Release 0.9.1

- Fix "Client XX command out of sync" messages sometimes happening on OSD reconnections
- Fix a bug where EC reads parallel with writes to the same object failed with -ERANGE error
- Slightly reduce the amount of metadata writes during journal flushing
- Correctly unmap NBD volumes when Proxmox forces map_volume use (with SWTPM and maybe some other cases)

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 
 project(vitastor)
 
-set(VERSION "0.9.0")
+set(VERSION "0.9.1")
 
 add_subdirectory(src)

csi/Makefile

@@ -1,4 +1,4 @@
-VERSION ?= v0.9.0
+VERSION ?= v0.9.1
 
 all: build push
 

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v0.9.0
+          image: vitalif/vitastor-csi:v0.9.1
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/deploy/007-csi-provisioner.yaml

@@ -116,7 +116,7 @@ spec:
             privileged: true
             capabilities:
               add: ["SYS_ADMIN"]
-          image: vitalif/vitastor-csi:v0.9.0
+          image: vitalif/vitastor-csi:v0.9.1
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/src/config.go

@@ -5,7 +5,7 @@ package vitastor
 
 const (
     vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "0.9.0"
+    vitastorCSIDriverVersion = "0.9.1"
 )
 
 // Config struct fills the parameters of request or user input

debian/changelog

@@ -1,10 +1,10 @@
-vitastor (0.9.0-1) unstable; urgency=medium
+vitastor (0.9.1-1) unstable; urgency=medium
 
   * Bugfixes
 
  -- Vitaliy Filippov <vitalif@yourcmc.ru>  Fri, 03 Jun 2022 02:09:44 +0300
 
-vitastor (0.9.0-1) unstable; urgency=medium
+vitastor (0.9.1-1) unstable; urgency=medium
 
   * Implement NFS proxy
   * Add documentation

debian/vitastor.Dockerfile

@@ -34,8 +34,8 @@ RUN set -e -x; \
     mkdir -p /root/packages/vitastor-$REL; \
     rm -rf /root/packages/vitastor-$REL/*; \
     cd /root/packages/vitastor-$REL; \
-    cp -r /root/vitastor vitastor-0.9.0; \
-    cd vitastor-0.9.0; \
+    cp -r /root/vitastor vitastor-0.9.1; \
+    cd vitastor-0.9.1; \
     ln -s /root/fio-build/fio-*/ ./fio; \
     FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
     ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
@@ -48,8 +48,8 @@ RUN set -e -x; \
     rm -rf a b; \
     echo "dep:fio=$FIO" > debian/fio_version; \
     cd /root/packages/vitastor-$REL; \
-    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.9.0.orig.tar.xz vitastor-0.9.0; \
-    cd vitastor-0.9.0; \
+    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.9.1.orig.tar.xz vitastor-0.9.1; \
+    cd vitastor-0.9.1; \
     V=$(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; \

docs/config/osd.ru.md

@@ -430,7 +430,7 @@ Flusher - это микро-поток (корутина), которая коп
 Находить и автоматически восстанавливать "лучшие версии" объектов с
 несовпадающими копиями/частями. При использовании репликации "лучшая"
 версия - версия, доступная в большем числе экземпляров, чем другие. При
-использовании кодов коррекции ошибок "лучшая" весрия - это подмножество
+использовании кодов коррекции ошибок "лучшая" версия - это подмножество
 частей данных и чётности, полностью соответствующих друг другу.
 
 Гипотетическая ситуация, в которой вы можете захотеть отключить этот

docs/config/src/osd.yml

@@ -474,7 +474,7 @@
     Находить и автоматически восстанавливать "лучшие версии" объектов с
     несовпадающими копиями/частями. При использовании репликации "лучшая"
     версия - версия, доступная в большем числе экземпляров, чем другие. При
-    использовании кодов коррекции ошибок "лучшая" весрия - это подмножество
+    использовании кодов коррекции ошибок "лучшая" версия - это подмножество
     частей данных и чётности, полностью соответствующих друг другу.
 
