osd, OSDMonitor, qa: mark ec overwrites non-experimental

Keep the pool flag around so we can distinguish between a pool that
should maintain hashes for each chunk, and a missing one is a bug, vs
an overwrites pool where we rely on bluestore checksums for detecting
corruption.

Signed-off-by: Josh Durgin <jdurgin@redhat.com>

diff --git a/qa/suites/krbd/rbd-nomount/tasks/krbd_data_pool.yaml b/qa/suites/krbd/rbd-nomount/tasks/krbd_data_pool.yaml
index 24985fb79d5260adce51dc005bf6e51f30ab95f1..35b9d67ebff8320fd877edee451fb8ccc69dae15 100644 (file)
--- a/qa/suites/krbd/rbd-nomount/tasks/krbd_data_pool.yaml
+++ b/qa/suites/krbd/rbd-nomount/tasks/krbd_data_pool.yaml
@@ -1,9 +1,3 @@
-overrides:
-  ceph:
-    conf:
-      global:
-        enable experimental unrecoverable data corrupting features: debug_white_box_testing_ec_overwrites
-
 tasks:
 - workunit:
     clients:

diff --git a/qa/suites/rados/thrash-erasure-code/workloads/ec-pool-snaps-few-objects-overwrites.yaml b/qa/suites/rados/thrash-erasure-code/workloads/ec-pool-snaps-few-objects-overwrites.yaml
index 7d494fdad985990585cfd1f3fa5648c4144f3040..d2ad70a57ecbf5fb74b31eb2bae1870abaaf07b0 100644 (file)
--- a/qa/suites/rados/thrash-erasure-code/workloads/ec-pool-snaps-few-objects-overwrites.yaml
+++ b/qa/suites/rados/thrash-erasure-code/workloads/ec-pool-snaps-few-objects-overwrites.yaml
@@ -12,7 +12,7 @@ tasks:
     objects: 50
     pool_snaps: true
     ec_pool: true
-    erasure_code_use_hacky_overwrites: true
+    erasure_code_use_overwrites: true
     op_weights:
       read: 100
       write: 100

diff --git a/qa/suites/rados/thrash-erasure-code/workloads/ec-small-objects-fast-read-overwrites.yaml b/qa/suites/rados/thrash-erasure-code/workloads/ec-small-objects-fast-read-overwrites.yaml
index c2e16487572f7f899e21f83100b33b331ba89518..b3f831b778eae6f3e17773e635fd0bdc246a2b3d 100644 (file)
--- a/qa/suites/rados/thrash-erasure-code/workloads/ec-small-objects-fast-read-overwrites.yaml
+++ b/qa/suites/rados/thrash-erasure-code/workloads/ec-small-objects-fast-read-overwrites.yaml
@@ -14,7 +14,7 @@ tasks:
     objects: 1024
     size: 16384
     ec_pool: true
-    erasure_code_use_hacky_overwrites: true
+    erasure_code_use_overwrites: true
     fast_read: true
     op_weights:
       read: 100

diff --git a/qa/suites/rados/thrash-erasure-code/workloads/ec-small-objects-overwrites.yaml b/qa/suites/rados/thrash-erasure-code/workloads/ec-small-objects-overwrites.yaml
index 80a581721699f14a252627f4b68b3aa712239a99..9baacef48906d32ca86c088bd487acbc8dd37d30 100644 (file)
--- a/qa/suites/rados/thrash-erasure-code/workloads/ec-small-objects-overwrites.yaml
+++ b/qa/suites/rados/thrash-erasure-code/workloads/ec-small-objects-overwrites.yaml
@@ -14,7 +14,7 @@ tasks:
     objects: 1024
     size: 16384
     ec_pool: true
-    erasure_code_use_hacky_overwrites: true
+    erasure_code_use_overwrites: true
     op_weights:
       read: 100
       write: 100

diff --git a/qa/suites/rados/thrash-erasure-code/workloads/ec-snaps-few-objects-overwrites.yaml b/qa/suites/rados/thrash-erasure-code/workloads/ec-snaps-few-objects-overwrites.yaml
index 00263c414cce54ad7d2f67d90f3956588e8ab7cb..b7c53819938256024ec4af0d73d1fabe00dc453b 100644 (file)
--- a/qa/suites/rados/thrash-erasure-code/workloads/ec-snaps-few-objects-overwrites.yaml
+++ b/qa/suites/rados/thrash-erasure-code/workloads/ec-snaps-few-objects-overwrites.yaml
@@ -11,7 +11,7 @@ tasks:
     ops: 4000
     objects: 50
     ec_pool: true
-    erasure_code_use_hacky_overwrites: true
+    erasure_code_use_overwrites: true
     op_weights:
       read: 100
       write: 100

