Accept pool names and hex inode numbers in vitastor-cli rm-data

rm-data read --pool and --inode with uint64_value(), so a pool name
became 0 and the pool was silently taken from the inode's pool bits,
i.e. "--pool <other pool> --inode <full inode number>" removed data in
a different pool than requested. A hex --inode became 0 and rm-data
"removed" inode 0, reporting success.

Resolve pool names like ls does (ENOENT for an unknown pool), parse
--inode as decimal or 0x hex, and fail with EINVAL on anything else
before removing data.

.gitea/workflows/test.yml

@@ -221,24 +221,6 @@ jobs:
           echo ""
         done
 
-  test_modify_pool:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: /root/vitastor/tests/test_modify_pool.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_etcd_fail:
     runs-on: ubuntu-latest
     needs: build
@@ -797,24 +779,6 @@ jobs:
           echo ""
         done
 
-  test_modify_image_resize:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: /root/vitastor/tests/test_modify_image_resize.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_rm_degraded:
     runs-on: ubuntu-latest
     needs: build
@@ -833,24 +797,6 @@ jobs:
           echo ""
         done
 
-  test_describe:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: /root/vitastor/tests/test_describe.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_snapshot_chain:
     runs-on: ubuntu-latest
     needs: build
@@ -1067,24 +1013,6 @@ jobs:
           echo ""
         done
 
-  test_kv_list_bounds:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: /root/vitastor/tests/test_kv_list_bounds.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_splitbrain:
     runs-on: ubuntu-latest
     needs: build
@@ -1265,24 +1193,6 @@ jobs:
           echo ""
         done
 
-  test_cli_help:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: /root/vitastor/tests/test_cli_help.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_root_node:
     runs-on: ubuntu-latest
     needs: build
@@ -1661,24 +1571,6 @@ jobs:
           echo ""
         done
 
-  test_ls_tree:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: /root/vitastor/tests/test_ls_tree.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_snapshot_read_bitmap:
     runs-on: ubuntu-latest
     needs: build
@@ -2471,24 +2363,6 @@ jobs:
           echo ""
         done
 
-  test_nfs_list_bounds:
-    runs-on: ubuntu-latest
-    needs: build
-    container: ${{env.TEST_IMAGE}}:${{github.sha}}
-    steps:
-    - name: Run test
-      id: test
-      timeout-minutes: 3
-      run: /root/vitastor/tests/test_nfs_list_bounds.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_write_encrypted:
     runs-on: ubuntu-latest
     needs: build

docs/usage/cli.en.md

@@ -231,8 +231,8 @@ Options:
 * `--writers-stopped` allows optimised removal in case of a single 'slim' read-write
   child and 'fat' removed parent: the child is merged into parent and parent is renamed
   to child in that case. In other cases parent layers are always merged into children.
-* `--exact` - remove multiple images with given names.
-* `--matching` - remove multiple images with names matching given glob patterns.
+* `--exact` - remove multiple images with names matching given glob patterns.
+* `--matching` - remove multiple images with given names
 * `--down-ok` - continue deletion/merging even if some data will be left on unavailable OSDs.
 
 ## flatten
@@ -243,15 +243,16 @@ Flatten a layer, i.e. merge data and detach it from parents.
 
 ## rm-data
 
-`vitastor-cli rm-data --pool <pool> --inode <inode> [--wait-list] [--min-offset <offset>]`
+`vitastor-cli rm-data --pool <id|name> --inode <inode> [--wait-list] [--min-offset <offset>]`
 
-Remove inode data without changing metadata.
+Remove inode data without changing metadata. `<inode>` may be decimal or 0x hex.
 
 ```
 --wait-list   Retrieve full objects listings before starting to remove objects.
               Requires more memory, but allows to show correct removal progress.
 --min-offset  Purge only data starting with specified offset.
 --max-offset  Purge only data before specified offset.
+              Offsets are in bytes or with a K/M/G/T unit suffix, decimal or 0x hex.
 --client_wait_up_timeout 16  Timeout for waiting until PGs are up in seconds.
 ```
 
@@ -287,7 +288,7 @@ Describe unclean object locations in the cluster. Options:
 
 ## fix
 
-`vitastor-cli fix [--objects <objects>] --bad-osds <osds> [--part <part>] [--check no]`
+`vitastor-cli fix [--objects <objects>] [--bad-osds <osds>] [--part <part>] [--check no]`
 
 Fix inconsistent objects in the cluster by deleting some copies.
 
@@ -298,7 +299,7 @@ Fix inconsistent objects in the cluster by deleting some copies.
     Plain text format: 0x<inode>:0x<stripe> <any delimiter> 0x<inode>:0x<stripe> ...
     JSON format: [{"inode":"0x...","stripe":"0x..."},...]
 --bad-osds <osds>
-    Required. Remove inconsistent copies/parts of objects from these OSDs, effectively
+    Remove inconsistent copies/parts of objects from these OSDs, effectively
     marking them bad and allowing Vitastor to recover objects from other copies.
 --part <number>
     Only remove EC part <number> (from 0 to pg_size-1), required for extreme
@@ -316,17 +317,14 @@ Allocate a new OSD number and reserve it by creating empty `/osd/stats/<n>` key.
 
 ## rm-osd
 
-`vitastor-cli rm-osd [-f|--force] [--allow-data-loss] [--allow-up] [--dry-run] <osd_id> [osd_id...]`
+`vitastor-cli rm-osd [--force] [--allow-data-loss] [--dry-run] <osd_id> [osd_id...]`
 
 Remove metadata and configuration for specified OSD(s) from etcd.
 
-Refuses to remove OSDs that are up or whose removal makes PGs degraded, offline or incomplete.
+Refuses to remove OSDs with data without `--force` and `--allow-data-loss`.
 
-* `-f|--force` - remove OSDs even if they are up or PGs become degraded or offline.
-* `--allow-data-loss` - remove OSDs even if PGs or objects become incomplete (DATA LOSS). Implies `--force`.
-* `--allow-up` - remove OSDs even if they are up.
-* `--dry-run` - only check if deletion is possible without data loss and
-  redundancy degradation.
+With `--dry-run` only checks if deletion is possible without data loss and
+redundancy degradation.
 
 ## osd-tree
 
@@ -358,7 +356,7 @@ host     stump
 
 ## ls-osd
 
-`vitastor-cli osds|ls-osds|ls-osd|osd-ls [-l|--long]`
+`vitastor-cli osds|ls-osd|osd-ls [-l|--long]`
 
 Show current OSDs as list, optionally with I/O statistics if -l is specified.
 
@@ -413,8 +411,8 @@ Create a pool. Required parameters:
 
 | <!-- -->                 | <!-- -->                                                                                |
 |--------------------------|-----------------------------------------------------------------------------------------|
-| `-s R` or `--pg_size R`  | Number of replicas for replicated pools, from 1 to 64                                   |
-| `--ec N+K`               | Number of data (N) and parity (K) chunks for erasure-coded pools, N+K from 3 to 64      |
+| `-s R` or `--pg_size R`  | Number of replicas for replicated pools                                                 |
+| `--ec N+K`               | Number of data (N) and parity (K) chunks for erasure-coded pools                        |
 | `-n N` or `--pg_count N` | PG count for the new pool (start with 10*\<OSD count\>/pg_size rounded to a power of 2) |
 
 Optional parameters:
@@ -428,7 +426,7 @@ Optional parameters:
 | `--block_size 128k`            | Put pool only on OSDs with this data block size                            |
 | `--bitmap_granularity 4k`      | Put pool only on OSDs with this logical sector size                        |
 | `--immediate_commit none`      | Put pool only on OSDs with this or larger immediate_commit (none < small < all) |
-| `--level_placement <rules>`    | Use additional failure domain rules (example: "dc=112233", "" to remove)   |
+| `--level_placement <rules>`    | Use additional failure domain rules (example: "dc=112233")                 |
 | `--raw_placement <rules>`      | Specify raw PG generation rules ([details](../config/pool.en.md#raw_placement)) |
 | `--local_reads primary`        | Local read policy for replicated pools: primary, nearest or random         |
 | `--primary_affinity_tags tags` | Prefer to put primary copies on OSDs with all specified tags               |
@@ -473,8 +471,6 @@ These, however, can still be modified with -f|--force.
 
 See [create-pool](#create-pool) for parameter descriptions.
 
-Renaming with --name fails if the new name is already taken by a different pool.
-
 Examples:
 
 `vitastor-cli modify-pool pool_A --name pool_B`
@@ -513,7 +509,7 @@ the Vitastor authorization model.
 
 ## modify-user
 
-`vitastor-cli modify-user|user-modify --groups <group1,group2,...> <username>`
+`vitastor-cli modify-user --groups <group1,group2,...> <username>`
 
 Create or update a user with the given name (matching TLS certificate CN).
 

docs/usage/cli.ru.md

@@ -239,8 +239,8 @@ vitastor-cli dd [iimg=<image> | if=<file>] [oimg=<image> | of=<file>] [bs=1M] \
   у удаляемой цепочки есть только один дочерний образ, содержащий небольшой объём данных.
   В этом случае дочерний образ вливается в родительский и удаляется, а родительский
   переименовывается в дочерний.
-* `--exact` - удалить все образы с точно заданными именами.
-* `--matching` - удалить все образы с именами, подходящими под переданные glob-шаблоны.
+* `--exact` - удалить все образы с именами, подходящими под переданные glob-шаблоны.
+* `--matching` - удалить все образы с точно заданными именами.
 * `--down-ok` - продолжать удаление/слияние, даже если часть данных останется неудалённой на недоступных OSD.
 
 ## flatten
@@ -252,15 +252,16 @@ vitastor-cli dd [iimg=<image> | if=<file>] [oimg=<image> | of=<file>] [bs=1M] \
 
 ## rm-data
 
-`vitastor-cli rm-data --pool <pool> --inode <inode> [--wait-list] [--min-offset <offset>]`
+`vitastor-cli rm-data --pool <id|name> --inode <inode> [--wait-list] [--min-offset <offset>]`
 
-Удалить данные инода, не меняя метаданные образов.
+Удалить данные инода, не меняя метаданные образов. `<inode>` можно задать в десятичном виде или в hex с 0x.
 
 ```
 --wait-list   Сначала запросить полный листинг объектов, а потом начать удалять.
               Требует больше памяти, но позволяет правильно печатать прогресс удаления.
 --min-offset  Удалять только данные, начиная с заданного смещения.
 --max-offset  Удалять только данные до (исключительно) заданного смещения.
+              Смещения задаются в байтах или с суффиксом K/M/G/T, в десятичном виде или в hex с 0x.
 --client_wait_up_timeout 16  Время ожидания поднятия PG в секундах.
 ```
 
@@ -302,7 +303,7 @@ vitastor-cli dd [iimg=<image> | if=<file>] [oimg=<image> | of=<file>] [bs=1M] \
 
 ## fix
 
-`vitastor-cli fix [--objects <объекты>] --bad-osds <osds> [--part <номер>] [--check no]`
+`vitastor-cli fix [--objects <объекты>] [--bad-osds <osds>] [--part <номер>] [--check no]`
 
 Исправить неконсистентные (неоднозначные) объекты путём удаления части копий.
 
@@ -313,9 +314,9 @@ vitastor-cli dd [iimg=<image> | if=<file>] [oimg=<image> | of=<file>] [bs=1M] \
     Простой формат: 0x<инод>:0x<смещение> <любой разделитель> 0x<инод>:0x<смещение> ...
     Формат JSON: [{"inode":"0x<инод>","stripe":"0x<смещение>"},...]
 --bad-osds <osds>
-    Обязательная опция. Удалить неконсистентные копии/части объектов с данных
-    OSD, таким образом признавая потерю этих копий и позволяя Vitastor-у
-    восстановить объекты из других копий.
+    Удалить неконсистентные копии/части объектов с данных OSD, таким образом
+    признавая потерю этих копий и позволяя Vitastor-у восстановить объекты из
+    других копий.
 --part <номер>
     Удалить только части EC с заданным номером (от 0 до pg_size-1). Нужно только
     в редких граничных случаях, когда один и тот же OSD содержит несколько частей
@@ -334,19 +335,14 @@ vitastor-cli dd [iimg=<image> | if=<file>] [oimg=<image> | of=<file>] [bs=1M] \
 
 ## rm-osd
 
-`vitastor-cli rm-osd [-f|--force] [--allow-data-loss] [--allow-up] [--dry-run] <osd_id> [osd_id...]`
+`vitastor-cli rm-osd [--force] [--allow-data-loss] [--dry-run] <osd_id> [osd_id...]`
 
 Удалить метаданные и конфигурацию для заданных OSD из etcd.
 
-Отказывается удалять работающие OSD, а также OSD, после удаления которых PG станут
-деградированными, недоступными (offline) или неполными (incomplete).
+Отказывается удалять OSD с данными без опций `--force` и `--allow-data-loss`.
 
-* `-f|--force` - удалить OSD, даже если они работают или PG станут деградированными или недоступными.
-* `--allow-data-loss` - удалить OSD, даже если PG или объекты станут неполными (ПОТЕРЯ ДАННЫХ).
-  Включает действие `--force`.
-* `--allow-up` - удалить OSD, даже если они работают.
-* `--dry-run` - только проверить, возможно ли удаление без потери данных и деградации
-  избыточности.
+С опцией `--dry-run` только проверяет, возможно ли удаление без потери данных и деградации
+избыточности.
 
 ## osd-tree
 
@@ -378,7 +374,7 @@ host     stump
 
 ## ls-osd
 
-`vitastor-cli osds|ls-osds|ls-osd|osd-ls [-l|--long]`
+`vitastor-cli osds|ls-osd|osd-ls [-l|--long]`
 
 Показать список OSD, со статистикой ввода-вывода, если установлено -l.
 
