From 970a1a43534249d422c62dfe699449dc0810aa67 Mon Sep 17 00:00:00 2001 From: Nikolay Samokhvalov Date: Fri, 12 Sep 2025 10:25:14 -0700 Subject: [PATCH 1/6] Fix CLI install script to support aarch64 architecture --- engine/scripts/cli_install.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/engine/scripts/cli_install.sh b/engine/scripts/cli_install.sh index ee46abfb..8dbda161 100644 --- a/engine/scripts/cli_install.sh +++ b/engine/scripts/cli_install.sh @@ -31,7 +31,7 @@ esac arch=$(uname -m) case "$arch" in x86_64*) arch="amd64" ;; - arm64*) arch="arm64" ;; + arm64*|aarch64*) arch="arm64" ;; *) echo "Unsupported architecture: $arch"; exit 1 ;; esac From a24216ba19abb54e67529b014533ce9cd9e76fd5 Mon Sep 17 00:00:00 2001 From: Bogdan Tsechoev Date: Wed, 24 Sep 2025 21:52:48 +0700 Subject: [PATCH 2/6] chore: remove non-functional depshield badge --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 9eada025..0bdc3e76 100644 --- a/README.md +++ b/README.md @@ -27,7 +27,7 @@
Latest release - CI pipeline status Go report DepShield Badge + CI pipeline status Go report Contributor Covenant Community Slack Twitter Follow
From ccb0396a7c7e0bb35faf4c77bfca7644fd05027d Mon Sep 17 00:00:00 2001 From: Artyom Kartasov Date: Fri, 3 Oct 2025 14:02:54 +0000 Subject: [PATCH 3/6] chore: PostgreSQL 18 support --- README.md | 2 +- engine/.gitlab-ci.yml | 5 + .../standard/postgres/default/18/pg_hba.conf | 128 +++ .../18/postgresql.dblab.postgresql.conf | 884 ++++++++++++++++++ engine/test/2.logical_generic.sh | 6 +- engine/test/4.physical_basebackup.sh | 6 +- .../Instance/Configuration/utils/index.ts | 3 +- 7 files changed, 1030 insertions(+), 4 deletions(-) create mode 100644 engine/configs/standard/postgres/default/18/pg_hba.conf create mode 100644 engine/configs/standard/postgres/default/18/postgresql.dblab.postgresql.conf diff --git a/README.md b/README.md index 0bdc3e76..8ae9f89a 100644 --- a/README.md +++ b/README.md @@ -92,7 +92,7 @@ Read more: - Theoretical max of snapshots/clones: 264 ([ZFS](https://en.wikipedia.org/wiki/ZFS), default) - Maximum size of PostgreSQL data directory: 256 quadrillion zebibytes, or 2128 bytes ([ZFS](https://en.wikipedia.org/wiki/ZFS), default) - Support & technologies - - Supported PostgreSQL versions: 9.6–17 + - Supported PostgreSQL versions: 9.6–18 - Thin cloning ([CoW](https://en.wikipedia.org/wiki/Copy-on-write)) technologies: [ZFS](https://en.wikipedia.org/wiki/ZFS) and [LVM](https://en.wikipedia.org/wiki/Logical_Volume_Manager_(Linux)) - UI for manual tasks and API & CLI for automation - Packaged in Docker containers for all components diff --git a/engine/.gitlab-ci.yml b/engine/.gitlab-ci.yml index 7499b869..14b2fa0a 100644 --- a/engine/.gitlab-ci.yml +++ b/engine/.gitlab-ci.yml @@ -477,6 +477,11 @@ bash-test-17: variables: POSTGRES_VERSION: 17 +bash-test-18: + <<: *bash_test + variables: + POSTGRES_VERSION: 18 + integration-test: services: - name: docker:24-dind diff --git a/engine/configs/standard/postgres/default/18/pg_hba.conf b/engine/configs/standard/postgres/default/18/pg_hba.conf new file mode 100644 index 00000000..cccbfad1 --- /dev/null +++ b/engine/configs/standard/postgres/default/18/pg_hba.conf @@ -0,0 +1,128 @@ +# PostgreSQL Client Authentication Configuration File +# =================================================== +# +# Refer to the "Client Authentication" section in the PostgreSQL +# documentation for a complete description of this file. A short +# synopsis follows. +# +# ---------------------- +# Authentication Records +# ---------------------- +# +# This file controls: which hosts are allowed to connect, how clients +# are authenticated, which PostgreSQL user names they can use, which +# databases they can access. Records take one of these forms: +# +# local DATABASE USER METHOD [OPTIONS] +# host DATABASE USER ADDRESS METHOD [OPTIONS] +# hostssl DATABASE USER ADDRESS METHOD [OPTIONS] +# hostnossl DATABASE USER ADDRESS METHOD [OPTIONS] +# hostgssenc DATABASE USER ADDRESS METHOD [OPTIONS] +# hostnogssenc DATABASE USER ADDRESS METHOD [OPTIONS] +# +# (The uppercase items must be replaced by actual values.) +# +# The first field is the connection type: +# - "local" is a Unix-domain socket +# - "host" is a TCP/IP socket (encrypted or not) +# - "hostssl" is a TCP/IP socket that is SSL-encrypted +# - "hostnossl" is a TCP/IP socket that is not SSL-encrypted +# - "hostgssenc" is a TCP/IP socket that is GSSAPI-encrypted +# - "hostnogssenc" is a TCP/IP socket that is not GSSAPI-encrypted +# +# DATABASE can be "all", "sameuser", "samerole", "replication", a +# database name, a regular expression (if it starts with a slash (/)) +# or a comma-separated list thereof. The "all" keyword does not match +# "replication". Access to replication must be enabled in a separate +# record (see example below). +# +# USER can be "all", a user name, a group name prefixed with "+", a +# regular expression (if it starts with a slash (/)) or a comma-separated +# list thereof. In both the DATABASE and USER fields you can also write +# a file name prefixed with "@" to include names from a separate file. +# +# ADDRESS specifies the set of hosts the record matches. It can be a +# host name, or it is made up of an IP address and a CIDR mask that is +# an integer (between 0 and 32 (IPv4) or 128 (IPv6) inclusive) that +# specifies the number of significant bits in the mask. A host name +# that starts with a dot (.) matches a suffix of the actual host name. +# Alternatively, you can write an IP address and netmask in separate +# columns to specify the set of hosts. Instead of a CIDR-address, you +# can write "samehost" to match any of the server's own IP addresses, +# or "samenet" to match any address in any subnet that the server is +# directly connected to. +# +# METHOD can be "trust", "reject", "scram-sha-256", "password", "gss", +# "sspi", "ident", "peer", "pam", "ldap", "radius", "cert" or "oauth". +# Note that "password" sends passwords in clear text; "scram-sha-256" is +# preferred since it sends encrypted passwords. +# +# OPTIONS are a set of options for the authentication in the format +# NAME=VALUE. The available options depend on the different +# authentication methods -- refer to the "Client Authentication" +# section in the documentation for a list of which options are +# available for which authentication methods. +# +# Database and user names containing spaces, commas, quotes and other +# special characters must be quoted. Quoting one of the keywords +# "all", "sameuser", "samerole" or "replication" makes the name lose +# its special character, and just match a database or username with +# that name. +# +# --------------- +# Include Records +# --------------- +# +# This file allows the inclusion of external files or directories holding +# more records, using the following keywords: +# +# include FILE +# include_if_exists FILE +# include_dir DIRECTORY +# +# FILE is the file name to include, and DIR is the directory name containing +# the file(s) to include. Any file in a directory will be loaded if suffixed +# with ".conf". The files of a directory are ordered by name. +# include_if_exists ignores missing files. FILE and DIRECTORY can be +# specified as a relative or an absolute path, and can be double-quoted if +# they contain spaces. +# +# ------------- +# Miscellaneous +# ------------- +# +# This file is read on server startup and when the server receives a +# SIGHUP signal. If you edit the file on a running system, you have to +# SIGHUP the server for the changes to take effect, run "pg_ctl reload", +# or execute "SELECT pg_reload_conf()". +# +# ---------------------------------- +# Put your actual configuration here +# ---------------------------------- +# +# If you want to allow non-local connections, you need to add more +# "host" records. In that case you will also need to make PostgreSQL +# listen on a non-local interface via the listen_addresses +# configuration parameter, or via the -i or -h command line switches. + +# CAUTION: Configuring the system for local "trust" authentication +# allows any local user to connect as any PostgreSQL user, including +# the database superuser. If you do not trust all your local users, +# use another authentication method. + + +# TYPE DATABASE USER ADDRESS METHOD + +# "local" is for Unix domain socket connections only +local all all trust +# IPv4 local connections: +host all all 127.0.0.1/32 trust +# IPv6 local connections: +host all all ::1/128 trust +# Allow replication connections from localhost, by a user with the +# replication privilege. +local replication all trust +host replication all 127.0.0.1/32 trust +host replication all ::1/128 trust + +host all all all scram-sha-256 diff --git a/engine/configs/standard/postgres/default/18/postgresql.dblab.postgresql.conf b/engine/configs/standard/postgres/default/18/postgresql.dblab.postgresql.conf new file mode 100644 index 00000000..425de11c --- /dev/null +++ b/engine/configs/standard/postgres/default/18/postgresql.dblab.postgresql.conf @@ -0,0 +1,884 @@ +# ----------------------------- +# PostgreSQL configuration file +# ----------------------------- +# +# This file consists of lines of the form: +# +# name = value +# +# (The "=" is optional.) Whitespace may be used. Comments are introduced with +# "#" anywhere on a line. The complete list of parameter names and allowed +# values can be found in the PostgreSQL documentation. +# +# The commented-out settings shown in this file represent the default values. +# Re-commenting a setting is NOT sufficient to revert it to the default value; +# you need to reload the server. +# +# This file is read on server startup and when the server receives a SIGHUP +# signal. If you edit the file on a running system, you have to SIGHUP the +# server for the changes to take effect, run "pg_ctl reload", or execute +# "SELECT pg_reload_conf()". Some parameters, which are marked below, +# require a server shutdown and restart to take effect. +# +# Any parameter can also be given as a command-line option to the server, e.g., +# "postgres -c log_connections=all". Some parameters can be changed at run time +# with the "SET" SQL command. +# +# Memory units: B = bytes Time units: us = microseconds +# kB = kilobytes ms = milliseconds +# MB = megabytes s = seconds +# GB = gigabytes min = minutes +# TB = terabytes h = hours +# d = days + + +#------------------------------------------------------------------------------ +# FILE LOCATIONS +#------------------------------------------------------------------------------ + +# The default values of these variables are driven from the -D command-line +# option or PGDATA environment variable, represented here as ConfigDir. + +#data_directory = 'ConfigDir' # use data in another directory + # (change requires restart) +#hba_file = 'ConfigDir/pg_hba.conf' # host-based authentication file + # (change requires restart) +#ident_file = 'ConfigDir/pg_ident.conf' # ident configuration file + # (change requires restart) + +# If external_pid_file is not explicitly set, no extra PID file is written. +#external_pid_file = '' # write an extra PID file + # (change requires restart) + + +#------------------------------------------------------------------------------ +# CONNECTIONS AND AUTHENTICATION +#------------------------------------------------------------------------------ + +# - Connection Settings - + +listen_addresses = '*' + # comma-separated list of addresses; + # defaults to 'localhost'; use '*' for all + # (change requires restart) +#port = 5432 # (change requires restart) +max_connections = 100 # (change requires restart) +#reserved_connections = 0 # (change requires restart) +#superuser_reserved_connections = 3 # (change requires restart) +#unix_socket_directories = '/var/run/postgresql' # comma-separated list of directories + # (change requires restart) +#unix_socket_group = '' # (change requires restart) +#unix_socket_permissions = 0777 # begin with 0 to use octal notation + # (change requires restart) +#bonjour = off # advertise server via Bonjour + # (change requires restart) +#bonjour_name = '' # defaults to the computer name + # (change requires restart) + +# - TCP settings - +# see "man tcp" for details + +#tcp_keepalives_idle = 0 # TCP_KEEPIDLE, in seconds; + # 0 selects the system default +#tcp_keepalives_interval = 0 # TCP_KEEPINTVL, in seconds; + # 0 selects the system default +#tcp_keepalives_count = 0 # TCP_KEEPCNT; + # 0 selects the system default +#tcp_user_timeout = 0 # TCP_USER_TIMEOUT, in milliseconds; + # 0 selects the system default + +#client_connection_check_interval = 0 # time between checks for client + # disconnection while running queries; + # 0 for never + +# - Authentication - + +#authentication_timeout = 1min # 1s-600s +#password_encryption = scram-sha-256 # scram-sha-256 or md5 +#scram_iterations = 4096 +#md5_password_warnings = on +#oauth_validator_libraries = '' # comma-separated list of trusted validator modules + +# GSSAPI using Kerberos +#krb_server_keyfile = 'FILE:${sysconfdir}/krb5.keytab' +#krb_caseins_users = off +#gss_accept_delegation = off + +# - SSL - + +#ssl = off +#ssl_ca_file = '' +#ssl_cert_file = 'server.crt' +#ssl_crl_file = '' +#ssl_crl_dir = '' +#ssl_key_file = 'server.key' +#ssl_ciphers = 'HIGH:MEDIUM:+3DES:!aNULL' # allowed TLSv1.2 ciphers +#ssl_tls13_ciphers = '' # allowed TLSv1.3 cipher suites, blank for default +#ssl_prefer_server_ciphers = on +#ssl_groups = 'X25519:prime256v1' +#ssl_min_protocol_version = 'TLSv1.2' +#ssl_max_protocol_version = '' +#ssl_dh_params_file = '' +#ssl_passphrase_command = '' +#ssl_passphrase_command_supports_reload = off + + +#------------------------------------------------------------------------------ +# RESOURCE USAGE (except WAL) +#------------------------------------------------------------------------------ + +# - Memory - + +shared_buffers = 128MB # min 128kB + # (change requires restart) +#huge_pages = try # on, off, or try + # (change requires restart) +#huge_page_size = 0 # zero for system default + # (change requires restart) +#temp_buffers = 8MB # min 800kB +#max_prepared_transactions = 0 # zero disables the feature + # (change requires restart) +# Caution: it is not advisable to set max_prepared_transactions nonzero unless +# you actively intend to use prepared transactions. +#work_mem = 4MB # min 64kB +#hash_mem_multiplier = 2.0 # 1-1000.0 multiplier on hash table work_mem +#maintenance_work_mem = 64MB # min 64kB +#autovacuum_work_mem = -1 # min 64kB, or -1 to use maintenance_work_mem +#logical_decoding_work_mem = 64MB # min 64kB +#max_stack_depth = 2MB # min 100kB +#shared_memory_type = mmap # the default is the first option + # supported by the operating system: + # mmap + # sysv + # windows + # (change requires restart) +dynamic_shared_memory_type = posix # the default is usually the first option + # supported by the operating system: + # posix + # sysv + # windows + # mmap + # (change requires restart) +#min_dynamic_shared_memory = 0MB # (change requires restart) +#vacuum_buffer_usage_limit = 2MB # size of vacuum and analyze buffer access strategy ring; + # 0 to disable vacuum buffer access strategy; + # range 128kB to 16GB + +# SLRU buffers (change requires restart) +#commit_timestamp_buffers = 0 # memory for pg_commit_ts (0 = auto) +#multixact_offset_buffers = 16 # memory for pg_multixact/offsets +#multixact_member_buffers = 32 # memory for pg_multixact/members +#notify_buffers = 16 # memory for pg_notify +#serializable_buffers = 32 # memory for pg_serial +#subtransaction_buffers = 0 # memory for pg_subtrans (0 = auto) +#transaction_buffers = 0 # memory for pg_xact (0 = auto) + +# - Disk - + +#temp_file_limit = -1 # limits per-process temp file space + # in kilobytes, or -1 for no limit + +#file_copy_method = copy # copy, clone (if supported by OS) + +#max_notify_queue_pages = 1048576 # limits the number of SLRU pages allocated + # for NOTIFY / LISTEN queue + +# - Kernel Resources - + +#max_files_per_process = 1000 # min 64 + # (change requires restart) + +# - Background Writer - + +#bgwriter_delay = 200ms # 10-10000ms between rounds +#bgwriter_lru_maxpages = 100 # max buffers written/round, 0 disables +#bgwriter_lru_multiplier = 2.0 # 0-10.0 multiplier on buffers scanned/round +#bgwriter_flush_after = 512kB # measured in pages, 0 disables + +# - I/O - + +#backend_flush_after = 0 # measured in pages, 0 disables +#effective_io_concurrency = 16 # 1-1000; 0 disables issuing multiple simultaneous IO requests +#maintenance_io_concurrency = 16 # 1-1000; same as effective_io_concurrency +#io_max_combine_limit = 128kB # usually 1-128 blocks (depends on OS) + # (change requires restart) +#io_combine_limit = 128kB # usually 1-128 blocks (depends on OS) + +#io_method = worker # worker, io_uring, sync + # (change requires restart) +#io_max_concurrency = -1 # Max number of IOs that one process + # can execute simultaneously + # -1 sets based on shared_buffers + # (change requires restart) +#io_workers = 3 # 1-32; + +# - Worker Processes - + +#max_worker_processes = 8 # (change requires restart) +#max_parallel_workers_per_gather = 2 # limited by max_parallel_workers +#max_parallel_maintenance_workers = 2 # limited by max_parallel_workers +#max_parallel_workers = 8 # number of max_worker_processes that + # can be used in parallel operations +#parallel_leader_participation = on + + +#------------------------------------------------------------------------------ +# WRITE-AHEAD LOG +#------------------------------------------------------------------------------ + +# - Settings - + +#wal_level = replica # minimal, replica, or logical + # (change requires restart) +#fsync = on # flush data to disk for crash safety + # (turning this off can cause + # unrecoverable data corruption) +#synchronous_commit = on # synchronization level; + # off, local, remote_write, remote_apply, or on +#wal_sync_method = fsync # the default is the first option + # supported by the operating system: + # open_datasync + # fdatasync (default on Linux and FreeBSD) + # fsync + # fsync_writethrough + # open_sync +#full_page_writes = on # recover from partial page writes +#wal_log_hints = off # also do full page writes of non-critical updates + # (change requires restart) +#wal_compression = off # enables compression of full-page writes; + # off, pglz, lz4, zstd, or on +#wal_init_zero = on # zero-fill new WAL files +#wal_recycle = on # recycle WAL files +#wal_buffers = -1 # min 32kB, -1 sets based on shared_buffers + # (change requires restart) +#wal_writer_delay = 200ms # 1-10000 milliseconds +#wal_writer_flush_after = 1MB # measured in pages, 0 disables +#wal_skip_threshold = 2MB + +#commit_delay = 0 # range 0-100000, in microseconds +#commit_siblings = 5 # range 1-1000 + +# - Checkpoints - + +#checkpoint_timeout = 5min # range 30s-1d +#checkpoint_completion_target = 0.9 # checkpoint target duration, 0.0 - 1.0 +#checkpoint_flush_after = 256kB # measured in pages, 0 disables +#checkpoint_warning = 30s # 0 disables +max_wal_size = 1GB +min_wal_size = 80MB + +# - Prefetching during recovery - + +#recovery_prefetch = try # prefetch pages referenced in the WAL? +#wal_decode_buffer_size = 512kB # lookahead window used for prefetching + # (change requires restart) + +# - Archiving - + +#archive_mode = off # enables archiving; off, on, or always + # (change requires restart) +#archive_library = '' # library to use to archive a WAL file + # (empty string indicates archive_command should + # be used) +#archive_command = '' # command to use to archive a WAL file + # placeholders: %p = path of file to archive + # %f = file name only + # e.g. 'test ! -f /mnt/server/archivedir/%f && cp %p /mnt/server/archivedir/%f' +#archive_timeout = 0 # force a WAL file switch after this + # number of seconds; 0 disables + +# - Archive Recovery - + +# These are only used in recovery mode. + +#restore_command = '' # command to use to restore an archived WAL file + # placeholders: %p = path of file to restore + # %f = file name only + # e.g. 'cp /mnt/server/archivedir/%f %p' +#archive_cleanup_command = '' # command to execute at every restartpoint +#recovery_end_command = '' # command to execute at completion of recovery + +# - Recovery Target - + +# Set these only when performing a targeted recovery. + +#recovery_target = '' # 'immediate' to end recovery as soon as a + # consistent state is reached + # (change requires restart) +#recovery_target_name = '' # the named restore point to which recovery will proceed + # (change requires restart) +#recovery_target_time = '' # the time stamp up to which recovery will proceed + # (change requires restart) +#recovery_target_xid = '' # the transaction ID up to which recovery will proceed + # (change requires restart) +#recovery_target_lsn = '' # the WAL LSN up to which recovery will proceed + # (change requires restart) +#recovery_target_inclusive = on # Specifies whether to stop: + # just after the specified recovery target (on) + # just before the recovery target (off) + # (change requires restart) +#recovery_target_timeline = 'latest' # 'current', 'latest', or timeline ID + # (change requires restart) +#recovery_target_action = 'pause' # 'pause', 'promote', 'shutdown' + # (change requires restart) + +# - WAL Summarization - + +#summarize_wal = off # run WAL summarizer process? +#wal_summary_keep_time = '10d' # when to remove old summary files, 0 = never + + +#------------------------------------------------------------------------------ +# REPLICATION +#------------------------------------------------------------------------------ + +# - Sending Servers - + +# Set these on the primary and on any standby that will send replication data. + +#max_wal_senders = 10 # max number of walsender processes + # (change requires restart) +#max_replication_slots = 10 # max number of replication slots + # (change requires restart) +#wal_keep_size = 0 # in megabytes; 0 disables +#max_slot_wal_keep_size = -1 # in megabytes; -1 disables +#idle_replication_slot_timeout = 0 # in seconds; 0 disables +#wal_sender_timeout = 60s # in milliseconds; 0 disables +#track_commit_timestamp = off # collect timestamp of transaction commit + # (change requires restart) + +# - Primary Server - + +# These settings are ignored on a standby server. + +#synchronous_standby_names = '' # standby servers that provide sync rep + # method to choose sync standbys, number of sync standbys, + # and comma-separated list of application_name + # from standby(s); '*' = all +#synchronized_standby_slots = '' # streaming replication standby server slot + # names that logical walsender processes will wait for + +# - Standby Servers - + +# These settings are ignored on a primary server. + +#primary_conninfo = '' # connection string to sending server +#primary_slot_name = '' # replication slot