public inbox for [email protected]
help / color / mirror / Atom feed[PATCH 6/8] Add default_toast_compression GUC
3+ messages / 3 participants
[nested] [flat]
* [PATCH 6/8] Add default_toast_compression GUC
@ 2021-03-10 08:35 Dilip Kumar <[email protected]>
0 siblings, 0 replies; 3+ messages in thread
From: Dilip Kumar @ 2021-03-10 08:35 UTC (permalink / raw)
Justin Pryzby and Dilip Kumar
---
src/backend/access/common/toast_compression.c | 46 +++++++++++++++++++
src/backend/access/common/tupdesc.c | 2 +-
src/backend/bootstrap/bootstrap.c | 2 +-
src/backend/commands/tablecmds.c | 8 ++--
src/backend/utils/misc/guc.c | 12 +++++
src/backend/utils/misc/postgresql.conf.sample | 1 +
src/include/access/toast_compression.h | 22 ++++++++-
src/test/regress/expected/compression.out | 16 +++++++
src/test/regress/expected/compression_1.out | 19 ++++++++
src/test/regress/sql/compression.sql | 8 ++++
10 files changed, 128 insertions(+), 8 deletions(-)
diff --git a/src/backend/access/common/toast_compression.c b/src/backend/access/common/toast_compression.c
index 3463b42438..e33f92687c 100644
--- a/src/backend/access/common/toast_compression.c
+++ b/src/backend/access/common/toast_compression.c
@@ -55,6 +55,9 @@ const CompressionRoutine toast_compression[] =
}
};
+/* Compile-time default */
+char *default_toast_compression = DEFAULT_TOAST_COMPRESSION;
+
/*
* pglz_cmcompress - compression routine for pglz compression method
*
@@ -306,3 +309,46 @@ GetCompressionRoutines(char method)
{
return &toast_compression[CompressionMethodToId(method)];
}
+
+/* check_hook: validate new default_toast_compression */
+bool
+check_default_toast_compression(char **newval, void **extra, GucSource source)
+{
+ if (**newval == '\0')
+ {
+ GUC_check_errdetail("%s cannot be empty.",
+ "default_toast_compression");
+ return false;
+ }
+
+ if (strlen(*newval) >= NAMEDATALEN)
+ {
+ GUC_check_errdetail("%s is too long (maximum %d characters).",
+ "default_toast_compression", NAMEDATALEN - 1);
+ return false;
+ }
+
+ if (!CompressionMethodIsValid(CompressionNameToMethod(*newval)))
+ {
+ /*
+ * When source == PGC_S_TEST, don't throw a hard error for a
+ * nonexistent compression method, only a NOTICE. See comments in
+ * guc.h.
+ */
+ if (source == PGC_S_TEST)
+ {
+ ereport(NOTICE,
+ (errcode(ERRCODE_UNDEFINED_OBJECT),
+ errmsg("compression method \"%s\" does not exist",
+ *newval)));
+ }
+ else
+ {
+ GUC_check_errdetail("Compression method \"%s\" does not exist.",
+ *newval);
+ return false;
+ }
+ }
+
+ return true;
+}
diff --git a/src/backend/access/common/tupdesc.c b/src/backend/access/common/tupdesc.c
index a66d1113db..362a371a6c 100644
--- a/src/backend/access/common/tupdesc.c
+++ b/src/backend/access/common/tupdesc.c
@@ -668,7 +668,7 @@ TupleDescInitEntry(TupleDesc desc,
att->attcollation = typeForm->typcollation;
if (IsStorageCompressible(typeForm->typstorage))
- att->attcompression = DefaultCompressionMethod;
+ att->attcompression = GetDefaultToastCompression();
else
att->attcompression = InvalidCompressionMethod;
diff --git a/src/backend/bootstrap/bootstrap.c b/src/backend/bootstrap/bootstrap.c
index af0c0aa77e..9be0841d08 100644
--- a/src/backend/bootstrap/bootstrap.c
+++ b/src/backend/bootstrap/bootstrap.c
