Release 0.9.4

- Improve QEMU driver performance by integrating io_uring in it (up to 1.5x total iops improvement)
- Fix QEMU driver deadlocks which started to reproduce in qemu-img after iothread fixes
- Fix `vitastor-cli status` reporting more etcds than actually exists (fix etcd address duplication in config on reload)
- Fix `vitastor-cli ls` crashing on inodes in non-existing pools
- Delete old garbage /pool/stats/ keys for non-existing (deleted) pools
- Reduce memory usage of etcds initialized by make-etcd script
- Fix OSDs almost always crashing on etcd restart due to "revisions were compacted" (support reloading state from etcd)
- Fix a crash and a stall possible mostly in HDD setups with small journal and big (512k, 900k) random writes
- Add notes about HDDs to documentation. You are officially allowed to use HDD-only Vitastor with HGST/Toshiba/EXOS :)

.gitea/workflows/test.yml

@@ -622,114 +622,6 @@ jobs:
           echo ""
         done
 
-  test_heal_csum_32k_dmj:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 10
-      run: TEST_NAME=csum_32k_dmj OSD_ARGS="--data_csum_type crc32c --csum_block_size 32k --inmemory_metadata false --inmemory_journal false" OFFSET_ARGS=$OSD_ARGS /root/vitastor/tests/test_heal.sh
-    - name: Print logs
-      if: always() && steps.test.outcome == 'failure'
-      run: |
-        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
-          echo "-------- $i --------"
-          cat $i
-          echo ""
-        done
-
-  test_heal_csum_32k_dj:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 10
-      run: TEST_NAME=csum_32k_dj  OSD_ARGS="--data_csum_type crc32c --csum_block_size 32k --inmemory_journal false" OFFSET_ARGS=$OSD_ARGS /root/vitastor/tests/test_heal.sh
-    - name: Print logs
-      if: always() && steps.test.outcome == 'failure'
-      run: |
-        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
-          echo "-------- $i --------"
-          cat $i
-          echo ""
-        done
-
-  test_heal_csum_32k:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 10
-      run: TEST_NAME=csum_32k     OSD_ARGS="--data_csum_type crc32c --csum_block_size 32k" OFFSET_ARGS=$OSD_ARGS /root/vitastor/tests/test_heal.sh
-    - name: Print logs
-      if: always() && steps.test.outcome == 'failure'
-      run: |
-        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
-          echo "-------- $i --------"
-          cat $i
-          echo ""
-        done
-
-  test_heal_csum_4k_dmj:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 10
-      run: TEST_NAME=csum_4k_dmj  OSD_ARGS="--data_csum_type crc32c --inmemory_metadata false --inmemory_journal false" OFFSET_ARGS=$OSD_ARGS /root/vitastor/tests/test_heal.sh
-    - name: Print logs
-      if: always() && steps.test.outcome == 'failure'
-      run: |
-        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
-          echo "-------- $i --------"
-          cat $i
-          echo ""
-        done
-
-  test_heal_csum_4k_dj:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 10
-      run: TEST_NAME=csum_4k_dj   OSD_ARGS="--data_csum_type crc32c --inmemory_journal false" OFFSET_ARGS=$OSD_ARGS /root/vitastor/tests/test_heal.sh
-    - name: Print logs
-      if: always() && steps.test.outcome == 'failure'
-      run: |
-        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
-          echo "-------- $i --------"
-          cat $i
-          echo ""
-        done
-
-  test_heal_csum_4k:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 10
-      run: TEST_NAME=csum_4k      OSD_ARGS="--data_csum_type crc32c" OFFSET_ARGS=$OSD_ARGS /root/vitastor/tests/test_heal.sh
-    - name: Print logs
-      if: always() && steps.test.outcome == 'failure'
-      run: |
-        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
-          echo "-------- $i --------"
-          cat $i
-          echo ""
-        done
-
   test_scrub:
     runs-on: ubuntu-latest
     needs: build

.gitea/workflows/tests-to-yaml.pl

@@ -7,8 +7,7 @@ for my $line (<>)
     if ($line =~ /\.\/(test_[^\.]+)/s)
     {
         chomp $line;
-        my $base_name = $1;
-        my $test_name = $base_name;
+        my $test_name = $1;
         my $timeout = 3;
         if ($test_name eq 'test_etcd_fail' || $test_name eq 'test_heal' || $test_name eq 'test_add_osd' ||
             $test_name eq 'test_interrupted_rebalance' || $test_name eq 'test_rebalance_verify')
@@ -17,12 +16,7 @@ for my $line (<>)
         }
         while ($line =~ /([^\s=]+)=(\S+)/gs)
         {
-            if ($1 eq 'TEST_NAME')
-            {
-                $test_name = $base_name.'_'.$2;
-                last;
-            }
-            elsif ($1 eq 'SCHEME' && $2 eq 'ec')
+            if ($1 eq 'SCHEME' && $2 eq 'ec')
             {
                 $test_name .= '_ec';
             }

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 
 project(vitastor)
 
-set(VERSION "0.9.3")
+set(VERSION "0.9.4")
 
 add_subdirectory(src)

csi/Makefile

@@ -1,4 +1,4 @@
-VERSION ?= v0.9.3
+VERSION ?= v0.9.4
 
 all: build push
 

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v0.9.3
+          image: vitalif/vitastor-csi:v0.9.4
           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:v0.9.3
+          image: vitalif/vitastor-csi:v0.9.4
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/src/config.go

@@ -5,7 +5,7 @@ package vitastor
 
 const (
     vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "0.9.3"
+    vitastorCSIDriverVersion = "0.9.4"
 )
 
 // Config struct fills the parameters of request or user input

debian/changelog

@@ -1,10 +1,10 @@
-vitastor (0.9.3-1) unstable; urgency=medium
+vitastor (0.9.4-1) unstable; urgency=medium
 
   * Bugfixes
 
  -- Vitaliy Filippov <vitalif@yourcmc.ru>  Fri, 03 Jun 2022 02:09:44 +0300
 
-vitastor (0.9.3-1) unstable; urgency=medium
+vitastor (0.9.4-1) unstable; urgency=medium
 
   * Implement NFS proxy
   * Add documentation

debian/patched-qemu.Dockerfile

@@ -28,13 +28,19 @@ RUN apt-get --download-only source qemu
 
 ADD patches /root/vitastor/patches
 ADD src/qemu_driver.c /root/vitastor/src/qemu_driver.c
+
+#RUN set -e; \
+#    apt-get install -y wget; \
+#    wget -q -O /etc/apt/trusted.gpg.d/vitastor.gpg https://vitastor.io/debian/pubkey.gpg; \
+#    (echo deb http://vitastor.io/debian $REL main > /etc/apt/sources.list.d/vitastor.list); \
+#    (echo "APT::Install-Recommends false;" > /etc/apt/apt.conf) && \
+#    apt-get update; \
+#    apt-get install -y vitastor-client vitastor-client-dev quilt
+
 RUN set -e; \
-    apt-get install -y wget; \
-    wget -q -O /etc/apt/trusted.gpg.d/vitastor.gpg https://vitastor.io/debian/pubkey.gpg; \
-    (echo deb http://vitastor.io/debian $REL main > /etc/apt/sources.list.d/vitastor.list); \
-    (echo "APT::Install-Recommends false;" > /etc/apt/apt.conf) && \
+    dpkg -i /root/packages/vitastor-$REL/vitastor-client_*.deb /root/packages/vitastor-$REL/vitastor-client-dev_*.deb; \
     apt-get update; \
-    apt-get install -y vitastor-client vitastor-client-dev quilt; \
+    apt-get install -y quilt; \
     mkdir -p /root/packages/qemu-$REL; \
     rm -rf /root/packages/qemu-$REL/*; \
     cd /root/packages/qemu-$REL; \

debian/vitastor.Dockerfile

@@ -35,8 +35,8 @@ RUN set -e -x; \
     mkdir -p /root/packages/vitastor-$REL; \
     rm -rf /root/packages/vitastor-$REL/*; \
     cd /root/packages/vitastor-$REL; \
-    cp -r /root/vitastor vitastor-0.9.3; \
-    cd vitastor-0.9.3; \
+    cp -r /root/vitastor vitastor-0.9.4; \
+    cd vitastor-0.9.4; \
     ln -s /root/fio-build/fio-*/ ./fio; \
     FIO=$(head -n1 fio/debian/changelog | perl -pe 's/^.*\((.*?)\).*$/$1/'); \
     ls /usr/include/linux/raw.h || cp ./debian/raw.h /usr/include/linux/raw.h; \
@@ -49,8 +49,8 @@ RUN set -e -x; \
     rm -rf a b; \
     echo "dep:fio=$FIO" > debian/fio_version; \
     cd /root/packages/vitastor-$REL; \
-    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.9.3.orig.tar.xz vitastor-0.9.3; \
-    cd vitastor-0.9.3; \
+    tar --sort=name --mtime='2020-01-01' --owner=0 --group=0 --exclude=debian -cJf vitastor_0.9.4.orig.tar.xz vitastor-0.9.4; \
+    cd vitastor-0.9.4; \
     V=$(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/layout-osd.en.md

@@ -24,8 +24,6 @@ initialization and can't be changed after it without losing data.
 - [disable_journal_fsync](#disable_journal_fsync)
 - [disable_device_lock](#disable_device_lock)
 - [disk_alignment](#disk_alignment)
-- [data_csum_type](#data_csum_type)
-- [csum_block_size](#csum_block_size)
 
 ## data_device
 
@@ -176,42 +174,3 @@ Intel Optane (probably, not tested yet).
 
 Clients don't need to be aware of disk_alignment, so it's not required to
 put a modified value into etcd key /vitastor/config/global.
-
-## data_csum_type
-
-- Type: string
-- Default: none
-
-Data checksum type to use. May be "crc32c" or "none". Set to "crc32c" to
-enable data checksums.
-
-## csum_block_size
-
-- Type: integer
-- Default: 4096
-
-Checksum calculation block size.
-
-Must be equal or a multiple of [bitmap_granularity](layout-cluster.en.md#bitmap_granularity)
-(which is usually 4 KB).
-
-Checksums increase metadata size by 4 bytes per each csum_block_size of data.
-
-Checksums are always a compromise:
-1. You either sacrifice +1 GB RAM per 1 TB of data
-2. Or you raise csum_block_size, for example, to 32k and sacrifice
-   50% random write iops due to checksum read-modify-write
-3. Or you turn off [inmemory_metadata](osd.en.md#inmemory_metadata) and
-   sacrifice 50% random read iops due to checksum reads
-
-Option 1 (default) is recommended for all-flash setups because these usually
-have enough RAM.
-
-Option 2 is recommended for HDD-only setups. HDD-only setups usually do NOT
-have enough RAM for the default 4 KB csum_block_size.
-
-Option 3 is recommended for SSD+HDD setups (because metadata SSDs will handle
-extra reads without any performance drop) and also *maybe* for NVMe all-flash
-setups when you don't have enough RAM (because NVMe drives have plenty
-of read iops to spare). You may also consider enabling
-[cached_read_meta](osd.en.md#cached_read_meta) in this case.

docs/config/layout-osd.ru.md

@@ -25,8 +25,6 @@
 - [disable_journal_fsync](#disable_journal_fsync)
 - [disable_device_lock](#disable_device_lock)
 - [disk_alignment](#disk_alignment)
-- [data_csum_type](#data_csum_type)
-- [csum_block_size](#csum_block_size)
 
 ## data_device
 
@@ -185,52 +183,3 @@ journal_block_size и meta_block_size. Однако единственные SSD
 
 Клиентам не обязательно знать про disk_alignment, так что помещать значение
 этого параметра в etcd в /vitastor/config/global не нужно.
-
-## data_csum_type
-
-- Тип: строка
-- Значение по умолчанию: none
-
-Тип используемых OSD контрольных сумм данных. Может быть "crc32c" или "none".
-Установите в "crc32c", чтобы включить расчёт и проверку контрольных сумм данных.
-
-Следует понимать, что контрольные суммы в зависимости от размера блока их
-расчёта либо увеличивают потребление памяти, либо снижают производительность.
-Подробнее смотрите в описании параметра [csum_block_size](#csum_block_size).
-
-## csum_block_size
-
-- Тип: целое число
-- Значение по умолчанию: 4096
-
-Размер блока расчёта контрольных сумм.
-
-Должен быть равен или кратен [bitmap_granularity](layout-cluster.ru.md#bitmap_granularity)
-(который обычно равен 4 КБ).
-
-Контрольные суммы увеличивают размер метаданных на 4 байта на каждые
-csum_block_size данных.
-
-Контрольные суммы - это всегда компромисс:
-1. Вы либо жертвуете потреблением +1 ГБ памяти на 1 ТБ дискового пространства
-2. Либо вы повышаете csum_block_size до, скажем, 32k и жертвуете 50%
-   скорости случайной записи из-за цикла чтения-изменения-записи для расчёта
-   новых контрольных сумм
-3. Либо вы отключаете [inmemory_metadata](osd.ru.md#inmemory_metadata) и
-   жертвуете 50% скорости случайного чтения из-за чтения контрольных сумм
-   с диска
-
-Вариант 1 (при настройках по умолчанию) рекомендуется для SSD (All-Flash)
-кластеров, потому что памяти в них обычно хватает.
-
-Вариант 2 рекомендуется для кластеров на одних жёстких дисках (без SSD
-под метаданные). На 4 кб блок контрольной суммы памяти в таких кластерах
-обычно НЕ хватает.
-
-Вариант 3 рекомендуется для гибридных кластеров (SSD+HDD), потому что
-скорости SSD под метаданными хватит, чтобы обработать дополнительные чтения
-без снижения производительности. Также вариант 3 *может* рекомендоваться
-для All-Flash кластеров на основе NVMe-дисков, когда памяти НЕ достаточно,
-потому что NVMe-диски имеют огромный запас производительности по чтению.
-В таких случаях, возможно, также имеет смысл включать параметр
-[cached_read_meta](osd.ru.md#cached_read_meta).

docs/config/osd.en.md

@@ -31,9 +31,6 @@ them, even without restarting by updating configuration in etcd.
 - [max_flusher_count](#max_flusher_count)
 - [inmemory_metadata](#inmemory_metadata)
 - [inmemory_journal](#inmemory_journal)
-- [cached_read_data](#cached_read_data)
-- [cached_read_meta](#cached_read_meta)
-- [cached_read_journal](#cached_read_journal)
 - [journal_sector_buffer_count](#journal_sector_buffer_count)
 - [journal_no_same_sector_overwrites](#journal_no_same_sector_overwrites)
 - [throttle_small_writes](#throttle_small_writes)
@@ -258,46 +255,6 @@ is typically very small because it's sufficient to have 16-32 MB journal
 for SSD OSDs. However, in theory it's possible that you'll want to turn it
 off for hybrid (HDD+SSD) OSDs with large journals on quick devices.
 
-## cached_read_data
-
-- Type: boolean
-- Default: false
-
-Read data through Linux page cache, i.e. use a file descriptor opened without
-O_DIRECT for data reads. May improve read performance for frequently accessed
-data if it fits in RAM. Memory in page cache is shared by all processes and
-not accounted in OSD memory consumption.
-
-## cached_read_meta
-
-- Type: boolean
-- Default: false
-
-Read metadata through Linux page cache. May be beneficial when checksums
-are enabled and [inmemory_metadata](#inmemory_metadata) is disabled, because
-in this case metadata blocks are read from disk to verify checksums on every
-read request and caching them may reduce this extra read load.
-
-Absolutely pointless to enable with enabled inmemory_metadata because all
-metadata is kept in memory anyway, and likely pointless without checksums,
-because in that case, metadata blocks are read from disk only during journal
-flushing.
-
-If the same device is used for data and metadata, enabling [cached_read_data](#cached_read_data)
-also enables this parameter, given that it isn't turned off explicitly.
-
-## cached_read_journal
-
-- Type: boolean
-- Default: false
-
-Read buffered data from journal through Linux page cache. Does not have sense
-without disabling [inmemory_journal](#inmemory_journal), which, again, is
-enabled by default.
-
-If the same device is used for metadata and journal, enabling [cached_read_meta](#cached_read_meta)
-also enables this parameter, given that it isn't turned off explicitly.
-
 ## journal_sector_buffer_count
 
 - Type: integer

docs/config/osd.ru.md

@@ -32,9 +32,6 @@
 - [max_flusher_count](#max_flusher_count)
 - [inmemory_metadata](#inmemory_metadata)
 - [inmemory_journal](#inmemory_journal)
-- [cached_read_data](#cached_read_data)
-- [cached_read_meta](#cached_read_meta)
-- [cached_read_journal](#cached_read_journal)
 - [journal_sector_buffer_count](#journal_sector_buffer_count)
 - [journal_no_same_sector_overwrites](#journal_no_same_sector_overwrites)
 - [throttle_small_writes](#throttle_small_writes)
@@ -266,51 +263,6 @@ Flusher - это микро-поток (корутина), которая коп
 параметра может оказаться полезным для гибридных OSD (HDD+SSD) с большими
 журналами, расположенными на быстром по сравнению с HDD устройстве.
 
-## cached_read_data
-
-- Тип: булево (да/нет)
-- Значение по умолчанию: false
-
-Читать данные через системный кэш Linux (page cache), то есть, использовать
-для чтения данных файловый дескриптор, открытый без флага O_DIRECT. Может
-улучшить производительность чтения для часто используемых данных, если они
-помещаются в память. Память кэша разделяется между всеми процессами в
-системе и не учитывается в потреблении памяти процессом OSD.
-
-## cached_read_meta
-
-- Тип: булево (да/нет)
-- Значение по умолчанию: false
-
-Читать метаданные через системный кэш Linux. Может быть полезно, когда
-включены контрольные суммы, а параметр [inmemory_metadata](#inmemory_metadata)
-отключён, так как в этом случае блоки метаданных читаются с диска при каждом
-запросе чтения для проверки контрольных сумм и их кэширование может снизить
-дополнительную нагрузку на диск.
-
-Абсолютно бессмысленно включать данный параметр, если параметр
-inmemory_metadata включён (по умолчанию это так), и также вероятно
-бессмысленно включать его, если не включены контрольные суммы, так как в
-этом случае блоки метаданных читаются с диска только во время сброса
-журнала.
-
-Если одно и то же устройство используется для данных и метаданных, включение
-[cached_read_data](#cached_read_data) также включает данный параметр, при
-условии, что он не отключён явным образом.
-
-## cached_read_journal
-
-- Тип: булево (да/нет)
-- Значение по умолчанию: false
-
-Читать буферизованные в журнале данные через системный кэш Linux. Не имеет
-смысла без отключения параметра [inmemory_journal](#inmemory_journal),
-который, опять же, по умолчанию включён.
-
-Если одно и то же устройство используется для метаданных и журнала,
-включение [cached_read_meta](#cached_read_meta) также включает данный
-параметр, при условии, что он не отключён явным образом.
-
 ## journal_sector_buffer_count
 
 - Тип: целое число

docs/config/src/layout-osd.yml

@@ -204,77 +204,3 @@
 
     Клиентам не обязательно знать про disk_alignment, так что помещать значение
     этого параметра в etcd в /vitastor/config/global не нужно.
-- name: data_csum_type
-  type: string
-  default: none
-  info: |
-    Data checksum type to use. May be "crc32c" or "none". Set to "crc32c" to
-    enable data checksums.
-  info_ru: |
-    Тип используемых OSD контрольных сумм данных. Может быть "crc32c" или "none".
-    Установите в "crc32c", чтобы включить расчёт и проверку контрольных сумм данных.
-
-    Следует понимать, что контрольные суммы в зависимости от размера блока их
-    расчёта либо увеличивают потребление памяти, либо снижают производительность.
-    Подробнее смотрите в описании параметра [csum_block_size](#csum_block_size).
-- name: csum_block_size
-  type: int
-  default: 4096
-  info: |
-    Checksum calculation block size.
-
-    Must be equal or a multiple of [bitmap_granularity](layout-cluster.en.md#bitmap_granularity)
-    (which is usually 4 KB).
-
-    Checksums increase metadata size by 4 bytes per each csum_block_size of data.
-
-    Checksums are always a compromise:
-    1. You either sacrifice +1 GB RAM per 1 TB of data
-    2. Or you raise csum_block_size, for example, to 32k and sacrifice
-       50% random write iops due to checksum read-modify-write
-    3. Or you turn off [inmemory_metadata](osd.en.md#inmemory_metadata) and
-       sacrifice 50% random read iops due to checksum reads
-
-    Option 1 (default) is recommended for all-flash setups because these usually
-    have enough RAM.
-
-    Option 2 is recommended for HDD-only setups. HDD-only setups usually do NOT
-    have enough RAM for the default 4 KB csum_block_size.
-
-    Option 3 is recommended for SSD+HDD setups (because metadata SSDs will handle
-    extra reads without any performance drop) and also *maybe* for NVMe all-flash
-    setups when you don't have enough RAM (because NVMe drives have plenty
-    of read iops to spare). You may also consider enabling
-    [cached_read_meta](osd.en.md#cached_read_meta) in this case.
-  info_ru: |
-    Размер блока расчёта контрольных сумм.
-
-    Должен быть равен или кратен [bitmap_granularity](layout-cluster.ru.md#bitmap_granularity)
-    (который обычно равен 4 КБ).
-
-    Контрольные суммы увеличивают размер метаданных на 4 байта на каждые
-    csum_block_size данных.
-
-    Контрольные суммы - это всегда компромисс:
-    1. Вы либо жертвуете потреблением +1 ГБ памяти на 1 ТБ дискового пространства
-    2. Либо вы повышаете csum_block_size до, скажем, 32k и жертвуете 50%
-       скорости случайной записи из-за цикла чтения-изменения-записи для расчёта
-       новых контрольных сумм
-    3. Либо вы отключаете [inmemory_metadata](osd.ru.md#inmemory_metadata) и
-       жертвуете 50% скорости случайного чтения из-за чтения контрольных сумм
-       с диска
-
-    Вариант 1 (при настройках по умолчанию) рекомендуется для SSD (All-Flash)
-    кластеров, потому что памяти в них обычно хватает.
-
-    Вариант 2 рекомендуется для кластеров на одних жёстких дисках (без SSD
-    под метаданные). На 4 кб блок контрольной суммы памяти в таких кластерах
-    обычно НЕ хватает.
-
-    Вариант 3 рекомендуется для гибридных кластеров (SSD+HDD), потому что
-    скорости SSD под метаданными хватит, чтобы обработать дополнительные чтения
-    без снижения производительности. Также вариант 3 *может* рекомендоваться
-    для All-Flash кластеров на основе NVMe-дисков, когда памяти НЕ достаточно,
-    потому что NVMe-диски имеют огромный запас производительности по чтению.
-    В таких случаях, возможно, также имеет смысл включать параметр
-    [cached_read_meta](osd.ru.md#cached_read_meta).

docs/config/src/osd.yml

@@ -260,70 +260,6 @@
     достаточно 16- или 32-мегабайтного журнала. Однако в теории отключение
     параметра может оказаться полезным для гибридных OSD (HDD+SSD) с большими
     журналами, расположенными на быстром по сравнению с HDD устройстве.
-- name: cached_read_data
-  type: bool
-  default: false
-  info: |
-    Read data through Linux page cache, i.e. use a file descriptor opened without
-    O_DIRECT for data reads. May improve read performance for frequently accessed
-    data if it fits in RAM. Memory in page cache is shared by all processes and
-    not accounted in OSD memory consumption.
-  info_ru: |
-    Читать данные через системный кэш Linux (page cache), то есть, использовать
-    для чтения данных файловый дескриптор, открытый без флага O_DIRECT. Может
-    улучшить производительность чтения для часто используемых данных, если они
-    помещаются в память. Память кэша разделяется между всеми процессами в
-    системе и не учитывается в потреблении памяти процессом OSD.
-- name: cached_read_meta
-  type: bool
-  default: false
-  info: |
-    Read metadata through Linux page cache. May be beneficial when checksums
-    are enabled and [inmemory_metadata](#inmemory_metadata) is disabled, because
-    in this case metadata blocks are read from disk to verify checksums on every
-    read request and caching them may reduce this extra read load.
-
-    Absolutely pointless to enable with enabled inmemory_metadata because all
-    metadata is kept in memory anyway, and likely pointless without checksums,
-    because in that case, metadata blocks are read from disk only during journal
-    flushing.
-
-    If the same device is used for data and metadata, enabling [cached_read_data](#cached_read_data)
-    also enables this parameter, given that it isn't turned off explicitly.
-  info_ru: |
-    Читать метаданные через системный кэш Linux. Может быть полезно, когда
-    включены контрольные суммы, а параметр [inmemory_metadata](#inmemory_metadata)
-    отключён, так как в этом случае блоки метаданных читаются с диска при каждом
-    запросе чтения для проверки контрольных сумм и их кэширование может снизить
-    дополнительную нагрузку на диск.
-
-    Абсолютно бессмысленно включать данный параметр, если параметр
-    inmemory_metadata включён (по умолчанию это так), и также вероятно
-    бессмысленно включать его, если не включены контрольные суммы, так как в
-    этом случае блоки метаданных читаются с диска только во время сброса
-    журнала.
-
-    Если одно и то же устройство используется для данных и метаданных, включение
-    [cached_read_data](#cached_read_data) также включает данный параметр, при
-    условии, что он не отключён явным образом.
-- name: cached_read_journal
-  type: bool
-  default: false
-  info: |
-    Read buffered data from journal through Linux page cache. Does not have sense
-    without disabling [inmemory_journal](#inmemory_journal), which, again, is
-    enabled by default.
-
-    If the same device is used for metadata and journal, enabling [cached_read_meta](#cached_read_meta)
-    also enables this parameter, given that it isn't turned off explicitly.
-  info_ru: |
-    Читать буферизованные в журнале данные через системный кэш Linux. Не имеет
-    смысла без отключения параметра [inmemory_journal](#inmemory_journal),
-    который, опять же, по умолчанию включён.
-
-    Если одно и то же устройство используется для метаданных и журнала,
-    включение [cached_read_meta](#cached_read_meta) также включает данный
-    параметр, при условии, что он не отключён явным образом.
 - name: journal_sector_buffer_count
   type: int
   default: 32

docs/installation/source.en.md

@@ -21,7 +21,7 @@
 
 ## Basic instructions
 
-Download source, for example using git: `git clone --recurse-submodules https://yourcmc.ru/git/vitalif/vitastor/`
+Download source, for example using git: `git clone --recurse-submodules https://git.yourcmc.ru/vitalif/vitastor/`
 
 Get `fio` source and symlink it into `<vitastor>/fio`. If you don't want to build fio engine,
 you can disable it by passing `-DWITH_FIO=no` to cmake.
@@ -41,7 +41,7 @@ It's recommended to build the QEMU driver (qemu_driver.c) in-tree, as a part of
 QEMU build process. To do that:
 - Install vitastor client library headers (from source or from vitastor-client-dev package)
 - Take a corresponding patch from `patches/qemu-*-vitastor.patch` and apply it to QEMU source
-- Copy `src/qemu_driver.c` to QEMU source directory as `block/block-vitastor.c`
+- Copy `src/qemu_driver.c` to QEMU source directory as `block/vitastor.c`
 - Build QEMU as usual
 
 But it is also possible to build it out-of-tree. To do that:

docs/installation/source.ru.md

@@ -21,7 +21,7 @@
 
 ## Базовая инструкция
 
-Скачайте исходные коды, например, из git: `git clone --recurse-submodules https://yourcmc.ru/git/vitalif/vitastor/`
+Скачайте исходные коды, например, из git: `git clone --recurse-submodules https://git.yourcmc.ru/vitalif/vitastor/`
 
 Скачайте исходные коды пакета `fio`, распакуйте их и создайте символическую ссылку на них
 в директории исходников Vitastor: `<vitastor>/fio`. Либо, если вы не хотите собирать плагин fio,
@@ -41,7 +41,7 @@ cmake .. && make -j8 install
 Драйвер QEMU (qemu_driver.c) рекомендуется собирать вместе с самим QEMU. Для этого:
 - Установите заголовки клиентской библиотеки Vitastor (из исходников или из пакета vitastor-client-dev)
 - Возьмите соответствующий патч из `patches/qemu-*-vitastor.patch` и примените его к исходникам QEMU
-- Скопируйте [src/qemu_driver.c](../../src/qemu_driver.c) в директорию исходников QEMU как `block/block-vitastor.c`
+- Скопируйте [src/qemu_driver.c](../../src/qemu_driver.c) в директорию исходников QEMU как `block/vitastor.c`
 - Соберите QEMU как обычно
 
 Однако в целях отладки драйвер также можно собирать отдельно от QEMU. Для этого:
@@ -60,7 +60,7 @@ cmake .. && make -j8 install
       * Для QEMU 2.0+: `<qemu>/qapi-types.h` &rarr; `<vitastor>/qemu/b/qemu/qapi-types.h`
    - `config-host.h` и `qapi` нужны, т.к. в них содержатся автогенерируемые заголовки
 - Сконфигурируйте cmake Vitastor с `WITH_QEMU=yes` (`cmake .. -DWITH_QEMU=yes`) и, если вы
-  используете RHEL-подобый дистрибутив, также с `QEMU_PLUGINDIR=qemu-kvm`.
+  используете RHEL-подобный дистрибутив, также с `QEMU_PLUGINDIR=qemu-kvm`.
 - После этого в процессе сборки Vitastor также будет собираться подходящий для вашей
   версии QEMU `block-vitastor.so`.
 - Таким образом можно использовать драйвер даже с немодифицированным QEMU, но в этом случае

docs/intro/features.en.md

@@ -30,7 +30,6 @@
 - [Write throttling to smooth random write workloads in SSD+HDD configurations](../config/osd.en.md#throttle_small_writes)
 - [RDMA/RoCEv2 support via libibverbs](../config/network.en.md#rdma_device)
 - [Scrubbing without checksums](../config/osd.en.md#auto_scrub) (verification of copies)
-- [Checksums](../config/layout-osd.en.md#data_csum_type)
 
 ## Plugins and tools
 
@@ -56,6 +55,7 @@ The following features are planned for the future:
 - iSCSI proxy
 - Multi-threaded client
 - Faster failover
+- Checksums
 - Tiered storage (SSD caching)
 - NVDIMM support
 - Compression (possibly)

docs/intro/features.ru.md

@@ -32,7 +32,6 @@
 - [Сглаживание производительности случайной записи в SSD+HDD конфигурациях](../config/osd.ru.md#throttle_small_writes)
 - [Поддержка RDMA/RoCEv2 через libibverbs](../config/network.ru.md#rdma_device)
 - [Фоновая проверка целостности без контрольных сумм](../config/osd.ru.md#auto_scrub) (сверка копий)
-- [Контрольные суммы](../config/layout-osd.ru.md#data_csum_type)
 
 ## Драйверы и инструменты
 
@@ -56,6 +55,7 @@
 - iSCSI-прокси
 - Многопоточный клиент
 - Более быстрое переключение при отказах
+- Контрольные суммы
 - Поддержка SSD-кэширования (tiered storage)
 - Поддержка NVDIMM
 - Возможно, сжатие

docs/usage/disk.en.md

@@ -86,8 +86,6 @@ Options (both modes):
 --journal_size 1G/32M      Set journal size (area or partition size)
 --block_size 1M/128k       Set blockstore object size
 --bitmap_granularity 4k    Set bitmap granularity
---data_csum_type none      Set data checksum type (crc32c or none)
---csum_block_size 4k       Set data checksum block size
 --data_device_block 4k     Override data device block size
 --meta_device_block 4k     Override metadata device block size
 --journal_device_block 4k  Override journal device block size
@@ -102,9 +100,8 @@ checks the device cache status on start and tries to disable cache for SATA/SAS
 If it doesn't succeed it issues a warning in the system log.
 