@@ -408,7 +404,7 @@ OSD  PARENT            UP    SIZE  USED%    TAGS          WEIGHT  BLOCK  BITMAP
 
 ## pg-list
 
-`vitastor-cli pg-list|pg-ls|list-pg|ls-pg|ls-pgs|pgs [OPTIONS] [state1+state2] [^state3] [...]`
+`vitastor-cli pg-list|pg-ls|list-pg|ls-pg|ls-pgs [OPTIONS] [state1+state2] [^state3] [...]`
 
 Вывести список PG с состояними, удовлетворяющими любому из переданных фильтров (^ или !
 в начале фильтра означает отрицание). Опции:
@@ -434,8 +430,8 @@ OSD  PARENT            UP    SIZE  USED%    TAGS          WEIGHT  BLOCK  BITMAP
 
 | <!-- -->                  | <!-- -->                                                                                      |
 |---------------------------|-----------------------------------------------------------------------------------------------|
-| `-s R` или `--pg_size R`  | Число копий данных для реплицированных пулов, от 1 до 64                                      |
-| `--ec N+K`                | Число частей данных (N) и чётности (K) для пулов с кодами коррекции ошибок, N+K от 3 до 64    |
+| `-s R` или `--pg_size R`  | Число копий данных для реплицированных пулов                                                  |
+| `--ec N+K`                | Число частей данных (N) и чётности (K) для пулов с кодами коррекции ошибок                    |
 | `-n N` или `--pg_count N` | Число PG для нового пула (начните с 10*\<число OSD\>/pg_size, округлённого до степени двойки) |
 
 Необязательные параметры:
@@ -449,7 +445,7 @@ OSD  PARENT            UP    SIZE  USED%    TAGS          WEIGHT  BLOCK  BITMAP
 | `--block_size 128k`            | ...только OSD с данным размером блока                                      |
 | `--bitmap_granularity 4k`      | ...только OSD с данным размером логического сектора                        |
 | `--immediate_commit none`      | ...только OSD с этим или большим immediate_commit (none < small < all)     |
-| `--level_placement <rules>`    | Задать правила дополнительных доменов отказа (пример: "dc=112233", "" — удалить) |
+| `--level_placement <rules>`    | Задать правила дополнительных доменов отказа (пример: "dc=112233")         |
 | `--raw_placement <rules>`      | Задать низкоуровневые правила генерации PG ([детали](../config/pool.ru.md#raw_placement)) |
 | `--local_reads primary`        | Политика локальных чтений для реплик: primary, nearest или random          |
 | `--primary_affinity_tags tags` | Предпочитать OSD со всеми данными тегами для роли первичных                |
@@ -492,8 +488,6 @@ OSD  PARENT            UP    SIZE  USED%    TAGS          WEIGHT  BLOCK  BITMAP
 
 Описания параметров смотрите в [create-pool](#create-pool).
 
-Переименование с --name запрещается, если новое название уже занято другим пулом.
-
 Примеры:
 
 `vitastor-cli modify-pool pool_A --name pool_B`
@@ -534,7 +528,7 @@ OSD  PARENT            UP    SIZE  USED%    TAGS          WEIGHT  BLOCK  BITMAP
 
 ## modify-user
 
-`vitastor-cli modify-user|user-modify --groups <group1,group2,...> <username>`
+`vitastor-cli modify-user --groups <group1,group2,...> <username>`
 
 Создать или изменить пользователя с указанным именем (совпадающим с CN TLS-сертификата).
 

src/CMakeLists.txt

@@ -21,11 +21,8 @@ if("${CMAKE_INSTALL_PREFIX}" MATCHES "^/usr/local/?$")
 endif()
 set(ENABLE_COVERAGE false CACHE BOOL "Enable code coverage")
 
-set(CMAKE_CXX_STANDARD 17)
-set(CMAKE_CXX_STANDARD_REQUIRED ON)
-
 add_definitions(-DVITASTOR_VERSION="3.2.2")
-add_definitions(-D_GNU_SOURCE -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -Wall -Wno-c99-designator -Wno-vla-cxx-extension -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -fno-omit-frame-pointer -fvisibility=hidden -I ${CMAKE_SOURCE_DIR}/src)
+add_definitions(-D_GNU_SOURCE -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 -Wall -Wno-sign-compare -Wno-comment -Wno-parentheses -Wno-pointer-arith -fdiagnostics-color=always -fno-omit-frame-pointer -fvisibility=hidden -I ${CMAKE_SOURCE_DIR}/src)
 add_link_options(-fno-omit-frame-pointer)
 if (${WITH_ASAN})
 	add_definitions(-fsanitize=address)

src/blockstore/blockstore_heap.cpp

@@ -572,7 +572,7 @@ void blockstore_heap_t::finish_load()
     if (postponed_items.size())
     {
         // Sort "postponed" items and load in batches
-        std::sort(postponed_items.begin(), postponed_items.end(), [](const heap_list_item_t* a, const heap_list_item_t* b)
+        std::sort(postponed_items.begin(), postponed_items.end(), [this](const heap_list_item_t* a, const heap_list_item_t* b)
         {
             return a->entry.inode < b->entry.inode || a->entry.inode == b->entry.inode &&
                 (a->entry.stripe < b->entry.stripe || a->entry.stripe == b->entry.stripe &&

src/blockstore/blockstore_init.cpp

@@ -273,7 +273,7 @@ resume_6:
             rc->buf = (uint8_t*)memalign_or_die(MEM_ALIGNMENT, rc->len);
         data = ((ring_data_t*)sqe->user_data);
         data->iov = (iovec){ rc->buf, rc->len };
-        data->callback = [rc](ring_data_t *data)
+        data->callback = [this, rc](ring_data_t *data)
         {
             if (data->res < 0)
             {

src/blockstore/blockstore_write.cpp

@@ -355,7 +355,7 @@ resume_11:
             BS_SUBMIT_GET_SQE(sqe, data);
             io_uring_prep_fsync(sqe, dsk.data_fd, IORING_FSYNC_DATASYNC);
             data->iov = { 0 };
-            data->callback = [this, fs = data_fsync_cur](ring_data_t *data)
+            data->callback = [this, op, fs = data_fsync_cur](ring_data_t *data)
             {
                 live = true;
                 if (data->res != 0)

src/blockstore/v1/sync.cpp

@@ -83,8 +83,10 @@ int blockstore_impl_t::continue_sync(blockstore_op_t *op)
         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, 0))

src/client/cluster_client.cpp

@@ -245,7 +245,7 @@ void cluster_client_t::inc_wait(uint64_t opcode, uint64_t flags, cluster_op_t *n
         {
             next->prev_wait += inc;
             assert(next->prev_wait >= 0);
-            if (!next->prev_wait && !continuing_ops)
+            if (!next->prev_wait)
             {
                 // Kind of std::vector with local "small vector optimisation"
                 if (bh_op_count >= bh_op_max)

src/client/messenger.h

@@ -71,8 +71,8 @@ struct msgr_rdma_connection_t;
 struct msgr_rdma_context_t;
 #endif
 
-class op_aes_xts_encrypt_t;
-class op_aes_xts_decrypt_t;
+struct op_aes_xts_encrypt_t;
+struct op_aes_xts_decrypt_t;
 void destroy_aes_xts_encrypt(op_aes_xts_encrypt_t *encrypt_ctx);
 void destroy_aes_xts_decrypt(op_aes_xts_decrypt_t *decrypt_ctx);
 
@@ -216,7 +216,7 @@ protected:
     friend class copy_op_writer_t;
     friend class gcm_op_writer_t;
     friend class get_op_writer_t;
-    friend struct osd_client_t;
+    friend class osd_client_t;
 
     int keepalive_timer_id = -1;
 

src/client/msgr_handshake.cpp

@@ -284,6 +284,7 @@ bool msgr_handshake_t::on_error(const std::string & prefix)
 
 bool msgr_handshake_t::init(bool server_mode)
 {
+    this->ctx = ctx;
     std::unique_ptr<EVP_PKEY_CTX, decltype(&EVP_PKEY_CTX_free)> kctx(EVP_PKEY_CTX_new(ctx->params, NULL), EVP_PKEY_CTX_free);
     if (!kctx)
         return on_error("EVP_PKEY_CTX_new with EC params: ");

src/cmd/cli.cpp

@@ -108,20 +108,21 @@ static const char* help_text =
     "  --writers-stopped allows optimised removal in case of a single 'slim' read-write\n"
     "  child and 'fat' removed parent: the child is merged into parent and parent is renamed\n"
     "  to child in that case. In other cases parent layers are always merged into children.\n"
-    "  --exact            Remove multiple images with given names.\n"
-    "  --matching         Remove multiple images with names matching given glob patterns.\n"
+    "  --exact            Remove multiple images with names matching given glob patterns.\n"
+    "  --matching         Remove multiple images with given names\n"
     "  --writers-stopped  Allow renaming inodes over their read/write children.\n"
     "  --down-ok          Continue deletion/merging even if some data will be left on unavailable OSDs.\n"
     "\n"
     "vitastor-cli flatten <layer>\n"
     "  Flatten a layer, i.e. merge data and detach it from parents.\n"
     "\n"
-    "vitastor-cli rm-data --pool <pool> --inode <inode> [--wait-list] [--min-offset <offset>]\n"
-    "  Remove inode data without changing metadata.\n"
+    "vitastor-cli rm-data --pool <id|name> --inode <inode> [--wait-list] [--min-offset <offset>]\n"
+    "  Remove inode data without changing metadata. <inode> may be decimal or 0x hex.\n"
     "  --wait-list   Retrieve full objects listings before starting to remove objects.\n"
     "                Requires more memory, but allows to show correct removal progress.\n"
     "  --min-offset  Purge only data starting with specified offset.\n"
     "  --max-offset  Purge only data before specified offset.\n"
+    "                Offsets are in bytes or with a K/M/G/T unit suffix, decimal or 0x hex.\n"
     "  --client_wait_up_timeout 16  Timeout for waiting until PGs are up in seconds.\n"
     "\n"
     "vitastor-cli merge-data <from> <to> [--target <target>]\n"
@@ -145,15 +146,12 @@ static const char* help_text =
     "  --min-offset, --max-offset\n"
     "      Restrict listing to specific offsets inside inodes.\n"
     "\n"
-    "vitastor-cli raw-ls --pool_id ID (--pg_num NUM|--offset NUM) [OPTIONS]\n"
+    "vitastor-cli raw-ls [OPTIONS]\n"
     "  Find object(s) in the cluster using raw secondary listing operations. Options:\n"
     "  [--min_inode NUM] [--max_inode NUM] [--offset NUM] [--pg_num NUM] [--pg_count COUNT]\n"
     "  [--pg_stripe_size NUM] [--osds 1,2,3,...]\n"
-    "  --pool_id (numeric pool ID) is required. --pg_num is required unless --offset is given,\n"
-    "  in which case the PG is calculated from the offset. --pg_count, --pg_stripe_size and\n"
-    "  --osds default to the pool configuration and are required if the pool does not exist.\n"
     "\n"
-    "vitastor-cli fix [--objects <objects>] --bad-osds <osds> [--part <part>] [--check no]\n"
+    "vitastor-cli fix [--objects <objects>] [--bad-osds <osds>] [--part <part>] [--check no]\n"
     "  Fix inconsistent objects in the cluster by deleting some copies.\n"
     "  --objects <objects>\n"
     "      Objects to fix, either in plain text or JSON format. If not specified,\n"
@@ -161,7 +159,7 @@ static const char* help_text =
     "      Plain text format: 0x<inode>:0x<stripe> <any delimiter> 0x<inode>:0x<stripe> ...\n"
     "      JSON format: [{\"inode\":\"0x...\",\"stripe\":\"0x...\"},...]\n"
     "  --bad-osds <osds>\n"
-    "      Required. Remove inconsistent copies/parts of objects from these OSDs, effectively\n"
+    "      Remove inconsistent copies/parts of objects from these OSDs, effectively\n"
     "      marking them bad and allowing Vitastor to recover objects from other copies.\n"
     "  --part <number>\n"
     "      Only remove EC part <number> (from 0 to pg_size-1), required for extreme\n"
@@ -173,19 +171,16 @@ static const char* help_text =
     "vitastor-cli alloc-osd\n"
     "  Allocate a new OSD number and reserve it by creating empty /osd/stats/<n> key.\n"
     "\n"
-    "vitastor-cli rm-osd [-f|--force] [--allow-data-loss] [--allow-up] [--dry-run] <osd_id> [osd_id...]\n"
+    "vitastor-cli rm-osd [--force] [--allow-data-loss] [--dry-run] <osd_id> [osd_id...]\n"
     "  Remove metadata and configuration for specified OSD(s) from etcd.\n"
-    "  Refuses to remove OSDs that are up or whose removal makes PGs degraded, offline or incomplete.\n"
-    "  -f|--force         Remove OSDs even if they are up or PGs become degraded or offline.\n"
-    "  --allow-data-loss  Remove OSDs even if PGs or objects become incomplete (DATA LOSS). Implies --force.\n"
-    "  --allow-up         Remove OSDs even if they are up.\n"
-    "  --dry-run          Only check if deletion is possible without data loss and\n"
-    "                     redundancy degradation.\n"
+    "  Refuses to remove OSDs with data without --force and --allow-data-loss.\n"
+    "  With --dry-run only checks if deletion is possible without data loss and\n"
+    "  redundancy degradation.\n"
     "\n"
     "vitastor-cli osd-tree [-l|--long]\n"
     "  Show current OSD tree, optionally with I/O statistics if -l is specified.\n"
     "\n"
-    "vitastor-cli osds|ls-osds|ls-osd|osd-ls [-l|--long]\n"
+    "vitastor-cli osds|ls-osd|osd-ls [-l|--long]\n"
     "  Show current OSDs as list, optionally with I/O statistics if -l is specified.\n"
     "\n"
     "vitastor-cli modify-osd [--tags tag1,tag2,...] [--reweight <number>] [--noout true/false] <osd_number>\n"
@@ -203,8 +198,8 @@ static const char* help_text =
     "\n"
     "vitastor-cli create-pool|pool-create <name> (-s <pg_size>|--ec <N>+<K>) -n <pg_count> [OPTIONS]\n"
     "  Create a pool. Required parameters:\n"
-    "    -s|--pg_size R   Number of replicas for replicated pools, from 1 to 64\n"
-    "    --ec N+K         Number of data (N) and parity (K) chunks for erasure-coded pools, N+K from 3 to 64\n"
+    "    -s|--pg_size R   Number of replicas for replicated pools\n"
+    "    --ec N+K         Number of data (N) and parity (K) chunks for erasure-coded pools\n"
     "    -n|--pg_count N  PG count for the new pool (start with 10*<OSD count>/pg_size rounded to a power of 2)\n"
     "  Optional parameters:\n"
     "    --pg_minsize <number>         R or N+K minus number of failures to tolerate without downtime\n"
@@ -214,7 +209,7 @@ static const char* help_text =
     "    --block_size 128k             Put pool only on OSDs with this data block size\n"
     "    --bitmap_granularity 4k       Put pool only on OSDs with this logical sector size\n"
     "    --immediate_commit all        Put pool only on OSDs with this or larger immediate_commit (none < small < all)\n"
-    "    --level_placement <rules>     Use additional failure domain rules (example: \"dc=112233\", \"\" to remove)\n"
+    "    --level_placement <rules>     Use additional failure domain rules (example: \"dc=112233\")\n"
     "    --raw_placement <rules>       Specify raw PG generation rules (see documentation for details)\n"
     "    --local_reads primary         Local read policy for replicated pools: primary, nearest or random\n"
     "    --primary_affinity_tags tags  Prefer to put primary copies on OSDs with all specified tags\n"
@@ -241,7 +236,6 @@ static const char* help_text =
     "    [--immediate_commit <all|small|none>] [--pg_stripe_size <size>]\n"
     "  These, however, can still be modified with -f|--force.\n"
     "  See create-pool for parameter descriptions.\n"
-    "  Renaming with --name fails if another pool already has the new name.\n"
     "  Examples:\n"
     "    vitastor-cli modify-pool pool_A --name pool_B\n"
     "    vitastor-cli modify-pool 2 --pg_size 4 -n 128\n"
@@ -260,7 +254,7 @@ static const char* help_text =
     "vitastor-cli ls-users|user-ls|ls-user|list-users [<name> ...]\n"
     "  List users (only with specified names if passed).\n"
     "\n"
-    "vitastor-cli modify-user|user-modify --type <type> --groups group1,group2,... <username>\n"
+    "vitastor-cli modify-user --type <type> --groups group1,group2,... <username>\n"
     "  Create or update user permissions. User names match CN of their certificates.\n"
     "  --type TYPE      Set user type: client or admin. Default is client.\n"
     "  --groups GROUPS  Set user's groups.\n"

