mirror of
https://github.com/postgres/postgres.git
synced 2025-05-20 00:03:14 -04:00
Revert "Allow on-line enabling and disabling of data checksums"
This reverts the backend sides of commit 1fde38beaa0c3e66c340efc7cc0dc272d6254bb0. I have, at least for now, left the pg_verify_checksums tool in place, as this tool can be very valuable without the rest of the patch as well, and since it's a read-only tool that only runs when the cluster is down it should be a lot safer.
This commit is contained in:
parent
03c11796a9
commit
a228cc13ae
@ -19566,71 +19566,6 @@ postgres=# SELECT * FROM pg_walfile_name_offset(pg_stop_backup());
|
||||
|
||||
</sect2>
|
||||
|
||||
<sect2 id="functions-admin-checksum">
|
||||
<title>Data Checksum Functions</title>
|
||||
|
||||
<para>
|
||||
The functions shown in <xref linkend="functions-checksums-table" /> can
|
||||
be used to enable or disable data checksums in a running cluster.
|
||||
See <xref linkend="checksums" /> for details.
|
||||
</para>
|
||||
|
||||
<table id="functions-checksums-table">
|
||||
<title>Checksum <acronym>SQL</acronym> Functions</title>
|
||||
<tgroup cols="3">
|
||||
<thead>
|
||||
<row>
|
||||
<entry>Function</entry>
|
||||
<entry>Return Type</entry>
|
||||
<entry>Description</entry>
|
||||
</row>
|
||||
</thead>
|
||||
<tbody>
|
||||
<row>
|
||||
<entry>
|
||||
<indexterm>
|
||||
<primary>pg_enable_data_checksums</primary>
|
||||
</indexterm>
|
||||
<literal><function>pg_enable_data_checksums(<optional><parameter>cost_delay</parameter> <type>int</type>, <parameter>cost_limit</parameter> <type>int</type></optional>)</function></literal>
|
||||
</entry>
|
||||
<entry>
|
||||
void
|
||||
</entry>
|
||||
<entry>
|
||||
<para>
|
||||
Initiates data checksums for the cluster. This will switch the data checksums mode
|
||||
to <literal>in progress</literal> and start a background worker that will process
|
||||
all data in the database and enable checksums for it. When all data pages have had
|
||||
checksums enabled, the cluster will automatically switch to checksums
|
||||
<literal>on</literal>.
|
||||
</para>
|
||||
<para>
|
||||
If <parameter>cost_delay</parameter> and <parameter>cost_limit</parameter> are
|
||||
specified, the speed of the process is throttled using the same principles as
|
||||
<link linkend="runtime-config-resource-vacuum-cost">Cost-based Vacuum Delay</link>.
|
||||
</para>
|
||||
</entry>
|
||||
</row>
|
||||
<row>
|
||||
<entry>
|
||||
<indexterm>
|
||||
<primary>pg_disable_data_checksums</primary>
|
||||
</indexterm>
|
||||
<literal><function>pg_disable_data_checksums()</function></literal>
|
||||
</entry>
|
||||
<entry>
|
||||
void
|
||||
</entry>
|
||||
<entry>
|
||||
Disables data checksums for the cluster.
|
||||
</entry>
|
||||
</row>
|
||||
</tbody>
|
||||
</tgroup>
|
||||
</table>
|
||||
|
||||
</sect2>
|
||||
|
||||
<sect2 id="functions-admin-dbobject">
|
||||
<title>Database Object Management Functions</title>
|
||||
|
||||
|
@ -214,9 +214,9 @@ PostgreSQL documentation
|
||||
<para>
|
||||
Use checksums on data pages to help detect corruption by the
|
||||
I/O system that would otherwise be silent. Enabling checksums
|
||||
may incur a noticeable performance penalty. If set, checksums
|
||||
are calculated for all objects, in all databases. See
|
||||
<xref linkend="checksums" /> for details.
|
||||
may incur a noticeable performance penalty. This option can only
|
||||
be set during initialization, and cannot be changed later. If
|
||||
set, checksums are calculated for all objects, in all databases.
|
||||
</para>
|
||||
</listitem>
|
||||
</varlistentry>
|
||||
|
@ -284,7 +284,6 @@
|
||||
&pgtestfsync;
|
||||
&pgtesttiming;
|
||||
&pgupgrade;
|
||||
&pgVerifyChecksums;
|
||||
&pgwaldump;
|
||||
&postgres;
|
||||
&postmaster;
|
||||
|
@ -230,87 +230,6 @@
|
||||
</para>
|
||||
</sect1>
|
||||
|
||||
<sect1 id="checksums">
|
||||
<title>Data checksums</title>
|
||||
<indexterm>
|
||||
<primary>checksums</primary>
|
||||
</indexterm>
|
||||
|
||||
<para>
|
||||
Data pages are not checksum protected by default, but this can optionally be enabled for a cluster.
|
||||
When enabled, each data page will be assigned a checksum that is updated when the page is
|
||||
written and verified every time the page is read. Only data pages are protected by checksums,
|
||||
internal data structures and temporary files are not.
|
||||
</para>
|
||||
|
||||
<para>
|
||||
Checksums are normally enabled when the cluster is initialized using
|
||||
<link linkend="app-initdb-data-checksums"><application>initdb</application></link>. They
|
||||
can also be enabled or disabled at runtime. In all cases, checksums are enabled or disabled
|
||||
at the full cluster level, and cannot be specified individually for databases or tables.
|
||||
</para>
|
||||
|
||||
<para>
|
||||
The current state of checksums in the cluster can be verified by viewing the value
|
||||
of the read-only configuration variable <xref linkend="guc-data-checksums" /> by
|
||||
issuing the command <command>SHOW data_checksums</command>.
|
||||
</para>
|
||||
|
||||
<para>
|
||||
When attempting to recover from corrupt data it may be necessary to bypass the checksum
|
||||
protection in order to recover data. To do this, temporarily set the configuration parameter
|
||||
<xref linkend="guc-ignore-checksum-failure" />.
|
||||
</para>
|
||||
|
||||
<sect2 id="checksums-enable-disable">
|
||||
<title>On-line enabling of checksums</title>
|
||||
|
||||
<para>
|
||||
Checksums can be enabled or disabled online, by calling the appropriate
|
||||
<link linkend="functions-admin-checksum">functions</link>.
|
||||
Disabling of checksums takes effect immediately when the function is called.
|
||||
</para>
|
||||
|
||||
<para>
|
||||
Enabling checksums will put the cluster in <literal>inprogress</literal> mode.
|
||||
During this time, checksums will be written but not verified. In addition to
|
||||
this, a background worker process is started that enables checksums on all
|
||||
existing data in the cluster. Once this worker has completed processing all
|
||||
databases in the cluster, the checksum mode will automatically switch to
|
||||
<literal>on</literal>.
|
||||
</para>
|
||||
|
||||
<para>
|
||||
The process will initially wait for all open transactions to finish before
|
||||
it starts, so that it can be certain that there are no tables that have been
|
||||
created inside a transaction that has not committed yet and thus would not
|
||||
be visible to the process enabling checksums. It will also, for each database,
|
||||
wait for all pre-existing temporary tables to get removed before it finishes.
|
||||
If long-lived temporary tables are used in the application it may be necessary
|
||||
to terminate these application connections to allow the process to complete.
|
||||
Information about open transactions and connections with temporary tables is
|
||||
written to log.
|
||||
</para>
|
||||
|
||||
<para>
|
||||
If the cluster is stopped while in <literal>inprogress</literal> mode, for
|
||||
any reason, then this process must be restarted manually. To do this,
|
||||
re-execute the function <function>pg_enable_data_checksums()</function>
|
||||
once the cluster has been restarted. It is not possible to resume the work,
|
||||
the process has to start over and re-process the cluster.
|
||||
</para>
|
||||
|
||||
<note>
|
||||
<para>
|
||||
Enabling checksums can cause significant I/O to the system, as most of the
|
||||
database pages will need to be rewritten, and will be written both to the
|
||||
data files and the WAL.
|
||||
</para>
|
||||
</note>
|
||||
|
||||
</sect2>
|
||||
</sect1>
|
||||
|
||||
<sect1 id="wal-intro">
|
||||
<title>Write-Ahead Logging (<acronym>WAL</acronym>)</title>
|
||||
|
||||
|
@ -17,7 +17,6 @@
|
||||
#include "access/xlog.h"
|
||||
#include "access/xlog_internal.h"
|
||||
#include "catalog/pg_control.h"
|
||||
#include "storage/bufpage.h"
|
||||
#include "utils/guc.h"
|
||||
#include "utils/timestamp.h"
|
||||
|
||||
@ -138,18 +137,6 @@ xlog_desc(StringInfo buf, XLogReaderState *record)
|
||||
xlrec.ThisTimeLineID, xlrec.PrevTimeLineID,
|
||||
timestamptz_to_str(xlrec.end_time));
|
||||
}
|
||||
else if (info == XLOG_CHECKSUMS)
|
||||
{
|
||||
xl_checksum_state xlrec;
|
||||
|
||||
memcpy(&xlrec, rec, sizeof(xl_checksum_state));
|
||||
if (xlrec.new_checksumtype == PG_DATA_CHECKSUM_VERSION)
|
||||
appendStringInfo(buf, "on");
|
||||
else if (xlrec.new_checksumtype == PG_DATA_CHECKSUM_INPROGRESS_VERSION)
|
||||
appendStringInfo(buf, "inprogress");
|
||||
else
|
||||
appendStringInfo(buf, "off");
|
||||
}
|
||||
}
|
||||
|
||||
const char *
|
||||
@ -195,9 +182,6 @@ xlog_identify(uint8 info)
|
||||
case XLOG_FPI_FOR_HINT:
|
||||
id = "FPI_FOR_HINT";
|
||||
break;
|
||||
case XLOG_CHECKSUMS:
|
||||
id = "CHECKSUMS";
|
||||
break;
|
||||
}
|
||||
|
||||
return id;
|
||||
|
@ -856,7 +856,6 @@ static void SetLatestXTime(TimestampTz xtime);
|
||||
static void SetCurrentChunkStartTime(TimestampTz xtime);
|
||||
static void CheckRequiredParameterValues(void);
|
||||
static void XLogReportParameters(void);
|
||||
static void XlogChecksums(ChecksumType new_type);
|
||||
static void checkTimeLineSwitch(XLogRecPtr lsn, TimeLineID newTLI,
|
||||
TimeLineID prevTLI);
|
||||
static void LocalSetXLogInsertAllowed(void);
|
||||
@ -1034,7 +1033,7 @@ XLogInsertRecord(XLogRecData *rdata,
|
||||
Assert(RedoRecPtr < Insert->RedoRecPtr);
|
||||
RedoRecPtr = Insert->RedoRecPtr;
|
||||
}
|
||||
doPageWrites = (Insert->fullPageWrites || Insert->forcePageWrites || DataChecksumsInProgress());
|
||||
doPageWrites = (Insert->fullPageWrites || Insert->forcePageWrites);
|
||||
|
||||
if (fpw_lsn != InvalidXLogRecPtr && fpw_lsn <= RedoRecPtr && doPageWrites)
|
||||
{
|
||||
@ -4674,6 +4673,10 @@ ReadControlFile(void)
|
||||
(SizeOfXLogLongPHD - SizeOfXLogShortPHD);
|
||||
|
||||
CalculateCheckpointSegments();
|
||||
|
||||
/* Make the initdb settings visible as GUC variables, too */
|
||||
SetConfigOption("data_checksums", DataChecksumsEnabled() ? "yes" : "no",
|
||||
PGC_INTERNAL, PGC_S_OVERRIDE);
|
||||
}
|
||||
|
||||
void
|
||||
@ -4745,90 +4748,12 @@ GetMockAuthenticationNonce(void)
|
||||
* Are checksums enabled for data pages?
