Release 0.5.6

- Fix operation statistics
- Fix a rebalance hang introduced in 0.5.5
- Test PG count changes with actual data moving
- Fix a possible 'unexpected pg state: 0' error during PG count change

debian/changelog

@@ -1,4 +1,4 @@
-vitastor (0.5.5-1) unstable; urgency=medium
+vitastor (0.5.6-1) unstable; urgency=medium
 
   * Bugfixes
 

debian/vitastor.Dockerfile

@@ -40,10 +40,10 @@ RUN set -e -x; \
     mkdir -p /root/packages/vitastor-$REL; \
     rm -rf /root/packages/vitastor-$REL/*; \
     cd /root/packages/vitastor-$REL; \
-    cp -r /root/vitastor vitastor-0.5.5; \
-    ln -s /root/packages/qemu-$REL/qemu-*/ vitastor-0.5.5/qemu; \
-    ln -s /root/fio-build/fio-*/ vitastor-0.5.5/fio; \
-    cd vitastor-0.5.5; \
+    cp -r /root/vitastor vitastor-0.5.6; \
+    ln -s /root/packages/qemu-$REL/qemu-*/ vitastor-0.5.6/qemu; \
+    ln -s /root/fio-build/fio-*/ vitastor-0.5.6/fio; \
+    cd vitastor-0.5.6; \
     FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
     QEMU=$(head -n1 qemu/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
     sh copy-qemu-includes.sh; \
@@ -59,8 +59,8 @@ RUN set -e -x; \
     echo "dep:fio=$FIO" > debian/substvars; \
     echo "dep:qemu=$QEMU" >> debian/substvars; \
     cd /root/packages/vitastor-$REL; \
-    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.5.5.orig.tar.xz vitastor-0.5.5; \
-    cd vitastor-0.5.5; \
+    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.5.6.orig.tar.xz vitastor-0.5.6; \
+    cd vitastor-0.5.6; \
     V=$(head -n1 debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
     DEBFULLNAME="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v "$V""$REL" "Rebuild for $REL"; \
     DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa; \

mon/mon.js

@@ -379,7 +379,7 @@ class Mon
                     }
                     if (this.verbose)
                     {
-                        console.log(e);
+                        console.log(JSON.stringify(e));
                     }
                 }
                 if (stats_changed)
@@ -974,21 +974,21 @@ class Mon
             for (const op in st.op_stats||{})
             {
                 op_stats[op] = op_stats[op] || { count: 0n, usec: 0n, bytes: 0n };
-                op_stats[op].count += BigInt(st.op_stats.count||0);
-                op_stats[op].usec += BigInt(st.op_stats.usec||0);
-                op_stats[op].bytes += BigInt(st.op_stats.bytes||0);
+                op_stats[op].count += BigInt(st.op_stats[op].count||0);
+                op_stats[op].usec += BigInt(st.op_stats[op].usec||0);
+                op_stats[op].bytes += BigInt(st.op_stats[op].bytes||0);
             }
             for (const op in st.subop_stats||{})
             {
                 subop_stats[op] = subop_stats[op] || { count: 0n, usec: 0n };
-                subop_stats[op].count += BigInt(st.subop_stats.count||0);
-                subop_stats[op].usec += BigInt(st.subop_stats.usec||0);
+                subop_stats[op].count += BigInt(st.subop_stats[op].count||0);
+                subop_stats[op].usec += BigInt(st.subop_stats[op].usec||0);
             }
             for (const op in st.recovery_stats||{})
             {
                 recovery_stats[op] = recovery_stats[op] || { count: 0n, bytes: 0n };
-                recovery_stats[op].count += BigInt(st.recovery_stats.count||0);
-                recovery_stats[op].bytes += BigInt(st.recovery_stats.bytes||0);
+                recovery_stats[op].count += BigInt(st.recovery_stats[op].count||0);
+                recovery_stats[op].bytes += BigInt(st.recovery_stats[op].bytes||0);
             }
         }
         for (const op in op_stats)

rpm/build-tarball.sh

@@ -48,4 +48,4 @@ FIO=`rpm -qi fio | perl -e 'while(<>) { /^Epoch[\s:]+(\S+)/ && print "$1:"; /^Ve
 QEMU=`rpm -qi qemu qemu-kvm | perl -e 'while(<>) { /^Epoch[\s:]+(\S+)/ && print "$1:"; /^Version[\s:]+(\S+)/ && print $1; /^Release[\s:]+(\S+)/ && print "-$1"; }'`
 perl -i -pe 's/(Requires:\s*fio)([^\n]+)?/$1 = '$FIO'/' $VITASTOR/rpm/vitastor-el$EL.spec
 perl -i -pe 's/(Requires:\s*qemu(?:-kvm)?)([^\n]+)?/$1 = '$QEMU'/' $VITASTOR/rpm/vitastor-el$EL.spec
-tar --transform 's#^#vitastor-0.5.5/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.5.5$(rpm --eval '%dist').tar.gz *
+tar --transform 's#^#vitastor-0.5.6/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.5.6$(rpm --eval '%dist').tar.gz *

