pg.ddx.io  pgsql-committers@postgresql.org mailing list archive  
help / color / mirror / Atom feed
Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
26+ messages / 5 participants
[nested] [flat]

* Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
@ 2021-08-23 06:13 Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  0 siblings, 1 reply; 26+ messages in thread

From: Amit Kapila @ 2021-08-23 06:13 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Mon, Aug 23, 2021 at 9:53 AM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>
> On Mon, Aug 23, 2021 at 9:11 AM houzj.fnst@fujitsu.com
> <houzj.fnst@fujitsu.com> wrote:
>
> > 4)
> > -extern File SharedFileSetCreate(SharedFileSet *fileset, const char *name);
> > -extern File SharedFileSetOpen(SharedFileSet *fileset, const char *name,
> > -                                                         int mode);
> > -extern bool SharedFileSetDelete(SharedFileSet *fileset, const char *name,
> > -                                                               bool error_on_failure);
> >  extern void SharedFileSetDeleteAll(SharedFileSet *fileset);
> > -extern void SharedFileSetUnregister(SharedFileSet *input_fileset);
> >
> > I noticed the patch delete part of public api, is it better to keep the old api and
> > let them invoke new api internally ? Having said that, I didn’t find any open source
> > extension use these old api, so it might be fine to delete them.
>
> Right, those were internally used by buffile.c but now we have changed
> buffile.c to directly use the fileset interfaces, so we better remove
> them.
>

I also don't see any reason to keep those exposed from
sharedfileset.h. I see that even in the original commit dc6c4c9dc2,
these APIs seem to be introduced to be used by buffile. Andres/Thomas,
do let us know if you think otherwise?

One more comment:
I think v1-0001-Sharedfileset-refactoring doesn't have a way for
cleaning up worker.c temporary files on error/exit. It is better to
have that to make it an independent patch.

-- 
With Regards,
Amit Kapila.





^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
@ 2021-08-23 07:22 ` Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  0 siblings, 1 reply; 26+ messages in thread

From: Dilip Kumar @ 2021-08-23 07:22 UTC (permalink / raw)
  To: Amit Kapila <amit.kapila16@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Mon, Aug 23, 2021 at 11:43 AM Amit Kapila <amit.kapila16@gmail.com> wrote:
>
> On Mon, Aug 23, 2021 at 9:53 AM Dilip Kumar <dilipbalaut@gmail.com> wrote:
> >
> > On Mon, Aug 23, 2021 at 9:11 AM houzj.fnst@fujitsu.com
> > <houzj.fnst@fujitsu.com> wrote:
> >
> > > 4)
> > > -extern File SharedFileSetCreate(SharedFileSet *fileset, const char *name);
> > > -extern File SharedFileSetOpen(SharedFileSet *fileset, const char *name,
> > > -                                                         int mode);
> > > -extern bool SharedFileSetDelete(SharedFileSet *fileset, const char *name,
> > > -                                                               bool error_on_failure);
> > >  extern void SharedFileSetDeleteAll(SharedFileSet *fileset);
> > > -extern void SharedFileSetUnregister(SharedFileSet *input_fileset);
> > >
> > > I noticed the patch delete part of public api, is it better to keep the old api and
> > > let them invoke new api internally ? Having said that, I didn’t find any open source
> > > extension use these old api, so it might be fine to delete them.
> >
> > Right, those were internally used by buffile.c but now we have changed
> > buffile.c to directly use the fileset interfaces, so we better remove
> > them.
> >
>
> I also don't see any reason to keep those exposed from
> sharedfileset.h. I see that even in the original commit dc6c4c9dc2,
> these APIs seem to be introduced to be used by buffile. Andres/Thomas,
> do let us know if you think otherwise?
>
> One more comment:
> I think v1-0001-Sharedfileset-refactoring doesn't have a way for
> cleaning up worker.c temporary files on error/exit. It is better to
> have that to make it an independent patch.

I think we should handle that in worker.c itself, by adding a
before_dsm_detach function before_shmem_exit right?  Or you are
thinking that in FileSetInit, we keep the mechanism of filesetlist
like we were doing in SharedFileSetInit?  I think that will just add
unnecessary complexity in the first patch which will eventually go
away in the second patch.  And if we do that then SharedFileSetInit
can not directly use the FileSetInit, otherwise, the dsm based fileset
will also get registered for cleanup in filesetlist so for that we
might need to pass one parameter to the FileSetInit() that whether to
register for cleanup or not and that will again not look clean because
now we are again adding the conditional cleanup, IMHO that is the same
problem what we are trying to cleanup in SharedFileSetInit by
introducing a new FileSetInit.

I think what we can do is, introduce a new function
FileSetInitInternal(), that will do what FileSetInit() is doing today
and now both SharedFileSetInit() and the FileSetInit() will call this
function, and along with that SharedFileSetInit(), will register the
dsm based cleanup and FileSetInit() will do the filesetlist based
cleanup.  But IMHO, we should try to go in this direction only if we
are sure that we want to commit the first patch and not the second.

-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com





^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
@ 2021-08-23 08:13   ` Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  0 siblings, 1 reply; 26+ messages in thread

From: Amit Kapila @ 2021-08-23 08:13 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Mon, Aug 23, 2021 at 12:52 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>
> On Mon, Aug 23, 2021 at 11:43 AM Amit Kapila <amit.kapila16@gmail.com> wrote:
> >
> > On Mon, Aug 23, 2021 at 9:53 AM Dilip Kumar <dilipbalaut@gmail.com> wrote:
> > >
> > > On Mon, Aug 23, 2021 at 9:11 AM houzj.fnst@fujitsu.com
> > > <houzj.fnst@fujitsu.com> wrote:
> > >
> > > > 4)
> > > > -extern File SharedFileSetCreate(SharedFileSet *fileset, const char *name);
> > > > -extern File SharedFileSetOpen(SharedFileSet *fileset, const char *name,
> > > > -                                                         int mode);
> > > > -extern bool SharedFileSetDelete(SharedFileSet *fileset, const char *name,
> > > > -                                                               bool error_on_failure);
> > > >  extern void SharedFileSetDeleteAll(SharedFileSet *fileset);
> > > > -extern void SharedFileSetUnregister(SharedFileSet *input_fileset);
> > > >
> > > > I noticed the patch delete part of public api, is it better to keep the old api and
> > > > let them invoke new api internally ? Having said that, I didn’t find any open source
> > > > extension use these old api, so it might be fine to delete them.
> > >
> > > Right, those were internally used by buffile.c but now we have changed
> > > buffile.c to directly use the fileset interfaces, so we better remove
> > > them.
> > >
> >
> > I also don't see any reason to keep those exposed from
> > sharedfileset.h. I see that even in the original commit dc6c4c9dc2,
> > these APIs seem to be introduced to be used by buffile. Andres/Thomas,
> > do let us know if you think otherwise?
> >
> > One more comment:
> > I think v1-0001-Sharedfileset-refactoring doesn't have a way for
> > cleaning up worker.c temporary files on error/exit. It is better to
> > have that to make it an independent patch.
>
> I think we should handle that in worker.c itself, by adding a
> before_dsm_detach function before_shmem_exit right?
>

Yeah, I thought of handling it in worker.c similar to what you've in 0002 patch.

