diff mbox

[17/39] mds: send resolve acks after master updates are safely logged

Message ID 1363531902-24909-18-git-send-email-zheng.z.yan@intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Yan, Zheng March 17, 2013, 2:51 p.m. UTC 
From: "Yan, Zheng" <zheng.z.yan@intel.com>

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
---
 src/mds/MDCache.cc | 33 +++++++++++++++++++++++++++++----
 src/mds/MDCache.h  |  7 ++++++-
 src/mds/Server.cc  |  9 +++++++++
 src/mds/journal.cc |  2 +-
 4 files changed, 45 insertions(+), 6 deletions(-)

Comments

Gregory Farnum March 20, 2013, 10:58 p.m. UTC | #1 
Reviewed-by: Greg Farnum <greg@inktank.com>

On Sun, Mar 17, 2013 at 7:51 AM, Yan, Zheng <zheng.z.yan@intel.com> wrote:
> From: "Yan, Zheng" <zheng.z.yan@intel.com>
>
> Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
> ---
>  src/mds/MDCache.cc | 33 +++++++++++++++++++++++++++++----
>  src/mds/MDCache.h  |  7 ++++++-
>  src/mds/Server.cc  |  9 +++++++++
>  src/mds/journal.cc |  2 +-
>  4 files changed, 45 insertions(+), 6 deletions(-)
>
> diff --git a/src/mds/MDCache.cc b/src/mds/MDCache.cc
> index 6853bf1..9b37b1e 100644
> --- a/src/mds/MDCache.cc
> +++ b/src/mds/MDCache.cc
> @@ -2177,6 +2177,17 @@ void MDCache::committed_master_slave(metareqid_t r, int from)
>      log_master_commit(r);
>  }
>
> +void MDCache::logged_master_update(metareqid_t reqid)
> +{
> +  dout(10) << "logged_master_update " << reqid << dendl;
> +  assert(uncommitted_masters.count(reqid));
> +  uncommitted_masters[reqid].safe = true;
> +  if (pending_masters.count(reqid)) {
> +    pending_masters.erase(reqid);
> +    if (pending_masters.empty())
> +      process_delayed_resolve();
> +  }
> +}
>
>  /*
>   * The mds could crash after receiving all slaves' commit acknowledgement,
> @@ -2764,8 +2775,23 @@ void MDCache::handle_resolve(MMDSResolve *m)
>      return;
>    }
>
> +  discard_delayed_resolve(from);
> +
>    // ambiguous slave requests?
>    if (!m->slave_requests.empty()) {
> +    for (vector<metareqid_t>::iterator p = m->slave_requests.begin();
> +        p != m->slave_requests.end();
> +        ++p) {
> +      if (uncommitted_masters.count(*p) && !uncommitted_masters[*p].safe)
> +       pending_masters.insert(*p);
> +    }
> +
> +    if (!pending_masters.empty()) {
> +      dout(10) << " still have pending updates, delay processing slave resolve" << dendl;
> +      delayed_resolve[from] = m;
> +      return;
> +    }
> +
>      MMDSResolveAck *ack = new MMDSResolveAck;
>      for (vector<metareqid_t>::iterator p = m->slave_requests.begin();
>          p != m->slave_requests.end();
> @@ -2788,7 +2814,6 @@ void MDCache::handle_resolve(MMDSResolve *m)
>
>    if (!resolve_ack_gather.empty() || !need_resolve_rollback.empty()) {
>      dout(10) << "delay processing subtree resolve" << dendl;
> -    discard_delayed_resolve(from);
>      delayed_resolve[from] = m;
>      return;
>    }
> @@ -2883,10 +2908,10 @@ void MDCache::handle_resolve(MMDSResolve *m)
>  void MDCache::process_delayed_resolve()
>  {
>    dout(10) << "process_delayed_resolve" << dendl;
> -  for (map<int, MMDSResolve *>::iterator p = delayed_resolve.begin();
> -       p != delayed_resolve.end(); ++p)
> +  map<int, MMDSResolve*> tmp;
> +  tmp.swap(delayed_resolve);
> +  for (map<int, MMDSResolve*>::iterator p = tmp.begin(); p != tmp.end(); ++p)
>      handle_resolve(p->second);
> -  delayed_resolve.clear();
>  }
>
>  void MDCache::discard_delayed_resolve(int who)