rpm/vitastor-el7.Dockerfile

@@ -37,7 +37,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-0.5.5.el7.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.5.6.el7.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el7.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el7.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        0.5.5
+Version:        0.5.6
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-0.5.5.el7.tar.gz
+Source0:        vitastor-0.5.6.el7.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el8.Dockerfile

@@ -35,7 +35,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-0.5.5.el8.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.5.6.el8.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el8.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el8.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        0.5.5
+Version:        0.5.6
 Release:        1%{?dist}
 Summary:        Vitastor, a fast software-defined clustered block storage
 
 License:        Vitastor Network Public License 1.1
 URL:            https://vitastor.io/
-Source0:        vitastor-0.5.5.el8.tar.gz
+Source0:        vitastor-0.5.6.el8.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

src/blockstore_write.cpp

@@ -510,6 +510,7 @@ int blockstore_impl_t::dequeue_del(blockstore_op_t *op)
     {
         return 0;
     }
+    write_iodepth++;
     io_uring_sqe *sqe = NULL;
     if (immediate_commit != IMMEDIATE_NONE ||
         (journal_block_size - journal.in_sector_pos) < sizeof(journal_entry_del) &&

src/osd_cluster.cpp

@@ -142,7 +142,7 @@ json11::Json osd_t::get_statistics()
     }
     st["host"] = self_state["host"];
     json11::Json::object op_stats, subop_stats;
-    for (int i = 0; i <= OSD_OP_MAX; i++)
+    for (int i = OSD_OP_MIN; i <= OSD_OP_MAX; i++)
     {
         op_stats[osd_op_names[i]] = json11::Json::object {
             { "count", c_cli.stats.op_stat_count[i] },
@@ -150,7 +150,7 @@ json11::Json osd_t::get_statistics()
             { "bytes", c_cli.stats.op_stat_bytes[i] },
         };
     }
-    for (int i = 0; i <= OSD_OP_MAX; i++)
+    for (int i = OSD_OP_MIN; i <= OSD_OP_MAX; i++)
     {
         subop_stats[osd_op_names[i]] = json11::Json::object {
             { "count", c_cli.stats.subop_stat_count[i] },
@@ -593,7 +593,10 @@ void osd_t::apply_pg_config()
                     }
                     else
                     {
-                        throw std::runtime_error("Unexpected PG "+std::to_string(pg_num)+" state: "+std::to_string(pg_it->second.state));
+                        throw std::runtime_error(
+                            "Unexpected PG "+std::to_string(pool_id)+"/"+std::to_string(pg_num)+
+                            " state: "+std::to_string(pg_it->second.state)
+                        );
                     }
                 }
                 auto & pg = this->pgs[{ .pool_id = pool_id, .pg_num = pg_num }];

src/osd_flush.cpp

@@ -95,7 +95,7 @@ void osd_t::handle_flush_op(bool rollback, pool_id_t pool_id, pg_num_t pg_num, p
     {
         // This flush batch is done
         std::vector<osd_op_t*> continue_ops;
-        auto & pg = pgs[pg_id];
+        auto & pg = pgs.at(pg_id);
         auto it = pg.flush_actions.begin(), prev_it = it;
         auto erase_start = it;
         while (1)

src/osd_peering.cpp

@@ -473,7 +473,9 @@ bool osd_t::stop_pg(pg_t & pg)
         return false;
     }
     pg.state = pg.state & ~PG_ACTIVE | PG_STOPPING;
-    if (pg.inflight == 0 && !pg.flush_batch)
+    if (pg.inflight == 0 && !pg.flush_batch &&
+        // We must either forget all PG's unstable writes or wait for it to become clean
+        dirty_pgs.find({ .pool_id = pg.pool_id, .pg_num = pg.pg_num }) == dirty_pgs.end())
     {
         finish_stop_pg(pg);
     }