on sending server +#hot_standby = on # "off" disallows queries during recovery + # (change requires restart) +#max_standby_archive_delay = 30s # max delay before canceling queries + # when reading WAL from archive; + # -1 allows indefinite delay +#max_standby_streaming_delay = 30s # max delay before canceling queries + # when reading streaming WAL; + # -1 allows indefinite delay +#wal_receiver_create_temp_slot = off # create temp slot if primary_slot_name + # is not set +#wal_receiver_status_interval = 10s # send replies at least this often + # 0 disables +#hot_standby_feedback = off # send info from standby to prevent + # query conflicts +#wal_receiver_timeout = 60s # time that receiver waits for + # communication from primary + # in milliseconds; 0 disables +#wal_retrieve_retry_interval = 5s # time to wait before retrying to + # retrieve WAL after a failed attempt +#recovery_min_apply_delay = 0 # minimum delay for applying changes during recovery +#sync_replication_slots = off # enables slot synchronization on the physical standby from the primary + +# - Subscribers - + +# These settings are ignored on a publisher. + +#max_active_replication_origins = 10 # max number of active replication origins + # (change requires restart) +#max_logical_replication_workers = 4 # taken from max_worker_processes + # (change requires restart) +#max_sync_workers_per_subscription = 2 # taken from max_logical_replication_workers +#max_parallel_apply_workers_per_subscription = 2 # taken from max_logical_replication_workers + + +#------------------------------------------------------------------------------ +# QUERY TUNING +#------------------------------------------------------------------------------ + +# - Planner Method Configuration - + +#enable_async_append = on +#enable_bitmapscan = on +#enable_gathermerge = on +#enable_hashagg = on +#enable_hashjoin = on +#enable_incremental_sort = on +#enable_indexscan = on +#enable_indexonlyscan = on +#enable_material = on +#enable_memoize = on +#enable_mergejoin = on +#enable_nestloop = on +#enable_parallel_append = on +#enable_parallel_hash = on +#enable_partition_pruning = on +#enable_partitionwise_join = off +#enable_partitionwise_aggregate = off +#enable_presorted_aggregate = on +#enable_seqscan = on +#enable_sort = on +#enable_tidscan = on +#enable_group_by_reordering = on +#enable_distinct_reordering = on +#enable_self_join_elimination = on + +# - Planner Cost Constants - + +#seq_page_cost = 1.0 # measured on an arbitrary scale +#random_page_cost = 4.0 # same scale as above +#cpu_tuple_cost = 0.01 # same scale as above +#cpu_index_tuple_cost = 0.005 # same scale as above +#cpu_operator_cost = 0.0025 # same scale as above +#parallel_setup_cost = 1000.0 # same scale as above +#parallel_tuple_cost = 0.1 # same scale as above +#min_parallel_table_scan_size = 8MB +#min_parallel_index_scan_size = 512kB +#effective_cache_size = 4GB + +#jit_above_cost = 100000 # perform JIT compilation if available + # and query more expensive than this; + # -1 disables +#jit_inline_above_cost = 500000 # inline small functions if query is + # more expensive than this; -1 disables +#jit_optimize_above_cost = 500000 # use expensive JIT optimizations if + # query is more expensive than this; + # -1 disables + +# - Genetic Query Optimizer - + +#geqo = on +#geqo_threshold = 12 +#geqo_effort = 5 # range 1-10 +#geqo_pool_size = 0 # selects default based on effort +#geqo_generations = 0 # selects default based on effort +#geqo_selection_bias = 2.0 # range 1.5-2.0 +#geqo_seed = 0.0 # range 0.0-1.0 + +# - Other Planner Options - + +#default_statistics_target = 100 # range 1-10000 +#constraint_exclusion = partition # on, off, or partition +#cursor_tuple_fraction = 0.1 # range 0.0-1.0 +#from_collapse_limit = 8 +#jit = on # allow JIT compilation +#join_collapse_limit = 8 # 1 disables collapsing of explicit + # JOIN clauses +#plan_cache_mode = auto # auto, force_generic_plan or + # force_custom_plan +#recursive_worktable_factor = 10.0 # range 0.001-1000000 + + +#------------------------------------------------------------------------------ +# REPORTING AND LOGGING +#------------------------------------------------------------------------------ + +# - Where to Log - + +#log_destination = 'stderr' # Valid values are combinations of + # stderr, csvlog, jsonlog, syslog, and + # eventlog, depending on platform. + # csvlog and jsonlog require + # logging_collector to be on. + +# This is used when logging to stderr: +#logging_collector = off # Enable capturing of stderr, jsonlog, + # and csvlog into log files. Required + # to be on for csvlogs and jsonlogs. + # (change requires restart) + +# These are only used if logging_collector is on: +#log_directory = 'log' # directory where log files are written, + # can be absolute or relative to PGDATA +#log_filename = 'postgresql-%Y-%m-%d_%H%M%S.log' # log file name pattern, + # can include strftime() escapes +#log_file_mode = 0600 # creation mode for log files, + # begin with 0 to use octal notation +#log_rotation_age = 1d # Automatic rotation of logfiles will + # happen after that time. 0 disables. +#log_rotation_size = 10MB # Automatic rotation of logfiles will + # happen after that much log output. + # 0 disables. +#log_truncate_on_rotation = off # If on, an existing log file with the + # same name as the new log file will be + # truncated rather than appended to. + # But such truncation only occurs on + # time-driven rotation, not on restarts + # or size-driven rotation. Default is + # off, meaning append to existing files + # in all cases. + +# These are relevant when logging to syslog: +#syslog_facility = 'LOCAL0' +#syslog_ident = 'postgres' +#syslog_sequence_numbers = on +#syslog_split_messages = on + +# This is only relevant when logging to eventlog (Windows): +# (change requires restart) +#event_source = 'PostgreSQL' + +# - When to Log - + +#log_min_messages = warning # values in order of decreasing detail: + # debug5 + # debug4 + # debug3 + # debug2 + # debug1 + # info + # notice + # warning + # error + # log + # fatal + # panic + +#log_min_error_statement = error # values in order of decreasing detail: + # debug5 + # debug4 + # debug3 + # debug2 + # debug1 + # info + # notice + # warning + # error + # log + # fatal + # panic (effectively off) + +#log_min_duration_statement = -1 # -1 is disabled, 0 logs all statements + # and their durations, > 0 logs only + # statements running at least this number + # of milliseconds + +#log_min_duration_sample = -1 # -1 is disabled, 0 logs a sample of statements + # and their durations, > 0 logs only a sample of + # statements running at least this number + # of milliseconds; + # sample fraction is determined by log_statement_sample_rate + +#log_statement_sample_rate = 1.0 # fraction of logged statements exceeding + # log_min_duration_sample to be logged; + # 1.0 logs all such statements, 0.0 never logs + + +#log_transaction_sample_rate = 0.0 # fraction of transactions whose statements + # are logged regardless of their duration; 1.0 logs all + # statements from all transactions, 0.0 never logs + +#log_startup_progress_interval = 10s # Time between progress updates for + # long-running startup operations. + # 0 disables the feature, > 0 indicates + # the interval in milliseconds. + +# - What to Log - + +#debug_print_parse = off +#debug_print_rewritten = off +#debug_print_plan = off +#debug_pretty_print = on +#log_autovacuum_min_duration = 10min # log autovacuum activity; + # -1 disables, 0 logs all actions and + # their durations, > 0 logs only + # actions running at least this number + # of milliseconds. +#log_checkpoints = on +#log_connections = '' # log aspects of connection setup + # options include receipt, authentication, authorization, + # setup_durations, and all to log all of these aspects +#log_disconnections = off +#log_duration = off # log statement duration +#log_error_verbosity = default # terse, default, or verbose messages +#log_hostname = off +#log_line_prefix = '%m [%p] ' # special values: + # %a = application name + # %u = user name + # %d = database name + # %r = remote host and port + # %h = remote host + # %L = local address + # %b = backend type + # %p = process ID + # %P = process ID of parallel group leader + # %t = timestamp without milliseconds + # %m = timestamp with milliseconds + # %n = timestamp with milliseconds (as a Unix epoch) + # %Q = query ID (0 if none or not computed) + # %i = command tag + # %e = SQL state + # %c = session ID + # %l = session line number + # %s = session start timestamp + # %v = virtual transaction ID + # %x = transaction ID (0 if none) + # %q = stop here in non-session + # processes + # %% = '%' + # e.g. '<%u%%%d> ' +#log_lock_waits = off # log lock waits >= deadlock_timeout +#log_lock_failures = off # log lock failures +#log_recovery_conflict_waits = off # log standby recovery conflict waits + # >= deadlock_timeout +#log_parameter_max_length = -1 # when logging statements, limit logged + # bind-parameter values to N bytes; + # -1 means print in full, 0 disables +#log_parameter_max_length_on_error = 0 # when logging an error, limit logged + # bind-parameter values to N bytes; + # -1 means print in full, 0 disables +#log_statement = 'none' # none, ddl, mod, all +#log_replication_commands = off +#log_temp_files = -1 # log temporary files equal or larger + # than the specified size in kilobytes; + # -1 disables, 0 logs all temp files +log_timezone = 'Etc/UTC' + +# - Process Title - + +#cluster_name = '' # added to process titles if nonempty + # (change requires restart) +#update_process_title = on + + +#------------------------------------------------------------------------------ +# STATISTICS +#------------------------------------------------------------------------------ + +# - Cumulative Query and Index Statistics - + +#track_activities = on +#track_activity_query_size = 1024 # (change requires restart) +#track_counts = on +#track_cost_delay_timing = off +#track_io_timing = off +#track_wal_io_timing = off +#track_functions = none # none, pl, all +#stats_fetch_consistency = cache # cache, none, snapshot + + +# - Monitoring - + +#compute_query_id = auto +#log_statement_stats = off +#log_parser_stats = off +#log_planner_stats = off +#log_executor_stats = off + + +#------------------------------------------------------------------------------ +# VACUUMING +#------------------------------------------------------------------------------ + +# - Automatic Vacuuming - + +#autovacuum = on # Enable autovacuum subprocess? 