 You can also pass other OSD options here as arguments and they'll be persisted
-in the superblock: cached_read_data, cached_read_meta, cached_read_journal,
-inmemory_metadata, inmemory_journal, max_write_iodepth,
-min_flusher_count, max_flusher_count, journal_sector_buffer_count,
+to the superblock: max_write_iodepth, max_write_iodepth, min_flusher_count,
+max_flusher_count, inmemory_metadata, inmemory_journal, journal_sector_buffer_count,
 journal_no_same_sector_overwrites, throttle_small_writes, throttle_target_iops,
 throttle_target_mbs, throttle_target_parallelism, throttle_threshold_us.
 See [Runtime OSD Parameters](../config/osd.en.md) for details.
@@ -252,9 +249,7 @@ Options (see also [Cluster-Wide Disk Layout Parameters](../config/layout-cluster
 ```
 --object_size 128k       Set blockstore block size
 --bitmap_granularity 4k  Set bitmap granularity
---journal_size 16M       Set journal size
---data_csum_type none    Set data checksum type (crc32c or none)
---csum_block_size 4k     Set data checksum block size
+--journal_size 32M       Set journal size
 --device_block_size 4k   Set device block size
 --journal_offset 0       Set journal offset
 --device_size 0          Set device size

docs/usage/disk.ru.md

@@ -87,8 +87,6 @@ vitastor-disk - инструмент командной строки для уп
 --journal_size 1G/32M      Задать размер журнала (области или раздела журнала)
 --block_size 1M/128k       Задать размер объекта хранилища
 --bitmap_granularity 4k    Задать гранулярность битовых карт
---data_csum_type none      Задать тип контрольных сумм (crc32c или none)
---csum_block_size 4k       Задать размер блока расчёта контрольных сумм
 --data_device_block 4k     Задать размер блока устройства данных
 --meta_device_block 4k     Задать размер блока метаданных
 --journal_device_block 4k  Задать размер блока журнала
@@ -103,9 +101,8 @@ vitastor-disk - инструмент командной строки для уп
 это не удаётся, в системный журнал выводится предупреждение.
 
 Вы можете передать данной команде и некоторые другие опции OSD в качестве аргументов
-и они тоже будут сохранены в суперблок: cached_read_data, cached_read_meta,
-cached_read_journal, inmemory_metadata, inmemory_journal, max_write_iodepth,
-min_flusher_count, max_flusher_count, journal_sector_buffer_count,
+и они тоже будут сохранены в суперблок: max_write_iodepth, max_write_iodepth, min_flusher_count,
+max_flusher_count, inmemory_metadata, inmemory_journal, journal_sector_buffer_count,
 journal_no_same_sector_overwrites, throttle_small_writes, throttle_target_iops,
 throttle_target_mbs, throttle_target_parallelism, throttle_threshold_us.
 Читайте об этих параметрах подробнее в разделе [Изменяемые параметры OSD](../config/osd.ru.md).
@@ -257,9 +254,7 @@ OSD отключены fsync-и.
 ```
 --object_size 128k       Размер блока хранилища
 --bitmap_granularity 4k  Гранулярность битовых карт
---journal_size 16M       Размер журнала
---data_csum_type none    Задать тип контрольных сумм (crc32c или none)
---csum_block_size 4k     Задать размер блока расчёта контрольных сумм
+--journal_size 32M       Размер журнала
 --device_block_size 4k   Размер блока устройства
 --journal_offset 0       Смещение журнала
 --device_size 0          Размер устройства

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 = '0.9.3'
+VERSION = '0.9.4'
 
 LOG = logging.getLogger(__name__)
 

patches/qemu-2.12-vitastor.patch

@@ -0,0 +1,176 @@
+diff --git a/block/Makefile.objs b/block/Makefile.objs
+index d644bac60a..e404236291 100644
+--- a/block/Makefile.objs
++++ b/block/Makefile.objs
+@@ -19,6 +19,7 @@ block-obj-$(if $(CONFIG_LIBISCSI),y,n) += iscsi-opts.o
+ block-obj-$(CONFIG_LIBNFS) += nfs.o
+ block-obj-$(CONFIG_CURL) += curl.o
+ block-obj-$(CONFIG_RBD) += rbd.o
++block-obj-$(CONFIG_VITASTOR) += vitastor.o
+ block-obj-$(CONFIG_GLUSTERFS) += gluster.o
+ block-obj-$(CONFIG_VXHS) += vxhs.o
+ block-obj-$(CONFIG_LIBSSH2) += ssh.o
+@@ -39,6 +40,8 @@ curl.o-cflags      := $(CURL_CFLAGS)
+ curl.o-libs        := $(CURL_LIBS)
+ rbd.o-cflags       := $(RBD_CFLAGS)
+ rbd.o-libs         := $(RBD_LIBS)
++vitastor.o-cflags  := $(VITASTOR_CFLAGS)
++vitastor.o-libs    := $(VITASTOR_LIBS)
+ gluster.o-cflags   := $(GLUSTERFS_CFLAGS)
+ gluster.o-libs     := $(GLUSTERFS_LIBS)
+ vxhs.o-libs        := $(VXHS_LIBS)
+diff --git a/configure b/configure
+index 0a19b033bc..58b7fbf24c 100755
+--- a/configure
++++ b/configure
+@@ -398,6 +398,7 @@ trace_backends="log"
+ trace_file="trace"
+ spice=""
+ rbd=""
++vitastor=""
+ smartcard=""
+ libusb=""
+ usb_redir=""
+@@ -1213,6 +1214,10 @@ for opt do
+   ;;
+   --enable-rbd) rbd="yes"
+   ;;
++  --disable-vitastor) vitastor="no"
++  ;;
++  --enable-vitastor) vitastor="yes"
++  ;;
+   --disable-xfsctl) xfs="no"
+   ;;
+   --enable-xfsctl) xfs="yes"
+@@ -1601,6 +1606,7 @@ disabled with --disable-FEATURE, default is enabled if available:
+   vhost-crypto    vhost-crypto acceleration support
+   spice           spice
+   rbd             rados block device (rbd)
++  vitastor        vitastor block device
+   libiscsi        iscsi support
+   libnfs          nfs support
+   smartcard       smartcard support (libcacard)
+@@ -3594,6 +3600,27 @@ EOF
+   fi
+ fi
+ 
++##########################################
++# vitastor probe
++if test "$vitastor" != "no" ; then
++  cat > $TMPC <<EOF
++#include <vitastor_c.h>
++int main(void) {
++  vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++  return 0;
++}
++EOF
++  vitastor_libs="-lvitastor_client"
++  if compile_prog "" "$vitastor_libs" ; then
++    vitastor=yes
++  else
++    if test "$vitastor" = "yes" ; then
++      feature_not_found "vitastor block device" "Install vitastor-client-dev"
++    fi
++    vitastor=no
++  fi
++fi
++
+ ##########################################
+ # libssh2 probe
+ min_libssh2_version=1.2.8
+@@ -5837,6 +5864,7 @@ echo "Trace output file $trace_file-<pid>"
+ fi
+ echo "spice support     $spice $(echo_version $spice $spice_protocol_version/$spice_server_version)"
+ echo "rbd support       $rbd"
++echo "vitastor support  $vitastor"
+ echo "xfsctl support    $xfs"
+ echo "smartcard support $smartcard"
+ echo "libusb            $libusb"
+@@ -6416,6 +6444,11 @@ if test "$rbd" = "yes" ; then
+   echo "RBD_CFLAGS=$rbd_cflags" >> $config_host_mak
+   echo "RBD_LIBS=$rbd_libs" >> $config_host_mak
+ fi
++if test "$vitastor" = "yes" ; then
++  echo "CONFIG_VITASTOR=m" >> $config_host_mak
++  echo "VITASTOR_CFLAGS=$vitastor_cflags" >> $config_host_mak
++  echo "VITASTOR_LIBS=$vitastor_libs" >> $config_host_mak
++fi
+ 
+ echo "CONFIG_COROUTINE_BACKEND=$coroutine" >> $config_host_mak
+ if test "$coroutine_pool" = "yes" ; then
+diff --git a/qapi/block-core.json b/qapi/block-core.json
+index c50517bff3..c780bb2c1c 100644
+--- a/qapi/block-core.json
++++ b/qapi/block-core.json
+@@ -2514,7 +2514,7 @@
+             'dmg', 'file', 'ftp', 'ftps', 'gluster', 'host_cdrom',
+             'host_device', 'http', 'https', 'iscsi', 'luks', 'nbd', 'nfs',
+             'null-aio', 'null-co', 'nvme', 'parallels', 'qcow', 'qcow2', 'qed',
+-            'quorum', 'raw', 'rbd', 'replication', 'sheepdog', 'ssh',
++            'quorum', 'raw', 'rbd', 'vitastor', 'replication', 'sheepdog', 'ssh',
+             'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', 'vxhs' ] }
+ 
+ ##
+@@ -3217,6 +3217,28 @@
+             '*snap-id': 'uint32',
+             '*tag': 'str' } }
+ 
++##
++# @BlockdevOptionsVitastor:
++#
++# Driver specific block device options for vitastor
++#
++# @image:       Image name
++# @inode:       Inode number
++# @pool:        Pool ID
++# @size:        Desired image size in bytes
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
++##
++{ 'struct': 'BlockdevOptionsVitastor',
++  'data': { '*inode': 'uint64',
++            '*pool': 'uint64',
++            '*size': 'uint64',
++            '*image': 'str',
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
++
+ ##
+ # @ReplicationMode:
+ #
+@@ -3547,6 +3569,7 @@
+       'rbd':        'BlockdevOptionsRbd',
+       'replication':'BlockdevOptionsReplication',
+       'sheepdog':   'BlockdevOptionsSheepdog',
++      'vitastor':   'BlockdevOptionsVitastor',
+       'ssh':        'BlockdevOptionsSsh',
+       'throttle':   'BlockdevOptionsThrottle',
+       'vdi':        'BlockdevOptionsGenericFormat',
+@@ -3991,6 +4014,17 @@
+             '*subformat':           'BlockdevVhdxSubformat',
+             '*block-state-zero':    'bool' } }
+ 
++##
++# @BlockdevCreateOptionsVitastor:
++#
++# Driver specific image creation options for Vitastor.
++#
++# @size: Size of the virtual disk in bytes
++##
++{ 'struct': 'BlockdevCreateOptionsVitastor',
++  'data': { 'location':         'BlockdevOptionsVitastor',
++            'size':             'size' } }
++
+ ##
+ # @BlockdevVpcSubformat:
+ #
+@@ -4074,6 +4108,7 @@
+       'rbd':            'BlockdevCreateOptionsRbd',
+       'replication':    'BlockdevCreateNotSupported',
+       'sheepdog':       'BlockdevCreateOptionsSheepdog',
++      'vitastor':       'BlockdevCreateOptionsVitastor',
+       'ssh':            'BlockdevCreateOptionsSsh',
+       'throttle':       'BlockdevCreateNotSupported',
+       'vdi':            'BlockdevCreateOptionsVdi',

patches/qemu-5.2-vitastor.patch

@@ -0,0 +1,181 @@
+Index: qemu-5.2+dfsg/qapi/block-core.json
+===================================================================
+--- qemu-5.2+dfsg.orig/qapi/block-core.json
++++ qemu-5.2+dfsg/qapi/block-core.json
+@@ -2831,7 +2831,7 @@
+             'luks', 'nbd', 'nfs', 'null-aio', 'null-co', 'nvme', 'parallels',
+             'qcow', 'qcow2', 'qed', 'quorum', 'raw', 'rbd',
+             { 'name': 'replication', 'if': 'defined(CONFIG_REPLICATION)' },
+-            'sheepdog',
++            'sheepdog', 'vitastor',
+             'ssh', 'throttle', 'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] }
+ 
+ ##
+@@ -3668,6 +3668,28 @@
+             '*tag': 'str' } }
+ 
+ ##
++# @BlockdevOptionsVitastor:
++#
++# Driver specific block device options for vitastor
++#
++# @image:       Image name
++# @inode:       Inode number
++# @pool:        Pool ID
++# @size:        Desired image size in bytes
++# @config-path: Path to Vitastor configuration
++# @etcd-host:   etcd connection address(es)
++# @etcd-prefix: etcd key/value prefix
++##
++{ 'struct': 'BlockdevOptionsVitastor',
++  'data': { '*inode': 'uint64',
++            '*pool': 'uint64',
++            '*size': 'uint64',
++            '*image': 'str',
++            '*config-path': 'str',
++            '*etcd-host': 'str',
++            '*etcd-prefix': 'str' } }
++
++##
+ # @ReplicationMode:
+ #
+ # An enumeration of replication modes.
+@@ -4015,6 +4037,7 @@
+       'replication': { 'type': 'BlockdevOptionsReplication',
+                        'if': 'defined(CONFIG_REPLICATION)' },
+       'sheepdog':   'BlockdevOptionsSheepdog',
++      'vitastor':   'BlockdevOptionsVitastor',
+       'ssh':        'BlockdevOptionsSsh',
+       'throttle':   'BlockdevOptionsThrottle',
+       'vdi':        'BlockdevOptionsGenericFormat',
+@@ -4404,6 +4427,17 @@
+             '*cluster-size' :   'size' } }
+ 
+ ##
++# @BlockdevCreateOptionsVitastor:
++#
++# Driver specific image creation options for Vitastor.
++#
++# @size: Size of the virtual disk in bytes
++##
++{ 'struct': 'BlockdevCreateOptionsVitastor',
++  'data': { 'location':         'BlockdevOptionsVitastor',
++            'size':             'size' } }
++
++##
+ # @BlockdevVmdkSubformat:
+ #
+ # Subformat options for VMDK images
+@@ -4665,6 +4699,7 @@
+       'qed':            'BlockdevCreateOptionsQed',
+       'rbd':            'BlockdevCreateOptionsRbd',
+       'sheepdog':       'BlockdevCreateOptionsSheepdog',
++      'vitastor':       'BlockdevCreateOptionsVitastor',
+       'ssh':            'BlockdevCreateOptionsSsh',
+       'vdi':            'BlockdevCreateOptionsVdi',
+       'vhdx':           'BlockdevCreateOptionsVhdx',
+Index: qemu-5.2+dfsg/block/meson.build
+===================================================================
+--- qemu-5.2+dfsg.orig/block/meson.build
++++ qemu-5.2+dfsg/block/meson.build
+@@ -76,6 +76,7 @@ foreach m : [
+   ['CONFIG_LIBNFS', 'nfs', libnfs, 'nfs.c'],
+   ['CONFIG_LIBSSH', 'ssh', libssh, 'ssh.c'],
+   ['CONFIG_RBD', 'rbd', rbd, 'rbd.c'],
++  ['CONFIG_VITASTOR', 'vitastor', vitastor, 'vitastor.c'],
+ ]
+   if config_host.has_key(m[0])
+     if enable_modules
+Index: qemu-5.2+dfsg/configure
+===================================================================
+--- qemu-5.2+dfsg.orig/configure
++++ qemu-5.2+dfsg/configure
+@@ -372,6 +372,7 @@ trace_backends="log"
+ trace_file="trace"
+ spice=""
+ rbd=""
++vitastor=""
+ smartcard=""
+ u2f="auto"
+ libusb=""
+@@ -1263,6 +1264,10 @@ for opt do
+   ;;
+   --enable-rbd) rbd="yes"
+   ;;
++  --disable-vitastor) vitastor="no"
++  ;;
++  --enable-vitastor) vitastor="yes"
++  ;;
+   --disable-xfsctl) xfs="no"
+   ;;
+   --enable-xfsctl) xfs="yes"
+@@ -1827,6 +1832,7 @@ disabled with --disable-FEATURE, default
+   vhost-vdpa      vhost-vdpa kernel backend support
+   spice           spice
+   rbd             rados block device (rbd)
++  vitastor        vitastor block device
+   libiscsi        iscsi support
+   libnfs          nfs support
+   smartcard       smartcard support (libcacard)
+@@ -3719,6 +3725,27 @@ EOF
+ fi
+ 
+ ##########################################
++# vitastor probe
++if test "$vitastor" != "no" ; then
++  cat > $TMPC <<EOF
++#include <vitastor_c.h>
++int main(void) {
++  vitastor_c_create_qemu(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0);
++  return 0;
++}
++EOF
++  vitastor_libs="-lvitastor_client"
++  if compile_prog "" "$vitastor_libs" ; then
++    vitastor=yes
++  else
++    if test "$vitastor" = "yes" ; then
++      feature_not_found "vitastor block device" "Install vitastor-client-dev"
++    fi
++    vitastor=no
++  fi
++fi
++
++##########################################
+ # libssh probe
+ if test "$libssh" != "no" ; then
+   if $pkg_config --exists libssh; then
+@@ -6456,6 +6483,10 @@ if test "$rbd" = "yes" ; then
+   echo "CONFIG_RBD=y" >> $config_host_mak
+   echo "RBD_LIBS=$rbd_libs" >> $config_host_mak
+ fi
++if test "$vitastor" = "yes" ; then
++  echo "CONFIG_VITASTOR=y" >> $config_host_mak
++  echo "VITASTOR_LIBS=$vitastor_libs" >> $config_host_mak
++fi
+ 
+ echo "CONFIG_COROUTINE_BACKEND=$coroutine" >> $config_host_mak
+ if test "$coroutine_pool" = "yes" ; then
+Index: qemu-5.2+dfsg/meson.build
+===================================================================
+--- qemu-5.2+dfsg.orig/meson.build
++++ qemu-5.2+dfsg/meson.build
+@@ -596,6 +596,10 @@ rbd = not_found
+ if 'CONFIG_RBD' in config_host
+   rbd = declare_dependency(link_args: config_host['RBD_LIBS'].split())
+ endif
++vitastor = not_found
++if 'CONFIG_VITASTOR' in config_host
++  vitastor = declare_dependency(link_args: config_host['VITASTOR_LIBS'].split())
++endif
+ glusterfs = not_found
+ if 'CONFIG_GLUSTERFS' in config_host
+   glusterfs = declare_dependency(compile_args: config_host['GLUSTERFS_CFLAGS'].split(),
+@@ -2145,6 +2149,7 @@ endif
+ # TODO: add back protocol and server version
+ summary_info += {'spice support':     config_host.has_key('CONFIG_SPICE')}
+ summary_info += {'rbd support':       config_host.has_key('CONFIG_RBD')}
++summary_info += {'vitastor support':  config_host.has_key('CONFIG_VITASTOR')}
+ summary_info += {'xfsctl support':    config_host.has_key('CONFIG_XFS')}
+ summary_info += {'smartcard support': config_host.has_key('CONFIG_SMARTCARD')}
+ summary_info += {'U2F support':       u2f.found()}

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-0.9.3/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.9.3$(rpm --eval '%dist').tar.gz *
+tar --transform 's#^#vitastor-0.9.4/#' --exclude 'rpm/*.rpm' -czf $VITASTOR/../vitastor-0.9.4$(rpm --eval '%dist').tar.gz *

rpm/qemu-kvm-4.2-el7.spec.patch

@@ -22,7 +22,7 @@
  Name: qemu-kvm
  Version: 4.2.0
 -Release: 29.vitastor%{?dist}.6
-+Release: 32.vitastor%{?dist}.6
++Release: 34.vitastor%{?dist}.6
  # Epoch because we pushed a qemu-1.0 package. AIUI this can't ever be dropped
  Epoch: 15
  License: GPLv2 and GPLv2+ and CC-BY

rpm/qemu-kvm-4.2-el8.spec.patch

@@ -13,7 +13,7 @@
  Name: qemu-kvm
  Version: 4.2.0
 -Release: 29%{?dist}.6
-+Release: 32.vitastor%{?dist}.6
++Release: 33.vitastor%{?dist}.6
  # Epoch because we pushed a qemu-1.0 package. AIUI this can't ever be dropped
  Epoch: 15
  License: GPLv2 and GPLv2+ and CC-BY

rpm/qemu-kvm-6.2-el8.spec.patch

@@ -0,0 +1,103 @@
+--- qemu-kvm-6.2.spec.orig	2023-07-18 13:52:57.636625440 +0000
++++ qemu-kvm-6.2.spec	2023-07-18 13:52:19.011683886 +0000
+@@ -73,6 +73,7 @@ Requires: %{name}-hw-usbredir = %{epoch}
+ %endif                                                           \
+ Requires: %{name}-block-iscsi = %{epoch}:%{version}-%{release}   \
+ Requires: %{name}-block-rbd = %{epoch}:%{version}-%{release}     \
++Requires: %{name}-block-vitastor = %{epoch}:%{version}-%{release}\
+ Requires: %{name}-block-ssh = %{epoch}:%{version}-%{release}
+ 
+ # Macro to properly setup RHEL/RHEV conflict handling
+@@ -83,7 +84,7 @@ Obsoletes: %1-rhev <= %{epoch}:%{version
+ Summary: QEMU is a machine emulator and virtualizer
+ Name: qemu-kvm
+ Version: 6.2.0
+-Release: 32%{?rcrel}%{?dist}
++Release: 32.vitastor%{?rcrel}%{?dist}
+ # Epoch because we pushed a qemu-1.0 package. AIUI this can't ever be dropped
+ Epoch: 15
+ License: GPLv2 and GPLv2+ and CC-BY
+@@ -122,6 +123,7 @@ Source37: tests_data_acpi_pc_SSDT.dimmpx
+ Source38: tests_data_acpi_q35_FACP.slic
+ Source39: tests_data_acpi_q35_SSDT.dimmpxm
+ Source40: tests_data_acpi_virt_SSDT.memhp
++Source41: qemu-vitastor.c
+ 
+ Patch0001: 0001-redhat-Adding-slirp-to-the-exploded-tree.patch
+ Patch0005: 0005-Initial-redhat-build.patch
+@@ -652,6 +654,7 @@ Patch255: kvm-scsi-protect-req-aiocb-wit
+ Patch256: kvm-dma-helpers-prevent-dma_blk_cb-vs-dma_aio_cancel-rac.patch
+ # For bz#2090990 - qemu crash with error scsi_req_unref(SCSIRequest *): Assertion `req->refcount > 0' failed or scsi_dma_complete(void *, int): Assertion `r->req.aiocb != NULL' failed [8.7.0]
+ Patch257: kvm-virtio-scsi-reset-SCSI-devices-from-main-loop-thread.patch
++Patch258: qemu-6.2-vitastor.patch
+ 
+ BuildRequires: wget
+ BuildRequires: rpm-build
+@@ -689,6 +692,7 @@ BuildRequires: libcurl-devel
+ BuildRequires: libssh-devel
+ BuildRequires: librados-devel
+ BuildRequires: librbd-devel
++BuildRequires: vitastor-client-devel
+ %if %{have_gluster}
+ # For gluster block driver
+ BuildRequires: glusterfs-api-devel
+@@ -926,6 +930,14 @@ Install this package if you want to acce
+ using the rbd protocol.
+ 
+ 
++%package  block-vitastor
++Summary: QEMU Vitastor block driver
++Requires: %{name}-common%{?_isa} = %{epoch}:%{version}-%{release}
++
++%description block-vitastor
++This package provides the additional Vitastor block driver for QEMU.
++
++
+ %package  block-ssh
+ Summary: QEMU SSH block driver
+ Requires: %{name}-common%{?_isa} = %{epoch}:%{version}-%{release}
+@@ -979,6 +991,7 @@ This package provides usbredir support.
+ rm -fr slirp
+ mkdir slirp
+ %autopatch -p1
++cp %{SOURCE41} ./block/vitastor.c
+ 
+ %global qemu_kvm_build qemu_kvm_build
+ mkdir -p %{qemu_kvm_build}
+@@ -994,7 +1007,7 @@ cp -f %{SOURCE40} tests/data/acpi/virt/S
+ # --build-id option is used for giving info to the debug packages.
+ buildldflags="VL_LDFLAGS=-Wl,--build-id"
+ 
+-%global block_drivers_list qcow2,raw,file,host_device,nbd,iscsi,rbd,blkdebug,luks,null-co,nvme,copy-on-read,throttle
++%global block_drivers_list qcow2,raw,file,host_device,nbd,iscsi,rbd,vitastor,blkdebug,luks,null-co,nvme,copy-on-read,throttle
+ 
+ %if 0%{have_gluster}
+     %global block_drivers_list %{block_drivers_list},gluster
+@@ -1149,9 +1162,7 @@ pushd %{qemu_kvm_build}
+   --firmwarepath=%{_prefix}/share/qemu-firmware \
+   --meson="git" \
+   --target-list="%{buildarch}" \
+-  --block-drv-rw-whitelist=%{block_drivers_list} \
+   --audio-drv-list= \
+-  --block-drv-ro-whitelist=vmdk,vhdx,vpc,https,ssh \
+   --with-coroutine=ucontext \
+   --with-git=git \
+   --tls-priority=@QEMU,SYSTEM \
+@@ -1197,6 +1208,7 @@ pushd %{qemu_kvm_build}
+ %endif
+   --enable-pie \
+   --enable-rbd \
++  --enable-vitastor \
+ %if 0%{have_librdma}
+   --enable-rdma \
+ %endif
+@@ -1794,6 +1806,9 @@ sh %{_sysconfdir}/sysconfig/modules/kvm.
+ %files block-rbd
+ %{_libdir}/qemu-kvm/block-rbd.so
+ 
++%files block-vitastor
++%{_libdir}/qemu-kvm/block-vitastor.so
++
+ %files block-ssh
+ %{_libdir}/qemu-kvm/block-ssh.so
+ 

rpm/qemu-kvm-7.2-el9.spec.patch

@@ -0,0 +1,93 @@
+--- qemu-kvm-7.2.spec.orig	2023-06-22 13:56:19.000000000 +0000
++++ qemu-kvm-7.2.spec	2023-07-18 07:55:22.347090196 +0000
+@@ -100,8 +100,6 @@
+ %endif
+ 
+ %global target_list %{kvm_target}-softmmu
+-%global block_drivers_rw_list qcow2,raw,file,host_device,nbd,iscsi,rbd,blkdebug,luks,null-co,nvme,copy-on-read,throttle,compress
+-%global block_drivers_ro_list vdi,vmdk,vhdx,vpc,https
+ %define qemudocdir %{_docdir}/%{name}
+ %global firmwaredirs "%{_datadir}/qemu-firmware:%{_datadir}/ipxe/qemu:%{_datadir}/seavgabios:%{_datadir}/seabios"
+ 
+@@ -126,6 +124,7 @@ Requires: %{name}-device-usb-host = %{ep
+ Requires: %{name}-device-usb-redirect = %{epoch}:%{version}-%{release}   \
+ %endif                                                           \
+ Requires: %{name}-block-rbd = %{epoch}:%{version}-%{release}     \
++Requires: %{name}-block-vitastor = %{epoch}:%{version}-%{release}\
+ Requires: %{name}-audio-pa = %{epoch}:%{version}-%{release}
+ 
+ # Since SPICE is removed from RHEL-9, the following Obsoletes:
+@@ -148,7 +147,7 @@ Obsoletes: %{name}-block-ssh <= %{epoch}
+ Summary: QEMU is a machine emulator and virtualizer
+ Name: qemu-kvm
+ Version: 7.2.0
+-Release: 14%{?rcrel}%{?dist}%{?cc_suffix}.1
++Release: 14.vitastor%{?rcrel}%{?dist}%{?cc_suffix}.1
+ # Epoch because we pushed a qemu-1.0 package. AIUI this can't ever be dropped
+ # Epoch 15 used for RHEL 8
+ # Epoch 17 used for RHEL 9 (due to release versioning offset in RHEL 8.5)
+@@ -171,6 +170,7 @@ Source28: 95-kvm-memlock.conf
+ Source30: kvm-s390x.conf
+ Source31: kvm-x86.conf
+ Source36: README.tests
++Source37: qemu-vitastor.c
+ 
+ 
+ Patch0004: 0004-Initial-redhat-build.patch
+@@ -418,6 +418,7 @@ Patch134: kvm-target-i386-Fix-BZHI-instr
+ Patch135: kvm-intel-iommu-fail-DEVIOTLB_UNMAP-without-dt-mode.patch
+ # For bz#2203745 - Disk detach is unsuccessful while the guest is still booting [rhel-9.2.0.z]
+ Patch136: kvm-acpi-pcihp-allow-repeating-hot-unplug-requests.patch
++Patch137: qemu-7.2-vitastor.patch
+ 
+ %if %{have_clang}
+ BuildRequires: clang
+@@ -449,6 +450,7 @@ BuildRequires: libcurl-devel
+ %if %{have_block_rbd}
+ BuildRequires: librbd-devel
+ %endif
++BuildRequires: vitastor-client-devel
+ # We need both because the 'stap' binary is probed for by configure
+ BuildRequires: systemtap
+ BuildRequires: systemtap-sdt-devel
+@@ -642,6 +644,14 @@ using the rbd protocol.
+ %endif
+ 
+ 
++%package  block-vitastor
++Summary: QEMU Vitastor block driver
++Requires: %{name}-common%{?_isa} = %{epoch}:%{version}-%{release}
++
++%description block-vitastor
++This package provides the additional Vitastor block driver for QEMU.
++
++
+ %package  audio-pa
+ Summary: QEMU PulseAudio audio driver
+ Requires: %{name}-common%{?_isa} = %{epoch}:%{version}-%{release}
+@@ -719,6 +729,7 @@ This package provides usbredir support.
+ %prep
+ %setup -q -n qemu-%{version}%{?rcstr}
+ %autopatch -p1
++cp %{SOURCE37} ./block/vitastor.c
+ 
+ %global qemu_kvm_build qemu_kvm_build
+ mkdir -p %{qemu_kvm_build}
+@@ -946,6 +957,7 @@ run_configure \
+ %if %{have_block_rbd}
+   --enable-rbd \
+ %endif
++  --enable-vitastor \
+ %if %{have_librdma}
+   --enable-rdma \
+ %endif
+@@ -1426,6 +1438,9 @@ useradd -r -u 107 -g qemu -G kvm -d / -s
+ %files block-rbd
+ %{_libdir}/%{name}/block-rbd.so
+ %endif
++%files block-vitastor
++%{_libdir}/%{name}/block-vitastor.so
++
+ %files audio-pa
+ %{_libdir}/%{name}/audio-pa.so
+ 

