Refactor lock manager initialization to make it a bit less special
Split the shared and local initialization to separate functions, and
follow the common naming conventions. With this, we no longer create
the LockMethodLocalHash hash table in the postmaster process, which
was always pointless.
Re
Rename some shared memory initialization routines
To make them follow the usual naming convention where
FoobarShmemSize() calculates the amount of shared memory needed by
Foobar subsystem, and FoobarShmemInit() performs the initialization.
I didn't rename CreateLWLocks() and InitShmmeIndex(), bec
Fix garbled process name on backend crash
The log message on backend crash used wrong variable, which could be
uninitialized. Introduced in commit 28a520c0b7.
Reported-by: Alexander Lakhin
Discussion:
https://www.postgresql.org/message-id/451b0797-83b8-cdbc-727f-8d7a7b0e3...@gmail.com
Branch
--
Relax fsyncing at end of a bulk load that was not WAL-logged
And improve the comments.
Backpatch to v17 where this was introduced.
Reviewed-by: Noah Misch
Discussion:
https://www.postgresql.org/message-id/cac7d1b6-8358-40be-af0b-21bc9b27d...@iki.fi
Branch
--
master
Details
---
https:/
Relax fsyncing at end of a bulk load that was not WAL-logged
And improve the comments.
Backpatch to v17 where this was introduced.
Reviewed-by: Noah Misch
Discussion:
https://www.postgresql.org/message-id/cac7d1b6-8358-40be-af0b-21bc9b27d...@iki.fi
Branch
--
REL_17_STABLE
Details
---
Refactor CopyOneRowTo
The handling of binary and text formats are quite different here, so
it's more clear to check for the format first and have two separate
loops.
Author: jian he
Reviewed-by: Ilia Evdokimov, Junwang Zhao
Discussion:
https://www.postgresql.org/message-id/cacjufxfzhcefbqf0m%2b
Remove unused 'cur_skey' argument from IndexScanOK()
Commit a78fcfb51243 removed the last use of it.
Author: Hugo Zhang, Aleksander Alekseev
Reviewed-by: Daniel Gustafsson
Discussion:
https://www.postgresql.org/message-id/NT0PR01MB129459E243721B954611938F9CDD2%40NT0PR01MB1294.CHNPR01.prod.partne
Fix bad indentation introduced in commit f011e82c2c
Branch
--
master
Details
---
https://git.postgresql.org/pg/commitdiff/8de5ca1dc9fa809102acd1983ee19159d0bc469f
Modified Files
--
src/backend/access/transam/xlogprefetcher.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-
Consolidate postmaster code to launch background processes
Much of the code in process_pm_child_exit() to launch replacement
processes when one exits or when progressing to next postmaster state
was unnecessary, because the ServerLoop will launch any missing
background processes anyway. Remove the
Initialize HASHCTL differently, to suppress Coverity warning
Coverity complained that the hash_create() call might access
hash_table_ctl->hctl. That's a false alarm, hash_create() only
accesses that field when passed the HASH_SHARED_MEM flag. Try to
silence it by using a plain local variable inste
Fix comment on processes being kept over a restart
All child processes except the syslogger are killed on a restart. The
archiver might be already running though, if it was started during
recovery.