'on' + # requires track_counts to also be on. +autovacuum_worker_slots = 16 # autovacuum worker slots to allocate + # (change requires restart) +#autovacuum_max_workers = 3 # max number of autovacuum subprocesses +#autovacuum_naptime = 1min # time between autovacuum runs +#autovacuum_vacuum_threshold = 50 # min number of row updates before + # vacuum +#autovacuum_vacuum_insert_threshold = 1000 # min number of row inserts + # before vacuum; -1 disables insert + # vacuums +#autovacuum_analyze_threshold = 50 # min number of row updates before + # analyze +#autovacuum_vacuum_scale_factor = 0.2 # fraction of table size before vacuum +#autovacuum_vacuum_insert_scale_factor = 0.2 # fraction of unfrozen pages + # before insert vacuum +#autovacuum_analyze_scale_factor = 0.1 # fraction of table size before analyze +#autovacuum_vacuum_max_threshold = 100000000 # max number of row updates + # before vacuum; -1 disables max + # threshold +#autovacuum_freeze_max_age = 200000000 # maximum XID age before forced vacuum + # (change requires restart) +#autovacuum_multixact_freeze_max_age = 400000000 # maximum multixact age + # before forced vacuum + # (change requires restart) +#autovacuum_vacuum_cost_delay = 2ms # default vacuum cost delay for + # autovacuum, in milliseconds; + # -1 means use vacuum_cost_delay +#autovacuum_vacuum_cost_limit = -1 # default vacuum cost limit for + # autovacuum, -1 means use + # vacuum_cost_limit + +# - Cost-Based Vacuum Delay - + +#vacuum_cost_delay = 0 # 0-100 milliseconds (0 disables) +#vacuum_cost_page_hit = 1 # 0-10000 credits +#vacuum_cost_page_miss = 2 # 0-10000 credits +#vacuum_cost_page_dirty = 20 # 0-10000 credits +#vacuum_cost_limit = 200 # 1-10000 credits + +# - Default Behavior - + +#vacuum_truncate = on # enable truncation after vacuum + +# - Freezing - + +#vacuum_freeze_table_age = 150000000 +#vacuum_freeze_min_age = 50000000 +#vacuum_failsafe_age = 1600000000 +#vacuum_multixact_freeze_table_age = 150000000 +#vacuum_multixact_freeze_min_age = 5000000 +#vacuum_multixact_failsafe_age = 1600000000 +#vacuum_max_eager_freeze_failure_rate = 0.03 # 0 disables eager scanning + +#------------------------------------------------------------------------------ +# CLIENT CONNECTION DEFAULTS +#------------------------------------------------------------------------------ + +# - Statement Behavior - + +#client_min_messages = notice # values in order of decreasing detail: + # debug5 + # debug4 + # debug3 + # debug2 + # debug1 + # log + # notice + # warning + # error +#search_path = '"$user", public' # schema names +#row_security = on +#default_table_access_method = 'heap' +#default_tablespace = '' # a tablespace name, '' uses the default +#default_toast_compression = 'pglz' # 'pglz' or 'lz4' +#temp_tablespaces = '' # a list of tablespace names, '' uses + # only default tablespace +#check_function_bodies = on +#default_transaction_isolation = 'read committed' +#default_transaction_read_only = off +#default_transaction_deferrable = off +#session_replication_role = 'origin' +#statement_timeout = 0 # in milliseconds, 0 is disabled +#transaction_timeout = 0 # in milliseconds, 0 is disabled +#lock_timeout = 0 # in milliseconds, 0 is disabled +#idle_in_transaction_session_timeout = 0 # in milliseconds, 0 is disabled +#idle_session_timeout = 0 # in milliseconds, 0 is disabled +#bytea_output = 'hex' # hex, escape +#xmlbinary = 'base64' +#xmloption = 'content' +#gin_pending_list_limit = 4MB +#createrole_self_grant = '' # set and/or inherit +#event_triggers = on + +# - Locale and Formatting - + +datestyle = 'iso, mdy' +#intervalstyle = 'postgres' +timezone = 'Etc/UTC' +#timezone_abbreviations = 'Default' # Select the set of available time zone + # abbreviations. Currently, there are + # Default + # Australia (historical usage) + # India + # You can create your own file in + # share/timezonesets/. +#extra_float_digits = 1 # min -15, max 3; any value >0 actually + # selects precise output mode +#client_encoding = sql_ascii # actually, defaults to database + # encoding + +# These settings are initialized by initdb, but they can be changed. +lc_messages = 'en_US.utf8' # locale for system error message + # strings +lc_monetary = 'en_US.utf8' # locale for monetary formatting +lc_numeric = 'en_US.utf8' # locale for number formatting +lc_time = 'en_US.utf8' # locale for time formatting + +#icu_validation_level = warning # report ICU locale validation + # errors at the given level + +# default configuration for text search +default_text_search_config = 'pg_catalog.english' + +# - Shared Library Preloading - + +#local_preload_libraries = '' +#session_preload_libraries = '' +#shared_preload_libraries = '' # (change requires restart) +#jit_provider = 'llvmjit' # JIT library to use + +# - Other Defaults - + +#dynamic_library_path = '$libdir' +#extension_control_path = '$system' +#gin_fuzzy_search_limit = 0 + + +#------------------------------------------------------------------------------ +# LOCK MANAGEMENT +#------------------------------------------------------------------------------ + +#deadlock_timeout = 1s +#max_locks_per_transaction = 64 # min 10 + # (change requires restart) +#max_pred_locks_per_transaction = 64 # min 10 + # (change requires restart) +#max_pred_locks_per_relation = -2 # negative values mean + # (max_pred_locks_per_transaction + # / -max_pred_locks_per_relation) - 1 +#max_pred_locks_per_page = 2 # min 0 + + +#------------------------------------------------------------------------------ +# VERSION AND PLATFORM COMPATIBILITY +#------------------------------------------------------------------------------ + +# - Previous PostgreSQL Versions - + +#array_nulls = on +#backslash_quote = safe_encoding # on, off, or safe_encoding +#escape_string_warning = on +#lo_compat_privileges = off +#quote_all_identifiers = off +#standard_conforming_strings = on +#synchronize_seqscans = on + +# - Other Platforms and Clients - + +#transform_null_equals = off +#allow_alter_system = on + + +#------------------------------------------------------------------------------ +# ERROR HANDLING +#------------------------------------------------------------------------------ + +#exit_on_error = off # terminate session on any error? +#restart_after_crash = on # reinitialize after backend crash? +#data_sync_retry = off # retry or panic on failure to fsync + # data? + # (change requires restart) +#recovery_init_sync_method = fsync # fsync, syncfs (Linux 5.8+) + + +#------------------------------------------------------------------------------ +# CONFIG FILE INCLUDES +#------------------------------------------------------------------------------ + +# These options allow settings to be loaded from files other than the +# default postgresql.conf. Note that these are directives, not variable +# assignments, so they can usefully be given more than once. + +#include_dir = '...' # include files ending in '.conf' from + # a directory, e.g., 'conf.d' +#include_if_exists = '...' # include file only if it exists +#include = '...' # include file + + +#------------------------------------------------------------------------------ +# CUSTOMIZED OPTIONS +#------------------------------------------------------------------------------ + +# Add settings for extensions here diff --git a/engine/test/2.logical_generic.sh b/engine/test/2.logical_generic.sh index 93fdb268..fb21a94b 100644 --- a/engine/test/2.logical_generic.sh +++ b/engine/test/2.logical_generic.sh @@ -19,6 +19,10 @@ export DLE_SERVER_PORT=${DLE_SERVER_PORT:-12345} export DLE_PORT_POOL_FROM=${DLE_PORT_POOL_FROM:-9000} export DLE_PORT_POOL_TO=${DLE_PORT_POOL_TO:-9099} +if [ "${POSTGRES_VERSION}" = "18" ]; then + EXTENDED_IMAGE_TAG="" +fi + DIR=${0%/*} if [[ "${SOURCE_HOST}" = "172.17.0.1" ]]; then @@ -103,7 +107,7 @@ yq eval -i ' .provision.portPool.to = env(DLE_PORT_POOL_TO) | .retrieval.spec.logicalDump.options.dumpLocation = env(DLE_TEST_MOUNT_DIR) + "/" + env(DLE_TEST_POOL_NAME) + "/dump" | .retrieval.spec.logicalRestore.options.dumpLocation = env(DLE_TEST_MOUNT_DIR) + "/" + env(DLE_TEST_POOL_NAME) + "/dump" | - .databaseContainer.dockerImage = "registry.gitlab.com/postgres-ai/custom-images/extended-postgres:" + strenv(POSTGRES_VERSION) + env(EXTENDED_IMAGE_TAG) + .databaseContainer.dockerImage = "registry.gitlab.com/postgres-ai/custom-images/extended-postgres:" + strenv(POSTGRES_VERSION) + strenv(EXTENDED_IMAGE_TAG) ' "${configDir}/server.yml" SHARED_PRELOAD_LIBRARIES="pg_stat_statements, auto_explain, pgaudit, logerrors, pg_stat_kcache" diff --git a/engine/test/4.physical_basebackup.sh b/engine/test/4.physical_basebackup.sh index eb562197..d7d1e001 100644 --- a/engine/test/4.physical_basebackup.sh +++ b/engine/test/4.physical_basebackup.sh @@ -18,6 +18,10 @@ export DLE_SERVER_PORT=${DLE_SERVER_PORT:-12345} export DLE_PORT_POOL_FROM=${DLE_PORT_POOL_FROM:-9000} export DLE_PORT_POOL_TO=${DLE_PORT_POOL_TO:-9099} +if [ "${POSTGRES_VERSION}" = "18" ]; then + EXTENDED_IMAGE_TAG="" +fi + DIR=${0%/*} if [[ "${SOURCE_HOST}" = "172.17.0.1" ]]; then @@ -115,7 +119,7 @@ yq eval -i ' .poolManager.mountDir = env(DLE_TEST_MOUNT_DIR) | .provision.portPool.from = env(DLE_PORT_POOL_FROM) | .provision.portPool.to = env(DLE_PORT_POOL_TO) | - .databaseContainer.dockerImage = "registry.gitlab.com/postgres-ai/custom-images/extended-postgres:" + strenv(POSTGRES_VERSION) + env(EXTENDED_IMAGE_TAG) | + .databaseContainer.dockerImage = "registry.gitlab.com/postgres-ai/custom-images/extended-postgres:" + strenv(POSTGRES_VERSION) + strenv(EXTENDED_IMAGE_TAG) | .retrieval.spec.physicalRestore.options.envs.PGUSER = strenv(SOURCE_USERNAME) | .retrieval.spec.physicalRestore.options.envs.PGPASSWORD = strenv(SOURCE_PASSWORD) | .retrieval.spec.physicalRestore.options.envs.PGHOST = strenv(SOURCE_HOST) | diff --git a/ui/packages/shared/pages/Instance/Configuration/utils/index.ts b/ui/packages/shared/pages/Instance/Configuration/utils/index.ts index 51dd9c6b..1447d129 100644 --- a/ui/packages/shared/pages/Instance/Configuration/utils/index.ts +++ b/ui/packages/shared/pages/Instance/Configuration/utils/index.ts @@ -19,6 +19,7 @@ const dockerImagesConfig = { '15': ['0.5.3', '0.5.2', '0.5.1'], '16': ['0.5.3', '0.5.2', '0.5.1'], '17': ['0.5.3', '0.5.2', '0.5.1'], + '18': ['0.6.1'], } export type FormValuesKey = keyof FormValues @@ -170,7 +171,7 @@ export const createFallbackDockerImage = ( dockerPath: string, dockerTag: string, ): DockerImage => { - const majorVersion = getImageMajorVersion(dockerPath) || '17' // Default to 17 if version can't be extracted + const majorVersion = getImageMajorVersion(dockerPath) || '18' // Default to 18 if version can't be extracted return { package_group: 'postgresai', From 28c2e6de4728737a2200ec514efff8ed8bc6268c Mon Sep 17 00:00:00 2001 From: Artyom Kartasov Date: Thu, 9 Oct 2025 15:00:54 +0000 Subject: [PATCH 4/6] fix: improve performance of the dblab clone list command (#647) --- engine/.gitlab-ci.yml | 4 +- engine/Dockerfile.dblab-server-debug | 2 +- engine/Makefile | 2 +- engine/go.mod | 2 +- engine/go.sum | 2 - engine/internal/cloning/base.go | 29 ++- engine/internal/provision/mode_local.go | 48 +++- engine/internal/provision/mode_local_test.go | 12 + engine/internal/provision/pool/manager.go | 5 +- .../internal/provision/resources/resources.go | 6 + .../provision/thinclones/lvm/lvmanager.go | 19 ++ .../provision/thinclones/zfs/branching.go | 16 -- .../internal/provision/thinclones/zfs/zfs.go | 215 +++++++++++++++++- .../provision/thinclones/zfs/zfs_test.go | 118 ++++++++++ .../engine/postgres/snapshot/physical.go | 3 +- engine/internal/srv/branch.go | 41 ++-- engine/internal/srv/routes.go | 84 ++++++- engine/pkg/models/clone.go | 21 +- engine/pkg/util/branching/branching.go | 9 + 19 files changed, 559 insertions(+), 79 deletions(-) diff --git a/engine/.gitlab-ci.yml b/engine/.gitlab-ci.yml index 14b2fa0a..862deb7a 100644 --- a/engine/.gitlab-ci.yml +++ b/engine/.gitlab-ci.yml @@ -1,6 +1,6 @@ default: image: - name: golang:1.23 + name: golang:1.24 pull_policy: if-not-present stages: @@ -58,7 +58,7 @@ lint: build-binary-alpine: <<: *only_engine image: - name: golang:1.23-alpine + name: golang:1.24-alpine pull_policy: if-not-present stage: build-binary artifacts: diff --git a/engine/Dockerfile.dblab-server-debug