@@ -733,7 +733,7 @@ DefineAttr(char *name, char *type, int attnum, int nullness)
attrtypes[attnum]->atttypmod = -1;
attrtypes[attnum]->attislocal = true;
if (IsStorageCompressible(attrtypes[attnum]->attstorage))
- attrtypes[attnum]->attcompression = DefaultCompressionMethod;
+ attrtypes[attnum]->attcompression = GetDefaultToastCompression();
else
attrtypes[attnum]->attcompression = InvalidCompressionMethod;
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index e20dd5f63c..a0d2af0cde 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -11971,7 +11971,7 @@ ATExecAlterColumnType(AlteredTableInfo *tab, Relation rel,
if (!IsStorageCompressible(tform->typstorage))
attTup->attcompression = InvalidCompressionMethod;
else if (!CompressionMethodIsValid(attTup->attcompression))
- attTup->attcompression = DefaultCompressionMethod;
+ attTup->attcompression = GetDefaultToastCompression();
}
else
attTup->attcompression = InvalidCompressionMethod;
@@ -17847,9 +17847,9 @@ GetAttributeCompression(Form_pg_attribute att, char *compression)
/* fallback to default compression if it's not specified */
if (compression == NULL)
- return DefaultCompressionMethod;
-
- cmethod = CompressionNameToMethod(compression);
+ cmethod = GetDefaultToastCompression();
+ else
+ cmethod = CompressionNameToMethod(compression);
return cmethod;
}
diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c
index 953837085f..e59ed5b214 100644
--- a/src/backend/utils/misc/guc.c
+++ b/src/backend/utils/misc/guc.c
@@ -33,6 +33,7 @@
#include "access/gin.h"
#include "access/rmgr.h"
#include "access/tableam.h"
+#include "access/toast_compression.h"
#include "access/transam.h"
#include "access/twophase.h"
#include "access/xact.h"
@@ -3915,6 +3916,17 @@ static struct config_string ConfigureNamesString[] =
check_default_table_access_method, NULL, NULL
},
+ {
+ {"default_toast_compression", PGC_USERSET, CLIENT_CONN_STATEMENT,
+ gettext_noop("Sets the default compression for new columns."),
+ NULL,
+ GUC_IS_NAME
+ },
+ &default_toast_compression,
+ DEFAULT_TOAST_COMPRESSION,
+ check_default_toast_compression, NULL, NULL
+ },
+
{
{"default_tablespace", PGC_USERSET, CLIENT_CONN_STATEMENT,
gettext_noop("Sets the default tablespace to create tables and indexes in."),
diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample
index f46c2dd7a8..7d7a433dcc 100644
--- a/src/backend/utils/misc/postgresql.conf.sample
+++ b/src/backend/utils/misc/postgresql.conf.sample
@@ -659,6 +659,7 @@
#temp_tablespaces = '' # a list of tablespace names, '' uses
# only default tablespace
#default_table_access_method = 'heap'
+#default_toast_compression = 'pglz' # 'pglz' or 'lz4'
#check_function_bodies = on
#default_transaction_isolation = 'read committed'
#default_transaction_read_only = off
diff --git a/src/include/access/toast_compression.h b/src/include/access/toast_compression.h
index 38800cb97a..e9d9ce5634 100644
--- a/src/include/access/toast_compression.h
+++ b/src/include/access/toast_compression.h
@@ -15,6 +15,14 @@
#include "postgres.h"
+#include "utils/guc.h"
+
+/* default compression method if not specified. */
+#define DEFAULT_TOAST_COMPRESSION "pglz"
+
+/* GUCs */
+extern char *default_toast_compression;
+
/*
* Built-in compression methods. pg_attribute will store this in the
* attcompression column.