src/cmd/cli_dd.cpp

@@ -37,6 +37,7 @@ struct dd_in_info_t
     // in
     std::string iimg, ifile;
     bool in_direct = false;
+    bool detect_size = true;
 
     // out
     cli_result_t result;
@@ -67,7 +68,10 @@ struct dd_in_info_t
                 return;
             }
             in_granularity = pool_it->second.bitmap_granularity;
-            in_size = iwatch->cfg.size;
+            if (detect_size)
+            {
+                in_size = iwatch->cfg.size;
+            }
             in_seekable = true;
             return;
         }
@@ -88,31 +92,33 @@ struct dd_in_info_t
         {
             ifd = 0;
         }
-        struct stat st;
-        if (fstat(ifd, &st) < 0)
+        if (detect_size)
         {
-            result = (cli_result_t){ .err = errno, .text = "Failed to stat "+ifile+": "+std::string(strerror(errno)) };
-            close(ifd);
-            ifd = -1;
-            return;
-        }
-        if (S_ISREG(st.st_mode))
-        {
-            in_size = st.st_size;
-        }
-        else if (S_ISBLK(st.st_mode))
-        {
-            if (ioctl(ifd, BLKGETSIZE64, &in_size) < 0)
+            struct stat st;
+            if (fstat(ifd, &st) < 0)
             {
-                result = (cli_result_t){ .err = errno, .text = "Failed to get "+ifile+" size: "+std::string(strerror(errno)) };
+                result = (cli_result_t){ .err = errno, .text = "Failed to stat "+ifile+": "+std::string(strerror(errno)) };
                 close(ifd);
                 ifd = -1;
                 return;
             }
+            if (S_ISREG(st.st_mode))
+            {
+                in_size = st.st_size;
+            }
+            else if (S_ISBLK(st.st_mode))
+            {
+                if (ioctl(ifd, BLKGETSIZE64, &in_size) < 0)
+                {
+                    result = (cli_result_t){ .err = errno, .text = "Failed to get "+ifile+" size: "+std::string(strerror(errno)) };
+                    close(ifd);
+                    ifd = -1;
+                    return;
+                }
+            }
         }
         in_seekable = false;
-        // a seekable character device has no size (st_size 0), read it like a pipe
-        if (!S_ISCHR(st.st_mode) && lseek(ifd, 1, SEEK_SET) == (off_t)1)
+        if (lseek(ifd, 1, SEEK_SET) == (off_t)1)
         {
             in_seekable = true;
             lseek(ifd, 0, SEEK_SET);
@@ -169,7 +175,7 @@ struct dd_out_info_t
         return NULL;
     }
 
-    bool open_output(cli_tool_t *parent, int & state, int base_state, uint64_t oseek, uint64_t blocksize)
+    bool open_output(cli_tool_t *parent, int & state, int base_state)
     {
         if (state == base_state)
             goto resume_1;
@@ -206,13 +212,6 @@ struct dd_out_info_t
                     return true;
                 }
             }
-            if ((oseek % out_granularity) || (blocksize % out_granularity))
-            {
-                result = (cli_result_t){ .err = EINVAL, .text = "Unaligned write to Vitastor is not supported" };
-                parent->cli->st_cli->close_watch(owatch);
-                owatch = NULL;
-                return true;
-            }
             if (out_size % 4096)
             {
                 out_size += (4096 - (out_size % 4096));
@@ -289,13 +288,13 @@ resume_2:
         }
         if (ofile != "")
         {
-            ofd = open(ofile.c_str(), (out_direct ? O_DIRECT : 0) | (out_append ? O_WRONLY|O_APPEND : O_RDWR) | (out_create ? O_CREAT : 0), 0666);
+            ofd = open(ofile.c_str(), (out_direct ? O_DIRECT : 0) | (out_append ? O_APPEND : O_RDWR) | (out_create ? O_CREAT : 0), 0666);
             if (ofd < 0)
             {
                 result = (cli_result_t){ .err = errno, .text = "Failed to open "+ofile+": "+std::string(strerror(errno)) };
                 return true;
             }
-            if (out_trunc && ftruncate(ofd, out_size ? out_size : oseek) < 0)
+            if (out_trunc && ftruncate(ofd, out_size) < 0)
             {
                 result = (cli_result_t){ .err = errno, .text = "Failed to truncate "+ofile+": "+std::string(strerror(errno)) };
                 return true;
@@ -315,16 +314,6 @@ resume_2:
             out_seekable = true;
             lseek(ofd, 0, SEEK_SET);
         }
-        struct stat st;
-        if (fstat(ofd, &st) < 0)
-        {
-            result = (cli_result_t){ .err = errno, .text = "Failed to stat "+(ofile != "" ? ofile : "stdout")+": "+std::string(strerror(errno)) };
-            return true;
-        }
-        if (!S_ISREG(st.st_mode) && !S_ISBLK(st.st_mode))
-        {
-            end_fsync = false;
-        }
         return true;
     }
 
@@ -406,7 +395,6 @@ struct cli_dd_t
     uint64_t written_size = 0;
     uint64_t written_progress = 0;
     timespec tv_begin = {}, tv_progress = {};
-    bool progress_shown = false;
     int state = 0;
     int copy_error = 0;
     int in_waiting = 0, out_waiting = 0;
@@ -425,7 +413,6 @@ struct cli_dd_t
             auto res = read(fd, buf, blocksize < to_skip ? blocksize : to_skip);
             if (res <= 0)
             {
-                free(buf);
                 return res == 0 ? -EPIPE : -errno;
             }
             to_skip -= res;
@@ -735,12 +722,6 @@ struct cli_dd_t
         {
             return;
         }
-        if (end && !end_status && !parent->json_output)
-        {
-            if (progress_shown)
-                fprintf(stderr, "\r\033[K");
-            return;
-        }
         timespec tv_now;
         clock_gettime(CLOCK_REALTIME, &tv_now);
         double sec_delta = ((tv_now.tv_sec - tv_progress.tv_sec) + (double)(tv_now.tv_nsec - tv_progress.tv_nsec)/1000000000.0);
@@ -783,7 +764,6 @@ struct cli_dd_t
                 format_size((uint64_t)(delta/sec_delta), true).c_str(),
                 format_size((uint64_t)(written_size/sec_total), true).c_str()
             );
-            progress_shown = true;
         }
     }
 
@@ -846,12 +826,6 @@ struct cli_dd_t
             state = 100;
             return;
         }
-        if (oinfo.ofile != "" && oinfo.out_append && oinfo.out_trunc)
-        {
-            result = (cli_result_t){ .err = EINVAL, .text = "conv=trunc and oflag=append can't be used together" };
-            state = 100;
-            return;
-        }
         if ((iinfo.iimg != "" ? "i"+iinfo.iimg : "f"+iinfo.ifile) == (oinfo.oimg != "" ? "i"+oinfo.oimg : "f"+oinfo.ofile))
         {
             result = (cli_result_t){ .err = EINVAL, .text = "Input and output image/file can't be equal" };
@@ -874,20 +848,13 @@ struct cli_dd_t
             state = 100;
             return;
         }
-        if (iinfo.in_seekable && iseek >= iinfo.in_size)
-        {
-            iinfo.close_input(parent);
-            result = (cli_result_t){ .err = EINVAL, .text = "Input seek position is beyond end of input" };
-            state = 100;
-            return;
-        }
-        if (!oinfo.out_size && (iinfo.in_seekable || bytelimit))
+        if (!oinfo.out_size)
         {
             oinfo.out_size = oseek + (iinfo.in_seekable && (!bytelimit || iinfo.in_size-iseek < bytelimit) ? iinfo.in_size-iseek : bytelimit);
         }
 resume_1:
 resume_2:
-        if (!oinfo.open_output(parent, state, 1, oseek, blocksize))
+        if (!oinfo.open_output(parent, state, 1))
         {
             return;
         }
@@ -904,6 +871,11 @@ resume_2:
             goto close_end;
         }
         // Copy data
+        if (iinfo.in_seekable && iseek >= iinfo.in_size)
+        {
+            result = (cli_result_t){ .err = EINVAL, .text = "Input seek position is beyond end of input" };
+            goto close_end;
+        }
         if (!iinfo.iwatch && !iinfo.in_seekable && iseek)
         {
             // Read and ignore some data from input
@@ -917,8 +889,9 @@ resume_2:
         in_iodepth = iinfo.in_seekable ? iodepth : 1;
         out_iodepth = oinfo.out_seekable ? iodepth : 1;
         write_zero = write_zero || !oinfo.out_seekable;
+        oinfo.end_fsync = oinfo.end_fsync && oinfo.out_seekable;
         read_offset = 0;
-        read_end = iinfo.in_seekable ? iinfo.in_size-iseek : UINT64_MAX;
+        read_end = iinfo.in_seekable ? iinfo.in_size-iseek : 0;
         if (oinfo.out_size && (!read_end || read_end > oinfo.out_size-oseek))
             read_end = oinfo.out_size-oseek;
         if (bytelimit && (!read_end || read_end > bytelimit))
@@ -1027,14 +1000,10 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_dd(json11::Json cfg)
     if (!dd->iodepth)
         dd->iodepth = 4;
     if (cfg["status"] == "none")
-    {
-        dd->end_status = false;
-        progress = false;
-    }
-    else if (cfg["status"] == "noxfer")
         dd->end_status = false;
     else if (cfg["status"] == "progress")
         progress = true;
+    dd->iinfo.detect_size = cfg["size"].is_null();
     dd->oinfo.out_size = parse_size(cfg["size"].as_string());
     dd->conv = explode_json(",", cfg["conv"]);
     dd->iflag = explode_json(",", cfg["iflag"]);

src/cmd/cli_describe.cpp

@@ -41,8 +41,6 @@ struct cli_describe_t
     std::vector<osd_num_t> only_osds;
     uint64_t min_inode = 0, max_inode = 0;
     uint64_t min_offset = 0, max_offset = 0;
-    std::map<osd_num_t, std::string> skipped_pgs;
-    bool incomplete = false;
 
     cli_tool_t *parent = NULL;
     int state = 0;
@@ -57,13 +55,6 @@ struct cli_describe_t
         return state == 100;
     }
 
