Merge pull request #23629 from wangxiaoguang/fix_deep_scrub

os/bluestore: fix deep-scrub operation againest disk silent errors

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: David Zafman <dzafman@redhat.com>

src/include/rados.h

@@ -470,6 +470,7 @@ enum {
 	CEPH_OSD_OP_FLAG_FADVISE_DONTNEED   = 0x20,/* data will not be accessed in the near future */
 	CEPH_OSD_OP_FLAG_FADVISE_NOCACHE   = 0x40, /* data will be accessed only once by this client */
 	CEPH_OSD_OP_FLAG_WITH_REFERENCE   = 0x80, /* need reference couting */
+	CEPH_OSD_OP_FLAG_BYPASS_CLEAN_CACHE = 0x100, /* bypass ObjectStore cache, mainly for deep-scrub */
 };
 
 #define EOLDSNAPC    85  /* ORDERSNAP flag set; writer has old snapc*/

src/os/bluestore/BlueStore.cc

@@ -1306,7 +1306,8 @@ void BlueStore::BufferSpace::read(
   uint32_t offset,
   uint32_t length,
   BlueStore::ready_regions_t& res,
-  interval_set<uint32_t>& res_intervals)
+  interval_set<uint32_t>& res_intervals,
+  int flags)
 {
   res.clear();
   res_intervals.clear();
@@ -1320,7 +1321,13 @@ void BlueStore::BufferSpace::read(
          ++i) {
       Buffer *b = i->second.get();
       ceph_assert(b->end() > offset);
-      if (b->is_writing() || b->is_clean()) {
+
+      bool val = false;
+      if (flags & BYPASS_CLEAN_CACHE)
+        val = b->is_writing();
+      else
+        val = b->is_writing() || b->is_clean();
+      if (val) {
         if (b->offset < offset) {
 	  uint32_t skip = offset - b->offset;
 	  uint32_t l = min(length, b->length - skip);
@@ -7408,6 +7415,7 @@ int BlueStore::_do_read(
 {
   FUNCTRACE(cct);
   int r = 0;
+  int read_cache_policy = 0; // do not bypass clean or dirty cache
 
   dout(20) << __func__ << " 0x" << std::hex << offset << "~" << length
            << " size 0x" << o->onode.size << " (" << std::dec
@@ -7442,6 +7450,13 @@ int BlueStore::_do_read(
 
   ready_regions_t ready_regions;
 
+  // for deep-scrub, we only read dirty cache and bypass clean cache in
+  // order to read underlying block device in case there are silent disk errors.
+  if (op_flags & CEPH_OSD_OP_FLAG_BYPASS_CLEAN_CACHE) {
+    dout(20) << __func__ << " will bypass cache and do direct read" << dendl;
+    read_cache_policy = BufferSpace::BYPASS_CLEAN_CACHE;
+  }
+
   // build blob-wise list to of stuff read (that isn't cached)
   blobs2read_t blobs2read;
   unsigned left = length;
@@ -7467,7 +7482,8 @@ int BlueStore::_do_read(
     ready_regions_t cache_res;
     interval_set<uint32_t> cache_interval;
     bptr->shared_blob->bc.read(
-      bptr->shared_blob->get_cache(), b_off, b_len, cache_res, cache_interval);
+      bptr->shared_blob->get_cache(), b_off, b_len, cache_res, cache_interval,
+      read_cache_policy);
     dout(20) << __func__ << "  blob " << *bptr << std::hex
 	     << " need 0x" << b_off << "~" << b_len
 	     << " cache has 0x" << cache_interval

src/os/bluestore/BlueStore.h

@@ -247,6 +247,10 @@ public:
 
   /// map logical extent range (object) onto buffers
   struct BufferSpace {
+    enum {
+      BYPASS_CLEAN_CACHE = 0x1,  // bypass clean cache
+    };
+
     typedef boost::intrusive::list<
       Buffer,
       boost::intrusive::member_hook<
@@ -346,7 +350,8 @@ public:
 
     void read(Cache* cache, uint32_t offset, uint32_t length,
 	      BlueStore::ready_regions_t& res,
-	      interval_set<uint32_t>& res_intervals);
+	      interval_set<uint32_t>& res_intervals,
+	      int flags = 0);
 
     void truncate(Cache* cache, uint32_t offset) {
       discard(cache, offset, (uint32_t)-1 - offset);

src/osd/ReplicatedBackend.cc

@@ -598,7 +598,8 @@ int ReplicatedBackend::be_deep_scrub(
   dout(10) << __func__ << " " << poid << " pos " << pos << dendl;
   int r;
   uint32_t fadvise_flags = CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL |
-                           CEPH_OSD_OP_FLAG_FADVISE_DONTNEED;
+                           CEPH_OSD_OP_FLAG_FADVISE_DONTNEED |
+                           CEPH_OSD_OP_FLAG_BYPASS_CLEAN_CACHE;
 
   utime_t sleeptime;
   sleeptime.set_from_double(cct->_conf->osd_debug_deep_scrub_sleep);

src/osd/osd_types.cc

@@ -100,6 +100,12 @@ const char * ceph_osd_op_flag_name(unsigned flag)
     case CEPH_OSD_OP_FLAG_FADVISE_NOCACHE:
       name = "fadvise_nocache";
       break;
+    case CEPH_OSD_OP_FLAG_WITH_REFERENCE:
+      name = "with_reference";
+      break;
+    case CEPH_OSD_OP_FLAG_BYPASS_CLEAN_CACHE:
+      name = "bypass_clean_cache";
+      break;
     default:
       name = "???";
   };