The split in the comments between "other special children" and the
first group of "background tasks
Refactor code to handle death of a backend or bgworker in postmaster
Currently, when a child process exits, the postmaster first scans
through BackgroundWorkerList, to see if it the child process was a
background worker. If not found, then it scans through BackendList to
see if it was a regular ba
Make BackgroundWorkerList doubly-linked
This allows ForgetBackgroundWorker() and ReportBackgroundWorkerExit()
to take a RegisteredBgWorker pointer as argument, rather than a list
iterator. That feels a little more natural. But more importantly, this
paves the way for more refactoring in the next c
Fix pg_rewind debug output to print the source timeline history
getTimelineHistory() is called twice, to read the source and the
target timeline history files. However, the loop to print the file
with the --debug option used the wrong variable when dealing with the
source. As a result, the source'
Fix pg_rewind debug output to print the source timeline history
getTimelineHistory() is called twice, to read the source and the
target timeline history files. However, the loop to print the file
with the --debug option used the wrong variable when dealing with the
source. As a result, the source'
Fix pg_rewind debug output to print the source timeline history
getTimelineHistory() is called twice, to read the source and the
target timeline history files. However, the loop to print the file
with the --debug option used the wrong variable when dealing with the
source. As a result, the source'
Fix pg_rewind debug output to print the source timeline history
getTimelineHistory() is called twice, to read the source and the
target timeline history files. However, the loop to print the file
with the --debug option used the wrong variable when dealing with the
source. As a result, the source'
Fix pg_rewind debug output to print the source timeline history
getTimelineHistory() is called twice, to read the source and the
target timeline history files. However, the loop to print the file
with the --debug option used the wrong variable when dealing with the
source. As a result, the source'
Fix pg_rewind debug output to print the source timeline history
getTimelineHistory() is called twice, to read the source and the
target timeline history files. However, the loop to print the file
with the --debug option used the wrong variable when dealing with the
source. As a result, the source'
Fix pg_rewind debug output to print the source timeline history
getTimelineHistory() is called twice, to read the source and the
target timeline history files. However, the loop to print the file
with the --debug option used the wrong variable when dealing with the
source. As a result, the source'
Make fallback MD5 implementation thread-safe on big-endian systems
Replace a static scratch buffer with a local variable, because a
static buffer makes the function not thread-safe. This function is
used in client-code in libpq, so it needs to be thread-safe. It was
until commit b67b57a966, which
Make fallback MD5 implementation thread-safe on big-endian systems
Replace a static scratch buffer with a local variable, because a
static buffer makes the function not thread-safe. This function is
used in client-code in libpq, so it needs to be thread-safe. It was
until commit b67b57a966, which
Make fallback MD5 implementation thread-safe on big-endian systems
Replace a static scratch buffer with a local variable, because a
static buffer makes the function not thread-safe. This function is
used in client-code in libpq, so it needs to be thread-safe. It was
until commit b67b57a966, which
Make fallback MD5 implementation thread-safe on big-endian systems
Replace a static scratch buffer with a local variable, because a
static buffer makes the function not thread-safe. This function is
used in client-code in libpq, so it needs to be thread-safe. It was
until commit b67b57a966, which
Make fallback MD5 implementation thread-safe on big-endian systems
Replace a static scratch buffer with a local variable, because a
static buffer makes the function not thread-safe. This function is
used in client-code in libpq, so it needs to be thread-safe. It was
until commit b67b57a966, which
Mark misc static global variables as const
Reviewed-by: Andres Freund
Discussion:
https://www.postgresql.org/message-id/54c29fb0-edf2-48ea-9814-44e918bbd...@iki.fi
Branch
--
master
Details
---
https://git.postgresql.org/pg/commitdiff/fe8dd65bf28db1a6ad690ffcd5124d1863b5a4c6
Modified Fi
Make nullSemAction const, add 'const' decorators to related functions
To make it more clear that these should never be modified.
Reviewed-by: Andres Freund
Discussion:
https://www.postgresql.org/message-id/54c29fb0-edf2-48ea-9814-44e918bbd...@iki.fi
Branch
--
master
Details
---
https:/
Turn a few 'validnsps' static variables into locals
There was no need for these to be static buffers, local variables work
just as well. I think they were marked as 'static' to imply that they
are read-only, but 'const' is more appropriate for that, so change
them to const.
To make it possible to
Constify fields and parameters in spell.c
I started by marking VoidString as const, and fixing the fallout by
marking more fields and function arguments as const. It proliferated
quite a lot, but all within spell.c and spell.h.
A more narrow patch to get rid of the static VoidString buffer would
Use psprintf to simplify gtsvectorout()
The buffer allocation was correct, but looked archaic and scary:
- It was weird to calculate the buffer size before determining which
format string was used. With the same effort, we could've used the
right-sized buffer for each branch.