|
||||
*/
|
||||
bool
|
||||
DataChecksumsNeedWrite(void)
|
||||
DataChecksumsEnabled(void)
|
||||
{
|
||||
Assert(ControlFile != NULL);
|
||||
return (ControlFile->data_checksum_version > 0);
|
||||
}
|
||||
|
||||
bool
|
||||
DataChecksumsNeedVerify(void)
|
||||
{
|
||||
Assert(ControlFile != NULL);
|
||||
|
||||
/*
|
||||
* Only verify checksums if they are fully enabled in the cluster. In
|
||||
* inprogress state they are only updated, not verified.
|
||||
*/
|
||||
return (ControlFile->data_checksum_version == PG_DATA_CHECKSUM_VERSION);
|
||||
}
|
||||
|
||||
bool
|
||||
DataChecksumsInProgress(void)
|
||||
{
|
||||
Assert(ControlFile != NULL);
|
||||
return (ControlFile->data_checksum_version == PG_DATA_CHECKSUM_INPROGRESS_VERSION);
|
||||
}
|
||||
|
||||
void
|
||||
SetDataChecksumsInProgress(void)
|
||||
{
|
||||
Assert(ControlFile != NULL);
|
||||
if (ControlFile->data_checksum_version > 0)
|
||||
return;
|
||||
|
||||
XlogChecksums(PG_DATA_CHECKSUM_INPROGRESS_VERSION);
|
||||
|
||||
LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
|
||||
ControlFile->data_checksum_version = PG_DATA_CHECKSUM_INPROGRESS_VERSION;
|
||||
UpdateControlFile();
|
||||
LWLockRelease(ControlFileLock);
|
||||
}
|
||||
|
||||
void
|
||||
SetDataChecksumsOn(void)
|
||||
{
|
||||
Assert(ControlFile != NULL);
|
||||
|
||||
LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
|
||||
|
||||
if (ControlFile->data_checksum_version != PG_DATA_CHECKSUM_INPROGRESS_VERSION)
|
||||
{
|
||||
LWLockRelease(ControlFileLock);
|
||||
elog(ERROR, "Checksums not in inprogress mode");
|
||||
}
|
||||
|
||||
ControlFile->data_checksum_version = PG_DATA_CHECKSUM_VERSION;
|
||||
UpdateControlFile();
|
||||
LWLockRelease(ControlFileLock);
|
||||
|
||||
XlogChecksums(PG_DATA_CHECKSUM_VERSION);
|
||||
}
|
||||
|
||||
void
|
||||
SetDataChecksumsOff(void)
|
||||
{
|
||||
LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
|
||||
|
||||
ControlFile->data_checksum_version = 0;
|
||||
UpdateControlFile();
|
||||
LWLockRelease(ControlFileLock);
|
||||
|
||||
XlogChecksums(0);
|
||||
}
|
||||
|
||||
/* guc hook */
|
||||
const char *
|
||||
show_data_checksums(void)
|
||||
{
|
||||
if (ControlFile->data_checksum_version == PG_DATA_CHECKSUM_VERSION)
|
||||
return "on";
|
||||
else if (ControlFile->data_checksum_version == PG_DATA_CHECKSUM_INPROGRESS_VERSION)
|
||||
return "inprogress";
|
||||
else
|
||||
return "off";
|
||||
}
|
||||
|
||||
/*
|
||||
* Returns a fake LSN for unlogged relations.
|
||||
*
|
||||
@ -7863,16 +7788,6 @@ StartupXLOG(void)
|
||||
*/
|
||||
CompleteCommitTsInitialization();
|
||||
|
||||
/*
|
||||
* If we reach this point with checksums in inprogress state, we notify
|
||||
* the user that they need to manually restart the process to enable
|
||||
* checksums.
|
||||
*/
|
||||
if (ControlFile->data_checksum_version == PG_DATA_CHECKSUM_INPROGRESS_VERSION)
|
||||
ereport(WARNING,
|
||||
(errmsg("checksum state is \"inprogress\" with no worker"),
|
||||
errhint("Either disable or enable checksums by calling the pg_disable_data_checksums() or pg_enable_data_checksums() functions.")));
|
||||
|
||||
/*
|
||||
* All done with end-of-recovery actions.
|
||||
*
|
||||
@ -9626,22 +9541,6 @@ XLogReportParameters(void)
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Log the new state of checksums
|
||||
*/
|
||||
static void
|
||||
XlogChecksums(ChecksumType new_type)
|
||||
{
|
||||
xl_checksum_state xlrec;
|
||||
|
||||
xlrec.new_checksumtype = new_type;
|
||||
|
||||
XLogBeginInsert();
|
||||
XLogRegisterData((char *) &xlrec, sizeof(xl_checksum_state));
|
||||
|
||||
XLogInsert(RM_XLOG_ID, XLOG_CHECKSUMS);
|
||||
}
|
||||
|
||||
/*
|
||||
* Update full_page_writes in shared memory, and write an
|
||||
* XLOG_FPW_CHANGE record if necessary.
|
||||
@ -10070,17 +9969,6 @@ xlog_redo(XLogReaderState *record)
|
||||
/* Keep track of full_page_writes */
|
||||
lastFullPageWrites = fpw;
|
||||
}
|
||||
else if (info == XLOG_CHECKSUMS)
|
||||
{
|
||||
xl_checksum_state state;
|
||||
|
||||
memcpy(&state, XLogRecGetData(record), sizeof(xl_checksum_state));
|
||||
|
||||
LWLockAcquire(ControlFileLock, LW_EXCLUSIVE);
|
||||
ControlFile->data_checksum_version = state.new_checksumtype;
|
||||
UpdateControlFile();
|
||||
LWLockRelease(ControlFileLock);
|
||||
}
|
||||
}
|
||||
|
||||
#ifdef WAL_DEBUG
|
||||
|
@ -24,7 +24,6 @@
|
||||
#include "catalog/pg_type.h"
|
||||
#include "funcapi.h"
|
||||
#include "miscadmin.h"
|
||||
#include "postmaster/checksumhelper.h"
|
||||
#include "replication/walreceiver.h"
|
||||
#include "storage/smgr.h"
|
||||
#include "utils/builtins.h"
|
||||
@ -699,61 +698,3 @@ pg_backup_start_time(PG_FUNCTION_ARGS)
|
||||
|
||||
PG_RETURN_DATUM(xtime);
|
||||
}
|
||||
|
||||
/*
|
||||
* Disables checksums for the cluster, unless already disabled.
|
||||
*
|
||||
* Has immediate effect - the checksums are set to off right away.
|
||||
*/
|
||||
Datum
|
||||
disable_data_checksums(PG_FUNCTION_ARGS)
|
||||
{
|
||||
/*
|
||||
* If we don't need to write new checksums, then clearly they are already
|
||||
* disabled.
|
||||
*/
|
||||
if (!DataChecksumsNeedWrite())
|
||||
ereport(ERROR,
|
||||
(errmsg("data checksums already disabled")));
|
||||
|
||||
ShutdownChecksumHelperIfRunning();
|
||||
|
||||
SetDataChecksumsOff();
|
||||
|
||||
PG_RETURN_VOID();
|
||||
}
|
||||
|
||||
/*
|
||||
* Enables checksums for the cluster, unless already enabled.
|
||||
*
|
||||
* Supports vacuum-like cost-based throttling, to limit system load.
|
||||
* Starts a background worker that updates checksums on existing data.
|
||||
*/
|
||||
Datum
|
||||
enable_data_checksums(PG_FUNCTION_ARGS)
|
||||
{
|
||||
int cost_delay = PG_GETARG_INT32(0);
|
||||
int cost_limit = PG_GETARG_INT32(1);
|
||||
|
||||
if (cost_delay < 0)
|
||||
ereport(ERROR,
|
||||
(errmsg("cost delay cannot be less than zero")));
|
||||
if (cost_limit <= 0)
|
||||
ereport(ERROR,
|
||||
(errmsg("cost limit must be a positive value")));
|
||||
|
||||
/*
|
||||
* Allow state change from "off" or from "inprogress", since this is how
|
||||
* we restart the worker if necessary.
|
||||
*/
|
||||
if (DataChecksumsNeedVerify())
|
||||
ereport(ERROR,
|
||||
(errmsg("data checksums already enabled")));
|
||||
|
||||
SetDataChecksumsInProgress();
|
||||
if (!StartChecksumHelperLauncher(cost_delay, cost_limit))
|
||||
ereport(ERROR,
|
||||
(errmsg("failed to start checksum helper process")));
|
||||
|
||||
PG_RETURN_VOID();
|
||||
}
|
||||
|
@ -1027,11 +1027,6 @@ CREATE OR REPLACE FUNCTION pg_stop_backup (
|
||||
RETURNS SETOF record STRICT VOLATILE LANGUAGE internal as 'pg_stop_backup_v2'
|
||||
PARALLEL RESTRICTED;
|
||||
|
||||
CREATE OR REPLACE FUNCTION pg_enable_data_checksums (
|
||||
cost_delay int DEFAULT 0, cost_limit int DEFAULT 100)
|
||||
RETURNS void STRICT VOLATILE LANGUAGE internal AS 'enable_data_checksums'
|
||||
PARALLEL RESTRICTED;
|
||||
|
||||
-- legacy definition for compatibility with 9.3
|
||||
CREATE OR REPLACE FUNCTION
|
||||
json_populate_record(base anyelement, from_json json, use_json_as_text boolean DEFAULT false)
|
||||
|
@ -12,8 +12,7 @@ subdir = src/backend/postmaster
|
||||
top_builddir = ../../..
|
||||
include $(top_builddir)/src/Makefile.global
|
||||
|
||||
OBJS = autovacuum.o bgworker.o bgwriter.o checkpointer.o checksumhelper.o \
|
||||
fork_process.o pgarch.o pgstat.o postmaster.o startup.o syslogger.o \
|
||||
walwriter.o
|
||||
OBJS = autovacuum.o bgworker.o bgwriter.o checkpointer.o fork_process.o \
|
||||
pgarch.o pgstat.o postmaster.o startup.o syslogger.o walwriter.o
|
||||
|
||||
include $(top_srcdir)/src/backend/common.mk
|
||||
|
@ -20,7 +20,6 @@
|
||||
#include "pgstat.h"
|
||||
#include "port/atomics.h"
|
||||
#include "postmaster/bgworker_internals.h"
|
||||
#include "postmaster/checksumhelper.h"
|
||||
#include "postmaster/postmaster.h"
|
||||
#include "replication/logicallauncher.h"
|
||||
#include "replication/logicalworker.h"
|
||||
@ -130,12 +129,6 @@ static const struct
|
||||
},
|
||||
{
|
||||
"ApplyWorkerMain", ApplyWorkerMain
|
||||
},
|
||||
{
|
||||
"ChecksumHelperLauncherMain", ChecksumHelperLauncherMain
|
||||
},
|
||||
{
|
||||
"ChecksumHelperWorkerMain", ChecksumHelperWorkerMain
|
||||
}
|
||||
};
|
||||
|
||||
|
@ -1,855 +0,0 @@
|
||||
/*-------------------------------------------------------------------------
|
||||
*
|
||||
* checksumhelper.c
|
||||
* Background worker to walk the database and write checksums to pages
|
||||
*
|
||||
* When enabling data checksums on a database at initdb time, no extra process
|
||||
* is required as each page is checksummed, and verified, at accesses. When
|
||||
* enabling checksums on an already running cluster, which was not initialized
|
||||
* with checksums, this helper worker will ensure that all pages are
|
||||
* checksummed before verification of the checksums is turned on.