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-0.9.3.el7.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.9.4.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:        0.9.3
+Version:        0.9.4
 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-0.9.3.el7.tar.gz
+Source0:        vitastor-0.9.4.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-0.9.3.el8.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.9.4.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:        0.9.3
+Version:        0.9.4
 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-0.9.3.el8.tar.gz
+Source0:        vitastor-0.9.4.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-0.9.3.el9.tar.gz ~/rpmbuild/SOURCES; \
+    cp /root/vitastor-0.9.4.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:        0.9.3
+Version:        0.9.4
 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-0.9.3.el9.tar.gz
+Source0:        vitastor-0.9.4.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="0.9.3")
+add_definitions(-DVERSION="0.9.4")
 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/allocator.cpp

@@ -143,83 +143,34 @@ uint64_t allocator::get_free_count()
     return free;
 }
 
-// FIXME: Move to utils?
 void bitmap_set(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity)
 {
-    if (start == 0 && len == 32*bitmap_granularity)
-        *((uint32_t*)bitmap) = UINT32_MAX;
-    else if (start == 0 && len == 64*bitmap_granularity)
-        *((uint64_t*)bitmap) = UINT64_MAX;
-    else
+    if (start == 0)
     {
-        unsigned bit_start = start / bitmap_granularity;
-        unsigned bit_end = ((start + len) + bitmap_granularity - 1) / bitmap_granularity;
-        while (bit_start < bit_end)
+        if (len == 32*bitmap_granularity)
         {
-            if (!(bit_start & 7) && bit_end >= bit_start+8)
-            {
-                ((uint8_t*)bitmap)[bit_start / 8] = UINT8_MAX;
-                bit_start += 8;
-            }
-            else
-            {
-                ((uint8_t*)bitmap)[bit_start / 8] |= 1 << (bit_start % 8);
-                bit_start++;
-            }
+            *((uint32_t*)bitmap) = UINT32_MAX;
+            return;
+        }
+        else if (len == 64*bitmap_granularity)
+        {
+            *((uint64_t*)bitmap) = UINT64_MAX;
+            return;
+        }
+    }
+    unsigned bit_start = start / bitmap_granularity;
+    unsigned bit_end = ((start + len) + bitmap_granularity - 1) / bitmap_granularity;
+    while (bit_start < bit_end)
+    {
+        if (!(bit_start & 7) && bit_end >= bit_start+8)
+        {
+            ((uint8_t*)bitmap)[bit_start / 8] = UINT8_MAX;
+            bit_start += 8;
+        }
+        else
+        {
+            ((uint8_t*)bitmap)[bit_start / 8] |= 1 << (bit_start % 8);
+            bit_start++;
         }
     }
 }
-
-void bitmap_clear(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity)
-{
-    if (start == 0 && len == 32*bitmap_granularity)
-        *((uint32_t*)bitmap) = 0;
-    else if (start == 0 && len == 64*bitmap_granularity)
-        *((uint64_t*)bitmap) = 0;
-    else
-    {
-        unsigned bit_start = start / bitmap_granularity;
-        unsigned bit_end = ((start + len) + bitmap_granularity - 1) / bitmap_granularity;
-        while (bit_start < bit_end)
-        {
-            if (!(bit_start & 7) && bit_end >= bit_start+8)
-            {
-                ((uint8_t*)bitmap)[bit_start / 8] = 0;
-                bit_start += 8;
-            }
-            else
-            {
-                ((uint8_t*)bitmap)[bit_start / 8] &= (0xFF ^ (1 << (bit_start % 8)));
-                bit_start++;
-            }
-        }
-    }
-}
-
-bool bitmap_check(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity)
-{
-    bool r = false;
-    if (start == 0 && len == 32*bitmap_granularity)
-        r = !!*((uint32_t*)bitmap);
-    else if (start == 0 && len == 64*bitmap_granularity)
-        r = !!*((uint64_t*)bitmap);
-    else
-    {
-        unsigned bit_start = start / bitmap_granularity;
-        unsigned bit_end = ((start + len) + bitmap_granularity - 1) / bitmap_granularity;
-        while (bit_start < bit_end)
-        {
-            if (!(bit_start & 7) && bit_end >= bit_start+8)
-            {
-                r = r || !!((uint8_t*)bitmap)[bit_start / 8];
-                bit_start += 8;
-            }
-            else
-            {
-                r = r || (((uint8_t*)bitmap)[bit_start / 8] & (1 << (bit_start % 8)));
-                bit_start++;
-            }
-        }
-    }
-    return r;
-}

src/allocator.h

@@ -23,5 +23,3 @@ public:
 };
 
 void bitmap_set(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity);
-void bitmap_clear(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity);
-bool bitmap_check(void *bitmap, uint64_t start, uint64_t len, uint64_t bitmap_granularity);

src/blockstore.h

@@ -77,7 +77,6 @@ Output:
   -EINVAL = invalid input parameters
   -ENOENT = requested object/version does not exist for reads
   -ENOSPC = no space left in the store for writes
-  -EDOM = checksum error.
 - version = the version actually read or written
 
 ## BS_OP_DELETE

src/blockstore_disk.cpp

@@ -40,31 +40,10 @@ void blockstore_disk_t::parse_config(std::map<std::string, std::string> & config
     data_block_size = parse_size(config["block_size"]);
     journal_device = config["journal_device"];
     journal_offset = parse_size(config["journal_offset"]);
-    disk_alignment = parse_size(config["disk_alignment"]);
-    journal_block_size = parse_size(config["journal_block_size"]);
-    meta_block_size = parse_size(config["meta_block_size"]);
-    bitmap_granularity = parse_size(config["bitmap_granularity"]);
-    meta_format = stoull_full(config["meta_format"]);
-    cached_read_data = config["cached_read_data"] == "true" || config["cached_read_data"] == "yes" || config["cached_read_data"] == "1";
-    cached_read_meta = cached_read_data && (meta_device == data_device || meta_device == "") &&
-        config.find("cached_read_meta") == config.end() ||
-        config["cached_read_meta"] == "true" || config["cached_read_meta"] == "yes" || config["cached_read_meta"] == "1";
-    cached_read_journal = cached_read_meta && (journal_device == meta_device || journal_device == "") &&
-        config.find("cached_read_journal") == config.end() ||
-        config["cached_read_journal"] == "true" || config["cached_read_journal"] == "yes" || config["cached_read_journal"] == "1";
-    if (config["data_csum_type"] == "crc32c")
-    {
-        data_csum_type = BLOCKSTORE_CSUM_CRC32C;
-    }
-    else if (config["data_csum_type"] == "" || config["data_csum_type"] == "none")
-    {
-        data_csum_type = BLOCKSTORE_CSUM_NONE;
-    }
-    else
-    {
-        throw std::runtime_error("data_csum_type="+config["data_csum_type"]+" is unsupported, only \"crc32c\" and \"none\" are supported");
-    }
-    csum_block_size = parse_size(config["csum_block_size"]);
+    disk_alignment = strtoull(config["disk_alignment"].c_str(), NULL, 10);
+    journal_block_size = strtoull(config["journal_block_size"].c_str(), NULL, 10);
+    meta_block_size = strtoull(config["meta_block_size"].c_str(), NULL, 10);
+    bitmap_granularity = strtoull(config["bitmap_granularity"].c_str(), NULL, 10);
     // Validate
     if (!data_block_size)
     {
@@ -112,23 +91,7 @@ void blockstore_disk_t::parse_config(std::map<std::string, std::string> & config
     }
     if (data_block_size % bitmap_granularity)
     {
-        throw std::runtime_error("Data block size must be a multiple of sparse write tracking granularity");
-    }
-    if (!data_csum_type)
-    {
-        csum_block_size = 0;
-    }
-    else if (!csum_block_size)
-    {
-        csum_block_size = bitmap_granularity;
-    }
-    if (csum_block_size && (csum_block_size % bitmap_granularity))
-    {
-        throw std::runtime_error("Checksum block size must be a multiple of sparse write tracking granularity");
-    }
-    if (csum_block_size && (data_block_size % csum_block_size))
-    {
-        throw std::runtime_error("Checksum block size must be a divisor of data block size");
+        throw std::runtime_error("Block size must be a multiple of sparse write tracking granularity");
     }
     if (meta_device == "")
     {
@@ -147,9 +110,7 @@ void blockstore_disk_t::parse_config(std::map<std::string, std::string> & config
         throw std::runtime_error("journal_offset must be a multiple of journal_block_size = "+std::to_string(journal_block_size));
     }
     clean_entry_bitmap_size = data_block_size / bitmap_granularity / 8;
-    clean_dyn_size = clean_entry_bitmap_size*2 + (csum_block_size
-        ? data_block_size/csum_block_size*(data_csum_type & 0xFF) : 0);
-    clean_entry_size = sizeof(clean_disk_entry) + clean_dyn_size + 4 /*entry_csum*/;
+    clean_entry_size = sizeof(clean_disk_entry) + 2*clean_entry_bitmap_size;
 }
 
 void blockstore_disk_t::calc_lengths(bool skip_meta_check)
@@ -199,25 +160,6 @@ void blockstore_disk_t::calc_lengths(bool skip_meta_check)
     // required metadata size
     block_count = data_len / data_block_size;
     meta_len = (1 + (block_count - 1 + meta_block_size / clean_entry_size) / (meta_block_size / clean_entry_size)) * meta_block_size;
-    if (meta_format == BLOCKSTORE_META_FORMAT_V1 ||
-        !meta_format && !skip_meta_check && meta_area_size < meta_len && !data_csum_type)
-    {
-        uint64_t clean_entry_v0_size = sizeof(clean_disk_entry) + 2*clean_entry_bitmap_size;
-        uint64_t meta_v0_len = (1 + (block_count - 1 + meta_block_size / clean_entry_v0_size)
-            / (meta_block_size / clean_entry_v0_size)) * meta_block_size;
-        if (meta_format == BLOCKSTORE_META_FORMAT_V1 || meta_area_size >= meta_v0_len)
-        {
-            // Old metadata fits.
-            printf("Warning: Using old metadata format without checksums because the new format doesn't fit into provided area\n");
-            clean_entry_size = clean_entry_v0_size;
-            meta_len = meta_v0_len;
-            meta_format = BLOCKSTORE_META_FORMAT_V1;
-        }
-        else
-            meta_format = BLOCKSTORE_META_FORMAT_V2;
-    }
-    else
-        meta_format = BLOCKSTORE_META_FORMAT_V2;
     if (!skip_meta_check && meta_area_size < meta_len)
     {
         throw std::runtime_error("Metadata area is too small, need at least "+std::to_string(meta_len)+" bytes");
@@ -295,18 +237,6 @@ void blockstore_disk_t::open_data()
     {
         throw std::runtime_error(std::string("Failed to lock data device: ") + strerror(errno));
     }
-    if (cached_read_data)
-    {
-        read_data_fd = open(data_device.c_str(), O_RDWR);
-        if (read_data_fd == -1)
-        {
-            throw std::runtime_error("Failed to open data device "+data_device+": "+std::string(strerror(errno)));
-        }
-    }
-    else
-    {
-        read_data_fd = data_fd;
-    }
 }
 
 void blockstore_disk_t::open_meta()
@@ -327,18 +257,6 @@ void blockstore_disk_t::open_meta()
         {
             throw std::runtime_error(std::string("Failed to lock metadata device: ") + strerror(errno));
         }
-        if (cached_read_meta)
-        {
-            read_meta_fd = open(meta_device.c_str(), O_RDWR);
-            if (read_meta_fd == -1)
-            {
-                throw std::runtime_error("Failed to open metadata device "+meta_device+": "+std::string(strerror(errno)));
-            }
-        }
-        else
-        {
-            read_meta_fd = meta_fd;
-        }
     }
     else
     {
@@ -357,22 +275,6 @@ void blockstore_disk_t::open_meta()
             ") is not a multiple of data device sector size ("+std::to_string(meta_device_sect)+")"
         );
     }
-    if (!cached_read_meta)
-    {
-        read_meta_fd = meta_fd;
-    }
-    else if (meta_device == data_device && cached_read_data)
-    {
-        read_meta_fd = read_data_fd;
-    }
-    else
-    {
-        read_meta_fd = open(meta_device.c_str(), O_RDWR);
-        if (read_meta_fd == -1)
-        {
-            throw std::runtime_error("Failed to open metadata device "+meta_device+": "+std::string(strerror(errno)));
-        }
-    }
 }
 
 void blockstore_disk_t::open_journal()
@@ -407,26 +309,6 @@ void blockstore_disk_t::open_journal()
             ") is not a multiple of journal device sector size ("+std::to_string(journal_device_sect)+")"
         );
     }
-    if (!cached_read_journal)
-    {
-        read_journal_fd = journal_fd;
-    }
-    else if (journal_device == meta_device && cached_read_meta)
-    {
-        read_journal_fd = read_meta_fd;
-    }
-    else if (journal_device == data_device && cached_read_data)
-    {
-        read_journal_fd = read_data_fd;
-    }
-    else
-    {
-        read_journal_fd = open(journal_device.c_str(), O_RDWR);
-        if (read_journal_fd == -1)
-        {
-            throw std::runtime_error("Failed to open journal device "+journal_device+": "+std::string(strerror(errno)));
-        }
-    }
 }
 
 void blockstore_disk_t::close_all()
@@ -437,12 +319,5 @@ void blockstore_disk_t::close_all()
         close(meta_fd);
     if (journal_fd >= 0 && journal_fd != meta_fd)
         close(journal_fd);
-    if (read_data_fd >= 0 && read_data_fd != data_fd)
-        close(read_data_fd);
-    if (read_meta_fd >= 0 && read_meta_fd != meta_fd)
-        close(read_meta_fd);
-    if (read_journal_fd >= 0 && read_journal_fd != journal_fd)
-        close(read_journal_fd);
     data_fd = meta_fd = journal_fd = -1;
-    read_data_fd = read_meta_fd = read_journal_fd = -1;
 }

src/blockstore_disk.h

@@ -8,10 +8,6 @@
 #include <string>
 #include <map>
 
-#define BLOCKSTORE_CSUM_NONE 0
-// Lower byte of checksum type is its length
-#define BLOCKSTORE_CSUM_CRC32C 0x104
-
 struct blockstore_disk_t
 {
     std::string data_device, meta_device, journal_device;
@@ -25,24 +21,17 @@ struct blockstore_disk_t
     uint64_t meta_block_size = 4096;
     // Sparse write tracking granularity. 4 KB is a good choice. Must be a multiple of disk_alignment
     uint64_t bitmap_granularity = 4096;
-    // Data checksum type, BLOCKSTORE_CSUM_NONE or BLOCKSTORE_CSUM_CRC32C
-    uint32_t data_csum_type = BLOCKSTORE_CSUM_NONE;
-    // Checksum block size, must be a multiple of bitmap_granularity
-    uint32_t csum_block_size = 4096;
     // By default, Blockstore locks all opened devices exclusively. This option can be used to disable locking
     bool disable_flock = false;
-    // Use linux page cache for reads. If enabled, separate buffered FDs will be opened for reading
-    bool cached_read_data = false, cached_read_meta = false, cached_read_journal = false;
 
     int meta_fd = -1, data_fd = -1, journal_fd = -1;
-    int read_meta_fd = -1, read_data_fd = -1, read_journal_fd = -1;
-    uint64_t meta_offset, meta_device_sect, meta_device_size, meta_len, meta_format = 0;
+    uint64_t meta_offset, meta_device_sect, meta_device_size, meta_len;
     uint64_t data_offset, data_device_sect, data_device_size, data_len;
     uint64_t journal_offset, journal_device_sect, journal_device_size, journal_len;
 
     uint32_t block_order;
     uint64_t block_count;
-    uint32_t clean_entry_bitmap_size = 0, clean_entry_size = 0, clean_dyn_size = 0;
+    uint32_t clean_entry_bitmap_size = 0, clean_entry_size = 0;
 
     void parse_config(std::map<std::string, std::string> & config);
     void open_data();
@@ -50,13 +39,4 @@ struct blockstore_disk_t
     void open_journal();
     void calc_lengths(bool skip_meta_check = false);
     void close_all();
-
-    inline uint64_t dirty_dyn_size(uint64_t offset, uint64_t len)
-    {
-        // Checksums may be partial if write is not aligned with csum_block_size
-        return clean_entry_bitmap_size + (csum_block_size && len > 0
-            ? ((offset+len+csum_block_size-1)/csum_block_size - offset/csum_block_size)
-                * (data_csum_type & 0xFF)
-            : 0);
-    }
 };

src/blockstore_flush.h

@@ -1,22 +1,10 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 
-#define COPY_BUF_JOURNAL 1
-#define COPY_BUF_DATA 2
-#define COPY_BUF_ZERO 4
-#define COPY_BUF_CSUM_FILL 8
-#define COPY_BUF_COALESCED 16
-#define COPY_BUF_META_BLOCK 32
-#define COPY_BUF_JOURNALED_BIG 64
-
 struct copy_buffer_t
 {
-    int copy_flags;
-    uint64_t offset, len, disk_offset;
-    uint64_t journal_sector; // only for reads: sector+1 if used and !journal.inmemory, otherwise 0
+    uint64_t offset, len;
     void *buf;
-    uint8_t *csum_buf;
-    int *dyn_data;
 };
 
 struct meta_sector_t
@@ -49,7 +37,7 @@ class journal_flusher_co
 {
     blockstore_impl_t *bs;
     journal_flusher_t *flusher;
-    int wait_state, wait_count, wait_journal_count;
+    int wait_state, wait_count;
     struct io_uring_sqe *sqe;
     struct ring_data_t *data;
 
@@ -58,39 +46,28 @@ class journal_flusher_co
     obj_ver_id cur;
     std::map<obj_ver_id, dirty_entry>::iterator dirty_it, dirty_start, dirty_end;
     std::map<object_id, uint64_t>::iterator repeat_it;
-    std::function<void(ring_data_t*)> simple_callback_r, simple_callback_rj, simple_callback_w;
+    std::function<void(ring_data_t*)> simple_callback_r, simple_callback_w;
 
     bool skip_copy, has_delete, has_writes;
     std::vector<copy_buffer_t> v;
     std::vector<copy_buffer_t>::iterator it;
-    int i;
-    bool fill_incomplete, cleared_incomplete;
-    int read_to_fill_incomplete;
     int copy_count;
-    uint64_t clean_loc, clean_ver, old_clean_loc, old_clean_ver;
+    uint64_t clean_loc, old_clean_loc;
     flusher_meta_write_t meta_old, meta_new;
     bool clean_init_bitmap;
     uint64_t clean_bitmap_offset, clean_bitmap_len;
-    uint8_t *clean_init_dyn_ptr;
-    uint8_t *new_clean_bitmap;
+    void *new_clean_bitmap;
 
     uint64_t new_trim_pos;
 
+    // local: scan_dirty()
+    uint64_t offset, end_offset, submit_offset, submit_len;
+
     friend class journal_flusher_t;
-    void scan_dirty();
-    bool read_dirty(int wait_base);
-    bool modify_meta_do_reads(int wait_base);
-    bool wait_meta_reads(int wait_base);
+    bool scan_dirty(int wait_base);
     bool modify_meta_read(uint64_t meta_loc, flusher_meta_write_t &wr, int wait_base);
-    bool clear_incomplete_csum_block_bits(int wait_base);
-    void calc_block_checksums(uint32_t *new_data_csums, bool skip_overwrites);
-    void update_metadata_entry();
-    bool write_meta_block(flusher_meta_write_t & meta_block, int wait_base);
     void update_clean_db();
-    void free_data_blocks();
     bool fsync_batch(bool fsync_meta, int wait_base);
-    bool trim_journal(int wait_base);
-    void free_buffers();
 public:
     journal_flusher_co();
     bool loop();
@@ -118,10 +95,9 @@ class journal_flusher_t
 
     std::map<uint64_t, meta_sector_t> meta_sectors;
     std::deque<object_id> flush_queue;
-    std::map<object_id, uint64_t> flush_versions; // FIXME: consider unordered_map?
+    std::map<object_id, uint64_t> flush_versions;
 
     bool try_find_older(std::map<obj_ver_id, dirty_entry>::iterator & dirty_end, obj_ver_id & cur);
-    bool try_find_other(std::map<obj_ver_id, dirty_entry>::iterator & dirty_end, obj_ver_id & cur);
 
 public:
     journal_flusher_t(blockstore_impl_t *bs);
@@ -136,5 +112,4 @@ public:
     void unshift_flush(obj_ver_id oid, bool force);
     void remove_flush(object_id oid);
     void dump_diagnostics();
-    bool is_mutated(uint64_t clean_loc);
 };

src/blockstore_impl.cpp

@@ -13,7 +13,6 @@ blockstore_impl_t::blockstore_impl_t(blockstore_config_t & config, ring_loop_t *
     initialized = 0;
     parse_config(config, true);
     zero_object = (uint8_t*)memalign_or_die(MEM_ALIGNMENT, dsk.data_block_size);
-    alloc_dyn_data = dsk.clean_dyn_size > sizeof(void*) || dsk.csum_block_size > 0;
     try
     {
         dsk.open_data();
@@ -39,8 +38,8 @@ blockstore_impl_t::~blockstore_impl_t()
     dsk.close_all();
     if (metadata_buffer)
         free(metadata_buffer);
-    if (clean_bitmaps)
-        free(clean_bitmaps);
+    if (clean_bitmap)
+        free(clean_bitmap);
 }
 
 bool blockstore_impl_t::is_started()

src/blockstore_impl.h

@@ -93,10 +93,11 @@
 
 // "VITAstor"
 #define BLOCKSTORE_META_MAGIC_V1 0x726F747341544956l
-#define BLOCKSTORE_META_FORMAT_V1 1
-#define BLOCKSTORE_META_FORMAT_V2 2
+#define BLOCKSTORE_META_VERSION_V1 1
 
 // metadata header (superblock)
+// FIXME: After adding the OSD superblock, add a key to metadata
+// and journal headers to check if they belong to the same OSD
 struct __attribute__((__packed__)) blockstore_meta_header_v1_t
 {
     uint64_t zero;
@@ -107,29 +108,14 @@ struct __attribute__((__packed__)) blockstore_meta_header_v1_t
     uint32_t bitmap_granularity;
 };
 
-struct __attribute__((__packed__)) blockstore_meta_header_v2_t
-{
-    uint64_t zero;
-    uint64_t magic;
-    uint64_t version;
-    uint32_t meta_block_size;
-    uint32_t data_block_size;
-    uint32_t bitmap_granularity;
-    uint32_t data_csum_type;
-    uint32_t csum_block_size;
-    uint32_t header_csum;
-};
-
 // 32 bytes = 24 bytes + block bitmap (4 bytes by default) + external attributes (also bitmap, 4 bytes by default)
 // per "clean" entry on disk with fixed metadata tables
+// FIXME: maybe add crc32's to metadata
 struct __attribute__((__packed__)) clean_disk_entry
 {
     object_id oid;
     uint64_t version;
     uint8_t bitmap[];
-    // Two more fields come after bitmap in metadata version 2:
-    // uint32_t data_csum[];
-    // uint32_t entry_csum;
 };
 
 // 32 = 16 + 16 bytes per "clean" entry in memory (object_id => clean_entry)
@@ -139,7 +125,7 @@ struct __attribute__((__packed__)) clean_entry
     uint64_t location;
 };
 
-// 64 = 24 + 40 bytes per dirty entry in memory (obj_ver_id => dirty_entry). Plus checksums
+// 64 = 24 + 40 bytes per dirty entry in memory (obj_ver_id => dirty_entry)
 struct __attribute__((__packed__)) dirty_entry
 {
     uint32_t state;
@@ -148,7 +134,7 @@ struct __attribute__((__packed__)) dirty_entry
     uint32_t offset;   // data offset within object (stripe)
     uint32_t len;      // data length
     uint64_t journal_sector; // journal sector used for this entry
-    void* dyn_data;    // dynamic data: external bitmap and data block checksums. may be a pointer to the in-memory journal
+    void* bitmap;   // either external bitmap itself when it fits, or a pointer to it when it doesn't
 };
 
 // - Sync must be submitted after previous writes/deletes (not before!)
@@ -177,23 +163,12 @@ struct __attribute__((__packed__)) dirty_entry
 // Suspend operation until there is some free space on the data device
 #define WAIT_FREE 5
 
-struct used_clean_obj_t
+struct fulfill_read_t
 {
-    int refs;
-    bool was_freed; // was freed by a parallel flush?
-    bool was_changed; // was changed by a parallel flush?
+    uint64_t offset, len;
+    uint64_t journal_sector; // sector+1 if used and !journal.inmemory, otherwise 0
 };
 
-// https://github.com/algorithm-ninja/cpp-btree
-// https://github.com/greg7mdp/sparsepp/ was used previously, but it was TERRIBLY slow after resizing
-// with sparsepp, random reads dropped to ~700 iops very fast with just as much as ~32k objects in the DB
-typedef btree::btree_map<object_id, clean_entry> blockstore_clean_db_t;
-typedef std::map<obj_ver_id, dirty_entry> blockstore_dirty_db_t;
-
-#include "blockstore_init.h"
-
-#include "blockstore_flush.h"
-
 #define PRIV(op) ((blockstore_op_private_t*)(op)->private_data)
 #define FINISH_OP(op) PRIV(op)->~blockstore_op_private_t(); std::function<void (blockstore_op_t*)>(op->callback)(op)
 
@@ -206,8 +181,7 @@ struct blockstore_op_private_t
     int op_state;
 
     // Read
-    uint64_t clean_block_used;
-    std::vector<copy_buffer_t> read_vec;
+    std::vector<fulfill_read_t> read_vec;
 
     // Sync, write
     int min_flushed_journal_sector, max_flushed_journal_sector;
@@ -223,6 +197,16 @@ struct blockstore_op_private_t
     int sync_small_checked, sync_big_checked;
 };
 
+// https://github.com/algorithm-ninja/cpp-btree
+// https://github.com/greg7mdp/sparsepp/ was used previously, but it was TERRIBLY slow after resizing
+// with sparsepp, random reads dropped to ~700 iops very fast with just as much as ~32k objects in the DB
+typedef btree::btree_map<object_id, clean_entry> blockstore_clean_db_t;
+typedef std::map<obj_ver_id, dirty_entry> blockstore_dirty_db_t;
+
+#include "blockstore_init.h"
+
+#include "blockstore_flush.h"
+
 typedef uint32_t pool_id_t;
 typedef uint64_t pool_pg_id_t;
 
@@ -269,7 +253,7 @@ class blockstore_impl_t
 
     std::map<pool_id_t, pool_shard_settings_t> clean_db_settings;
     std::map<pool_pg_id_t, blockstore_clean_db_t> clean_db_shards;
-    uint8_t *clean_bitmaps = NULL;
+    uint8_t *clean_bitmap = NULL;
     blockstore_dirty_db_t dirty_db;
     std::vector<blockstore_op_t*> submit_queue;
     std::vector<obj_ver_id> unsynced_big_writes, unsynced_small_writes;
@@ -283,10 +267,6 @@ class blockstore_impl_t
     journal_flusher_t *flusher;
     int big_to_flush = 0;
     int write_iodepth = 0;
-    bool alloc_dyn_data = false;
-
-    // clean data blocks referenced by read operations
-    std::map<uint64_t, used_clean_obj_t> used_clean_objects;
 
     bool live = false, queue_stall = false;
     ring_loop_t *ringloop;
@@ -330,30 +310,8 @@ class blockstore_impl_t
 
     // Read
     int dequeue_read(blockstore_op_t *read_op);
-    void find_holes(std::vector<copy_buffer_t> & read_vec, uint32_t item_start, uint32_t item_end,
-        std::function<int(int, bool, uint32_t, uint32_t)> callback);
-    int fulfill_read(blockstore_op_t *read_op,
-        uint64_t &fulfilled, uint32_t item_start, uint32_t item_end,
-        uint32_t item_state, uint64_t item_version, uint64_t item_location,
-        uint64_t journal_sector, uint8_t *csum, int *dyn_data);
-    bool fulfill_clean_read(blockstore_op_t *read_op, uint64_t & fulfilled,
-        uint8_t *clean_entry_bitmap, int *dyn_data,
-        uint32_t item_start, uint32_t item_end, uint64_t clean_loc, uint64_t clean_ver);
-    int fill_partial_checksum_blocks(std::vector<copy_buffer_t> & rv, uint64_t & fulfilled,
-        uint8_t *clean_entry_bitmap, int *dyn_data, bool from_journal, uint8_t *read_buf, uint64_t read_offset, uint64_t read_end);
-    int pad_journal_read(std::vector<copy_buffer_t> & rv, copy_buffer_t & cp,
-        uint64_t dirty_offset, uint64_t dirty_end, uint64_t dirty_loc, uint8_t *csum_ptr, int *dyn_data,
-        uint64_t offset, uint64_t submit_len, uint64_t & blk_begin, uint64_t & blk_end, uint8_t* & blk_buf);
-    bool read_range_fulfilled(std::vector<copy_buffer_t> & rv, uint64_t & fulfilled, uint8_t *read_buf,
-        uint8_t *clean_entry_bitmap, uint32_t item_start, uint32_t item_end);
-    bool read_checksum_block(blockstore_op_t *op, int rv_pos, uint64_t &fulfilled, uint64_t clean_loc);
-    uint8_t* read_clean_meta_block(blockstore_op_t *read_op, uint64_t clean_loc, int rv_pos);
-    bool verify_padded_checksums(uint8_t *clean_entry_bitmap, uint8_t *csum_buf, uint32_t offset,
-        iovec *iov, int n_iov, std::function<void(uint32_t, uint32_t, uint32_t)> bad_block_cb);
-    bool verify_journal_checksums(uint8_t *csums, uint32_t offset,
-        iovec *iov, int n_iov, std::function<void(uint32_t, uint32_t, uint32_t)> bad_block_cb);
-    bool verify_clean_padded_checksums(blockstore_op_t *op, uint64_t clean_loc, uint8_t *dyn_data, bool from_journal,
-        iovec *iov, int n_iov, std::function<void(uint32_t, uint32_t, uint32_t)> bad_block_cb);
+    int fulfill_read(blockstore_op_t *read_op, uint64_t &fulfilled, uint32_t item_start, uint32_t item_end,
+        uint32_t item_state, uint64_t item_version, uint64_t item_location, uint64_t journal_sector);
     int fulfill_read_push(blockstore_op_t *op, void *buf, uint64_t offset, uint64_t len,
         uint32_t item_state, uint64_t item_version);
     void handle_read_event(ring_data_t *data, blockstore_op_t *op);
@@ -384,7 +342,6 @@ class blockstore_impl_t
     int continue_rollback(blockstore_op_t *op);
     void mark_rolled_back(const obj_ver_id & ov);
     void erase_dirty(blockstore_dirty_db_t::iterator dirty_start, blockstore_dirty_db_t::iterator dirty_end, uint64_t clean_loc);
-    void free_dirty_dyn_data(dirty_entry & e);
 