b/engine/Dockerfile.dblab-server-debug index af6b1f17..dd8b13c7 100644 --- a/engine/Dockerfile.dblab-server-debug +++ b/engine/Dockerfile.dblab-server-debug @@ -1,7 +1,7 @@ # How to start a container: https://postgres.ai/docs/how-to-guides/administration/engine-manage # Compile stage -FROM golang:1.23 AS build-env +FROM golang:1.24 AS build-env # Build Delve RUN go install github.com/go-delve/delve/cmd/dlv@latest diff --git a/engine/Makefile b/engine/Makefile index 84bf96de..ffb2edf0 100644 --- a/engine/Makefile +++ b/engine/Makefile @@ -34,7 +34,7 @@ help: ## Display the help message all: clean build ## Build all binary components of the project install-lint: ## Install the linter to $GOPATH/bin which is expected to be in $PATH - curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(go env GOPATH)/bin v1.61.0 + curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(go env GOPATH)/bin v1.64.8 run-lint: ## Run linters golangci-lint run diff --git a/engine/go.mod b/engine/go.mod index e851a499..d9b4c811 100644 --- a/engine/go.mod +++ b/engine/go.mod @@ -1,6 +1,6 @@ module gitlab.com/postgres-ai/database-lab/v3 -go 1.23.12 +go 1.24.7 require ( github.com/AlekSi/pointer v1.2.0 diff --git a/engine/go.sum b/engine/go.sum index 8399d633..2a847cb5 100644 --- a/engine/go.sum +++ b/engine/go.sum @@ -310,8 +310,6 @@ github.com/gogo/protobuf v1.3.0/go.mod h1:SlYgWuQ5SjCEi6WLHjHCa1yvBfUnHcTbrrZtXP github.com/gogo/protobuf v1.3.1/go.mod h1:SlYgWuQ5SjCEi6WLHjHCa1yvBfUnHcTbrrZtXPKa29o= github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q= github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q= -github.com/golang-jwt/jwt/v4 v4.5.1 h1:JdqV9zKUdtaa9gdPlywC3aeoEsR681PlKC+4F5gQgeo= -github.com/golang-jwt/jwt/v4 v4.5.1/go.mod h1:m21LjoU+eqJr34lmDMbreY2eSTRJ1cv77w39/MY0Ch0= github.com/golang-jwt/jwt/v4 v4.5.2 h1:YtQM7lnr8iZ+j5q71MGKkNw9Mn7AjHM68uc9g5fXeUI= github.com/golang-jwt/jwt/v4 v4.5.2/go.mod h1:m21LjoU+eqJr34lmDMbreY2eSTRJ1cv77w39/MY0Ch0= github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q= diff --git a/engine/internal/cloning/base.go b/engine/internal/cloning/base.go index be3e2b20..952a9436 100644 --- a/engine/internal/cloning/base.go +++ b/engine/internal/cloning/base.go @@ -435,8 +435,10 @@ func (c *Base) refreshCloneMetadata(w *CloneWrapper) { return } + c.cloneMutex.Lock() w.Clone.Metadata.CloneDiffSize = sessionState.CloneDiffSize w.Clone.Metadata.LogicalSize = sessionState.LogicalReferenced + c.cloneMutex.Unlock() } // UpdateClone updates clone. @@ -527,11 +529,6 @@ func (c *Base) ResetClone(cloneID string, resetOptions types.ResetCloneRequest) log.Warn("clone has dependent snapshots", cloneID) c.cloneMutex.Lock() w.Clone.Revision++ - w.Clone.HasDependent = true - c.cloneMutex.Unlock() - } else { - c.cloneMutex.Lock() - w.Clone.HasDependent = false c.cloneMutex.Unlock() } @@ -630,6 +627,8 @@ func (c *Base) GetClones() []*models.Clone { clones := make([]*models.Clone, 0, c.lenClones()) c.cloneMutex.RLock() + requestsByPool := make(map[string][]resources.SessionStateRequest) + for _, cloneWrapper := range c.clones { if cloneWrapper.Clone.Snapshot != nil { snapshot, err := c.getSnapshotByID(cloneWrapper.Clone.Snapshot.ID) @@ -642,12 +641,30 @@ func (c *Base) GetClones() []*models.Clone { } } - c.refreshCloneMetadata(cloneWrapper) + if cloneWrapper.Session != nil && cloneWrapper.Clone != nil { + pool := cloneWrapper.Session.Pool + requestsByPool[pool] = append(requestsByPool[pool], resources.SessionStateRequest{ + CloneID: cloneWrapper.Clone.ID, + Branch: cloneWrapper.Clone.Branch, + }) + } clones = append(clones, cloneWrapper.Clone) } c.cloneMutex.RUnlock() + sessionStates, err := c.provision.GetBatchSessionState(requestsByPool) + if err != nil { + log.Err("failed to get batch session states: ", err) + } + + for _, clone := range clones { + if state, ok := sessionStates[clone.ID]; ok { + clone.Metadata.CloneDiffSize = state.CloneDiffSize + clone.Metadata.LogicalSize = state.LogicalReferenced + } + } + sort.Slice(clones, func(i, j int) bool { return clones[i].CreatedAt.After(clones[j].CreatedAt.Time) }) diff --git a/engine/internal/provision/mode_local.go b/engine/internal/provision/mode_local.go index 1d9e4958..e457e859 100644 --- a/engine/internal/provision/mode_local.go +++ b/engine/internal/provision/mode_local.go @@ -274,10 +274,8 @@ func (p *Provisioner) ResetSession(session *resources.Session, clone *models.Clo return nil, errors.Wrap(err, "failed to stop container") } - if clone.Revision == branching.DefaultRevision || !clone.HasDependent { - if err = fsm.DestroyClone(clone.Branch, name, clone.Revision); err != nil { - return nil, errors.Wrap(err, "failed to destroy clone") - } + if err = fsm.DestroyClone(clone.Branch, name, clone.Revision); err != nil { + return nil, errors.Wrap(err, "failed to destroy clone") } if err = newFSManager.CreateClone(clone.Branch, name, snapshot.ID, clone.Revision); err != nil { @@ -300,9 +298,14 @@ func (p *Provisioner) ResetSession(session *resources.Session, clone *models.Clo } snapshotModel := &models.Snapshot{ - ID: snapshot.ID, - CreatedAt: models.NewLocalTime(snapshot.CreatedAt), - DataStateAt: models.NewLocalTime(snapshot.DataStateAt), + ID: snapshot.ID, + CreatedAt: models.NewLocalTime(snapshot.CreatedAt), + DataStateAt: models.NewLocalTime(snapshot.DataStateAt), + PhysicalSize: snapshot.Used, + LogicalSize: snapshot.LogicalReferenced, + Pool: snapshot.Pool, + Branch: snapshot.Branch, + Message: snapshot.Message, } return snapshotModel, nil @@ -335,6 +338,31 @@ func (p *Provisioner) GetSessionState(s *resources.Session, branch, cloneID stri return fsm.GetSessionState(branch, cloneID) } +// GetBatchSessionState retrieves session states for multiple clones efficiently. +func (p *Provisioner) GetBatchSessionState(batch map[string][]resources.SessionStateRequest) (map[string]resources.SessionState, error) { + batchResults := make(map[string]resources.SessionState) + + for poolName, reqs := range batch { + fsm, err := p.pm.GetFSManager(poolName) + if err != nil { + log.Err(fmt.Sprintf("failed to find filesystem manager for pool %s: %v", poolName, err)) + continue + } + + results, err := fsm.GetBatchSessionState(reqs) + if err != nil { + log.Err(fmt.Sprintf("failed to get batch session state for pool %s: %v", poolName, err)) + continue + } + + for cloneID, state := range results { + batchResults[cloneID] = state + } + } + + return batchResults, nil +} + // GetPoolEntryList provides an ordered list of available pools. func (p *Provisioner) GetPoolEntryList() []models.PoolEntry { fsmList := p.pm.GetFSManagerOrderedList() @@ -604,10 +632,8 @@ func (p *Provisioner) CleanupCloneDataset(clone *models.Clone, pool string) erro return nil } - if clone.Revision == branching.DefaultRevision && !clone.HasDependent { - if err := fsm.DestroyDataset(branching.CloneDataset(pool, clone.Branch, clone.ID)); err != nil { - return fmt.Errorf("failed to destroy clone dataset: %w", err) - } + if err = fsm.DestroyClone(clone.Branch, clone.ID, clone.Revision); err != nil { + return fmt.Errorf("failed to destroy clone: %w", err) } return nil diff --git a/engine/internal/provision/mode_local_test.go b/engine/internal/provision/mode_local_test.go index 72c70e13..9183ec2a 100644 --- a/engine/internal/provision/mode_local_test.go +++ b/engine/internal/provision/mode_local_test.go @@ -102,6 +102,10 @@ func (m mockFSManager) GetSessionState(_, _ string) (*resources.SessionState, er return nil, nil } +func (m mockFSManager) GetBatchSessionState(_ []resources.SessionStateRequest) (map[string]resources.SessionState, error) { + return make(map[string]resources.SessionState), nil +} + func (m mockFSManager) GetFilesystemState() (models.FileSystem, error) { return models.FileSystem{Mode: "zfs"}, nil } @@ -214,6 +218,14 @@ func (m mockFSManager) KeepRelation(_ string) error { return nil } +func (m mockFSManager) GetDatasetOrigins(_ string) []string { + return nil +} + +func (m mockFSManager) GetActiveDatasets(_ string) ([]string, error) { + return nil, nil +} + func TestBuildPoolEntry(t *testing.T) { testCases := []struct { pool *resources.Pool diff --git a/engine/internal/provision/pool/manager.go b/engine/internal/provision/pool/manager.go index 1c63a6a2..d07fa242 100644 --- a/engine/internal/provision/pool/manager.go +++ b/engine/internal/provision/pool/manager.go @@ -39,6 +39,7 @@ type Cloner interface { // StateReporter describes methods of state reporting. type StateReporter interface { GetSessionState(branch, name string) (*resources.SessionState, error) + GetBatchSessionState(requests []resources.SessionStateRequest) (map[string]resources.SessionState, error) GetFilesystemState() (models.FileSystem, error) } @@ -57,7 +58,7 @@ type Branching interface { VerifyBranchMetadata() error CreateDataset(datasetName string) error CreateBranch(branchName, snapshotID string) error - DestroyDataset(branchName string) (err error) + DestroyDataset(dataset string) (err error) ListBranches() (map[string]string, error) ListAllBranches(filterPools []string) ([]models.BranchEntity, error) GetRepo() (*models.Repo, error) @@ -78,6 +79,8 @@ type Branching interface { Reset(snapshotID string, options thinclones.ResetOptions) error HasDependentEntity(snapshotName string) ([]string, error) KeepRelation(snapshotName string) error + GetDatasetOrigins(snapshotName string) []string + GetActiveDatasets(dataset string) ([]string, error) } // Pooler describes methods for Pool providing. diff --git a/engine/internal/provision/resources/resources.go b/engine/internal/provision/resources/resources.go index 1a5538ee..5892bb76 100644 --- a/engine/internal/provision/resources/resources.go +++ b/engine/internal/provision/resources/resources.go @@ -48,3 +48,9 @@ type SessionState struct { CloneDiffSize uint64 LogicalReferenced uint64 } + +// SessionStateRequest defines a request for batch session state retrieval. +type SessionStateRequest struct { + CloneID string + Branch string +} diff --git a/engine/internal/provision/thinclones/lvm/lvmanager.go b/engine/internal/provision/thinclones/lvm/lvmanager.go index 8afc4c74..c7fc0d59 100644 --- a/engine/internal/provision/thinclones/lvm/lvmanager.go +++ b/engine/internal/provision/thinclones/lvm/lvmanager.go @@ -136,6 +136,11 @@ func (m *LVManager) GetSessionState(_, _ string) (*resources.SessionState, error return &resources.SessionState{}, nil } +// GetBatchSessionState is not implemented. +func (m *LVManager) GetBatchSessionState(_ []resources.SessionStateRequest) (map[string]resources.SessionState, error) { + return make(map[string]resources.SessionState), nil +} + // GetFilesystemState is not implemented. func (m *LVManager) GetFilesystemState() (models.FileSystem, error) { // TODO(anatoly): Implement. @@ -316,3 +321,17 @@ func (m *LVManager) KeepRelation(_ string) error { return nil } + +// GetDatasetOrigins provides a list of dataset origins. +func (m *LVManager) GetDatasetOrigins(_ string) []string { + log.Msg("GetDatasetOrigins is not supported for LVM. Skip the operation") + + return nil +} + +// GetActiveDatasets provides a list of active datasets. +func (m *LVManager) GetActiveDatasets(_ string) ([]string, error) { + log.Msg("GetDatasetOrigins is not supported for LVM. Skip the operation") + + return nil, nil +} diff --git a/engine/internal/provision/thinclones/zfs/branching.go b/engine/internal/provision/thinclones/zfs/branching.go index 601fa095..cb12b2c6 100644 --- a/engine/internal/provision/thinclones/zfs/branching.go +++ b/engine/internal/provision/thinclones/zfs/branching.go @@ -539,22 +539,6 @@ func (m *Manager) HasDependentEntity(snapshotName string) ([]string, error) { dependentClones := strings.Split(clones, ",") - // Check clones of dependent snapshots. - if child != "" { - // check all child snapshots - childList := strings.Split(child, ",") - - for _, childSnapshot := range childList { - // TODO: limit the max level of recursion. - childClones, err := m.HasDependentEntity(childSnapshot) - if err != nil { - return nil, fmt.Errorf("failed to check dependent clones of dependent snapshots: %w", err) - } - - dependentClones = append(dependentClones, childClones...) - } - } - return dependentClones, nil } diff --git a/engine/internal/provision/thinclones/zfs/zfs.go b/engine/internal/provision/thinclones/zfs/zfs.go index 4672ea64..bc55fb68 100644 --- a/engine/internal/provision/thinclones/zfs/zfs.go +++ b/engine/internal/provision/thinclones/zfs/zfs.go @@ -9,6 +9,7 @@ import ( "encoding/base64" "fmt" "path" + "sort" "strconv" "strings" "sync" @@ -235,13 +236,27 @@ func (m *Manager) DestroyClone(branchName, cloneName string, revision int) error return nil } + cloneDataset := m.config.Pool.CloneDataset(branchName, cloneName) + cloneOrigins := m.GetDatasetOrigins(cloneDataset) + + if m.hasDependentSnapshots(cloneOrigins, cloneMountName) { + log.Msg(fmt.Sprintf("clone %q has dependent snapshot; skipping", cloneMountName)) + return nil + } + + // TODO: check pre-clone for physical mode. + if len(cloneOrigins) <= branching.MinDatasetNumber { + // There are no other revisions, so we can destroy the entire clone dataset. + cloneMountName = cloneDataset + } + // Delete the clone and all snapshots and clones depending on it. // TODO(anatoly): right now, we are using this function only for // deleting thin clones created by users. If we are going to use // this function to delete clones used during the preparation // of baseline snapshots, we need to omit `-R`, to avoid // unexpected deletion of users' clones. - cmd := fmt.Sprintf("zfs destroy %s", cloneMountName) + cmd := fmt.Sprintf("zfs destroy -r %s", cloneMountName) if _, err = m.runner.Run(cmd); err != nil { if strings.Contains(cloneName, "clone_pre") { @@ -254,6 +269,59 @@ func (m *Manager) DestroyClone(branchName, cloneName string, revision int) error return nil } +func (m *Manager) GetDatasetOrigins(cloneDataset string) []string { + listZfsClonesCmd := "zfs list -H -o origin -r " + cloneDataset + + out, err := m.runner.Run(listZfsClonesCmd, false) + if err != nil { + log.Warn(fmt.Sprintf("failed to check clone dataset %s: %v", cloneDataset, err)) + return nil + } + + lines := strings.Split(strings.TrimSpace(out), "\n") + + return lines +} + +func (m *Manager) GetActiveDatasets(cloneDataset string) ([]string, error) { + listZfsClonesCmd := fmt.Sprintf("zfs list -t snapshot -H -o name -r %s | grep %s", m.config.Pool.Name, cloneDataset) + + out, err := m.runner.Run(listZfsClonesCmd, false) + if err != nil { + log.Dbg(fmt.Sprintf("no active datasets %s: %v", cloneDataset, err)) + } + + lines := strings.Split(strings.TrimSpace(out), "\n") + + datasetRegistry := make([]string, 0, len(lines)) + + for _, line := range lines { + name := strings.TrimSpace(line) + if name == "" || name == empty { + continue + } + + datasetRegistry = append(datasetRegistry, name) + } + + return datasetRegistry, nil +} + +func (m *Manager) hasDependentSnapshots(origins []string, cloneMountName string) bool { + for _, name := range origins { + if name == empty { + continue + } + + if strings.HasPrefix(name, cloneMountName) { + log.Dbg(fmt.Sprintf("%s has dependent snapshot %s", cloneMountName, name)) + return true + } + } + + return false +} + // cloneExists checks whether a ZFS clone exists. func (m *Manager) cloneExists(name string) (bool, error) { listZfsClonesCmd := "zfs list -r " + m.config.Pool.Name @@ -532,13 +600,128 @@ func (m *Manager) CleanupSnapshots(retentionLimit int) ([]string, error) { return nil, errors.Wrap(err, "failed to clean up snapshots") } + if err := m.cleanupEmptyDatasets(clonesOutput); err != nil { + return nil, fmt.Errorf("failed to clean up empty datasets: %w", err) + } + lines := strings.Split(out, "\n") m.RefreshSnapshotList() + firstSnapshotID := "" + + m.mu.Lock() + if l := len(m.snapshots); l > 0 { + firstSnapshotID = m.snapshots[l-1].ID + } + m.mu.Unlock() + + m.reviewParentProperty(firstSnapshotID) + return lines, nil } +func (m *Manager) reviewParentProperty(snapshotID string) { + if snapshotID == "" { + return + } + + parent, err := m.getProperty(parentProp, snapshotID) + if err != nil { + log.Err("failed to review parent property:", err) + + return + } + + if parent == "" { + return + } + + _, err = m.GetSnapshotProperties(parent) + if err != nil { + // Parent snapshot not found, clean up the property. + if err = m.setParent("", snapshotID); err != nil { + log.Err(err) + } + } +} + +func (m *Manager) cleanupEmptyDatasets(clonesOutput string) error { + datasetsToRemove := m.getEmptyDatasets(clonesOutput) + + for _, dataset := range datasetsToRemove { + log.Dbg("Remove empty dataset: ", dataset) + + if err := m.DestroyDataset(dataset); err != nil { + return fmt.Errorf("failed to destroy dataset %s: %w", dataset, err) + } + } + + return nil +} + +func (m *Manager) getEmptyDatasets(clonesOutput string) []string { + const outputParts = 2 + + lines := strings.Split(strings.TrimSpace(clonesOutput), "\n") + + allDatasets := make(map[string]struct{}) + emptyDatasets := []string{} + + for _, line := range lines { + if line == "" { + continue + } + + parts := strings.Fields(line) + if len(parts) != outputParts { + continue + } + + dataset := parts[0] + origin := parts[1] + + // Skip branch datasets (only process clones) + // /branch///r + pathParts := strings.Split(dataset, "/") + if len(pathParts) <= 3 || pathParts[1] != branching.BranchDir { + continue + } + + allDatasets[dataset] = struct{}{} + + if origin == empty { + emptyDatasets = append(emptyDatasets, dataset) + } + } + + // Find empty datasets without children + datasetsToRemove := []string{} + + for _, dataset := range emptyDatasets { + hasChild := false + prefix := dataset + "/" + + for other := range allDatasets { + if strings.HasPrefix(other, prefix) { + hasChild = true + break + } + } + + if !hasChild { + datasetsToRemove = append(datasetsToRemove, dataset) + } + } + + // Sort by depth (the deepest first) to avoid conflicts + sort.Slice(datasetsToRemove, func(i, j int) bool { + return strings.Count(datasetsToRemove[i], "/") > strings.Count(datasetsToRemove[j], "/") + }) + + return datasetsToRemove +} + func (m *Manager) getBusySnapshotList(clonesOutput string) []string { systemClones := make(map[string]string) branchingSnapshotDatasets := []string{} @@ -600,7 +783,7 @@ func (m *Manager) GetSessionState(branch, name string) (*resources.SessionState, var sEntry *ListEntry - entryName := path.Join(m.config.Pool.Name, "branch", branch, name) + entryName := branching.CloneDataset(m.config.Pool.Name, branch, name) for _, entry := range entries { if entry.Name == entryName { @@ -621,6 +804,34 @@ func (m *Manager) GetSessionState(branch, name string) (*resources.SessionState, return state, nil } +// GetBatchSessionState returns session states for multiple clones in a single ZFS query. +func (m *Manager) GetBatchSessionState(requests []resources.SessionStateRequest) (map[string]resources.SessionState, error) { + entries, err := m.listFilesystems(m.config.Pool.Name) + if err != nil { + return nil, fmt.Errorf("failed to list filesystems: %w", err) + } + + entryMap := make(map[string]*ListEntry, len(entries)) + for _, entry := range entries { + entryMap[entry.Name] = entry + } + + sessionStates := make(map[string]resources.SessionState, len(requests)) + + for _, req := range requests { + entryName := branching.CloneDataset(m.config.Pool.Name, req.Branch, req.CloneID) + + if entry, ok := entryMap[entryName]; ok { + sessionStates[req.CloneID] = resources.SessionState{ + CloneDiffSize: entry.Used, + LogicalReferenced: entry.LogicalReferenced, + } + } + } + + return sessionStates, nil +} + // GetFilesystemState returns a disk state. func (m *Manager) GetFilesystemState() (models.FileSystem, error) { parts := strings.SplitN(m.config.Pool.Name, "/", 2) diff --git a/engine/internal/provision/thinclones/zfs/zfs_test.go b/engine/internal/provision/thinclones/zfs/zfs_test.go index 0001c8a6..040eb73a 100644 --- a/engine/internal/provision/thinclones/zfs/zfs_test.go +++ b/engine/internal/provision/thinclones/zfs/zfs_test.go @@ -2,6 +2,7 @@ package zfs import ( "errors" + "sort" "testing" "github.com/stretchr/testify/assert" @@ -234,3 +235,120 @@ func TestSnapshotList(t *testing.T) { require.Equal(t, []resources.Snapshot{{ID: "test3"}, {ID: "test1"}}, fsManager.SnapshotList()) }) } + +func TestCleanupEmptyDatasets(t *testing.T) { + tests := []struct { + name string + input string + expectedDestroyed []string + }{ + { + name: "datasets with children should not be removed", + input: `test_pool - +test_pool/branch - +test_pool/branch/main - +test_pool/branch/main/clone001 - +test_pool/branch/main/clone001/r0 test_pool@snapshot001`, + expectedDestroyed: []string{}, + }, + { + name: "empty branch datasets without children should not be removed", + input: `test_pool - +test_pool/branch - +test_pool/branch/main - +test_pool/branch/branch1 - +test_pool/branch/branch2 -`, + expectedDestroyed: []string{}, + }, + { + name: "mixed case - some with children, some without", + input: `test_pool - +test_pool/branch - +test_pool/branch/main - +test_pool/branch/main/clone001 - +test_pool/branch/main/clone001/r0 test_pool@snapshot001 +test_pool/branch/main/clone002 - +test_pool/branch/main/clone002/r0 test_pool@snapshot002 +test_pool/branch/branch - +test_pool/temporary -`, + expectedDestroyed: []string{}, + }, + + { + name: "empty input", + input: ``, + expectedDestroyed: []string{}, + }, + { + name: "only whitespace", + input: ` `, + expectedDestroyed: []string{}, + }, + { + name: "malformed lines should be skipped", + input: `test_pool - +test_pool/branch +invalid line without tabs +test_pool/orphaned - + - +test_pool/valid test_pool@snap1`, + expectedDestroyed: []string{}, + }, + { + name: "original example", + input: `test_dblab_pool - +test_dblab_pool/branch - +test_dblab_pool/branch/main - +test_dblab_pool/branch/main/clone_pre_20250923095219 - +test_dblab_pool/branch/main/clone_pre_20250923095219/r0 test_dblab_pool@snapshot_20250923095219_pre +test_dblab_pool/branch/main/clone_pre_20250923095500 - +test_dblab_pool/branch/main/clone_pre_20250923095500/r0 test_dblab_pool@snapshot_20250923095500_pre +test_dblab_pool/branch/main/clone_pre_20250923100000 - +test_dblab_pool/branch/main/clone_pre_20250923100000/r0 test_dblab_pool@snapshot_20250923100000_pre`, + expectedDestroyed: []string{}, + }, + { + name: "should skip branch datasets and only process clones", + input: `test_pool - +test_pool/branch - +test_pool/branch/main - +test_pool/branch/main/clone001 - +test_pool/branch/main/clone002 - +test_pool/branch/feature - +test_pool/branch/feature/orphaned_clone - +test_pool/other - +test_pool/other/dataset -`, + expectedDestroyed: []string{ + "test_pool/branch/main/clone001", + "test_pool/branch/main/clone002", + "test_pool/branch/feature/orphaned_clone", + // Note: test_pool/other/dataset is NOT removed (not under /branch/) + }, + }, + } + + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + fsManager := NewFSManager(runnerMock{}, Config{Pool: &resources.Pool{Name: "testPool"}}) + + destroyedDatasets := fsManager.getEmptyDatasets(tt.input) + + sort.Strings(destroyedDatasets) + sort.Strings(tt.expectedDestroyed) + + if len(destroyedDatasets) != len(tt.expectedDestroyed) { + t.Errorf("destroyed count mismatch: got %d, want %d\nDestroyed: %v\nExpected: %v", + len(destroyedDatasets), len(tt.expectedDestroyed), + destroyedDatasets, tt.expectedDestroyed) + return + } + + for i := range destroyedDatasets { + if destroyedDatasets[i] != tt.expectedDestroyed[i] { + t.Errorf("destroyed dataset mismatch at index %d: got %s, want %s", + i, destroyedDatasets[i], tt.expectedDestroyed[i]) + } + } + }) + } +} diff --git a/engine/internal/retrieval/engine/postgres/snapshot/physical.go b/engine/internal/retrieval/engine/postgres/snapshot/physical.go index 61df63a0..f4177db6 100644 --- a/engine/internal/retrieval/engine/postgres/snapshot/physical.go +++ b/engine/internal/retrieval/engine/postgres/snapshot/physical.go @@ -367,7 +367,8 @@ func (p *PhysicalInitial) run(ctx context.Context) (err error) { defer func() { if err != nil { - if errDestroy := p.cloneManager.DestroyClone(branching.DefaultBranch, cloneName, branching.DefaultRevision); errDestroy != nil { + cloneDataset := branching.CloneDataset(p.fsPool.Name, branching.DefaultBranch, cloneName) + if errDestroy := p.cloneManager.DestroyDataset(cloneDataset); errDestroy != nil { log.Err(fmt.Sprintf("failed to destroy clone %q: %v", cloneName, errDestroy)) } } diff --git a/engine/internal/srv/branch.go b/engine/internal/srv/branch.go index 389b931c..5c1b0b46 100644 --- a/engine/internal/srv/branch.go +++ b/engine/internal/srv/branch.go @@ -185,6 +185,16 @@ func (s *Server) createBranch(w http.ResponseWriter, r *http.Request) { } } + snapshotID := createRequest.SnapshotID + + if snapshotID != "" { + fsm, err = s.getFSManagerForSnapshot(snapshotID) + if err != nil { + api.SendBadRequestError(w, r, err.Error()) + return + } + } + if fsm == nil { api.SendBadRequestError(w, r, "no pool manager found") return @@ -201,8 +211,6 @@ func (s *Server) createBranch(w http.ResponseWriter, r *http.Request) { return } - snapshotID := createRequest.SnapshotID - if snapshotID == "" { if createRequest.BaseBranch == "" { api.SendBadRequestError(w, r, "either base branch name or base snapshot ID must be specified") @@ -434,17 +442,6 @@ func (s *Server) snapshot(w http.ResponseWriter, r *http.Request) { return } - snapshot, err := s.Cloning.GetSnapshotByID(snapshotName) - if err != nil { - api.SendBadRequestError(w, r, err.Error()) - return - } - - if err := s.Cloning.UpdateCloneSnapshot(clone.ID, snapshot); err != nil { - api.SendBadRequestError(w, r, err.Error()) - return - } - s.tm.SendEvent(context.Background(), telemetry.SnapshotCreatedEvent, telemetry.SnapshotCreated{}) if err := api.WriteJSON(w, http.StatusOK, types.SnapshotResponse{SnapshotID: snapshotName}); err != nil { @@ -632,11 +629,17 @@ func snapshotsToRemove(repo *models.Repo, snapshotID, branchName string) []strin } func traverseUp(repo *models.Repo, snapshotID, branchName string) []string { + removingList := []string{} + visited := make(map[string]struct{}) snapshotPointer := repo.Snapshots[snapshotID] - removingList := []string{} + for snapshotPointer.Parent != "-" && snapshotPointer.Parent != "" { + if _, found := visited[snapshotPointer.ID]; found { + break + } + + visited[snapshotPointer.ID] = struct{}{} - for snapshotPointer.Parent != "-" { for _, snapshotRoot := range snapshotPointer.Root { if snapshotRoot == branchName { return removingList @@ -644,7 +647,13 @@ func traverseUp(repo *models.Repo, snapshotID, branchName string) []string { } removingList = append(removingList, snapshotPointer.ID) - snapshotPointer = repo.Snapshots[snapshotPointer.Parent] + + nextSnapshot, exists := repo.Snapshots[snapshotPointer.Parent] + if !exists { + break + } + + snapshotPointer = nextSnapshot } return removingList diff --git a/engine/internal/srv/routes.go b/engine/internal/srv/routes.go index 470634ab..55b7afc8 100644 --- a/engine/internal/srv/routes.go +++ b/engine/internal/srv/routes.go @@ -322,6 +322,28 @@ func (s *Server) deleteSnapshot(w http.ResponseWriter, r *http.Request) { } } + // When recursively deleting, set the branch label to the parent + if force && snapshotProperties.Parent != "" { + parentProps, err := fsm.GetSnapshotProperties(snapshotProperties.Parent) + if err != nil { + log.Err(err.Error()) + } + + branchName := snapshotProperties.Branch + fullDataset, _, found := strings.Cut(snapshotID, "@") + + if branchName == "" && found { + branchName, _ = branching.ParseBranchName(fullDataset, poolName) + } + + if branchName != "" && !isRoot(parentProps.Root, branchName) { + err := fsm.AddBranchProp(branchName, snapshotProperties.Parent) + if err != nil { + log.Err(err.Error()) + } + } + } + if err = fsm.DestroySnapshot(snapshotID, thinclones.DestroyOptions{Force: force}); err != nil { api.SendBadRequestError(w, r, err.Error()) return @@ -333,22 +355,37 @@ func (s *Server) deleteSnapshot(w http.ResponseWriter, r *http.Request) { return } - if snapshotProperties.Clones == "" && snapshot.NumClones == 0 { + if snapshotProperties.Clones == "" && snapshot.NumClones == 0 && snapshotProperties.Child == "" { // Destroy dataset if there are no related objects if fullDataset, _, found := strings.Cut(snapshotID, "@"); found && fullDataset != poolName { - if err = fsm.DestroyDataset(fullDataset); err != nil { + activeDatasets, err := fsm.GetActiveDatasets(fullDataset) + if err != nil { api.SendBadRequestError(w, r, err.Error()) return } + // No active datasets or clones + if len(activeDatasets) == 0 && !s.hasActiveClone(fullDataset, poolName) { + if err = fsm.DestroyDataset(fullDataset); err != nil { + api.SendBadRequestError(w, r, err.Error()) + return + } + } + // Remove dle:branch and dle:root from parent snapshot if snapshotProperties.Parent != "" { + parentProps, err := fsm.GetSnapshotProperties(snapshotProperties.Parent) + if err != nil { + log.Err(err.Error()) + } + branchName := snapshotProperties.Branch if branchName == "" { branchName, _ = branching.ParseBranchName(fullDataset, poolName) } - if branchName != "" { + // Clean up user branch labels and prevent main branch deletion + if branchName != "" && branchName != branching.DefaultBranch && isRoot(parentProps.Root, branchName) { if err := fsm.DeleteBranchProp(branchName, snapshotProperties.Parent); err != nil { log.Err(err.Error()) } @@ -359,11 +396,18 @@ func (s *Server) deleteSnapshot(w http.ResponseWriter, r *http.Request) { } } - // TODO: review all available revisions. Destroy base dataset only if there no any revision. - if baseDataset, found := strings.CutSuffix(fullDataset, "/r0"); found { - if err = fsm.DestroyDataset(baseDataset); err != nil { - api.SendBadRequestError(w, r, err.Error()) - return + // Check if the dataset ends with revision (for example, /r0) + if branching.RevisionPattern.MatchString(fullDataset) { + // Remove the revision suffix + baseDataset := branching.RevisionPattern.ReplaceAllString(fullDataset, "") + origins := fsm.GetDatasetOrigins(baseDataset) + + // If this is the last revision, remove the base dataset + if len(origins) < branching.MinDatasetNumber { + if err = fsm.DestroyDataset(baseDataset); err != nil { + api.SendBadRequestError(w, r, err.Error()) + return + } } } } @@ -391,6 +435,30 @@ func (s *Server) deleteSnapshot(w http.ResponseWriter, r *http.Request) { } } +func (s *Server) hasActiveClone(fullDataset, poolName string) bool { + cloneID, ok := branching.ParseCloneName(fullDataset, poolName) + if !ok { + return false + } + + _, errClone := s.Cloning.GetClone(cloneID) + if errClone != nil && errClone.Error() == "clone not found" { + return false + } + + return true +} + +func isRoot(root, branch string) bool { + if root == "" || branch == "" { + return false + } + + rootBranches := strings.Split(root, ",") + + return containsString(rootBranches, branch) +} + func (s *Server) detectPoolName(snapshotID string) (string, error) { const snapshotParts = 2 diff --git a/engine/pkg/models/clone.go b/engine/pkg/models/clone.go index b7300175..da6e4d1c 100644 --- a/engine/pkg/models/clone.go +++ b/engine/pkg/models/clone.go @@ -6,17 +6,16 @@ package models // Clone defines a clone model. type Clone struct { - ID string `json:"id"` - Snapshot *Snapshot `json:"snapshot"` - Branch string `json:"branch"` - Revision int `json:"revision"` - HasDependent bool `json:"hasDependent"` - Protected bool `json:"protected"` - DeleteAt *LocalTime `json:"deleteAt"` - CreatedAt *LocalTime `json:"createdAt"` - Status Status `json:"status"` - DB Database `json:"db"` - Metadata CloneMetadata `json:"metadata"` + ID string `json:"id"` + Snapshot *Snapshot `json:"snapshot"` + Branch string `json:"branch"` + Revision int `json:"revision"` + Protected bool `json:"protected"` + DeleteAt *LocalTime `json:"deleteAt"` + CreatedAt *LocalTime `json:"createdAt"` + Status Status `json:"status"` + DB Database `json:"db"` + Metadata CloneMetadata `json:"metadata"` } // CloneMetadata contains fields describing a clone model. diff --git a/engine/pkg/util/branching/branching.go b/engine/pkg/util/branching/branching.go index 75053856..0d3a9ad9 100644 --- a/engine/pkg/util/branching/branching.go +++ b/engine/pkg/util/branching/branching.go @@ -8,6 +8,7 @@ package branching import ( "fmt" "path" + "regexp" "strings" ) @@ -20,8 +21,16 @@ const ( // BranchDir defines branch directory in the pool. BranchDir = "branch" + + // MinDatasetNumber is 2 because: + // - test_dblab_pool/branch/001-branch/clone001 - root + // - test_dblab_pool/branch/001-branch/clone001/r0 - revision + MinDatasetNumber = 2 ) +// RevisionPattern creates a regex pattern to match dataset revision. +var RevisionPattern = regexp.MustCompile(`/r\d+$`) + // BranchName returns a full branch name in the data pool. func BranchName(poolName, branchName string) string { return path.Join(poolName, BranchDir, branchName) From 0848f339517dc2e86f76f188449aca0ab08558cf Mon Sep 17 00:00:00 2001 From: Artyom Kartasov Date: Fri, 10 Oct 2025 10:59:37 +0000 Subject: [PATCH 5/6] fix: install google-cloud-sdk --- engine/.gitlab-ci.yml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/engine/.gitlab-ci.yml b/engine/.gitlab-ci.yml index 862deb7a..22c505d9 100644 --- a/engine/.gitlab-ci.yml +++ b/engine/.gitlab-ci.yml @@ -87,8 +87,8 @@ build-binary-client-master: - make build-client # Install google-cloud-sdk. + - curl -fsSL https://packages.cloud.google.com/apt/doc/apt-key.gpg | gpg --dearmor -o /usr/share/keyrings/cloud.google.gpg - echo "deb [signed-by=/usr/share/keyrings/cloud.google.gpg] http://packages.cloud.google.com/apt cloud-sdk main" | tee -a /etc/apt/sources.list.d/google-cloud-sdk.list - - curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key --keyring /usr/share/keyrings/cloud.google.gpg add - - apt-get update && apt-get install -y google-cloud-sdk # Authenticate. @@ -107,8 +107,8 @@ build-binary-client: - make build-client # Install google-cloud-sdk. + - curl -fsSL https://packages.cloud.google.com/apt/doc/apt-key.gpg | gpg --dearmor -o /usr/share/keyrings/cloud.google.gpg - echo "deb [signed-by=/usr/share/keyrings/cloud.google.gpg] http://packages.cloud.google.com/apt