From a644d52a4fe000827020b28736062a54c9a91b44 Mon Sep 17 00:00:00 2001 From: Ashish Pandey Date: Tue, 13 Mar 2018 14:03:20 +0530 Subject: cluster/ec: Change default read policy to gfid-hash Problem: Whenever we read data from file over NFS, NFS reads more data then requested and caches it. Based on the stat information it makes sure that the cached/pre-read data is valid or not. Consider 4 + 2 EC volume and all the bricks are on differnt nodes. In EC, with round-robin read policy, reads are sent on different set of data bricks. This way, it balances the read fops to go on all the bricks and avoid heating UP (overloading) same set of bricks. Due to small difference in clock speed, it is possible that we get minor difference for atime, mtime or ctime for different bricks. That might cause a different stat returned to NFS based on which NFS will discard cached/pre-read data which is actually not changed and could be used. Solution: Change read policy for EC as gfid-hash. That will force all the read to go to same set of bricks. >Change-Id: I825441cc519e94bf3dc3aa0bd4cb7c6ae6392c84 >BUG: 1554743 >Signed-off-by: Ashish Pandey Change-Id: I825441cc519e94bf3dc3aa0bd4cb7c6ae6392c84 BUG: 1557906 Signed-off-by: Ashish Pandey --- tests/basic/ec/ec-read-policy.t | 7 +++---- xlators/cluster/ec/src/ec.c | 2 +- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/tests/basic/ec/ec-read-policy.t b/tests/basic/ec/ec-read-policy.t index e4390aa07cb..fe6fe6576e7 100644 --- a/tests/basic/ec/ec-read-policy.t +++ b/tests/basic/ec/ec-read-policy.t @@ -20,10 +20,9 @@ TEST $CLI volume start $V0 TEST glusterfs --direct-io-mode=yes --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 volume operations work fine -EXPECT "round-robin" mount_get_option_value $M0 $V0-disperse-0 read-policy -TEST $CLI volume set $V0 disperse.read-policy gfid-hash -EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "gfid-hash" mount_get_option_value $M0 $V0-disperse-0 read-policy -TEST $CLI volume reset $V0 disperse.read-policy + +EXPECT "gfid-hash" mount_get_option_value $M0 $V0-disperse-0 read-policy +TEST $CLI volume set $V0 disperse.read-policy round-robin EXPECT_WITHIN $CONFIG_UPDATE_TIMEOUT "round-robin" mount_get_option_value $M0 $V0-disperse-0 read-policy #TEST if the option gives the intended behavior. The way we perform this test diff --git a/xlators/cluster/ec/src/ec.c b/xlators/cluster/ec/src/ec.c index f25760049c3..429cac956a5 100644 --- a/xlators/cluster/ec/src/ec.c +++ b/xlators/cluster/ec/src/ec.c @@ -1580,7 +1580,7 @@ struct volume_options options[] = { .key = {"read-policy" }, .type = GF_OPTION_TYPE_STR, .value = {"round-robin", "gfid-hash"}, - .default_value = "round-robin", + .default_value = "gfid-hash", .op_version = {GD_OP_VERSION_3_7_6}, .flags = OPT_FLAG_SETTABLE | OPT_FLAG_CLIENT_OPT | OPT_FLAG_DOC, .tags = {"disperse"}, -- cgit