     // List
     void process_list(blockstore_op_t *op);

src/blockstore_init.cpp

@@ -65,7 +65,7 @@ int blockstore_init_meta::loop()
     GET_SQE();
     data->iov = { metadata_buffer, bs->dsk.meta_block_size };
     data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
-    my_uring_prep_readv(sqe, bs->dsk.read_meta_fd, &data->iov, 1, bs->dsk.meta_offset);
+    my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset);
     bs->ringloop->submit();
     submitted++;
 resume_1:
@@ -77,20 +77,13 @@ resume_1:
     if (iszero((uint64_t*)metadata_buffer, bs->dsk.meta_block_size / sizeof(uint64_t)))
     {
         {
-            blockstore_meta_header_v2_t *hdr = (blockstore_meta_header_v2_t *)metadata_buffer;
+            blockstore_meta_header_v1_t *hdr = (blockstore_meta_header_v1_t *)metadata_buffer;
             hdr->zero = 0;
             hdr->magic = BLOCKSTORE_META_MAGIC_V1;
-            hdr->version = bs->dsk.meta_format;
+            hdr->version = BLOCKSTORE_META_VERSION_V1;
             hdr->meta_block_size = bs->dsk.meta_block_size;
             hdr->data_block_size = bs->dsk.data_block_size;
             hdr->bitmap_granularity = bs->dsk.bitmap_granularity;
-            if (bs->dsk.meta_format >= BLOCKSTORE_META_FORMAT_V2)
-            {
-                hdr->data_csum_type = bs->dsk.data_csum_type;
-                hdr->csum_block_size = bs->dsk.csum_block_size;
-                hdr->header_csum = 0;
-                hdr->header_csum = crc32c(0, hdr, sizeof(*hdr));
-            }
         }
         if (bs->readonly)
         {
@@ -116,62 +109,28 @@ resume_1:
     }
     else
     {
-        blockstore_meta_header_v2_t *hdr = (blockstore_meta_header_v2_t *)metadata_buffer;
-        if (hdr->zero != 0 || hdr->magic != BLOCKSTORE_META_MAGIC_V1 || hdr->version < BLOCKSTORE_META_FORMAT_V1)
+        blockstore_meta_header_v1_t *hdr = (blockstore_meta_header_v1_t *)metadata_buffer;
+        if (hdr->zero != 0 ||
+            hdr->magic != BLOCKSTORE_META_MAGIC_V1 ||
+            hdr->version != BLOCKSTORE_META_VERSION_V1)
         {
             printf(
-                "Metadata is corrupt or too old (pre-0.6.x).\n"
-                " If this is a new OSD, please zero out the metadata area before starting it.\n"
-                " If you need to upgrade from 0.5.x, convert metadata with vitastor-disk.\n"
-            );
-            exit(1);
-        }
-        if (hdr->version == BLOCKSTORE_META_FORMAT_V2)
-        {
-            uint32_t csum = hdr->header_csum;
-            hdr->header_csum = 0;
-            if (crc32c(0, hdr, sizeof(*hdr)) != csum)
-            {
-                printf("Metadata header is corrupt (checksum mismatch).\n");
-                exit(1);
-            }
-            hdr->header_csum = csum;
-            bs->dsk.meta_format = BLOCKSTORE_META_FORMAT_V2;
-        }
-        else if (hdr->version == BLOCKSTORE_META_FORMAT_V1)
-        {
-            hdr->data_csum_type = 0;
-            hdr->csum_block_size = 0;
-            hdr->header_csum = 0;
-            // Enable compatibility mode - entries without checksums
-            bs->dsk.clean_entry_size = sizeof(clean_disk_entry) + bs->dsk.clean_entry_bitmap_size*2;
-            bs->dsk.meta_len = (1 + (bs->dsk.block_count - 1 + bs->dsk.meta_block_size / bs->dsk.clean_entry_size)
-                / (bs->dsk.meta_block_size / bs->dsk.clean_entry_size)) * bs->dsk.meta_block_size;
-            bs->dsk.meta_format = BLOCKSTORE_META_FORMAT_V1;
-            printf("Warning: Starting with metadata in the old format without checksums, as stored on disk\n");
-        }
-        else if (hdr->version > BLOCKSTORE_META_FORMAT_V2)
-        {
-            printf(
-                "Metadata format is too new for me (stored version is %lu, max supported %u).\n",
-                hdr->version, BLOCKSTORE_META_FORMAT_V2
+                "Metadata is corrupt or old version.\n"
+                " If this is a new OSD please zero out the metadata area before starting it.\n"
+                " If you need to upgrade from 0.5.x please request it via the issue tracker.\n"
             );
             exit(1);
         }
         if (hdr->meta_block_size != bs->dsk.meta_block_size ||
             hdr->data_block_size != bs->dsk.data_block_size ||
-            hdr->bitmap_granularity != bs->dsk.bitmap_granularity ||
-            hdr->data_csum_type != bs->dsk.data_csum_type ||
-            hdr->csum_block_size != bs->dsk.csum_block_size)
+            hdr->bitmap_granularity != bs->dsk.bitmap_granularity)
         {
             printf(
                 "Configuration stored in metadata superblock"
-                " (meta_block_size=%u, data_block_size=%u, bitmap_granularity=%u, data_csum_type=%u, csum_block_size=%u)"
-                " differs from OSD configuration (%lu/%u/%lu, %u/%u).\n",
+                " (meta_block_size=%u, data_block_size=%u, bitmap_granularity=%u)"
+                " differs from OSD configuration (%lu/%u/%lu).\n",
                 hdr->meta_block_size, hdr->data_block_size, hdr->bitmap_granularity,
-                hdr->data_csum_type, hdr->csum_block_size,
-                bs->dsk.meta_block_size, bs->dsk.data_block_size, bs->dsk.bitmap_granularity,
-                bs->dsk.data_csum_type, bs->dsk.csum_block_size
+                bs->dsk.meta_block_size, bs->dsk.data_block_size, bs->dsk.bitmap_granularity
             );
             exit(1);
         }
@@ -202,7 +161,7 @@ resume_2:
                 data->iov = { bufs[i].buf, bufs[i].size };
                 data->callback = [this, i](ring_data_t *data) { handle_event(data, i); };
                 if (!zero_on_init)
-                    my_uring_prep_readv(sqe, bs->dsk.read_meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
+                    my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + bufs[i].offset);
                 else
                 {
                     // Fill metadata with zeroes
@@ -259,7 +218,7 @@ resume_2:
             GET_SQE();
             data->iov = { metadata_buffer, bs->dsk.meta_block_size };
             data->callback = [this](ring_data_t *data) { handle_event(data, -1); };
-            my_uring_prep_readv(sqe, bs->dsk.read_meta_fd, &data->iov, 1, bs->dsk.meta_offset + (1+next_offset)*bs->dsk.meta_block_size);
+            my_uring_prep_readv(sqe, bs->dsk.meta_fd, &data->iov, 1, bs->dsk.meta_offset + (1+next_offset)*bs->dsk.meta_block_size);
             submitted++;
 resume_5:
             if (submitted > 0)
@@ -320,22 +279,12 @@ bool blockstore_init_meta::handle_meta_block(uint8_t *buf, uint64_t entries_per_
     for (uint64_t i = 0; i < max_i; i++)
     {
         clean_disk_entry *entry = (clean_disk_entry*)(buf + i*bs->dsk.clean_entry_size);
+        if (!bs->inmemory_meta && bs->dsk.clean_entry_bitmap_size)
+        {
+            memcpy(bs->clean_bitmap + (done_cnt+i)*2*bs->dsk.clean_entry_bitmap_size, &entry->bitmap, 2*bs->dsk.clean_entry_bitmap_size);
+        }
         if (entry->oid.inode > 0)
         {
-            if (bs->dsk.meta_format >= BLOCKSTORE_META_FORMAT_V2)
-            {
-                // Check entry crc32
-                uint32_t *entry_csum = (uint32_t*)((uint8_t*)entry + bs->dsk.clean_entry_size - 4);
-                if (*entry_csum != crc32c(0, entry, bs->dsk.clean_entry_size - 4))
-                {
-                    printf("Metadata entry %lu is corrupt (checksum mismatch), skipping\n", done_cnt+i);
-                    continue;
-                }
-            }
-            if (!bs->inmemory_meta && bs->dsk.clean_entry_bitmap_size)
-            {
-                memcpy(bs->clean_bitmaps + (done_cnt+i) * 2 * bs->dsk.clean_entry_bitmap_size, &entry->bitmap, 2 * bs->dsk.clean_entry_bitmap_size);
-            }
             auto & clean_db = bs->clean_db_shard(entry->oid);
             auto clean_it = clean_db.find(entry->oid);
             if (clean_it == clean_db.end() || clean_it->second.version < entry->version)
@@ -467,7 +416,7 @@ int blockstore_init_journal::loop()
     data = ((ring_data_t*)sqe->user_data);
     data->iov = { submitted_buf, bs->journal.block_size };
     data->callback = simple_callback;
-    my_uring_prep_readv(sqe, bs->dsk.read_journal_fd, &data->iov, 1, bs->journal.offset);
+    my_uring_prep_readv(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset);
     bs->ringloop->submit();
     wait_count = 1;
 resume_1:
@@ -491,9 +440,7 @@ resume_1:
             .size = sizeof(journal_entry_start),
             .reserved = 0,
             .journal_start = bs->journal.block_size,
-            .version = JOURNAL_VERSION_V2,
-            .data_csum_type = bs->dsk.data_csum_type,
-            .csum_block_size = bs->dsk.csum_block_size,
+            .version = JOURNAL_VERSION,
         };
         ((journal_entry_start*)submitted_buf)->crc32 = je_crc32((journal_entry*)submitted_buf);
         if (bs->readonly)
@@ -545,36 +492,18 @@ resume_1:
         if (je_start->magic != JOURNAL_MAGIC ||
             je_start->type != JE_START ||
             je_crc32((journal_entry*)je_start) != je_start->crc32 ||
-            je_start->size != JE_START_V0_SIZE && je_start->size != JE_START_V1_SIZE && je_start->size != JE_START_V2_SIZE)
+            je_start->size != sizeof(journal_entry_start) && je_start->size != JE_START_LEGACY_SIZE)
         {
             // Entry is corrupt
-            fprintf(stderr, "First entry of the journal is corrupt or unsupported\n");
+            fprintf(stderr, "First entry of the journal is corrupt\n");
             exit(1);
         }
-        if (je_start->size == JE_START_V0_SIZE ||
-            (je_start->version != JOURNAL_VERSION_V1 || je_start->size != JE_START_V1_SIZE) &&
-            (je_start->version != JOURNAL_VERSION_V2 || je_start->size != JE_START_V2_SIZE))
+        if (je_start->size == JE_START_LEGACY_SIZE || je_start->version != JOURNAL_VERSION)
         {
             fprintf(
-                stderr, "The code only supports journal versions 2 and 1, but it is %lu on disk."
-                    " Please use vitastor-disk to rewrite the journal\n",
-                je_start->size == JE_START_V0_SIZE ? 0 : je_start->version
-            );
-            exit(1);
-        }
-        if (je_start->version == JOURNAL_VERSION_V1)
-        {
-            je_start->data_csum_type = 0;
-            je_start->csum_block_size = 0;
-        }
-        if (je_start->data_csum_type != bs->dsk.data_csum_type ||
-            je_start->csum_block_size != bs->dsk.csum_block_size)
-        {
-            printf(
-                "Configuration stored in journal superblock (data_csum_type=%u, csum_block_size=%u)"
-                " differs from OSD configuration (%u/%u).\n",
-                je_start->data_csum_type, je_start->csum_block_size,
-                bs->dsk.data_csum_type, bs->dsk.csum_block_size
+                stderr, "The code only supports journal version %d, but it is %lu on disk."
+                    " Please use the previous version to flush the journal before upgrading OSD\n",
+                JOURNAL_VERSION, je_start->size == JE_START_LEGACY_SIZE ? 0 : je_start->version
             );
             exit(1);
         }
@@ -607,7 +536,7 @@ resume_1:
                     end - journal_pos < JOURNAL_BUFFER_SIZE ? end - journal_pos : JOURNAL_BUFFER_SIZE,
                 };
                 data->callback = [this](ring_data_t *data1) { handle_event(data1); };
-                my_uring_prep_readv(sqe, bs->dsk.read_journal_fd, &data->iov, 1, bs->journal.offset + journal_pos);
+                my_uring_prep_readv(sqe, bs->dsk.journal_fd, &data->iov, 1, bs->journal.offset + journal_pos);
                 bs->ringloop->submit();
             }
             while (done.size() > 0)
@@ -776,14 +705,11 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                     snprintf(err, 1024, "BUG: calculated journal data offset (%08lx) != stored journal data offset (%08lx)", location, je->small_write.data_offset);
                     throw std::runtime_error(err);
                 }
-                small_write_data.clear();
+                uint32_t data_crc32 = 0;
                 if (location >= done_pos && location+je->small_write.len <= done_pos+len)
                 {
                     // data is within this buffer
-                    small_write_data.push_back((iovec){
-                        .iov_base = (uint8_t*)buf + location - done_pos,
-                        .iov_len = je->small_write.len,
-                    });
+                    data_crc32 = crc32c(0, (uint8_t*)buf + location - done_pos, je->small_write.len);
                 }
                 else
                 {
@@ -798,10 +724,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                                 ? location+je->small_write.len : done[i].pos+done[i].len);
                             uint64_t part_begin = (location < done[i].pos ? done[i].pos : location);
                             covered += part_end - part_begin;
-                            small_write_data.push_back((iovec){
-                                .iov_base = (uint8_t*)done[i].buf + part_begin - done[i].pos,
-                                .iov_len = part_end - part_begin,
-                            });
+                            data_crc32 = crc32c(data_crc32, (uint8_t*)done[i].buf + part_begin - done[i].pos, part_end - part_begin);
                         }
                     }
                     if (covered < je->small_write.len)
@@ -811,102 +734,12 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         return 2;
                     }
                 }
-                bool data_csum_valid = true;
-                if (!bs->dsk.csum_block_size)
-                {
-                    uint32_t data_crc32 = 0;
-                    for (auto & sd: small_write_data)
-                    {
-                        data_crc32 = crc32c(data_crc32, sd.iov_base, sd.iov_len);
-                    }
-                    data_csum_valid = data_crc32 == je->small_write.crc32_data;
-                    if (!data_csum_valid)
-                    {
-                        printf(
-                            "Journal entry data is corrupt for small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u - data crc32 %x != %x\n",
-                            je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
-                            je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
-                            je->small_write.offset, je->small_write.len,
-                            data_crc32, je->small_write.crc32_data
-                        );
-                    }
-                }
-                else if (je->small_write.len > 0)
-                {
-                    // FIXME: deduplicate with disk_tool_journal.cpp
-                    // like in enqueue_write()
-                    uint32_t start = je->small_write.offset / bs->dsk.csum_block_size;
-                    uint32_t end = (je->small_write.offset+je->small_write.len-1) / bs->dsk.csum_block_size;
-                    uint32_t data_csum_size = (end-start+1) * (bs->dsk.data_csum_type & 0xFF);
-                    uint32_t required_size = sizeof(journal_entry_small_write) + bs->dsk.clean_entry_bitmap_size + data_csum_size;
-                    if (je->size != required_size)
-                    {
-                        printf(
-                            "Journal entry data has invalid size for small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u - should be %u bytes but is %u bytes\n",
-                            je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
-                            je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
-                            je->small_write.offset, je->small_write.len,
-                            required_size, je->size
-                        );
-                        data_csum_valid = false;
-                    }
-                    else
-                    {
-                        int sd_num = 0;
-                        size_t sd_pos = 0;
-                        uint32_t *block_csums = (uint32_t*)((uint8_t*)je + sizeof(journal_entry_small_write) + bs->dsk.clean_entry_bitmap_size);
-                        for (uint32_t pos = start; pos <= end; pos++, block_csums++)
-                        {
-                            size_t block_left = (pos == start
-                                ? (start == end
-                                    ? je->small_write.len
-                                    : bs->dsk.csum_block_size - je->small_write.offset%bs->dsk.csum_block_size)
-                                : (pos < end
-                                    ? bs->dsk.csum_block_size
-                                    : (je->small_write.offset + je->small_write.len)%bs->dsk.csum_block_size));
-                            if (pos > start && pos == end && block_left == 0)
-                            {
-                                // full last block
-                                block_left = bs->dsk.csum_block_size;
-                            }
-                            uint32_t block_crc32 = 0;
-                            while (block_left > 0)
-                            {
-                                assert(sd_num < small_write_data.size());
-                                if (small_write_data[sd_num].iov_len >= sd_pos+block_left)
-                                {
-                                    block_crc32 = crc32c(block_crc32, (uint8_t*)small_write_data[sd_num].iov_base+sd_pos, block_left);
-                                    sd_pos += block_left;
-                                    break;
-                                }
-                                else
-                                {
-                                    block_crc32 = crc32c(block_crc32, (uint8_t*)small_write_data[sd_num].iov_base+sd_pos, small_write_data[sd_num].iov_len-sd_pos);
-                                    block_left -= (small_write_data[sd_num].iov_len-sd_pos);
-                                    sd_pos = 0;
-                                    sd_num++;
-                                }
-                            }
-                            if (block_crc32 != *block_csums)
-                            {
-                                printf(
-                                    "Journal entry data is corrupt for small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u - block %u crc32 %x != %x\n",
-                                    je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
-                                    je->small_write.oid.inode, je->small_write.oid.stripe, je->small_write.version,
-                                    je->small_write.offset, je->small_write.len,
-                                    pos, block_crc32, *block_csums
-                                );
-                                data_csum_valid = false;
-                                break;
-                            }
-                        }
-                    }
-                }
-                if (!data_csum_valid)
+                if (data_crc32 != je->small_write.crc32_data)
                 {
                     // journal entry is corrupt, stop here
                     // interesting thing is that we must clear the corrupt entry if we're not readonly,
                     // because we don't write next entries in the same journal block
+                    printf("Journal entry data is corrupt (data crc32 %x != %x)\n", data_crc32, je->small_write.crc32_data);
                     memset((uint8_t*)buf + proc_pos - done_pos + pos, 0, bs->journal.block_size - pos);
                     bs->journal.next_free = prev_free;
                     init_write_buf = (uint8_t*)buf + proc_pos - done_pos;
@@ -922,14 +755,11 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         .oid = je->small_write.oid,
                         .version = je->small_write.version,
                     };
-                    uint64_t dyn_size = bs->dsk.dirty_dyn_size(je->small_write.offset, je->small_write.len);
-                    void *dyn = NULL;
-                    void *dyn_from = (uint8_t*)je + sizeof(journal_entry_small_write);
-                    if (!bs->alloc_dyn_data)
+                    void *bmp = NULL;
+                    void *bmp_from = (uint8_t*)je + sizeof(journal_entry_small_write);
+                    if (bs->dsk.clean_entry_bitmap_size <= sizeof(void*))
                     {
-                        // Bitmap without checksum is only 4 bytes for 128k objects, save it inline
-                        // It can even contain 4 byte bitmap + 4 byte CRC32 for 4 kb writes :)
-                        memcpy(&dyn, dyn_from, dyn_size);
+                        memcpy(&bmp, bmp_from, bs->dsk.clean_entry_bitmap_size);
                     }
                     else
                     {
@@ -937,9 +767,8 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         // allocations for entry bitmaps. This can only be fixed by using
                         // a patched map with dynamic entry size, but not the btree_map,
                         // because it doesn't keep iterators valid all the time.
-                        dyn = malloc_or_die(dyn_size+sizeof(int));
-                        *((int*)dyn) = 1;
-                        memcpy((uint8_t*)dyn+sizeof(int), dyn_from, dyn_size);
+                        bmp = malloc_or_die(bs->dsk.clean_entry_bitmap_size);
+                        memcpy(bmp, bmp_from, bs->dsk.clean_entry_bitmap_size);
                     }
                     bs->dirty_db.emplace(ov, (dirty_entry){
                         .state = (BS_ST_SMALL_WRITE | BS_ST_SYNCED),
@@ -948,7 +777,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         .offset = je->small_write.offset,
                         .len = je->small_write.len,
                         .journal_sector = proc_pos,
-                        .dyn_data = dyn,
+                        .bitmap = bmp,
                     });
                     bs->journal.used_sectors[proc_pos]++;
 #ifdef BLOCKSTORE_DEBUG
@@ -1007,13 +836,11 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         .oid = je->big_write.oid,
                         .version = je->big_write.version,
                     };
-                    uint64_t dyn_size = bs->dsk.dirty_dyn_size(je->big_write.offset, je->big_write.len);
-                    void *dyn = NULL;
-                    void *dyn_from = (uint8_t*)je + sizeof(journal_entry_big_write);
-                    if (!bs->alloc_dyn_data)
+                    void *bmp = NULL;
+                    void *bmp_from = (uint8_t*)je + sizeof(journal_entry_big_write);
+                    if (bs->dsk.clean_entry_bitmap_size <= sizeof(void*))
                     {
-                        // Bitmap without checksum is only 4 bytes for 128k objects, save it inline
-                        memcpy(&dyn, dyn_from, dyn_size);
+                        memcpy(&bmp, bmp_from, bs->dsk.clean_entry_bitmap_size);
                     }
                     else
                     {
@@ -1021,9 +848,8 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         // allocations for entry bitmaps. This can only be fixed by using
                         // a patched map with dynamic entry size, but not the btree_map,
                         // because it doesn't keep iterators valid all the time.
-                        dyn = malloc_or_die(dyn_size+sizeof(int));
-                        *((int*)dyn) = 1;
-                        memcpy((uint8_t*)dyn+sizeof(int), dyn_from, dyn_size);
+                        bmp = malloc_or_die(bs->dsk.clean_entry_bitmap_size);
+                        memcpy(bmp, bmp_from, bs->dsk.clean_entry_bitmap_size);
                     }
                     auto dirty_it = bs->dirty_db.emplace(ov, (dirty_entry){
                         .state = (BS_ST_BIG_WRITE | BS_ST_SYNCED),
@@ -1032,7 +858,7 @@ int blockstore_init_journal::handle_journal_part(void *buf, uint64_t done_pos, u
                         .offset = je->big_write.offset,
                         .len = je->big_write.len,
                         .journal_sector = proc_pos,
-                        .dyn_data = dyn,
+                        .bitmap = bmp,
                     }).first;
                     if (bs->data_alloc->get(je->big_write.location >> bs->dsk.block_order))
                     {

src/blockstore_init.h

@@ -50,7 +50,6 @@ class blockstore_init_journal
     uint64_t next_free;
     std::vector<bs_init_journal_done> done;
     std::vector<obj_ver_id> double_allocs;
-    std::vector<iovec> small_write_data;
     uint64_t journal_pos = 0;
     uint64_t continue_pos = 0;
     void *init_write_buf = NULL;

src/blockstore_journal.cpp

@@ -17,7 +17,6 @@ blockstore_journal_check_t::blockstore_journal_check_t(blockstore_impl_t *bs)
 // Check if we can write <required> entries of <size> bytes and <data_after> data bytes after them to the journal
 int blockstore_journal_check_t::check_available(blockstore_op_t *op, int entries_required, int size, int data_after)
 {
-    uint64_t prev_next = next_sector;
     int required = entries_required;
     while (1)
     {
@@ -36,19 +35,11 @@ int blockstore_journal_check_t::check_available(blockstore_op_t *op, int entries
             }
             required -= fits;
             next_in_pos += fits * size;
-            if (next_sector != prev_next || !sectors_to_write)
-            {
-                // Except the previous call to this function
-                sectors_to_write++;
-            }
+            sectors_to_write++;
         }
         else if (bs->journal.sector_info[next_sector].dirty)
         {
-            if (next_sector != prev_next || !sectors_to_write)
-            {
-                // Except the previous call to this function
-                sectors_to_write++;
-            }
+            sectors_to_write++;
         }
         if (required <= 0)
         {
@@ -298,31 +289,3 @@ void journal_t::dump_diagnostics()
         journal_used_it == used_sectors.end() ? 0 : journal_used_it->second
     );
 }
-
-static uint64_t zero_page[4096];
-
-uint32_t crc32c_pad(uint32_t prev_crc, const void *buf, size_t len, size_t left_pad, size_t right_pad)
-{
-    uint32_t r = prev_crc;
-    while (left_pad >= 4096)
-    {
-        r = crc32c(r, zero_page, 4096);
-        left_pad -= 4096;
-    }
-    if (left_pad > 0)
-        r = crc32c(r, zero_page, left_pad);
-    r = crc32c(r, buf, len);
-    while (right_pad >= 4096)
-    {
-        r = crc32c(r, zero_page, 4096);
-        right_pad -= 4096;
-    }
-    if (left_pad > 0)
-        r = crc32c(r, zero_page, right_pad);
-    return r;
-}
-
-uint32_t crc32c_nopad(uint32_t prev_crc, const void *buf, size_t len, size_t left_pad, size_t right_pad)
-{
-    return crc32c(0, buf, len);
-}

src/blockstore_journal.h

@@ -8,8 +8,7 @@
 
 #define MIN_JOURNAL_SIZE 4*1024*1024
 #define JOURNAL_MAGIC 0x4A33
-#define JOURNAL_VERSION_V1 1
-#define JOURNAL_VERSION_V2 2
+#define JOURNAL_VERSION 1
 #define JOURNAL_BUFFER_SIZE 4*1024*1024
 #define JOURNAL_ENTRY_HEADER_SIZE 16
 
@@ -33,7 +32,7 @@
 #define JE_BIG_WRITE_INSTANT   0x08
 #define JE_MAX         0x08
 
-// crc32c comes first to ease calculation
+// crc32c comes first to ease calculation and is equal to crc32()
 struct __attribute__((__packed__)) journal_entry_start
 {
     uint32_t crc32;
@@ -43,12 +42,8 @@ struct __attribute__((__packed__)) journal_entry_start
     uint32_t reserved;
     uint64_t journal_start;
     uint64_t version;
-    uint32_t data_csum_type;
-    uint32_t csum_block_size;
 };
-#define JE_START_V0_SIZE 24
-#define JE_START_V1_SIZE 32
-#define JE_START_V2_SIZE 40
+#define JE_START_LEGACY_SIZE 24
 
 struct __attribute__((__packed__)) journal_entry_small_write
 {
@@ -64,12 +59,10 @@ struct __attribute__((__packed__)) journal_entry_small_write
     // small_write entries contain <len> bytes of data which is stored in next sectors
     // data_offset is its offset within journal
     uint64_t data_offset;
-    uint32_t crc32_data; // zero when data_csum_type != 0
+    uint32_t crc32_data;
     // small_write and big_write entries are followed by the "external" bitmap
     // its size is dynamic and included in journal entry's <size> field
     uint8_t bitmap[];
-    // and then data checksums if data_csum_type != 0
-    // uint32_t data_crc32c[];
 };
 
 struct __attribute__((__packed__)) journal_entry_big_write
@@ -87,8 +80,6 @@ struct __attribute__((__packed__)) journal_entry_big_write
     // small_write and big_write entries are followed by the "external" bitmap
     // its size is dynamic and included in journal entry's <size> field
     uint8_t bitmap[];
-    // and then data checksums if data_csum_type != 0
-    // uint32_t data_crc32c[];
 };
 
 struct __attribute__((__packed__)) journal_entry_stable
@@ -227,6 +218,3 @@ struct blockstore_journal_check_t
 };
 
 journal_entry* prefill_single_journal_entry(journal_t & journal, uint16_t type, uint32_t size);
-
-uint32_t crc32c_pad(uint32_t prev_crc, const void *buf, size_t len, size_t left_pad, size_t right_pad);
-uint32_t crc32c_nopad(uint32_t prev_crc, const void *buf, size_t len, size_t left_pad, size_t right_pad);

src/blockstore_open.cpp

@@ -133,24 +133,19 @@ void blockstore_impl_t::calc_lengths()
     {
         metadata_buffer = memalign(MEM_ALIGNMENT, dsk.meta_len);
         if (!metadata_buffer)
-            throw std::runtime_error("Failed to allocate memory for the metadata ("+std::to_string(dsk.meta_len/1024/1024)+" MB)");
+            throw std::runtime_error("Failed to allocate memory for the metadata");
     }
-    else if (dsk.clean_entry_bitmap_size || dsk.data_csum_type)
+    else if (dsk.clean_entry_bitmap_size)
     {
-        clean_bitmaps = (uint8_t*)malloc(dsk.block_count * 2 * dsk.clean_entry_bitmap_size);
-        if (!clean_bitmaps)
-        {
-            throw std::runtime_error(
-                "Failed to allocate memory for the metadata sparse write bitmap ("+
-                std::to_string(dsk.block_count * 2 * dsk.clean_entry_bitmap_size / 1024 / 1024)+" MB)"
-            );
-        }
+        clean_bitmap = (uint8_t*)malloc(dsk.block_count * 2*dsk.clean_entry_bitmap_size);
+        if (!clean_bitmap)
+            throw std::runtime_error("Failed to allocate memory for the metadata sparse write bitmap");
     }
     if (journal.inmemory)
     {
         journal.buffer = memalign(MEM_ALIGNMENT, journal.len);
         if (!journal.buffer)
-            throw std::runtime_error("Failed to allocate memory for journal ("+std::to_string(journal.len/1024/1024)+" MB)");
+            throw std::runtime_error("Failed to allocate memory for journal");
     }
     else
     {

src/blockstore_read.cpp

@@ -1,7 +1,6 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 
-#include <limits.h>
 #include "blockstore_impl.h"
 
 int blockstore_impl_t::fulfill_read_push(blockstore_op_t *op, void *buf, uint64_t offset, uint64_t len,
@@ -9,7 +8,12 @@ int blockstore_impl_t::fulfill_read_push(blockstore_op_t *op, void *buf, uint64_
 {
     if (!len)
     {
-        // Zero-length read
+        // Zero-length version - skip
+        return 1;
+    }
+    else if (IS_IN_FLIGHT(item_state))
+    {
+        // Write not finished yet - skip
         return 1;
     }
     else if (IS_DELETE(item_state))
@@ -18,7 +22,6 @@ int blockstore_impl_t::fulfill_read_push(blockstore_op_t *op, void *buf, uint64_
         memset(buf, 0, len);
         return 1;
     }
-    assert(!IS_IN_FLIGHT(item_state));
     if (journal.inmemory && IS_JOURNAL(item_state))
     {
         memcpy(buf, (uint8_t*)journal.buffer + offset, len);
@@ -29,7 +32,7 @@ int blockstore_impl_t::fulfill_read_push(blockstore_op_t *op, void *buf, uint64_
     PRIV(op)->pending_ops++;
     my_uring_prep_readv(
         sqe,
-        IS_JOURNAL(item_state) ? dsk.read_journal_fd : dsk.read_data_fd,
+        IS_JOURNAL(item_state) ? dsk.journal_fd : dsk.data_fd,
         &data->iov, 1,
         (IS_JOURNAL(item_state) ? dsk.journal_offset : dsk.data_offset) + offset
     );
@@ -37,115 +40,59 @@ int blockstore_impl_t::fulfill_read_push(blockstore_op_t *op, void *buf, uint64_
     return 1;
 }
 