src/osd_primary.cpp

@@ -103,7 +103,7 @@ void osd_t::continue_primary_read(osd_op_t *cur_op)
     if (op_data->st == 1)      goto resume_1;
     else if (op_data->st == 2) goto resume_2;
     {
-        auto & pg = pgs[{ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num }];
+        auto & pg = pgs.at({ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num });
         for (int role = 0; role < op_data->pg_data_size; role++)
         {
             op_data->stripes[role].read_start = op_data->stripes[role].req_start;
@@ -211,7 +211,7 @@ void osd_t::continue_primary_write(osd_op_t *cur_op)
         return;
     }
     osd_primary_op_data_t *op_data = cur_op->op_data;
-    auto & pg = pgs[{ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num }];
+    auto & pg = pgs.at({ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num });
     if (op_data->st == 1)      goto resume_1;
     else if (op_data->st == 2) goto resume_2;
     else if (op_data->st == 3) goto resume_3;
@@ -582,7 +582,7 @@ resume_2:
         int dpg = 0;
         for (auto dirty_pg_num: dirty_pgs)
         {
-            pgs[dirty_pg_num].inflight++;
+            pgs.at(dirty_pg_num).inflight++;
             op_data->dirty_pgs[dpg++] = dirty_pg_num;
         }
         dirty_pgs.clear();
@@ -639,7 +639,7 @@ resume_6:
                         .pool_id = INODE_POOL(w.oid.inode),
                         .pg_num = map_to_pg(w.oid, st_cli.pool_config.at(INODE_POOL(w.oid.inode)).pg_stripe_size),
                     };
-                    if (pgs[wpg].state & PG_ACTIVE)
+                    if (pgs.at(wpg).state & PG_ACTIVE)
                     {
                         uint64_t & dest = this->unstable_writes[(osd_object_id_t){
                             .osd_num = unstable_osd.osd_num,
@@ -750,7 +750,7 @@ void osd_t::continue_primary_del(osd_op_t *cur_op)
         return;
     }
     osd_primary_op_data_t *op_data = cur_op->op_data;
-    auto & pg = pgs[{ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num }];
+    auto & pg = pgs.at({ .pool_id = INODE_POOL(op_data->oid.inode), .pg_num = op_data->pg_num });
     if (op_data->st == 1)      goto resume_1;
     else if (op_data->st == 2) goto resume_2;
     else if (op_data->st == 3) goto resume_3;

src/osd_primary_subops.cpp

@@ -40,7 +40,7 @@ void osd_t::finish_op(osd_op_t *cur_op, int retval)
     {
         if (cur_op->op_data->pg_num > 0)
         {
-            auto & pg = pgs[{ .pool_id = INODE_POOL(cur_op->op_data->oid.inode), .pg_num = cur_op->op_data->pg_num }];
+            auto & pg = pgs.at({ .pool_id = INODE_POOL(cur_op->op_data->oid.inode), .pg_num = cur_op->op_data->pg_num });
             pg.inflight--;
             assert(pg.inflight >= 0);
             if ((pg.state & PG_STOPPING) && pg.inflight == 0 && !pg.flush_batch)

tests/test_change_pg_count.sh

@@ -5,6 +5,9 @@
 dd if=/dev/zero of=./testdata/test_osd1.bin bs=1024 count=1 seek=$((1024*1024-1))
 dd if=/dev/zero of=./testdata/test_osd2.bin bs=1024 count=1 seek=$((1024*1024-1))
 dd if=/dev/zero of=./testdata/test_osd3.bin bs=1024 count=1 seek=$((1024*1024-1))
+dd if=/dev/zero of=./testdata/test_osd4.bin bs=1024 count=1 seek=$((1024*1024-1))
+dd if=/dev/zero of=./testdata/test_osd5.bin bs=1024 count=1 seek=$((1024*1024-1))
+dd if=/dev/zero of=./testdata/test_osd6.bin bs=1024 count=1 seek=$((1024*1024-1))
 
 build/src/vitastor-osd --osd_num 1 --bind_address 127.0.0.1 --etcd_address $ETCD_URL $(node mon/simple-offsets.js --format options --device ./testdata/test_osd1.bin 2>/dev/null) &>./testdata/osd1.log &
 OSD1_PID=$!
@@ -12,18 +15,26 @@ build/src/vitastor-osd --osd_num 2 --bind_address 127.0.0.1 --etcd_address $ETCD
 OSD2_PID=$!
 build/src/vitastor-osd --osd_num 3 --bind_address 127.0.0.1 --etcd_address $ETCD_URL $(node mon/simple-offsets.js --format options --device ./testdata/test_osd3.bin 2>/dev/null) &>./testdata/osd3.log &
 OSD3_PID=$!
+build/src/vitastor-osd --osd_num 4 --bind_address 127.0.0.1 --etcd_address $ETCD_URL $(node mon/simple-offsets.js --format options --device ./testdata/test_osd4.bin 2>/dev/null) &>./testdata/osd4.log &
+OSD4_PID=$!
+build/src/vitastor-osd --osd_num 5 --bind_address 127.0.0.1 --etcd_address $ETCD_URL $(node mon/simple-offsets.js --format options --device ./testdata/test_osd5.bin 2>/dev/null) &>./testdata/osd5.log &
+OSD5_PID=$!
+build/src/vitastor-osd --osd_num 6 --bind_address 127.0.0.1 --etcd_address $ETCD_URL $(node mon/simple-offsets.js --format options --device ./testdata/test_osd6.bin 2>/dev/null) &>./testdata/osd6.log &
+OSD6_PID=$!
 
