From e8aedcd40f9f24e5b821e1539275e40ebfccca94 Mon Sep 17 00:00:00 2001
From: Pranith Kumar K <pkarampu@redhat.com>
Date: Fri, 29 May 2020 14:24:53 +0530
Subject: 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>
---
 xlators/cluster/afr/src/afr-inode-write.c | 11 +++++++++--
 xlators/cluster/afr/src/afr-transaction.c |  9 +++++++--
 xlators/cluster/afr/src/afr.h             |  2 +-
 3 files changed, 17 insertions(+), 5 deletions(-)

(limited to 'xlators/cluster/afr')

diff --git a/xlators/cluster/afr/src/afr-inode-write.c b/xlators/cluster/afr/src/afr-inode-write.c
index c01b4131d58..1d6e4f3570a 100644
--- a/xlators/cluster/afr/src/afr-inode-write.c
+++ b/xlators/cluster/afr/src/afr-inode-write.c
@@ -2506,6 +2506,7 @@ afr_fsync(call_frame_t *frame, xlator_t *this, fd_t *fd, int32_t datasync,
     call_frame_t *transaction_frame = NULL;
     int ret = -1;
     int32_t op_errno = ENOMEM;
+    int8_t last_fsync = 0;
 
     AFR_ERROR_OUT_IF_FDCTX_INVALID(fd, this, op_errno, out);
     transaction_frame = copy_frame(frame);
@@ -2516,10 +2517,16 @@ afr_fsync(call_frame_t *frame, xlator_t *this, fd_t *fd, int32_t datasync,
     if (!local)
         goto out;
 
-    if (xdata)
+    if (xdata) {
         local->xdata_req = dict_copy_with_ref(xdata, NULL);
-    else
+        if (dict_get_int8(xdata, "last-fsync", &last_fsync) == 0) {
+            if (last_fsync) {
+                local->transaction.disable_delayed_post_op = _gf_true;
+            }
+        }
+    } else {
         local->xdata_req = dict_new();
+    }
 
     if (!local->xdata_req)
         goto out;
diff --git a/xlators/cluster/afr/src/afr-transaction.c b/xlators/cluster/afr/src/afr-transaction.c
index c7a7d28fa7c..67c3e0699e6 100644
--- a/xlators/cluster/afr/src/afr-transaction.c
+++ b/xlators/cluster/afr/src/afr-transaction.c
@@ -2422,8 +2422,13 @@ afr_is_delayed_changelog_post_op_needed(call_frame_t *frame, xlator_t *this,
         goto out;
     }
 
-    if ((local->op != GF_FOP_WRITE) && (local->op != GF_FOP_FXATTROP)) {
-        /*Only allow writes but shard does [f]xattrops on writes, so
+    if (local->transaction.disable_delayed_post_op) {
+        goto out;
+    }
+
+    if ((local->op != GF_FOP_WRITE) && (local->op != GF_FOP_FXATTROP) &&
+        (local->op != GF_FOP_FSYNC)) {
+        /*Only allow writes/fsyncs but shard does [f]xattrops on writes, so
          * they are fine too*/
         goto out;
     }
diff --git a/xlators/cluster/afr/src/afr.h b/xlators/cluster/afr/src/afr.h
index d690986e654..1fff5640940 100644
--- a/xlators/cluster/afr/src/afr.h
+++ b/xlators/cluster/afr/src/afr.h
@@ -901,7 +901,7 @@ typedef struct _afr_local {
         gf_boolean_t uninherit_done;
         gf_boolean_t uninherit_value;
 
-        /* post-op hook */
+        gf_boolean_t disable_delayed_post_op;
     } transaction;
 
     syncbarrier_t barrier;
-- 
cgit