-void blockstore_impl_t::find_holes(std::vector<copy_buffer_t> & read_vec,
-    uint32_t item_start, uint32_t item_end,
-    std::function<int(int, bool, uint32_t, uint32_t)> callback)
+// FIXME I've seen a bug here so I want some tests
+int blockstore_impl_t::fulfill_read(blockstore_op_t *read_op, uint64_t &fulfilled, uint32_t item_start, uint32_t item_end,
+    uint32_t item_state, uint64_t item_version, uint64_t item_location, uint64_t journal_sector)
 {
-    auto cur_start = item_start;
-    int i = 0;
-    while (cur_start < item_end)
+    uint32_t cur_start = item_start;
+    if (cur_start < read_op->offset + read_op->len && item_end > read_op->offset)
     {
-        // COPY_BUF_CSUM_FILL items are fake items inserted in the end, their offsets aren't in order
-        if (i >= read_vec.size() || read_vec[i].copy_flags & COPY_BUF_CSUM_FILL || read_vec[i].offset >= item_end)
+        cur_start = cur_start < read_op->offset ? read_op->offset : cur_start;
+        item_end = item_end > read_op->offset + read_op->len ? read_op->offset + read_op->len : item_end;
+        auto it = PRIV(read_op)->read_vec.begin();
+        while (1)
         {
-            // Hole (at end): cur_start .. item_end
-            i += callback(i, false, cur_start, item_end);
-            break;
-        }
-        else if (read_vec[i].offset > cur_start)
-        {
-            // Hole: cur_start .. min(read_vec[i].offset, item_end)
-            auto cur_end = read_vec[i].offset > item_end ? item_end : read_vec[i].offset;
-            i += callback(i, false, cur_start, cur_end);
-            cur_start = cur_end;
-        }
-        else if (read_vec[i].offset + read_vec[i].len > cur_start)
-        {
-            // Allocated: cur_start .. min(read_vec[i].offset + read_vec[i].len, item_end)
-            auto cur_end = read_vec[i].offset + read_vec[i].len;
-            cur_end = cur_end > item_end ? item_end : cur_end;
-            i += callback(i, true, cur_start, cur_end);
-            cur_start = cur_end;
-            i++;
-        }
-        else
-            i++;
-    }
-}
-
-int blockstore_impl_t::fulfill_read(blockstore_op_t *read_op,
-    uint64_t &fulfilled, uint32_t item_start, uint32_t item_end, // FIXME: Rename item_* to dirty_*
-    uint32_t item_state, uint64_t item_version, uint64_t item_location,
-    uint64_t journal_sector, uint8_t *csum, int *dyn_data)
-{
-    int r = 1;
-    if (item_start < read_op->offset + read_op->len && item_end > read_op->offset)
-    {
-        auto & rv = PRIV(read_op)->read_vec;
-        auto rd_start = item_start < read_op->offset ? read_op->offset : item_start;
-        auto rd_end = item_end > read_op->offset + read_op->len ? read_op->offset + read_op->len : item_end;
-        find_holes(rv, rd_start, rd_end, [&](int pos, bool alloc, uint32_t start, uint32_t end)
-        {
-            if (!r || alloc)
-                return 0;
-            if (!journal.inmemory && dsk.csum_block_size > dsk.bitmap_granularity && IS_JOURNAL(item_state) && !IS_DELETE(item_state))
+            for (; it != PRIV(read_op)->read_vec.end(); it++)
             {
-                uint32_t blk_begin = (start/dsk.csum_block_size) * dsk.csum_block_size;
-                blk_begin = blk_begin < item_start ? item_start : blk_begin;
-                uint32_t blk_end = ((end-1) / dsk.csum_block_size + 1) * dsk.csum_block_size;
-                blk_end = blk_end > item_end ? item_end : blk_end;
-                rv.push_back((copy_buffer_t){
-                    .copy_flags = COPY_BUF_JOURNAL|COPY_BUF_CSUM_FILL,
-                    .offset = blk_begin,
-                    .len = blk_end-blk_begin,
-                    .csum_buf = (csum + (blk_begin/dsk.csum_block_size -
-                        item_start/dsk.csum_block_size) * (dsk.data_csum_type & 0xFF)),
-                    .dyn_data = dyn_data,
-                });
-                if (dyn_data)
+                if (it->offset >= cur_start)
                 {
-                    (*dyn_data)++;
+                    break;
                 }
-                // Submit the journal checksum block read
-                if (!read_checksum_block(read_op, 1, fulfilled, item_location - item_start))
+                else if (it->offset + it->len > cur_start)
                 {
-                    r = 0;
+                    cur_start = it->offset + it->len;
+                    if (cur_start >= item_end)
+                    {
+                        goto endwhile;
+                    }
                 }
-                return 0;
             }
-            copy_buffer_t el = {
-                .copy_flags = (IS_JOURNAL(item_state) ? COPY_BUF_JOURNAL : COPY_BUF_DATA),
-                .offset = start,
-                .len = end-start,
-                .disk_offset = item_location + start - item_start,
-                .journal_sector = (IS_JOURNAL(item_state) ? journal_sector : 0),
-                .csum_buf = !csum ? NULL : (csum + (start - item_start) / dsk.csum_block_size * (dsk.data_csum_type & 0xFF)),
-                .dyn_data = dyn_data,
-            };
-            if (dyn_data)
+            if (it == PRIV(read_op)->read_vec.end() || it->offset > cur_start)
             {
-                (*dyn_data)++;
+                fulfill_read_t el = {
+                    .offset = cur_start,
+                    .len = it == PRIV(read_op)->read_vec.end() || it->offset >= item_end ? item_end-cur_start : it->offset-cur_start,
+                    .journal_sector = journal_sector,
+                };
+                it = PRIV(read_op)->read_vec.insert(it, el);
+                if (!fulfill_read_push(read_op,
+                    (uint8_t*)read_op->buf + el.offset - read_op->offset,
+                    item_location + el.offset - item_start,
+                    el.len, item_state, item_version))
+                {
+                    return 0;
+                }
+                fulfilled += el.len;
             }
-            if (IS_BIG_WRITE(item_state))
+            cur_start = it->offset + it->len;
+            if (it == PRIV(read_op)->read_vec.end() || cur_start >= item_end)
             {
-                // If we don't track it then we may IN THEORY read another object's data:
-                // submit read -> remove the object -> flush remove -> overwrite with another object -> finish read
-                // Very improbable, but possible
-                PRIV(read_op)->clean_block_used = 1;
+                break;
             }
-            rv.insert(rv.begin() + pos, el);
-            fulfilled += el.len;
-            if (!fulfill_read_push(read_op,
-                (uint8_t*)read_op->buf + el.offset - read_op->offset,
-                item_location + el.offset - item_start,
-                el.len, item_state, item_version))
-            {
-                r = 0;
-            }
-            return 1;
-        });
+        }
     }
-    return r;
+endwhile:
+    return 1;
 }
 
 uint8_t* blockstore_impl_t::get_clean_entry_bitmap(uint64_t block_loc, int offset)
@@ -159,225 +106,10 @@ uint8_t* blockstore_impl_t::get_clean_entry_bitmap(uint64_t block_loc, int offse
         clean_entry_bitmap = ((uint8_t*)metadata_buffer + sector + pos*dsk.clean_entry_size + sizeof(clean_disk_entry) + offset);
     }
     else
-        clean_entry_bitmap = (uint8_t*)(clean_bitmaps + meta_loc*2*dsk.clean_entry_bitmap_size + offset);
+        clean_entry_bitmap = (uint8_t*)(clean_bitmap + meta_loc*2*dsk.clean_entry_bitmap_size + offset);
     return clean_entry_bitmap;
 }
 
-int blockstore_impl_t::fill_partial_checksum_blocks(std::vector<copy_buffer_t> & rv, uint64_t & fulfilled,
-    uint8_t *clean_entry_bitmap, int *dyn_data, bool from_journal, uint8_t *read_buf, uint64_t read_offset, uint64_t read_end)
-{
-    if (read_end == read_offset)
-        return 0;
-    int required = 0;
-    read_buf -= read_offset;
-    uint32_t last_block = (read_end-1)/dsk.csum_block_size;
-    uint32_t start_block = read_offset/dsk.csum_block_size;
-    uint32_t end_block = 0;
-    while (start_block <= last_block)
-    {
-        if (read_range_fulfilled(rv, fulfilled, read_buf, clean_entry_bitmap,
-            start_block*dsk.csum_block_size < read_offset ? read_offset : start_block*dsk.csum_block_size,
-            (start_block+1)*dsk.csum_block_size > read_end ? read_end : (start_block+1)*dsk.csum_block_size))
-        {
-            // read_range_fulfilled() also adds zero-filled areas
-            start_block++;
-        }
-        else
-        {
-            // Find a sequence of checksum blocks required to be read
-            end_block = start_block;
-            while ((end_block+1)*dsk.csum_block_size < read_end &&
-                !read_range_fulfilled(rv, fulfilled, read_buf, clean_entry_bitmap,
-                    (end_block+1)*dsk.csum_block_size < read_offset ? read_offset : (end_block+1)*dsk.csum_block_size,
-                    (end_block+2)*dsk.csum_block_size > read_end ? read_end : (end_block+2)*dsk.csum_block_size))
-            {
-                end_block++;
-            }
-            end_block++;
-            // OK, mark this range as required
-            rv.push_back((copy_buffer_t){
-                .copy_flags = COPY_BUF_CSUM_FILL | (from_journal ? COPY_BUF_JOURNALED_BIG : 0),
-                .offset = start_block*dsk.csum_block_size,
-                .len = (end_block-start_block)*dsk.csum_block_size,
-                // save clean_entry_bitmap if we're reading clean data from the journal
-                .csum_buf = from_journal ? clean_entry_bitmap : NULL,
-                .dyn_data = dyn_data,
-            });
-            if (dyn_data)
-            {
-                (*dyn_data)++;
-            }
-            start_block = end_block;
-            required++;
-        }
-    }
-    return required;
-}
-
-// read_buf should be == op->buf - op->offset
-bool blockstore_impl_t::read_range_fulfilled(std::vector<copy_buffer_t> & rv, uint64_t & fulfilled, uint8_t *read_buf,
-    uint8_t *clean_entry_bitmap, uint32_t item_start, uint32_t item_end)
-{
-    bool all_done = true;
-    find_holes(rv, item_start, item_end, [&](int pos, bool alloc, uint32_t cur_start, uint32_t cur_end)
-    {
-        if (alloc)
-            return 0;
-        int diff = 0;
-        uint32_t bmp_start = cur_start/dsk.bitmap_granularity;
-        uint32_t bmp_end = cur_end/dsk.bitmap_granularity;
-        uint32_t bmp_pos = bmp_start;
-        while (bmp_pos < bmp_end)
-        {
-            while (bmp_pos < bmp_end && !(clean_entry_bitmap[bmp_pos >> 3] & (1 << (bmp_pos & 0x7))))
-                bmp_pos++;
-            if (bmp_pos > bmp_start)
-            {
-                // zero fill
-                copy_buffer_t el = {
-                    .copy_flags = COPY_BUF_ZERO,
-                    .offset = bmp_start*dsk.bitmap_granularity,
-                    .len = (bmp_pos-bmp_start)*dsk.bitmap_granularity,
-                };
-                rv.insert(rv.begin() + pos, el);
-                if (read_buf)
-                    memset(read_buf + el.offset, 0, el.len);
-                fulfilled += el.len;
-                diff++;
-            }
-            bmp_start = bmp_pos;
-            while (bmp_pos < bmp_end && (clean_entry_bitmap[bmp_pos >> 3] & (1 << (bmp_pos & 0x7))))
-                bmp_pos++;
-            if (bmp_pos > bmp_start)
-            {
-                // something is to be read
-                all_done = false;
-            }
-            bmp_start = bmp_pos;
-        }
-        return diff;
-    });
-    return all_done;
-}
-
-bool blockstore_impl_t::read_checksum_block(blockstore_op_t *op, int rv_pos, uint64_t &fulfilled, uint64_t clean_loc)
-{
-    auto & rv = PRIV(op)->read_vec;
-    auto *vi = &rv[rv.size()-rv_pos];
-    uint32_t item_start = vi->offset, item_end = vi->offset+vi->len;
-    uint32_t fill_size = 0;
-    int n_iov = 0;
-    find_holes(rv, item_start, item_end, [&](int pos, bool alloc, uint32_t cur_start, uint32_t cur_end)
-    {
-        if (alloc)
-        {
-            fill_size += cur_end-cur_start;
-            n_iov++;
-        }
-        else
-        {
-            if (cur_start < op->offset)
-            {
-                fill_size += op->offset-cur_start;
-                n_iov++;
-                cur_start = op->offset;
-            }
-            if (cur_end > op->offset+op->len)
-            {
-                fill_size += cur_end-(op->offset+op->len);
-                n_iov++;
-                cur_end = op->offset+op->len;
-            }
-            if (cur_end > cur_start)
-            {
-                n_iov++;
-            }
-        }
-        return 0;
-    });
-    void *buf = memalign_or_die(MEM_ALIGNMENT, fill_size + n_iov*sizeof(struct iovec));
-    iovec *iov = (struct iovec*)((uint8_t*)buf+fill_size);
-    n_iov = 0;
-    fill_size = 0;
-    find_holes(rv, item_start, item_end, [&](int pos, bool alloc, uint32_t cur_start, uint32_t cur_end)
-    {
-        int res = 0;
-        if (alloc)
-        {
-            iov[n_iov++] = (struct iovec){ (uint8_t*)buf+fill_size, cur_end-cur_start };
-            fill_size += cur_end-cur_start;
-        }
-        else
-        {
-            if (cur_start < op->offset)
-            {
-                iov[n_iov++] = (struct iovec){ (uint8_t*)buf+fill_size, op->offset-cur_start };
-                fill_size += op->offset-cur_start;
-                cur_start = op->offset;
-            }
-            auto lim_end = cur_end > op->offset+op->len ? op->offset+op->len : cur_end;
-            if (lim_end > cur_start)
-            {
-                iov[n_iov++] = (struct iovec){ (uint8_t*)op->buf+cur_start-op->offset, lim_end-cur_start };
-                rv.insert(rv.begin() + pos, (copy_buffer_t){
-                    .copy_flags = COPY_BUF_DATA,
-                    .offset = cur_start,
-                    .len = lim_end-cur_start,
-                });
-                fulfilled += lim_end-cur_start;
-                res++;
-            }
-            if (cur_end > op->offset+op->len)
-            {
-                iov[n_iov++] = (struct iovec){ (uint8_t*)buf+fill_size, cur_end - (op->offset+op->len) };
-                fill_size += cur_end - (op->offset+op->len);
-                cur_end = op->offset+op->len;
-            }
-        }
-        return res;
-    });
-    vi = &rv[rv.size()-rv_pos];
-    // Save buf into read_vec too but in a creepy way
-    // FIXME: Shit, something else should be invented %)
-    *vi = (copy_buffer_t){
-        .copy_flags = vi->copy_flags,
-        .offset = vi->offset,
-        .len = ((uint64_t)n_iov << 32) | fill_size,
-        .disk_offset = clean_loc + item_start,
-        .buf = (uint8_t*)buf,
-        .csum_buf = vi->csum_buf,
-        .dyn_data = vi->dyn_data,
-    };
-    int submit_fd = (vi->copy_flags & COPY_BUF_JOURNAL ? dsk.read_journal_fd : dsk.read_data_fd);
-    uint64_t submit_offset = (vi->copy_flags & COPY_BUF_JOURNAL ? journal.offset : dsk.data_offset);
-    uint32_t d_pos = 0;
-    for (int n_pos = 0; n_pos < n_iov; n_pos += IOV_MAX)
-    {
-        int n_cur = n_iov-n_pos < IOV_MAX ? n_iov-n_pos : IOV_MAX;
-        BS_SUBMIT_GET_SQE(sqe, data);
-        PRIV(op)->pending_ops++;
-        my_uring_prep_readv(sqe, submit_fd, iov + n_pos, n_cur, submit_offset + clean_loc + item_start + d_pos);
-        data->callback = [this, op](ring_data_t *data) { handle_read_event(data, op); };
-        if (n_pos > 0 || n_pos + IOV_MAX < n_iov)
-        {
-            uint32_t d_len = 0;
-            for (int i = 0; i < IOV_MAX; i++)
-                d_len += iov[n_pos+i].iov_len;
-            data->iov.iov_len = d_len;
-            d_pos += d_len;
-        }
-        else
-            data->iov.iov_len = item_end-item_start;
-    }
-    if (!(vi->copy_flags & COPY_BUF_JOURNAL))
-    {
-        // Reads running parallel to flushes of the same clean block may read
-        // a mixture of old and new data. So we don't verify checksums for such blocks.
-        PRIV(op)->clean_block_used = 1;
-    }
-    return true;
-}
-
 int blockstore_impl_t::dequeue_read(blockstore_op_t *read_op)
 {
     auto & clean_db = clean_db_shard(read_op->oid);
@@ -399,8 +131,6 @@ int blockstore_impl_t::dequeue_read(blockstore_op_t *read_op)
     }
     uint64_t fulfilled = 0;
     PRIV(read_op)->pending_ops = 0;
-    PRIV(read_op)->clean_block_used = 0;
-    auto & rv = PRIV(read_op)->read_vec;
     uint64_t result_version = 0;
     if (dirty_found)
     {
@@ -418,36 +148,23 @@ int blockstore_impl_t::dequeue_read(blockstore_op_t *read_op)
                     FINISH_OP(read_op);
                     return 2;
                 }
-                int *dyn_data = (int*)(dsk.csum_block_size > 0 && alloc_dyn_data ? dirty.dyn_data : NULL);
-                uint8_t *bmp_ptr = (alloc_dyn_data
-                    ? (uint8_t*)dirty.dyn_data + sizeof(int) : (uint8_t*)&dirty.dyn_data);
                 if (!result_version)
                 {
                     result_version = dirty_it->first.version;
                     if (read_op->bitmap)
                     {
+                        void *bmp_ptr = (dsk.clean_entry_bitmap_size > sizeof(void*) ? dirty_it->second.bitmap : &dirty_it->second.bitmap);
                         memcpy(read_op->bitmap, bmp_ptr, dsk.clean_entry_bitmap_size);
                     }
                 }
                 // If inmemory_journal is false, journal trim will have to wait until the read is completed
-                if (!IS_JOURNAL(dirty.state))
+                if (!fulfill_read(read_op, fulfilled, dirty.offset, dirty.offset + dirty.len,
+                    dirty.state, dirty_it->first.version, dirty.location + (IS_JOURNAL(dirty.state) ? 0 : dirty.offset),
+                    (IS_JOURNAL(dirty.state) ? dirty.journal_sector+1 : 0)))
                 {
-                    // Read from data disk, possibly checking checksums
-                    if (!fulfill_clean_read(read_op, fulfilled, bmp_ptr, dyn_data,
-                        dirty.offset, dirty.offset+dirty.len, dirty.location, dirty_it->first.version))
-                    {
-                        goto undo_read;
-                    }
-                }
-                else
-                {
-                    // Copy from memory or read from journal, possibly checking checksums
-                    if (!fulfill_read(read_op, fulfilled, dirty.offset, dirty.offset + dirty.len,
-                        dirty.state, dirty_it->first.version, dirty.location, dirty.journal_sector+1,
-                        journal.inmemory ? NULL : bmp_ptr+dsk.clean_entry_bitmap_size, dyn_data))
-                    {
-                        goto undo_read;
-                    }
+                    // need to wait. undo added requests, don't dequeue op
+                    PRIV(read_op)->read_vec.clear();
+                    return 0;
                 }
             }
             if (fulfilled == read_op->len || dirty_it == dirty_db.begin())
@@ -470,10 +187,50 @@ int blockstore_impl_t::dequeue_read(blockstore_op_t *read_op)
         }
         if (fulfilled < read_op->len)
         {
-            if (!fulfill_clean_read(read_op, fulfilled, NULL, NULL, 0, dsk.data_block_size,
-                clean_it->second.location, clean_it->second.version))
+            if (!dsk.clean_entry_bitmap_size)
             {
-                goto undo_read;
+                if (!fulfill_read(read_op, fulfilled, 0, dsk.data_block_size,
+                    (BS_ST_BIG_WRITE | BS_ST_STABLE), 0, clean_it->second.location, 0))
+                {
+                    // need to wait. undo added requests, don't dequeue op
+                    PRIV(read_op)->read_vec.clear();
+                    return 0;
+                }
+            }
+            else
+            {
+                uint8_t *clean_entry_bitmap = get_clean_entry_bitmap(clean_it->second.location, 0);
+                uint64_t bmp_start = 0, bmp_end = 0, bmp_size = dsk.data_block_size/dsk.bitmap_granularity;
+                while (bmp_start < bmp_size)
+                {
+                    while (!(clean_entry_bitmap[bmp_end >> 3] & (1 << (bmp_end & 0x7))) && bmp_end < bmp_size)
+                    {
+                        bmp_end++;
+                    }
+                    if (bmp_end > bmp_start)
+                    {
+                        // fill with zeroes
+                        assert(fulfill_read(read_op, fulfilled, bmp_start * dsk.bitmap_granularity,
+                            bmp_end * dsk.bitmap_granularity, (BS_ST_DELETE | BS_ST_STABLE), 0, 0, 0));
+                    }
+                    bmp_start = bmp_end;
+                    while (clean_entry_bitmap[bmp_end >> 3] & (1 << (bmp_end & 0x7)) && bmp_end < bmp_size)
+                    {
+                        bmp_end++;
+                    }
+                    if (bmp_end > bmp_start)
+                    {
+                        if (!fulfill_read(read_op, fulfilled, bmp_start * dsk.bitmap_granularity,
+                            bmp_end * dsk.bitmap_granularity, (BS_ST_BIG_WRITE | BS_ST_STABLE), 0,
+                            clean_it->second.location + bmp_start * dsk.bitmap_granularity, 0))
+                        {
+                            // need to wait. undo added requests, don't dequeue op
+                            PRIV(read_op)->read_vec.clear();
+                            return 0;
+                        }
+                        bmp_start = bmp_end;
+                    }
+                }
             }
         }
     }
@@ -485,7 +242,11 @@ int blockstore_impl_t::dequeue_read(blockstore_op_t *read_op)
         FINISH_OP(read_op);
         return 2;
     }
-    assert(fulfilled == read_op->len);
+    if (fulfilled < read_op->len)
+    {
+        assert(fulfill_read(read_op, fulfilled, 0, dsk.data_block_size, (BS_ST_DELETE | BS_ST_STABLE), 0, 0, 0));
+        assert(fulfilled == read_op->len);
+    }
     read_op->version = result_version;
     if (!PRIV(read_op)->pending_ops)
     {
@@ -510,309 +271,6 @@ int blockstore_impl_t::dequeue_read(blockstore_op_t *read_op)
     }
     read_op->retval = 0;
     return 2;
-undo_read:
-    // need to wait. undo added requests, don't dequeue op
-    if (dsk.csum_block_size > dsk.bitmap_granularity)
-    {
-        for (auto & vec: rv)
-        {
-            if ((vec.copy_flags & COPY_BUF_CSUM_FILL) && vec.buf)
-            {
-                free(vec.buf);
-                vec.buf = NULL;
-            }
-            if (vec.dyn_data && --(*vec.dyn_data) == 0) // refcount
-            {
-                free(vec.dyn_data);
-                vec.dyn_data = NULL;
-            }
-        }
-    }
-    rv.clear();
-    return 0;
-}
-
-int blockstore_impl_t::pad_journal_read(std::vector<copy_buffer_t> & rv, copy_buffer_t & cp,
-    // FIXME Passing dirty_entry& would be nicer
-    uint64_t dirty_offset, uint64_t dirty_end, uint64_t dirty_loc, uint8_t *csum_ptr, int *dyn_data,
-    uint64_t offset, uint64_t submit_len, uint64_t & blk_begin, uint64_t & blk_end, uint8_t* & blk_buf)
-{
-    if (offset % dsk.csum_block_size || submit_len % dsk.csum_block_size)
-    {
-        if (offset < blk_end)
-        {
-            // Already being read as a part of the previous checksum block series
-            cp.buf = blk_buf + offset - blk_begin;
-            cp.copy_flags |= COPY_BUF_COALESCED;
-            if (offset+submit_len > blk_end)
-                cp.len = blk_end-offset;
-            return 2;
-        }
-        else
-        {
-            // We don't use fill_partial_checksum_blocks for journal because journal writes never have holes (internal bitmap)
-            blk_begin = (offset/dsk.csum_block_size) * dsk.csum_block_size;
-            blk_begin = blk_begin < dirty_offset ? dirty_offset : blk_begin;
-            blk_end = ((offset+submit_len-1)/dsk.csum_block_size + 1) * dsk.csum_block_size;
-            blk_end = blk_end > dirty_end ? dirty_end : blk_end;
-            if (blk_begin < offset || blk_end > offset+submit_len)
-            {
-                blk_buf = (uint8_t*)memalign_or_die(MEM_ALIGNMENT, blk_end-blk_begin);
-                cp.buf = blk_buf + offset - blk_begin;
-                cp.copy_flags |= COPY_BUF_COALESCED;
-                rv.push_back((copy_buffer_t){
-                    .copy_flags = COPY_BUF_JOURNAL|COPY_BUF_CSUM_FILL,
-                    .offset = blk_begin,
-                    .len = blk_end-blk_begin,
-                    .disk_offset = dirty_loc + blk_begin - dirty_offset,
-                    .buf = blk_buf,
-                    .csum_buf = (csum_ptr + (blk_begin/dsk.csum_block_size -
-                        dirty_offset/dsk.csum_block_size) * (dsk.data_csum_type & 0xFF)),
-                    .dyn_data = dyn_data,
-                });
-                if (dyn_data)
-                {
-                    (*dyn_data)++;
-                }
-                return 1;
-            }
-        }
-    }
-    return 0;
-}
-
-bool blockstore_impl_t::fulfill_clean_read(blockstore_op_t *read_op, uint64_t & fulfilled,
-    uint8_t *clean_entry_bitmap, int *dyn_data, uint32_t item_start, uint32_t item_end, uint64_t clean_loc, uint64_t clean_ver)
-{
-    bool from_journal = clean_entry_bitmap != NULL;
-    if (!clean_entry_bitmap)
-    {
-        // NULL clean_entry_bitmap means we're reading from data, not from the journal,
-        // and the bitmap location is obvious
-        clean_entry_bitmap = get_clean_entry_bitmap(clean_loc, 0);
-    }
-    if (dsk.csum_block_size > dsk.bitmap_granularity)
-    {
-        auto & rv = PRIV(read_op)->read_vec;
-        int req = fill_partial_checksum_blocks(rv, fulfilled, clean_entry_bitmap, dyn_data, from_journal,
-            (uint8_t*)read_op->buf, read_op->offset, read_op->offset+read_op->len);
-        if (!inmemory_meta && !from_journal && req > 0)
-        {
-            // Read checksums from disk
-            uint8_t *csum_buf = read_clean_meta_block(read_op, clean_loc, rv.size()-req);
-            for (int i = req; i > 0; i--)
-            {
-                rv[rv.size()-i].csum_buf = csum_buf;
-            }
-        }
-        for (int i = req; i > 0; i--)
-        {
-            if (!read_checksum_block(read_op, i, fulfilled, clean_loc))
-            {
-                return false;
-            }
-        }
-        PRIV(read_op)->clean_block_used = req > 0;
-    }
-    else if (from_journal)
-    {
-        // Don't scan bitmap - journal writes don't have holes (internal bitmap)!
-        uint8_t *csum = !dsk.csum_block_size ? 0 : (clean_entry_bitmap + dsk.clean_entry_bitmap_size +
-            item_start/dsk.csum_block_size*(dsk.data_csum_type & 0xFF));
-        if (!fulfill_read(read_op, fulfilled, item_start, item_end,
-            (BS_ST_BIG_WRITE | BS_ST_STABLE), 0, clean_loc + item_start, 0, csum, dyn_data))
-        {
-            return false;
-        }
-        if (item_start > 0 && fulfilled < read_op->len)
-        {
-            // fill with zeroes
-            assert(fulfill_read(read_op, fulfilled, 0, item_start, (BS_ST_DELETE | BS_ST_STABLE), 0, 0, 0, NULL, NULL));
-        }
-        if (item_end < dsk.data_block_size && fulfilled < read_op->len)
-        {
-            // fill with zeroes
-            assert(fulfill_read(read_op, fulfilled, item_end, dsk.data_block_size, (BS_ST_DELETE | BS_ST_STABLE), 0, 0, 0, NULL, NULL));
-        }
-    }
-    else
-    {
-        bool csum_done = !dsk.csum_block_size || inmemory_meta;
-        uint8_t *csum_buf = clean_entry_bitmap;
-        uint64_t bmp_start = 0, bmp_end = 0, bmp_size = dsk.data_block_size/dsk.bitmap_granularity;
-        while (bmp_start < bmp_size)
-        {
-            while (!(clean_entry_bitmap[bmp_end >> 3] & (1 << (bmp_end & 0x7))) && bmp_end < bmp_size)
-            {
-                bmp_end++;
-            }
-            if (bmp_end > bmp_start)
-            {
-                // fill with zeroes
-                assert(fulfill_read(read_op, fulfilled, bmp_start * dsk.bitmap_granularity,
-                    bmp_end * dsk.bitmap_granularity, (BS_ST_DELETE | BS_ST_STABLE), 0, 0, 0, NULL, NULL));
-            }
-            bmp_start = bmp_end;
-            while (clean_entry_bitmap[bmp_end >> 3] & (1 << (bmp_end & 0x7)) && bmp_end < bmp_size)
-            {
-                bmp_end++;
-            }
-            if (bmp_end > bmp_start)
-            {
-                if (!csum_done)
-                {
-                    // Read checksums from disk
-                    csum_buf = read_clean_meta_block(read_op, clean_loc, PRIV(read_op)->read_vec.size());
-                    csum_done = true;
-                }
-                uint8_t *csum = !dsk.csum_block_size ? 0 : (csum_buf + 2*dsk.clean_entry_bitmap_size + bmp_start*(dsk.data_csum_type & 0xFF));
-                if (!fulfill_read(read_op, fulfilled, bmp_start * dsk.bitmap_granularity,
-                    bmp_end * dsk.bitmap_granularity, (BS_ST_BIG_WRITE | BS_ST_STABLE), 0,
-                    clean_loc + bmp_start * dsk.bitmap_granularity, 0, csum, dyn_data))
-                {
-                    return false;
-                }
-                bmp_start = bmp_end;
-            }
-        }
-    }
-    // Increment reference counter if clean data is being read from the disk
-    if (PRIV(read_op)->clean_block_used)
-    {
-        auto & uo = used_clean_objects[clean_loc];
-        uo.refs++;
-        if (dsk.csum_block_size && flusher->is_mutated(clean_loc))
-            uo.was_changed = true;
-        PRIV(read_op)->clean_block_used = clean_loc;
-    }
-    return true;
-}
-
-uint8_t* blockstore_impl_t::read_clean_meta_block(blockstore_op_t *op, uint64_t clean_loc, int rv_pos)
-{
-    auto & rv = PRIV(op)->read_vec;
-    auto sector = ((clean_loc >> dsk.block_order) / (dsk.meta_block_size / dsk.clean_entry_size)) * dsk.meta_block_size;
-    auto pos = ((clean_loc >> dsk.block_order) % (dsk.meta_block_size / dsk.clean_entry_size)) * dsk.clean_entry_size;
-    uint8_t *buf = (uint8_t*)memalign_or_die(MEM_ALIGNMENT, dsk.meta_block_size);
-    rv.insert(rv.begin()+rv_pos, (copy_buffer_t){
-        .copy_flags = COPY_BUF_META_BLOCK|COPY_BUF_CSUM_FILL,
-        .offset = pos,
-        .buf = buf,
-    });
-    BS_SUBMIT_GET_SQE(sqe, data);
-    data->iov = (struct iovec){ buf, dsk.meta_block_size };
-    PRIV(op)->pending_ops++;
-    my_uring_prep_readv(sqe, dsk.read_meta_fd, &data->iov, 1, dsk.meta_offset + dsk.meta_block_size + sector);
-    data->callback = [this, op](ring_data_t *data) { handle_read_event(data, op); };
-    // return pointer to checksums + bitmap
-    return buf + pos + sizeof(clean_disk_entry);
-}
-
-bool blockstore_impl_t::verify_padded_checksums(uint8_t *clean_entry_bitmap, uint8_t *csum_buf, uint32_t offset,
-    iovec *iov, int n_iov, std::function<void(uint32_t, uint32_t, uint32_t)> bad_block_cb)
-{
-    assert(!(offset % dsk.csum_block_size));
-    uint32_t *csums = (uint32_t*)csum_buf;
-    uint32_t block_csum = 0;
-    uint32_t block_done = 0;
-    uint32_t block_num = clean_entry_bitmap ? offset/dsk.csum_block_size : 0;
-    uint32_t bmp_pos = offset/dsk.bitmap_granularity;
-    for (int i = 0; i < n_iov; i++)
-    {
-        uint32_t pos = 0;
-        while (pos < iov[i].iov_len)
-        {
-            uint32_t start = pos;
-            uint8_t bit = (clean_entry_bitmap[bmp_pos >> 3] >> (bmp_pos & 0x7)) & 1;
-            while (pos < iov[i].iov_len && ((clean_entry_bitmap[bmp_pos >> 3] >> (bmp_pos & 0x7)) & 1) == bit)
-            {
-                pos += dsk.bitmap_granularity;
-                bmp_pos++;
-            }
-            uint32_t len = pos-start;
-            auto buf = (uint8_t*)iov[i].iov_base+start;
-            while (block_done+len >= dsk.csum_block_size)
-            {
-                auto cur_len = dsk.csum_block_size-block_done;
-                block_csum = crc32c_pad(block_csum, buf, bit ? cur_len : 0, bit ? 0 : cur_len, 0);
-                if (block_csum != csums[block_num])
-                {
-                    if (bad_block_cb)
-                        bad_block_cb(block_num*dsk.csum_block_size, block_csum, csums[block_num]);
-                    else
-                        return false;
-                }
-                block_num++;
-                buf += cur_len;
-                len -= cur_len;
-                block_done = block_csum = 0;
-            }
-            if (len > 0)
-            {
-                block_csum = crc32c_pad(block_csum, buf, bit ? len : 0, bit ? 0 : len, 0);
-                block_done += len;
-            }
-        }
-    }
-    assert(!block_done);
-    return true;
-}
-
-bool blockstore_impl_t::verify_journal_checksums(uint8_t *csums, uint32_t offset,
-    iovec *iov, int n_iov, std::function<void(uint32_t, uint32_t, uint32_t)> bad_block_cb)
-{
-    uint32_t block_csum = 0;
-    uint32_t block_num = 0;
-    uint32_t block_done = offset%dsk.csum_block_size;
-    for (int i = 0; i < n_iov; i++)
-    {
-        uint32_t len = iov[i].iov_len;
-        auto buf = (uint8_t*)iov[i].iov_base;
-        while (block_done+len >= dsk.csum_block_size)
-        {
-            auto cur_len = dsk.csum_block_size-block_done;
-            block_csum = crc32c(block_csum, buf, cur_len);
-            if (block_csum != ((uint32_t*)csums)[block_num])
-            {
-                if (bad_block_cb)
-                    bad_block_cb(block_num*dsk.csum_block_size, block_csum, ((uint32_t*)csums)[block_num]);
-                else
-                    return false;
-            }
-            block_num++;
-            buf += cur_len;
-            len -= cur_len;
-            block_done = block_csum = 0;
-        }
-        if (len > 0)
-        {
-            block_csum = crc32c(block_csum, buf, len);
-            block_done += len;
-        }
-    }
-    if (block_done > 0 && block_csum != ((uint32_t*)csums)[block_num])
-    {
-        if (bad_block_cb)
-            bad_block_cb(block_num*dsk.csum_block_size, block_csum, ((uint32_t*)csums)[block_num]);
-        else
-            return false;
-    }
-    return true;
-}
-
-bool blockstore_impl_t::verify_clean_padded_checksums(blockstore_op_t *op, uint64_t clean_loc, uint8_t *dyn_data, bool from_journal,
-    iovec *iov, int n_iov, std::function<void(uint32_t, uint32_t, uint32_t)> bad_block_cb)
-{
-    uint32_t offset = clean_loc % dsk.data_block_size;
-    if (from_journal)
-        return verify_padded_checksums(dyn_data, dyn_data + dsk.clean_entry_bitmap_size, offset, iov, n_iov, bad_block_cb);
-    clean_loc = (clean_loc >> dsk.block_order) << dsk.block_order;
-    if (!dyn_data)
-    {
-        assert(inmemory_meta);
-        dyn_data = get_clean_entry_bitmap(clean_loc, 0);
-    }
-    return verify_padded_checksums(dyn_data, dyn_data + 2*dsk.clean_entry_bitmap_size, offset, iov, n_iov, bad_block_cb);
 }
 