|
||||
*
|
||||
* Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group
|
||||
* Portions Copyright (c) 1994, Regents of the University of California
|
||||
*
|
||||
*
|
||||
* IDENTIFICATION
|
||||
* src/backend/postmaster/checksumhelper.c
|
||||
*
|
||||
*-------------------------------------------------------------------------
|
||||
*/
|
||||
#include "postgres.h"
|
||||
|
||||
#include "access/heapam.h"
|
||||
#include "access/htup_details.h"
|
||||
#include "access/xact.h"
|
||||
#include "catalog/pg_database.h"
|
||||
#include "commands/vacuum.h"
|
||||
#include "common/relpath.h"
|
||||
#include "miscadmin.h"
|
||||
#include "pgstat.h"
|
||||
#include "postmaster/bgworker.h"
|
||||
#include "postmaster/bgwriter.h"
|
||||
#include "postmaster/checksumhelper.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "storage/checksum.h"
|
||||
#include "storage/lmgr.h"
|
||||
#include "storage/ipc.h"
|
||||
#include "storage/procarray.h"
|
||||
#include "storage/smgr.h"
|
||||
#include "tcop/tcopprot.h"
|
||||
#include "utils/lsyscache.h"
|
||||
#include "utils/ps_status.h"
|
||||
|
||||
|
||||
typedef enum
|
||||
{
|
||||
SUCCESSFUL = 0,
|
||||
ABORTED,
|
||||
FAILED
|
||||
} ChecksumHelperResult;
|
||||
|
||||
typedef struct ChecksumHelperShmemStruct
|
||||
{
|
||||
pg_atomic_flag launcher_started;
|
||||
ChecksumHelperResult success;
|
||||
bool process_shared_catalogs;
|
||||
bool abort;
|
||||
/* Parameter values set on start */
|
||||
int cost_delay;
|
||||
int cost_limit;
|
||||
} ChecksumHelperShmemStruct;
|
||||
|
||||
/* Shared memory segment for checksumhelper */
|
||||
static ChecksumHelperShmemStruct * ChecksumHelperShmem;
|
||||
|
||||
/* Bookkeeping for work to do */
|
||||
typedef struct ChecksumHelperDatabase
|
||||
{
|
||||
Oid dboid;
|
||||
char *dbname;
|
||||
} ChecksumHelperDatabase;
|
||||
|
||||
typedef struct ChecksumHelperRelation
|
||||
{
|
||||
Oid reloid;
|
||||
char relkind;
|
||||
} ChecksumHelperRelation;
|
||||
|
||||
/* Prototypes */
|
||||
static List *BuildDatabaseList(void);
|
||||
static List *BuildRelationList(bool include_shared);
|
||||
static List *BuildTempTableList(void);
|
||||
static ChecksumHelperResult ProcessDatabase(ChecksumHelperDatabase * db);
|
||||
static void launcher_cancel_handler(SIGNAL_ARGS);
|
||||
|
||||
/*
|
||||
* Main entry point for checksumhelper launcher process.
|
||||
*/
|
||||
bool
|
||||
StartChecksumHelperLauncher(int cost_delay, int cost_limit)
|
||||
{
|
||||
BackgroundWorker bgw;
|
||||
BackgroundWorkerHandle *bgw_handle;
|
||||
|
||||
if (ChecksumHelperShmem->abort)
|
||||
{
|
||||
ereport(ERROR,
|
||||
(errmsg("could not start checksumhelper: has been cancelled")));
|
||||
}
|
||||
|
||||
ChecksumHelperShmem->cost_delay = cost_delay;
|
||||
ChecksumHelperShmem->cost_limit = cost_limit;
|
||||
|
||||
memset(&bgw, 0, sizeof(bgw));
|
||||
bgw.bgw_flags = BGWORKER_SHMEM_ACCESS | BGWORKER_BACKEND_DATABASE_CONNECTION;
|
||||
bgw.bgw_start_time = BgWorkerStart_RecoveryFinished;
|
||||
snprintf(bgw.bgw_library_name, BGW_MAXLEN, "postgres");
|
||||
snprintf(bgw.bgw_function_name, BGW_MAXLEN, "ChecksumHelperLauncherMain");
|
||||
snprintf(bgw.bgw_name, BGW_MAXLEN, "checksumhelper launcher");
|
||||
snprintf(bgw.bgw_type, BGW_MAXLEN, "checksumhelper launcher");
|
||||
bgw.bgw_restart_time = BGW_NEVER_RESTART;
|
||||
bgw.bgw_notify_pid = MyProcPid;
|
||||
bgw.bgw_main_arg = (Datum) 0;
|
||||
|
||||
if (!pg_atomic_test_set_flag(&ChecksumHelperShmem->launcher_started))
|
||||
{
|
||||
/* Failed to set means somebody else started */
|
||||
ereport(ERROR,
|
||||
(errmsg("could not start checksumhelper: already running")));
|
||||
}
|
||||
|
||||
if (!RegisterDynamicBackgroundWorker(&bgw, &bgw_handle))
|
||||
{
|
||||
pg_atomic_clear_flag(&ChecksumHelperShmem->launcher_started);
|
||||
return false;
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
/*
|
||||
* ShutdownChecksumHelperIfRunning
|
||||
* Request shutdown of the checksumhelper
|
||||
*
|
||||
* This does not turn off processing immediately, it signals the checksum
|
||||
* process to end when done with the current block.
|
||||
*/
|
||||
void
|
||||
ShutdownChecksumHelperIfRunning(void)
|
||||
{
|
||||
/* If the launcher isn't started, there is nothing to shut down */
|
||||
if (pg_atomic_unlocked_test_flag(&ChecksumHelperShmem->launcher_started))
|
||||
return;
|
||||
|
||||
/*
|
||||
* We don't need an atomic variable for aborting, setting it multiple
|
||||
* times will not change the handling.
|
||||
*/
|
||||
ChecksumHelperShmem->abort = true;
|
||||
}
|
||||
|
||||
/*
|
||||
* ProcessSingleRelationFork
|
||||
* Enable checksums in a single relation/fork.
|
||||
*
|
||||
* Returns true if successful, and false if *aborted*. On error, an actual
|
||||
* error is raised in the lower levels.
|
||||
*/
|
||||
static bool
|
||||
ProcessSingleRelationFork(Relation reln, ForkNumber forkNum, BufferAccessStrategy strategy)
|
||||
{
|
||||
BlockNumber numblocks = RelationGetNumberOfBlocksInFork(reln, forkNum);
|
||||
BlockNumber b;
|
||||
char activity[NAMEDATALEN * 2 + 128];
|
||||
|
||||
for (b = 0; b < numblocks; b++)
|
||||
{
|
||||
Buffer buf = ReadBufferExtended(reln, forkNum, b, RBM_NORMAL, strategy);
|
||||
|
||||
/*
|
||||
* Report to pgstat every 100 blocks (so as not to "spam")
|
||||
*/
|
||||
if ((b % 100) == 0)
|
||||
{
|
||||
snprintf(activity, sizeof(activity) - 1, "processing: %s.%s (%s block %d/%d)",
|
||||
get_namespace_name(RelationGetNamespace(reln)), RelationGetRelationName(reln),
|
||||
forkNames[forkNum], b, numblocks);
|
||||
pgstat_report_activity(STATE_RUNNING, activity);
|
||||
}
|
||||
|
||||
/* Need to get an exclusive lock before we can flag as dirty */
|
||||
LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
|
||||
|
||||
/*
|
||||
* Mark the buffer as dirty and force a full page write. We have to
|
||||
* re-write the page to WAL even if the checksum hasn't changed,
|
||||
* because if there is a replica it might have a slightly different
|
||||
* version of the page with an invalid checksum, caused by unlogged
|
||||
* changes (e.g. hintbits) on the master happening while checksums
|
||||
* were off. This can happen if there was a valid checksum on the page
|
||||
* at one point in the past, so only when checksums are first on, then
|
||||
* off, and then turned on again.
|
||||
*/
|
||||
START_CRIT_SECTION();
|
||||
MarkBufferDirty(buf);
|
||||
log_newpage_buffer(buf, false);
|
||||
END_CRIT_SECTION();
|
||||
|
||||
UnlockReleaseBuffer(buf);
|
||||
|
||||
/*
|
||||
* This is the only place where we check if we are asked to abort, the
|
||||
* abortion will bubble up from here.
|
||||
*/
|
||||
if (ChecksumHelperShmem->abort)
|
||||
return false;
|
||||
|
||||
vacuum_delay_point();
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
/*
|
||||
* ProcessSingleRelationByOid
|
||||
* Process a single relation based on oid.
|
||||
*
|
||||
* Returns true if successful, and false if *aborted*. On error, an actual error
|
||||
* is raised in the lower levels.
|
||||
*/
|
||||
static bool
|
||||
ProcessSingleRelationByOid(Oid relationId, BufferAccessStrategy strategy)
|
||||
{
|
||||
Relation rel;
|
||||
ForkNumber fnum;
|
||||
bool aborted = false;
|
||||
|
||||
StartTransactionCommand();
|
||||
|
||||
elog(DEBUG2, "Checksumhelper starting to process relation %d", relationId);
|
||||
rel = try_relation_open(relationId, AccessShareLock);
|
||||
if (rel == NULL)
|
||||
{
|
||||
/*
|
||||
* Relation no longer exist. We consider this a success, since there
|
||||
* are no pages in it that need checksums, and thus return true.
|
||||
*/
|
||||
elog(DEBUG1, "Checksumhelper skipping relation %d as it no longer exists", relationId);
|
||||
CommitTransactionCommand();
|
||||
pgstat_report_activity(STATE_IDLE, NULL);
|
||||
return true;
|
||||
}
|
||||
RelationOpenSmgr(rel);
|
||||
|
||||
for (fnum = 0; fnum <= MAX_FORKNUM; fnum++)
|
||||
{
|
||||
if (smgrexists(rel->rd_smgr, fnum))
|
||||
{
|
||||
if (!ProcessSingleRelationFork(rel, fnum, strategy))
|
||||
{
|
||||
aborted = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
relation_close(rel, AccessShareLock);
|
||||
elog(DEBUG2, "Checksumhelper done with relation %d: %s",
|
||||
relationId, (aborted ? "aborted" : "finished"));
|
||||
|
||||
CommitTransactionCommand();
|
||||
|
||||
pgstat_report_activity(STATE_IDLE, NULL);
|
||||
|
||||
return !aborted;
|
||||
}
|
||||
|
||||
/*
|
||||
* ProcessDatabase
|
||||
* Enable checksums in a single database.