     Гипотетическая ситуация, в которой вы можете захотеть отключить этот

patches/VitastorPlugin.pm

@@ -388,8 +388,6 @@ sub unmap_volume
     my ($class, $storeid, $scfg, $volname, $snapname) = @_;
     my $prefix = defined $scfg->{vitastor_prefix} ? $scfg->{vitastor_prefix} : 'pve/';
 
-    return 1 if !$scfg->{vitastor_nbd};
-
     my ($vtype, $name, $vmid) = $class->parse_volname($volname);
     $name .= '@'.$snapname if $snapname;
 
@@ -413,7 +411,7 @@ sub activate_volume
 sub deactivate_volume
 {
     my ($class, $storeid, $scfg, $volname, $snapname, $cache) = @_;
-    $class->unmap_volume($storeid, $scfg, $volname, $snapname);
+    $class->unmap_volume($storeid, $scfg, $volname, $snapname) if $scfg->{vitastor_nbd};
     return 1;
 }
 

patches/cinder-vitastor.py

@@ -50,7 +50,7 @@ from cinder.volume import configuration
 from cinder.volume import driver
 from cinder.volume import volume_utils
 
-VERSION = '0.9.0'
+VERSION = '0.9.1'
 
 LOG = logging.getLogger(__name__)
 

rpm/build-tarball.sh

@@ -24,4 +24,4 @@ rm fio
 mv fio-copy fio
 FIO=`rpm -qi fio | 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
-tar --transform 's#^#vitastor-0.9.0/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.9.0$(rpm --eval '%dist').tar.gz *
+tar --transform 's#^#vitastor-0.9.1/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.9.1$(rpm --eval '%dist').tar.gz *

rpm/vitastor-el7.Dockerfile

@@ -35,7 +35,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-0.9.0.el7.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.9.1.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:        0.9.0
+Version:        0.9.1
 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-0.9.0.el7.tar.gz
+Source0:        vitastor-0.9.1.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-0.9.0.el8.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.9.1.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:        0.9.0
+Version:        0.9.1
 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-0.9.0.el8.tar.gz
+Source0:        vitastor-0.9.1.el8.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

rpm/vitastor-el9.Dockerfile

@@ -18,7 +18,7 @@ ADD . /root/vitastor
 RUN set -e; \
     cd /root/vitastor/rpm; \
     sh build-tarball.sh; \
-    cp /root/vitastor-0.9.0.el9.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.9.1.el9.tar.gz ~/rpmbuild/SOURCES; \
     cp vitastor-el9.spec ~/rpmbuild/SPECS/vitastor.spec; \
     cd ~/rpmbuild/SPECS/; \
     rpmbuild -ba vitastor.spec; \

rpm/vitastor-el9.spec

@@ -1,11 +1,11 @@
 Name:           vitastor
-Version:        0.9.0
+Version:        0.9.1
 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-0.9.0.el9.tar.gz
+Source0:        vitastor-0.9.1.el9.tar.gz
 
 BuildRequires:  liburing-devel >= 0.6
 BuildRequires:  gperftools-devel

src/CMakeLists.txt

@@ -16,7 +16,7 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
 	set(CMAKE_INSTALL_RPATH "${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_LIBDIR}")
 endif()
 
-add_definitions(-DVERSION="0.9.0")
+add_definitions(-DVERSION="0.9.1")
 add_definitions(-Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -I ${CMAKE_SOURCE_DIR}/src)
 if (${WITH_ASAN})
 	add_definitions(-fsanitize=address -fno-omit-frame-pointer)