-- 
With Regards,
Amit Kapila.





^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
@ 2021-08-23 09:43     ` Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  0 siblings, 1 reply; 26+ messages in thread

From: Dilip Kumar @ 2021-08-23 09:43 UTC (permalink / raw)
  To: Amit Kapila <amit.kapila16@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Mon, Aug 23, 2021 at 1:43 PM Amit Kapila <amit.kapila16@gmail.com> wrote:

Note: merge comments from multiple mails

> > I think we should handle that in worker.c itself, by adding a
> > before_dsm_detach function before_shmem_exit right?
> >
>
> Yeah, I thought of handling it in worker.c similar to what you've in 0002 patch.
>

I have done handling in worker.c

On Mon, Aug 23, 2021 at 9:11 AM houzj.fnst@fujitsu.com
<houzj.fnst@fujitsu.com> wrote:
>
> On Sat, Aug 21, 2021 8:38 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>
> 1)
> +       TempTablespacePath(tempdirpath, tablespace);
> +       snprintf(path, MAXPGPATH, "%s/%s%lu.%u.sharedfileset",
> +                        tempdirpath, PG_TEMP_FILE_PREFIX,
> +                        (unsigned long) fileset->creator_pid, fileset->number);
>
> do we need to use different filename for shared and un-shared fileset ?

I was also thinking about the same, does it make sense to name it just
""%s/%s%lu.%u.fileset"?

On Mon, Aug 23, 2021 at 1:08 PM Masahiko Sawada <sawada.mshk@gmail.com> wrote:

> Here are some comments on 0001 patch:
>
> +/*
> + * Initialize a space for temporary files. This API can be used by shared
> + * fileset as well as if the temporary files are used only by single backend
> + * but the files need to be opened and closed multiple times and also the
> + * underlying files need to survive across transactions.
> + *
> + * Files will be distributed over the tablespaces configured in
> + * temp_tablespaces.
> + *
> + * Under the covers the set is one or more directories which will eventually
> + * be deleted.
> + */
>
> I think it's better to mention cleaning up here like we do in the
> comment of SharedFileSetInit().

Right, done

>
> ---
> I think we need to clean up both stream_fileset and subxact_fileset on
> proc exit. In 0002 patch cleans up the fileset but I think we need to
> do that also in 0001 patch.

Done

> ---
> There still are some comments using "shared fileset" in both buffile.c
> and worker.c.

Done


-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com

Attachments: download all (2 files, .tar.gz)