|
||||
*
|
||||
* We do this by launching a dynamic background worker into this database, and
|
||||
* waiting for it to finish. We have to do this in a separate worker, since
|
||||
* each process can only be connected to one database during its lifetime.
|
||||
*/
|
||||
static ChecksumHelperResult
|
||||
ProcessDatabase(ChecksumHelperDatabase * db)
|
||||
{
|
||||
BackgroundWorker bgw;
|
||||
BackgroundWorkerHandle *bgw_handle;
|
||||
BgwHandleStatus status;
|
||||
pid_t pid;
|
||||
char activity[NAMEDATALEN + 64];
|
||||
|
||||
ChecksumHelperShmem->success = FAILED;
|
||||
|
||||
memset(&bgw, 0, sizeof(bgw));
|
||||
bgw.bgw_flags = BGWORKER_SHMEM_ACCESS | BGWORKER_BACKEND_DATABASE_CONNECTION;
|
||||
bgw.bgw_start_time = BgWorkerStart_RecoveryFinished;
|
||||
snprintf(bgw.bgw_library_name, BGW_MAXLEN, "postgres");
|
||||
snprintf(bgw.bgw_function_name, BGW_MAXLEN, "ChecksumHelperWorkerMain");
|
||||
snprintf(bgw.bgw_name, BGW_MAXLEN, "checksumhelper worker");
|
||||
snprintf(bgw.bgw_type, BGW_MAXLEN, "checksumhelper worker");
|
||||
bgw.bgw_restart_time = BGW_NEVER_RESTART;
|
||||
bgw.bgw_notify_pid = MyProcPid;
|
||||
bgw.bgw_main_arg = ObjectIdGetDatum(db->dboid);
|
||||
|
||||
if (!RegisterDynamicBackgroundWorker(&bgw, &bgw_handle))
|
||||
{
|
||||
ereport(LOG,
|
||||
(errmsg("failed to start worker for checksumhelper in \"%s\"",
|
||||
db->dbname)));
|
||||
return FAILED;
|
||||
}
|
||||
|
||||
status = WaitForBackgroundWorkerStartup(bgw_handle, &pid);
|
||||
if (status != BGWH_STARTED)
|
||||
{
|
||||
ereport(LOG,
|
||||
(errmsg("failed to wait for worker startup for checksumhelper in \"%s\"",
|
||||
db->dbname)));
|
||||
return FAILED;
|
||||
}
|
||||
|
||||
ereport(DEBUG1,
|
||||
(errmsg("started background worker for checksums in \"%s\"",
|
||||
db->dbname)));
|
||||
|
||||
snprintf(activity, sizeof(activity) - 1,
|
||||
"Waiting for worker in database %s (pid %d)", db->dbname, pid);
|
||||
pgstat_report_activity(STATE_RUNNING, activity);
|
||||
|
||||
|
||||
status = WaitForBackgroundWorkerShutdown(bgw_handle);
|
||||
if (status != BGWH_STOPPED)
|
||||
{
|
||||
ereport(LOG,
|
||||
(errmsg("failed to wait for worker shutdown for checksumhelper in \"%s\"",
|
||||
db->dbname)));
|
||||
return FAILED;
|
||||
}
|
||||
|
||||
if (ChecksumHelperShmem->success == ABORTED)
|
||||
ereport(LOG,
|
||||
(errmsg("checksumhelper was aborted during processing in \"%s\"",
|
||||
db->dbname)));
|
||||
|
||||
ereport(DEBUG1,
|
||||
(errmsg("background worker for checksums in \"%s\" completed",
|
||||
db->dbname)));
|
||||
|
||||
pgstat_report_activity(STATE_IDLE, NULL);
|
||||
|
||||
return ChecksumHelperShmem->success;
|
||||
}
|
||||
|
||||
static void
|
||||
launcher_exit(int code, Datum arg)
|
||||
{
|
||||
ChecksumHelperShmem->abort = false;
|
||||
pg_atomic_clear_flag(&ChecksumHelperShmem->launcher_started);
|
||||
}
|
||||
|
||||
static void
|
||||
launcher_cancel_handler(SIGNAL_ARGS)
|
||||
{
|
||||
ChecksumHelperShmem->abort = true;
|
||||
}
|
||||
|
||||
static void
|
||||
WaitForAllTransactionsToFinish(void)
|
||||
{
|
||||
TransactionId waitforxid;
|
||||
|
||||
LWLockAcquire(XidGenLock, LW_SHARED);
|
||||
waitforxid = ShmemVariableCache->nextXid;
|
||||
LWLockRelease(XidGenLock);
|
||||
|
||||
while (true)
|
||||
{
|
||||
TransactionId oldestxid = GetOldestActiveTransactionId();
|
||||
|
||||
elog(DEBUG1, "Checking old transactions");
|
||||
if (TransactionIdPrecedes(oldestxid, waitforxid))
|
||||
{
|
||||
char activity[64];
|
||||
|
||||
/* Oldest running xid is older than us, so wait */
|
||||
snprintf(activity, sizeof(activity), "Waiting for current transactions to finish (waiting for %d)", waitforxid);
|
||||
pgstat_report_activity(STATE_RUNNING, activity);
|
||||
|
||||
/* Retry every 5 seconds */
|
||||
ResetLatch(MyLatch);
|
||||
(void) WaitLatch(MyLatch,
|
||||
WL_LATCH_SET | WL_TIMEOUT,
|
||||
5000,
|
||||
WAIT_EVENT_PG_SLEEP);
|
||||
}
|
||||
else
|
||||
{
|
||||
pgstat_report_activity(STATE_IDLE, NULL);
|
||||
return;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
void
|
||||
ChecksumHelperLauncherMain(Datum arg)
|
||||
{
|
||||
List *DatabaseList;
|
||||
List *remaining = NIL;
|
||||
ListCell *lc,
|
||||
*lc2;
|
||||
List *CurrentDatabases = NIL;
|
||||
bool found_failed = false;
|
||||
|
||||
on_shmem_exit(launcher_exit, 0);
|
||||
|
||||
ereport(DEBUG1,
|
||||
(errmsg("checksumhelper launcher started")));
|
||||
|
||||
pqsignal(SIGTERM, die);
|
||||
pqsignal(SIGINT, launcher_cancel_handler);
|
||||
|
||||
BackgroundWorkerUnblockSignals();
|
||||
|
||||
init_ps_display(pgstat_get_backend_desc(B_CHECKSUMHELPER_LAUNCHER), "", "", "");
|
||||
|
||||
/*
|
||||
* Initialize a connection to shared catalogs only.
|
||||
*/
|
||||
BackgroundWorkerInitializeConnection(NULL, NULL, 0);
|
||||
|
||||
/*
|
||||
* Set up so first run processes shared catalogs, but not once in every
|
||||
* db.
|
||||
*/
|
||||
ChecksumHelperShmem->process_shared_catalogs = true;
|
||||
|
||||
/*
|
||||
* Wait for all existing transactions to finish. This will make sure that
|
||||
* we can see all tables all databases, so we don't miss any. Anything
|
||||
* created after this point is known to have checksums on all pages
|
||||
* already, so we don't have to care about those.
|
||||
*/
|
||||
WaitForAllTransactionsToFinish();
|
||||
|
||||
/*
|
||||
* Create a database list. We don't need to concern ourselves with
|
||||
* rebuilding this list during runtime since any database created after
|
||||
* this process started will be running with checksums turned on from the
|
||||
* start.
|
||||
*/
|
||||
DatabaseList = BuildDatabaseList();
|
||||
|
||||
/*
|
||||
* If there are no databases at all to checksum, we can exit immediately
|
||||
* as there is no work to do.
|
||||
*/
|
||||
if (DatabaseList == NIL || list_length(DatabaseList) == 0)
|
||||
return;
|
||||
|
||||
foreach(lc, DatabaseList)
|
||||
{
|
||||
ChecksumHelperDatabase *db = (ChecksumHelperDatabase *) lfirst(lc);
|
||||
ChecksumHelperResult processing;
|
||||
|
||||
processing = ProcessDatabase(db);
|
||||
|
||||
if (processing == SUCCESSFUL)
|
||||
{
|
||||
pfree(db->dbname);
|
||||
pfree(db);
|
||||
|
||||
if (ChecksumHelperShmem->process_shared_catalogs)
|
||||
|
||||
/*
|
||||
* Now that one database has completed shared catalogs, we
|
||||
* don't have to process them again.
|
||||
*/
|
||||
ChecksumHelperShmem->process_shared_catalogs = false;
|
||||
}
|
||||
else if (processing == FAILED)
|
||||
{
|
||||
/*
|
||||
* Put failed databases on the remaining list.
|
||||
*/
|
||||
remaining = lappend(remaining, db);
|
||||
}
|
||||
else
|
||||
/* aborted */
|
||||
return;
|
||||
}
|
||||
list_free(DatabaseList);
|
||||
|
||||
/*
|
||||
* remaining now has all databases not yet processed. This can be because
|
||||
* they failed for some reason, or because the database was dropped
|
||||
* between us getting the database list and trying to process it. Get a
|
||||
* fresh list of databases to detect the second case where the database
|
||||
* was dropped before we had started processing it. If a database still
|
||||
* exists, but enabling checksums failed then we fail the entire
|
||||
* checksumming process and exit with an error.
|
||||
*/
|
||||
CurrentDatabases = BuildDatabaseList();
|
||||
|
||||
foreach(lc, remaining)
|
||||
{
|
||||
ChecksumHelperDatabase *db = (ChecksumHelperDatabase *) lfirst(lc);
|
||||
bool found = false;
|
||||
|
||||
foreach(lc2, CurrentDatabases)
|
||||
{
|
||||
ChecksumHelperDatabase *db2 = (ChecksumHelperDatabase *) lfirst(lc2);
|
||||
|
||||
if (db->dboid == db2->dboid)
|
||||
{
|
||||
found = true;
|
||||
ereport(WARNING,
|
||||
(errmsg("failed to enable checksums in \"%s\"",
|
||||
db->dbname)));
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if (found)
|
||||
found_failed = true;
|
||||
else
|
||||
{
|
||||
ereport(LOG,
|
||||
(errmsg("database \"%s\" has been dropped, skipping",
|
||||
db->dbname)));
|
||||
}
|
||||
|
||||
pfree(db->dbname);
|
||||
pfree(db);
|
||||
}
|
||||
list_free(remaining);
|
||||
|
||||
/* Free the extra list of databases */
|
||||
foreach(lc, CurrentDatabases)
|
||||
{
|
||||
ChecksumHelperDatabase *db = (ChecksumHelperDatabase *) lfirst(lc);
|
||||
|
||||
pfree(db->dbname);
|
||||
pfree(db);
|
||||
}
|
||||
list_free(CurrentDatabases);
|
||||
|
||||
if (found_failed)
|
||||
{
|
||||
/* Disable checksums on cluster, because we failed */
|
||||
SetDataChecksumsOff();
|
||||
ereport(ERROR,
|
||||
(errmsg("checksumhelper failed to enable checksums in all databases, aborting")));
|
||||
}
|
||||
|
||||
/*
|
||||
* Force a checkpoint to get everything out to disk.
