osd: explicitly set the reqid when proxying the write op

This is needed as in the following scenario:
- Client sends 3 writes and a read on the same object to base tier
- Set up cache tiering
- Client retries ops and sends the 3 writes and 1 read to the cache tier
- The 3 writes finished on the base tier, say with versions v1, v2 and v3
- Cache tier proxies the 1st write, and start to promote the object for the 2nd
write, the 2nd and 3rd writes and the read are blocked
- The proxied 1st write finishes on the base tier with version v4, and returns
to cache tier. But somehow the cache tier fails to send the reply due to socket
failure injecting
- Client retries the writes and the read again, the writes are identified as
dup ops
- The promotion finishes, it copies the pg_log entries from the base tier and
put it in the cache tier's pg_log. This includes the 3 writes on the base tier
and the proxied write
- The writes dispatches after the promotion, they are identified as completed
dup ops. Cache tier replies these write ops with the version from the base tier
(v1, v2 and v3)
- In the last, the read dispatches, it reads the version of the proxied write
(v4) and replies to client
- Client complains that 'racing read got wrong version'

Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com>

diff --git a/src/osd/ReplicatedPG.cc b/src/osd/ReplicatedPG.cc
index 85dcf9d43d05e6b96b1cdfcc338d1f981ad459ed..c9710bec31c1a372723e6aaf8b1c0b4d572e8618 100644 (file)
--- a/src/osd/ReplicatedPG.cc
+++ b/src/osd/ReplicatedPG.cc
@@ -2244,7 +2244,7 @@ void ReplicatedPG::do_proxy_write(OpRequestRef op, const hobject_t& missing_oid)
   unsigned flags = CEPH_OSD_FLAG_IGNORE_CACHE | CEPH_OSD_FLAG_IGNORE_OVERLAY;
   dout(10) << __func__ << " Start proxy write for " << *m << dendl;
 
-  ProxyWriteOpRef pwop(new ProxyWriteOp(op, soid, m->ops));
+  ProxyWriteOpRef pwop(new ProxyWriteOp(op, soid, m->ops, m->get_reqid()));
   pwop->ctx = new OpContext(op, m->get_reqid(), pwop->ops, this);
   pwop->mtime = m->get_mtime();
 
@@ -2257,7 +2257,8 @@ void ReplicatedPG::do_proxy_write(OpRequestRef op, const hobject_t& missing_oid)
                                         snapc, pwop->mtime,
                                         flags, NULL,
                                         new C_OnFinisher(fin, &osd->objecter_finisher),
-                                        &pwop->user_version);
+                                        &pwop->user_version,
+                                        pwop->reqid);
   fin->tid = tid;
   pwop->objecter_tid = tid;
   proxywrite_ops[tid] = pwop;

diff --git a/src/osd/ReplicatedPG.h b/src/osd/ReplicatedPG.h
index ec64b21a4a6b1260bbdba7576d558864925e6a1a..cc3ce84a4b1a82c2ab468c7b07c9b6fc9cbfc21c 100644 (file)
--- a/src/osd/ReplicatedPG.h
+++ b/src/osd/ReplicatedPG.h
@@ -267,12 +267,14 @@ public:
     bool sent_ack;
     utime_t mtime;
     bool canceled;
+    osd_reqid_t &reqid;
 
-    ProxyWriteOp(OpRequestRef _op, hobject_t oid, vector<OSDOp>& _ops)
+    ProxyWriteOp(OpRequestRef _op, hobject_t oid, vector<OSDOp>& _ops, osd_reqid_t _reqid)
       : ctx(NULL), op(_op), soid(oid),
         objecter_tid(0), ops(_ops),
        user_version(0), sent_disk(false),
-       sent_ack(false), canceled(false) { }
+       sent_ack(false), canceled(false),
+        reqid(_reqid) { }
   };
   typedef boost::shared_ptr<ProxyWriteOp> ProxyWriteOpRef;