- Commit aa0d35
Fix datatypes in comments in instr_time.h
The INSTR_TIME_GET_NANOSEC(t) and INSTR_TIME_GET_MICROSEC(t) macros
return a signed int64.
Discussion:
https://www.postgresql.org/message-id/zrhkv3maqfwns...@ip-10-97-1-34.eu-west-3.compute.internal
Branch
--
master
Details
---
https://git.post
Revert "Fix comments in instr_time.h and remove an unneeded cast to int64"
This reverts commit 3dcb09de7b. Tom Lane pointed out that it broke the
abstraction provided by the macros. The callers should not need to
know what the internal type is.
This commit is an exact revert, the next commit will
Fix comments in instr_time.h and remove an unneeded cast to int64
03023a2664 represented time as an int64 on all platforms but forgot to
update the comment related to INSTR_TIME_GET_MICROSEC() and provided
an incorrect comment for INSTR_TIME_GET_NANOSEC().
In passing remove an unneeded cast to in
Minor refactoring of assign_backendlist_entry()
Make assign_backendlist_entry() responsible just for allocating the
Backend struct. Linking it to the RegisteredBgWorker is the caller's
responsibility now. Seems more clear that way.
Discussion:
https://www.postgresql.org/message-id/835232c0-a5f7-
Fix outdated comment; all running bgworkers are in BackendList
Before commit 8a02b3d732, only bgworkers that connected to a database
had an entry in the Backendlist. Commit 8a02b3d732 changed that, but
forgot to update this comment.
Discussion:
https://www.postgresql.org/message-id/835232c0-a5f7
Refactor getWeights to write to caller-supplied buffer
This gets rid of the static result buffer.
Reviewed-by: Robert Haas
Discussion:
https://www.postgresql.org/message-id/7f86e06a-98c5-4ce3-8ec9-3885c8de0...@iki.fi
Branch
--
master
Details
---
https://git.postgresql.org/pg/commitdiff
Replace static buf with palloc in str_time()
The function is used only once in the startup process, so the leak
into current memory context is harmless.
This is a tiny step in making the server thread-safe.
Reviewed-by: Robert Haas
Discussion:
https://www.postgresql.org/message-id/7f86e06a-98c5
Replace static buf with a stack-allocated one in ReadControlFile
It's only used very locally within the function.
Reviewed-by: Robert Haas
Discussion:
https://www.postgresql.org/message-id/7f86e06a-98c5-4ce3-8ec9-3885c8de0...@iki.fi
Branch
--
master
Details
---
https://git.postgresql.o
Replace static bufs with a StringInfo in cash_words()
For clarity. The code was correct, and the buffer was large enough,
but string manipulation with no bounds checking is scary.
This incurs an extra palloc+pfree to every call, but in quick
performance testing, it doesn't seem to be significant.
Replace static buf with a stack-allocated one in 'seg' extension
The buffer is used only locally within the function. Also, the
initialization to '0' characters was unnecessary, the initial content
were always overwritten with sprintf(). I don't understand why it was
done that way, but it's been l
Remove leftover function declaration
Commit 9d9b9d46f3 removed the function (or rather, moved it to a
different source file and renamed it to SendCancelRequest), but forgot
the declaration in the header file.
Branch
--
master
Details
---
https://git.postgresql.org/pg/commitdiff/47c98035c
#ifndef guard around it.
--
Heikki Linnakangas
Neon (https://neon.tech)
Detach syslogger from shared memory
Commit aafc05de1b removed the calls to detach from shared memory from
syslogger startup. That was not intentional, so put them back.
Author: Rui Zhao
Reviewed-by: Aleksander Alekseev
Backpatch-through: 17
Discussion:
https://www.postgresql.org/message-id/11505
Detach syslogger from shared memory
Commit aafc05de1b removed the calls to detach from shared memory from
syslogger startup. That was not intentional, so put them back.