|
||||
*/
|
||||
RequestCheckpoint(CHECKPOINT_FORCE | CHECKPOINT_WAIT | CHECKPOINT_IMMEDIATE);
|
||||
|
||||
/*
|
||||
* Everything has been processed, so flag checksums enabled.
|
||||
*/
|
||||
SetDataChecksumsOn();
|
||||
|
||||
ereport(LOG,
|
||||
(errmsg("checksums enabled, checksumhelper launcher shutting down")));
|
||||
}
|
||||
|
||||
/*
|
||||
* ChecksumHelperShmemSize
|
||||
* Compute required space for checksumhelper-related shared memory
|
||||
*/
|
||||
Size
|
||||
ChecksumHelperShmemSize(void)
|
||||
{
|
||||
Size size;
|
||||
|
||||
size = sizeof(ChecksumHelperShmemStruct);
|
||||
size = MAXALIGN(size);
|
||||
|
||||
return size;
|
||||
}
|
||||
|
||||
/*
|
||||
* ChecksumHelperShmemInit
|
||||
* Allocate and initialize checksumhelper-related shared memory
|
||||
*/
|
||||
void
|
||||
ChecksumHelperShmemInit(void)
|
||||
{
|
||||
bool found;
|
||||
|
||||
ChecksumHelperShmem = (ChecksumHelperShmemStruct *)
|
||||
ShmemInitStruct("ChecksumHelper Data",
|
||||
ChecksumHelperShmemSize(),
|
||||
&found);
|
||||
|
||||
if (!found)
|
||||
{
|
||||
MemSet(ChecksumHelperShmem, 0, ChecksumHelperShmemSize());
|
||||
pg_atomic_init_flag(&ChecksumHelperShmem->launcher_started);
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* BuildDatabaseList
|
||||
* Compile a list of all currently available databases in the cluster
|
||||
*
|
||||
* This creates the list of databases for the checksumhelper workers to add
|
||||
* checksums to.
|
||||
*/
|
||||
static List *
|
||||
BuildDatabaseList(void)
|
||||
{
|
||||
List *DatabaseList = NIL;
|
||||
Relation rel;
|
||||
HeapScanDesc scan;
|
||||
HeapTuple tup;
|
||||
MemoryContext ctx = CurrentMemoryContext;
|
||||
MemoryContext oldctx;
|
||||
|
||||
StartTransactionCommand();
|
||||
|
||||
rel = heap_open(DatabaseRelationId, AccessShareLock);
|
||||
scan = heap_beginscan_catalog(rel, 0, NULL);
|
||||
|
||||
while (HeapTupleIsValid(tup = heap_getnext(scan, ForwardScanDirection)))
|
||||
{
|
||||
Form_pg_database pgdb = (Form_pg_database) GETSTRUCT(tup);
|
||||
ChecksumHelperDatabase *db;
|
||||
|
||||
oldctx = MemoryContextSwitchTo(ctx);
|
||||
|
||||
db = (ChecksumHelperDatabase *) palloc(sizeof(ChecksumHelperDatabase));
|
||||
|
||||
db->dboid = HeapTupleGetOid(tup);
|
||||
db->dbname = pstrdup(NameStr(pgdb->datname));
|
||||
|
||||
DatabaseList = lappend(DatabaseList, db);
|
||||
|
||||
MemoryContextSwitchTo(oldctx);
|
||||
}
|
||||
|
||||
heap_endscan(scan);
|
||||
heap_close(rel, AccessShareLock);
|
||||
|
||||
CommitTransactionCommand();
|
||||
|
||||
return DatabaseList;
|
||||
}
|
||||
|
||||
/*
|
||||
* BuildRelationList
|
||||
* Compile a list of all relations in the database
|
||||
*
|
||||
* If shared is true, both shared relations and local ones are returned, else
|
||||
* all non-shared relations are returned.
|
||||
* Temp tables are not included.
|
||||
*/
|
||||
static List *
|
||||
BuildRelationList(bool include_shared)
|
||||
{
|
||||
List *RelationList = NIL;
|
||||
Relation rel;
|
||||
HeapScanDesc scan;
|
||||
HeapTuple tup;
|
||||
MemoryContext ctx = CurrentMemoryContext;
|
||||
MemoryContext oldctx;
|
||||
|
||||
StartTransactionCommand();
|
||||
|
||||
rel = heap_open(RelationRelationId, AccessShareLock);
|
||||
scan = heap_beginscan_catalog(rel, 0, NULL);
|
||||
|
||||
while (HeapTupleIsValid(tup = heap_getnext(scan, ForwardScanDirection)))
|
||||
{
|
||||
Form_pg_class pgc = (Form_pg_class) GETSTRUCT(tup);
|
||||
ChecksumHelperRelation *relentry;
|
||||
|
||||
if (pgc->relpersistence == 't')
|
||||
continue;
|
||||
|
||||
if (pgc->relisshared && !include_shared)
|
||||
continue;
|
||||
|
||||
/*
|
||||
* Foreign tables have by definition no local storage that can be
|
||||
* checksummed, so skip.
|
||||
*/
|
||||
if (pgc->relkind == RELKIND_FOREIGN_TABLE)
|
||||
continue;
|
||||
|
||||
oldctx = MemoryContextSwitchTo(ctx);
|
||||
relentry = (ChecksumHelperRelation *) palloc(sizeof(ChecksumHelperRelation));
|
||||
|
||||
relentry->reloid = HeapTupleGetOid(tup);
|
||||
relentry->relkind = pgc->relkind;
|
||||
|
||||
RelationList = lappend(RelationList, relentry);
|
||||
|
||||
MemoryContextSwitchTo(oldctx);
|
||||
}
|
||||
|
||||
heap_endscan(scan);
|
||||
heap_close(rel, AccessShareLock);
|
||||
|
||||
CommitTransactionCommand();
|
||||
|
||||
return RelationList;
|
||||
}
|
||||
|
||||
/*
|
||||
* BuildTempTableList
|
||||
* Compile a list of all temporary tables in database
|
||||
*
|
||||
* Returns a List of oids.
|
||||
*/
|
||||
static List *
|
||||
BuildTempTableList(void)
|
||||
{
|
||||
List *RelationList = NIL;
|
||||
Relation rel;
|
||||
HeapScanDesc scan;
|
||||
HeapTuple tup;
|
||||
MemoryContext ctx = CurrentMemoryContext;
|
||||
MemoryContext oldctx;
|
||||
|
||||
StartTransactionCommand();
|
||||
|
||||
rel = heap_open(RelationRelationId, AccessShareLock);
|
||||
scan = heap_beginscan_catalog(rel, 0, NULL);
|
||||
|
||||
while (HeapTupleIsValid(tup = heap_getnext(scan, ForwardScanDirection)))
|
||||
{
|
||||
Form_pg_class pgc = (Form_pg_class) GETSTRUCT(tup);
|
||||
|
||||
if (pgc->relpersistence != 't')
|
||||
continue;
|
||||
|
||||
oldctx = MemoryContextSwitchTo(ctx);
|
||||
RelationList = lappend_oid(RelationList, HeapTupleGetOid(tup));
|
||||
MemoryContextSwitchTo(oldctx);
|
||||
}
|
||||
|
||||
heap_endscan(scan);
|
||||
heap_close(rel, AccessShareLock);
|
||||
|
||||
CommitTransactionCommand();
|
||||
|
||||
return RelationList;
|
||||
}
|
||||
|
||||
/*
|
||||
* Main function for enabling checksums in a single database
|
||||
*/
|
||||
void
|
||||
ChecksumHelperWorkerMain(Datum arg)
|
||||
{
|
||||
Oid dboid = DatumGetObjectId(arg);
|
||||
List *RelationList = NIL;
|
||||
List *InitialTempTableList = NIL;
|
||||
ListCell *lc;
|
||||
BufferAccessStrategy strategy;
|
||||
bool aborted = false;
|
||||
|
||||
pqsignal(SIGTERM, die);
|
||||
|
||||
BackgroundWorkerUnblockSignals();
|
||||
|
||||
init_ps_display(pgstat_get_backend_desc(B_CHECKSUMHELPER_WORKER), "", "", "");
|
||||
|
||||
ereport(DEBUG1,
|
||||
(errmsg("checksum worker starting for database oid %d", dboid)));
|
||||
|
||||
BackgroundWorkerInitializeConnectionByOid(dboid, InvalidOid, BGWORKER_BYPASS_ALLOWCONN);
|
||||
|
||||
/*
|
||||
* Get a list of all temp tables present as we start in this database. We
|
||||
* need to wait until they are all gone until we are done, since we cannot
|
||||
* access those files and modify them.
|
||||
*/
|
||||
InitialTempTableList = BuildTempTableList();
|
||||
|
||||
/*
|
||||
* Enable vacuum cost delay, if any.
|
||||
*/
|
||||
VacuumCostDelay = ChecksumHelperShmem->cost_delay;
|
||||
VacuumCostLimit = ChecksumHelperShmem->cost_limit;
|
||||
VacuumCostActive = (VacuumCostDelay > 0);
|
||||
VacuumCostBalance = 0;
|
||||
VacuumPageHit = 0;
|
||||
VacuumPageMiss = 0;
|
||||
VacuumPageDirty = 0;
|
||||
|
||||
/*
|
||||
* Create and set the vacuum strategy as our buffer strategy.
|
||||
*/
|
||||
strategy = GetAccessStrategy(BAS_VACUUM);
|
||||
|
||||
RelationList = BuildRelationList(ChecksumHelperShmem->process_shared_catalogs);
|
||||
foreach(lc, RelationList)
|
||||
{
|
||||
ChecksumHelperRelation *rel = (ChecksumHelperRelation *) lfirst(lc);
|
||||
|
||||
if (!ProcessSingleRelationByOid(rel->reloid, strategy))
|
||||
{
|
||||
aborted = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
list_free_deep(RelationList);
|
||||
|
||||
if (aborted)
|
||||
{
|
||||
ChecksumHelperShmem->success = ABORTED;
|
||||
ereport(DEBUG1,
|
||||
(errmsg("checksum worker aborted in database oid %d", dboid)));
|
||||
return;
|
||||
}
|
||||
|
||||
/*
|
||||
* Wait for all temp tables that existed when we started to go away. This
|
||||
* is necessary since we cannot "reach" them to enable checksums. Any temp
|
||||
* tables created after we started will already have checksums in them
|
||||
* (due to the inprogress state), so those are safe.