diff --git a/qa/suites/rbd/cli/pool/ec-data-pool.yaml b/qa/suites/rbd/cli/pool/ec-data-pool.yaml
index a6c35e57ae30f1848abfd4912447c9d75b29a90b..523d7450afb883d303a1311aece9903b18d09162 100644 (file)
--- a/qa/suites/rbd/cli/pool/ec-data-pool.yaml
+++ b/qa/suites/rbd/cli/pool/ec-data-pool.yaml
@@ -3,12 +3,10 @@ tasks:
     client.0:
       - sudo ceph osd erasure-code-profile set teuthologyprofile ruleset-failure-domain=osd m=1 k=2
       - sudo ceph osd pool create datapool 4 4 erasure teuthologyprofile
-      - sudo ceph osd pool set datapool debug_white_box_testing_ec_overwrites true
+      - sudo ceph osd pool set datapool allow_ec_overwrites true
 
 overrides:
   ceph:
     conf:
-      global:
-        enable experimental unrecoverable data corrupting features: debug_white_box_testing_ec_overwrites
       client:
         rbd default data pool: datapool

diff --git a/qa/suites/rbd/librbd/pool/ec-data-pool.yaml b/qa/suites/rbd/librbd/pool/ec-data-pool.yaml
index a6c35e57ae30f1848abfd4912447c9d75b29a90b..523d7450afb883d303a1311aece9903b18d09162 100644 (file)
--- a/qa/suites/rbd/librbd/pool/ec-data-pool.yaml
+++ b/qa/suites/rbd/librbd/pool/ec-data-pool.yaml
@@ -3,12 +3,10 @@ tasks:
     client.0:
       - sudo ceph osd erasure-code-profile set teuthologyprofile ruleset-failure-domain=osd m=1 k=2
       - sudo ceph osd pool create datapool 4 4 erasure teuthologyprofile
-      - sudo ceph osd pool set datapool debug_white_box_testing_ec_overwrites true
+      - sudo ceph osd pool set datapool allow_ec_overwrites true
 
 overrides:
   ceph:
     conf:
-      global:
-        enable experimental unrecoverable data corrupting features: debug_white_box_testing_ec_overwrites
       client:
         rbd default data pool: datapool

diff --git a/qa/suites/rbd/qemu/pool/ec-data-pool.yaml b/qa/suites/rbd/qemu/pool/ec-data-pool.yaml
index a6c35e57ae30f1848abfd4912447c9d75b29a90b..523d7450afb883d303a1311aece9903b18d09162 100644 (file)
--- a/qa/suites/rbd/qemu/pool/ec-data-pool.yaml
+++ b/qa/suites/rbd/qemu/pool/ec-data-pool.yaml
@@ -3,12 +3,10 @@ tasks:
     client.0:
       - sudo ceph osd erasure-code-profile set teuthologyprofile ruleset-failure-domain=osd m=1 k=2
       - sudo ceph osd pool create datapool 4 4 erasure teuthologyprofile
-      - sudo ceph osd pool set datapool debug_white_box_testing_ec_overwrites true
+      - sudo ceph osd pool set datapool allow_ec_overwrites true
 
 overrides:
   ceph:
     conf:
-      global:
-        enable experimental unrecoverable data corrupting features: debug_white_box_testing_ec_overwrites
       client:
         rbd default data pool: datapool

diff --git a/qa/tasks/ceph_manager.py b/qa/tasks/ceph_manager.py
index c6d5ef4691d612679daed147f744da43dcc86fb0..f4c9ebc7e9dc1bea89e3911dbdf86dcfeb1d1bd5 100644 (file)
--- a/qa/tasks/ceph_manager.py
+++ b/qa/tasks/ceph_manager.py
@@ -1479,7 +1479,7 @@ class CephManager:
     def create_pool_with_unique_name(self, pg_num=16,
                                      erasure_code_profile_name=None,
                                      min_size=None,
-                                     erasure_code_use_hacky_overwrites=False):
+                                     erasure_code_use_overwrites=False):
         """
         Create a pool named unique_pool_X where X is unique.
         """
@@ -1492,7 +1492,7 @@ class CephManager:
                 pg_num,
                 erasure_code_profile_name=erasure_code_profile_name,
                 min_size=min_size,
-                erasure_code_use_hacky_overwrites=erasure_code_use_hacky_overwrites)
+                erasure_code_use_overwrites=erasure_code_use_overwrites)
         return name
 