 void blockstore_impl_t::handle_read_event(ring_data_t *data, blockstore_op_t *op)
@@ -826,139 +284,6 @@ void blockstore_impl_t::handle_read_event(ring_data_t *data, blockstore_op_t *op
     }
     if (PRIV(op)->pending_ops == 0)
     {
-        if (dsk.csum_block_size)
-        {
-            // verify checksums if required
-            auto & rv = PRIV(op)->read_vec;
-            void *meta_block = NULL;
-            if (dsk.csum_block_size > dsk.bitmap_granularity)
-            {
-                for (int i = rv.size()-1; i >= 0 && (rv[i].copy_flags & COPY_BUF_CSUM_FILL); i--)
-                {
-                    if (rv[i].copy_flags & COPY_BUF_META_BLOCK)
-                    {
-                        // Metadata read. Skip
-                        assert(!meta_block);
-                        meta_block = rv[i].buf;
-                        rv[i].buf = NULL;
-                        continue;
-                    }
-                    struct iovec *iov = (struct iovec*)((uint8_t*)rv[i].buf + (rv[i].len & 0xFFFFFFFF));
-                    int n_iov = rv[i].len >> 32;
-                    bool ok = true;
-                    if (rv[i].copy_flags & COPY_BUF_JOURNAL)
-                    {
-                        // SMALL_WRITE from journal
-                        verify_journal_checksums(
-                            rv[i].csum_buf, rv[i].offset, iov, n_iov,
-                            [&](uint32_t bad_block, uint32_t calc_csum, uint32_t stored_csum)
-                            {
-                                ok = false;
-                                printf(
-                                    "Checksum mismatch in object %lx:%lx v%lu in journal at 0x%lx, checksum block #%u: got %08x, expected %08x\n",
-                                    op->oid.inode, op->oid.stripe, op->version,
-                                    rv[i].disk_offset, bad_block / dsk.csum_block_size, calc_csum, stored_csum
-                                );
-                            }
-                        );
-                    }
-                    else
-                    {
-                        // BIG_WRITE from journal or clean data
-                        // Do not verify checksums if the data location is/was mutated by flushers
-                        auto & uo = used_clean_objects.at((rv[i].disk_offset >> dsk.block_order) << dsk.block_order);
-                        if (!uo.was_changed)
-                        {
-                            verify_clean_padded_checksums(
-                                op, rv[i].disk_offset, rv[i].csum_buf, (rv[i].copy_flags & COPY_BUF_JOURNALED_BIG), iov, n_iov,
-                                [&](uint32_t bad_block, uint32_t calc_csum, uint32_t stored_csum)
-                                {
-                                    ok = false;
-                                    printf(
-                                        "Checksum mismatch in object %lx:%lx v%lu in %s data at 0x%lx, checksum block #%u: got %08x, expected %08x\n",
-                                        op->oid.inode, op->oid.stripe, op->version,
-                                        (rv[i].copy_flags & COPY_BUF_JOURNALED_BIG ? "redirect-write" : "clean"),
-                                        rv[i].disk_offset, bad_block / dsk.csum_block_size, calc_csum, stored_csum
-                                    );
-                                }
-                            );
-                        }
-                    }
-                    if (!ok)
-                    {
-                        op->retval = -EDOM;
-                    }
-                    free(rv[i].buf);
-                    rv[i].buf = NULL;
-                    if (rv[i].dyn_data && --(*rv[i].dyn_data) == 0) // refcount
-                    {
-                        free(rv[i].dyn_data);
-                        rv[i].dyn_data = NULL;
-                    }
-                }
-            }
-            else
-            {
-                for (auto & vec: rv)
-                {
-                    if (vec.copy_flags & COPY_BUF_META_BLOCK)
-                    {
-                        // Metadata read. Skip
-                        assert(!meta_block);
-                        meta_block = vec.buf;
-                        vec.buf = NULL;
-                        continue;
-                    }
-                    if (vec.csum_buf)
-                    {
-                        uint32_t *csum = (uint32_t*)vec.csum_buf;
-                        for (size_t p = 0; p < vec.len; p += dsk.csum_block_size, csum++)
-                        {
-                            if (crc32c(0, (uint8_t*)op->buf + vec.offset - op->offset + p, dsk.csum_block_size) != *csum)
-                            {
-                                // checksum error
-                                printf(
-                                    "Checksum mismatch in object %lx:%lx v%lu in %s area at offset 0x%lx+0x%lx: %08x vs %08x\n",
-                                    op->oid.inode, op->oid.stripe, op->version,
-                                    (vec.copy_flags & COPY_BUF_JOURNAL) ? "journal" : "data", vec.disk_offset, p,
-                                    crc32c(0, (uint8_t*)op->buf + vec.offset - op->offset + p, dsk.csum_block_size), *csum
-                                );
-                                op->retval = -EDOM;
-                                break;
-                            }
-                        }
-                    }
-                    if (vec.dyn_data && --(*vec.dyn_data) == 0) // refcount
-                    {
-                        free(vec.dyn_data);
-                        vec.dyn_data = NULL;
-                    }
-                }
-            }
-            if (meta_block)
-            {
-                // Free after checking
-                free(meta_block);
-                meta_block = NULL;
-            }
-        }
-        if (PRIV(op)->clean_block_used)
-        {
-            // Release clean data block
-            auto uo_it = used_clean_objects.find(PRIV(op)->clean_block_used);
-            if (uo_it != used_clean_objects.end())
-            {
-                uo_it->second.refs--;
-                if (uo_it->second.refs <= 0)
-                {
-                    if (uo_it->second.was_freed)
-                    {
-                        data_alloc->set(PRIV(op)->clean_block_used, false);
-                    }
-                    used_clean_objects.erase(uo_it);
-                }
-            }
-        }
         if (!journal.inmemory)
         {
             // Release journal sector usage
@@ -999,9 +324,8 @@ int blockstore_impl_t::read_bitmap(object_id oid, uint64_t target_version, void
                     *result_version = dirty_it->first.version;
                 if (bitmap)
                 {
-                    void *dyn_ptr = (alloc_dyn_data
-                        ? (uint8_t*)dirty_it->second.dyn_data + sizeof(int) : (uint8_t*)&dirty_it->second.dyn_data);
-                    memcpy(bitmap, dyn_ptr, dsk.clean_entry_bitmap_size);
+                    void *bmp_ptr = (dsk.clean_entry_bitmap_size > sizeof(void*) ? dirty_it->second.bitmap : &dirty_it->second.bitmap);
+                    memcpy(bitmap, bmp_ptr, dsk.clean_entry_bitmap_size);
                 }
                 return 0;
             }

src/blockstore_rollback.cpp

@@ -227,7 +227,11 @@ void blockstore_impl_t::erase_dirty(blockstore_dirty_db_t::iterator dirty_start,
             journal.used_sectors.erase(dirty_it->second.journal_sector);
             flusher->mark_trim_possible();
         }
-        free_dirty_dyn_data(dirty_it->second);
+        if (dsk.clean_entry_bitmap_size > sizeof(void*))
+        {
+            free(dirty_it->second.bitmap);
+            dirty_it->second.bitmap = NULL;
+        }
         if (dirty_it == dirty_start)
         {
             break;
@@ -236,18 +240,3 @@ void blockstore_impl_t::erase_dirty(blockstore_dirty_db_t::iterator dirty_start,
     }
     dirty_db.erase(dirty_start, dirty_end);
 }
-
-void blockstore_impl_t::free_dirty_dyn_data(dirty_entry & e)
-{
-    if (e.dyn_data)
-    {
-        if (alloc_dyn_data &&
-            --*((int*)e.dyn_data) == 0) // refcount
-        {
-            // dyn_data contains the bitmap and checksums
-            // free it if it doesn't refer to the in-memory journal
-            free(e.dyn_data);
-        }
-        e.dyn_data = NULL;
-    }
-}

src/blockstore_sync.cpp

@@ -78,23 +78,7 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
         // 2nd step: Data device is synced, prepare & write journal entries
         // Check space in the journal and journal memory buffers
         blockstore_journal_check_t space_check(this);
-        if (dsk.csum_block_size)
-        {
-            // More complex check because all journal entries have different lengths
-            int left = PRIV(op)->sync_big_writes.size();
-            for (auto & sbw: PRIV(op)->sync_big_writes)
-            {
-                left--;
-                auto & dirty_entry = dirty_db.at(sbw);
-                uint64_t dyn_size = dsk.dirty_dyn_size(dirty_entry.offset, dirty_entry.len);
-                if (!space_check.check_available(op, 1, sizeof(journal_entry_big_write) + dyn_size,
-                    left == 0 ? JOURNAL_STABILIZE_RESERVATION : 0))
-                {
-                    return 0;
-                }
-            }
-        }
-        else if (!space_check.check_available(op, PRIV(op)->sync_big_writes.size(),
+        if (!space_check.check_available(op, PRIV(op)->sync_big_writes.size(),
             sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size, JOURNAL_STABILIZE_RESERVATION))
         {
             return 0;
@@ -106,17 +90,16 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
         int s = 0;
         while (it != PRIV(op)->sync_big_writes.end())
         {
-            auto & dirty_entry = dirty_db.at(*it);
-            uint64_t dyn_size = dsk.dirty_dyn_size(dirty_entry.offset, dirty_entry.len);
-            if (!journal.entry_fits(sizeof(journal_entry_big_write) + dyn_size) &&
+            if (!journal.entry_fits(sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size) &&
                 journal.sector_info[journal.cur_sector].dirty)
             {
                 prepare_journal_sector_write(journal.cur_sector, op);
                 s++;
             }
+            auto & dirty_entry = dirty_db.at(*it);
             journal_entry_big_write *je = (journal_entry_big_write*)prefill_single_journal_entry(
                 journal, (dirty_entry.state & BS_ST_INSTANT) ? JE_BIG_WRITE_INSTANT : JE_BIG_WRITE,
-                sizeof(journal_entry_big_write) + dyn_size
+                sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size
             );
             dirty_entry.journal_sector = journal.sector_info[journal.cur_sector].offset;
             journal.used_sectors[journal.sector_info[journal.cur_sector].offset]++;
@@ -132,8 +115,8 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
             je->offset = dirty_entry.offset;
             je->len = dirty_entry.len;
             je->location = dirty_entry.location;
-            memcpy((void*)(je+1), (alloc_dyn_data
-                ? (uint8_t*)dirty_entry.dyn_data+sizeof(int) : (uint8_t*)&dirty_entry.dyn_data), dyn_size);
+            memcpy((void*)(je+1), (dsk.clean_entry_bitmap_size > sizeof(void*)
+                ? dirty_entry.bitmap : &dirty_entry.bitmap), dsk.clean_entry_bitmap_size);
             je->crc32 = je_crc32((journal_entry*)je);
             journal.crc32_last = je->crc32;
             it++;

src/blockstore_write.cpp

@@ -8,21 +8,12 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
     // Check or assign version number
     bool found = false, deleted = false, unsynced = false, is_del = (op->opcode == BS_OP_DELETE);
     bool wait_big = false, wait_del = false;
-    void *dyn = NULL;
-    if (is_del)
-    {
-        op->len = 0;
-    }
-    size_t dyn_size = dsk.dirty_dyn_size(op->offset, op->len);
-    if (!is_del && alloc_dyn_data)
-    {
-        // FIXME: Working with `dyn_data` has to be refactored somehow but I first have to decide how :)
-        // +sizeof(int) = refcount
-        dyn = calloc_or_die(1, dyn_size+sizeof(int));
-        *((int*)dyn) = 1;
-    }
-    uint8_t *dyn_ptr = (uint8_t*)(alloc_dyn_data ? dyn+sizeof(int) : &dyn);
+    void *bmp = NULL;
     uint64_t version = 1;
+    if (!is_del && dsk.clean_entry_bitmap_size > sizeof(void*))
+    {
+        bmp = calloc_or_die(1, dsk.clean_entry_bitmap_size);
+    }
     if (dirty_db.size() > 0)
     {
         auto dirty_it = dirty_db.upper_bound((obj_ver_id){
@@ -42,9 +33,10 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
                 : ((dirty_it->second.state & BS_ST_WORKFLOW_MASK) == BS_ST_WAIT_BIG);
             if (!is_del && !deleted)
             {
-                void *dyn_from = alloc_dyn_data
-                    ? (uint8_t*)dirty_it->second.dyn_data + sizeof(int) : (uint8_t*)&dirty_it->second.dyn_data;
-                memcpy(dyn_ptr, dyn_from, dsk.clean_entry_bitmap_size);
+                if (dsk.clean_entry_bitmap_size > sizeof(void*))
+                    memcpy(bmp, dirty_it->second.bitmap, dsk.clean_entry_bitmap_size);
+                else
+                    bmp = dirty_it->second.bitmap;
             }
         }
     }
@@ -58,7 +50,7 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
             if (!is_del)
             {
                 void *bmp_ptr = get_clean_entry_bitmap(clean_it->second.location, dsk.clean_entry_bitmap_size);
-                memcpy(dyn_ptr, bmp_ptr, dsk.clean_entry_bitmap_size);
+                memcpy((dsk.clean_entry_bitmap_size > sizeof(void*) ? bmp : &bmp), bmp_ptr, dsk.clean_entry_bitmap_size);
             }
         }
         else
@@ -120,9 +112,9 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
             printf("Write %lx:%lx v%lu requested, but we already have v%lu\n", op->oid.inode, op->oid.stripe, op->version, version);
 #endif
             op->retval = -EEXIST;
-            if (!is_del && alloc_dyn_data)
+            if (!is_del && dsk.clean_entry_bitmap_size > sizeof(void*))
             {
-                free(dyn);
+                free(bmp);
             }
             return false;
         }
@@ -166,50 +158,26 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
         if (op->bitmap)
         {
             // Only allow to overwrite part of the object bitmap respective to the write's offset/len
+            uint8_t *bmp_ptr = (uint8_t*)(dsk.clean_entry_bitmap_size > sizeof(void*) ? bmp : &bmp);
             uint32_t bit = op->offset/dsk.bitmap_granularity;
             uint32_t bits_left = op->len/dsk.bitmap_granularity;
             while (!(bit % 8) && bits_left >= 8)
             {
                 // Copy bytes
-                dyn_ptr[bit/8] = ((uint8_t*)op->bitmap)[bit/8];
+                bmp_ptr[bit/8] = ((uint8_t*)op->bitmap)[bit/8];
                 bit += 8;
                 bits_left -= 8;
             }
             while (bits_left > 0)
             {
                 // Copy bits
-                dyn_ptr[bit/8] = (dyn_ptr[bit/8] & ~(1 << (bit%8)))
+                bmp_ptr[bit/8] = (bmp_ptr[bit/8] & ~(1 << (bit%8)))
                     | (((uint8_t*)op->bitmap)[bit/8] & (1 << bit%8));
                 bit++;
                 bits_left--;
             }
         }
     }
-    // Calculate checksums
-    // FIXME: Allow to receive checksums from outside?
-    if (!is_del && dsk.data_csum_type && op->len > 0)
-    {
-        uint32_t *data_csums = (uint32_t*)(dyn_ptr + dsk.clean_entry_bitmap_size);
-        uint32_t start = op->offset / dsk.csum_block_size;
-        uint32_t end = (op->offset+op->len-1) / dsk.csum_block_size;
-        auto fn = state & BS_ST_BIG_WRITE ? crc32c_pad : crc32c_nopad;
-        if (start == end)
-            data_csums[0] = fn(0, op->buf, op->len, op->offset - start*dsk.csum_block_size, end*dsk.csum_block_size - (op->offset+op->len));
-        else
-        {
-            // First block
-            data_csums[0] = fn(0, op->buf, dsk.csum_block_size*(start+1)-op->offset, op->offset - start*dsk.csum_block_size, 0);
-            // Intermediate blocks
-            for (uint32_t i = start+1; i < end; i++)
-                data_csums[i-start] = crc32c(0, (uint8_t*)op->buf + dsk.csum_block_size*i-op->offset, dsk.csum_block_size);
-            // Last block
-            data_csums[end-start] = fn(
-                0, (uint8_t*)op->buf + end*dsk.csum_block_size - op->offset,
-                op->offset+op->len - end*dsk.csum_block_size,
-                0, (end+1)*dsk.csum_block_size - (op->offset+op->len)
-            );
-        }
-    }
     dirty_db.emplace((obj_ver_id){
         .oid = op->oid,
         .version = op->version,
@@ -220,7 +188,7 @@ bool blockstore_impl_t::enqueue_write(blockstore_op_t *op)
         .offset = is_del ? 0 : op->offset,
         .len = is_del ? 0 : op->len,
         .journal_sector = 0,
-        .dyn_data = dyn,
+        .bitmap = bmp,
     });
     return true;
 }
@@ -229,7 +197,8 @@ void blockstore_impl_t::cancel_all_writes(blockstore_op_t *op, blockstore_dirty_
 {
     while (dirty_it != dirty_db.end() && dirty_it->first.oid == op->oid)
     {
-        free_dirty_dyn_data(dirty_it->second);
+        if (dsk.clean_entry_bitmap_size > sizeof(void*))
+            free(dirty_it->second.bitmap);
         dirty_db.erase(dirty_it++);
     }
     bool found = false;
@@ -311,7 +280,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
     {
         blockstore_journal_check_t space_check(this);
         if (!space_check.check_available(op, unsynced_big_write_count + 1,
-            sizeof(journal_entry_big_write) + dsk.clean_dyn_size,
+            sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size,
             (dirty_it->second.state & BS_ST_INSTANT) ? JOURNAL_INSTANT_RESERVATION : JOURNAL_STABILIZE_RESERVATION))
         {
             return 0;
@@ -394,13 +363,12 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
     {
         // Small (journaled) write
         // First check if the journal has sufficient space
-        uint64_t dyn_size = dsk.dirty_dyn_size(op->offset, op->len);
         blockstore_journal_check_t space_check(this);
         if (unsynced_big_write_count &&
             !space_check.check_available(op, unsynced_big_write_count,
-                sizeof(journal_entry_big_write) + dsk.clean_dyn_size, 0)
+                sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size, 0)
             || !space_check.check_available(op, 1,
-                sizeof(journal_entry_small_write) + dyn_size,
+                sizeof(journal_entry_small_write) + dsk.clean_entry_bitmap_size,
                 op->len + ((dirty_it->second.state & BS_ST_INSTANT) ? JOURNAL_INSTANT_RESERVATION : JOURNAL_STABILIZE_RESERVATION)))
         {
             return 0;
@@ -409,7 +377,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         BS_SUBMIT_CHECK_SQES(
             // Write current journal sector only if it's dirty and full, or in the immediate_commit mode
             (immediate_commit != IMMEDIATE_NONE ||
-                !journal.entry_fits(sizeof(journal_entry_small_write) + dyn_size) ? 1 : 0) +
+                !journal.entry_fits(sizeof(journal_entry_small_write) + dsk.clean_entry_bitmap_size) ? 1 : 0) +
             (op->len > 0 ? 1 : 0)
         );
         write_iodepth++;
@@ -417,7 +385,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         auto cb = [this, op](ring_data_t *data) { handle_write_event(data, op); };
         if (immediate_commit == IMMEDIATE_NONE)
         {
-            if (!journal.entry_fits(sizeof(journal_entry_small_write) + dyn_size))
+            if (!journal.entry_fits(sizeof(journal_entry_small_write) + dsk.clean_entry_bitmap_size))
             {
                 prepare_journal_sector_write(journal.cur_sector, op);
             }
@@ -429,7 +397,7 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         // Then pre-fill journal entry
         journal_entry_small_write *je = (journal_entry_small_write*)prefill_single_journal_entry(
             journal, op->opcode == BS_OP_WRITE_STABLE ? JE_SMALL_WRITE_INSTANT : JE_SMALL_WRITE,
-            sizeof(journal_entry_small_write) + dyn_size
+            sizeof(journal_entry_small_write) + dsk.clean_entry_bitmap_size
         );
         dirty_it->second.journal_sector = journal.sector_info[journal.cur_sector].offset;
         journal.used_sectors[journal.sector_info[journal.cur_sector].offset]++;
@@ -463,9 +431,8 @@ int blockstore_impl_t::dequeue_write(blockstore_op_t *op)
         je->offset = op->offset;
         je->len = op->len;
         je->data_offset = journal.next_free;
-        je->crc32_data = dsk.csum_block_size ? 0 : crc32c(0, op->buf, op->len);
-        memcpy((void*)(je+1), (alloc_dyn_data
-            ? (uint8_t*)dirty_it->second.dyn_data+sizeof(int) : (uint8_t*)&dirty_it->second.dyn_data), dyn_size);
+        je->crc32_data = crc32c(0, op->buf, op->len);
+        memcpy((void*)(je+1), (dsk.clean_entry_bitmap_size > sizeof(void*) ? dirty_it->second.bitmap : &dirty_it->second.bitmap), dsk.clean_entry_bitmap_size);
         je->crc32 = je_crc32((journal_entry*)je);
         journal.crc32_last = je->crc32;
         if (immediate_commit != IMMEDIATE_NONE)
@@ -534,9 +501,9 @@ resume_2:
             .version = op->version,
         });
         assert(dirty_it != dirty_db.end());
-        uint64_t dyn_size = dsk.dirty_dyn_size(op->offset, op->len);
         blockstore_journal_check_t space_check(this);
-        if (!space_check.check_available(op, 1, sizeof(journal_entry_big_write) + dyn_size,
+        if (!space_check.check_available(op, 1,
+            sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size,
             ((dirty_it->second.state & BS_ST_INSTANT) ? JOURNAL_INSTANT_RESERVATION : JOURNAL_STABILIZE_RESERVATION)))
         {
             return 0;
@@ -544,7 +511,7 @@ resume_2:
         BS_SUBMIT_CHECK_SQES(1);
         journal_entry_big_write *je = (journal_entry_big_write*)prefill_single_journal_entry(
             journal, op->opcode == BS_OP_WRITE_STABLE ? JE_BIG_WRITE_INSTANT : JE_BIG_WRITE,
-            sizeof(journal_entry_big_write) + dyn_size
+            sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size
         );
         dirty_it->second.journal_sector = journal.sector_info[journal.cur_sector].offset;
         journal.used_sectors[journal.sector_info[journal.cur_sector].offset]++;
@@ -560,8 +527,7 @@ resume_2:
         je->offset = op->offset;
         je->len = op->len;
         je->location = dirty_it->second.location;
-        memcpy((void*)(je+1), (alloc_dyn_data
-            ? (uint8_t*)dirty_it->second.dyn_data+sizeof(int) : (uint8_t*)&dirty_it->second.dyn_data), dyn_size);
+        memcpy((void*)(je+1), (dsk.clean_entry_bitmap_size > sizeof(void*) ? dirty_it->second.bitmap : &dirty_it->second.bitmap), dsk.clean_entry_bitmap_size);
         je->crc32 = je_crc32((journal_entry*)je);
         journal.crc32_last = je->crc32;
         prepare_journal_sector_write(journal.cur_sector, op);

src/cli_ls.cpp

@@ -56,14 +56,15 @@ struct image_lister_t
             {
                 continue;
             }
-            auto & pool_cfg = parent->cli->st_cli.pool_config.at(INODE_POOL(ic.second.num));
+            auto pool_it = parent->cli->st_cli.pool_config.find(INODE_POOL(ic.second.num));
+            bool good_pool = pool_it != parent->cli->st_cli.pool_config.end();
             auto item = json11::Json::object {
                 { "name", ic.second.name },
                 { "size", ic.second.size },
                 { "used_size", 0 },
                 { "readonly", ic.second.readonly },
                 { "pool_id", (uint64_t)INODE_POOL(ic.second.num) },
-                { "pool_name", pool_cfg.name },
+                { "pool_name", good_pool ? pool_it->second.name : "? (ID:"+std::to_string(INODE_POOL(ic.second.num))+")" },
                 { "inode_num", INODE_NO_POOL(ic.second.num) },
                 { "inode_id", ic.second.num },
             };
@@ -247,6 +248,8 @@ resume_1:
         if (state == 1)
             goto resume_1;
         get_list();
+        if (state == 100)
+            return;
         if (show_stats)
         {
 resume_1:
@@ -269,7 +272,7 @@ resume_1:
             { "key", "name" },
             { "title", "NAME" },
         });
-        if (!list_pool_id)
+        if (list_pool_name == "")
         {
             cols.push_back(json11::Json::object{
                 { "key", "pool_name" },

src/disk_simple_offsets.cpp

@@ -10,7 +10,6 @@
 #include "json11/json11.hpp"
 #include "str_util.h"
 #include "blockstore.h"
-#include "blockstore_disk.h"
 