|
||||
*/
|
||||
while (true)
|
||||
{
|
||||
List *CurrentTempTables;
|
||||
ListCell *lc;
|
||||
int numleft;
|
||||
char activity[64];
|
||||
|
||||
CurrentTempTables = BuildTempTableList();
|
||||
numleft = 0;
|
||||
foreach(lc, InitialTempTableList)
|
||||
{
|
||||
if (list_member_oid(CurrentTempTables, lfirst_oid(lc)))
|
||||
numleft++;
|
||||
}
|
||||
list_free(CurrentTempTables);
|
||||
|
||||
if (numleft == 0)
|
||||
break;
|
||||
|
||||
/* At least one temp table left to wait for */
|
||||
snprintf(activity, sizeof(activity), "Waiting for %d temp tables to be removed", numleft);
|
||||
pgstat_report_activity(STATE_RUNNING, activity);
|
||||
|
||||
/* Retry every 5 seconds */
|
||||
ResetLatch(MyLatch);
|
||||
(void) WaitLatch(MyLatch,
|
||||
WL_LATCH_SET | WL_TIMEOUT,
|
||||
5000,
|
||||
WAIT_EVENT_PG_SLEEP);
|
||||
}
|
||||
|
||||
list_free(InitialTempTableList);
|
||||
|
||||
ChecksumHelperShmem->success = SUCCESSFUL;
|
||||
ereport(DEBUG1,
|
||||
(errmsg("checksum worker completed in database oid %d", dboid)));
|
||||
}
|
@ -4125,11 +4125,6 @@ pgstat_get_backend_desc(BackendType backendType)
|
||||
case B_WAL_WRITER:
|
||||
backendDesc = "walwriter";
|
||||
break;
|
||||
case B_CHECKSUMHELPER_LAUNCHER:
|
||||
backendDesc = "checksumhelper launcher";
|
||||
break;
|
||||
case B_CHECKSUMHELPER_WORKER:
|
||||
backendDesc = "checksumhelper worker";
|
||||
}
|
||||
|
||||
return backendDesc;
|
||||
|
@ -1384,7 +1384,7 @@ sendFile(const char *readfilename, const char *tarfilename, struct stat *statbuf
|
||||
|
||||
_tarWriteHeader(tarfilename, NULL, statbuf, false);
|
||||
|
||||
if (!noverify_checksums && DataChecksumsNeedVerify())
|
||||
if (!noverify_checksums && DataChecksumsEnabled())
|
||||
{
|
||||
char *filename;
|
||||
|
||||
|
@ -199,7 +199,6 @@ DecodeXLogOp(LogicalDecodingContext *ctx, XLogRecordBuffer *buf)
|
||||
case XLOG_FPW_CHANGE:
|
||||
case XLOG_FPI_FOR_HINT:
|
||||
case XLOG_FPI:
|
||||
case XLOG_CHECKSUMS:
|
||||
break;
|
||||
default:
|
||||
elog(ERROR, "unexpected RM_XLOG_ID record type: %u", info);
|
||||
|
@ -27,7 +27,6 @@
|
||||
#include "postmaster/autovacuum.h"
|
||||
#include "postmaster/bgworker_internals.h"
|
||||
#include "postmaster/bgwriter.h"
|
||||
#include "postmaster/checksumhelper.h"
|
||||
#include "postmaster/postmaster.h"
|
||||
#include "replication/logicallauncher.h"
|
||||
#include "replication/slot.h"
|
||||
@ -262,7 +261,6 @@ CreateSharedMemoryAndSemaphores(bool makePrivate, int port)
|
||||
WalSndShmemInit();
|
||||
WalRcvShmemInit();
|
||||
ApplyLauncherShmemInit();
|
||||
ChecksumHelperShmemInit();
|
||||
|
||||
/*
|
||||
* Set up other modules that need some shared memory space
|
||||
|
@ -9,8 +9,7 @@ have a very low measured incidence according to research on large server farms,
|
||||
http://www.cs.toronto.edu/~bianca/papers/sigmetrics09.pdf, discussed
|
||||
2010/12/22 on -hackers list.
|
||||
|
||||
Checksums can be enabled at initdb time, but can also be turned on and off
|
||||
using pg_enable_data_checksums()/pg_disable_data_checksums() at runtime.
|
||||
Current implementation requires this be enabled system-wide at initdb time.
|
||||
|
||||
The checksum is not valid at all times on a data page!!
|
||||
The checksum is valid when the page leaves the shared pool and is checked
|
||||
|
@ -93,7 +93,7 @@ PageIsVerified(Page page, BlockNumber blkno)
|
||||
*/
|
||||
if (!PageIsNew(page))
|
||||
{
|
||||
if (DataChecksumsNeedVerify())
|
||||
if (DataChecksumsEnabled())
|
||||
{
|
||||
checksum = pg_checksum_page((char *) page, blkno);
|
||||
|
||||
@ -1168,7 +1168,7 @@ PageSetChecksumCopy(Page page, BlockNumber blkno)
|
||||
static char *pageCopy = NULL;
|
||||
|
||||
/* If we don't need a checksum, just return the passed-in data */
|
||||
if (PageIsNew(page) || !DataChecksumsNeedWrite())
|
||||
if (PageIsNew(page) || !DataChecksumsEnabled())
|
||||
return (char *) page;
|
||||
|
||||
/*
|
||||
@ -1195,7 +1195,7 @@ void
|
||||
PageSetChecksumInplace(Page page, BlockNumber blkno)
|
||||
{
|
||||
/* If we don't need a checksum, just return */
|
||||
if (PageIsNew(page) || !DataChecksumsNeedWrite())
|
||||
if (PageIsNew(page) || !DataChecksumsEnabled())
|
||||
return;
|
||||
|
||||
((PageHeader) page)->pd_checksum = pg_checksum_page((char *) page, blkno);
|
||||
|
@ -32,7 +32,6 @@
|
||||
#include "access/transam.h"
|
||||
#include "access/twophase.h"
|
||||
#include "access/xact.h"
|
||||
#include "access/xlog.h"
|
||||
#include "access/xlog_internal.h"
|
||||
#include "catalog/namespace.h"
|
||||
#include "catalog/pg_authid.h"
|
||||
@ -69,7 +68,6 @@
|
||||
#include "replication/walreceiver.h"
|
||||
#include "replication/walsender.h"
|
||||
#include "storage/bufmgr.h"
|
||||
#include "storage/checksum.h"
|
||||
#include "storage/dsm_impl.h"
|
||||
#include "storage/standby.h"
|
||||
#include "storage/fd.h"
|
||||
@ -422,17 +420,6 @@ static const struct config_enum_entry password_encryption_options[] = {
|
||||
{NULL, 0, false}
|
||||
};
|
||||
|
||||
/*
|
||||
* data_checksum used to be a boolean, but was only set by initdb so there is
|
||||
* no need to support variants of boolean input.
|
||||
*/
|
||||
static const struct config_enum_entry data_checksum_options[] = {
|
||||
{"on", DATA_CHECKSUMS_ON, true},
|
||||
{"off", DATA_CHECKSUMS_OFF, true},
|
||||
{"inprogress", DATA_CHECKSUMS_INPROGRESS, true},
|
||||
{NULL, 0, false}
|
||||
};
|
||||
|
||||
/*
|
||||
* Options for enum values stored in other modules
|
||||
*/
|
||||
@ -528,7 +515,7 @@ static int max_identifier_length;
|
||||
static int block_size;
|
||||
static int segment_size;
|
||||
static int wal_block_size;
|
||||
static int data_checksums_tmp; /* only accessed locally! */
|
||||
static bool data_checksums;
|
||||
static bool integer_datetimes;
|
||||
static bool assert_enabled;
|
||||
|
||||
@ -1697,6 +1684,17 @@ static struct config_bool ConfigureNamesBool[] =
|
||||
NULL, NULL, NULL
|
||||
},
|
||||
|
||||
{
|
||||
{"data_checksums", PGC_INTERNAL, PRESET_OPTIONS,
|
||||
gettext_noop("Shows whether data checksums are turned on for this cluster."),
|
||||
NULL,
|
||||
GUC_NOT_IN_SAMPLE | GUC_DISALLOW_IN_FILE
|
||||
},
|
||||
&data_checksums,
|
||||
false,
|
||||
NULL, NULL, NULL
|
||||
},
|
||||
|
||||
{
|
||||
{"syslog_sequence_numbers", PGC_SIGHUP, LOGGING_WHERE,
|
||||
gettext_noop("Add sequence number to syslog messages to avoid duplicate suppression."),
|
||||
@ -4129,17 +4127,6 @@ static struct config_enum ConfigureNamesEnum[] =
|
||||
NULL, NULL, NULL
|
||||
},
|
||||
|
||||
{
|
||||
{"data_checksums", PGC_INTERNAL, PRESET_OPTIONS,
|
||||
gettext_noop("Shows whether data checksums are turned on for this cluster."),
|
||||
NULL,
|
||||
GUC_NOT_IN_SAMPLE | GUC_DISALLOW_IN_FILE
|
||||
},
|
||||
&data_checksums_tmp,
|
||||
DATA_CHECKSUMS_OFF, data_checksum_options,
|
||||
NULL, NULL, show_data_checksums
|
||||
},
|
||||
|
||||
/* End-of-list marker */
|
||||
{
|
||||
{NULL, 0, 0, NULL, NULL}, NULL, 0, NULL, NULL, NULL, NULL
|
||||
|
@ -590,15 +590,6 @@ check_control_data(ControlData *oldctrl,
|
||||
* check_for_isn_and_int8_passing_mismatch().
|
||||
*/
|
||||
|
||||
/*
|
||||
* If checksums have been turned on in the old cluster, but the
|
||||
* checksumhelper have yet to finish, then disallow upgrading. The user
|
||||
* should either let the process finish, or turn off checksums, before
|
||||
* retrying.
|
||||
*/
|
||||
if (oldctrl->data_checksum_version == 2)
|
||||
pg_fatal("transition to data checksums not completed in old cluster\n");
|
||||
|
||||
/*
|
||||
* We might eventually allow upgrades from checksum to no-checksum
|
||||
* clusters.
|
||||
|
@ -226,7 +226,7 @@ typedef struct
|
||||
uint32 large_object;
|
||||
bool date_is_int;
|
||||
bool float8_pass_by_value;
|
||||
uint32 data_checksum_version;
|
||||
bool data_checksum_version;
|
||||
} ControlData;
|
||||
|
||||
/*
|
||||
|
@ -307,10 +307,7 @@ main(int argc, char *argv[])
|
||||
printf(_("Data checksum version: %d\n"), ControlFile->data_checksum_version);
|
||||
printf(_("Files scanned: %" INT64_MODIFIER "d\n"), files);
|
||||
printf(_("Blocks scanned: %" INT64_MODIFIER "d\n"), blocks);
|
||||
if (ControlFile->data_checksum_version == PG_DATA_CHECKSUM_INPROGRESS_VERSION)
|
||||
printf(_("Blocks left in progress: %" INT64_MODIFIER "d\n"), badblocks);
|
||||
else
|
||||
printf(_("Bad checksums: %" INT64_MODIFIER "d\n"), badblocks);
|
||||
printf(_("Bad checksums: %" INT64_MODIFIER "d\n"), badblocks);
|
||||
|
||||
if (badblocks > 0)
|
||||
return 1;
|
||||
|
@ -154,7 +154,7 @@ extern PGDLLIMPORT int wal_level;
|
||||
* of the bits make it to disk, but the checksum wouldn't match. Also WAL-log
|
||||
* them if forced by wal_log_hints=on.