-    bool is_osd_up(osd_num_t osd_num)
-    {
-        auto & peer_states = parent->cli->st_cli->peer_states;
-        auto peer_it = peer_states.find(osd_num);
-        return peer_it != peer_states.end() && !peer_it->second.is_null();
-    }
-
     void parse_options(json11::Json cfg)
     {
         uint64_t pool_id;
@@ -92,18 +83,19 @@ struct cli_describe_t
         }
         only_pg = cfg["pg"].uint64_value();
         min_inode = cfg["inode"].uint64_value();
-        min_offset = stoull_full(cfg["min_offset"].string_value(), 0);
-        max_offset = stoull_full(cfg["max_offset"].string_value(), 0);
         if (min_inode)
         {
             if (!INODE_POOL(min_inode))
                 min_inode |= (uint64_t)only_pool << (64-POOL_ID_BITS);
             max_inode = min_inode;
+            min_offset = max_offset = 0;
         }
         else
         {
             min_inode = stoull_full(cfg["min_inode"].string_value(), 0); // to support 0x...
             max_inode = stoull_full(cfg["max_inode"].string_value(), 0);
+            min_offset = stoull_full(cfg["min_offset"].string_value(), 0);
+            max_offset = stoull_full(cfg["max_offset"].string_value(), 0);
             if (!min_inode && !max_inode && only_pool)
             {
                 min_inode = (uint64_t)only_pool << (64-POOL_ID_BITS);
@@ -111,9 +103,6 @@ struct cli_describe_t
                     (((uint64_t)1 << (64-POOL_ID_BITS)) - 1);
             }
         }
-        // The OSD ends the listing at (max_inode, max_offset) inclusive
-        if (max_inode && cfg["max_offset"].is_null())
-            max_offset = UINT64_MAX;
         only_osds = parse_uint64_list(cfg["osds"]);
         object_state = stoull_full(cfg["object_state"].string_value(), 0);
         if (!object_state && cfg["object_state"].is_string())
@@ -169,43 +158,10 @@ struct cli_describe_t
                 if (pp.first >= min_pool && (!max_pool || pp.first <= max_pool))
                 {
                     for (auto & pgp: pp.second.pg_config)
-                    {
-                        if (only_pool && only_pg && (pp.first != only_pool || pgp.first != only_pg))
-                            continue;
-                        if (is_osd_up(pgp.second.cur_primary))
-                            only_osds.push_back(pgp.second.cur_primary);
-                        else
-                        {
-                            auto & pgs = skipped_pgs[pgp.second.cur_primary];
-                            pgs += (pgs == "" ? "" : ", ")+std::to_string(pp.first)+"/"+std::to_string(pgp.first);
-                        }
-                    }
+                        only_osds.push_back(pgp.second.cur_primary);
                 }
             }
         }
-        else
-        {
-            std::vector<osd_num_t> filtered_osds;
-            for (auto osd_num: only_osds)
-            {
-                if (is_osd_up(osd_num))
-                    filtered_osds.push_back(osd_num);
-                else
-                    skipped_pgs[osd_num] = "";
-            }
-            only_osds = filtered_osds;
-        }
-        // Requests to an OSD which is down are never answered
-        for (auto & sk: skipped_pgs)
-        {
-            if (!sk.first)
-                fprintf(stderr, "No primary OSD for PG %s, skipping\n", sk.second.c_str());
-            else if (sk.second != "")
-                fprintf(stderr, "OSD %ju is down, skipping PG %s\n", sk.first, sk.second.c_str());
-            else
-                fprintf(stderr, "OSD %ju is down, skipping it\n", sk.first);
-            incomplete = true;
-        }
         remove_duplicates(only_osds);
         parent->cli->init_msgr();
         if (parent->json_output && parent->is_command_line)
@@ -234,7 +190,6 @@ struct cli_describe_t
             {
                 if (op->reply.hdr.retval < 0)
                 {
-                    incomplete = true;
                     fprintf(
                         stderr, "Failed to describe objects on OSD %ju (retval=%jd)\n",
                         osd_num, op->reply.hdr.retval
@@ -242,7 +197,6 @@ struct cli_describe_t
                 }
                 else if (op->reply.describe.result_bytes != op->reply.hdr.retval * sizeof(osd_reply_describe_item_t))
                 {
-                    incomplete = true;
                     fprintf(
                         stderr, "Invalid response size from OSD %ju (expected %ju bytes, got %ju bytes)\n",
                         osd_num, op->reply.hdr.retval * sizeof(osd_reply_describe_item_t), op->reply.describe.result_bytes
@@ -309,13 +263,6 @@ struct cli_describe_t
         {
             result.data = describe_items;
         }
-        if (incomplete)
-        {
-            result.err = EIO;
-            if (parent->json_output && parent->is_command_line)
-                parent->json_output = false;
-            result.text = "The listing is incomplete, see the messages above";
-        }
         state = 100;
         describe_items.clear();
     }

src/cmd/cli_fix.cpp

@@ -21,20 +21,12 @@ struct cli_fix_t
     json11::Json options;
     cli_result_t result;
     json11::Json::array fix_result;
-    bool incomplete = false;
 
     bool is_done()
     {
         return state == 100;
     }
 
-    bool is_osd_up(osd_num_t osd_num)
-    {
-        auto & peer_states = parent->cli->st_cli->peer_states;
-        auto peer_it = peer_states.find(osd_num);
-        return peer_it != peer_states.end() && !peer_it->second.is_null();
-    }
-
     void parse_objects_str(std::string str)
     {
         str = trim(str);
@@ -131,20 +123,6 @@ struct cli_fix_t
             state = 100;
             return;
         }
-        {
-            std::string down_osds;
-            for (auto osd_num: bad_osds)
-            {
-                if (!is_osd_up(osd_num))
-                    down_osds += (down_osds == "" ? "" : ", ")+std::to_string(osd_num);
-            }
-            if (down_osds != "")
-            {
-                result = (cli_result_t){ .err = EAGAIN, .text = "Bad OSD(s) "+down_osds+" are down, can't remove object copies from them" };
-                state = 100;
-                return;
-            }
-        }
         remove_duplicates(objects);
         parent->cli->init_msgr();
     resume_1:
@@ -160,7 +138,6 @@ struct cli_fix_t
             if (pool_cfg_it == parent->cli->st_cli->pool_config.end())
             {
                 fprintf(stderr, "Object %jx:%jx is from unknown pool\n", obj.inode, obj.stripe);
-                incomplete = true;
                 continue;
             }
             auto & pool_cfg = pool_cfg_it->second;
@@ -173,20 +150,9 @@ struct cli_fix_t
                     stderr, "Object %jx:%jx is from PG %u/%u which is not currently active\n",
                     obj.inode, obj.stripe, pool_cfg_it->first, pg_num
                 );
-                incomplete = true;
                 continue;
             }
             osd_num_t primary_osd = pg_it->second.cur_primary;
-            if (!is_osd_up(primary_osd))
-            {
-                // Requests to an OSD which is down are never answered
-                fprintf(
-                    stderr, "Object %jx:%jx is from PG %u/%u whose primary OSD %ju is down\n",
-                    obj.inode, obj.stripe, pool_cfg_it->first, pg_num, primary_osd
-                );
-                incomplete = true;
-                continue;
-            }
             // Describe -> Remove some copies -> Scrub again
             osd_op_t *op = new osd_op_t;
             op->req = (osd_any_op_t){
@@ -206,7 +172,6 @@ struct cli_fix_t
                 if (op->reply.hdr.retval < 0 || op->reply.describe.result_bytes != op->reply.hdr.retval * sizeof(osd_reply_describe_item_t))
                 {
                     fprintf(stderr, "Failed to describe objects on OSD %ju (retval=%jd)\n", primary_osd, op->reply.hdr.retval);
-                    incomplete = true;
                     parent->waiting--;
                     loop();
                 }
@@ -243,7 +208,6 @@ struct cli_fix_t
                                 (*rm_count)--;
                                 if (rm_op->reply.hdr.retval < 0)
                                 {
-                                    incomplete = true;
                                     fprintf(
                                         stderr, "Failed to remove object %jx:%jx from OSD %ju (retval=%jd)\n",
                                         rm_op->req.sec_del.oid.inode, rm_op->req.sec_del.oid.stripe,
@@ -288,7 +252,6 @@ struct cli_fix_t
                                     {
                                         if (scrub_op->reply.hdr.retval < 0 && scrub_op->reply.hdr.retval != -ENOENT)
                                         {
-                                            incomplete = true;
                                             fprintf(
                                                 stderr, "Failed to scrub %jx:%jx on OSD %ju (retval=%jd)\n",
                                                 obj.inode, obj.stripe, primary_osd, scrub_op->reply.hdr.retval
@@ -326,11 +289,6 @@ struct cli_fix_t
         {
             result.data = fix_result;
         }
-        if (incomplete)
-        {
-            result.err = EIO;
-            result.text = "Some objects were not fixed, see the messages above";
-        }
         state = 100;
     }
 };

src/cmd/cli_ls.cpp

@@ -250,17 +250,11 @@ resume_1:
 
     json11::Json::array to_tree(const json11::Json::array & array)
     {
-        std::set<uint64_t> listed;
-        for (const auto & item: array)
-        {
-            listed.insert(item["inode_id"].uint64_value());
-        }
         std::map<uint64_t, json11::Json::array> children;
         for (const auto & item: array)
         {
             uint64_t parent_id = item["parent_inode_id"].uint64_value();
-            // Layers with a filtered out parent are shown as roots
-            children[listed.find(parent_id) != listed.end() ? parent_id : 0].push_back(item);
+            children[parent_id].push_back(item);
         }
         json11::Json::array tree;
         std::function<void(uint64_t, const std::string &)> add_children = [&](uint64_t parent_id, const std::string & prefix)

src/cmd/cli_modify.cpp

@@ -287,20 +287,7 @@ std::function<bool(cli_result_t &)> cli_tool_t::start_modify(json11::Json cfg)
     changer->parent = this;
     changer->image_name = cfg["image"].string_value();
     changer->new_name = cfg["rename"].string_value();
-    if (!cfg["resize"].is_null())
-    {
-        bool ok = false;
-        changer->new_size = parse_size(cfg["resize"].as_string(), &ok);
-        if (!ok)
-        {
-            delete changer;
-            return [size = cfg["resize"].as_string()](cli_result_t & result)
-            {
-                result = (cli_result_t){ .err = EINVAL, .text = "Invalid syntax for size: "+size };
-                return true;
-            };
-        }
-    }
+    changer->new_size = parse_size(cfg["resize"].as_string());
     changer->force_size = cfg["force_size"].bool_value();
     changer->inc_size = cfg["inc_size"].bool_value();
     changer->force = cfg["force"].bool_value();

src/cmd/cli_osd_tree.cpp

@@ -412,8 +412,6 @@ resume_1:
         load_osd_tree();
         if (parent->waiting > 0)
             return;
-        if (state == 100)
-            return;
         format_tree();
         state = 100;
     }

src/cmd/cli_pg_ls.cpp

@@ -251,7 +251,7 @@ resume_1:
             { "title", "MISPLACED" },
         });
         cols.push_back(json11::Json::object{
-            { "key", "fmt_degraded" },
+            { "key", "fmt_misplaced" },
             { "title", "DEGRADED" },
         });
         cols.push_back(json11::Json::object{
@@ -273,8 +273,6 @@ resume_1:
         load_pg_stats();
         if (parent->waiting > 0)
             return;
-        if (state == 100)
-            return;
         format_pgs();
         state = 100;
     }

src/cmd/cli_pool_cfg.cpp

@@ -103,22 +103,24 @@ std::string validate_pool_config(json11::Json::object & new_cfg, json11::Json ol
             // level=rule, level=rule, ...
             if (!value.is_object())
             {
-                if (!value.is_null() && !value.is_string())
-                {
-                    return key+" must be a string";
-                }
                 json11::Json::object obj;
                 for (auto & item: explode(",", value.string_value(), true))
                 {
                     auto pair = explode("=", item, true);
-                    if (pair.size() != 2)
+                    if (pair.size() >= 2)
                     {
-                        return "--level_placement must be <level>=<rule>[,<level>=<rule>...], but it is "+value.string_value();
+                        obj[pair[0]] = pair[1];
                     }
-                    obj[pair[0]] = pair[1];
                 }
-                // empty value = remove the rules; null keeps the old ones from being merged back
-                value = obj.size() ? json11::Json(obj) : json11::Json();
+                if (obj.size())
+                {
+                    value = obj;
+                }
+                else
+                {
+                    new_cfg.erase(kv_it++);
+                    continue;
+                }
             }
         }
         else if (key == "osd_tags" || key == "primary_affinity_tags")
@@ -167,10 +169,6 @@ std::string validate_pool_config(json11::Json::object & new_cfg, json11::Json ol
     {
         new_cfg.erase("local_reads");
     }
-    if (new_cfg.find("level_placement") != new_cfg.end() && new_cfg["level_placement"].is_null())
-    {
-        new_cfg.erase("level_placement");
-    }
 
     // Prevent autovivification of object keys. Now we don't modify the config, we just check it
     json11::Json cfg = new_cfg;
@@ -235,10 +233,9 @@ std::string validate_pool_config(json11::Json::object & new_cfg, json11::Json ol
     {
         return "PG size can't be smaller than 3 for EC/XOR pools";
     }
-    // same limit as in etcd_state_client.cpp and mon/pool_config.js
-    if (pg_size > 64)
+    if (pg_size > 256)
     {
-        return "PG size can't be greater than 64";
+        return "PG size can't be greater than 256";
     }
 
     // PG rules

src/cmd/cli_pool_modify.cpp

@@ -116,21 +116,7 @@ resume_1:
                 state = 100;
                 return;
             }
-            if (new_cfg["name"] != old_cfg["name"])
-            {
-                for (auto & pce: kv.value.object_items())
-                {
-                    if (pce.second["name"] == new_cfg["name"])
-                    {
-                        result = (cli_result_t){
-                            .err = EEXIST,
-                            .text = "Pool with name \""+new_cfg["name"].string_value()+"\" already exists (ID "+pce.first+")",
-                        };
-                        state = 100;
-                        return;
-                    }
-                }
-            }
+
             if (new_cfg.find("used_for_app") != new_cfg.end() && !force)
             {
                 // Check that pool doesn't have images

src/cmd/cli_rm_data.cpp

@@ -1,6 +1,7 @@
 // Copyright (c) Vitaliy Filippov, 2019+
 // License: VNPL-1.1 (see README.md for details)
 