     @contextlib.contextmanager
@@ -1504,15 +1504,14 @@ class CephManager:
     def create_pool(self, pool_name, pg_num=16,
                     erasure_code_profile_name=None,
                     min_size=None,
-                    erasure_code_use_hacky_overwrites=False):
+                    erasure_code_use_overwrites=False):
         """
         Create a pool named from the pool_name parameter.
         :param pool_name: name of the pool being created.
         :param pg_num: initial number of pgs.
         :param erasure_code_profile_name: if set and !None create an
                                           erasure coded pool using the profile
-        :param erasure_code_use_hacky_overwrites: if true, use the hacky
-                                                  overwrites mode
+        :param erasure_code_use_overwrites: if true, allow overwrites
         """
         with self.lock:
             assert isinstance(pool_name, basestring)
@@ -1531,10 +1530,10 @@ class CephManager:
                     'osd', 'pool', 'set', pool_name,
                     'min_size',
                     str(min_size))
-            if erasure_code_use_hacky_overwrites:
+            if erasure_code_use_overwrites:
                 self.raw_cluster_cmd(
                     'osd', 'pool', 'set', pool_name,
-                    'debug_white_box_testing_ec_overwrites',
+                    'allow_ec_overwrites',
                     'true')
             self.pools[pool_name] = pg_num
         time.sleep(1)

diff --git a/qa/tasks/rados.py b/qa/tasks/rados.py
index 15a35e5988ddc46bf284254533085ec91c9a44bc..4e4f746cb05e843ed323322e8b84f8c628550f35 100644 (file)
--- a/qa/tasks/rados.py
+++ b/qa/tasks/rados.py
@@ -55,9 +55,7 @@ def task(ctx, config):
               rollback: 2
               snap_remove: 0
             ec_pool: create an ec pool, defaults to False
-            erasure_code_use_hacky_overwrites: use the whitebox
-                                               testing experimental
-                                               overwrites mode
+            erasure_code_use_overwrites: test overwrites, default false
             erasure_code_profile:
               name: teuthologyprofile
               k: 2
@@ -139,7 +137,7 @@ def task(ctx, config):
         'ceph_test_rados']
     if config.get('ec_pool', False):
         args.extend(['--no-omap'])
-        if config.get('erasure_code_use_hacky_overwrites', False):
+        if config.get('erasure_code_use_overwrites', False):
             args.extend(['--no-sparse'])
         else:
             args.extend(['--ec-pool'])
@@ -230,8 +228,8 @@ def task(ctx, config):
                 else:
                     pool = manager.create_pool_with_unique_name(
                         erasure_code_profile_name=profile_name,
-                        erasure_code_use_hacky_overwrites=
-                          config.get('erasure_code_use_hacky_overwrites', False)
+                        erasure_code_use_overwrites=
+                          config.get('erasure_code_use_overwrites', False)
                     )
                     created_pools.append(pool)
                     if config.get('fast_read', False):

diff --git a/qa/workunits/rbd/krbd_data_pool.sh b/qa/workunits/rbd/krbd_data_pool.sh
index 2c83d34ca874341874fd65fe22a6df4798c30573..0b7b6c933ec8e680b9b7537bed1a5508cb9b3d68 100755 (executable)
--- a/qa/workunits/rbd/krbd_data_pool.sh
+++ b/qa/workunits/rbd/krbd_data_pool.sh
@@ -84,7 +84,7 @@ function count_data_objects() {
 ceph osd pool create repdata 24 24
 ceph osd erasure-code-profile set teuthologyprofile ruleset-failure-domain=osd m=1 k=2
 ceph osd pool create ecdata 24 24 erasure teuthologyprofile
-ceph osd pool set ecdata debug_white_box_testing_ec_overwrites true
+ceph osd pool set ecdata allow_ec_overwrites true
 ceph osd pool create rbdnonzero 24 24
 ceph osd pool create clonesonly 24 24
 