@@ -36,8 +44,6 @@ typedef enum CompressionId
LZ4_COMPRESSION_ID = 1
} CompressionId;
-/* use default compression method if it is not specified. */
-#define DefaultCompressionMethod PGLZ_COMPRESSION
#define IsValidCompression(cm) ((cm) != InvalidCompressionMethod)
#define IsStorageCompressible(storage) ((storage) != TYPSTORAGE_PLAIN && \
@@ -67,6 +73,8 @@ typedef struct CompressionRoutine
extern char CompressionNameToMethod(char *compression);
extern const CompressionRoutine *GetCompressionRoutines(char method);
+extern bool check_default_toast_compression(char **newval, void **extra,
+ GucSource source);
/*
* CompressionMethodToId - Convert compression method to compression id.
@@ -115,5 +123,15 @@ GetCompressionMethodName(char method)
return GetCompressionRoutines(method)->cmname;
}
+/*
+ * GetDefaultToastCompression -- get the current toast compression
+ *
+ * This exists to hide the use of the default_toast_compression GUC variable.
+ */
+static inline char
+GetDefaultToastCompression(void)
+{
+ return CompressionNameToMethod(default_toast_compression);
+}
#endif /* TOAST_COMPRESSION_H */
diff --git a/src/test/regress/expected/compression.out b/src/test/regress/expected/compression.out
index 6981d580dc..9ddffc8b18 100644
--- a/src/test/regress/expected/compression.out
+++ b/src/test/regress/expected/compression.out
@@ -231,6 +231,22 @@ CREATE TABLE cminh(f1 TEXT COMPRESSION lz4) INHERITS(cmdata);
NOTICE: merging column "f1" with inherited definition
ERROR: column "f1" has a compression method conflict
DETAIL: pglz versus lz4
+-- test default_toast_compression GUC
+SET default_toast_compression = '';
+ERROR: invalid value for parameter "default_toast_compression": ""
+DETAIL: default_toast_compression cannot be empty.
+SET default_toast_compression = 'I do not exist compression';
+ERROR: invalid value for parameter "default_toast_compression": "I do not exist compression"
+DETAIL: Compression method "I do not exist compression" does not exist.
+SET default_toast_compression = 'lz4';
+DROP TABLE cmdata2;
+CREATE TABLE cmdata2 (f1 text);
+\d+ cmdata2
+ Table "public.cmdata2"
+ Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description
+--------+------+-----------+----------+---------+----------+-------------+--------------+-------------
+ f1 | text | | | | extended | lz4 | |
+
-- check data is ok
SELECT length(f1) FROM cmdata;
length
diff --git a/src/test/regress/expected/compression_1.out b/src/test/regress/expected/compression_1.out
index 893c18c7fa..03a7f46554 100644
--- a/src/test/regress/expected/compression_1.out
+++ b/src/test/regress/expected/compression_1.out
@@ -237,6 +237,25 @@ CREATE TABLE cminh(f1 TEXT COMPRESSION lz4) INHERITS(cmdata);
NOTICE: merging column "f1" with inherited definition
ERROR: column "f1" has a compression method conflict
DETAIL: pglz versus lz4
+-- test default_toast_compression GUC
+SET default_toast_compression = '';
+ERROR: invalid value for parameter "default_toast_compression": ""
+DETAIL: default_toast_compression cannot be empty.
+SET default_toast_compression = 'I do not exist compression';
+ERROR: invalid value for parameter "default_toast_compression": "I do not exist compression"
+DETAIL: Compression method "I do not exist compression" does not exist.
+SET default_toast_compression = 'lz4';
+ERROR: unsupported LZ4 compression method
+DETAIL: This functionality requires the server to be built with lz4 support.
+HINT: You need to rebuild PostgreSQL using --with-lz4.
