cluster/afr: Fixing the flaws in arbiter becoming source patch

Problem:
Setting the write_subvol value to read_subvol in case of metadata
transaction during pre-op (commit 19f9bcff4aada589d4321356c2670ed283f02c03)
might lead to the original problem of arbiter becoming source.

Scenario:
1) All bricks are up and good
2) 2 writes w1 and w2 are in progress in parallel
3) ctx->read_subvol is good for all the subvolumes
4) w1 succeeds on brick0 and fails on brick1, yet to do post-op on
   the disk
5) read/lookup comes on the same file and refreshes read_subvols back
   to all good
6) metadata transaction happens which makes ctx->write_subvol to be
   assigned with ctx->read_subvol which is all good
7) w2 succeeds on brick1 and fails on brick0 and this will update the
   brick in reverse order leading to arbiter becoming source

Fix:
Instead of setting the ctx->write_subvol to ctx->read_subvol in the
pre-op statge, if there is a metadata transaction, check in the
function __afr_set_in_flight_sb_status() if it is a data/metadata
transaction. Use the value of ctx->write_subvol if it is a data
transactions and ctx->read_subvol value for other transactions.

With this patch we assign the value of ctx->write_subvol in the
afr_transaction_perform_fop() with the on disk value, instead of
assigning it in the afr_changelog_pre_op() with the in memory value.

Change-Id: Id2025a7e965f0578af35b1abaac793b019c43cc4
BUG: 1482064
Signed-off-by: karthik-us <ksubrahm@redhat.com>

1 files changed, 14 insertions, 8 deletions

diff --git a/xlators/cluster/afr/src/afr.h b/xlators/cluster/afr/src/afr.h
index 7a7cb2e656f..fb8b3b1d136 100644
--- a/xlators/cluster/afr/src/afr.h
+++ b/xlators/cluster/afr/src/afr.h
@@ -376,6 +376,16 @@ typedef enum {
         AFR_FOP_LOCK_QUORUM_FAILED,
 } afr_fop_lock_state_t;
 
+typedef struct _afr_inode_ctx {
+        uint64_t        read_subvol;
+        uint64_t        write_subvol;
+        int             lock_count;
+        int             spb_choice;
+        gf_timer_t      *timer;
+        gf_boolean_t    need_refresh;
+} afr_inode_ctx_t;
+
+
 typedef struct _afr_local {
 	glusterfs_fop_t  op;
         unsigned int call_count;
@@ -832,17 +842,10 @@ typedef struct _afr_local {
         compound_args_t *c_args;
 
         gf_boolean_t is_read_txn;
+        afr_inode_ctx_t *inode_ctx;
 } afr_local_t;
 
 
-typedef struct _afr_inode_ctx {
-        uint64_t        read_subvol;
-        uint64_t        write_subvol;
-        int             spb_choice;
-        gf_timer_t      *timer;
-        gf_boolean_t    need_refresh;
-} afr_inode_ctx_t;
-
 typedef struct afr_spbc_timeout {
         call_frame_t *frame;
         gf_boolean_t d_spb;
@@ -1274,4 +1277,7 @@ afr_write_subvol_set (call_frame_t *frame, xlator_t *this);
 
 int
 afr_write_subvol_reset (call_frame_t *frame, xlator_t *this);
+
+int
+afr_set_inode_local (xlator_t *this, afr_local_t *local, inode_t *inode);
 #endif /* __AFR_H__ */