+#include <ctype.h>
 #include "cli.h"
 #include "cluster_client.h"
 
@@ -23,6 +24,7 @@ struct rm_inode_t
 {
     uint64_t inode = 0;
     pool_id_t pool_id = 0;
+    std::string pool_name;
     uint64_t min_offset = 0;
     uint64_t max_offset = 0;
     bool down_ok = false;
@@ -302,6 +304,25 @@ struct rm_inode_t
             goto resume_1;
         if (state == 100)
             return;
+        if (pool_name != "")
+        {
+            pool_id = 0;
+            for (auto & pp: parent->cli->st_cli->pool_config)
+            {
+                if (pp.second.name == pool_name)
+                {
+                    pool_id = pp.first;
+                    break;
+                }
+            }
+            if (!pool_id)
+            {
+                result = (cli_result_t){ .err = ENOENT, .text = "Pool "+pool_name+" does not exist" };
+                state = 100;
+                return;
+            }
+            inode = INODE_WITH_POOL(pool_id, inode);
+        }
         if (!pool_id)
         {
             result = (cli_result_t){ .err = EINVAL, .text = "Pool is not specified" };
@@ -317,39 +338,103 @@ struct rm_inode_t
     }
 };
 
+// Decimal or 0x hex, without sign, octal or overflow
+static bool parse_rm_number(std::string s, uint64_t & value)
+{
+    int base = 10;
+    if (s.size() > 2 && s[0] == '0' && (s[1] == 'x' || s[1] == 'X'))
+    {
+        s = s.substr(2);
+        base = 16;
+    }
+    if (s == "" || s.find_first_not_of(base == 16 ? "0123456789abcdefABCDEF" : "0123456789") != std::string::npos)
+        return false;
+    errno = 0;
+    value = strtoull(s.c_str(), NULL, base);
+    return !errno;
+}
+
+// Command-line values are strings with optional K/M/G/T suffixes, internal callers pass numbers
+static bool parse_rm_offset(const json11::Json & value, uint64_t & offset)
+{
+    if (!value.is_string())
+    {
+        offset = value.uint64_value();
+        return true;
+    }
+    std::string s = value.string_value();
+    int shift = 0;
+    switch (s.size() ? tolower(s.back()) : 0)
+    {
+        case 'k': shift = 10; break;
+        case 'm': shift = 20; break;
+        case 'g': shift = 30; break;
+        case 't': shift = 40; break;
+    }
+    if (shift)
+        s.pop_back();
+    if (!parse_rm_number(s, offset) || offset > (UINT64_MAX >> shift))
+        return false;
+    offset <<= shift;
+    return true;
+}
+
+static bool parse_rm_inode(const json11::Json & value, uint64_t & inode)
+{
+    if (!value.is_string())
+    {
+        inode = value.uint64_value();
+        return true;
+    }
+    return parse_rm_number(value.string_value(), inode);
+}
+
+// A non-numeric string is a pool name, resolved after loading the pool configuration
+static bool parse_rm_pool(const json11::Json & value, uint64_t & pool_id, std::string & pool_name)
+{
+    pool_id = value.uint64_value();
+    if (value.is_string() && !pool_id && value.string_value() != "0")
+        pool_name = value.string_value();
+    return pool_id < POOL_ID_MAX && (!value.is_string() || value.string_value() != "");
+}
+
 std::function<bool(cli_result_t &)> cli_tool_t::start_rm_data(json11::Json cfg)
 {
+    uint64_t inode = 0, pool_id = 0, min_offset = 0, max_offset = 0;
+    std::string pool_name, error;
+    if (!parse_rm_inode(cfg["inode"], inode))
+        error = "Invalid --inode value: "+cfg["inode"].as_string();
+    else if (!parse_rm_pool(cfg["pool"], pool_id, pool_name))
+        error = "Invalid --pool value: "+cfg["pool"].as_string();
+    else if (!parse_rm_offset(cfg["min_offset"], min_offset))
+        error = "Invalid --min-offset value: "+cfg["min_offset"].as_string();
+    else if (!parse_rm_offset(cfg["max_offset"], max_offset))
+        error = "Invalid --max-offset value: "+cfg["max_offset"].as_string();
+    else if (!max_offset && cfg["max_offset"].is_string())
+        error = "--max-offset 0 is invalid, omit it to remove data up to the end";
+    else if (max_offset && min_offset >= max_offset)
+        error = "--min-offset must be less than --max-offset";
+    if (error != "")
+    {
+        return [error](cli_result_t & result)
+        {
+            result = (cli_result_t){ .err = EINVAL, .text = error };
+            return true;
+        };
+    }
     auto remover = new rm_inode_t();
     remover->parent = this;
-    remover->inode = cfg["inode"].uint64_value();
-    remover->pool_id = cfg["pool"].uint64_value();
+    remover->inode = inode;
+    remover->pool_id = pool_id;
+    remover->pool_name = pool_name;
     if (remover->pool_id)
     {
         remover->inode = (remover->inode & (((uint64_t)1 << (64-POOL_ID_BITS)) - 1)) | (((uint64_t)remover->pool_id) << (64-POOL_ID_BITS));
     }
     remover->down_ok = cfg["down_ok"].bool_value();
     remover->pool_id = INODE_POOL(remover->inode);
-    bool min_max_ok = true;
-    if (!cfg["min_offset"].is_null())
-    {
-        remover->min_offset = cfg["min_offset"].uint64_value();
-        if (!remover->min_offset && cfg["min_offset"].as_string() != "0")
-            min_max_ok = false;
-    }
-    if (!cfg["max_offset"].is_null())
-    {
-        remover->max_offset = cfg["max_offset"].uint64_value();
-        if (!remover->max_offset && cfg["max_offset"].as_string() != "0")
-            min_max_ok = false;
-    }
-    if (!min_max_ok)
-    {
-        return [](cli_result_t & result)
-        {
-            result = (cli_result_t){ .err = EINVAL, .text = "Invalid min_offset or max_offset" };
-            return true;
-        };
-    }
+    remover->min_offset = min_offset;
+    remover->max_offset = max_offset;
     return [remover](cli_result_t & result)
     {
         remover->loop();

src/cmd/cli_rm_osd.cpp

@@ -170,8 +170,7 @@ struct rm_osd_t
             }
             if (still_up.size() && !allow_up)
                 error += (still_up.size() == 1 ? "OSD " : "OSDs ") + implode(", ", still_up) +
-                    (still_up.size() == 1 ? " is" : " are") + " still up. Use `vitastor-disk purge` to delete " +
-                    (still_up.size() == 1 ? "it" : "them") + ".\n";
+                    (still_up.size() == 1 ? "is" : "are") + " still up. Use `vitastor-disk purge` to delete them.\n";
             if (is_dataloss && !force_dataloss && !dry_run)
                 error += "OSDs not deleted. Please move data to other OSDs or bypass this check with --allow-data-loss if you know what you are doing.\n";
             else if (is_warning && !force_warning && !dry_run)

src/kv/kv_cli.cpp

@@ -664,7 +664,7 @@ void kv_cli_t::handle_cmd(const std::vector<std::string> & cmd, std::function<vo
         kv_cli_list_t *lst = new kv_cli_list_t;
         std::string start = cmd.size() >= 2 ? cmd[1] : "";
         std::string end = cmd.size() >= 3 ? cmd[2] : "";
-        lst->handle = db->list_start(start, end);
+        lst->handle = db->list_start(start);
         lst->db = db;
         lst->format = opname == "dump" ? 1 : (opname == "dumpjson" ? 2 : 0);
         lst->cb = std::move(cb);

src/kv/kv_db.cpp

@@ -190,8 +190,6 @@ struct kv_op_t
     kv_db_t *db;
     int opcode;
     std::string key, value;
-    // for list: stop before the first key >= list_end, unless list_end is empty
-    std::string list_end;
     int res;
     bool in_next = false;
     bool next_retry_pending = false;
@@ -2023,12 +2021,6 @@ void kv_op_t::next_get()
     }
     if (kv_it != blk->data.end())
     {
-        if (list_end != "" && kv_it->first >= list_end)
-        {
-            // End of the listing range
-            finish(-ENOENT);
-            return;
-        }
         // Send this item
         assert(blk->type == KV_LEAF || blk->type == KV_LEAF_SPLIT);
         this->res = 0;
@@ -2040,12 +2032,6 @@ void kv_op_t::next_get()
     // Find next block
     else if (blk->type == KV_LEAF_SPLIT)
     {
-        if (list_end != "" && blk->right_half >= list_end)
-        {
-            // The right half is beyond the listing range
-            finish(-ENOENT);
-            return;
-        }
         // Left half finished, go to the right
         recheck_policy = KV_RECHECK_LEAF;
         key = blk->right_half;
@@ -2077,12 +2063,6 @@ void kv_op_t::next_go_up()
             // Block can be updated and key_lt may be lower. Don't rewind it
             key = blk->key_lt;
         }
-        if (list_end != "" && key >= list_end)
-        {
-            // Next keys are beyond the listing range, don't read the next block
-            finish(-ENOENT);
-            return;
-        }
         skip_equal = false;
         path.pop_back();
         cur_level--;
@@ -2214,11 +2194,6 @@ void vitastorkv_dbw_t::del(const std::string & key, std::function<void(int res)>
 }
 
 void* vitastorkv_dbw_t::list_start(const std::string & start)
-{
-    return list_start(start, "");
-}
-
-void* vitastorkv_dbw_t::list_start(const std::string & start, const std::string & end)
 {
     if (!db->inode_id || db->closing)
         return NULL;
@@ -2226,7 +2201,6 @@ void* vitastorkv_dbw_t::list_start(const std::string & start, const std::string
     op->db = db;
     op->opcode = KV_LIST;
     op->key = start;
-    op->list_end = end;
     op->callback = [](kv_op_t *){};
     op->exec();
     return op;

src/kv/vitastor_kv.h

@@ -40,8 +40,6 @@ struct __attribute__((visibility("default"))) vitastorkv_dbw_t
         std::function<bool(int res, const std::string & value)> cas_compare = NULL);
 
     void* list_start(const std::string & start);
-    // list keys >= start and < end (all keys >= start if end is empty)
-    void* list_start(const std::string & start, const std::string & end);
     void list_next(void *handle, std::function<void(int res, const std::string & key, const std::string & value)> cb);
     void list_close(void *handle);
 

src/nfs/nfs_kv.cpp

@@ -110,16 +110,6 @@ std::string kv_direntry_key(uint64_t dir_ino, const std::string & filename)
     return (char*)key + filename;
 }
 
-std::string kv_prefix_end(const std::string & prefix)
-{
-    std::string end = prefix;
-    while (end.size() && (uint8_t)end.back() == 0xff)
-        end.pop_back();
-    if (end.size())
-        end.back()++;
-    return end;
-}
-
 std::string kv_direntry_filename(const std::string & key)
 {
     // decode as: d <length> <hex dir_ino> / <filename>

src/nfs/nfs_kv.h

@@ -130,8 +130,6 @@ int kv_map_type(const std::string & type);
 fattr3 get_kv_attributes(nfs_proxy_t *proxy, uint64_t ino, json11::Json attrs);
 std::string kv_direntry_key(uint64_t dir_ino, const std::string & filename);
 std::string kv_direntry_filename(const std::string & key);
-// The first key after all keys starting with prefix, to stop a listing at the end of the prefix
-std::string kv_prefix_end(const std::string & prefix);
 std::string kv_inode_prefix_key(uint64_t ino, const char *prefix);
 std::string kv_inode_key(uint64_t ino);
 uint64_t kv_key_inode(const std::string & key, int prefix_len = 1);

src/nfs/nfs_kv_defrag.cpp

@@ -317,7 +317,7 @@ void kv_fs_defrag_all_t::run(int st)
     else if (st == 6)
         goto resume_6;
     clock_gettime(CLOCK_REALTIME, &now);
-    list_shared = proxy->db->list_start("shared", kv_prefix_end("shared"));
+    list_shared = proxy->db->list_start("shared");
     proxy->db->list_next(list_shared, [this](int res, const std::string & key, const std::string & value)
     {
         if (res == -ENOENT || key.substr(0, 6) != "shared")
@@ -482,7 +482,7 @@ void kv_fs_state_t::upgrade_db(std::function<void(int)> cb)
             return;
         }
         // Create missing shared inode index keys
-        auto list_inodes = proxy->db->list_start("i", kv_prefix_end("i"));
+        auto list_inodes = proxy->db->list_start("i");
         proxy->db->list_next(list_inodes, [=](int res, const std::string & key, const std::string & value)
         {
             if (res == -ENOENT || key.substr(0, 1) != "i" || key == "id")

src/nfs/nfs_kv_readdir.cpp

@@ -241,7 +241,7 @@ resume_2:
         st->cookieverf = ((uint64_t)lrand48() | ((uint64_t)lrand48() << 31) | ((uint64_t)lrand48() << 62));
     }
     st->getattr_cur = st->entries.size();
-    st->list_handle = st->self->parent->db->list_start(st->start, kv_prefix_end(st->prefix));
+    st->list_handle = st->self->parent->db->list_start(st->start);
     st->self->parent->db->list_next(st->list_handle, [=](int res, const std::string & key, const std::string & value)
     {
         st->res = res;

src/nfs/nfs_kv_remove.cpp

@@ -181,7 +181,7 @@ resume_3:
     if (st->is_rmdir)
     {
         // (4) Check if the directory actually is not empty
-        st->list_handle = st->self->parent->db->list_start(kv_direntry_key(st->ino, ""), kv_prefix_end(kv_direntry_key(st->ino, "")));
+        st->list_handle = st->self->parent->db->list_start(kv_direntry_key(st->ino, ""));
         st->self->parent->db->list_next(st->list_handle, [st](int res, const std::string & key, const std::string & value)
         {
             st->res = res;

