cluster/afr: Delay post-op for fsync

Problem:
AFR doesn't delay post-op for fsync fop. For fsync heavy workloads
this leads to un-necessary fxattrop/finodelk for every fsync leading
to bad performance.

Fix:
Have delayed post-op for fsync. Add special flag in xdata to indicate
that afr shouldn't delay post-op in cases where either the
process will terminate or graph-switch would happen. Otherwise it leads
to un-necessary heals when the graph-switch/process-termination
happens before delayed-post-op completes.

Fixes: #1253
Change-Id: I531940d13269a111c49e0510d49514dc169f4577
Signed-off-by: Pranith Kumar K <pkarampu@redhat.com>

1 files changed, 14 insertions, 1 deletions

diff --git a/xlators/cluster/dht/src/dht-rebalance.c b/xlators/cluster/dht/src/dht-rebalance.c
index c36995020d8..af74d1a33e7 100644
--- a/xlators/cluster/dht/src/dht-rebalance.c
+++ b/xlators/cluster/dht/src/dht-rebalance.c
@@ -1525,6 +1525,7 @@ dht_migrate_file(xlator_t *this, loc_t *loc, xlator_t *from, xlator_t *to,
     xlator_t *old_target = NULL;
     xlator_t *hashed_subvol = NULL;
     fd_t *linkto_fd = NULL;
+    dict_t *xdata = NULL;
 
     if (from == to) {
         gf_msg_debug(this->name, 0,
@@ -1848,7 +1849,15 @@ dht_migrate_file(xlator_t *this, loc_t *loc, xlator_t *from, xlator_t *to,
 
     /* TODO: Sync the locks */
 
-    ret = syncop_fsync(to, dst_fd, 0, NULL, NULL, NULL, NULL);
+    xdata = dict_new();
+    if (!xdata || dict_set_int8(xdata, "last-fsync", 1)) {
+        gf_log(this->name, GF_LOG_ERROR,
+               "%s: failed to set last-fsync flag on "
+               "%s (%s)",
+               loc->path, to->name, strerror(ENOMEM));
+    }
+
+    ret = syncop_fsync(to, dst_fd, 0, NULL, NULL, xdata, NULL);
     if (ret) {
         gf_log(this->name, GF_LOG_WARNING, "%s: failed to fsync on %s (%s)",
                loc->path, to->name, strerror(-ret));
@@ -2311,11 +2320,15 @@ out:
 
     if (dst_fd)
         syncop_close(dst_fd);
+
     if (src_fd)
         syncop_close(src_fd);
     if (linkto_fd)
         syncop_close(linkto_fd);
 
+    if (xdata)
+        dict_unref(xdata);
+
     loc_wipe(&tmp_loc);
     loc_wipe(&parent_loc);