Author: Rui Zhao
Reviewed-by: Aleksander Alekseev
Backpatch-through: 17
Discussion:
https://www.postgresql.org/message-id/11505
Remove dead generators for cyrillic encoding conversion tables
These tools were used to read the koi-iso.tab, koi-win.tab, and
koi-alt.tab files, which contained the mappings between the
single-byte cyrillic encodings. However, those data files were removed
in commit 4c3c8c048d, back in 2003. Thes
On 29/07/2024 17:30, Heikki Linnakangas wrote:
On 29/07/2024 16:25, Heikki Linnakangas wrote:
On 29/07/2024 16:23, Daniel Gustafsson wrote:
On 29 Jul 2024, at 15:18, Heikki Linnakangas wrote:
Move cancel key generation to after forking the backend
longfin seems a tad sad about this one
Fix double-release of spinlock
Commit 9d9b9d46f3 added spinlocks to protect the fields in ProcSignal
flags, but in EmitProcSignalBarrier(), the spinlock was released
twice. With most spinlock implementations, releasing a lock that's not
held is not easy to notice, because most of the time it does
On 29/07/2024 16:25, Heikki Linnakangas wrote:
On 29/07/2024 16:23, Daniel Gustafsson wrote:
On 29 Jul 2024, at 15:18, Heikki Linnakangas wrote:
Move cancel key generation to after forking the backend
longfin seems a tad sad about this one:
procsignal.c:87:3: error: redefinition of typedef
On 29/07/2024 16:23, Daniel Gustafsson wrote:
On 29 Jul 2024, at 15:18, Heikki Linnakangas wrote:
Move cancel key generation to after forking the backend
longfin seems a tad sad about this one:
procsignal.c:87:3: error: redefinition of typedef 'ProcSignalHeader' is a C11
featur
Fix compiler warning/error about typedef redefinitions
Per buildfarm member 'sifaka':
procsignal.c:87:3: error: redefinition of typedef 'ProcSignalHeader' is a
C11 feature [-Werror,-Wtypedef-redefinition]
Branch
--
master
Details
---
https://git.postgresql.org/pg/commitdiff/8bda213
Move cancel key generation to after forking the backend
Move responsibility of generating the cancel key to the backend
process. The cancel key is now generated after forking, and the
backend advertises it in the ProcSignal array. When a cancel request
arrives, the backend handling it scans the Pr
Fix outdated comment in smgrtruncate()
Commit c5315f4f44 replaced smgr_fsm_nblocks and smgr_vm_nblocks with
smgr_cached_nblocks, but forgot to update this comment.
Author: Kirill Reshke
Discussion:
https://www.postgresql.org/message-id/caldssph9va6sdsvjrcmspeyramf%2brfisk7gqjo1dtrnd3vd...@mail.g
Fallback to uuid for ossp-uuid with meson
The upstream name for the ossp-uuid package / pkg-config file is
"uuid". Many distributions change this to be "ossp-uuid" to not
conflict with e2fsprogs.
This lookup fails on distributions which don't change this name, for
example NixOS / nixpkgs. Both "o
Support absolute bindir/libdir in regression tests with meson
Passing an absolute bindir/libdir will install the binaries and
libraries to /tmp_install/ and
/tmp_install/ respectively.
This path is correctly passed to the regression test suite via
configure/make, but not via meson, yet. This is b
Fallback to clang in PATH with meson
Some distributions put clang into a different path than the llvm
binary path.
For example, this is the case on NixOS / nixpkgs, which failed to find
clang with meson before this patch.
Author: Wolfgang Walther
Reviewed-by: Nazir Bilal Yavuz, Alvaro Herrera, P
Fallback to uuid for ossp-uuid with meson
The upstream name for the ossp-uuid package / pkg-config file is
"uuid". Many distributions change this to be "ossp-uuid" to not
conflict with e2fsprogs.
This lookup fails on distributions which don't change this name, for
example NixOS / nixpkgs. Both "o
Fallback to clang in PATH with meson
Some distributions put clang into a different path than the llvm
binary path.
For example, this is the case on NixOS / nixpkgs, which failed to find
clang with meson before this patch.