> diff --git a/src/mds/MDCache.h b/src/mds/MDCache.h
> index 379f715..8f262b9 100644
> --- a/src/mds/MDCache.h
> +++ b/src/mds/MDCache.h
> @@ -281,14 +281,16 @@ public:
>                                 snapid_t follows=CEPH_NOSNAP);
>
>    // slaves
> -  void add_uncommitted_master(metareqid_t reqid, LogSegment *ls, set<int> &slaves) {
> +  void add_uncommitted_master(metareqid_t reqid, LogSegment *ls, set<int> &slaves, bool safe=false) {
>      uncommitted_masters[reqid].ls = ls;
>      uncommitted_masters[reqid].slaves = slaves;
> +    uncommitted_masters[reqid].safe = safe;
>    }
>    void wait_for_uncommitted_master(metareqid_t reqid, Context *c) {
>      uncommitted_masters[reqid].waiters.push_back(c);
>    }
>    void log_master_commit(metareqid_t reqid);
> +  void logged_master_update(metareqid_t reqid);
>    void _logged_master_commit(metareqid_t reqid, LogSegment *ls, list<Context*> &waiters);
>    void committed_master_slave(metareqid_t r, int from);
>    void finish_committed_masters();
> @@ -320,9 +322,12 @@ protected:
>      set<int> slaves;
>      LogSegment *ls;
>      list<Context*> waiters;
> +    bool safe;
>    };
>    map<metareqid_t, umaster>                 uncommitted_masters;         // master: req -> slave set
>
> +  set<metareqid_t>             pending_masters;
> +
>    //map<metareqid_t, bool>     ambiguous_slave_updates;         // for log trimming.
>    //map<metareqid_t, Context*> waiting_for_slave_update_commit;
>    friend class ESlaveUpdate;
> diff --git a/src/mds/Server.cc b/src/mds/Server.cc
> index 8e89e4c..1330f11 100644
> --- a/src/mds/Server.cc
> +++ b/src/mds/Server.cc
> @@ -4463,6 +4463,9 @@ void Server::_link_remote_finish(MDRequest *mdr, bool inc,
>
>    assert(g_conf->mds_kill_link_at != 3);
>
> +  if (!mdr->more()->witnessed.empty())
> +    mdcache->logged_master_update(mdr->reqid);
> +
>    if (inc) {
>      // link the new dentry
>      dn->pop_projected_linkage();
> @@ -5073,6 +5076,9 @@ void Server::_unlink_local_finish(MDRequest *mdr,
>  {
>    dout(10) << "_unlink_local_finish " << *dn << dendl;
>
> +  if (!mdr->more()->witnessed.empty())
> +    mdcache->logged_master_update(mdr->reqid);
> +
>    // unlink main dentry
>    dn->get_dir()->unlink_inode(dn);
>    dn->pop_projected_linkage();
> @@ -5881,6 +5887,9 @@ void Server::_rename_finish(MDRequest *mdr, CDentry *srcdn, CDentry *destdn, CDe
>  {
>    dout(10) << "_rename_finish " << *mdr << dendl;
>
> +  if (!mdr->more()->witnessed.empty())
> +    mdcache->logged_master_update(mdr->reqid);
> +
>    // apply
>    _rename_apply(mdr, srcdn, destdn, straydn);
>
> diff --git a/src/mds/journal.cc b/src/mds/journal.cc
> index 3375e40..6475eec 100644
> --- a/src/mds/journal.cc
> +++ b/src/mds/journal.cc
> @@ -1738,7 +1738,7 @@ void EUpdate::replay(MDS *mds)
>      dout(10) << "EUpdate.replay " << reqid << " had slaves, expecting a matching ECommitted" << dendl;
>      _segment->uncommitted_masters.insert(reqid);
>      set<int> slaves;
> -    mds->mdcache->add_uncommitted_master(reqid, _segment, slaves);
> +    mds->mdcache->add_uncommitted_master(reqid, _segment, slaves, true);
>    }
>
>    if (client_map.length()) {
> --
> 1.7.11.7
>
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/src/mds/MDCache.cc b/src/mds/MDCache.cc
index 6853bf1..9b37b1e 100644
--- a/src/mds/MDCache.cc
+++ b/src/mds/MDCache.cc
@@ -2177,6 +2177,17 @@  void MDCache::committed_master_slave(metareqid_t r, int from)
     log_master_commit(r);
 }
 
