0/${V0}2 +TEST $GFS --volfile-id=/$V0 --volfile-server=$H0 $M0; +EXPECT_WITHIN $CHILD_UP_TIMEOUT "2" ec_child_up_count $V0 0 +TEST stat $M0 +EXPECT_WITHIN $UMOUNT_TIMEOUT "Y" force_umount $M0 + +# When only 1 brick is up mount should fail. +TEST kill_brick $V0 $H0 $B0/${V0}1 +TEST $GFS --volfile-id=/$V0 --volfile-server=$H0 $M0; +# Wait for 5 seconds even after that up_count should show 1 +sleep 5 +EXPECT_WITHIN $CHILD_UP_TIMEOUT "1" ec_child_up_count $V0 0 +TEST ! stat $M0 +EXPECT_WITHIN $UMOUNT_TIMEOUT "Y" force_umount $M0 + +# Mount already succeeded. Test that the brick up down are leading to correct +# state changes in ec. +TEST $CLI volume stop $V0 +TEST $CLI volume start $V0 force +TEST $GFS --volfile-id=/$V0 --volfile-server=$H0 $M0; +EXPECT_WITHIN $CHILD_UP_TIMEOUT "3" ec_child_up_count $V0 0 +TEST touch $M0/a + +# kill 1 brick and the up_count should become 2, fops should still succeed +TEST kill_brick $V0 $H0 $B0/${V0}1 +EXPECT_WITHIN $CHILD_UP_TIMEOUT "2" ec_child_up_count $V0 0 +TEST touch $M0/b + +# kill one more brick and the up_count should become 1, fops should fail +TEST kill_brick $V0 $H0 $B0/${V0}2 +EXPECT_WITHIN $CHILD_UP_TIMEOUT "1" ec_child_up_count $V0 0 +TEST ! touch $M0/c + +# kill one more brick and the up_count should become 0, fops should still fail +TEST kill_brick $V0 $H0 $B0/${V0}0 +EXPECT_WITHIN $CHILD_UP_TIMEOUT "0" ec_child_up_count $V0 0 +TEST ! touch $M0/c + +# Bring up all the bricks up and see that up_count is 3 and fops are succeeding +# again. +TEST $CLI volume start $V0 force +EXPECT_WITHIN $CHILD_UP_TIMEOUT "3" ec_child_up_count $V0 0 +TEST touch $M0/c + +cleanup -- cgit