 // Calculate offsets for a block device and print OSD command line parameters
 void disk_tool_simple_offsets(json11::Json cfg, bool json_output)
@@ -21,39 +20,23 @@ void disk_tool_simple_offsets(json11::Json cfg, bool json_output)
         fprintf(stderr, "Device path is missing\n");
         exit(1);
     }
-    uint64_t data_block_size = parse_size(cfg["object_size"].string_value());
+    uint64_t object_size = parse_size(cfg["object_size"].string_value());
     uint64_t bitmap_granularity = parse_size(cfg["bitmap_granularity"].string_value());
     uint64_t journal_size = parse_size(cfg["journal_size"].string_value());
     uint64_t device_block_size = parse_size(cfg["device_block_size"].string_value());
     uint64_t journal_offset = parse_size(cfg["journal_offset"].string_value());
     uint64_t device_size = parse_size(cfg["device_size"].string_value());
-    uint32_t csum_block_size = parse_size(cfg["csum_block_size"].string_value());
-    uint32_t data_csum_type = BLOCKSTORE_CSUM_NONE;
-    if (cfg["data_csum_type"] == "crc32c")
-        data_csum_type = BLOCKSTORE_CSUM_CRC32C;
-    else if (cfg["data_csum_type"].string_value() != "" && cfg["data_csum_type"].string_value() != "none")
-    {
-        fprintf(
-            stderr, "data_csum_type=%s is unsupported, only \"crc32c\" and \"none\" are supported",
-            cfg["data_csum_type"].string_value().c_str()
-        );
-        exit(1);
-    }
     std::string format = cfg["format"].string_value();
     if (json_output)
         format = "json";
-    if (!data_block_size)
-        data_block_size = 1 << DEFAULT_DATA_BLOCK_ORDER;
+    if (!object_size)
+        object_size = 1 << DEFAULT_DATA_BLOCK_ORDER;
     if (!bitmap_granularity)
         bitmap_granularity = DEFAULT_BITMAP_GRANULARITY;
     if (!journal_size)
         journal_size = 16*1024*1024;
     if (!device_block_size)
         device_block_size = 4096;
-    if (!data_csum_type)
-        csum_block_size = 0;
-    else if (!csum_block_size)
-        csum_block_size = bitmap_granularity;
     uint64_t orig_device_size = device_size;
     if (!device_size)
     {
@@ -102,30 +85,22 @@ void disk_tool_simple_offsets(json11::Json cfg, bool json_output)
         fprintf(stderr, "Invalid device block size specified: %lu\n", device_block_size);
         exit(1);
     }
-    if (data_block_size < device_block_size || data_block_size > MAX_DATA_BLOCK_SIZE ||
-        data_block_size & (data_block_size-1) != 0)
+    if (object_size < device_block_size || object_size > MAX_DATA_BLOCK_SIZE ||
+        object_size & (object_size-1) != 0)
     {
-        fprintf(stderr, "Invalid object size specified: %lu\n", data_block_size);
+        fprintf(stderr, "Invalid object size specified: %lu\n", object_size);
         exit(1);
     }
-    if (bitmap_granularity < device_block_size || bitmap_granularity > data_block_size ||
+    if (bitmap_granularity < device_block_size || bitmap_granularity > object_size ||
         bitmap_granularity & (bitmap_granularity-1) != 0)
     {
         fprintf(stderr, "Invalid bitmap granularity specified: %lu\n", bitmap_granularity);
         exit(1);
     }
-    if (csum_block_size && (data_block_size % csum_block_size))
-    {
-        fprintf(stderr, "csum_block_size must be a divisor of data_block_size\n");
-        exit(1);
-    }
     journal_offset = ((journal_offset+device_block_size-1)/device_block_size)*device_block_size;
     uint64_t meta_offset = journal_offset + ((journal_size+device_block_size-1)/device_block_size)*device_block_size;
-    uint64_t data_csum_size = (data_csum_type ? data_block_size/csum_block_size*(data_csum_type & 0xFF) : 0);
-    uint64_t clean_entry_bitmap_size = data_block_size/bitmap_granularity/8;
-    uint64_t clean_entry_size = 24 /*sizeof(clean_disk_entry)*/ + 2*clean_entry_bitmap_size + data_csum_size + 4 /*entry_csum*/;
-    uint64_t entries_per_block = device_block_size / clean_entry_size;
-    uint64_t object_count = ((device_size-meta_offset)/data_block_size);
+    uint64_t entries_per_block = (device_block_size / (24 + 2*object_size/bitmap_granularity/8));
+    uint64_t object_count = ((device_size-meta_offset)/object_size);
     uint64_t meta_size = (1 + (object_count+entries_per_block-1)/entries_per_block) * device_block_size;
     uint64_t data_offset = meta_offset + meta_size;
     if (format == "json")

src/disk_tool.cpp

@@ -59,8 +59,6 @@ static const char *help_text =
     "    --journal_size 32M/1G      Set journal size (area or partition size)\n"
     "    --block_size 128k/1M       Set blockstore object size\n"
     "    --bitmap_granularity 4k    Set bitmap granularity\n"
-    "    --data_csum_type none      Set data checksum type (crc32c or none)\n"
-    "    --csum_block_size 4k       Set data checksum block size\n"
     "    --data_device_block 4k     Override data device block size\n"
     "    --meta_device_block 4k     Override metadata device block size\n"
     "    --journal_device_block 4k  Override journal device block size\n"
@@ -74,9 +72,8 @@ static const char *help_text =
     "  If it doesn't succeed it issues a warning in the system log.\n"
     "  \n"
     "  You can also pass other OSD options here as arguments and they'll be persisted\n"
-    "  in the superblock: cached_read_data, cached_read_meta, cached_read_journal,\n"
-    "  inmemory_metadata, inmemory_journal, max_write_iodepth,\n"
-    "  min_flusher_count, max_flusher_count, journal_sector_buffer_count,\n"
+    "  to the superblock: max_write_iodepth, max_write_iodepth, min_flusher_count,\n"
+    "  max_flusher_count, inmemory_metadata, inmemory_journal, journal_sector_buffer_count,\n"
     "  journal_no_same_sector_overwrites, throttle_small_writes, throttle_target_iops,\n"
     "  throttle_target_mbs, throttle_target_parallelism, throttle_threshold_us.\n"
     "\n"
@@ -164,8 +161,6 @@ static const char *help_text =
     "    --object_size 128k       Set blockstore block size\n"
     "    --bitmap_granularity 4k  Set bitmap granularity\n"
     "    --journal_size 16M       Set journal size\n"
-    "    --data_csum_type none    Set data checksum type (crc32c or none)\n"
-    "    --csum_block_size 4k     Set data checksum block size\n"
     "    --device_block_size 4k   Set device block size\n"
     "    --journal_offset 0       Set journal offset\n"
     "    --device_size 0          Set device size\n"
@@ -275,19 +270,6 @@ int main(int argc, char *argv[])
             fprintf(stderr, "Invalid JSON: %s\n", json_err.c_str());
             return 1;
         }
-        if (entries[0]["type"] == "start")
-        {
-            self.dsk.data_csum_type = csum_type_from_str(entries[0]["data_csum_type"].string_value());
-            self.dsk.csum_block_size = entries[0]["csum_block_size"].uint64_value();
-        }
-        if (self.options["data_csum_type"] != "")
-        {
-            self.dsk.data_csum_type = csum_type_from_str(self.options["data_csum_type"]);
-        }
-        if (self.options["csum_block_size"] != "")
-        {
-            self.dsk.csum_block_size = stoull_full(self.options["csum_block_size"], 0);
-        }
         return self.write_json_journal(entries);
     }
     else if (!strcmp(cmd[0], "dump-meta"))

src/disk_tool.h

@@ -64,19 +64,17 @@ struct disk_tool_t
     ring_loop_t *ringloop;
     ring_consumer_t ring_consumer;
     int remap_active;
-    journal_entry_start je_start;
     uint8_t *new_journal_buf, *new_meta_buf, *new_journal_ptr, *new_journal_data;
     uint64_t new_journal_in_pos;
     int64_t data_idx_diff;
     uint64_t total_blocks, free_first, free_last;
-    uint64_t new_clean_entry_bitmap_size, new_data_csum_size, new_clean_entry_size, new_entries_per_block;
+    uint64_t new_clean_entry_bitmap_size, new_clean_entry_size, new_entries_per_block;
     int new_journal_fd, new_meta_fd;
     resizer_data_moving_t *moving_blocks;
 
     bool started;
     void *small_write_data;
     uint32_t data_crc32;
-    bool data_csum_valid;
     uint32_t crc32_last;
     uint32_t new_crc32_prev;
 
@@ -86,11 +84,11 @@ struct disk_tool_t
     void dump_journal_entry(int num, journal_entry *je, bool json);
     int process_journal(std::function<int(void*)> block_fn);
     int process_journal_block(void *buf, std::function<void(int, journal_entry*)> iter_fn);
-    int process_meta(std::function<void(blockstore_meta_header_v2_t *)> hdr_fn,
+    int process_meta(std::function<void(blockstore_meta_header_v1_t *)> hdr_fn,
         std::function<void(uint64_t, clean_disk_entry*, uint8_t*)> record_fn);
 
     int dump_meta();
-    void dump_meta_header(blockstore_meta_header_v2_t *hdr);
+    void dump_meta_header(blockstore_meta_header_v1_t *hdr);
     void dump_meta_entry(uint64_t block_num, clean_disk_entry *entry, uint8_t *bitmap);
 
     int write_json_journal(json11::Json entries);
@@ -98,7 +96,7 @@ struct disk_tool_t
 
     int resize_data();
     int resize_parse_params();
-    void resize_init(blockstore_meta_header_v2_t *hdr);
+    void resize_init(blockstore_meta_header_v1_t *hdr);
     int resize_remap_blocks();
     int resize_copy_data();
     int resize_rewrite_journal();
@@ -143,5 +141,3 @@ json11::Json read_parttable(std::string dev);
 uint64_t dev_size_from_parttable(json11::Json pt);
 uint64_t free_from_parttable(json11::Json pt);
 int fix_partition_type(std::string dev_by_uuid);
-std::string csum_type_str(uint32_t data_csum_type);
-uint32_t csum_type_from_str(std::string data_csum_type);

src/disk_tool_journal.cpp

@@ -55,23 +55,6 @@ int disk_tool_t::dump_journal()
                     printf("offset %08lx:\n", journal_pos);
                 else
                     printf(",\"entries\":[\n");
-                if (journal_pos == 0)
-                {
-                    // Fill journal header to know checksum type & size
-                    journal_entry *je = (journal_entry*)journal_buf;
-                    if (je->magic == JOURNAL_MAGIC && je->type == JE_START &&
-                        (je->start.version == JOURNAL_VERSION_V1 || je->start.version == JOURNAL_VERSION_V2))
-                    {
-                        memcpy(&je_start, je, sizeof(je_start));
-                        if (je_start.size == JE_START_V0_SIZE)
-                            je_start.version = 0;
-                        if (je_start.version < JOURNAL_VERSION_V2)
-                        {
-                            je_start.data_csum_type = 0;
-                            je_start.csum_block_size = 0;
-                        }
-                    }
-                }
                 first_entry = true;
                 process_journal_block(journal_buf, [this](int num, journal_entry *je) { dump_journal_entry(num, je, json); });
                 if (json)
@@ -137,22 +120,8 @@ int disk_tool_t::process_journal(std::function<int(void*)> block_fn)
         fprintf(stderr, "offset %08lx: journal superblock is invalid\n", journal_pos);
         r = 1;
     }
-    else if (je->start.size != JE_START_V0_SIZE && je->start.version != JOURNAL_VERSION_V1 && je->start.version != JOURNAL_VERSION_V2)
-    {
-        fprintf(stderr, "offset %08lx: journal superblock contains version %lu, but I only understand 0, 1 and 2\n",
-            journal_pos, je->start.size == JE_START_V0_SIZE ? 0 : je->start.version);
-        r = 1;
-    }
     else
     {
-        memcpy(&je_start, je, sizeof(je_start));
-        if (je_start.size == JE_START_V0_SIZE)
-            je_start.version = 0;
-        if (je_start.version < JOURNAL_VERSION_V2)
-        {
-            je_start.data_csum_type = 0;
-            je_start.csum_block_size = 0;
-        }
         started = false;
         crc32_last = 0;
         block_fn(data);
@@ -214,49 +183,7 @@ int disk_tool_t::process_journal_block(void *buf, std::function<void(int, journa
             }
             small_write_data = memalign_or_die(MEM_ALIGNMENT, je->small_write.len);
             assert(pread(dsk.journal_fd, small_write_data, je->small_write.len, dsk.journal_offset+je->small_write.data_offset) == je->small_write.len);
-            data_crc32 = je_start.csum_block_size ? 0 : crc32c(0, small_write_data, je->small_write.len);
-            data_csum_valid = (data_crc32 == je->small_write.crc32_data);
-            if (je_start.csum_block_size && je->small_write.len > 0)
-            {
-                // like in enqueue_write()
-                uint32_t start = je->small_write.offset / je_start.csum_block_size;
-                uint32_t end = (je->small_write.offset+je->small_write.len-1) / je_start.csum_block_size;
-                uint32_t data_csum_size = (end-start+1) * (je_start.data_csum_type & 0xFF);
-                if (je->size < sizeof(journal_entry_small_write) + data_csum_size)
-                {
-                    data_csum_valid = false;
-                }
-                else
-                {
-                    uint32_t calc_csum = 0;
-                    uint32_t *block_csums = (uint32_t*)((uint8_t*)je + je->size - data_csum_size);
-                    if (start == end)
-                    {
-                        calc_csum = crc32c(0, (uint8_t*)small_write_data, je->small_write.len);
-                        data_csum_valid = data_csum_valid && (calc_csum == *block_csums++);
-                    }
-                    else
-                    {
-                        // First block
-                        calc_csum = crc32c(0, (uint8_t*)small_write_data,
-                            je_start.csum_block_size*(start+1)-je->small_write.offset);
-                        data_csum_valid = data_csum_valid && (calc_csum == *block_csums++);
-                        // Intermediate blocks
-                        for (uint32_t i = start+1; i < end; i++)
-                        {
-                            calc_csum = crc32c(0, (uint8_t*)small_write_data +
-                                je_start.csum_block_size*i-je->small_write.offset, je_start.csum_block_size);
-                            data_csum_valid = data_csum_valid && (calc_csum == *block_csums++);
-                        }
-                        // Last block
-                        calc_csum = crc32c(
-                            0, (uint8_t*)small_write_data + end*je_start.csum_block_size - je->small_write.offset,
-                            je->small_write.offset+je->small_write.len - end*je_start.csum_block_size
-                        );
-                        data_csum_valid = data_csum_valid && (calc_csum == *block_csums++);
-                    }
-                }
-            }
+            data_crc32 = crc32c(0, small_write_data, je->small_write.len);
         }
         iter_fn(entry, je);
         if (je->type == JE_SMALL_WRITE || je->type == JE_SMALL_WRITE_INSTANT)
@@ -296,40 +223,29 @@ void disk_tool_t::dump_journal_entry(int num, journal_entry *je, bool json)
     if (je->type == JE_START)
     {
         printf(
-            json ? ",\"type\":\"start\",\"start\":\"0x%lx\"" : "je_start start=%08lx",
+            json ? ",\"type\":\"start\",\"start\":\"0x%lx\"}" : "je_start start=%08lx\n",
             je->start.journal_start
         );
-        if (je->start.data_csum_type)
-        {
-            printf(
-                json ? ",\"data_csum_type\":\"%s\",\"csum_block_size\":%u" : " data_csum_type=%s csum_block_size=%u",
-                csum_type_str(je->start.data_csum_type).c_str(), je->start.csum_block_size
-            );
-        }
-        printf(json ? "}" : "\n");
     }
     else if (je->type == JE_SMALL_WRITE || je->type == JE_SMALL_WRITE_INSTANT)
     {
-        auto & sw = je->small_write;
         printf(
             json ? ",\"type\":\"small_write%s\",\"inode\":\"0x%lx\",\"stripe\":\"0x%lx\",\"ver\":\"%lu\",\"offset\":%u,\"len\":%u,\"loc\":\"0x%lx\""
                 : "je_small_write%s oid=%lx:%lx ver=%lu offset=%u len=%u loc=%08lx",
             je->type == JE_SMALL_WRITE_INSTANT ? "_instant" : "",
-            sw.oid.inode, sw.oid.stripe, sw.version, sw.offset, sw.len, sw.data_offset
+            je->small_write.oid.inode, je->small_write.oid.stripe,
+            je->small_write.version, je->small_write.offset, je->small_write.len,
+            je->small_write.data_offset
         );
-        if (journal_calc_data_pos != sw.data_offset)
+        if (journal_calc_data_pos != je->small_write.data_offset)
         {
             printf(json ? ",\"bad_loc\":true,\"calc_loc\":\"0x%lx\""
                 : " (mismatched, calculated = %lu)", journal_pos);
         }
-        uint32_t data_csum_size = (!je_start.csum_block_size
-            ? 0
-            : ((sw.offset + sw.len - 1)/je_start.csum_block_size - sw.offset/je_start.csum_block_size + 1)
-                *(je_start.data_csum_type & 0xFF));
-        if (je->size > sizeof(journal_entry_small_write) + data_csum_size)
+        if (je->small_write.size > sizeof(journal_entry_small_write))
         {
             printf(json ? ",\"bitmap\":\"" : " (bitmap: ");
-            for (int i = sizeof(journal_entry_small_write); i < je->size - data_csum_size; i++)
+            for (int i = sizeof(journal_entry_small_write); i < je->small_write.size; i++)
             {
                 printf("%02x", ((uint8_t*)je)[i]);
             }
@@ -338,56 +254,34 @@ void disk_tool_t::dump_journal_entry(int num, journal_entry *je, bool json)
         if (dump_with_data)
         {
             printf(json ? ",\"data\":\"" : " (data: ");
-            for (int i = 0; i < sw.len; i++)
+            for (int i = 0; i < je->small_write.len; i++)
             {
                 printf("%02x", ((uint8_t*)small_write_data)[i]);
             }
             printf(json ? "\"" : ")");
         }
-        if (data_csum_size > 0 && je->size >= sizeof(journal_entry_small_write) + data_csum_size)
-        {
-            printf(json ? ",\"block_csums\":\"" : " block_csums=");
-            uint8_t *block_csums = (uint8_t*)je + je->size - data_csum_size;
-            for (int i = 0; i < data_csum_size; i++)
-                printf("%02x", block_csums[i]);
-            printf(json ? "\"" : "");
-        }
-        else
-        {
-            printf(json ? ",\"data_crc32\":\"%08x\"" : " data_crc32=%08x", sw.crc32_data);
-        }
         printf(
-            json ? ",\"data_valid\":%s}" : "%s\n",
-            (data_csum_valid
-                ? (json ? "true" : " (valid)")
-                : (json ? "false" : " (invalid)"))
+            json ? ",\"data_crc32\":\"%08x\",\"data_valid\":%s}" : " data_crc32=%08x%s\n",
+            je->small_write.crc32_data,
+            (data_crc32 != je->small_write.crc32_data
+                ? (json ? "false" : " (invalid)")
+                : (json ? "true" : " (valid)"))
         );
     }
     else if (je->type == JE_BIG_WRITE || je->type == JE_BIG_WRITE_INSTANT)
     {
-        auto & bw = je->big_write;
         printf(
             json ? ",\"type\":\"big_write%s\",\"inode\":\"0x%lx\",\"stripe\":\"0x%lx\",\"ver\":\"%lu\",\"offset\":%u,\"len\":%u,\"loc\":\"0x%lx\""
                 : "je_big_write%s oid=%lx:%lx ver=%lu offset=%u len=%u loc=%08lx",
             je->type == JE_BIG_WRITE_INSTANT ? "_instant" : "",
-            bw.oid.inode, bw.oid.stripe, bw.version, bw.offset, bw.len, bw.location
+            je->big_write.oid.inode, je->big_write.oid.stripe,
+            je->big_write.version, je->big_write.offset, je->big_write.len,
+            je->big_write.location
         );
-        uint32_t data_csum_size = (!je_start.csum_block_size
-            ? 0
-            : ((bw.offset + bw.len - 1)/je_start.csum_block_size - bw.offset/je_start.csum_block_size + 1)
-                *(je_start.data_csum_type & 0xFF));
-        if (data_csum_size > 0 && je->size >= sizeof(journal_entry_big_write) + data_csum_size)
-        {
-            printf(json ? ",\"block_csums\":\"" : " block_csums=");
-            uint8_t *block_csums = (uint8_t*)je + je->size - data_csum_size;
-            for (int i = 0; i < data_csum_size; i++)
-                printf("%02x", block_csums[i]);
-            printf(json ? "\"" : "");
-        }
-        if (bw.size > sizeof(journal_entry_big_write) + data_csum_size)
+        if (je->big_write.size > sizeof(journal_entry_big_write))
         {
             printf(json ? ",\"bitmap\":\"" : " (bitmap: ");
-            for (int i = sizeof(journal_entry_big_write); i < bw.size - data_csum_size; i++)
+            for (int i = sizeof(journal_entry_big_write); i < je->big_write.size; i++)
             {
                 printf("%02x", ((uint8_t*)je)[i]);
             }
@@ -444,9 +338,7 @@ int disk_tool_t::write_json_journal(json11::Json entries)
         .type = JE_START,
         .size = sizeof(journal_entry_start),
         .journal_start = dsk.journal_block_size,
-        .version = JOURNAL_VERSION_V2,
-        .data_csum_type = dsk.data_csum_type,
-        .csum_block_size = dsk.csum_block_size,
+        .version = JOURNAL_VERSION,
     };
     ((journal_entry*)new_journal_buf)->crc32 = je_crc32((journal_entry*)new_journal_buf);
     new_journal_ptr += dsk.journal_block_size;
@@ -466,11 +358,9 @@ int disk_tool_t::write_json_journal(json11::Json entries)
         uint32_t entry_size = (type == JE_START
             ? sizeof(journal_entry_start)
             : (type == JE_SMALL_WRITE || type == JE_SMALL_WRITE_INSTANT
-                ? sizeof(journal_entry_small_write) + dsk.clean_entry_bitmap_size +
-                    (dsk.data_csum_type ? rec["len"].uint64_value()/dsk.csum_block_size*(dsk.data_csum_type & 0xFF) : 0)
+                ? sizeof(journal_entry_small_write) + dsk.clean_entry_bitmap_size
                 : (type == JE_BIG_WRITE || type == JE_BIG_WRITE_INSTANT
-                    ? sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size +
-                        (dsk.data_csum_type ? rec["len"].uint64_value()/dsk.csum_block_size*(dsk.data_csum_type & 0xFF) : 0)
+                    ? sizeof(journal_entry_big_write) + dsk.clean_entry_bitmap_size
                     : sizeof(journal_entry_del))));
         if (dsk.journal_block_size < new_journal_in_pos + entry_size)
         {
@@ -512,24 +402,12 @@ int disk_tool_t::write_json_journal(json11::Json entries)
                 .offset = (uint32_t)rec["offset"].uint64_value(),
                 .len = (uint32_t)rec["len"].uint64_value(),
                 .data_offset = (uint64_t)(new_journal_data-new_journal_buf),
-                .crc32_data = !dsk.data_csum_type ? 0 : (uint32_t)sscanf_json("%x", rec["data_crc32"]),
+                .crc32_data = (uint32_t)sscanf_json("%x", rec["data_crc32"]),
             };
-            uint32_t data_csum_size = !dsk.data_csum_type ? 0 : ne->small_write.len/dsk.csum_block_size*(dsk.data_csum_type & 0xFF);
-            fromhexstr(rec["bitmap"].string_value(), dsk.clean_entry_bitmap_size, ((uint8_t*)ne) + sizeof(journal_entry_small_write) + data_csum_size);
+            fromhexstr(rec["bitmap"].string_value(), dsk.clean_entry_bitmap_size, ((uint8_t*)ne) + sizeof(journal_entry_small_write));
             fromhexstr(rec["data"].string_value(), ne->small_write.len, new_journal_data);
-            if (dsk.data_csum_type)
-                fromhexstr(rec["block_csums"].string_value(), data_csum_size, ((uint8_t*)ne) + sizeof(journal_entry_small_write));
             if (rec["data"].is_string())
-            {
-                if (!dsk.data_csum_type)
-                    ne->small_write.crc32_data = crc32c(0, new_journal_data, ne->small_write.len);
-                else if (dsk.data_csum_type == BLOCKSTORE_CSUM_CRC32C)
-                {
-                    uint32_t *block_csums = (uint32_t*)(((uint8_t*)ne) + sizeof(journal_entry_small_write));
-                    for (uint32_t i = 0; i < ne->small_write.len; i += dsk.csum_block_size, block_csums++)
-                        *block_csums = crc32c(0, new_journal_data+i, dsk.csum_block_size);
-                }
-            }
+                ne->small_write.crc32_data = crc32c(0, new_journal_data, ne->small_write.len);
             new_journal_data += ne->small_write.len;
         }
         else if (type == JE_BIG_WRITE || type == JE_BIG_WRITE_INSTANT)
@@ -548,10 +426,7 @@ int disk_tool_t::write_json_journal(json11::Json entries)
                 .len = (uint32_t)rec["len"].uint64_value(),
                 .location = sscanf_json(NULL, rec["loc"]),
             };
-            uint32_t data_csum_size = !dsk.data_csum_type ? 0 : ne->big_write.len/dsk.csum_block_size*(dsk.data_csum_type & 0xFF);
-            fromhexstr(rec["bitmap"].string_value(), dsk.clean_entry_bitmap_size, ((uint8_t*)ne) + sizeof(journal_entry_big_write) + data_csum_size);
-            if (dsk.data_csum_type)
-                fromhexstr(rec["block_csums"].string_value(), data_csum_size, ((uint8_t*)ne) + sizeof(journal_entry_big_write));
+            fromhexstr(rec["bitmap"].string_value(), dsk.clean_entry_bitmap_size, ((uint8_t*)ne) + sizeof(journal_entry_big_write));
         }
         else if (type == JE_STABLE || type == JE_ROLLBACK || type == JE_DELETE)
         {

src/disk_tool_meta.cpp

@@ -5,7 +5,7 @@
 #include "rw_blocking.h"
 #include "osd_id.h"
 
-int disk_tool_t::process_meta(std::function<void(blockstore_meta_header_v2_t *)> hdr_fn,
+int disk_tool_t::process_meta(std::function<void(blockstore_meta_header_v1_t *)> hdr_fn,
     std::function<void(uint64_t, clean_disk_entry*, uint8_t*)> record_fn)
 {
     if (dsk.meta_block_size % DIRECT_IO_ALIGNMENT)
@@ -28,38 +28,12 @@ int disk_tool_t::process_meta(std::function<void(blockstore_meta_header_v2_t *)>
     lseek64(dsk.meta_fd, dsk.meta_offset, 0);
     read_blocking(dsk.meta_fd, data, dsk.meta_block_size);
     // Check superblock
-    blockstore_meta_header_v2_t *hdr = (blockstore_meta_header_v2_t *)data;
-    if (hdr->zero == 0 && hdr->magic == BLOCKSTORE_META_MAGIC_V1)
+    blockstore_meta_header_v1_t *hdr = (blockstore_meta_header_v1_t *)data;
+    if (hdr->zero == 0 &&
+        hdr->magic == BLOCKSTORE_META_MAGIC_V1 &&
+        hdr->version == BLOCKSTORE_META_VERSION_V1)
     {
-        if (hdr->version == BLOCKSTORE_META_FORMAT_V1)
-        {
-            // Vitastor 0.6-0.8 - static array of clean_disk_entry with bitmaps
-            hdr->data_csum_type = 0;
-            hdr->csum_block_size = 0;
-            hdr->header_csum = 0;
-        }
-        else if (hdr->version == BLOCKSTORE_META_FORMAT_V2)
-        {
-            // Vitastor 0.9 - static array of clean_disk_entry with bitmaps and checksums
-            if (hdr->data_csum_type != 0 &&
-                hdr->data_csum_type != BLOCKSTORE_CSUM_CRC32C)
-            {
-                fprintf(stderr, "I don't know checksum format %u, the only supported format is crc32c = %u.\n", hdr->data_csum_type, BLOCKSTORE_CSUM_CRC32C);
-                free(data);
-                close(dsk.meta_fd);
-                dsk.meta_fd = -1;
-                return 1;
-            }
-        }
-        else
-        {
-            // Unsupported version
-            fprintf(stderr, "Metadata format is too new for me (stored version is %lu, max supported %u).\n", hdr->version, BLOCKSTORE_META_FORMAT_V2);
-            free(data);
-            close(dsk.meta_fd);
-            dsk.meta_fd = -1;
-            return 1;
-        }
+        // Vitastor 0.6-0.7 - static array of clean_disk_entry with bitmaps
         if (hdr->meta_block_size != dsk.meta_block_size)
         {
             fprintf(stderr, "Using block size of %u bytes based on information from the superblock\n", hdr->meta_block_size);
@@ -71,24 +45,14 @@ int disk_tool_t::process_meta(std::function<void(blockstore_meta_header_v2_t *)>
                 memcpy(new_data, data, dsk.meta_block_size);
                 free(data);
                 data = new_data;
-                hdr = (blockstore_meta_header_v2_t *)data;
+                hdr = (blockstore_meta_header_v1_t *)data;
             }
         }
-        dsk.meta_format = hdr->version;
-        dsk.data_block_size = hdr->data_block_size;
-        dsk.csum_block_size = hdr->csum_block_size;
-        dsk.data_csum_type = hdr->data_csum_type;
         dsk.bitmap_granularity = hdr->bitmap_granularity;
-        dsk.clean_entry_bitmap_size = (hdr->data_block_size / hdr->bitmap_granularity + 7) / 8;
-        dsk.clean_entry_size = sizeof(clean_disk_entry) + 2*dsk.clean_entry_bitmap_size
-            + (hdr->data_csum_type
-                ? ((hdr->data_block_size+hdr->csum_block_size-1)/hdr->csum_block_size
-                    *(hdr->data_csum_type & 0xff))
-                : 0)
-            + (dsk.meta_format == BLOCKSTORE_META_FORMAT_V2 ? 4 /*entry_csum*/ : 0);
+        dsk.clean_entry_bitmap_size = hdr->data_block_size / hdr->bitmap_granularity / 8;
+        dsk.clean_entry_size = sizeof(clean_disk_entry) + 2*dsk.clean_entry_bitmap_size;
         uint64_t block_num = 0;
         hdr_fn(hdr);
-        hdr = NULL;
         meta_pos = dsk.meta_block_size;
         lseek64(dsk.meta_fd, dsk.meta_offset+meta_pos, 0);
         while (meta_pos < dsk.meta_len)
@@ -103,15 +67,6 @@ int disk_tool_t::process_meta(std::function<void(blockstore_meta_header_v2_t *)>
                     clean_disk_entry *entry = (clean_disk_entry*)((uint8_t*)data + blk + ioff);
                     if (entry->oid.inode)
                     {
-                        if (dsk.data_csum_type)
-                        {
-                            uint32_t *entry_csum = (uint32_t*)((uint8_t*)entry + dsk.clean_entry_size - 4);
-                            if (*entry_csum != crc32c(0, entry, dsk.clean_entry_size - 4))
-                            {
-                                fprintf(stderr, "Metadata entry %lu is corrupt (checksum mismatch), skipping\n", block_num);
-                                continue;
-                            }
-                        }
                         record_fn(block_num, entry, entry->bitmap);
                     }
                 }
@@ -152,35 +107,21 @@ int disk_tool_t::process_meta(std::function<void(blockstore_meta_header_v2_t *)>
 int disk_tool_t::dump_meta()
 {
     int r = process_meta(
-        [this](blockstore_meta_header_v2_t *hdr) { dump_meta_header(hdr); },
+        [this](blockstore_meta_header_v1_t *hdr) { dump_meta_header(hdr); },
         [this](uint64_t block_num, clean_disk_entry *entry, uint8_t *bitmap) { dump_meta_entry(block_num, entry, bitmap); }
     );
-    if (r == 0)
-        printf("\n]}\n");
+    printf("\n]}\n");
     return r;
 }
 