src/blockstore_flush.cpp

@@ -536,14 +536,27 @@ resume_1:
                 return false;
             }
             // zero out old metadata entry
+            {
+                clean_disk_entry *old_entry = (clean_disk_entry*)((uint8_t*)meta_old.buf + meta_old.pos*bs->dsk.clean_entry_size);
+                if (old_entry->oid.inode != 0 && old_entry->oid != cur.oid)
+                {
+                    printf("Fatal error (metadata corruption or bug): tried to wipe metadata entry %lu (%lx:%lx v%lu) as old location of %lx:%lx\n",
+                        old_clean_loc >> bs->dsk.block_order, old_entry->oid.inode, old_entry->oid.stripe,
+                        old_entry->version, cur.oid.inode, cur.oid.stripe);
+                    exit(1);
+                }
+            }
             memset((uint8_t*)meta_old.buf + meta_old.pos*bs->dsk.clean_entry_size, 0, bs->dsk.clean_entry_size);
-            await_sqe(15);
-            data->iov = (struct iovec){ meta_old.buf, bs->dsk.meta_block_size };
-            data->callback = simple_callback_w;
-            my_uring_prep_writev(
-                sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bs->dsk.meta_block_size + meta_old.sector
-            );
-            wait_count++;
+            if (meta_old.sector != meta_new.sector)
+            {
+                await_sqe(15);
+                data->iov = (struct iovec){ meta_old.buf, bs->dsk.meta_block_size };
+                data->callback = simple_callback_w;
+                my_uring_prep_writev(
+                    sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bs->dsk.meta_block_size + meta_old.sector
+                );
+                wait_count++;
+            }
         }
         if (has_delete)
         {

src/blockstore_read.cpp

@@ -138,10 +138,6 @@ int blockstore_impl_t::dequeue_read(blockstore_op_t *read_op)
         {
             dirty_entry& dirty = dirty_it->second;
             bool version_ok = !IS_IN_FLIGHT(dirty.state) && read_op->version >= dirty_it->first.version;
-            if (IS_SYNCED(dirty.state))
-            {
-                version_ok = true;
-            }
             if (version_ok)
             {
                 if (IS_DELETE(dirty.state))

src/blockstore_rollback.cpp

@@ -179,7 +179,7 @@ void blockstore_impl_t::erase_dirty(blockstore_dirty_db_t::iterator dirty_start,
     {
         object_id oid = dirty_it->first.oid;
 #ifdef BLOCKSTORE_DEBUG
-        printf("Unblock writes-after-delete %lx:%lx v%lx\n", oid.inode, oid.stripe, dirty_it->first.version);
+        printf("Unblock writes-after-delete %lx:%lx v%lu\n", oid.inode, oid.stripe, dirty_it->first.version);
 #endif
         dirty_it = dirty_end;
         // Unblock operations blocked by delete flushing

src/messenger.cpp

@@ -251,6 +251,10 @@ void osd_messenger_t::try_connect_peer_addr(osd_num_t peer_osd, const char *peer
         return;
     }
     clients[peer_fd] = new osd_client_t();
+    if (log_level > 0)
+    {
+        fprintf(stderr, "Connecting to OSD %lu at %s:%d (client %d)\n", peer_osd, peer_host, peer_port, peer_fd);
+    }
     clients[peer_fd]->peer_addr = addr;
     clients[peer_fd]->peer_port = peer_port;
     clients[peer_fd]->peer_fd = peer_fd;
@@ -313,7 +317,10 @@ void osd_messenger_t::handle_peer_epoll(int peer_fd, int epoll_events)
     if (epoll_events & EPOLLRDHUP)
     {
         // Stop client
-        fprintf(stderr, "[OSD %lu] client %d disconnected\n", this->osd_num, peer_fd);
+        if (log_level > 0)
+        {
+            fprintf(stderr, "[OSD %lu] client %d disconnected\n", this->osd_num, peer_fd);
+        }
         stop_client(peer_fd, true);
     }
     else if (epoll_events & EPOLLIN)

src/messenger.h

@@ -50,7 +50,7 @@ struct osd_client_t
 
     sockaddr_storage peer_addr;
     int peer_port;
-    int peer_fd;
+    int peer_fd = -1;
     int peer_state;
     int connect_timeout_id = -1;
     int ping_time_remaining = 0;
@@ -87,11 +87,7 @@ struct osd_client_t
     std::vector<iovec> send_list, next_send_list;
     std::vector<msgr_sendp_t> outbox, next_outbox;
 