src/nfs/nfs_kv_rename.cpp

@@ -138,7 +138,7 @@ resume_2:
         {
             // Check that the destination directory is empty
             st->new_dir_prefix = kv_direntry_key(st->new_direntry["ino"].uint64_value(), "");
-            st->list_handle = st->self->parent->db->list_start(st->new_dir_prefix, kv_prefix_end(st->new_dir_prefix));
+            st->list_handle = st->self->parent->db->list_start(st->new_dir_prefix);
             st->self->parent->db->list_next(st->list_handle, [st](int res, const std::string & key, const std::string & value)
             {
                 st->res = res;

src/osd/osd_scrub.cpp

@@ -558,11 +558,13 @@ void osd_t::scrub_check_results(osd_op_t *cur_op)
         }
         else
         {
+            int total = 0;
             for (int i = 0; i < op_data->stripe_count; i++)
             {
                 if (!op_data->stripes[i].not_exists)
                 {
                     // use "missing" flag to distinguish actual read errors and inconsistent chunks
+                    total++;
                     op_data->stripes[i].missing = true;
                 }
             }

src/test/test_cas.cpp

@@ -371,7 +371,7 @@ int main(int narg, char *args[])
     auto ringloop = new ring_loop_t(RINGLOOP_DEFAULT_SIZE);
     auto epmgr = new epoll_manager_t(ringloop);
     auto cli = cluster_client_t::create(ringloop, epmgr->tfd, cfg);
-    test_data_t data = { .cli = cli, .ringloop = ringloop, .inode = inode };
+    test_data_t data = { .cli = cli, .ringloop = ringloop, inode = inode };
     // Wait for init
     cli->on_ready([&]() { data.done = true; });
     data.wait();

src/test/test_cluster_client.cpp

@@ -1122,37 +1122,6 @@ void test_pg_config_disappears()
     printf("[ok] test_pg_config_disappears\n");
 }
 
-void test_sync_released_during_continue_ops()
-{
-    json11::Json config;
-    timerfd_manager_t *tfd = new timerfd_manager_t([](int fd, bool wr, std::function<void(int, int)> callback){});
-    etcd_mock_t etcd_store;
-    etcd_state_client_mock_t *mock = new etcd_state_client_mock_t(etcd_store);
-    mock->pause();
-    cluster_client_t *cli = new cluster_client_t(NULL, tfd, config, std::unique_ptr<etcd_state_client_t>(mock));
-
-    configure_single_pg_pool(mock);
-    mock->resume();
-    // The OSD isn't connected: the write waits, and the SYNC waits for the write
-    int *r1 = test_write(cli, 0, 4096, 0x55);
-    int *r2 = test_sync(cli);
-
-    // The write fails in continue_ops(), and the SYNC it releases completes and is freed at once:
-    // continue_ops() must not go on from the write to the SYNC
-    can_complete(r1);
-    can_complete(r2);
-    mock->set("/vitastor/pg/config", json11::Json::object {
-        { "items", json11::Json::object { } }
-    });
-    assert(*r1 == -EINVAL);
-    check_completed(r2);
-    delete r1;
-
-    delete cli;
-    delete tfd;
-    printf("[ok] test_sync_released_during_continue_ops\n");
-}
-
 void test_snapshot_over_nonexistent_pool()
 {
     json11::Json config;
@@ -1357,7 +1326,6 @@ int main(int narg, char *args[])
     test_sync_fail_dirty_state_loss();
     cluster_client_test_t::test_vault();
     test_pg_config_disappears();
-    test_sync_released_during_continue_ops();
     test_snapshot_over_nonexistent_pool();
     return 0;
 }

tests/run_tests.sh

@@ -18,8 +18,6 @@ SCHEME=ec ./test_change_pg_count.sh
 
 ./test_create_nomaxid.sh
 
-./test_modify_pool.sh
-
 ./test_etcd_fail.sh
 ANTIETCD=1 ./test_etcd_fail.sh
 
@@ -66,10 +64,7 @@ OLD=1 ./test_move_reappear.sh
 
 ./test_rm.sh
 
-./test_modify_image_resize.sh
-
 ./test_rm_degraded.sh
-./test_describe.sh
 
 ./test_snapshot_chain.sh
 SCHEME=ec ./test_snapshot_chain.sh
@@ -85,7 +80,6 @@ OLD=1 SCHEME=ec ./test_snapshot_down.sh
 
 ./test_kv_stress.sh
 IMMEDIATE_COMMIT=1 ./test_kv_stress.sh
-./test_kv_list_bounds.sh
 
 ./test_splitbrain.sh
 
@@ -101,8 +95,6 @@ OLD=1 SCHEME=ec IMMEDIATE_COMMIT=1 ./test_rebalance_verify.sh
 
 ./test_dd.sh
 
-./test_cli_help.sh
-
 ./test_root_node.sh
 
 ./test_switch_primary.sh
@@ -130,7 +122,6 @@ OLD=1 ./test_corrupt_all.sh
 
 ./test_reweight_half.sh
 ./test_snapshot_pool2.sh
-./test_ls_tree.sh
 ./test_snapshot_read_bitmap.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
@@ -185,7 +176,6 @@ TEST_NAME=old_csum_4k      OLD=1 OSD_ARGS="--data_csum_type crc32c" OFFSET_ARGS=
 ./test_nfs.sh
 ./test_nfs_unaligned_append.sh
 ./test_nfs_long_readdir.sh
-./test_nfs_list_bounds.sh
 
 ./test_write_encrypted.sh
 SCHEME=ec ./test_write_encrypted.sh

tests/test_cli_help.sh

@@ -1,14 +0,0 @@
-#!/bin/bash -ex
-
-# Test that vitastor-cli --help knows every command name and alias the CLI accepts
-
-. `dirname $0`/common.sh
-
-for cmd in $(grep -o 'cmd\[0\] == "[^"]*"' src/cmd/cli.cpp | sed 's/.*== "//; s/"$//'); do
-    build/src/cmd/vitastor-cli --help $cmd > ./testdata/help.txt 2>&1 || true
-    if grep -q '^Unknown command' ./testdata/help.txt; then
-        format_error "vitastor-cli --help $cmd does not know the command"
-    fi
-done
-
-format_green OK

tests/test_dd.sh

@@ -24,85 +24,4 @@ $VITASTOR_CLI dd iimg=testimg2 iodepth=4 bs=1M count=128 > ./testdata/testfile1
 diff ./testdata/testfile ./testdata/testfile1
 rm ./testdata/testfile1
 
-# size= sets the output size, the input size is still detected
-$VITASTOR_CLI dd iimg=testimg oimg=testimg3 iodepth=4 size=192M
-$VITASTOR_CLI dd if=./testdata/testfile oimg=testimg4 iodepth=4 size=192M
-for img in testimg3 testimg4; do
-    size=$($VITASTOR_CLI ls --json | jq -r '.[] | select(.name == "'$img'") | .size')
-    [[ "$size" = $((192*1024*1024)) ]] || format_error "dd size=192M created $img with size $size"
-    $VITASTOR_CLI dd iimg=$img iodepth=4 bs=1M count=128 > ./testdata/testfile1
-    diff ./testdata/testfile ./testdata/testfile1
-    rm ./testdata/testfile1
-done
-
-# skip beyond the end of input fails before the output image is created
-rc=0
-$VITASTOR_CLI dd iimg=testimg oimg=testimg5 bs=1M skip=200 count=1 || rc=$?
-[[ $rc = 22 ]] || format_error "dd skip beyond the end of input returned $rc instead of EINVAL"
-if $VITASTOR_CLI ls --json | jq -e '.[] | select(.name == "testimg5")'; then
-    format_error "dd skip beyond the end of input created the output image"
-fi
-
-# status=none prints nothing, also with the default --progress 1
-$VITASTOR_CLI dd iimg=testimg of=./testdata/testfile1 iodepth=4 status=none 2>./testdata/dd.err
-[[ ! -s ./testdata/dd.err ]] || format_error "dd status=none printed: $(cat ./testdata/dd.err)"
-diff ./testdata/testfile ./testdata/testfile1
-rm ./testdata/testfile1
-
-# status=noxfer drops the final statistics line
-$VITASTOR_CLI --progress 0 dd iimg=testimg of=./testdata/testfile1 iodepth=4 status=noxfer 2>./testdata/dd.err
-[[ ! -s ./testdata/dd.err ]] || format_error "dd status=noxfer printed: $(cat ./testdata/dd.err)"
-rm ./testdata/testfile1
-# with --progress 1 the progress line, if it was shown at all, is cleared at the end
-clear_line=$'\r\033[K'
-for count in 128 4; do
-    $VITASTOR_CLI dd iimg=testimg of=./testdata/testfile1 iodepth=4 bs=1M count=$count status=noxfer 2>./testdata/dd.err
-    if [[ $(wc -l < ./testdata/dd.err) != 0 || ( -s ./testdata/dd.err && "$(cat ./testdata/dd.err)" != *copied*"$clear_line" ) ]]; then
-        format_error "dd status=noxfer count=$count printed: $(cat -v ./testdata/dd.err)"
-    fi
-    head -c ${count}M ./testdata/testfile | cmp - ./testdata/testfile1
-    rm ./testdata/testfile1
-done
-
-# oflag=append appends to the output file
-cp ./testdata/over ./testdata/testfile1
-$VITASTOR_CLI dd iimg=testimg of=./testdata/testfile1 iodepth=4 bs=1M count=8 oflag=append
-(cat ./testdata/over; head -c 8M ./testdata/testfile) | cmp - ./testdata/testfile1 || format_error "dd oflag=append did not append to the output file"
-rm ./testdata/testfile1
-# conv=trunc contradicts oflag=append: fail without touching the output file
-cp ./testdata/over ./testdata/testfile1
-rc=0
-$VITASTOR_CLI dd iimg=testimg of=./testdata/testfile1 iodepth=4 bs=1M count=8 oflag=append conv=trunc || rc=$?
-[[ $rc = 22 ]] || format_error "dd conv=trunc oflag=append returned $rc instead of EINVAL"
-cmp ./testdata/over ./testdata/testfile1 || format_error "dd conv=trunc oflag=append changed the output file"
-rm ./testdata/testfile1
-
-# pipe in without count - copy to the end of input
-$VITASTOR_CLI dd iimg=testimg iodepth=4 | $VITASTOR_CLI dd of=./testdata/testfile1 iodepth=4
-diff ./testdata/testfile ./testdata/testfile1
-rm ./testdata/testfile1
-$VITASTOR_CLI dd iimg=testimg iodepth=4 | $VITASTOR_CLI dd of=./testdata/testfile1 iodepth=4 bs=1M seek=4
-(head -c 4M /dev/zero; cat ./testdata/testfile) | cmp - ./testdata/testfile1 || format_error "dd from a pipe with seek= did not copy the whole input"
-rm ./testdata/testfile1
-
-# unaligned image I/O fails with EINVAL before the output image is created or resized
-for args in "if=./testdata/testfile oimg=testimg6 seek=512B" "if=./testdata/testfile oimg=testimg2 seek=512B" "iimg=testimg oimg=testimg7 skip=512B"; do
-    rc=0
-    $VITASTOR_CLI dd iodepth=4 $args || rc=$?
-    [[ $rc = 22 ]] || format_error "dd $args returned $rc instead of EINVAL"
-done
-if $VITASTOR_CLI ls --json | jq -e '.[] | select(.name == "testimg6" or .name == "testimg7")'; then
-    format_error "dd with unaligned image I/O created the output image"
-fi
-size=$($VITASTOR_CLI ls --json | jq -r '.[] | select(.name == "testimg2") | .size')
-[[ "$size" = $((128*1024*1024)) ]] || format_error "dd with unaligned seek resized testimg2 to $size"
-
-# a character device is read like a pipe, up to count= or size=
-$VITASTOR_CLI dd if=/dev/zero oimg=testimg8 size=32M
-size=$($VITASTOR_CLI ls --json | jq -r '.[] | select(.name == "testimg8") | .size')
-[[ "$size" = $((32*1024*1024)) ]] || format_error "dd if=/dev/zero size=32M created testimg8 with size $size"
-$VITASTOR_CLI dd if=/dev/zero of=./testdata/testfile1 bs=1M count=4 conv=nosparse
-head -c 4M /dev/zero | cmp - ./testdata/testfile1 || format_error "dd if=/dev/zero count=4 did not write 4 MiB of zeros"
-rm ./testdata/testfile1
-
 format_green OK

