From: Sage Weil <sage@redhat.com>
Date: Fri, 10 Feb 2017 04:01:14 +0000 (-0500)
Subject: osdc/Objecter: force pg_read ops to ignore cache overlay
X-Git-Tag: v12.0.1~383^2~10
X-Git-Url: http://git-server-git.apps.pok.os.sepia.ceph.com/?a=commitdiff_plain;h=ef74cf71aa0dd7fca23d53e947d7f08496a4cee1;p=ceph.git

osdc/Objecter: force pg_read ops to ignore cache overlay

pg_read is only used for PG listing and hit_set_{list,get}; these
operations can't and shouldn't consider the tiering overlay.

This makes the _calc_target behavior with the explicit pgid make sense;
otherwise, what would it mean to try to read pg x.1 from pool x and get
redirected to pg y.1 in pool y?

Signed-off-by: Sage Weil <sage@redhat.com>
---

diff --git a/src/osdc/Objecter.h b/src/osdc/Objecter.h
index 582950949219..8756482127ec 100644
--- a/src/osdc/Objecter.h
+++ b/src/osdc/Objecter.h
@@ -2277,7 +2277,9 @@ public:
     Context *onack, epoch_t *reply_epoch,
     int *ctx_budget) {
     Op *o = new Op(object_t(), oloc,
-		   op.ops, flags | global_op_flags.read() | CEPH_OSD_FLAG_READ,
+		   op.ops,
+		   flags | global_op_flags.read() | CEPH_OSD_FLAG_READ |
+		   CEPH_OSD_FLAG_IGNORE_OVERLAY,
 		   onack, NULL);
     o->target.precalc_pgid = true;
     o->target.base_pgid = pg_t(hash, oloc.pool);