-    ~osd_client_t()
-    {
-        free(in_buf);
-        in_buf = NULL;
-    }
+    ~osd_client_t();
 };
 
 struct osd_wanted_peer_t

src/msgr_stop.cpp

@@ -122,17 +122,6 @@ void osd_messenger_t::stop_client(int peer_fd, bool force, bool force_delete)
         // Cancel outbound operations
         cancel_osd_ops(cl);
     }
-#ifndef __MOCK__
-    // And close the FD only when everything is done
-    // ...because peer_fd number can get reused after close()
-    close(peer_fd);
-#ifdef WITH_RDMA
-    if (cl->rdma_conn)
-    {
-        delete cl->rdma_conn;
-    }
-#endif
-#endif
     // Find the item again because it can be invalidated at this point
     it = clients.find(peer_fd);
     if (it != clients.end())
@@ -145,3 +134,25 @@ void osd_messenger_t::stop_client(int peer_fd, bool force, bool force_delete)
         delete cl;
     }
 }
+
+osd_client_t::~osd_client_t()
+{
+    free(in_buf);
+    in_buf = NULL;
+    if (peer_fd >= 0)
+    {
+        // Close the FD only when the client is actually destroyed
+        // Which only happens when all references are cleared
+        close(peer_fd);
+        peer_fd = -1;
+    }
+#ifndef __MOCK__
+#ifdef WITH_RDMA
+    if (rdma_conn)
+    {
+        delete rdma_conn;
+        rdma_conn = NULL;
+    }
+#endif
+#endif
+}

src/osd_flush.cpp

@@ -305,7 +305,7 @@ void osd_t::submit_recovery_op(osd_recovery_op_t *op)
     };
     if (log_level > 2)
     {
-        printf("Submitting recovery operation for %lx:%lx\n", op->oid.inode, op->oid.stripe);
+        printf("Submitting recovery operation for %lx:%lx (%s)\n", op->oid.inode, op->oid.stripe, op->degraded ? "degraded" : "misplaced");
     }
     op->osd_op->peer_fd = -1;
     op->osd_op->callback = [this, op](osd_op_t *osd_op)

src/osd_peering_pg.cpp

@@ -255,7 +255,7 @@ void pg_obj_state_check_t::finish_object()
     }
     else if (n_mismatched > 0)
     {
-        if (log_level > 2 && (replicated || n_roles >= pg->pg_cursize))
+        if (log_level > 2)
         {
             printf("Object is misplaced: %lx:%lx version=%lu/%lu\n", oid.inode, oid.stripe, target_ver, max_ver);
         }

src/osd_primary_subops.cpp

@@ -357,7 +357,7 @@ void osd_t::handle_primary_subop(osd_op_t *subop, osd_op_t *cur_op)
 #ifdef OSD_DEBUG
         uint64_t peer_osd = msgr.clients.find(subop->peer_fd) != msgr.clients.end()
             ? msgr.clients[subop->peer_fd]->osd_num : osd_num;
-        printf("subop %lu from osd %lu: version = %lu\n", opcode, peer_osd, version);
+        printf("subop %s %lx:%lx from osd %lu: version = %lu\n", osd_op_names[opcode], subop->req.sec_rw.oid.inode, subop->req.sec_rw.oid.stripe, peer_osd, version);
 #endif
         if (op_data->fact_ver != UINT64_MAX)
         {

src/vitastor.pc.in

@@ -6,7 +6,7 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
 
 Name: Vitastor
 Description: Vitastor client library
-Version: 0.9.0
+Version: 0.9.1
 Libs: -L${libdir} -lvitastor_client
 Cflags: -I${includedir}
 

tests/test_heal.sh

@@ -46,8 +46,8 @@ kill_osds()
 kill_osds &
 
 LD_PRELOAD="build/src/libfio_vitastor.so" \
-    fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=4k -direct=1 -iodepth=16 -fsync=256 -rw=randwrite \
-        -mirror_file=./testdata/mirror.bin -etcd=$ETCD_URL -image=testimg -loops=10 -runtime=120
+    fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bsrange=4k-128k -direct=1 -iodepth=32 -fsync=256 -rw=randrw \
+        -randrepeat=0 -refill_buffers=1 -mirror_file=./testdata/mirror.bin -etcd=$ETCD_URL -image=testimg -loops=10 -runtime=120
 
 qemu-img convert -S 4096 -p \
     -f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:image=testimg" \