+DROP TABLE cmdata2;
+CREATE TABLE cmdata2 (f1 text);
+\d+ cmdata2
+ Table "public.cmdata2"
+ Column | Type | Collation | Nullable | Default | Storage | Compression | Stats target | Description
+--------+------+-----------+----------+---------+----------+-------------+--------------+-------------
+ f1 | text | | | | extended | pglz | |
+
-- check data is ok
SELECT length(f1) FROM cmdata;
length
diff --git a/src/test/regress/sql/compression.sql b/src/test/regress/sql/compression.sql
index b085c9fbd9..6c9b24f1f7 100644
--- a/src/test/regress/sql/compression.sql
+++ b/src/test/regress/sql/compression.sql
@@ -103,6 +103,14 @@ SELECT pg_column_compression(f1) FROM cmpart;
CREATE TABLE cminh() INHERITS(cmdata, cmdata1);
CREATE TABLE cminh(f1 TEXT COMPRESSION lz4) INHERITS(cmdata);
+-- test default_toast_compression GUC
+SET default_toast_compression = '';
+SET default_toast_compression = 'I do not exist compression';
+SET default_toast_compression = 'lz4';
+DROP TABLE cmdata2;
+CREATE TABLE cmdata2 (f1 text);
+\d+ cmdata2
+
-- check data is ok
SELECT length(f1) FROM cmdata;
SELECT length(f1) FROM cmdata1;
--
2.17.0
--cvVnyQ+4j833TQvp
Content-Type: text/x-diff; charset=us-ascii
Content-Disposition: attachment;
filename="0007-Alter-table-set-compression.patch"
^ permalink raw reply [nested|flat] 3+ messages in thread
* WaitEventSetWaitBlock() can still hang on Windows due to connection reset
@ 2024-10-22 10:00 Alexander Lakhin <[email protected]>
2025-04-17 07:10 ` RE: WaitEventSetWaitBlock() can still hang on Windows due to connection reset Hayato Kuroda (Fujitsu) <[email protected]>
0 siblings, 1 reply; 3+ messages in thread
From: Alexander Lakhin @ 2024-10-22 10:00 UTC (permalink / raw)
To: pgsql-hackers; Thomas Munro <[email protected]>
Hello hackers,
[ a follow-up to [1] separated to focus on this issue ]
Let me bring your attention to a failure [2], presented by drongo in the
last week, with the following diagnostics:
[10:30:30.954](2.110s) ok 5 - compare primary and standby dumps
### Restarting node "primary"
# Running: pg_ctl -w -D
C:\\prog\\bf\\root\\HEAD\\pgsql.build/testrun/recovery/027_stream_regress\\data/t_027_stream_regress_primary_data/pgdata
-l C:\\prog\\bf\\root\\HEAD\\pgsql.build/testrun/recovery/027_stream_regress\\log/027_stream_regress_primary.log restart
waiting for server to shut down.... done
server stopped
waiting for server to start.... done
server started
# Postmaster PID for node "primary" is 8908
Waiting for replication conn standby_1's replay_lsn to pass 0/158C8B98 on primary
[10:41:32.115](661.161s) # poll_query_until timed out executing this query:
# SELECT '0/158C8B98' <= replay_lsn AND state = 'streaming'
# FROM pg_catalog.pg_stat_replication
# WHERE application_name IN ('standby_1', 'walreceiver')
# expecting this output:
# t
# last actual query output:
#
027_stream_regress_standby_1.log contains:
2024-10-14 10:30:28.483 UTC [4320:12] 027_stream_regress.pl LOG: disconnection: session time: 0:00:03.793 user=pgrunner
database=postgres host=127.0.0.1 port=61748
2024-10-14 10:30:31.442 UTC [8468:2] LOG: replication terminated by primary server
2024-10-14 10:30:31.442 UTC [8468:3] DETAIL: End of WAL reached on timeline 1 at 0/158C8B98.