v2-0001-Sharedfileset-refactoring.patch (text/x-patch, 40.8K) download From ced3a5e0222c2f89a977add167615f09d99d107a Mon Sep 17 00:00:00 2001 From: Dilip Kumar <dilipkumar@localhost.localdomain> Date: Wed, 18 Aug 2021 15:52:21 +0530 Subject: [PATCH v2 1/2] Sharedfileset refactoring Currently, sharedfileset.c is designed for a very specific purpose i.e. one backend could create the fileset and could be shared across multiple backend so the fileset should be created in DSM. But in some use cases, we need exact behavior as sharedfileset that the files created under this should be named files and should survive the transaction and should allow to have feature of open and close. In this patch we have refactored these files such that there will be two files a) fileset.c which will provide general-purpose interfaces b) sharedfileset.c, which will internally used fileset.c but this will be specific for DSM-based filesets. --- src/backend/replication/logical/worker.c | 89 +++++++---- src/backend/storage/file/Makefile | 1 + src/backend/storage/file/buffile.c | 82 +++++----- src/backend/storage/file/fd.c | 2 +- src/backend/storage/file/fileset.c | 204 +++++++++++++++++++++++++ src/backend/storage/file/sharedfileset.c | 239 +----------------------------- src/backend/utils/sort/logtape.c | 8 +- src/backend/utils/sort/sharedtuplestore.c | 5 +- src/include/storage/buffile.h | 12 +- src/include/storage/fileset.h | 40 +++++ src/include/storage/sharedfileset.h | 14 +- 11 files changed, 366 insertions(+), 330 deletions(-) create mode 100644 src/backend/storage/file/fileset.c create mode 100644 src/include/storage/fileset.h diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index ecaed15..d98ebab 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -39,13 +39,13 @@ * BufFile infrastructure supports temporary files that exceed the OS file size * limit, (b) provides a way for automatic clean up on the error and (c) provides * a way to survive these files across local transactions and allow to open and - * close at stream start and close. We decided to use SharedFileSet + * close at stream start and close. We decided to use FileSet * infrastructure as without that it deletes the files on the closure of the * file and if we decide to keep stream files open across the start/stop stream * then it will consume a lot of memory (more than 8K for each BufFile and * there could be multiple such BufFiles as the subscriber could receive * multiple start/stop streams for different transactions before getting the - * commit). Moreover, if we don't use SharedFileSet then we also need to invent + * commit). Moreover, if we don't use FileSet then we also need to invent * a new way to pass filenames to BufFile APIs so that we are allowed to open * the file we desired across multiple stream-open calls for the same * transaction. @@ -231,8 +231,8 @@ typedef struct ApplyExecutionData typedef struct StreamXidHash { TransactionId xid; /* xid is the hash key and must be first */ - SharedFileSet *stream_fileset; /* shared file set for stream data */ - SharedFileSet *subxact_fileset; /* shared file set for subxact info */ + FileSet *stream_fileset; /* file set for stream data */ + FileSet *subxact_fileset; /* file set for subxact info */ } StreamXidHash; static MemoryContext ApplyMessageContext = NULL; @@ -255,8 +255,8 @@ static bool in_streamed_transaction = false; static TransactionId stream_xid = InvalidTransactionId; /* - * Hash table for storing the streaming xid information along with shared file - * set for streaming and subxact files. + * Hash table for storing the streaming xid information along with filesets + * for streaming and subxact files. */ static HTAB *xidhash = NULL; @@ -1299,10 +1299,10 @@ apply_handle_stream_abort(StringInfo s) /* open the changes file */ changes_filename(path, MyLogicalRepWorker->subid, xid); - fd = BufFileOpenShared(ent->stream_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); /* OK, truncate the file at the right offset */ - BufFileTruncateShared(fd, subxact_data.subxacts[subidx].fileno, + BufFileTruncateFileSet(fd, subxact_data.subxacts[subidx].fileno, subxact_data.subxacts[subidx].offset); BufFileClose(fd); @@ -1355,7 +1355,7 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) errmsg_internal("transaction %u not found in stream XID hash table", xid))); - fd = BufFileOpenShared(ent->stream_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDONLY); buffer = palloc(BLCKSZ); initStringInfo(&s2); @@ -2508,6 +2508,33 @@ UpdateWorkerStats(XLogRecPtr last_lsn, TimestampTz send_time, bool reply) } } + /* + * Cleanup filesets. + */ +static void +worker_cleanup(int code, Datum arg) +{ + HASH_SEQ_STATUS status; + StreamXidHash *hentry; + + /* + * Scan the xidhash table if created and from each entry delete stream + * fileset and the subxact fileset. + */ + if (xidhash) + { + hash_seq_init(&status, xidhash); + while ((hentry = (StreamXidHash *) hash_seq_search(&status)) != NULL) + { + FileSetDeleteAll(hentry->stream_fileset); + + /* Delete the subxact fileset only if it is created */ + if (hentry->subxact_fileset) + FileSetDeleteAll(hentry->subxact_fileset); + } + } +} + /* * Apply main loop. */ @@ -2534,6 +2561,12 @@ LogicalRepApplyLoop(XLogRecPtr last_received) "LogicalStreamingContext", ALLOCSET_DEFAULT_SIZES); + /* + * Register before-shmem-exit hook to ensure filesets are dropped while we + * can still report stats for underlying temporary files. + */ + before_shmem_exit(worker_cleanup, (Datum) 0); + /* mark as idle, before starting to loop */ pgstat_report_activity(STATE_IDLE, NULL); @@ -2979,7 +3012,7 @@ subxact_info_write(Oid subid, TransactionId xid) if (ent->subxact_fileset) { cleanup_subxact_info(); - SharedFileSetDeleteAll(ent->subxact_fileset); + FileSetDeleteAll(ent->subxact_fileset); pfree(ent->subxact_fileset); ent->subxact_fileset = NULL; } @@ -2997,18 +3030,18 @@ subxact_info_write(Oid subid, TransactionId xid) MemoryContext oldctx; /* - * We need to maintain shared fileset across multiple stream - * start/stop calls. So, need to allocate it in a persistent context. + * We need to maintain fileset across multiple stream start/stop calls. + * So, need to allocate it in a persistent context. */ oldctx = MemoryContextSwitchTo(ApplyContext); - ent->subxact_fileset = palloc(sizeof(SharedFileSet)); - SharedFileSetInit(ent->subxact_fileset, NULL); + ent->subxact_fileset = palloc(sizeof(FileSet)); + FileSetInit(ent->subxact_fileset); MemoryContextSwitchTo(oldctx); - fd = BufFileCreateShared(ent->subxact_fileset, path); + fd = BufFileCreateFileSet(ent->subxact_fileset, path); } else - fd = BufFileOpenShared(ent->subxact_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDWR); len = sizeof(SubXactInfo) * subxact_data.nsubxacts; @@ -3062,7 +3095,7 @@ subxact_info_read(Oid subid, TransactionId xid) subxact_filename(path, subid, xid); - fd = BufFileOpenShared(ent->subxact_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDONLY); /* read number of subxact items */ if (BufFileRead(fd, &subxact_data.nsubxacts, @@ -3219,7 +3252,7 @@ stream_cleanup_files(Oid subid, TransactionId xid) /* Delete the change file and release the stream fileset memory */ changes_filename(path, subid, xid); - SharedFileSetDeleteAll(ent->stream_fileset); + FileSetDeleteAll(ent->stream_fileset); pfree(ent->stream_fileset); ent->stream_fileset = NULL; @@ -3227,7 +3260,7 @@ stream_cleanup_files(Oid subid, TransactionId xid) if (ent->subxact_fileset) { subxact_filename(path, subid, xid); - SharedFileSetDeleteAll(ent->subxact_fileset); + FileSetDeleteAll(ent->subxact_fileset); pfree(ent->subxact_fileset); ent->subxact_fileset = NULL; } @@ -3243,8 +3276,8 @@ stream_cleanup_files(Oid subid, TransactionId xid) * * Open a file for streamed changes from a toplevel transaction identified * by stream_xid (global variable). If it's the first chunk of streamed - * changes for this transaction, initialize the shared fileset and create the - * buffile, otherwise open the previously created file. + * changes for this transaction, initialize the fileset and create the buffile, + * otherwise open the previously created file. * * This can only be called at the beginning of a "streaming" block, i.e. * between stream_start/stream_stop messages from the upstream. @@ -3285,7 +3318,7 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) if (first_segment) { MemoryContext savectx; - SharedFileSet *fileset; + FileSet *fileset; if (found) ereport(ERROR, @@ -3293,16 +3326,16 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); /* - * We need to maintain shared fileset across multiple stream - * start/stop calls. So, need to allocate it in a persistent context. + * We need to maintain fileset across multiple stream start/stop calls. + * So, need to allocate it in a persistent context. */ savectx = MemoryContextSwitchTo(ApplyContext); - fileset = palloc(sizeof(SharedFileSet)); + fileset = palloc(sizeof(FileSet)); - SharedFileSetInit(fileset, NULL); + FileSetInit(fileset); MemoryContextSwitchTo(savectx); - stream_fd = BufFileCreateShared(fileset, path); + stream_fd = BufFileCreateFileSet(fileset, path); /* Remember the fileset for the next stream of the same transaction */ ent->xid = xid; @@ -3320,7 +3353,7 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) * Open the file and seek to the end of the file because we always * append the changes file. */ - stream_fd = BufFileOpenShared(ent->stream_fileset, path, O_RDWR); + stream_fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); BufFileSeek(stream_fd, 0, 0, SEEK_END); } diff --git a/src/backend/storage/file/Makefile b/src/backend/storage/file/Makefile index 5e1291b..660ac51 100644 --- a/src/backend/storage/file/Makefile +++ b/src/backend/storage/file/Makefile @@ -16,6 +16,7 @@ OBJS = \ buffile.o \ copydir.o \ fd.o \ + fileset.o \ reinit.o \ sharedfileset.o diff --git a/src/backend/storage/file/buffile.c b/src/backend/storage/file/buffile.c index a4be5fe..b9ca298 100644 --- a/src/backend/storage/file/buffile.c +++ b/src/backend/storage/file/buffile.c @@ -39,7 +39,7 @@ * BufFile also supports temporary files that can be used by the single backend * when the corresponding files need to be survived across the transaction and * need to be opened and closed multiple times. Such files need to be created - * as a member of a SharedFileSet. + * as a member of a FileSet. *------------------------------------------------------------------------- */ @@ -77,8 +77,8 @@ struct BufFile bool dirty; /* does buffer need to be written? */ bool readOnly; /* has the file been set to read only? */ - SharedFileSet *fileset; /* space for segment files if shared */ - const char *name; /* name of this BufFile if shared */ + FileSet *fileset; /* space for fileset for fileset based file */ + const char *name; /* name of this BufFile */ /* * resowner is the ResourceOwner to use for underlying temp files. (We @@ -104,7 +104,7 @@ static void extendBufFile(BufFile *file); static void BufFileLoadBuffer(BufFile *file); static void BufFileDumpBuffer(BufFile *file); static void BufFileFlush(BufFile *file); -static File MakeNewSharedSegment(BufFile *file, int segment); +static File MakeNewSegment(BufFile *file, int segment); /* * Create BufFile and perform the common initialization. @@ -160,7 +160,7 @@ extendBufFile(BufFile *file) if (file->fileset == NULL) pfile = OpenTemporaryFile(file->isInterXact); else - pfile = MakeNewSharedSegment(file, file->numFiles); + pfile = MakeNewSegment(file, file->numFiles); Assert(pfile >= 0); @@ -214,34 +214,34 @@ BufFileCreateTemp(bool interXact) * Build the name for a given segment of a given BufFile. */ static void -SharedSegmentName(char *name, const char *buffile_name, int segment) +SegmentName(char *name, const char *buffile_name, int segment) { snprintf(name, MAXPGPATH, "%s.%d", buffile_name, segment); } /* - * Create a new segment file backing a shared BufFile. + * Create a new segment file backing a fileset BufFile. */ static File -MakeNewSharedSegment(BufFile *buffile, int segment) +MakeNewSegment(BufFile *buffile, int segment) { char name[MAXPGPATH]; File file; /* * It is possible that there are files left over from before a crash - * restart with the same name. In order for BufFileOpenShared() not to + * restart with the same name. In order for BufFileOpen() not to * get confused about how many segments there are, we'll unlink the next * segment number if it already exists. */ - SharedSegmentName(name, buffile->name, segment + 1); - SharedFileSetDelete(buffile->fileset, name, true); + SegmentName(name, buffile->name, segment + 1); + FileSetDelete(buffile->fileset, name, true); /* Create the new segment. */ - SharedSegmentName(name, buffile->name, segment); - file = SharedFileSetCreate(buffile->fileset, name); + SegmentName(name, buffile->name, segment); + file = FileSetCreate(buffile->fileset, name); - /* SharedFileSetCreate would've errored out */ + /* FileSetCreate would've errored out */ Assert(file > 0); return file; @@ -251,7 +251,7 @@ MakeNewSharedSegment(BufFile *buffile, int segment) * Create a BufFile that can be discovered and opened read-only by other * backends that are attached to the same SharedFileSet using the same name. * - * The naming scheme for shared BufFiles is left up to the calling code. The + * The naming scheme for fileset BufFiles is left up to the calling code. The * name will appear as part of one or more filenames on disk, and might * provide clues to administrators about which subsystem is generating * temporary file data. Since each SharedFileSet object is backed by one or @@ -259,7 +259,7 @@ MakeNewSharedSegment(BufFile *buffile, int segment) * unrelated SharedFileSet objects. */ BufFile * -BufFileCreateShared(SharedFileSet *fileset, const char *name) +BufFileCreateFileSet(FileSet *fileset, const char *name) { BufFile *file; @@ -267,7 +267,7 @@ BufFileCreateShared(SharedFileSet *fileset, const char *name) file->fileset = fileset; file->name = pstrdup(name); file->files = (File *) palloc(sizeof(File)); - file->files[0] = MakeNewSharedSegment(file, 0); + file->files[0] = MakeNewSegment(file, 0); file->readOnly = false; return file; @@ -275,13 +275,13 @@ BufFileCreateShared(SharedFileSet *fileset, const char *name) /* * Open a file that was previously created in another backend (or this one) - * with BufFileCreateShared in the same SharedFileSet using the same name. + * with BufFileCreateFileSet in the same FileSet using the same name. * The backend that created the file must have called BufFileClose() or - * BufFileExportShared() to make sure that it is ready to be opened by other + * BufFileExportFileSet() to make sure that it is ready to be opened by other * backends and render it read-only. */ BufFile * -BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) +BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) { BufFile *file; char segment_name[MAXPGPATH]; @@ -304,8 +304,8 @@ BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) files = repalloc(files, sizeof(File) * capacity); } /* Try to load a segment. */ - SharedSegmentName(segment_name, name, nfiles); - files[nfiles] = SharedFileSetOpen(fileset, segment_name, mode); + SegmentName(segment_name, name, nfiles); + files[nfiles] = FileSetOpen(fileset, segment_name, mode); if (files[nfiles] <= 0) break; ++nfiles; @@ -333,18 +333,18 @@ BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) } /* - * Delete a BufFile that was created by BufFileCreateShared in the given - * SharedFileSet using the given name. + * Delete a BufFile that was created by BufFileCreateFileSet in the given + * FileSet using the given name. * * It is not necessary to delete files explicitly with this function. It is * provided only as a way to delete files proactively, rather than waiting for - * the SharedFileSet to be cleaned up. + * the FileSet to be cleaned up. * * Only one backend should attempt to delete a given name, and should know * that it exists and has been exported or closed. */ void -BufFileDeleteShared(SharedFileSet *fileset, const char *name) +BufFileDeleteFileSet(FileSet *fileset, const char *name) { char segment_name[MAXPGPATH]; int segment = 0; @@ -357,8 +357,8 @@ BufFileDeleteShared(SharedFileSet *fileset, const char *name) */ for (;;) { - SharedSegmentName(segment_name, name, segment); - if (!SharedFileSetDelete(fileset, segment_name, true)) + SegmentName(segment_name, name, segment); + if (!FileSetDelete(fileset, segment_name, true)) break; found = true; ++segment; @@ -367,16 +367,16 @@ BufFileDeleteShared(SharedFileSet *fileset, const char *name) } if (!found) - elog(ERROR, "could not delete unknown shared BufFile \"%s\"", name); + elog(ERROR, "could not delete unknown BufFile \"%s\"", name); } /* - * BufFileExportShared --- flush and make read-only, in preparation for sharing. + * BufFileExportFileSet --- flush and make read-only, in preparation for sharing. */ void -BufFileExportShared(BufFile *file) +BufFileExportFileSet(BufFile *file) { - /* Must be a file belonging to a SharedFileSet. */ + /* Must be a file belonging to a FileSet. */ Assert(file->fileset != NULL); /* It's probably a bug if someone calls this twice. */ @@ -785,7 +785,7 @@ BufFileTellBlock(BufFile *file) #endif /* - * Return the current shared BufFile size. + * Return the current fileset based BufFile size. * * Counts any holes left behind by BufFileAppend as part of the size. * ereport()s on failure. @@ -811,8 +811,8 @@ BufFileSize(BufFile *file) } /* - * Append the contents of source file (managed within shared fileset) to - * end of target file (managed within same shared fileset). + * Append the contents of source file (managed within fileset) to + * end of target file (managed within same fileset). * * Note that operation subsumes ownership of underlying resources from * "source". Caller should never call BufFileClose against source having @@ -854,11 +854,11 @@ BufFileAppend(BufFile *target, BufFile *source) } /* - * Truncate a BufFile created by BufFileCreateShared up to the given fileno and - * the offset. + * Truncate a BufFile created by BufFileCreateFileSet up to the given fileno + * and the offset. */ void -BufFileTruncateShared(BufFile *file, int fileno, off_t offset) +BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset) { int numFiles = file->numFiles; int newFile = fileno; @@ -876,12 +876,12 @@ BufFileTruncateShared(BufFile *file, int fileno, off_t offset) { if ((i != fileno || offset == 0) && i != 0) { - SharedSegmentName(segment_name, file->name, i); + SegmentName(segment_name, file->name, i); FileClose(file->files[i]); - if (!SharedFileSetDelete(file->fileset, segment_name, true)) + if (!FileSetDelete(file->fileset, segment_name, true)) ereport(ERROR, (errcode_for_file_access(), - errmsg("could not delete shared fileset \"%s\": %m", + errmsg("could not delete fileset \"%s\": %m", segment_name))); numFiles--; newOffset = MAX_PHYSICAL_FILESIZE; diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c index b58b399..433e283 100644 --- a/src/backend/storage/file/fd.c +++ b/src/backend/storage/file/fd.c @@ -1921,7 +1921,7 @@ PathNameDeleteTemporaryFile(const char *path, bool error_on_failure) /* * Unlike FileClose's automatic file deletion code, we tolerate - * non-existence to support BufFileDeleteShared which doesn't know how + * non-existence to support BufFileDeleteFileSet which doesn't know how * many segments it has to delete until it runs out. */ if (stat_errno == ENOENT) diff --git a/src/backend/storage/file/fileset.c b/src/backend/storage/file/fileset.c new file mode 100644 index 0000000..a720c49 --- /dev/null +++ b/src/backend/storage/file/fileset.c @@ -0,0 +1,204 @@ +/*------------------------------------------------------------------------- + * + * fileset.c + * temporary file set management. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/backend/storage/file/fileset.c + * + * FileSets provide a temporary namespace (think directory) so that files can + * be discovered by name + * + * FileSets can be used by backends when the temporary files need to be + * opened/closed multiple times and the underlying files need to survive across + * transactions. + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include <limits.h> + +#include "catalog/pg_tablespace.h" +#include "commands/tablespace.h" +#include "common/hashfn.h" +#include "miscadmin.h" +#include "storage/ipc.h" +#include "storage/fileset.h" +#include "utils/builtins.h" + +static void FileSetPath(char *path, FileSet *fileset, Oid tablespace); +static void FilePath(char *path, FileSet *fileset, const char *name); +static Oid ChooseTablespace(const FileSet *fileset, const char *name); + +/* + * Initialize a space for temporary files. This API can be used by shared + * fileset as well as if the temporary files are used only by single backend + * but the files need to be opened and closed multiple times and also the + * underlying files need to survive across transactions. + * + * The callers are expected to explicitly remove such files by using + * SharedFileSetDelete/ SharedFileSetDeleteAll. + * + * Files will be distributed over the tablespaces configured in + * temp_tablespaces. + * + * Under the covers the set is one or more directories which will eventually + * be deleted. + */ +void +FileSetInit(FileSet *fileset) +{ + static uint32 counter = 0; + + fileset->creator_pid = MyProcPid; + fileset->number = counter; + counter = (counter + 1) % INT_MAX; + + /* Capture the tablespace OIDs so that all backends agree on them. */ + PrepareTempTablespaces(); + fileset->ntablespaces = + GetTempTablespaces(&fileset->tablespaces[0], + lengthof(fileset->tablespaces)); + if (fileset->ntablespaces == 0) + { + /* If the GUC is empty, use current database's default tablespace */ + fileset->tablespaces[0] = MyDatabaseTableSpace; + fileset->ntablespaces = 1; + } + else + { + int i; + + /* + * An entry of InvalidOid means use the default tablespace for the + * current database. Replace that now, to be sure that all users of + * the FileSet agree on what to do. + */ + for (i = 0; i < fileset->ntablespaces; i++) + { + if (fileset->tablespaces[i] == InvalidOid) + fileset->tablespaces[i] = MyDatabaseTableSpace; + } + } +} + +/* + * Create a new file in the given set. + */ +File +FileSetCreate(FileSet *fileset, const char *name) +{ + char path[MAXPGPATH]; + File file; + + FilePath(path, fileset, name); + file = PathNameCreateTemporaryFile(path, false); + + /* If we failed, see if we need to create the directory on demand. */ + if (file <= 0) + { + char tempdirpath[MAXPGPATH]; + char filesetpath[MAXPGPATH]; + Oid tablespace = ChooseTablespace(fileset, name); + + TempTablespacePath(tempdirpath, tablespace); + FileSetPath(filesetpath, fileset, tablespace); + PathNameCreateTemporaryDir(tempdirpath, filesetpath); + file = PathNameCreateTemporaryFile(path, true); + } + + return file; +} + +/* + * Open a file that was created with FileSetCreate() */ +File +FileSetOpen(FileSet *fileset, const char *name, int mode) +{ + char path[MAXPGPATH]; + File file; + + FilePath(path, fileset, name); + file = PathNameOpenTemporaryFile(path, mode); + + return file; +} + +/* + * Delete a file that was created with FileSetCreate(). + * Return true if the file existed, false if didn't. + */ +bool +FileSetDelete(FileSet *fileset, const char *name, + bool error_on_failure) +{ + char path[MAXPGPATH]; + + FilePath(path, fileset, name); + + return PathNameDeleteTemporaryFile(path, error_on_failure); +} + +/* + * Delete all files in the set. + */ +void +FileSetDeleteAll(FileSet *fileset) +{ + char dirpath[MAXPGPATH]; + int i; + + /* + * Delete the directory we created in each tablespace. Doesn't fail + * because we use this in error cleanup paths, but can generate LOG + * message on IO error. + */ + for (i = 0; i < fileset->ntablespaces; ++i) + { + FileSetPath(dirpath, fileset, fileset->tablespaces[i]); + PathNameDeleteTemporaryDir(dirpath); + } +} + +/* + * Build the path for the directory holding the files backing a FileSet in a + * given tablespace. + */ +static void +FileSetPath(char *path, FileSet *fileset, Oid tablespace) +{ + char tempdirpath[MAXPGPATH]; + + TempTablespacePath(tempdirpath, tablespace); + snprintf(path, MAXPGPATH, "%s/%s%lu.%u.sharedfileset", + tempdirpath, PG_TEMP_FILE_PREFIX, + (unsigned long) fileset->creator_pid, fileset->number); +} + +/* + * Sorting hat to determine which tablespace a given temporary file belongs in. + */ +static Oid +ChooseTablespace(const FileSet *fileset, const char *name) +{ + uint32 hash = hash_any((const unsigned char *) name, strlen(name)); + + return fileset->tablespaces[hash % fileset->ntablespaces]; +} + +/* + * Compute the full path of a file in a FileSet. + */ +static void +FilePath(char *path, FileSet *fileset, const char *name) +{ + char dirpath[MAXPGPATH]; + + FileSetPath(dirpath, fileset, ChooseTablespace(fileset, name)); + snprintf(path, MAXPGPATH, "%s/%s", dirpath, name); +} diff --git a/src/backend/storage/file/sharedfileset.c b/src/backend/storage/file/sharedfileset.c index ed37c94..96ad968 100644 --- a/src/backend/storage/file/sharedfileset.c +++ b/src/backend/storage/file/sharedfileset.c @@ -13,10 +13,6 @@ * files can be discovered by name, and a shared ownership semantics so that * shared files survive until the last user detaches. * - * SharedFileSets can be used by backends when the temporary files need to be - * opened/closed multiple times and the underlying files need to survive across - * transactions. - * *------------------------------------------------------------------------- */ @@ -33,13 +29,7 @@ #include "storage/sharedfileset.h" #include "utils/builtins.h" -static List *filesetlist = NIL; - static void SharedFileSetOnDetach(dsm_segment *segment, Datum datum); -static void SharedFileSetDeleteOnProcExit(int status, Datum arg); -static void SharedFileSetPath(char *path, SharedFileSet *fileset, Oid tablespace); -static void SharedFilePath(char *path, SharedFileSet *fileset, const char *name); -static Oid ChooseTablespace(const SharedFileSet *fileset, const char *name); /* * Initialize a space for temporary files that can be opened by other backends. @@ -47,13 +37,6 @@ static Oid ChooseTablespace(const SharedFileSet *fileset, const char *name); * SharedFileSet with 'seg'. Any contained files will be deleted when the * last backend detaches. * - * We can also use this interface if the temporary files are used only by - * single backend but the files need to be opened and closed multiple times - * and also the underlying files need to survive across transactions. For - * such cases, dsm segment 'seg' should be passed as NULL. Callers are - * expected to explicitly remove such files by using SharedFileSetDelete/ - * SharedFileSetDeleteAll or we remove such files on proc exit. - * * Files will be distributed over the tablespaces configured in * temp_tablespaces. * @@ -63,61 +46,14 @@ static Oid ChooseTablespace(const SharedFileSet *fileset, const char *name); void SharedFileSetInit(SharedFileSet *fileset, dsm_segment *seg) { - static uint32 counter = 0; - SpinLockInit(&fileset->mutex); fileset->refcnt = 1; - fileset->creator_pid = MyProcPid; - fileset->number = counter; - counter = (counter + 1) % INT_MAX; - - /* Capture the tablespace OIDs so that all backends agree on them. */ - PrepareTempTablespaces(); - fileset->ntablespaces = - GetTempTablespaces(&fileset->tablespaces[0], - lengthof(fileset->tablespaces)); - if (fileset->ntablespaces == 0) - { - /* If the GUC is empty, use current database's default tablespace */ - fileset->tablespaces[0] = MyDatabaseTableSpace; - fileset->ntablespaces = 1; - } - else - { - int i; - /* - * An entry of InvalidOid means use the default tablespace