tests/test_describe.sh

@@ -1,98 +0,0 @@
-#!/bin/bash -ex
-
-# Test vitastor-cli describe and fix on degraded objects and with down OSDs
-
-PG_COUNT=4
-PG_SIZE=3
-PG_MINSIZE=2
-# Keep degraded objects until the checks are done
-GLOBAL_CONFIG=',"no_recovery":true'
-. `dirname $0`/run_3osds.sh
-
-$VITASTOR_CLI create -s 32M testimg
-
-# Data written while OSD 3 is down is degraded when it comes back
-kill -9 $OSD3_PID
-$ETCDCTL del /vitastor/osd/state/3
-wait_condition 60 "$ETCDCTL get --prefix /vitastor/pg/state/ --print-value-only | jq -s -e '[ .[] | select(.state | index(\"degraded\")) ] | length == $PG_COUNT'" "PG peering without OSD 3"
-$VITASTOR_CLI dd if=/dev/urandom oimg=testimg bs=1M count=32
-start_osd 3
-wait_condition 60 "$ETCDCTL get --prefix /vitastor/pg/state/ --print-value-only | jq -s -e '[ .[] | select((.state | index(\"active\")) and (.state | index(\"has_degraded\"))) ] | length == $PG_COUNT'" "PG peering with OSD 3"
-
-INODE_ID=$($VITASTOR_CLI ls --json | jq -r '.[] | select(.name == "testimg") | .inode_id')
-INODE=$(printf '0x%x' $INODE_ID)
-INODE_NUM=$((INODE_ID & 0xffffffffffff))
-
-# --inode lists the whole inode, not only its first object
-all=$($VITASTOR_CLI describe --json | jq -c '[ .[] | select(.inode == "'$INODE'") | .stripe ] | unique')
-if [[ $(echo "$all" | jq length) -le 1 ]]; then
-    format_error "describe should list more than one degraded object of testimg: $all"
-fi
-one=$($VITASTOR_CLI describe --pool 1 --inode $INODE_NUM --json | jq -c '[ .[].stripe ] | unique')
-if [[ "$one" != "$all" ]]; then
-    format_error "describe --inode lists objects $one instead of $all"
-fi
-
-# --min-offset and --max-offset narrow --inode, and --max-inode includes its whole inode
-second=$(echo "$all" | jq -r '.[1]')
-part=$($VITASTOR_CLI describe --pool 1 --inode $INODE_NUM --min-offset $second --max-offset $second --json | jq -c '[ .[].stripe ] | unique')
-if [[ "$part" != "[\"$second\"]" ]]; then
-    format_error "describe --inode --min-offset $second --max-offset $second lists objects $part"
-fi
-range=$($VITASTOR_CLI describe --min-inode $INODE --max-inode $INODE --json | jq -c '[ .[].stripe ] | unique')
-if [[ "$range" != "$all" ]]; then
-    format_error "describe --min-inode $INODE --max-inode $INODE lists objects $range instead of $all"
-fi
-
-# describe and fix must not wait for an OSD which is down.
-# Stop the monitor so that PGs keep the down OSD as their primary,
-# and stop a primary OSD which has the latest data, so other PGs stay degraded.
-VICTIM=$($VITASTOR_CLI ls-pgs --json | jq -r '[ .[].cur_primary | select(. == 1 or . == 2) ] | first')
-VICTIM_PG=$($VITASTOR_CLI ls-pgs --json | jq -r '[ .[] | select(.cur_primary == '$VICTIM') | .pg_num ] | first')
-OTHER_PG=$($VITASTOR_CLI ls-pgs --json | jq -r '[ .[] | select(.cur_primary != '$VICTIM') | .pg_num ] | first')
-OTHER_PG_COUNT=$($VITASTOR_CLI ls-pgs --json | jq '[ .[] | select(.cur_primary != '$VICTIM') ] | length')
-if [[ "$VICTIM" = null || "$OTHER_PG_COUNT" = 0 ]]; then
-    format_error "Expected PGs with primary OSD 1 or 2 and PGs with other primary OSDs"
-fi
-VICTIM_OBJ=$($VITASTOR_CLI describe --pool 1 --pg $VICTIM_PG --json | jq -r '.[0] | .inode+":"+.stripe')
-OTHER_OBJ=$($VITASTOR_CLI describe --pool 1 --pg $OTHER_PG --json | jq -r '.[0] | .inode+":"+.stripe')
-
-kill -9 $MON_PID
-eval kill -9 \$OSD${VICTIM}_PID
-$ETCDCTL del /vitastor/osd/state/$VICTIM
-wait_condition 60 "$ETCDCTL get --prefix /vitastor/pg/state/ --print-value-only | jq -s -e '[ .[] | select(.primary != $VICTIM and (.state | index(\"degraded\"))) ] | length == $OTHER_PG_COUNT'" "PG peering without OSD $VICTIM"
-# Keep PG 1/$VICTIM_PG active with the down primary, as it is until the OSD's etcd lease expires
-$ETCDCTL put /vitastor/pg/state/1/$VICTIM_PG '{"peers":[1,2,3],"primary":'$VICTIM',"state":["active"]}'
-
-# A listing with skipped OSDs or PGs is incomplete: EIO, but still valid JSON on stdout
-for args in "" "--osds 1,2,3" "--pool 1 --pg $VICTIM_PG"; do
-    rc=0
-    timeout 30 $VITASTOR_CLI describe $args --json > ./testdata/describe.json 2> ./testdata/describe.err || rc=$?
-    [[ $rc == 5 ]] || format_error "describe $args exited with $rc instead of EIO with OSD $VICTIM down"
-    grep -q "OSD $VICTIM is down, skipping \(it\|PG 1/$VICTIM_PG\)" ./testdata/describe.err || \
-        format_error "describe $args should warn about OSD $VICTIM: $(cat ./testdata/describe.err)"
-    grep -q "The listing is incomplete" ./testdata/describe.err || \
-        format_error "describe $args should say that the listing is incomplete: $(cat ./testdata/describe.err)"
-    count=$(jq length ./testdata/describe.json) || format_error "describe $args printed invalid JSON"
-    if [[ "$args" == --pool* ]]; then
-        [[ $count == 0 ]] || format_error "describe $args should list nothing"
-    else
-        [[ $count -gt 0 ]] || format_error "describe $args should still list objects from the other OSDs"
-    fi
-done
-
-if timeout 30 $VITASTOR_CLI fix --bad-osds $VICTIM --objects $OTHER_OBJ 2> ./testdata/fix.err; then
-    format_error "fix should refuse to work with bad OSD $VICTIM down"
-fi
-grep -q "Bad OSD(s) $VICTIM are down" ./testdata/fix.err || format_error "fix printed: $(cat ./testdata/fix.err)"
-
-# An object which is skipped is not fixed: EIO
-rc=0
-timeout 30 $VITASTOR_CLI fix --bad-osds 3 --objects $VICTIM_OBJ 2> ./testdata/fix.err || rc=$?
-[[ $rc == 5 ]] || format_error "fix exited with $rc instead of EIO on an object from PG 1/$VICTIM_PG with primary OSD $VICTIM down"
-grep -q "is from PG 1/$VICTIM_PG whose primary OSD $VICTIM is down" ./testdata/fix.err || \
-    format_error "fix should skip the object from PG 1/$VICTIM_PG: $(cat ./testdata/fix.err)"
-grep -q "Some objects were not fixed" ./testdata/fix.err || \
-    format_error "fix should say that it skipped objects: $(cat ./testdata/fix.err)"
-
-format_green OK

tests/test_kv_list_bounds.sh

@@ -1,45 +0,0 @@
-#!/bin/bash -ex
-# Test K/V listings with an end key: they must return exactly the keys of their range,
-# also when the range spans several blocks or ends in the middle of a block.
-
-PG_COUNT=16
-. `dirname $0`/run_3osds.sh
-
-$VITASTOR_CLI create -s 1G kvlist
-KV="build/src/kv/vitastor-kv --config_path $VITASTOR_CFG kvlist"
-
-# 1000 keys with 100-byte values span several 4 KB blocks
-VALUE=$(printf 'v%.0s' $(seq 1 100))
-(
-    for i in $(seq -f '%03g' 0 999); do
-        echo "set t/a$i $VALUE"
-    done
-    echo "set t/b0 v"
-) | $KV > ./testdata/kv_list_set.log 2>&1
-if [ "$(grep -c '^OK' ./testdata/kv_list_set.log)" -ne 1001 ]; then
-    format_error "Failed to set the keys"
-fi
-
-list_keys()
-{
-    $KV list "$@" | sed 's/ = .*//'
-}
-
-if [ "$(list_keys t/a t/b)" != "$(seq -f 't/a%03g' 0 999)" ]; then
-    format_error "list t/a t/b did not return exactly t/a000..t/a999"
-fi
-if [ "$(list_keys t/a5 t/a6)" != "$(seq -f 't/a%03g' 500 599)" ]; then
-    format_error "list t/a5 t/a6 did not return exactly t/a500..t/a599"
-fi
-if [ -n "$(list_keys t/c t/d)" ]; then
-    format_error "list t/c t/d returned keys"
-fi
-if [ "$($KV dump t/a5 t/a6 | grep -c '^set ')" -ne 100 ]; then
-    format_error "dump t/a5 t/a6 did not return 100 keys"
-fi
-# Without an end, the listing goes on past the range
-if [ "$(list_keys t/a | head -n 1001)" != "$(seq -f 't/a%03g' 0 999; echo t/b0)" ]; then
-    format_error "list t/a did not return t/a000..t/a999, then t/b0"
-fi
-
-format_green OK

tests/test_level_placement.sh

@@ -36,23 +36,4 @@ $ETCDCTL get --prefix /vitastor/pg/config --print-value-only | \
         (. | map_values((. - 1) / 2 | floor) | unique | length) == 6 and
         (. | map_values((. - 1) / 4 | floor) | unique | length) == 3) ] | length) == 32'
 
-# A malformed --level_placement is refused, an empty one removes the rules
-r=0
-$VITASTOR_CLI modify-pool testpool --level_placement rack || r=$?
-if [[ $r != 22 ]]; then
-    format_error "modify-pool --level_placement rack should fail with EINVAL (22), but exited with $r"
-fi
-$ETCDCTL get --print-value-only /vitastor/config/pools | jq -e '.["1"].level_placement == {"rack":"112233"}' || \
-    format_error "level_placement should stay rack=112233 after a refused change"
-$VITASTOR_CLI modify-pool testpool --level_placement ''
-$ETCDCTL get --print-value-only /vitastor/config/pools | jq -e '.["1"] | has("level_placement") | not' || \
-    format_error "modify-pool --level_placement '' should remove level_placement"
-sleep 2
-if grep -q 'configuration is invalid' ./testdata/mon.log; then
-    format_error "Monitor refused the pool configuration without level_placement"
-fi
-$ETCDCTL get --prefix /vitastor/pg/config --print-value-only | \
-    jq -s -e '([ .[0].items["1"] | .[].osd_set | map_values(. | tonumber) | select(
-        (. | map_values((. - 1) / 2 | floor) | unique | length) == 6) ] | length) == 32'
-
 format_green OK

tests/test_ls_tree.sh

@@ -1,40 +0,0 @@
-#!/bin/bash -ex
-
-# Test vitastor-cli ls --tree with filters which leave out parent layers
-
-. `dirname $0`/run_3osds.sh
-
-$VITASTOR_CLI create -s 128M testimg
-$VITASTOR_CLI snap-create testimg@snap1
-$VITASTOR_CLI create --parent testimg@snap1 testclone
-
-$VITASTOR_CLI create-pool testpool2 -s 3 -n 4 --failure_domain osd
-wait_pool_up 30 2 3 4
-$VITASTOR_CLI create --parent testimg@snap1 -p testpool2 testclone2
-
-# First column of each row without the header
-check_tree()
-{
-    local expected=$1
-    shift
-    local rows=$($VITASTOR_CLI ls --tree "$@" | tail -n +2 | sed 's/  .*//' | tr '\n' ';')
-    if [[ "$rows" != "$expected" ]]; then
-        format_error "ls --tree $* shows '$rows', expected '$expected'"
-    fi
-}
-
-$VITASTOR_CLI ls --tree
-
-check_tree 'testimg@snap1;├─ testclone;├─ testclone2;└─ testimg;'
-check_tree 'testimg@snap1;└─ testimg;' 'testimg*'
-# Layers whose parent is filtered out are shown as roots
-check_tree 'testimg;' testimg
-check_tree 'testclone;testimg;' testclone testimg
-check_tree 'testclone;' -n 1
-check_tree 'testclone2;' -p testpool2
-
-if ! $VITASTOR_CLI ls --tree testimg | grep -q ' testimg@snap1 *$'; then
-    format_error "ls --tree testimg should show testimg@snap1 as the parent"
-fi
-
-format_green OK

tests/test_modify_image_resize.sh

@@ -1,28 +0,0 @@
-#!/bin/bash -ex
-
-# Test that modify refuses an invalid --resize value instead of ignoring it
-
-. `dirname $0`/common.sh
-
-wait_etcd
-
-$ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":1,"failure_domain":"osd"}}'
-
-$VITASTOR_CLI create -s 1G --pool testpool testimg
-
-for size in 1.5G 10X abc ''; do
-    r=0
-    $VITASTOR_CLI modify testimg --resize "$size" || r=$?
-    if [[ $r != 22 ]]; then
-        format_error "modify --resize '$size' should fail with EINVAL (22), but exited with $r"
-    fi
-done
-
-$ETCDCTL get --print-value-only /vitastor/config/inode/1/1 | jq -e '.size == 1073741824' || \
-    format_error "Image size should stay 1G after refused resizes"
-
-$VITASTOR_CLI modify testimg --resize 2G
-$ETCDCTL get --print-value-only /vitastor/config/inode/1/1 | jq -e '.size == 2147483648' || \
-    format_error "Image size should be 2G after --resize 2G"
-
-format_green OK