2024-10-14 10:30:31.442 UTC [8468:4] FATAL: could not send end-of-streaming message to primary: server closed the
connection unexpectedly
This probably means the server terminated abnormally
before or while processing the request.
no COPY in progress
2024-10-14 10:30:31.443 UTC [5452:7] LOG: invalid resource manager ID 101 at 0/158C8B98
2024-10-14 10:35:06.986 UTC [8648:21] LOG: restartpoint starting: time
2024-10-14 10:35:06.991 UTC [8648:22] LOG: restartpoint complete: wrote 0 buffers (0.0%), wrote 1 SLRU buffers; 0 WAL
file(s) added, 0 removed, 1 recycled; write=0.001 s, sync=0.001 s, total=0.005 s; sync files=0, longest=0.000 s,
average=0.000 s; distance=15336 kB, estimate=69375 kB; lsn=0/158C8B20, redo lsn=0/158C8B20
2024-10-14 10:35:06.991 UTC [8648:23] LOG: recovery restart point at 0/158C8B20
2024-10-14 10:35:06.991 UTC [8648:24] DETAIL: Last completed transaction was at log time 2024-10-14 10:30:24.820804+00.
2024-10-14 10:41:32.510 UTC [4220:4] LOG: received immediate shutdown request
(That is, primary was restarted, but standby didn't reconnect to it,
waiting for something...)
$node_primary->restart was added to 027_stream_regress.pl on 2024-06-27
(with 0844b3968), so this can explain why is it the first noticed failure
of this kind.
I managed to reproduce this failure locally, then I reduced the 027 test
to just restarting primary in a loop, and with debug logging added (please
find attached) I could see what makes standby hang:
2024-10-22 08:42:20.016 UTC [6652] DETAIL: End of WAL reached on timeline 1 at 0/5D14C98.
2024-10-22 08:42:20.016 UTC [6652] FATAL: could not send end-of-streaming message to primary: server closed the
connection unexpectedly
This probably means the server terminated abnormally
before or while processing the request.
no COPY in progress
2024-10-22 08:42:20.016 UTC [21268] LOG: invalid record length at 0/5D14C98: expected at least 24, got 0
2024-10-22 08:42:20.088 UTC [8256] LOG: !!!WalReceiverMain| before walrcv_connect
!!!libpqrcv_connect| before loop
!!!libpqrcv_connect| before WaitLatchOrSocket(io_flag: 64)
!!!libpqrcv_connect| after WaitLatchOrSocket, rc: 1
!!!libpqrcv_connect| before WaitLatchOrSocket(io_flag: 64)
!!!WaitEventSetWaitBlock| before WaitForMultipleObjects
!!!WaitEventSetWaitBlock| WaitForMultipleObjects returned: 3
!!!libpqrcv_connect| after WaitLatchOrSocket, rc: 64
!!!libpqrcv_connect| before WaitLatchOrSocket(io_flag: 4)
!!!libpqrcv_connect| after WaitLatchOrSocket, rc: 4
!!!libpqrcv_connect| before WaitLatchOrSocket(io_flag: 2)
!!!WaitEventSetWaitBlock| WL_SOCKET_READABLE, cur_event->fd: 844, WSAGetLastError(): 10054
!!!WaitEventSetWaitBlock| before WaitForMultipleObjects
2024-10-22 08:44:49.399 UTC [15352] LOG: restartpoint starting: time
...