+void MDCache::logged_master_update(metareqid_t reqid)
+{
+  dout(10) << "logged_master_update " << reqid << dendl;
+  assert(uncommitted_masters.count(reqid));
+  uncommitted_masters[reqid].safe = true;
+  if (pending_masters.count(reqid)) {
+    pending_masters.erase(reqid);
+    if (pending_masters.empty())
+      process_delayed_resolve();
+  }
+}
 
 /*
  * The mds could crash after receiving all slaves' commit acknowledgement,
@@ -2764,8 +2775,23 @@  void MDCache::handle_resolve(MMDSResolve *m)
     return;
   }
 
+  discard_delayed_resolve(from);
+
   // ambiguous slave requests?
   if (!m->slave_requests.empty()) {
+    for (vector<metareqid_t>::iterator p = m->slave_requests.begin();
+	 p != m->slave_requests.end();
+	 ++p) {
+      if (uncommitted_masters.count(*p) && !uncommitted_masters[*p].safe)
+	pending_masters.insert(*p);
+    }
+
+    if (!pending_masters.empty()) {
+      dout(10) << " still have pending updates, delay processing slave resolve" << dendl;
+      delayed_resolve[from] = m;
+      return;
+    }
+
     MMDSResolveAck *ack = new MMDSResolveAck;
     for (vector<metareqid_t>::iterator p = m->slave_requests.begin();
 	 p != m->slave_requests.end();
@@ -2788,7 +2814,6 @@  void MDCache::handle_resolve(MMDSResolve *m)
 
   if (!resolve_ack_gather.empty() || !need_resolve_rollback.empty()) {
     dout(10) << "delay processing subtree resolve" << dendl;
-    discard_delayed_resolve(from);
     delayed_resolve[from] = m;
     return;
   }
@@ -2883,10 +2908,10 @@  void MDCache::handle_resolve(MMDSResolve *m)
 void MDCache::process_delayed_resolve()
 {
   dout(10) << "process_delayed_resolve" << dendl;
-  for (map<int, MMDSResolve *>::iterator p = delayed_resolve.begin();
-       p != delayed_resolve.end(); ++p)
+  map<int, MMDSResolve*> tmp;
+  tmp.swap(delayed_resolve);
+  for (map<int, MMDSResolve*>::iterator p = tmp.begin(); p != tmp.end(); ++p)
     handle_resolve(p->second);
-  delayed_resolve.clear();
 }
 
 void MDCache::discard_delayed_resolve(int who)
diff --git a/src/mds/MDCache.h b/src/mds/MDCache.h
index 379f715..8f262b9 100644
--- a/src/mds/MDCache.h
+++ b/src/mds/MDCache.h
@@ -281,14 +281,16 @@  public:
 				snapid_t follows=CEPH_NOSNAP);
 
   // slaves
-  void add_uncommitted_master(metareqid_t reqid, LogSegment *ls, set<int> &slaves) {
+  void add_uncommitted_master(metareqid_t reqid, LogSegment *ls, set<int> &slaves, bool safe=false) {
     uncommitted_masters[reqid].ls = ls;
     uncommitted_masters[reqid].slaves = slaves;
+    uncommitted_masters[reqid].safe = safe;
   }
   void wait_for_uncommitted_master(metareqid_t reqid, Context *c) {
     uncommitted_masters[reqid].waiters.push_back(c);
   }
   void log_master_commit(metareqid_t reqid);
+  void logged_master_update(metareqid_t reqid);
   void _logged_master_commit(metareqid_t reqid, LogSegment *ls, list<Context*> &waiters);
   void committed_master_slave(metareqid_t r, int from);
   void finish_committed_masters();
@@ -320,9 +322,12 @@  protected:
     set<int> slaves;
     LogSegment *ls;
     list<Context*> waiters;
+    bool safe;
   };
   map<metareqid_t, umaster>                 uncommitted_masters;         // master: req -> slave set
 
+  set<metareqid_t>		pending_masters;
+
   //map<metareqid_t, bool>     ambiguous_slave_updates;         // for log trimming.
   //map<metareqid_t, Context*> waiting_for_slave_update_commit;
   friend class ESlaveUpdate;
diff --git a/src/mds/Server.cc b/src/mds/Server.cc
index 8e89e4c..1330f11 100644
--- a/src/mds/Server.cc
+++ b/src/mds/Server.cc
@@ -4463,6 +4463,9 @@  void Server::_link_remote_finish(MDRequest *mdr, bool inc,
 
   assert(g_conf->mds_kill_link_at != 3);
 
+  if (!mdr->more()->witnessed.empty())
+    mdcache->logged_master_update(mdr->reqid);
+
   if (inc) {
     // link the new dentry
     dn->pop_projected_linkage();
@@ -5073,6 +5076,9 @@  void Server::_unlink_local_finish(MDRequest *mdr,
 {
   dout(10) << "_unlink_local_finish " << *dn << dendl;
 
+  if (!mdr->more()->witnessed.empty())
+    mdcache->logged_master_update(mdr->reqid);
+
   // unlink main dentry
   dn->get_dir()->unlink_inode(dn);
   dn->pop_projected_linkage();
@@ -5881,6 +5887,9 @@  void Server::_rename_finish(MDRequest *mdr, CDentry *srcdn, CDentry *destdn, CDe
 {
   dout(10) << "_rename_finish " << *mdr << dendl;
 
+  if (!mdr->more()->witnessed.empty())
+    mdcache->logged_master_update(mdr->reqid);
+
   // apply
   _rename_apply(mdr, srcdn, destdn, straydn);
 
diff --git a/src/mds/journal.cc b/src/mds/journal.cc
index 3375e40..6475eec 100644
--- a/src/mds/journal.cc
+++ b/src/mds/journal.cc
@@ -1738,7 +1738,7 @@  void EUpdate::replay(MDS *mds)
     dout(10) << "EUpdate.replay " << reqid << " had slaves, expecting a matching ECommitted" << dendl;
     _segment->uncommitted_masters.insert(reqid);
     set<int> slaves;
-    mds->mdcache->add_uncommitted_master(reqid, _segment, slaves);
+    mds->mdcache->add_uncommitted_master(reqid, _segment, slaves, true);
   }
   
   if (client_map.length()) {