for the - * current database. Replace that now, to be sure that all users of - * the SharedFileSet agree on what to do. - */ - for (i = 0; i < fileset->ntablespaces; i++) - { - if (fileset->tablespaces[i] == InvalidOid) - fileset->tablespaces[i] = MyDatabaseTableSpace; - } - } + FileSetInit(&fileset->fs); /* Register our cleanup callback. */ if (seg) on_dsm_detach(seg, SharedFileSetOnDetach, PointerGetDatum(fileset)); - else - { - static bool registered_cleanup = false; - - if (!registered_cleanup) - { - /* - * We must not have registered any fileset before registering the - * fileset clean up. - */ - Assert(filesetlist == NIL); - on_proc_exit(SharedFileSetDeleteOnProcExit, 0); - registered_cleanup = true; - } - - filesetlist = lcons((void *) fileset, filesetlist); - } } /* @@ -148,86 +84,12 @@ SharedFileSetAttach(SharedFileSet *fileset, dsm_segment *seg) } /* - * Create a new file in the given set. - */ -File -SharedFileSetCreate(SharedFileSet *fileset, const char *name) -{ - char path[MAXPGPATH]; - File file; - - SharedFilePath(path, fileset, name); - file = PathNameCreateTemporaryFile(path, false); - - /* If we failed, see if we need to create the directory on demand. */ - if (file <= 0) - { - char tempdirpath[MAXPGPATH]; - char filesetpath[MAXPGPATH]; - Oid tablespace = ChooseTablespace(fileset, name); - - TempTablespacePath(tempdirpath, tablespace); - SharedFileSetPath(filesetpath, fileset, tablespace); - PathNameCreateTemporaryDir(tempdirpath, filesetpath); - file = PathNameCreateTemporaryFile(path, true); - } - - return file; -} - -/* - * Open a file that was created with SharedFileSetCreate(), possibly in - * another backend. - */ -File -SharedFileSetOpen(SharedFileSet *fileset, const char *name, int mode) -{ - char path[MAXPGPATH]; - File file; - - SharedFilePath(path, fileset, name); - file = PathNameOpenTemporaryFile(path, mode); - - return file; -} - -/* - * Delete a file that was created with SharedFileSetCreate(). - * Return true if the file existed, false if didn't. - */ -bool -SharedFileSetDelete(SharedFileSet *fileset, const char *name, - bool error_on_failure) -{ - char path[MAXPGPATH]; - - SharedFilePath(path, fileset, name); - - return PathNameDeleteTemporaryFile(path, error_on_failure); -} - -/* * Delete all files in the set. */ void SharedFileSetDeleteAll(SharedFileSet *fileset) { - char dirpath[MAXPGPATH]; - int i; - - /* - * Delete the directory we created in each tablespace. Doesn't fail - * because we use this in error cleanup paths, but can generate LOG - * message on IO error. - */ - for (i = 0; i < fileset->ntablespaces; ++i) - { - SharedFileSetPath(dirpath, fileset, fileset->tablespaces[i]); - PathNameDeleteTemporaryDir(dirpath); - } - - /* Unregister the shared fileset */ - SharedFileSetUnregister(fileset); + return FileSetDeleteAll(&fileset->fs); } /* @@ -255,100 +117,5 @@ SharedFileSetOnDetach(dsm_segment *segment, Datum datum) * this function so we can safely access its data. */ if (unlink_all) - SharedFileSetDeleteAll(fileset); -} - -/* - * Callback function that will be invoked on the process exit. This will - * process the list of all the registered sharedfilesets and delete the - * underlying files. - */ -static void -SharedFileSetDeleteOnProcExit(int status, Datum arg) -{ - /* - * Remove all the pending shared fileset entries. We don't use foreach() - * here because SharedFileSetDeleteAll will remove the current element in - * filesetlist. Though we have used foreach_delete_current() to remove the - * element from filesetlist it could only fix up the state of one of the - * loops, see SharedFileSetUnregister. - */ - while (list_length(filesetlist) > 0) - { - SharedFileSet *fileset = (SharedFileSet *) linitial(filesetlist); - - SharedFileSetDeleteAll(fileset); - } - - filesetlist = NIL; -} - -/* - * Unregister the shared fileset entry registered for cleanup on proc exit. - */ -void -SharedFileSetUnregister(SharedFileSet *input_fileset) -{ - ListCell *l; - - /* - * If the caller is following the dsm based cleanup then we don't maintain - * the filesetlist so return. - */ - if (filesetlist == NIL) - return; - - foreach(l, filesetlist) - { - SharedFileSet *fileset = (SharedFileSet *) lfirst(l); - - /* Remove the entry from the list */ - if (input_fileset == fileset) - { - filesetlist = foreach_delete_current(filesetlist, l); - return; - } - } - - /* Should have found a match */ - Assert(false); -} - -/* - * Build the path for the directory holding the files backing a SharedFileSet - * in a given tablespace. - */ -static void -SharedFileSetPath(char *path, SharedFileSet *fileset, Oid tablespace) -{ - char tempdirpath[MAXPGPATH]; - - TempTablespacePath(tempdirpath, tablespace); - snprintf(path, MAXPGPATH, "%s/%s%lu.%u.sharedfileset", - tempdirpath, PG_TEMP_FILE_PREFIX, - (unsigned long) fileset->creator_pid, fileset->number); -} - -/* - * Sorting hat to determine which tablespace a given shared temporary file - * belongs in. - */ -static Oid -ChooseTablespace(const SharedFileSet *fileset, const char *name) -{ - uint32 hash = hash_any((const unsigned char *) name, strlen(name)); - - return fileset->tablespaces[hash % fileset->ntablespaces]; -} - -/* - * Compute the full path of a file in a SharedFileSet. - */ -static void -SharedFilePath(char *path, SharedFileSet *fileset, const char *name) -{ - char dirpath[MAXPGPATH]; - - SharedFileSetPath(dirpath, fileset, ChooseTablespace(fileset, name)); - snprintf(path, MAXPGPATH, "%s/%s", dirpath, name); + FileSetDeleteAll(&fileset->fs); } diff --git a/src/backend/utils/sort/logtape.c b/src/backend/utils/sort/logtape.c index cafc087..f7994d7 100644 --- a/src/backend/utils/sort/logtape.c +++ b/src/backend/utils/sort/logtape.c @@ -564,7 +564,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, lt = &lts->tapes[i]; pg_itoa(i, filename); - file = BufFileOpenShared(fileset, filename, O_RDONLY); + file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY); filesize = BufFileSize(file); /* @@ -610,7 +610,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, * offset). * * The only thing that currently prevents writing to the leader tape from - * working is the fact that BufFiles opened using BufFileOpenShared() are + * working is the fact that BufFiles opened using BufFileOpenFileSet() are * read-only by definition, but that could be changed if it seemed * worthwhile. For now, writing to the leader tape will raise a "Bad file * descriptor" error, so tuplesort must avoid writing to the leader tape @@ -722,7 +722,7 @@ LogicalTapeSetCreate(int ntapes, bool preallocate, TapeShare *shared, char filename[MAXPGPATH]; pg_itoa(worker, filename); - lts->pfile = BufFileCreateShared(fileset, filename); + lts->pfile = BufFileCreateFileSet(&fileset->fs, filename); } else lts->pfile = BufFileCreateTemp(false); @@ -1096,7 +1096,7 @@ LogicalTapeFreeze(LogicalTapeSet *lts, int tapenum, TapeShare *share) /* Handle extra steps when caller