-void disk_tool_t::dump_meta_header(blockstore_meta_header_v2_t *hdr)
+void disk_tool_t::dump_meta_header(blockstore_meta_header_v1_t *hdr)
 {
     if (hdr)
     {
-        if (hdr->version == BLOCKSTORE_META_FORMAT_V1)
-        {
-            printf(
-                "{\"version\":\"0.6\",\"meta_block_size\":%u,\"data_block_size\":%u,\"bitmap_granularity\":%u,"
-                "\"entries\":[\n",
-                hdr->meta_block_size, hdr->data_block_size, hdr->bitmap_granularity
-            );
-        }
-        else if (hdr->version == BLOCKSTORE_META_FORMAT_V2)
-        {
-            printf(
-                "{\"version\":\"0.9\",\"meta_block_size\":%u,\"data_block_size\":%u,\"bitmap_granularity\":%u,"
-                "\"data_csum_type\":%s,\"csum_block_size\":%u,\"entries\":[\n",
-                hdr->meta_block_size, hdr->data_block_size, hdr->bitmap_granularity,
-                csum_type_str(hdr->data_csum_type).c_str(), hdr->csum_block_size
-            );
-        }
+        printf(
+            "{\"version\":\"0.6\",\"meta_block_size\":%u,\"data_block_size\":%u,\"bitmap_granularity\":%u,\"entries\":[\n",
+            hdr->meta_block_size, hdr->data_block_size, hdr->bitmap_granularity
+        );
     }
     else
     {
@@ -210,15 +151,6 @@ void disk_tool_t::dump_meta_entry(uint64_t block_num, clean_disk_entry *entry, u
         {
             printf("%02x", bitmap[dsk.clean_entry_bitmap_size + i]);
         }
-        if (dsk.csum_block_size && dsk.data_csum_type)
-        {
-            uint8_t *csums = bitmap + dsk.clean_entry_bitmap_size*2;
-            printf("\",\"block_csums\":\"");
-            for (uint64_t i = 0; i < (dsk.data_block_size+dsk.csum_block_size-1)/dsk.csum_block_size*(dsk.data_csum_type & 0xFF); i++)
-            {
-                printf("%02x", csums[i]);
-            }
-        }
         printf("\"}");
     }
     else
@@ -232,30 +164,18 @@ int disk_tool_t::write_json_meta(json11::Json meta)
 {
     new_meta_buf = (uint8_t*)memalign_or_die(MEM_ALIGNMENT, new_meta_len);
     memset(new_meta_buf, 0, new_meta_len);
-    blockstore_meta_header_v2_t *new_hdr = (blockstore_meta_header_v2_t *)new_meta_buf;
+    blockstore_meta_header_v1_t *new_hdr = (blockstore_meta_header_v1_t *)new_meta_buf;
     new_hdr->zero = 0;
     new_hdr->magic = BLOCKSTORE_META_MAGIC_V1;
-    new_hdr->version = meta["version"].uint64_value() == BLOCKSTORE_META_FORMAT_V1
-        ? BLOCKSTORE_META_FORMAT_V1 : BLOCKSTORE_META_FORMAT_V2;
+    new_hdr->version = BLOCKSTORE_META_VERSION_V1;
     new_hdr->meta_block_size = meta["meta_block_size"].uint64_value()
         ? meta["meta_block_size"].uint64_value() : 4096;
     new_hdr->data_block_size = meta["data_block_size"].uint64_value()
         ? meta["data_block_size"].uint64_value() : 131072;
     new_hdr->bitmap_granularity = meta["bitmap_granularity"].uint64_value()
         ? meta["bitmap_granularity"].uint64_value() : 4096;
-    new_hdr->data_csum_type = meta["data_csum_type"].is_number()
-        ? meta["data_csum_type"].uint64_value()
-        : (meta["data_csum_type"].string_value() == "crc32c"
-            ? BLOCKSTORE_CSUM_CRC32C
-            : BLOCKSTORE_CSUM_NONE);
-    new_hdr->csum_block_size = meta["csum_block_size"].uint64_value();
-    uint32_t new_clean_entry_header_size = (new_hdr->version == BLOCKSTORE_META_FORMAT_V1
-        ? sizeof(clean_disk_entry) : sizeof(clean_disk_entry) + 4 /*entry_csum*/);
-    new_clean_entry_bitmap_size = (new_hdr->data_block_size / new_hdr->bitmap_granularity + 7) / 8;
-    new_data_csum_size = (new_hdr->data_csum_type
-        ? ((new_hdr->data_block_size+new_hdr->csum_block_size-1)/new_hdr->csum_block_size*(new_hdr->data_csum_type & 0xFF))
-        : 0);
-    new_clean_entry_size = new_clean_entry_header_size + 2*new_clean_entry_bitmap_size + new_data_csum_size;
+    new_clean_entry_bitmap_size = new_hdr->data_block_size / new_hdr->bitmap_granularity / 8;
+    new_clean_entry_size = sizeof(clean_disk_entry) + 2*new_clean_entry_bitmap_size;
     new_entries_per_block = new_hdr->meta_block_size / new_clean_entry_size;
     for (const auto & e: meta["entries"].array_items())
     {
@@ -274,21 +194,8 @@ int disk_tool_t::write_json_meta(json11::Json meta)
         new_entry->oid.inode = (sscanf_json(NULL, e["pool"]) << (64-POOL_ID_BITS)) | sscanf_json(NULL, e["inode"]);
         new_entry->oid.stripe = sscanf_json(NULL, e["stripe"]);
         new_entry->version = sscanf_json(NULL, e["version"]);
-        fromhexstr(e["bitmap"].string_value(), new_clean_entry_bitmap_size,
-            ((uint8_t*)new_entry) + sizeof(clean_disk_entry));
-        fromhexstr(e["ext_bitmap"].string_value(), new_clean_entry_bitmap_size,
-            ((uint8_t*)new_entry) + sizeof(clean_disk_entry) + new_clean_entry_bitmap_size);
-        if (new_hdr->version == BLOCKSTORE_META_FORMAT_V2)
-        {
-            if (new_hdr->data_csum_type != 0)
-            {
-                fromhexstr(e["data_csum"].string_value(), new_data_csum_size,
-                    ((uint8_t*)new_entry) + sizeof(clean_disk_entry) + 2*new_clean_entry_bitmap_size);
-            }
-            uint32_t *new_entry_csum = (uint32_t*)(((uint8_t*)new_entry) + sizeof(clean_disk_entry) +
-                2*new_clean_entry_bitmap_size + new_data_csum_size);
-            *new_entry_csum = crc32c(0, new_entry, new_clean_entry_size - 4);
-        }
+        fromhexstr(e["bitmap"].string_value(), new_clean_entry_bitmap_size, ((uint8_t*)new_entry) + sizeof(clean_disk_entry));
+        fromhexstr(e["ext_bitmap"].string_value(), new_clean_entry_bitmap_size, ((uint8_t*)new_entry) + sizeof(clean_disk_entry) + new_clean_entry_bitmap_size);
     }
     int r = resize_write_new_meta();
     free(new_meta_buf);

src/disk_tool_prepare.cpp

@@ -8,9 +8,6 @@
 int disk_tool_t::prepare_one(std::map<std::string, std::string> options, int is_hdd)
 {
     static const char *allow_additional_params[] = {
-        "cached_read_data",
-        "cached_read_meta",
-        "cached_read_journal",
         "max_write_iodepth",
         "max_write_iodepth",
         "min_flusher_count",
@@ -119,7 +116,6 @@ int disk_tool_t::prepare_one(std::map<std::string, std::string> options, int is_
     try
     {
         dsk.parse_config(options);
-        dsk.cached_read_data = dsk.cached_read_meta = dsk.cached_read_journal = false;
         dsk.open_data();
         dsk.open_meta();
         dsk.open_journal();
@@ -483,7 +479,6 @@ int disk_tool_t::get_meta_partition(std::vector<vitastor_dev_info_t> & ssds, std
     {
         blockstore_disk_t dsk;
         dsk.parse_config(options);
-        dsk.cached_read_data = dsk.cached_read_meta = dsk.cached_read_journal = false;
         dsk.open_data();
         dsk.open_meta();
         dsk.open_journal();

src/disk_tool_resize.cpp

@@ -29,7 +29,7 @@ int disk_tool_t::resize_data()
     fprintf(stderr, "Reading metadata\n");
     data_alloc = new allocator((new_data_len < dsk.data_len ? dsk.data_len : new_data_len) / dsk.data_block_size);
     r = process_meta(
-        [this](blockstore_meta_header_v2_t *hdr)
+        [this](blockstore_meta_header_v1_t *hdr)
         {
             resize_init(hdr);
         },
@@ -91,7 +91,6 @@ int disk_tool_t::resize_parse_params()
     try
     {
         dsk.parse_config(options);
-        dsk.cached_read_data = dsk.cached_read_meta = dsk.cached_read_journal = false;
         dsk.open_data();
         dsk.open_meta();
         dsk.open_journal();
@@ -140,7 +139,7 @@ int disk_tool_t::resize_parse_params()
     return 0;
 }
 
-void disk_tool_t::resize_init(blockstore_meta_header_v2_t *hdr)
+void disk_tool_t::resize_init(blockstore_meta_header_v1_t *hdr)
 {
     if (hdr && dsk.data_block_size != hdr->data_block_size)
     {
@@ -150,15 +149,6 @@ void disk_tool_t::resize_init(blockstore_meta_header_v2_t *hdr)
         }
         dsk.data_block_size = hdr->data_block_size;
     }
-    if (hdr && (dsk.data_csum_type != hdr->data_csum_type || dsk.csum_block_size != hdr->csum_block_size))
-    {
-        if (dsk.data_csum_type)
-        {
-            fprintf(stderr, "Using data checksum type %s from metadata superblock\n", csum_type_str(hdr->data_csum_type).c_str());
-        }
-        dsk.data_csum_type = hdr->data_csum_type;
-        dsk.csum_block_size = hdr->csum_block_size;
-    }
     if (((new_data_len-dsk.data_len) % dsk.data_block_size) ||
         ((new_data_offset-dsk.data_offset) % dsk.data_block_size))
     {
@@ -170,12 +160,8 @@ void disk_tool_t::resize_init(blockstore_meta_header_v2_t *hdr)
     free_last = (new_data_offset+new_data_len < dsk.data_offset+dsk.data_len)
         ? (dsk.data_offset+dsk.data_len-new_data_offset-new_data_len) / dsk.data_block_size
         : 0;
-    uint32_t new_clean_entry_header_size = sizeof(clean_disk_entry) + 4 /*entry_csum*/;
     new_clean_entry_bitmap_size = dsk.data_block_size / (hdr ? hdr->bitmap_granularity : 4096) / 8;
-    new_data_csum_size = (dsk.data_csum_type
-        ? ((dsk.data_block_size+dsk.csum_block_size-1)/dsk.csum_block_size*(dsk.data_csum_type & 0xFF))
-        : 0);
-    new_clean_entry_size = new_clean_entry_header_size + 2*new_clean_entry_bitmap_size + new_data_csum_size;
+    new_clean_entry_size = sizeof(clean_disk_entry) + 2 * new_clean_entry_bitmap_size;
     new_entries_per_block = dsk.meta_block_size/new_clean_entry_size;
     uint64_t new_meta_blocks = 1 + (new_data_len/dsk.data_block_size + new_entries_per_block-1) / new_entries_per_block;
     if (!new_meta_len)
@@ -363,25 +349,13 @@ int disk_tool_t::resize_rewrite_journal()
         {
             if (je->type == JE_START)
             {
-                if (je_start.data_csum_type != dsk.data_csum_type ||
-                    je_start.csum_block_size != dsk.csum_block_size)
-                {
-                    fprintf(
-                        stderr, "Error: journal header has different checksum parameters: %s/%u vs %s/%u\n",
-                        csum_type_str(je_start.data_csum_type).c_str(), je_start.csum_block_size,
-                        csum_type_str(dsk.data_csum_type).c_str(), dsk.csum_block_size
-                    );
-                    exit(1);
-                }
                 journal_entry *ne = (journal_entry*)(new_journal_ptr + new_journal_in_pos);
                 *((journal_entry_start*)ne) = (journal_entry_start){
                     .magic = JOURNAL_MAGIC,
                     .type = JE_START,
                     .size = sizeof(journal_entry_start),
                     .journal_start = dsk.journal_block_size,
-                    .version = JOURNAL_VERSION_V2,
-                    .data_csum_type = dsk.data_csum_type,
-                    .csum_block_size = dsk.csum_block_size,
+                    .version = JOURNAL_VERSION,
                 };
                 ne->crc32 = je_crc32(ne);
                 new_journal_ptr += dsk.journal_block_size;
@@ -462,17 +436,15 @@ int disk_tool_t::resize_rewrite_meta()
     new_meta_buf = (uint8_t*)memalign_or_die(MEM_ALIGNMENT, new_meta_len);
     memset(new_meta_buf, 0, new_meta_len);
     int r = process_meta(
-        [this](blockstore_meta_header_v2_t *hdr)
+        [this](blockstore_meta_header_v1_t *hdr)
         {
-            blockstore_meta_header_v2_t *new_hdr = (blockstore_meta_header_v2_t *)new_meta_buf;
+            blockstore_meta_header_v1_t *new_hdr = (blockstore_meta_header_v1_t *)new_meta_buf;
             new_hdr->zero = 0;
             new_hdr->magic = BLOCKSTORE_META_MAGIC_V1;
-            new_hdr->version = BLOCKSTORE_META_FORMAT_V1;
+            new_hdr->version = BLOCKSTORE_META_VERSION_V1;
             new_hdr->meta_block_size = dsk.meta_block_size;
             new_hdr->data_block_size = dsk.data_block_size;
             new_hdr->bitmap_granularity = dsk.bitmap_granularity ? dsk.bitmap_granularity : 4096;
-            new_hdr->data_csum_type = dsk.data_csum_type;
-            new_hdr->csum_block_size = dsk.csum_block_size;
         },
         [this](uint64_t block_num, clean_disk_entry *entry, uint8_t *bitmap)
         {
@@ -491,7 +463,7 @@ int disk_tool_t::resize_rewrite_meta()
             new_entry->oid = entry->oid;
             new_entry->version = entry->version;
             if (bitmap)
-                memcpy(new_entry->bitmap, bitmap, 2*new_clean_entry_bitmap_size + new_data_csum_size);
+                memcpy(new_entry->bitmap, bitmap, 2*new_clean_entry_bitmap_size);
             else
                 memset(new_entry->bitmap, 0xff, 2*new_clean_entry_bitmap_size);
         }

src/disk_tool_utils.cpp

@@ -373,22 +373,3 @@ int fix_partition_type(std::string dev_by_uuid)
     std::string out;
     return shell_exec({ "sfdisk", "--no-reread", "--force", "/dev/"+parent_dev }, script, &out, NULL);
 }
-
-std::string csum_type_str(uint32_t data_csum_type)
-{
-    std::string csum_type;
-    if (data_csum_type == BLOCKSTORE_CSUM_NONE)
-        csum_type = "none";
-    else if (data_csum_type == BLOCKSTORE_CSUM_CRC32C)
-        csum_type = "crc32c";
-    else
-        csum_type = std::to_string(data_csum_type);
-    return csum_type;
-}
-
-uint32_t csum_type_from_str(std::string data_csum_type)
-{
-    if (data_csum_type == "crc32c")
-        return BLOCKSTORE_CSUM_CRC32C;
-    return stoull_full(data_csum_type, 0);
-}

src/osd_primary_write.cpp

@@ -145,11 +145,6 @@ resume_3:
             // Mark object corrupted and retry
             op_data->object_state = mark_object_corrupted(pg, op_data->oid, op_data->object_state, op_data->stripes, true, false);
             op_data->prev_set = op_data->object_state ? op_data->object_state->read_target.data() : pg.cur_set.data();
-            if (cur_op->rmw_buf)
-            {
-                free(cur_op->rmw_buf);
-                cur_op->rmw_buf = NULL;
-            }
             goto retry_1;
         }
         deref_object_state(pg, &op_data->object_state, true);

src/qemu_driver.c

@@ -234,6 +234,7 @@ out:
     return;
 }
 
+#if defined VITASTOR_C_API_VERSION && VITASTOR_C_API_VERSION >= 2
 static void vitastor_uring_handler(void *opaque)
 {
     VitastorClient *client = (VitastorClient*)opaque;
@@ -266,20 +267,23 @@ static void vitastor_schedule_uring_handler(VitastorClient *client)
         replay_bh_schedule_oneshot_event(client->ctx, vitastor_uring_handler, opaque);
 #elif QEMU_VERSION_MAJOR >= 3 || QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR >= 8
         aio_bh_schedule_oneshot(client->ctx, vitastor_uring_handler, opaque);
-#elif QEMU_VERSION_MAJOR >= 2
+#else
         VitastorBH *vbh = (VitastorBH*)malloc(sizeof(VitastorBH));
         vbh->cli = client;
+#if QEMU_VERSION_MAJOR >= 2
         vbh->bh = aio_bh_new(bdrv_get_aio_context(task->bs), vitastor_bh_uring_handler, vbh);
-        qemu_bh_schedule(vbh->bh);
 #else
-        client->bh_uring_scheduled = 0;
-        do
-        {
-            vitastor_c_uring_handle_events(client->proxy);
-        } while (vitastor_c_uring_has_work(client->proxy));
+        vbh->bh = qemu_bh_new(vitastor_bh_uring_handler, vbh);
+#endif
+        qemu_bh_schedule(vbh->bh);
 #endif
     }
 }
+#else
+static void vitastor_schedule_uring_handler(VitastorClient *client)
+{
+}
+#endif
 
 static void coroutine_fn vitastor_co_get_metadata(VitastorRPC *task)
 {
@@ -406,20 +410,16 @@ static int vitastor_file_open(BlockDriverState *bs, QDict *options, int flags, E
         vitastor_aio_set_fd_handler, client, client->config_path, client->etcd_host, client->etcd_prefix,
         client->use_rdma, client->rdma_device, client->rdma_port_num, client->rdma_gid_index, client->rdma_mtu, 0
     );
-#else
-    client->proxy = vitastor_c_create_uring(
-        client->config_path, client->etcd_host, client->etcd_prefix,
-        client->use_rdma, client->rdma_device, client->rdma_port_num, client->rdma_gid_index, client->rdma_mtu, 0
-    );
-#endif
     if (!client->proxy)
     {
         fprintf(stderr, "vitastor: failed to create io_uring: %s - I/O will be slower\n", strerror(errno));
         client->uring_eventfd = -1;
+#endif
         client->proxy = vitastor_c_create_qemu(
             vitastor_aio_set_fd_handler, client, client->config_path, client->etcd_host, client->etcd_prefix,
             client->use_rdma, client->rdma_device, client->rdma_port_num, client->rdma_gid_index, client->rdma_mtu, 0
         );
+#if defined VITASTOR_C_API_VERSION && VITASTOR_C_API_VERSION >= 2
     }
     else
     {
@@ -433,6 +433,7 @@ static int vitastor_file_open(BlockDriverState *bs, QDict *options, int flags, E
         }
         universal_aio_set_fd_handler(client->ctx, client->uring_eventfd, vitastor_uring_handler, NULL, client);
     }
+#endif
     image = client->image = g_strdup(qdict_get_try_str(options, "image"));
     client->readonly = (flags & BDRV_O_RDWR) ? 1 : 0;
     // Get image metadata (size and readonly flag) or just wait until the client is ready
@@ -664,7 +665,8 @@ static void vitastor_co_generic_cb(void *opaque, long retval)
     task->bh = aio_bh_new(bdrv_get_aio_context(task->bs), vitastor_co_generic_bh_cb, opaque);
     qemu_bh_schedule(task->bh);
 #else
-    vitastor_co_generic_bh_cb(opaque);
+    task->bh = qemu_bh_new(vitastor_co_generic_bh_cb, opaque);
+    qemu_bh_schedule(task->bh);
 #endif
 }
 
@@ -741,7 +743,6 @@ static void vitastor_co_read_bitmap_cb(void *opaque, long retval, uint8_t *bitma
     VitastorRPC *task = opaque;
     VitastorClient *client = task->bs->opaque;
     task->ret = retval;
-    task->complete = 1;
     if (retval >= 0)
     {
         task->bitmap = bitmap;
@@ -753,15 +754,17 @@ static void vitastor_co_read_bitmap_cb(void *opaque, long retval, uint8_t *bitma
             client->last_bitmap = bitmap;
         }
     }
-    if (qemu_coroutine_self() != task->co)
-    {
-#if QEMU_VERSION_MAJOR >= 3 || QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR > 8
-        aio_co_wake(task->co);
+#if QEMU_VERSION_MAJOR > 4 || QEMU_VERSION_MAJOR == 4 && QEMU_VERSION_MINOR >= 2
+    replay_bh_schedule_oneshot_event(bdrv_get_aio_context(task->bs), vitastor_co_generic_bh_cb, opaque);
+#elif QEMU_VERSION_MAJOR >= 3 || QEMU_VERSION_MAJOR == 2 && QEMU_VERSION_MINOR >= 8
+    aio_bh_schedule_oneshot(bdrv_get_aio_context(task->bs), vitastor_co_generic_bh_cb, opaque);
+#elif QEMU_VERSION_MAJOR >= 2
+    task->bh = aio_bh_new(bdrv_get_aio_context(task->bs), vitastor_co_generic_bh_cb, opaque);
+    qemu_bh_schedule(task->bh);
 #else
-        qemu_coroutine_enter(task->co, NULL);
-        qemu_aio_release(task);
+    task->bh = qemu_bh_new(vitastor_co_generic_bh_cb, opaque);
+    qemu_bh_schedule(task->bh);
 #endif
-    }
 }
 
 static int coroutine_fn vitastor_co_block_status(

src/vitastor.pc.in

@@ -6,7 +6,7 @@ includedir=${prefix}/@CMAKE_INSTALL_INCLUDEDIR@
 
 Name: Vitastor
 Description: Vitastor client library
-Version: 0.9.3
+Version: 0.9.4
 Libs: -L${libdir} -lvitastor_client
 Cflags: -I${includedir}
 

src/vitastor_c.cpp

@@ -215,7 +215,7 @@ void vitastor_c_uring_wait_events(vitastor_c *client)
     client->ringloop->wait();
 }
 
-bool vitastor_c_uring_has_work(vitastor_c *client)
+int vitastor_c_uring_has_work(vitastor_c *client)
 {
     return client->ringloop->has_work();
 }

src/vitastor_c.h

@@ -46,7 +46,7 @@ int vitastor_c_uring_register_eventfd(vitastor_c *client);
 void vitastor_c_uring_wait_ready(vitastor_c *client);
 void vitastor_c_uring_handle_events(vitastor_c *client);
 void vitastor_c_uring_wait_events(vitastor_c *client);
-bool vitastor_c_uring_has_work(vitastor_c *client);
+int vitastor_c_uring_has_work(vitastor_c *client);
 void vitastor_c_read(vitastor_c *client, uint64_t inode, uint64_t offset, uint64_t len,
     struct iovec *iov, int iovcnt, VitastorReadHandler cb, void *opaque);
 void vitastor_c_write(vitastor_c *client, uint64_t inode, uint64_t offset, uint64_t len, uint64_t check_version,

tests/run_3osds.sh

@@ -27,9 +27,7 @@ fi
 start_osd()
 {
     local i=$1
-    build/src/vitastor-osd --osd_num $i --bind_address 127.0.0.1 $NO_SAME $OSD_ARGS --etcd_address $ETCD_URL \
-        $(build/src/vitastor-disk simple-offsets --format options ./testdata/test_osd$i.bin $OFFSET_ARGS 2>/dev/null) \
-        >>./testdata/osd$i.log 2>&1 &
+    build/src/vitastor-osd --osd_num $i --bind_address 127.0.0.1 $NO_SAME $OSD_ARGS --etcd_address $ETCD_URL $(build/src/vitastor-disk simple-offsets --format options ./testdata/test_osd$i.bin 2>/dev/null) >>./testdata/osd$i.log 2>&1 &
     eval OSD${i}_PID=$!
 }
 

tests/run_tests.sh

@@ -53,13 +53,6 @@ SCHEME=xor ./test_write.sh
 PG_SIZE=2 ./test_heal.sh
 SCHEME=ec ./test_heal.sh
 
-TEST_NAME=csum_32k_dmj OSD_ARGS="--data_csum_type crc32c --csum_block_size 32k --inmemory_metadata false --inmemory_journal false" OFFSET_ARGS=$OSD_ARGS ./test_heal.sh
-TEST_NAME=csum_32k_dj  OSD_ARGS="--data_csum_type crc32c --csum_block_size 32k --inmemory_journal false" OFFSET_ARGS=$OSD_ARGS ./test_heal.sh
-TEST_NAME=csum_32k     OSD_ARGS="--data_csum_type crc32c --csum_block_size 32k" OFFSET_ARGS=$OSD_ARGS ./test_heal.sh
-TEST_NAME=csum_4k_dmj  OSD_ARGS="--data_csum_type crc32c --inmemory_metadata false --inmemory_journal false" OFFSET_ARGS=$OSD_ARGS ./test_heal.sh
-TEST_NAME=csum_4k_dj   OSD_ARGS="--data_csum_type crc32c --inmemory_journal false" OFFSET_ARGS=$OSD_ARGS ./test_heal.sh
-TEST_NAME=csum_4k      OSD_ARGS="--data_csum_type crc32c" OFFSET_ARGS=$OSD_ARGS ./test_heal.sh
-
 ./test_scrub.sh
 ZERO_OSD=2 ./test_scrub.sh
 SCHEME=xor ./test_scrub.sh

tests/test_checksum.sh

@@ -1,37 +0,0 @@
-#!/bin/bash -ex
-
-OSD_ARGS="--data_csum_type crc32c --csum_block_size 32k --inmemory_journal false $OSD_ARGS"
-OFFSET_ARGS="--data_csum_type crc32c --csum_block_size 32k --inmemory_journal false $OFFSET_ARGS"
-PG_COUNT=${PG_COUNT:-64}
-. `dirname $0`/run_3osds.sh
-check_qemu
-
-IMG_SIZE=128
-
-$ETCDCTL put /vitastor/config/inode/1/1 '{"name":"testimg","size":'$((IMG_SIZE*1024*1024))'}'
-
-# Write
-LD_PRELOAD="build/src/libfio_vitastor.so" \
-    fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bs=1M -direct=1 -iodepth=4 \
-        -mirror_file=./testdata/mirror.bin -end_fsync=1 -rw=write -etcd=$ETCD_URL -image=testimg -runtime=10
-
-# Intentionally corrupt OSD data and restart it
-kill $OSD1_PID
-data_offset=$(build/src/vitastor-disk simple-offsets ./testdata/test_osd1.bin $OFFSET_ARGS | grep data_offset | awk '{print $2}')
-truncate -s $data_offset ./testdata/test_osd1.bin
-dd if=/dev/zero of=./testdata/test_osd1.bin bs=1024 count=1 seek=$((OSD_SIZE*1024-1))
-start_osd 1
-
-# FIXME: corrupt the journal WHEN OSD IS RUNNING and check reads too
-
-# Wait until start
-wait_up 10
-
-# Read everything back
-qemu-img convert -S 4096 -p \
-    -f raw "vitastor:etcd_host=127.0.0.1\:$ETCD_PORT/v3:image=testimg" \
-    -O raw ./testdata/read.bin
-
-diff ./testdata/read.bin ./testdata/mirror.bin
-
-format_green OK

tests/test_heal.sh

@@ -12,7 +12,6 @@ PG_COUNT=32
 . `dirname $0`/run_3osds.sh
 check_qemu
 
-# FIXME: Fix space rebalance priorities :)
 IMG_SIZE=960
 
 $ETCDCTL put /vitastor/config/inode/1/1 '{"name":"testimg","size":'$((IMG_SIZE*1024*1024))'}'
@@ -25,7 +24,6 @@ kill_osds()
 {
     sleep 5
 
-    echo Killing OSD 1
     kill -9 $OSD1_PID
     $ETCDCTL del /vitastor/osd/state/1
 
@@ -40,7 +38,6 @@ kill_osds()
     done
 
     sleep 5
-    echo Starting OSD 7
     start_osd 7
 
     sleep 5
@@ -49,19 +46,13 @@ kill_osds()
 kill_osds &
 
 LD_PRELOAD="build/src/libfio_vitastor.so" \
-    fio -thread -name=test -ioengine=build/src/libfio_vitastor.so -bsrange=4k-128k -blockalign=4k -direct=1 -iodepth=32 -fsync=256 -rw=randrw \
+    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" \
     -O raw ./testdata/read.bin
 
-if ! diff -q ./testdata/read.bin ./testdata/mirror.bin; then
-    format_error Data lost during self-heal
-fi
-
-if grep -qP 'Checksum mismatch|BUG' ./testdata/osd*.log; then
-    format_error Checksum mismatches or BUGs detected during test
-fi
+diff ./testdata/read.bin ./testdata/mirror.bin
 
 format_green OK

tests/test_move_reappear.sh

@@ -4,7 +4,7 @@
 
 OSD_SIZE=1024
 OSD_COUNT=5
-OSD_ARGS="$OSD_ARGS"
+OSD_ARGS=
 for i in $(seq 1 $OSD_COUNT); do
     dd if=/dev/zero of=./testdata/test_osd$i.bin bs=1024 count=1 seek=$((OSD_SIZE*1024-1))
     build/src/vitastor-osd --osd_num $i --bind_address 127.0.0.1 $OSD_ARGS --etcd_address $ETCD_URL $(build/src/vitastor-disk simple-offsets --format options ./testdata/test_osd$i.bin 2>/dev/null) >>./testdata/osd$i.log 2>&1 &

tests/test_vm_cont.sh

@@ -8,8 +8,7 @@ etcdctl --endpoints=http://127.0.0.1:12379/v3 del --prefix /vitastor/pg/state
 etcdctl --endpoints=http://127.0.0.1:12379/v3 del --prefix /vitastor/osd/state
 
 OSD_COUNT=3
-OSD_ARGS="$OSD_ARGS"
-OFFSET_ARGS="$OFFSET_ARGS"
+OSD_ARGS=
 for i in $(seq 1 $OSD_COUNT); do
     build/src/vitastor-osd --osd_num $i --bind_address 127.0.0.1 $OSD_ARGS --etcd_address $ETCD_URL $(build/src/vitastor-disk simple-offsets --format options ./testdata/test_osd$i.bin 2>/dev/null) >>./testdata/osd$i.log 2>&1 &
     eval OSD${i}_PID=$!

tests/test_write_no_same.sh

@@ -1,7 +1,7 @@
 #!/bin/bash -ex
 # Test the `no_same_sector_overwrites` mode
 
-OSD_ARGS="--journal_no_same_sector_overwrites true --journal_sector_buffer_count 1024 --disable_data_fsync 1 --immediate_commit all $OSD_ARGS"
+OSD_ARGS="--journal_no_same_sector_overwrites true --journal_sector_buffer_count 1024 --disable_data_fsync 1 --immediate_commit all"
 GLOBAL_CONF='{"immediate_commit":"all"}'
 
 . `dirname $0`/run_3osds.sh