diff --git a/src/mon/FSCommands.cc b/src/mon/FSCommands.cc
index cc2dfe04c0b2fb077cea3a0b8ee4a3252a43b813..630736c398990672880d5b1de126b65bcabd6c39 100644 (file)
--- a/src/mon/FSCommands.cc
+++ b/src/mon/FSCommands.cc
@@ -849,7 +849,7 @@ int FileSystemCommandHandler::_check_pool(
          << " is an erasure-coded pool.  Use of erasure-coded pools"
          << " for CephFS metadata is not permitted";
     return -EINVAL;
-  } else if (pool->is_erasure() && !pool->is_hacky_ecoverwrites()) {
+  } else if (pool->is_erasure() && !pool->allows_ecoverwrites()) {
     // non-overwriteable EC pools are only acceptable with a cache tier overlay
     if (!pool->has_tiers() || !pool->has_read_tier() || !pool->has_write_tier()) {
       *ss << "pool '" << pool_name << "' (id '" << pool_id << "')"

diff --git a/src/mon/MonCommands.h b/src/mon/MonCommands.h
index 3945e4b34800f342a861f29a79346d04bb1456b5..9506814f7be91b02d69fa9cf328e21a45d1c5586 100644 (file)
--- a/src/mon/MonCommands.h
+++ b/src/mon/MonCommands.h
@@ -737,7 +737,7 @@ COMMAND("osd pool get " \
        "get pool parameter <var>", "osd", "r", "cli,rest")
 COMMAND("osd pool set " \
        "name=pool,type=CephPoolname " \
-       "name=var,type=CephChoices,strings=size|min_size|crash_replay_interval|pg_num|pgp_num|crush_rule|crush_ruleset|hashpspool|nodelete|nopgchange|nosizechange|write_fadvise_dontneed|noscrub|nodeep-scrub|hit_set_type|hit_set_period|hit_set_count|hit_set_fpp|use_gmt_hitset|debug_fake_ec_pool|target_max_bytes|target_max_objects|cache_target_dirty_ratio|cache_target_dirty_high_ratio|cache_target_full_ratio|cache_min_flush_age|cache_min_evict_age|auid|min_read_recency_for_promote|min_write_recency_for_promote|fast_read|hit_set_grade_decay_rate|hit_set_search_last_n|scrub_min_interval|scrub_max_interval|deep_scrub_interval|recovery_priority|recovery_op_priority|scrub_priority|compression_mode|compression_algorithm|compression_required_ratio|compression_max_blob_size|compression_min_blob_size|csum_type|csum_min_block|csum_max_block|debug_white_box_testing_ec_overwrites " \
+       "name=var,type=CephChoices,strings=size|min_size|crash_replay_interval|pg_num|pgp_num|crush_rule|crush_ruleset|hashpspool|nodelete|nopgchange|nosizechange|write_fadvise_dontneed|noscrub|nodeep-scrub|hit_set_type|hit_set_period|hit_set_count|hit_set_fpp|use_gmt_hitset|debug_fake_ec_pool|target_max_bytes|target_max_objects|cache_target_dirty_ratio|cache_target_dirty_high_ratio|cache_target_full_ratio|cache_min_flush_age|cache_min_evict_age|auid|min_read_recency_for_promote|min_write_recency_for_promote|fast_read|hit_set_grade_decay_rate|hit_set_search_last_n|scrub_min_interval|scrub_max_interval|deep_scrub_interval|recovery_priority|recovery_op_priority|scrub_priority|compression_mode|compression_algorithm|compression_required_ratio|compression_max_blob_size|compression_min_blob_size|csum_type|csum_min_block|csum_max_block|allow_ec_overwrites " \
        "name=val,type=CephString " \
        "name=force,type=CephChoices,strings=--yes-i-really-mean-it,req=false", \
        "set pool parameter <var> to <val>", "osd", "rw", "cli,rest")

diff --git a/src/mon/OSDMonitor.cc b/src/mon/OSDMonitor.cc
index 07a99f23724920e710e2968eb801f157fdab3cb6..5cdbac9866ccb053e0b391af6e197d181ba050df 100644 (file)
--- a/src/mon/OSDMonitor.cc
+++ b/src/mon/OSDMonitor.cc
@@ -5768,18 +5768,13 @@ int OSDMonitor::prepare_command_pool_set(map<string,cmd_vartype> &cmdmap,
       ss << "expecting value 'true' or '1'";
       return -EINVAL;
     }
-  } else if (var == "debug_white_box_testing_ec_overwrites") {
+  } else if (var == "allow_ec_overwrites") {
+    if (!p.is_erasure()) {
+      ss << "ec overwrites can only be enabled for an erasure coded pool";
+      return -EINVAL;
+    }
     if (val == "true" || (interr.empty() && n == 1)) {
-      if (cct->check_experimental_feature_enabled(
-           "debug_white_box_testing_ec_overwrites")) {
        p.flags |= pg_pool_t::FLAG_EC_OVERWRITES;
-      } else {
-       ss << "debug_white_box_testing_ec_overwrites is an experimental feature "
-          << "and must be enabled.  Note, this feature does not yet actually "
-          << "work.  This flag merely enables some of the preliminary support "
-          << "for testing purposes.";
-       return -ENOTSUP;
-      }
     } else if (val == "false" || (interr.empty() && n == 0)) {
       ss << "ec overwrites cannot be disabled once enabled";
       return -EINVAL;