While for a previous successful reconnect we can see:
2024-10-22 08:42:17.275 UTC [6652] LOG: !!!WalReceiverMain| before walrcv_connect
!!!libpqrcv_connect| before loop
!!!libpqrcv_connect| before WaitLatchOrSocket(io_flag: 64)
!!!libpqrcv_connect| after WaitLatchOrSocket, rc: 1
!!!libpqrcv_connect| before WaitLatchOrSocket(io_flag: 64)
!!!WaitEventSetWaitBlock| before WaitForMultipleObjects
!!!WaitEventSetWaitBlock| WaitForMultipleObjects returned: 3
!!!libpqrcv_connect| after WaitLatchOrSocket, rc: 64
!!!libpqrcv_connect| before WaitLatchOrSocket(io_flag: 4)
!!!libpqrcv_connect| after WaitLatchOrSocket, rc: 4
!!!libpqrcv_connect| before WaitLatchOrSocket(io_flag: 2)
!!!WaitEventSetWaitBlock| WL_SOCKET_READABLE, cur_event->fd: 844, WSAGetLastError(): 10035
!!!WaitEventSetWaitBlock| before WaitForMultipleObjects
!!!WaitEventSetWaitBlock| WaitForMultipleObjects returned: 3
!!!libpqrcv_connect| after WaitLatchOrSocket, rc: 2
!!!libpqrcv_connect| before WaitLatchOrSocket(io_flag: 4)
!!!libpqrcv_connect| after WaitLatchOrSocket, rc: 4
!!!libpqrcv_connect| before WaitLatchOrSocket(io_flag: 2)
!!!WaitEventSetWaitBlock| WL_SOCKET_READABLE, cur_event->fd: 844, WSAGetLastError(): 10035
!!!WaitEventSetWaitBlock| before WaitForMultipleObjects
!!!WaitEventSetWaitBlock| WaitForMultipleObjects returned: 3
!!!libpqrcv_connect| after WaitLatchOrSocket, rc: 2
!!!libpqrcv_connect| before WaitLatchOrSocket(io_flag: 2)
!!!WaitEventSetWaitBlock| WL_SOCKET_READABLE, cur_event->fd: 844, WSAGetLastError(): 10035
!!!WaitEventSetWaitBlock| before WaitForMultipleObjects
!!!WaitEventSetWaitBlock| WaitForMultipleObjects returned: 3
!!!libpqrcv_connect| after WaitLatchOrSocket, rc: 2
!!!libpqrcv_connect| before WaitLatchOrSocket(io_flag: 2)
!!!WaitEventSetWaitBlock| WL_SOCKET_READABLE, cur_event->fd: 844, WSAGetLastError(): 10035
!!!WaitEventSetWaitBlock| before WaitForMultipleObjects
!!!WaitEventSetWaitBlock| WaitForMultipleObjects returned: 3
!!!libpqrcv_connect| after WaitLatchOrSocket, rc: 2
!!!libpqrcv_connect| after loop
(The full log is attached too.)
In other words, if WSARecv() fails with WSAECONNRESET, calling
WaitForMultipleObjects() still leads to the hang.
I reproduced this on a8458f508~1 and on 97d891010, so the issue itself is
not new...
[1] https://www.postgresql.org/message-id/CA%2BhUKGKn%2BxWjaEnQ%2BiYYs7STG7_nNP5w5VMb1vSvQfAkkOxOUA%40ma...
[2] https://buildfarm.postgresql.org/cgi-bin/show_log.pl?nm=drongo&dt=2024-10-14%2010%3A08%3A17
Best regards,
Alexander
Attachments:
[application/x-perl] 099_primary_restart.pl (1.4K, ../../[email protected]/2-099_primary_restart.pl)
download
[text/x-log] 099_primary_restart_standby_1.log (190.3K, ../../[email protected]/3-099_primary_restart_standby_1.log)
download
[text/x-patch] walreceiver-win-socket-debugging.patch (3.9K, ../../[email protected]/4-walreceiver-win-socket-debugging.patch)
download | inline diff:
diff --git a/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c b/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c
index 97f957cd87..9acf524e8f 100644
--- a/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c
+++ b/src/backend/replication/libpqwalreceiver/libpqwalreceiver.c
@@ -221,6 +221,7 @@ libpqrcv_connect(const char *conninfo, bool replication, bool logical,
* Per spec for PQconnectPoll, first wait till socket is write-ready.