|
||||
*/
|
||||
#define XLogHintBitIsNeeded() (DataChecksumsNeedWrite() || wal_log_hints)
|
||||
#define XLogHintBitIsNeeded() (DataChecksumsEnabled() || wal_log_hints)
|
||||
|
||||
/* Do we need to WAL-log information required only for Hot Standby and logical replication? */
|
||||
#define XLogStandbyInfoActive() (wal_level >= WAL_LEVEL_REPLICA)
|
||||
@ -257,13 +257,7 @@ extern char *XLogFileNameP(TimeLineID tli, XLogSegNo segno);
|
||||
extern void UpdateControlFile(void);
|
||||
extern uint64 GetSystemIdentifier(void);
|
||||
extern char *GetMockAuthenticationNonce(void);
|
||||
extern bool DataChecksumsNeedWrite(void);
|
||||
extern bool DataChecksumsNeedVerify(void);
|
||||
extern bool DataChecksumsInProgress(void);
|
||||
extern void SetDataChecksumsInProgress(void);
|
||||
extern void SetDataChecksumsOn(void);
|
||||
extern void SetDataChecksumsOff(void);
|
||||
extern const char *show_data_checksums(void);
|
||||
extern bool DataChecksumsEnabled(void);
|
||||
extern XLogRecPtr GetFakeLSNForUnloggedRel(void);
|
||||
extern Size XLOGShmemSize(void);
|
||||
extern void XLOGShmemInit(void);
|
||||
|
@ -25,7 +25,6 @@
|
||||
#include "lib/stringinfo.h"
|
||||
#include "pgtime.h"
|
||||
#include "storage/block.h"
|
||||
#include "storage/checksum.h"
|
||||
#include "storage/relfilenode.h"
|
||||
|
||||
|
||||
@ -241,12 +240,6 @@ typedef struct xl_restore_point
|
||||
char rp_name[MAXFNAMELEN];
|
||||
} xl_restore_point;
|
||||
|
||||
/* Information logged when checksum level is changed */
|
||||
typedef struct xl_checksum_state
|
||||
{
|
||||
ChecksumType new_checksumtype;
|
||||
} xl_checksum_state;
|
||||
|
||||
/* End of recovery mark, when we don't do an END_OF_RECOVERY checkpoint */
|
||||
typedef struct xl_end_of_recovery
|
||||
{
|
||||
|
@ -76,7 +76,6 @@ typedef struct CheckPoint
|
||||
#define XLOG_END_OF_RECOVERY 0x90
|
||||
#define XLOG_FPI_FOR_HINT 0xA0
|
||||
#define XLOG_FPI 0xB0
|
||||
#define XLOG_CHECKSUMS 0xC0
|
||||
|
||||
|
||||
/*
|
||||
|
@ -10169,14 +10169,6 @@
|
||||
proargnames => '{max_data_alignment,database_block_size,blocks_per_segment,wal_block_size,bytes_per_wal_segment,max_identifier_length,max_index_columns,max_toast_chunk_size,large_object_chunk_size,float4_pass_by_value,float8_pass_by_value,data_page_checksum_version}',
|
||||
prosrc => 'pg_control_init' },
|
||||
|
||||
{ oid => '3996', descr => 'disable data checksums',
|
||||
proname => 'pg_disable_data_checksums', provolatile => 'v',
|
||||
prorettype => 'void', proargtypes => '', prosrc => 'disable_data_checksums' },
|
||||
{ oid => '3998', descr => 'enable data checksums',
|
||||
proname => 'pg_enable_data_checksums', provolatile => 'v',
|
||||
prorettype => 'void', proargtypes => 'int4 int4',
|
||||
proargnames => '{cost_delay,cost_limit}', prosrc => 'enable_data_checksums' },
|
||||
|
||||
# collation management functions
|
||||
{ oid => '3445', descr => 'import collations from operating system',
|
||||
proname => 'pg_import_system_collations', procost => '100',
|
||||
|
@ -710,9 +710,7 @@ typedef enum BackendType
|
||||
B_STARTUP,
|
||||
B_WAL_RECEIVER,
|
||||
B_WAL_SENDER,
|
||||
B_WAL_WRITER,
|
||||
B_CHECKSUMHELPER_LAUNCHER,
|
||||
B_CHECKSUMHELPER_WORKER
|
||||
B_WAL_WRITER
|
||||
} BackendType;
|
||||
|
||||
|
||||
|
@ -1,31 +0,0 @@
|
||||
/*-------------------------------------------------------------------------
|
||||
*
|
||||
* checksumhelper.h
|
||||
* header file for checksum helper background worker
|
||||
*
|
||||
*
|
||||
* Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group
|
||||
* Portions Copyright (c) 1994, Regents of the University of California
|
||||
*
|
||||
* src/include/postmaster/checksumhelper.h
|
||||
*
|
||||
*-------------------------------------------------------------------------
|
||||
*/
|
||||
#ifndef CHECKSUMHELPER_H
|
||||
#define CHECKSUMHELPER_H
|
||||
|
||||
/* Shared memory */
|
||||
extern Size ChecksumHelperShmemSize(void);
|
||||
extern void ChecksumHelperShmemInit(void);
|
||||
|
||||
/* Start the background processes for enabling checksums */
|
||||
bool StartChecksumHelperLauncher(int cost_delay, int cost_limit);
|
||||
|
||||
/* Shutdown the background processes, if any */
|
||||
void ShutdownChecksumHelperIfRunning(void);
|
||||
|
||||
/* Background worker entrypoints */
|
||||
void ChecksumHelperLauncherMain(Datum arg);
|
||||
void ChecksumHelperWorkerMain(Datum arg);
|
||||
|
||||
#endif /* CHECKSUMHELPER_H */
|
@ -194,7 +194,6 @@ typedef PageHeaderData *PageHeader;
|
||||
*/
|
||||
#define PG_PAGE_LAYOUT_VERSION 4
|
||||
#define PG_DATA_CHECKSUM_VERSION 1
|
||||
#define PG_DATA_CHECKSUM_INPROGRESS_VERSION 2
|
||||
|
||||
/* ----------------------------------------------------------------
|
||||
* page support macros
|
||||
|
@ -15,13 +15,6 @@
|
||||
|
||||
#include "storage/block.h"
|
||||
|
||||
typedef enum ChecksumType
|
||||
{
|
||||
DATA_CHECKSUMS_OFF = 0,
|
||||
DATA_CHECKSUMS_ON,
|
||||
DATA_CHECKSUMS_INPROGRESS
|
||||
} ChecksumType;
|
||||
|
||||
/*
|
||||
* Compute the checksum for a Postgres page. The page must be aligned on a
|
||||
* 4-byte boundary.
|
||||
|
@ -12,8 +12,7 @@ subdir = src/test
|
||||
top_builddir = ../..
|
||||
include $(top_builddir)/src/Makefile.global
|
||||
|
||||
SUBDIRS = perl regress isolation modules authentication recovery subscription \
|
||||
checksum
|
||||
SUBDIRS = perl regress isolation modules authentication recovery subscription
|
||||
|
||||
# Test suites that are not safe by default but can be run if selected
|
||||
# by the user via the whitespace-separated list in variable
|
||||
|
2
src/test/checksum/.gitignore
vendored
2
src/test/checksum/.gitignore
vendored
@ -1,2 +0,0 @@
|
||||
# Generated by test suite
|
||||
/tmp_check/
|
@ -1,24 +0,0 @@
|
||||
#-------------------------------------------------------------------------
|
||||
#
|
||||
# Makefile for src/test/checksum
|
||||
#
|
||||
# Portions Copyright (c) 1996-2018, PostgreSQL Global Development Group
|
||||
# Portions Copyright (c) 1994, Regents of the University of California
|
||||
#
|
||||
# src/test/checksum/Makefile
|
||||
#
|
||||
#-------------------------------------------------------------------------
|
||||
|
||||
subdir = src/test/checksum
|
||||
top_builddir = ../../..
|
||||
include $(top_builddir)/src/Makefile.global
|
||||
|
||||
check:
|
||||
$(prove_check)
|
||||
|
||||
installcheck:
|
||||
$(prove_installcheck)
|
||||
|
||||
clean distclean maintainer-clean:
|
||||
rm -rf tmp_check
|
||||
|
@ -1,22 +0,0 @@
|
||||
src/test/checksum/README
|
||||
|
||||
Regression tests for data checksums
|
||||
===================================
|
||||
|
||||
This directory contains a test suite for enabling data checksums
|
||||
in a running cluster with streaming replication.
|
||||
|
||||
Running the tests
|
||||
=================
|
||||
|
||||
make check
|
||||
|
||||
or
|
||||
|
||||
make installcheck
|
||||
|
||||
NOTE: This creates a temporary installation (in the case of "check"),
|
||||
with multiple nodes, be they master or standby(s) for the purpose of
|
||||
the tests.
|
||||
|
||||
NOTE: This requires the --enable-tap-tests argument to configure.