tests/test_modify_pool.sh

@@ -1,53 +0,0 @@
-#!/bin/bash -ex
-
-# Test that modify-pool --name refuses to take the name of another pool
-
-. `dirname $0`/common.sh
-
-wait_etcd
-
-POOL='"scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":1,"failure_domain":"osd"'
-$ETCDCTL put /vitastor/config/pools '{"1":{"name":"pool1",'$POOL'},"2":{"name":"pool2",'$POOL'}}'
-
-for p in pool2 2; do
-    r=0
-    $VITASTOR_CLI modify-pool $p --name pool1 || r=$?
-    if [[ $r != 17 ]]; then
-        format_error "modify-pool $p --name pool1 should fail with EEXIST (17), but exited with $r"
-    fi
-done
-
-names=$($ETCDCTL get --print-value-only /vitastor/config/pools | jq -c '[ .[].name ]')
-if [[ "$names" != '["pool1","pool2"]' ]]; then
-    format_error "Pool names should stay pool1, pool2, but they are $names"
-fi
-
-# A free name and the pool's own name are still accepted
-$VITASTOR_CLI modify-pool pool2 --name pool3
-$VITASTOR_CLI modify-pool pool3 --name pool3 --pg_count 2
-
-cfg=$($ETCDCTL get --print-value-only /vitastor/config/pools | jq -c '[ .[] | [ .name, .pg_count ] ]')
-if [[ "$cfg" != '[["pool1",1],["pool3",2]]' ]]; then
-    format_error "Pools should be pool1 (1 PG) and pool3 (2 PGs), but they are $cfg"
-fi
-
-# Test that create-pool and modify-pool refuse pg_size > 64, which OSDs and clients don't support
-$ETCDCTL put /vitastor/config/pools '{"1":{"name":"testpool","scheme":"replicated","pg_size":2,"pg_minsize":1,"pg_count":1,"failure_domain":"osd"}}'
-
-for args in "create-pool bigpool -s 65 -n 1 --force" "create-pool bigpool --ec 62+3 -n 1 --force" "modify-pool testpool -s 65"; do
-    r=0
-    $VITASTOR_CLI $args || r=$?
-    if [[ $r != 22 ]]; then
-        format_error "$args should fail with EINVAL (22), but exited with $r"
-    fi
-done
-
-$ETCDCTL get --print-value-only /vitastor/config/pools | jq -e 'keys == ["1"] and .["1"].pg_size == 2' || \
-    format_error "Pool configuration should not change after refused commands"
-
-# 64 is still accepted
-$VITASTOR_CLI modify-pool testpool -s 64
-$ETCDCTL get --print-value-only /vitastor/config/pools | jq -e '.["1"].pg_size == 64' || \
-    format_error "modify-pool -s 64 should set pg_size to 64"
-
-format_green OK

tests/test_nfs_list_bounds.sh

@@ -1,103 +0,0 @@
-#!/bin/bash -ex
-# Test that RMDIR does not slow down after many K/V keys were created and deleted,
-# and that RENAME of a directory over an empty directory succeeds.
-#
-# K/V blocks emptied by deletes are never freed. The check that a directory is empty lists
-# its entries, and the listing used to go on past the end of the directory through all
-# empty blocks up to the next existing key. The keys below are created and deleted right
-# after the entries of the newest directories (dD... with 13 hex digits of inode number in
-# pool 1), so the emptied blocks are exactly where these listings ran.
-
-PG_COUNT=16
-. `dirname $0`/run_3osds.sh
-
-DIR_COUNT=50
-KEY_COUNT=10000
-
-$VITASTOR_CLI create -s 10G fsmeta
-$VITASTOR_CLI modify-pool --used-for-app fs:fsmeta testpool
-
-start_nfs()
-{
-    build/src/nfs/vitastor-nfs --config_path $VITASTOR_CFG start --fs fsmeta \
-        --portmap 0 --port 2050 --foreground 1 >>./testdata/nfs.log 2>&1 &
-    NFS_PID=$!
-    for i in $(seq 1 30); do
-        sudo mount localhost:/ ./testdata/nfs -o port=2050,mountport=2050,nfsvers=3,soft,nolock,tcp && return 0
-        sleep 1
-    done
-    format_error "Failed to mount vitastor-nfs"
-}
-
-stop_nfs()
-{
-    sudo umount ./testdata/nfs/
-    kill $NFS_PID
-    wait $NFS_PID || true
-}
-
-# Time RMDIR of $DIR_COUNT empty directories, in milliseconds
-rmdir_ms()
-{
-    local dir=$MNT/$1 start
-    mkdir $dir
-    for i in $(seq 1 $DIR_COUNT); do
-        mkdir $dir/d$i
-    done
-    start=$(date +%s%N)
-    for i in $(seq 1 $DIR_COUNT); do
-        rmdir $dir/d$i
-    done
-    echo $(( ($(date +%s%N) - start) / 1000000 ))
-    rmdir $dir
-}
-
-mkdir -p testdata/nfs
-MNT=$(pwd)/testdata/nfs
-trap "sudo umount -f $MNT"' || true; kill -9 $(jobs -p)' EXIT
-
-start_nfs
-BEFORE=$(rmdir_ms before)
-stop_nfs
-
-# Create and delete keys with 400-byte values after the entries of all directories
-VALUE=$(printf 'x%.0s' $(seq 1 400))
-(
-    for i in $(seq 1 $KEY_COUNT); do
-        echo "set dF100000000000000/k$i $VALUE"
-    done
-    for i in $(seq 1 $KEY_COUNT); do
-        echo "del dF100000000000000/k$i"
-    done
-) | build/src/kv/vitastor-kv --config_path $VITASTOR_CFG fsmeta > ./testdata/kv_churn.log 2>&1
-if [ "$(grep -c '^OK' ./testdata/kv_churn.log)" -ne $((KEY_COUNT*2)) ]; then
-    format_error "Failed to create and delete $KEY_COUNT keys"
-fi
-
-start_nfs
-AFTER=$(rmdir_ms after)
-if [ $AFTER -gt $((BEFORE*2)) ]; then
-    format_error "RMDIR of $DIR_COUNT directories took $AFTER ms after creating and deleting $KEY_COUNT keys, $BEFORE ms before"
-fi
-format_green "RMDIR of $DIR_COUNT directories: $BEFORE ms before, $AFTER ms after creating and deleting $KEY_COUNT keys"
-# READDIR still returns exactly the entries of a directory
-mkdir $MNT/list
-for i in $(seq 1 20); do
-    mkdir $MNT/list/e$i
-done
-if [ "$(ls -f $MNT/list | grep -c '^e')" -ne 20 ]; then
-    format_error "READDIR returned a wrong number of entries"
-fi
-# RENAME of a directory over an empty directory succeeds (the emptiness check used to take
-# the first key after the prefix, which belongs to another directory, for an entry)
-mkdir $MNT/list/e1/x
-if ! mv -T $MNT/list/e1 $MNT/list/e2; then
-    format_error "RENAME of a directory over an empty directory failed"
-fi
-if [ ! -d $MNT/list/e2/x ]; then
-    format_error "RENAME of a directory over an empty directory lost its contents"
-fi
-stop_nfs
-
-
-format_green OK

tests/test_rm.sh

@@ -24,4 +24,132 @@ sz=$(stat -c %s ./testdata/bin/testimg.bin)
 
 [[ "$sz" = 67108864 ]] || format_error "File size is $sz bytes after resize to 64 M"
 
+# test rm-data offset parsing and validation
+
+$VITASTOR_CLI create -s 32M rmimg
+dd if=/dev/urandom of=./testdata/bin/rmimg.bin bs=1M count=32
+$VITASTOR_CLI dd iodepth=4 bs=1M if=./testdata/bin/rmimg.bin oimg=rmimg
+
+check_rmimg()
+{
+    rm -f ./testdata/bin/check.bin
+    $VITASTOR_CLI dd iodepth=4 bs=1M conv=nosparse iimg=rmimg of=./testdata/bin/check.bin
+    cmp ./testdata/bin/check.bin ./testdata/bin/rmimg.bin || format_error "$1"
+}
+
+zero_rmimg()
+{
+    dd if=/dev/zero of=./testdata/bin/rmimg.bin bs=1M seek=$1 count=$2 conv=notrunc
+}
+
+check_rmimg "Image data differs after write"
+
+RM_DATA="$VITASTOR_CLI rm-data --pool 1 --inode $($VITASTOR_CLI ls --json rmimg | jq -r '.[0].inode_num')"
+
+# Bad offsets and empty ranges must fail without removing anything
+while IFS='|' read -r -u 3 args err; do
+    if out=$($RM_DATA $args 2>&1); then
+        format_error "rm-data $args should fail"
+    fi
+    [[ "$out" = "$err" ]] || format_error "rm-data $args failed with an unexpected error: $out"
+    check_rmimg "rm-data $args removed data"
+done 3<<EOF
+--min-offset 8M --max-offset 10X|Invalid --max-offset value: 10X
+--min-offset 8M --max-offset 1.5G|Invalid --max-offset value: 1.5G
+--min-offset 8M --max-offset 0x|Invalid --max-offset value: 0x
+--min-offset 8X --max-offset 16M|Invalid --min-offset value: 8X
+--min-offset 1.5M|Invalid --min-offset value: 1.5M
+--min-offset 8M --max-offset -8M|Invalid --max-offset value: -8M
+--min-offset -1|Invalid --min-offset value: -1
+--min-offset 16777217T|Invalid --min-offset value: 16777217T
+--min-offset 8M --max-offset 16777217T|Invalid --max-offset value: 16777217T
+--min-offset 18446744073709551616|Invalid --min-offset value: 18446744073709551616
+--min-offset 8M --max-offset 0x10000000000000000|Invalid --max-offset value: 0x10000000000000000
+--min-offset 16M --max-offset 8M|--min-offset must be less than --max-offset
+--min-offset 8M --max-offset 8M|--min-offset must be less than --max-offset
+--min-offset 16M --max-offset 0|--max-offset 0 is invalid, omit it to remove data up to the end
+--max-offset 0M|--max-offset 0 is invalid, omit it to remove data up to the end
+EOF
+
+$RM_DATA --min-offset 010M --max-offset 012M
+zero_rmimg 10 2
+check_rmimg "rm-data --min-offset 010M --max-offset 012M removed wrong data"
+
+$RM_DATA --min-offset 8M --max-offset 10M
+zero_rmimg 8 2
+check_rmimg "rm-data --min-offset 8M --max-offset 10M removed wrong data"
+
+$RM_DATA --min-offset $((20*1024*1024)) --max-offset $((24*1024*1024))
+zero_rmimg 20 4
+check_rmimg "rm-data with offsets in bytes removed wrong data"
+
+$RM_DATA --min-offset 0x1a00000 --max-offset 0x1c00000
+zero_rmimg 26 2
+check_rmimg "rm-data with hex offsets removed wrong data"
+
+$RM_DATA --min-offset 30M
+zero_rmimg 30 2
+check_rmimg "rm-data --min-offset 30M removed wrong data"
+
+# test rm-data pool names and hex inode numbers
+
+$VITASTOR_CLI create-pool testpool2 -s 2 -n 4 --failure_domain osd
+wait_pool_up 60 2 2 4
+
+$VITASTOR_CLI create -s 32M -p testpool2 rmimg2
+dd if=/dev/urandom of=./testdata/bin/rmimg2.bin bs=1M count=32
+$VITASTOR_CLI dd iodepth=4 bs=1M if=./testdata/bin/rmimg2.bin oimg=rmimg2
+
+zero_rmimg2()
+{
+    dd if=/dev/zero of=./testdata/bin/rmimg2.bin bs=1M seek=$1 count=$2 conv=notrunc
+}
+
+check_rmimg2()
+{
+    check_rmimg "$1"
+    rm -f ./testdata/bin/check.bin
+    $VITASTOR_CLI dd iodepth=4 bs=1M conv=nosparse iimg=rmimg2 of=./testdata/bin/check.bin
+    cmp ./testdata/bin/check.bin ./testdata/bin/rmimg2.bin || format_error "$1"
+}
+
+check_rmimg2 "Image data differs after write"
+
+INODE1=$($VITASTOR_CLI ls --json rmimg | jq -r '.[0].inode_num')
+INODE2=$($VITASTOR_CLI ls --json rmimg2 | jq -r '.[0].inode_num')
+[[ "$($VITASTOR_CLI ls --json rmimg2 | jq -r '.[0].pool_id')" = 2 ]] || format_error "rmimg2 is not in pool 2"
+
+# Bad inode numbers and unknown pools must fail without removing anything
+while IFS='|' read -r -u 3 args err; do
+    if out=$($VITASTOR_CLI rm-data $args 2>&1); then
+        format_error "rm-data $args should fail"
+    fi
+    [[ "$out" = "$err" ]] || format_error "rm-data $args failed with an unexpected error: $out"
+    check_rmimg2 "rm-data $args removed data"
+done 3<<EOF
+--pool 2 --inode ${INODE2}x|Invalid --inode value: ${INODE2}x
+--pool 2 --inode 0x|Invalid --inode value: 0x
+--pool 2 --inode 0x0x$INODE2|Invalid --inode value: 0x0x$INODE2
+--pool 2 --inode -1|Invalid --inode value: -1
+--pool 70000 --inode $INODE2|Invalid --pool value: 70000
+--pool nosuchpool --inode $(( (1<<48) | INODE1 ))|Pool nosuchpool does not exist
+EOF
+
+$VITASTOR_CLI rm-data --pool testpool2 --inode $INODE2 --min-offset 8M --max-offset 12M
+zero_rmimg2 8 4
+check_rmimg2 "rm-data --pool testpool2 --inode $INODE2 removed wrong data"
+
+$VITASTOR_CLI rm-data --pool 2 --inode $(printf 0x%x $INODE2) --min-offset 16M --max-offset 20M
+zero_rmimg2 16 4
+check_rmimg2 "rm-data --pool 2 --inode $(printf 0x%x $INODE2) removed wrong data"
+
+$VITASTOR_CLI rm-data --inode $(printf 0x%x $(( (2<<48) | INODE2 ))) --min-offset 20M --max-offset 24M
+zero_rmimg2 20 4
+check_rmimg2 "rm-data --inode $(printf 0x%x $(( (2<<48) | INODE2 ))) removed wrong data"
+
+# --pool overrides pool bits of --inode
+$VITASTOR_CLI rm-data --pool testpool --inode $(( (2<<48) | INODE1 )) --min-offset 0 --max-offset 4M
+zero_rmimg 0 4
+check_rmimg2 "rm-data --pool testpool --inode $(( (2<<48) | INODE1 )) removed wrong data"
+
 format_green OK