*/
status = PGRES_POLLING_WRITING;
+fprintf(stderr, "!!!libpqrcv_connect| before loop\n");
do
{
int io_flag;
@@ -236,11 +237,16 @@ libpqrcv_connect(const char *conninfo, bool replication, bool logical,
else
io_flag = WL_SOCKET_WRITEABLE;
+fprintf(stderr, "!!!libpqrcv_connect| before WaitLatchOrSocket(io_flag: %d)\n",
+io_flag);
+debug_latch = true;
rc = WaitLatchOrSocket(MyLatch,
WL_EXIT_ON_PM_DEATH | WL_LATCH_SET | io_flag,
PQsocket(conn->streamConn),
0,
WAIT_EVENT_LIBPQWALRECEIVER_CONNECT);
+debug_latch = false;
+fprintf(stderr, "!!!libpqrcv_connect| after WaitLatchOrSocket, rc: %d\n", rc);
/* Interrupted? */
if (rc & WL_LATCH_SET)
@@ -253,6 +267,7 @@ libpqrcv_connect(const char *conninfo, bool replication, bool logical,
if (rc & io_flag)
status = PQconnectPoll(conn->streamConn);
} while (status != PGRES_POLLING_OK && status != PGRES_POLLING_FAILED);
+fprintf(stderr, "!!!libpqrcv_connect| after loop\n");
if (PQstatus(conn->streamConn) != CONNECTION_OK)
goto bad_connection_errmsg;
diff --git a/src/backend/replication/walreceiver.c b/src/backend/replication/walreceiver.c
index a27aee63de..e14d8cbd59 100644
--- a/src/backend/replication/walreceiver.c
+++ b/src/backend/replication/walreceiver.c
@@ -300,12 +300,14 @@ WalReceiverMain(char *startup_data, size_t startup_data_len)
/* Establish the connection to the primary for XLOG streaming */
appname = cluster_name[0] ? cluster_name : "walreceiver";
+elog(LOG, "!!!WalReceiverMain| before walrcv_connect");
wrconn = walrcv_connect(conninfo, true, false, false, appname, &err);
if (!wrconn)
ereport(ERROR,
(errcode(ERRCODE_CONNECTION_FAILURE),
errmsg("streaming replication receiver \"%s\" could not connect to the primary server: %s",
appname, err)));
+elog(LOG, "!!!WalReceiverMain| wrconn: %p", wrconn);
/*
* Save user-visible connection string. This clobbers the original
diff --git a/src/backend/storage/ipc/latch.c b/src/backend/storage/ipc/latch.c
index 608eb66abe..e6506cf6a3 100644
--- a/src/backend/storage/ipc/latch.c
+++ b/src/backend/storage/ipc/latch.c
@@ -98,6 +98,8 @@
#endif
#endif
+bool debug_latch = false;
+
/* typedef in latch.h */
struct WaitEventSet
{
@@ -2029,6 +2034,8 @@ WaitEventSetWaitBlock(WaitEventSet *set, int cur_timeout,
occurred_events->fd = cur_event->fd;
return 1;
}
+if (debug_latch)
+fprintf(stderr, "\t!!!WaitEventSetWaitBlock| WL_SOCKET_READABLE, cur_event->fd: %d, WSAGetLastError(): %d\n", cur_event->fd, WSAGetLastError());
}
/*
@@ -2069,8 +2076,12 @@ WaitEventSetWaitBlock(WaitEventSet *set, int cur_timeout,
*
* Need to wait for ->nevents + 1, because signal handle is in [0].