diff --git a/src/osd/ECBackend.cc b/src/osd/ECBackend.cc
index ea285cc4e6f44162e9f98225740bd626eac2f7d9..569bb89529ecc05f7ec5aa05fcd07554f4521943 100644 (file)
--- a/src/osd/ECBackend.cc
+++ b/src/osd/ECBackend.cc
@@ -954,7 +954,7 @@ void ECBackend::handle_sub_read(
       ++i) {
     int r = 0;
     ECUtil::HashInfoRef hinfo;
-    if (!get_parent()->get_pool().is_hacky_ecoverwrites()) {
+    if (!get_parent()->get_pool().allows_ecoverwrites()) {
       hinfo = get_hash_info(i->first);
       if (!hinfo) {
        r = -EIO;
@@ -989,7 +989,7 @@ void ECBackend::handle_sub_read(
          );
       }
 
-      if (!get_parent()->get_pool().is_hacky_ecoverwrites()) {
+      if (!get_parent()->get_pool().allows_ecoverwrites()) {
        // This shows that we still need deep scrub because large enough files
        // are read in sections, so the digest check here won't be done here.
        // Do NOT check osd_read_eio_on_bad_digest here.  We need to report
@@ -1732,7 +1732,7 @@ bool ECBackend::try_state_to_reads()
 
   Op *op = &(waiting_state.front());
   if (op->requires_rmw() && pipeline_state.cache_invalid()) {
-    assert(get_parent()->get_pool().is_hacky_ecoverwrites());
+    assert(get_parent()->get_pool().allows_ecoverwrites());
     dout(20) << __func__ << ": blocking " << *op
             << " because it requires an rmw and the cache is invalid "
             << pipeline_state
@@ -1786,7 +1786,7 @@ bool ECBackend::try_state_to_reads()
   dout(10) << __func__ << ": " << *op << dendl;
 
   if (!op->remote_read.empty()) {
-    assert(get_parent()->get_pool().is_hacky_ecoverwrites());
+    assert(get_parent()->get_pool().allows_ecoverwrites());
     objects_read_async_no_cache(
       op->remote_read,
       [this, op](map<hobject_t,pair<int, extent_map> > &&results) {
@@ -1859,7 +1859,7 @@ bool ECBackend::try_reads_to_commit()
   dout(20) << __func__ << ": written: " << written << dendl;
   dout(20) << __func__ << ": op: " << *op << dendl;
 
-  if (!get_parent()->get_pool().is_hacky_ecoverwrites()) {
+  if (!get_parent()->get_pool().allows_ecoverwrites()) {
     for (auto &&i: op->log_entries) {
       if (i.requires_kraken()) {
        derr << __func__ << ": log entry " << i << " requires kraken"
@@ -2365,7 +2365,7 @@ void ECBackend::be_deep_scrub(
     o.digest_present = false;
     return;
   } else {
-    if (!get_parent()->get_pool().is_hacky_ecoverwrites()) {
+    if (!get_parent()->get_pool().allows_ecoverwrites()) {
       assert(hinfo->has_chunk_hash());
       if (hinfo->get_total_chunk_size() != pos) {
        dout(0) << "_scan_list  " << poid << " got incorrect size on read" << dendl;

diff --git a/src/osd/osd_types.h b/src/osd/osd_types.h
index 1c4e4c65a6cebbd8adc2a933a081b6492438288c..550ea8dfca310d32876807af007d9426acf2af16 100644 (file)
--- a/src/osd/osd_types.h
+++ b/src/osd/osd_types.h
@@ -1448,7 +1448,7 @@ public:
   }
   uint64_t required_alignment() const { return stripe_width; }
 
-  bool is_hacky_ecoverwrites() const {
+  bool allows_ecoverwrites() const {
     return has_flag(FLAG_EC_OVERWRITES);
   }