Author: Wolfgang Walther
Reviewed-by: Nazir Bilal Yavuz, Alvaro Herrera, P
Support falling back to non-preferred readline implementation with meson
To build with -Dreadline=enabled one can use either readline or
libedit. The -Dlibedit_preferred flag is supposed to control the order
of names to lookup. This works fine when either both libraries are
present or -Dreadline
Support falling back to non-preferred readline implementation with meson
To build with -Dreadline=enabled one can use either readline or
libedit. The -Dlibedit_preferred flag is supposed to control the order
of names to lookup. This works fine when either both libraries are
present or -Dreadline
Support absolute bindir/libdir in regression tests with meson
Passing an absolute bindir/libdir will install the binaries and
libraries to /tmp_install/ and
/tmp_install/ respectively.
This path is correctly passed to the regression test suite via
configure/make, but not via meson, yet. This is b
Support absolute bindir/libdir in regression tests with meson
Passing an absolute bindir/libdir will install the binaries and
libraries to /tmp_install/ and
/tmp_install/ respectively.
This path is correctly passed to the regression test suite via
configure/make, but not via meson, yet. This is b
Fallback to uuid for ossp-uuid with meson
The upstream name for the ossp-uuid package / pkg-config file is
"uuid". Many distributions change this to be "ossp-uuid" to not
conflict with e2fsprogs.
This lookup fails on distributions which don't change this name, for
example NixOS / nixpkgs. Both "o
Support falling back to non-preferred readline implementation with meson
To build with -Dreadline=enabled one can use either readline or
libedit. The -Dlibedit_preferred flag is supposed to control the order
of names to lookup. This works fine when either both libraries are
present or -Dreadline
Fallback to clang in PATH with meson
Some distributions put clang into a different path than the llvm
binary path.
For example, this is the case on NixOS / nixpkgs, which failed to find
clang with meson before this patch.
Author: Wolfgang Walther
Reviewed-by: Nazir Bilal Yavuz, Alvaro Herrera, P
Add test for early backend startup errors
The new test tests the libpq fallback behavior on an early error,
which was fixed in the previous commit.
This adds an IS_INJECTION_POINT_ATTACHED() macro, to allow writing
injected test code alongside the normal source code. In principle, the
new test co
Add tests for errors during SSL or GSSAPI handshake
These test that libpq correctly falls back to a plaintext connection
on handshake error, in the "prefer" modes.
Reviewed-by: Michael Paquier
Discussion:
https://www.postgresql.org/message-id/CAOYmi%2Bnwvu21mJ4DYKUa98HdfM_KZJi7B1MhyXtnsyOO-PB6Ww
Fix fallback behavior when server sends an ERROR early at startup
With sslmode=prefer, the desired behavior is to completely fail the
connection attempt, *not* fall back to a plaintext connection, if the
server responds to the SSLRequest with an error ('E') response instead
of rejecting SSL with a
Fix fallback behavior when server sends an ERROR early at startup
With sslmode=prefer, the desired behavior is to completely fail the
connection attempt, *not* fall back to a plaintext connection, if the
server responds to the SSLRequest with an error ('E') response instead
of rejecting SSL with a
Fix using injection points at backend startup in EXEC_BACKEND mode
Commit 86db52a506 changed the locking of injection points to use only
atomic ops and spinlocks, to make it possible to define injection
points in processes that don't have a PGPROC entry (yet). However, it
didn't work in EXEC_BACKE
Fix using injection points at backend startup in EXEC_BACKEND mode
Commit 86db52a506 changed the locking of injection points to use only
atomic ops and spinlocks, to make it possible to define injection
points in processes that don't have a PGPROC entry (yet). However, it
didn't work in EXEC_BACKE
Move resowner from common JitContext to LLVM specific
Only the LLVM specific code uses it since resource owners were made
extensible in commit b8bff07daa85c837a2747b4d35cd5a27e73fb7b2. This is
new in v17, so backpatch there to keep the branches from diverging
just yet.
Author: Andreas Karlsson
D
Move resowner from common JitContext to LLVM specific
Only the LLVM specific code uses it since resource owners were made
extensible in commit b8bff07daa85c837a2747b4d35cd5a27e73fb7b2. This is
new in v17, so backpatch there to keep the branches from diverging
just yet.