 cd mon
 npm install
 cd ..
-node mon/mon-main.js --etcd_url http://$ETCD_URL --etcd_prefix "/vitastor" &>./testdata/mon.log &
+node mon/mon-main.js --etcd_url http://$ETCD_URL --etcd_prefix "/vitastor" --verbose 1 &>./testdata/mon.log &
 MON_PID=$!
 
-$ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"replicated","pg_size":3,"pg_minsize":2,"pg_count":16,"failure_domain":"osd"}}'
+$ETCDCTL put /vitastor/config/global '{"immediate_commit":"all"}'
+
+$ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"replicated","pg_size":2,"pg_minsize":2,"pg_count":16,"failure_domain":"osd"}}'
 
 sleep 2
 
-if ! ($ETCDCTL get /vitastor/config/pgs --print-value-only | jq -s -e '(.[0].items["1"] | map((.osd_set | sort) == ["1","2","3"]) | length) == 16'); then
+if ! ($ETCDCTL get /vitastor/config/pgs --print-value-only | jq -s -e '(.[0].items["1"] | map((.osd_set | select(. > 0)) | length == 2) | length) == 16'); then
     format_error "FAILED: 16 PGS NOT CONFIGURED"
 fi
 
@@ -31,20 +42,31 @@ if ! ($ETCDCTL get --prefix /vitastor/pg/state/ --print-value-only | jq -s -e '(
     format_error "FAILED: 16 PGS NOT UP"
 fi
 
+LD_PRELOAD=libasan.so.5 \
+fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4M -direct=1 -iodepth=1 -fsync=1 -rw=write \
+    -etcd=$ETCD_URL -pool=1 -inode=2 -size=128M -cluster_log_level=10
+
 try_change()
 {
     n=$1
 
-    $ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"replicated","pg_size":3,"pg_minsize":2,"pg_count":'$n',"failure_domain":"osd"}}'
+    $ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"replicated","pg_size":2,"pg_minsize":2,"pg_count":'$n',"failure_domain":"osd"}}'
 
     for i in {1..10}; do
-        ($ETCDCTL get /vitastor/config/pgs --print-value-only | jq -s -e '(.[0].items["1"] | map((.osd_set | sort) == ["1","2","3"]) | length) == '$n) && \
-            ($ETCDCTL get --prefix /vitastor/pg/state/ --print-value-only | jq -s -e '([ .[] | select(.state == ["active"]) ] | length) == '$n'') && \
+        ($ETCDCTL get /vitastor/config/pgs --print-value-only | jq -s -e '(.[0].items["1"] | map((.osd_set | select(. > 0)) | length == 2) | length) == '$n) && \
+            ($ETCDCTL get --prefix /vitastor/pg/state/ --print-value-only | jq -s -e '([ .[] | select(.state == ["active"] or .state == ["active", "has_misplaced"]) ] | length) == '$n'') && \
             break
         sleep 1
     done
 
-    if ! ($ETCDCTL get /vitastor/config/pgs --print-value-only | jq -s -e '(.[0].items["1"] | map((.osd_set | sort) == ["1","2","3"]) | length) == '$n); then
+    # Wait for the rebalance to finish
+    for i in {1..60}; do
+        ($ETCDCTL get --prefix /vitastor/pg/state/ --print-value-only | jq -s -e '([ .[] | select(.state == ["active"]) ] | length) == '$n'') && \
+            break
+        sleep 1
+    done
+
+    if ! ($ETCDCTL get /vitastor/config/pgs --print-value-only | jq -s -e '(.[0].items["1"] | map((.osd_set | select(. > 0)) | length == 2) | length) == '$n); then
         $ETCDCTL get /vitastor/config/pgs
         $ETCDCTL get --prefix /vitastor/pg/state/
         format_error "FAILED: $n PGS NOT CONFIGURED"
@@ -77,4 +99,10 @@ try_change 17
 
 try_change 16
 
+# Monitor should report non-zero overall statistics at least once
+
+if ! (grep /vitastor/stats ./testdata/mon.log | jq -s -e '[ .[] | select((.kv.value.op_stats.primary_write.count | tonumber) > 0) ] | length > 0'); then
+    format_error "FAILED: monitor doesn't aggregate stats"
+fi
+
 format_green OK