cloud-sdk main" | tee -a /etc/apt/sources.list.d/google-cloud-sdk.list - - curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key --keyring /usr/share/keyrings/cloud.google.gpg add - - apt-get update && apt-get install -y google-cloud-sdk # Authenticate. @@ -128,8 +128,8 @@ build-binary-client-rc: - make build-client # Install google-cloud-sdk. + - curl -fsSL https://packages.cloud.google.com/apt/doc/apt-key.gpg | gpg --dearmor -o /usr/share/keyrings/cloud.google.gpg - echo "deb [signed-by=/usr/share/keyrings/cloud.google.gpg] http://packages.cloud.google.com/apt cloud-sdk main" | tee -a /etc/apt/sources.list.d/google-cloud-sdk.list - - curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key --keyring /usr/share/keyrings/cloud.google.gpg add - - apt-get update && apt-get install -y google-cloud-sdk # Authenticate. From e9faee86f9cf1ad0c5c9c13b03a143ed13b0e394 Mon Sep 17 00:00:00 2001 From: Artyom Kartasov Date: Fri, 10 Oct 2025 11:38:36 +0000 Subject: [PATCH 6/6] feat: display all branches including ambiguous ones and filter snapshots by dataset (#657) --- .../provision/thinclones/zfs/branching.go | 6 ++- engine/internal/srv/branch.go | 48 ++++++++++++++----- engine/internal/srv/routes.go | 11 ++++- engine/pkg/models/branch.go | 2 + engine/pkg/util/branching/branching.go | 12 +++++ ui/packages/ce/package.json | 2 +- .../ce/src/api/snapshots/getSnapshots.ts | 9 +++- ui/packages/shared/package.json | 2 +- .../shared/pages/CreateBranch/index.tsx | 38 ++++++++++----- .../shared/pages/CreateBranch/stores/Main.ts | 3 +- .../shared/types/api/endpoints/getBranches.ts | 2 + .../types/api/endpoints/getSnapshots.ts | 2 +- 12 files changed, 104 insertions(+), 33 deletions(-) diff --git a/engine/internal/provision/thinclones/zfs/branching.go b/engine/internal/provision/thinclones/zfs/branching.go index 601fa095..67893a82 100644 --- a/engine/internal/provision/thinclones/zfs/branching.go +++ b/engine/internal/provision/thinclones/zfs/branching.go @@ -267,13 +267,15 @@ func (m *Manager) ListAllBranches(poolList []string) ([]models.BranchEntity, err continue } + dataset := branching.ParseBaseDatasetFromSnapshot(fields[1]) + if !strings.Contains(fields[0], branchSep) { - branches = append(branches, models.BranchEntity{Name: fields[0], SnapshotID: fields[1]}) + branches = append(branches, models.BranchEntity{Name: fields[0], Dataset: dataset, SnapshotID: fields[1]}) continue } for _, branchName := range strings.Split(fields[0], branchSep) { - branches = append(branches, models.BranchEntity{Name: branchName, SnapshotID: fields[1]}) + branches = append(branches, models.BranchEntity{Name: branchName, Dataset: dataset, SnapshotID: fields[1]}) } } diff --git a/engine/internal/srv/branch.go b/engine/internal/srv/branch.go index 389b931c..6b5567fb 100644 --- a/engine/internal/srv/branch.go +++ b/engine/internal/srv/branch.go @@ -47,9 +47,6 @@ func (s *Server) listBranches(w http.ResponseWriter, r *http.Request) { branchDetails := make([]models.BranchView, 0, len(branches)) - // branchRegistry is used to display the "main" branch with only the most recent snapshot. - branchRegistry := make(map[string]int, 0) - for _, branchEntity := range branches { snapshotDetails, ok := repo.Snapshots[branchEntity.SnapshotID] if !ok { @@ -60,6 +57,7 @@ func (s *Server) listBranches(w http.ResponseWriter, r *http.Request) { branchView := models.BranchView{ Name: branchEntity.Name, + BaseDataset: branchEntity.Dataset, Parent: parentSnapshot, DataStateAt: snapshotDetails.DataStateAt, SnapshotID: snapshotDetails.ID, @@ -67,15 +65,6 @@ func (s *Server) listBranches(w http.ResponseWriter, r *http.Request) { NumSnapshots: numSnapshots, } - if position, ok := branchRegistry[branchEntity.Name]; ok { - if branchView.DataStateAt > branchDetails[position].DataStateAt { - branchDetails[position] = branchView - } - - continue - } - - branchRegistry[branchView.Name] = len(branchDetails) branchDetails = append(branchDetails, branchView) } @@ -136,15 +125,36 @@ func containsString(slice []string, s string) bool { } func (s *Server) getFSManagerForBranch(branchName string) (pool.FSManager, error) { + return s.getFSManagerForBranchAndDataset(branchName, "") +} + +func (s *Server) getFSManagerForBranchAndDataset(branchName, dataset string) (pool.FSManager, error) { allBranches, err := s.getAllAvailableBranches(s.pm.First()) if err != nil { return nil, fmt.Errorf("failed to get branch list: %w", err) } for _, branchEntity := range allBranches { - if branchEntity.Name == branchName { // TODO: filter by pool name as well because branch name is ambiguous. + if branchEntity.Name != branchName { + continue + } + + if dataset == "" { return s.getFSManagerForSnapshot(branchEntity.SnapshotID) } + + fsm, err := s.getFSManagerForSnapshot(branchEntity.SnapshotID) + if err != nil { + continue + } + + if fsm.Pool().Name == dataset { + return fsm, nil + } + } + + if dataset != "" { + return nil, fmt.Errorf("failed to find dataset %s of the branch: %s", dataset, branchName) } return nil, fmt.Errorf("failed to found dataset of the branch: %s", branchName) @@ -472,6 +482,18 @@ func filterSnapshotsByBranch(pool *resources.Pool, branch string, snapshots []mo return filtered } +func filterSnapshotsByDataset(dataset string, snapshots []models.Snapshot) []models.Snapshot { + filtered := make([]models.Snapshot, 0) + + for _, sn := range snapshots { + if sn.Pool == dataset { + filtered = append(filtered, sn) + } + } + + return filtered +} + func (s *Server) log(w http.ResponseWriter, r *http.Request) { branchName := mux.Vars(r)["branchName"] diff --git a/engine/internal/srv/routes.go b/engine/internal/srv/routes.go index 470634ab..6292330c 100644 --- a/engine/internal/srv/routes.go +++ b/engine/internal/srv/routes.go @@ -108,8 +108,11 @@ func (s *Server) getSnapshots(w http.ResponseWriter, r *http.Request) { return } - if branchRequest := r.URL.Query().Get("branch"); branchRequest != "" { - fsm, err := s.getFSManagerForBranch(branchRequest) + branchRequest := r.URL.Query().Get("branch") + datasetRequest := r.URL.Query().Get("dataset") + + if branchRequest != "" { + fsm, err := s.getFSManagerForBranchAndDataset(branchRequest, datasetRequest) if err != nil { api.SendBadRequestError(w, r, err.Error()) return @@ -123,6 +126,10 @@ func (s *Server) getSnapshots(w http.ResponseWriter, r *http.Request) { snapshots = filterSnapshotsByBranch(fsm.Pool(), branchRequest, snapshots) } + if branchRequest == "" && datasetRequest != "" { + snapshots = filterSnapshotsByDataset(datasetRequest, snapshots) + } + if err = api.WriteJSON(w, http.StatusOK, snapshots); err != nil { api.SendError(w, r, err) return diff --git a/engine/pkg/models/branch.go b/engine/pkg/models/branch.go index e29f3cc7..dcdf4203 100644 --- a/engine/pkg/models/branch.go +++ b/engine/pkg/models/branch.go @@ -35,6 +35,7 @@ type SnapshotDetails struct { // BranchView describes branch view. type BranchView struct { Name string `json:"name"` + BaseDataset string `json:"baseDataset"` Parent string `json:"parent"` DataStateAt string `json:"dataStateAt"` SnapshotID string `json:"snapshotID"` @@ -45,5 +46,6 @@ type BranchView struct { // BranchEntity defines a branch-snapshot pair. type BranchEntity struct { Name string + Dataset string SnapshotID string } diff --git a/engine/pkg/util/branching/branching.go b/engine/pkg/util/branching/branching.go index 75053856..6159bce1 100644 --- a/engine/pkg/util/branching/branching.go +++ b/engine/pkg/util/branching/branching.go @@ -108,3 +108,15 @@ func ParseBranchNameFromSnapshot(snapshot, poolName string) string { return branch } + +// ParseBaseDatasetFromSnapshot parses base dataset from the snapshot ID. +func ParseBaseDatasetFromSnapshot(snapshot string) string { + fullDataset, _, found := strings.Cut(snapshot, "@") + if !found { + return "" + } + + dataset, _, _ := strings.Cut(fullDataset, "/"+BranchDir+"/") + + return dataset +} diff --git a/ui/packages/ce/package.json b/ui/packages/ce/package.json index 098bfbe4..00d73fec 100644 --- a/ui/packages/ce/package.json +++ b/ui/packages/ce/package.json @@ -1,6 +1,6 @@ { "name": "@postgres.ai/ce", - "version": "4.0.1", + "version": "4.0.2", "private": true, "dependencies": { "@craco/craco": "^6.4.3", diff --git a/ui/packages/ce/src/api/snapshots/getSnapshots.ts b/ui/packages/ce/src/api/snapshots/getSnapshots.ts index b26788eb..16af68a8 100644 --- a/ui/packages/ce/src/api/snapshots/getSnapshots.ts +++ b/ui/packages/ce/src/api/snapshots/getSnapshots.ts @@ -13,7 +13,14 @@ import { import { request } from 'helpers/request' export const getSnapshots: GetSnapshots = async (req) => { - const url = `/snapshots${req.branchName ? `?branch=${req.branchName}` : ''}`; + const params = new URLSearchParams() + if (req.branchName) { + params.append('branch', req.branchName) + } + if (req.dataset) { + params.append('dataset', req.dataset) + } + const url = `/snapshots${params.toString() ? `?${params.toString()}` : ''}`; const response = await request(url); return { diff --git a/ui/packages/shared/package.json b/ui/packages/shared/package.json index 21743956..7efcdbb2 100644 --- a/ui/packages/shared/package.json +++ b/ui/packages/shared/package.json @@ -1,6 +1,6 @@ { "name": "@postgres.ai/shared", - "version": "4.0.1", + "version": "4.0.2", "scripts": { "build": "tsc -p tsconfig.build.json && node scripts/copy-assets.js", "pack": "node scripts/pack.js" diff --git a/ui/packages/shared/pages/CreateBranch/index.tsx b/ui/packages/shared/pages/CreateBranch/index.tsx index 0ae11354..d828d1d9 100644 --- a/ui/packages/shared/pages/CreateBranch/index.tsx +++ b/ui/packages/shared/pages/CreateBranch/index.tsx @@ -107,6 +107,7 @@ export const CreateBranchPage = observer( const classes = useStyles() const history = useHistory() const [branchSnapshots, setBranchSnapshots] = useState([]) + const [selectedBranchKey, setSelectedBranchKey] = useState('main|') const { load, @@ -131,8 +132,8 @@ export const CreateBranchPage = observer( }) } - const fetchSnapshots = async (branchName: string) => { - await getSnapshots(instanceId, branchName).then((response) => { + const fetchSnapshots = async (branchName: string, dataset?: string) => { + await getSnapshots(instanceId, branchName, dataset).then((response) => { if (response) { setBranchSnapshots(response) formik.setFieldValue('snapshotID', response[0]?.id) @@ -143,17 +144,28 @@ export const CreateBranchPage = observer( const handleParentBranchChange = async ( e: React.ChangeEvent, ) => { - const branchName = e.target.value + const compositeKey = e.target.value + const [branchName, dataset] = compositeKey.split('|') + + setSelectedBranchKey(compositeKey) formik.setFieldValue('baseBranch', branchName) - await fetchSnapshots(branchName) + await fetchSnapshots(branchName, dataset) } const [{ formik }] = useForm(handleSubmit) - useEffect(() => { - load(instanceId) - fetchSnapshots(formik.values.baseBranch) - }, [formik.values.baseBranch]) + useEffect(() => { + load(instanceId); + }, [instanceId]); + + useEffect(() => { + if (!branchesList?.length) return; + const selected = branchesList.find(b => b.name === formik.values.baseBranch); + if (!selected) return; + const compositeKey = `${selected.name}|${selected.baseDataset || ''}`; + setSelectedBranchKey(compositeKey); + fetchSnapshots(selected.name, selected.baseDataset); + }, [branchesList]); if (isBranchesLoading) { return @@ -207,16 +219,20 @@ export const CreateBranchPage = observer(