From ea95631ff47c8048f039faedbc0faa918c4e165a Mon Sep 17 00:00:00 2001
From: Pranith Kumar K <pkarampu@redhat.com>
Date: Thu, 5 Sep 2019 16:12:39 +0530
Subject: cluster/ec: quorum-count implementation

fixes: #721
Change-Id: I5333540e3c635ccf441cf1f4696e4c8986e38ea8
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>
---
 tests/basic/ec/ec-quorum-count-partial-failure.t |  50 +++++++
 tests/basic/ec/ec-quorum-count.t                 | 165 +++++++++++++++++++++++
 2 files changed, 215 insertions(+)
 create mode 100755 tests/basic/ec/ec-quorum-count-partial-failure.t
 create mode 100644 tests/basic/ec/ec-quorum-count.t

(limited to 'tests/basic')

diff --git a/tests/basic/ec/ec-quorum-count-partial-failure.t b/tests/basic/ec/ec-quorum-count-partial-failure.t
new file mode 100755
index 00000000000..79f5825ae10
--- /dev/null
+++ b/tests/basic/ec/ec-quorum-count-partial-failure.t
@@ -0,0 +1,50 @@
+#!/bin/bash
+
+. $(dirname $0)/../../include.rc
+. $(dirname $0)/../../volume.rc
+
+#This test checks that partial failure of fop results in main fop failure only
+cleanup;
+
+TEST glusterd
+TEST pidof glusterd
+TEST $CLI volume create $V0 disperse 6 redundancy 2 $H0:$B0/${V0}{0..5}
+TEST $CLI volume create $V1 $H0:$B0/${V1}{0..5}
+TEST $CLI volume set $V0 performance.flush-behind off
+TEST $CLI volume start $V0
+TEST glusterfs --entry-timeout=0 --attribute-timeout=0 -s $H0 --volfile-id=/$V0 $M0
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "6" ec_child_up_count $V0 0
+
+TEST dd if=/dev/urandom of=$M0/a bs=12347 count=1
+TEST dd if=/dev/urandom of=$M0/b bs=12347 count=1
+TEST cp $M0/b $M0/c
+TEST fallocate -p -l 101 $M0/c
+TEST $CLI volume stop $V0
+TEST $CLI volume set $V0 debug.delay-gen posix;
+TEST $CLI volume set $V0 delay-gen.delay-duration 10000000;
+TEST $CLI volume set $V0 delay-gen.enable WRITE;
+TEST $CLI volume set $V0 delay-gen.delay-percentage 100
+TEST $CLI volume set $V0 disperse.quorum-count 6
+TEST $CLI volume start $V0
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "6" ec_child_up_count $V0 0
+cksum=$(dd if=$M0/a bs=12345 count=1 | md5sum | awk '{print $1}')
+truncate -s 12345 $M0/a & #While write is waiting for 5 seconds, introduce failure
+fallocate -p -l 101 $M0/b &
+sleep 1
+TEST kill_brick $V0 $H0 $B0/${V0}0
+TEST wait
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $HEAL_TIMEOUT "^0$" get_pending_heal_count ${V0}
+EXPECT "12345" stat --format=%s $M0/a
+TEST kill_brick $V0 $H0 $B0/${V0}1
+TEST kill_brick $V0 $H0 $B0/${V0}2
+EXPECT_WITHIN $UMOUNT_TIMEOUT "Y" force_umount $M0;
+TEST glusterfs --entry-timeout=0 --attribute-timeout=0 -s $H0 --volfile-id $V0 $M0
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "4" ec_child_up_count $V0 0
+cksum_after_heal=$(dd if=$M0/a | md5sum | awk '{print $1}')
+TEST [[ $cksum == $cksum_after_heal ]]
+cksum=$(dd if=$M0/c | md5sum | awk '{print $1}')
+cksum_after_heal=$(dd if=$M0/b | md5sum | awk '{print $1}')
+TEST [[ $cksum == $cksum_after_heal ]]
+
+cleanup;
diff --git a/tests/basic/ec/ec-quorum-count.t b/tests/basic/ec/ec-quorum-count.t