*/
+if (debug_latch)
+fprintf(stderr, "\t!!!WaitEventSetWaitBlock| before WaitForMultipleObjects\n");
rc = WaitForMultipleObjects(set->nevents + 1, set->handles, FALSE,
cur_timeout);
+if (debug_latch)
+fprintf(stderr, "\t!!!WaitEventSetWaitBlock| WaitForMultipleObjects returned: %d\n", rc);
/* Check return code */
if (rc == WAIT_FAILED)
diff --git a/src/include/storage/latch.h b/src/include/storage/latch.h
index 7e194d536f..5387afdedc 100644
--- a/src/include/storage/latch.h
+++ b/src/include/storage/latch.h
@@ -193,4 +193,5 @@ extern void InitializeLatchWaitSet(void);
extern int GetNumRegisteredWaitEvents(WaitEventSet *set);
extern bool WaitEventSetCanReportClosed(void);
+extern PGDLLIMPORT bool debug_latch;
#endif /* LATCH_H */
^ permalink raw reply [nested|flat] 3+ messages in thread
* RE: WaitEventSetWaitBlock() can still hang on Windows due to connection reset
2024-10-22 10:00 WaitEventSetWaitBlock() can still hang on Windows due to connection reset Alexander Lakhin <[email protected]>
@ 2025-04-17 07:10 ` Hayato Kuroda (Fujitsu) <[email protected]>
0 siblings, 0 replies; 3+ messages in thread
From: Hayato Kuroda (Fujitsu) @ 2025-04-17 07:10 UTC (permalink / raw)
To: 'Alexander Lakhin' <[email protected]>; +Cc: pgsql-hackers; Thomas Munro <[email protected]>
Dear Alexander,
While analyzing the BF failure [1], I noticed that the same issue may happen here,
which means apply worker waited something. According to the log, apply worker (PID 2820)
stucked so that logical replication could not restart.
Regress log:
```
### Restarting node "pub"
# Running: pg_ctl --wait --pgdata C:\\prog\\bf\\root\\HEAD\\pgsql.build/...
waiting for server to shut down.... done
server stopped
waiting for server to start.... done
server started
# Postmaster PID for node "pub" is 980
timed out waiting for match: (?^:Streaming transactions committing after ([A-F0-9]+/[A-F0-9]+), ...
```
Subscriber log;
```
2025-04-12 05:08:44.630 UTC [2820:1] LOG: logical replication apply worker for subscription "sub" has started
2025-04-12 05:08:44.642 UTC [5652:6] LOG: background worker "logical replication apply worker" (PID 6344) exited with exit code 1
2025-04-12 05:13:27.352 UTC [3988:1] LOG: checkpoint starting: time
2025-04-12 05:13:36.825 UTC [3988:2] LOG: checkpoint complete: wrote 62 buffers ...
2025-04-12 05:15:01.265 UTC [5652:7] LOG: received immediate shutdown request
2025-04-12 05:15:01.353 UTC [5652:8] LOG: database system is shut down
```
Publisher log;
```
2025-04-12 05:08:44.634 UTC [1112:7] LOG: database system is shut down
2025-04-12 05:08:45.685 UTC [980:1] LOG: starting PostgreSQL 18devel on...
2025-04-12 05:08:45.687 UTC [980:2] LOG: listening on IPv4 address "127.0.0.1", port 18057
2025-04-12 05:08:46.225 UTC [4392:1] LOG: database system was shut down at 2025-04-12 05:08:43 UTC
2025-04-12 05:08:46.319 UTC [980:3] LOG: database system is ready to accept connections
2025-04-12 05:15:00.408 UTC [980:4] LOG: received immediate shutdown request
2025-04-12 05:15:00.942 UTC [980:5] LOG: database system is shut down
```
Now the report has been reported for both physical and logical replication,
but I suspected that this can happen for all the application.
[1]: https://buildfarm.postgresql.org/cgi-bin/show_stage_log.pl?nm=drongo&dt=2025-04-12%2003%3A59%3A3...
Best regards,
Hayato Kuroda
FUJITSU LIMITED
^ permalink raw reply [nested|flat] 3+ messages in thread
end of thread, other threads:[~2025-04-17 07:10 UTC | newest]
Thread overview: 3+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2021-03-10 08:35 [PATCH 6/8] Add default_toast_compression GUC Dilip Kumar <[email protected]>
2024-10-22 10:00 WaitEventSetWaitBlock() can still hang on Windows due to connection reset Alexander Lakhin <[email protected]>
2025-04-17 07:10 ` RE: WaitEventSetWaitBlock() can still hang on Windows due to connection reset Hayato Kuroda (Fujitsu) <[email protected]>
This inbox is served by agora; see mirroring instructions
for how to clone and mirror all data and code used for this inbox