|
@ -1,101 +0,0 @@
|
||||
# Test suite for testing enabling data checksums with streaming replication
|
||||
use strict;
|
||||
use warnings;
|
||||
use PostgresNode;
|
||||
use TestLib;
|
||||
use Test::More tests => 10;
|
||||
|
||||
my $MAX_TRIES = 30;
|
||||
|
||||
# Initialize master node
|
||||
my $node_master = get_new_node('master');
|
||||
$node_master->init(allows_streaming => 1);
|
||||
$node_master->start;
|
||||
my $backup_name = 'my_backup';
|
||||
|
||||
# Take backup
|
||||
$node_master->backup($backup_name);
|
||||
|
||||
# Create streaming standby linking to master
|
||||
my $node_standby_1 = get_new_node('standby_1');
|
||||
$node_standby_1->init_from_backup($node_master, $backup_name,
|
||||
has_streaming => 1);
|
||||
$node_standby_1->start;
|
||||
|
||||
# Create some content on master to have un-checksummed data in the cluster
|
||||
$node_master->safe_psql('postgres',
|
||||
"CREATE TABLE t AS SELECT generate_series(1,10000) AS a;");
|
||||
|
||||
# Wait for standbys to catch up
|
||||
$node_master->wait_for_catchup($node_standby_1, 'replay',
|
||||
$node_master->lsn('insert'));
|
||||
|
||||
# Check that checksums are turned off
|
||||
my $result = $node_master->safe_psql('postgres',
|
||||
"SELECT setting FROM pg_catalog.pg_settings WHERE name = 'data_checksums';");
|
||||
is($result, "off", 'ensure checksums are turned off on master');
|
||||
|
||||
$result = $node_standby_1->safe_psql('postgres',
|
||||
"SELECT setting FROM pg_catalog.pg_settings WHERE name = 'data_checksums';");
|
||||
is($result, "off", 'ensure checksums are turned off on standby_1');
|
||||
|
||||
# Enable checksums for the cluster
|
||||
$node_master->safe_psql('postgres', "SELECT pg_enable_data_checksums();");
|
||||
|
||||
# Ensure that the master has switched to inprogress immediately
|
||||
$result = $node_master->safe_psql('postgres',
|
||||
"SELECT setting FROM pg_catalog.pg_settings WHERE name = 'data_checksums';");
|
||||
is($result, "inprogress", 'ensure checksums are in progress on master');
|
||||
|
||||
# Wait for checksum enable to be replayed
|
||||
$node_master->wait_for_catchup($node_standby_1, 'replay');
|
||||
|
||||
# Ensure that the standby has switched to inprogress
|
||||
$result = $node_standby_1->safe_psql('postgres',
|
||||
"SELECT setting FROM pg_catalog.pg_settings WHERE name = 'data_checksums';");
|
||||
is($result, "inprogress", 'ensure checksums are in progress on standby_1');
|
||||
|
||||
# Insert some more data which should be checksummed on INSERT
|
||||
$node_master->safe_psql('postgres',
|
||||
"INSERT INTO t VALUES (generate_series(1,10000));");
|
||||
|
||||
# Wait for checksums enabled on the master
|
||||
for (my $i = 0; $i < $MAX_TRIES; $i++)
|
||||
{
|
||||
$result = $node_master->safe_psql('postgres',
|
||||
"SELECT setting FROM pg_catalog.pg_settings WHERE name = 'data_checksums';");
|
||||
last if ($result eq 'on');
|
||||
sleep(1);
|
||||
}
|
||||
is ($result, "on", 'ensure checksums are enabled on master');
|
||||
|
||||
# Wait for checksums enabled on the standby
|
||||
for (my $i = 0; $i < $MAX_TRIES; $i++)
|
||||
{
|
||||
$result = $node_standby_1->safe_psql('postgres',
|
||||
"SELECT setting FROM pg_catalog.pg_settings WHERE name = 'data_checksums';");
|
||||
last if ($result eq 'on');
|
||||
sleep(1);
|
||||
}
|
||||
is ($result, "on", 'ensure checksums are enabled on standby');
|
||||
|
||||
$result = $node_master->safe_psql('postgres', "SELECT count(a) FROM t");
|
||||
is ($result, "20000", 'ensure we can safely read all data with checksums');
|
||||
|
||||
# Disable checksums and ensure it's propagated to standby and that we can
|
||||
# still read all data
|
||||
$node_master->safe_psql('postgres', "SELECT pg_disable_data_checksums();");
|
||||
$result = $node_master->safe_psql('postgres',
|
||||
"SELECT setting FROM pg_catalog.pg_settings WHERE name = 'data_checksums';");
|
||||
is($result, "off", 'ensure checksums are in progress on master');
|
||||
|
||||
# Wait for checksum disable to be replayed
|
||||
$node_master->wait_for_catchup($node_standby_1, 'replay');
|
||||
|
||||
# Ensure that the standby has switched to off
|
||||
$result = $node_standby_1->safe_psql('postgres',
|
||||
"SELECT setting FROM pg_catalog.pg_settings WHERE name = 'data_checksums';");
|
||||
is($result, "off", 'ensure checksums are in progress on standby_1');
|
||||
|
||||
$result = $node_master->safe_psql('postgres', "SELECT count(a) FROM t");
|
||||
is ($result, "20000", 'ensure we can safely read all data without checksums');
|
@ -1,27 +0,0 @@
|
||||
Parsed test spec with 2 sessions
|
||||
|
||||
starting permutation: c_verify_checksums_off r_seqread c_enable_checksums c_verify_checksums_inprogress c_disable_checksums c_wait_checksums_off
|
||||
step c_verify_checksums_off: SELECT setting = 'off' FROM pg_catalog.pg_settings WHERE name = 'data_checksums';
|
||||
?column?
|
||||
|
||||
t
|
||||
step r_seqread: SELECT * FROM reader_loop();
|
||||
reader_loop
|
||||
|
||||
t
|
||||
step c_enable_checksums: SELECT pg_enable_data_checksums(1000);
|
||||
pg_enable_data_checksums
|
||||
|
||||
|
||||
step c_verify_checksums_inprogress: SELECT setting = 'inprogress' FROM pg_catalog.pg_settings WHERE name = 'data_checksums';
|
||||
?column?
|
||||
|
||||
t
|
||||
step c_disable_checksums: SELECT pg_disable_data_checksums();
|
||||
pg_disable_data_checksums
|
||||
|
||||
|
||||
step c_wait_checksums_off: SELECT test_checksums_off();
|
||||
test_checksums_off
|
||||
|
||||
t
|
@ -1,27 +0,0 @@
|
||||
Parsed test spec with 3 sessions
|
||||
|
||||
starting permutation: c_verify_checksums_off w_insert100k r_seqread c_enable_checksums c_wait_for_checksums c_verify_checksums_on
|
||||
step c_verify_checksums_off: SELECT setting = 'off' FROM pg_catalog.pg_settings WHERE name = 'data_checksums';
|
||||
?column?
|
||||
|
||||
t
|
||||
step w_insert100k: SELECT insert_1k(100);
|
||||
insert_1k
|
||||
|
||||
t
|
||||
step r_seqread: SELECT * FROM reader_loop();
|
||||
reader_loop
|
||||
|
||||
t
|
||||
step c_enable_checksums: SELECT pg_enable_data_checksums();
|
||||
pg_enable_data_checksums
|
||||
|
||||
|
||||
step c_wait_for_checksums: SELECT test_checksums_on();
|
||||
test_checksums_on
|
||||
|
||||
t
|
||||
step c_verify_checksums_on: SELECT setting = 'on' FROM pg_catalog.pg_settings WHERE name = 'data_checksums';
|
||||
?column?
|
||||
|
||||
t
|
@ -76,7 +76,3 @@ test: predicate-gin
|
||||
test: partition-key-update-1
|
||||
test: partition-key-update-2
|
||||
test: partition-key-update-3
|
||||
# The checksum_enable suite will enable checksums for the cluster so should
|
||||
# not run before anything expecting the cluster to have checksums turned off
|
||||
# test: checksum_cancel
|
||||
# test: checksum_enable
|
||||
|
@ -1,47 +0,0 @@
|
||||
setup
|
||||
{
|
||||
CREATE TABLE t1 (a serial, b integer, c text);
|
||||
INSERT INTO t1 (b, c) VALUES (generate_series(1,10000), 'starting values');
|
||||
|
||||
CREATE OR REPLACE FUNCTION test_checksums_off() RETURNS boolean AS $$
|
||||
DECLARE
|
||||
enabled boolean;
|
||||
BEGIN
|
||||
PERFORM pg_sleep(1);
|
||||
SELECT setting = 'off' INTO enabled FROM pg_catalog.pg_settings WHERE name = 'data_checksums';
|
||||
RETURN enabled;
|
||||
END;
|
||||
$$ LANGUAGE plpgsql;
|
||||
|
||||
CREATE OR REPLACE FUNCTION reader_loop() RETURNS boolean AS $$
|
||||
DECLARE
|
||||
counter integer;
|
||||
enabled boolean;
|
||||
BEGIN
|
||||
FOR counter IN 1..100 LOOP
|
||||
PERFORM count(a) FROM t1;
|
||||
END LOOP;
|
||||
RETURN True;
|
||||
END;
|
||||
$$ LANGUAGE plpgsql;
|
||||
}
|
||||
|
||||
teardown
|
||||
{
|
||||
DROP FUNCTION reader_loop();
|
||||
DROP FUNCTION test_checksums_off();
|
||||
|
||||
DROP TABLE t1;
|
||||
}
|
||||
|
||||
session "reader"
|
||||
step "r_seqread" { SELECT * FROM reader_loop(); }
|
||||
|
||||
session "checksums"
|
||||
step "c_verify_checksums_off" { SELECT setting = 'off' FROM pg_catalog.pg_settings WHERE name = 'data_checksums'; }
|
||||
step "c_enable_checksums" { SELECT pg_enable_data_checksums(1000); }
|
||||
step "c_disable_checksums" { SELECT pg_disable_data_checksums(); }
|
||||
step "c_verify_checksums_inprogress" { SELECT setting = 'inprogress' FROM pg_catalog.pg_settings WHERE name = 'data_checksums'; }
|
||||
step "c_wait_checksums_off" { SELECT test_checksums_off(); }
|
||||
|
||||
permutation "c_verify_checksums_off" "r_seqread" "c_enable_checksums" "c_verify_checksums_inprogress" "c_disable_checksums" "c_wait_checksums_off"
|
@ -1,70 +0,0 @@
|
||||
setup
|
||||
{
|
||||
CREATE TABLE t1 (a serial, b integer, c text);
|
||||
INSERT INTO t1 (b, c) VALUES (generate_series(1,10000), 'starting values');
|
||||
|
||||
CREATE OR REPLACE FUNCTION insert_1k(iterations int) RETURNS boolean AS $$
|
||||
DECLARE
|
||||
counter integer;
|
||||
BEGIN
|
||||
FOR counter IN 1..$1 LOOP
|
||||
INSERT INTO t1 (b, c) VALUES (
|
||||
generate_series(1, 1000),
|
||||
array_to_string(array(select chr(97 + (random() * 25)::int) from generate_series(1,250)), '')
|
||||
);
|
||||
PERFORM pg_sleep(0.1);
|
||||
END LOOP;
|
||||
RETURN True;
|
||||
END;
|
||||
$$ LANGUAGE plpgsql;
|
||||
|
||||
CREATE OR REPLACE FUNCTION test_checksums_on() RETURNS boolean AS $$
|
||||
DECLARE
|
||||
enabled boolean;
|
||||
BEGIN
|
||||
LOOP
|
||||
SELECT setting = 'on' INTO enabled FROM pg_catalog.pg_settings WHERE name = 'data_checksums';
|
||||
IF enabled THEN
|
||||
EXIT;
|
||||
END IF;
|
||||
PERFORM pg_sleep(1);
|
||||
END LOOP;
|
||||
RETURN enabled;
|
||||
END;
|
||||
$$ LANGUAGE plpgsql;
|
||||
|
||||
CREATE OR REPLACE FUNCTION reader_loop() RETURNS boolean AS $$
|
||||
DECLARE
|
||||
counter integer;
|
||||
BEGIN
|
||||
FOR counter IN 1..30 LOOP
|
||||
PERFORM count(a) FROM t1;
|
||||
PERFORM pg_sleep(0.2);
|
||||
END LOOP;
|
||||
RETURN True;
|
||||
END;
|
||||
$$ LANGUAGE plpgsql;
|
||||
}
|
||||
|
||||
teardown
|
||||
{
|
||||
DROP FUNCTION reader_loop();
|
||||
DROP FUNCTION test_checksums_on();
|
||||
DROP FUNCTION insert_1k(int);
|
||||
|
||||
DROP TABLE t1;
|
||||
}
|
||||
|
||||
session "writer"
|
||||
step "w_insert100k" { SELECT insert_1k(100); }
|
||||
|
||||
session "reader"
|
||||
step "r_seqread" { SELECT * FROM reader_loop(); }
|
||||
|
||||
session "checksums"
|
||||
step "c_verify_checksums_off" { SELECT setting = 'off' FROM pg_catalog.pg_settings WHERE name = 'data_checksums'; }
|
||||
step "c_enable_checksums" { SELECT pg_enable_data_checksums(); }
|
||||
step "c_wait_for_checksums" { SELECT test_checksums_on(); }
|
||||
step "c_verify_checksums_on" { SELECT setting = 'on' FROM pg_catalog.pg_settings WHERE name = 'data_checksums'; }
|
||||
|
||||
permutation "c_verify_checksums_off" "w_insert100k" "r_seqread" "c_enable_checksums" "c_wait_for_checksums" "c_verify_checksums_on"
|
Loading…
x
Reference in New Issue
Block a user