new file mode 100644
index 00000000000..56b5329c411
--- /dev/null
+++ b/tests/basic/ec/ec-quorum-count.t
@@ -0,0 +1,165 @@
+ #!/bin/bash
+
+. $(dirname $0)/../../include.rc
+. $(dirname $0)/../../volume.rc
+. $(dirname $0)/../../ec.rc
+
+cleanup
+TEST glusterd
+TEST pidof glusterd
+TEST $CLI volume create $V0 disperse 6 redundancy 2 $H0:$B0/${V0}{0..5}
+TEST $CLI volume create $V1 $H0:$B0/${V1}{0..5}
+TEST $CLI volume set $V0 disperse.eager-lock-timeout 5
+TEST $CLI volume set $V0 performance.flush-behind off
+
+#Should fail on non-disperse volume
+TEST ! $CLI volume set $V1 disperse.quorum-count 5
+
+#Should succeed on a valid range
+TEST ! $CLI volume set $V0 disperse.quorum-count 0
+TEST ! $CLI volume set $V0 disperse.quorum-count -0
+TEST ! $CLI volume set $V0 disperse.quorum-count abc
+TEST ! $CLI volume set $V0 disperse.quorum-count 10abc
+TEST ! $CLI volume set $V0 disperse.quorum-count 1
+TEST ! $CLI volume set $V0 disperse.quorum-count 2
+TEST ! $CLI volume set $V0 disperse.quorum-count 3
+TEST $CLI volume set $V0 disperse.quorum-count 4
+TEST $CLI volume start $V0
+TEST glusterfs --entry-timeout=0 --attribute-timeout=0 -s $H0 --volfile-id $V0 $M0
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "6" ec_child_up_count $V0 0
+
+#Test that the option is reflected in the mount
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "^4$" ec_option_value $V0 $M0 0 quorum-count
+TEST $CLI volume reset $V0 disperse.quorum-count
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "^0$" ec_option_value $V0 $M0 0 quorum-count
+TEST $CLI volume set $V0 disperse.quorum-count 6
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "^6$" ec_option_value $V0 $M0 0 quorum-count
+
+TEST touch $M0/a
+TEST touch $M0/data
+TEST setfattr -n trusted.def -v def $M0/a
+TEST touch $M0/src
+TEST touch $M0/del-me
+TEST mkdir $M0/dir1
+TEST dd if=/dev/zero of=$M0/read-file bs=1M count=1 oflag=direct
+TEST dd if=/dev/zero of=$M0/del-file bs=1M count=1 oflag=direct
+TEST gf_rm_file_and_gfid_link $B0/${V0}0 del-file
+#modify operations should fail as the file is not in quorum
+TEST ! dd if=/dev/zero of=$M0/del-file bs=1M count=1 oflag=direct
+TEST kill_brick $V0 $H0 $B0/${V0}0
+#Read should succeed even when quorum-count is not met
+TEST dd if=$M0/read-file of=/dev/null iflag=direct
+TEST ! touch $M0/a2
+TEST ! mkdir $M0/dir2
+TEST ! mknod  $M0/b2 b 4 5
+TEST ! ln -s $M0/a $M0/symlink
+TEST ! ln $M0/a $M0/link
+TEST ! mv $M0/src $M0/dst
+TEST ! rm -f $M0/del-me
+TEST ! rmdir $M0/dir1
+TEST ! dd if=/dev/zero of=$M0/a bs=1M count=1 conv=notrunc
+TEST ! dd if=/dev/zero of=$M0/data bs=1M count=1 conv=notrunc
+TEST ! truncate -s 0 $M0/a
+TEST ! setfattr -n trusted.abc -v abc $M0/a
+TEST ! setfattr -x trusted.def $M0/a
+TEST ! chmod +x $M0/a
+TEST ! fallocate -l 2m -n $M0/a
+TEST ! fallocate -p -l 512k $M0/a
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $HEAL_TIMEOUT "^0$" get_pending_heal_count ${V0}
+
+# reset the option and check whether the default redundancy count is
+# accepted or not.