Author: Andreas Karlsson
D
= InvalidBackendId;
+static pid_t pq_mq_parallel_leader_proc_number = INVALID_PROC_NUMBER;
I guess it was a historical mistake that this variable of type pid_t
instead of BackendId, but now it should be ProcNumber?
Yep, fixed thanks!
--
Heikki Linnakangas
Neon (https://neon.tech)
Use correct type for pq_mq_parallel_leader_proc_number variable
It's a ProcNumber, not a process id. Both are integers, so it's
harmless, but clearly wrong. It's been wrong since forever, the
mistake has survived through a couple of refactorings already.
Spotted-by: Thomas Munro
Discussion:
http
Use atomics to avoid locking in InjectionPointRun()
This allows using injection points without having a PGPROC, like early
at backend startup, or in the postmaster.
The injection points facility is new in v17, so backpatch there.
Reviewed-by: Michael Paquier
Disussion:
https://www.postgresql.o
Use atomics to avoid locking in InjectionPointRun()
This allows using injection points without having a PGPROC, like early
at backend startup, or in the postmaster.
The injection points facility is new in v17, so backpatch there.
Reviewed-by: Michael Paquier
Disussion:
https://www.postgresql.o
Fix outdated comment after removal of direct SSL fallback
The option to fall back from direct SSL to negotiated SSL or a
plaintext connection was removed in commit fb5718f35f.
Discussion:
https://www.postgresql.org/message-id/c82ad227-e049-4e18-8898-475a748b5...@iki.fi
Branch
--
REL_17_STAB
Fix outdated comment after removal of direct SSL fallback
The option to fall back from direct SSL to negotiated SSL or a
plaintext connection was removed in commit fb5718f35f.
Discussion:
https://www.postgresql.org/message-id/c82ad227-e049-4e18-8898-475a748b5...@iki.fi
Branch
--
master
Det
Lift limitation that PGPROC->links must be the first field
Since commit 5764f611e1, we've been using the ilist.h functions for
handling the linked list. There's no need for 'links' to be the first
element of the struct anymore, except for one call in InitProcess
where we used a straight cast from
Avoid 0-length memcpy to NULL with EXEC_BACKEND
memcpy(NULL, src, 0) is forbidden by POSIX, even though every
production version of libc allows it. Let's be tidy.
Per report from Thomas Munro, running UBSan with EXEC_BACKEND.
Backpatch to v17, where this code was added.
Discussion:
https://www.
Tighten check for --forkchild argument when spawning child process
Commit aafc05de1b removed all the other --fork* arguments. Altough
this is inconsequential, backpatch to v17 since this is new.
Author: Nathan Bossart
Discussion: https://www.postgresql.org/message-id/ZnCCEN0l3qWv-XpW@nathan
Bran
Avoid 0-length memcpy to NULL with EXEC_BACKEND
memcpy(NULL, src, 0) is forbidden by POSIX, even though every
production version of libc allows it. Let's be tidy.
Per report from Thomas Munro, running UBSan with EXEC_BACKEND.
Backpatch to v17, where this code was added.
Discussion:
https://www.
Tighten check for --forkchild argument when spawning child process
Commit aafc05de1b removed all the other --fork* arguments. Altough
this is inconsequential, backpatch to v17 since this is new.
Author: Nathan Bossart
Discussion: https://www.postgresql.org/message-id/ZnCCEN0l3qWv-XpW@nathan
Bran
Move bgworker specific logic to bgworker.c
For clarity, we've been slowly moving functions that are not called
from the postmaster process out of postmaster.c.