+TEST $CLI volume reset $V0 disperse.quorum-count
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "^0$" ec_option_value $V0 $M0 0 quorum-count
+TEST touch $M0/a1
+TEST touch $M0/data1
+TEST setfattr -n trusted.def -v def $M0/a1
+TEST touch $M0/src1
+TEST touch $M0/del-me1
+TEST mkdir $M0/dir11
+TEST kill_brick $V0 $H0 $B0/${V0}0
+TEST kill_brick $V0 $H0 $B0/${V0}1
+TEST touch $M0/a21
+TEST mkdir $M0/dir21
+TEST mknod  $M0/b21 b 4 5
+TEST ln -s $M0/a1 $M0/symlink1
+TEST ln $M0/a1 $M0/link1
+TEST mv $M0/src1 $M0/dst1
+TEST rm -f $M0/del-me1
+TEST rmdir $M0/dir11
+TEST dd if=/dev/zero of=$M0/a1 bs=1M count=1 conv=notrunc
+TEST dd if=/dev/zero of=$M0/data1 bs=1M count=1 conv=notrunc
+TEST truncate -s 0 $M0/a1
+TEST setfattr -n trusted.abc -v abc $M0/a1
+TEST setfattr -x trusted.def $M0/a1
+TEST chmod +x $M0/a1
+TEST fallocate -l 2m -n $M0/a1
+TEST fallocate -p -l 512k $M0/a1
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "6" ec_child_up_count $V0 0
+
+TEST touch $M0/a2
+TEST touch $M0/data2
+TEST setfattr -n trusted.def -v def $M0/a1
+TEST touch $M0/src2
+TEST touch $M0/del-me2
+TEST mkdir $M0/dir12
+TEST kill_brick $V0 $H0 $B0/${V0}0
+TEST kill_brick $V0 $H0 $B0/${V0}1
+TEST kill_brick $V0 $H0 $B0/${V0}2
+TEST ! touch $M0/a22
+TEST ! mkdir $M0/dir22
+TEST ! mknod  $M0/b22 b 4 5
+TEST ! ln -s $M0/a2 $M0/symlink2
+TEST ! ln $M0/a2 $M0/link2
+TEST ! mv $M0/src2 $M0/dst2
+TEST ! rm -f $M0/del-me2
+TEST ! rmdir $M0/dir12
+TEST ! dd if=/dev/zero of=$M0/a2 bs=1M count=1 conv=notrunc
+TEST ! dd if=/dev/zero of=$M0/data2 bs=1M count=1 conv=notrunc
+TEST ! truncate -s 0 $M0/a2
+TEST ! setfattr -n trusted.abc -v abc $M0/a2
+TEST ! setfattr -x trusted.def $M0/a2
+TEST ! chmod +x $M0/a2
+TEST ! fallocate -l 2m -n $M0/a2
+TEST ! fallocate -p -l 512k $M0/a2
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $CHILD_UP_TIMEOUT "6" ec_child_up_count $V0 0
+EXPECT_WITHIN $HEAL_TIMEOUT "^0$" get_pending_heal_count ${V0}
+
+# Set quorum-count to 5 and kill 1 brick and the fops should pass
+TEST $CLI volume set $V0 disperse.quorum-count 5
+EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "^5$" ec_option_value $V0 $M0 0 quorum-count
+TEST touch $M0/a3
+TEST touch $M0/data3
+TEST setfattr -n trusted.def -v def $M0/a3
+TEST touch $M0/src3
+TEST touch $M0/del-me3
+TEST mkdir $M0/dir13
+TEST kill_brick $V0 $H0 $B0/${V0}0
+TEST touch $M0/a31
+TEST mkdir $M0/dir31
+TEST mknod  $M0/b31 b 4 5
+TEST ln -s $M0/a3 $M0/symlink3
+TEST ln $M0/a3 $M0/link3
+TEST mv $M0/src3 $M0/dst3
+TEST rm -f $M0/del-me3
+TEST rmdir $M0/dir13
+TEST dd if=/dev/zero of=$M0/a3 bs=1M count=1 conv=notrunc
+TEST dd if=/dev/zero of=$M0/data3 bs=1M count=1 conv=notrunc
+TEST truncate -s 0 $M0/a3
+TEST setfattr -n trusted.abc -v abc $M0/a3
+TEST setfattr -x trusted.def $M0/a3
+TEST chmod +x $M0/a3
+TEST fallocate -l 2m -n $M0/a3
+TEST fallocate -p -l 512k $M0/a3
+TEST dd if=/dev/urandom of=$M0/heal-file bs=1M count=1 oflag=direct
+cksum_before_heal="$(md5sum $M0/heal-file | awk '{print $1}')"
+TEST $CLI volume start $V0 force
+EXPECT_WITHIN $HEAL_TIMEOUT "^0$" get_pending_heal_count ${V0}
+TEST kill_brick $V0 $H0 $B0/${V0}4
+TEST kill_brick $V0 $H0 $B0/${V0}5
+cksum_after_heal=$(dd if=$M0/heal-file iflag=direct | md5sum | awk '{print $1}')
+TEST [[ $cksum_before_heal == $cksum_after_heal ]]
+cleanup;
-- 
cgit