Author: Xing Guo
Discussion:
https://www.postgresql.org/message-id/CACpMh%2BDBHVT4xPGimzvex%3DwMdMLQEu9PYhT%2BkwwD2x2nu9dU_Q%40mail.gma
Remove redundant SetProcessingMode(InitProcessing) calls
After several refactoring iterations, auxiliary processes are no
longer initialized from the bootstrapper. Using the InitProcessing
mode for initializing auxiliary processes is more appropriate. Since
the global variable Mode is initialized
Fix missing installation/uninstallation rules for BackgroundPsql.pm
Commit d5fd7865 backported BackgroundPsql perl module module with
helper functions for tests running interactive or background psql
tasks to PG 12 to 15, but did not add installation/uninstallation
rules of the build system, causi
Fix missing installation/uninstallation rules for BackgroundPsql.pm
Commit d5fd7865 backported BackgroundPsql perl module module with
helper functions for tests running interactive or background psql
tasks to PG 12 to 15, but did not add installation/uninstallation
rules of the build system, causi
Fix missing installation/uninstallation rules for BackgroundPsql.pm
Commit d5fd7865 backported BackgroundPsql perl module module with
helper functions for tests running interactive or background psql
tasks to PG 12 to 15, but did not add installation/uninstallation
rules of the build system, causi
Fix missing installation/uninstallation rules for BackgroundPsql.pm
Commit d5fd7865 backported BackgroundPsql perl module module with
helper functions for tests running interactive or background psql
tasks to PG 12 to 15, but did not add installation/uninstallation
rules of the build system, causi
Fix MVCC bug with prepared xact with subxacts on standby
We did not recover the subtransaction IDs of prepared transactions
when starting a hot standby from a shutdown checkpoint. As a result,
such subtransactions were considered as aborted, rather than
in-progress. That would lead to hint bits be
tests: Trim newline from result returned by BackgroundPsql->query
This went unnoticed, because only a few existing callers of
BackgroundPsql->query used the result, and the ones that did were not
bothered by an extra newline. I noticed because I was about to add a
new test that checks the result.
tests: Trim newline from result returned by BackgroundPsql->query
This went unnoticed, because only a few existing callers of
BackgroundPsql->query used the result, and the ones that did were not
bothered by an extra newline. I noticed because I was about to add a
new test that checks the result.
Fix MVCC bug with prepared xact with subxacts on standby
We did not recover the subtransaction IDs of prepared transactions
when starting a hot standby from a shutdown checkpoint. As a result,
such subtransactions were considered as aborted, rather than
in-progress. That would lead to hint bits be
tests: Trim newline from result returned by BackgroundPsql->query
This went unnoticed, because only a few existing callers of
BackgroundPsql->query used the result, and the ones that did were not
bothered by an extra newline. I noticed because I was about to add a
new test that checks the result.
Fix MVCC bug with prepared xact with subxacts on standby
We did not recover the subtransaction IDs of prepared transactions
when starting a hot standby from a shutdown checkpoint. As a result,
such subtransactions were considered as aborted, rather than
in-progress. That would lead to hint bits be
tests: Trim newline from result returned by BackgroundPsql->query
This went unnoticed, because only a few existing callers of
BackgroundPsql->query used the result, and the ones that did were not
bothered by an extra newline. I noticed because I was about to add a
new test that checks the result.
Fix MVCC bug with prepared xact with subxacts on standby
We did not recover the subtransaction IDs of prepared transactions
when starting a hot standby from a shutdown checkpoint. As a result,
such subtransactions were considered as aborted, rather than
in-progress. That would lead to hint bits be
tests: Trim newline from result returned by BackgroundPsql->query
This went unnoticed, because only a few existing callers of
BackgroundPsql->query used the result, and the ones that did were not
bothered by an extra newline. I noticed because I was about to add a
new test that checks the result.
Fix MVCC bug with prepared xact with subxacts on standby
We did not recover the subtransaction IDs of prepared transactions
when starting a hot standby from a shutdown checkpoint. As a result,
such subtransactions were considered as aborted, rather than
in-progress. That would lead to hint bits be
Fix MVCC bug with prepared xact with subxacts on standby
We did not recover the subtransaction IDs of prepared transactions
when starting a hot standby from a shutdown checkpoint. As a result,
such subtransactions were considered as aborted, rather than
in-progress. That would lead to hint bits be
1 - 100 of 790 matches
Mail list logo