is to share its tapeset */ if (share) { - BufFileExportShared(lts->pfile); + BufFileExportFileSet(lts->pfile); share->firstblocknumber = lt->firstBlockNumber; } } diff --git a/src/backend/utils/sort/sharedtuplestore.c b/src/backend/utils/sort/sharedtuplestore.c index 57e35db..72acd54 100644 --- a/src/backend/utils/sort/sharedtuplestore.c +++ b/src/backend/utils/sort/sharedtuplestore.c @@ -310,7 +310,8 @@ sts_puttuple(SharedTuplestoreAccessor *accessor, void *meta_data, /* Create one. Only this backend will write into it. */ sts_filename(name, accessor, accessor->participant); - accessor->write_file = BufFileCreateShared(accessor->fileset, name); + accessor->write_file = + BufFileCreateFileSet(&accessor->fileset->fs, name); /* Set up the shared state for this backend's file. */ participant = &accessor->sts->participants[accessor->participant]; @@ -559,7 +560,7 @@ sts_parallel_scan_next(SharedTuplestoreAccessor *accessor, void *meta_data) sts_filename(name, accessor, accessor->read_participant); accessor->read_file = - BufFileOpenShared(accessor->fileset, name, O_RDONLY); + BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY); } /* Seek and load the chunk header. */ diff --git a/src/include/storage/buffile.h b/src/include/storage/buffile.h index 566523d..032a823 100644 --- a/src/include/storage/buffile.h +++ b/src/include/storage/buffile.h @@ -26,7 +26,7 @@ #ifndef BUFFILE_H #define BUFFILE_H -#include "storage/sharedfileset.h" +#include "storage/fileset.h" /* BufFile is an opaque type whose details are not known outside buffile.c. */ @@ -46,11 +46,11 @@ extern int BufFileSeekBlock(BufFile *file, long blknum); extern int64 BufFileSize(BufFile *file); extern long BufFileAppend(BufFile *target, BufFile *source); -extern BufFile *BufFileCreateShared(SharedFileSet *fileset, const char *name); -extern void BufFileExportShared(BufFile *file); -extern BufFile *BufFileOpenShared(SharedFileSet *fileset, const char *name, +extern BufFile *BufFileCreateFileSet(FileSet *fileset, const char *name); +extern void BufFileExportFileSet(BufFile *file); +extern BufFile *BufFileOpenFileSet(FileSet *fileset, const char *name, int mode); -extern void BufFileDeleteShared(SharedFileSet *fileset, const char *name); -extern void BufFileTruncateShared(BufFile *file, int fileno, off_t offset); +extern void BufFileDeleteFileSet(FileSet *fileset, const char *name); +extern void BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset); #endif /* BUFFILE_H */ diff --git a/src/include/storage/fileset.h b/src/include/storage/fileset.h new file mode 100644 index 0000000..8795fd1 --- /dev/null +++ b/src/include/storage/fileset.h @@ -0,0 +1,40 @@ +/*------------------------------------------------------------------------- + * + * fileset.h + * temporary file management. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/storage/fileset.h + * + *------------------------------------------------------------------------- + */ + +#ifndef FILESET_H +#define FILESET_H + +#include "storage/fd.h" + +/* + * A set of temporary files. + */ +typedef struct FileSet +{ + pid_t creator_pid; /* PID of the creating process */ + uint32 number; /* per-PID identifier */ + int ntablespaces; /* number of tablespaces to use */ + Oid tablespaces[8]; /* OIDs of tablespaces to use. Assumes that + * it's rare that there more than temp + * tablespaces. */ +} FileSet; + +extern void FileSetInit(FileSet *fileset); +extern File FileSetCreate(FileSet *fileset, const char *name); +extern File FileSetOpen(FileSet *fileset, const char *name, + int mode); +extern bool FileSetDelete(FileSet *fileset, const char *name, + bool error_on_failure); +extern void FileSetDeleteAll(FileSet *fileset); + +#endif diff --git a/src/include/storage/sharedfileset.h b/src/include/storage/sharedfileset.h index 09ba121..59becfb 100644 --- a/src/include/storage/sharedfileset.h +++ b/src/include/storage/sharedfileset.h @@ -17,6 +17,7 @@ #include "storage/dsm.h" #include "storage/fd.h" +#include "storage/fileset.h" #include "storage/spin.h" /* @@ -24,24 +25,13 @@ */ typedef struct SharedFileSet { - pid_t creator_pid; /* PID of the creating process */ - uint32 number; /* per-PID identifier */ + FileSet fs; slock_t mutex; /* mutex protecting the reference count */ int refcnt; /* number of attached backends */ - int ntablespaces; /* number of tablespaces to use */ - Oid tablespaces[8]; /* OIDs of tablespaces to use. Assumes that - * it's rare that there more than temp - * tablespaces. */ } SharedFileSet; extern void SharedFileSetInit(SharedFileSet *fileset, dsm_segment *seg); extern void SharedFileSetAttach(SharedFileSet *fileset, dsm_segment *seg); -extern File SharedFileSetCreate(SharedFileSet *fileset, const char *name); -extern File SharedFileSetOpen(SharedFileSet *fileset, const char *name, - int mode); -extern bool SharedFileSetDelete(SharedFileSet *fileset, const char *name, - bool error_on_failure); extern void SharedFileSetDeleteAll(SharedFileSet *fileset); -extern void SharedFileSetUnregister(SharedFileSet *input_fileset); #endif -- 1.8.3.1
v2-0002-Better-usage-of-sharedfileset-in-apply-worker.patch (text/x-patch, 17.6K) download From d764f828e1cbbf6a69b9adf929282cb12b501ddb Mon Sep 17 00:00:00 2001 From: Dilip Kumar <dilipkumar@localhost.localdomain> Date: Mon, 23 Aug 2021 15:07:28 +0530 Subject: [PATCH v2 2/2] Better usage of sharedfileset in apply worker Instead of using a separate shared fileset for each xid, use one shared fileset for whole lifetime of the worker. So for each xid, just create shared buffile under that shared fileset and remove the file whenever we are done with the file. For subxact file we only need to create once we get the first subtransaction and for detecting that we also extend the buffile open and buffile delete interfaces to allow the missing files. --- src/backend/replication/logical/worker.c | 238 ++++++------------------------ src/backend/storage/file/buffile.c | 23 ++- src/backend/utils/sort/logtape.c | 2 +- src/backend/utils/sort/sharedtuplestore.c | 3 +- src/include/storage/buffile.h | 5 +- 5 files changed, 65 insertions(+), 206 deletions(-) diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index d98ebab..f991e09 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -221,20 +221,6 @@ typedef struct ApplyExecutionData PartitionTupleRouting *proute; /* partition routing info */ } ApplyExecutionData; -/* - * Stream xid hash entry. Whenever we see a new xid we create this entry in the - * xidhash and along with it create the streaming file and store the fileset handle. - * The subxact file is created iff there is any subxact info under this xid. This - * entry is used on the subsequent streams for the xid to get the corresponding - * fileset handles, so storing them in hash makes the search faster. - */ -typedef struct StreamXidHash -{ - TransactionId xid; /* xid is the hash key and must be first */ - FileSet *stream_fileset; /* file set for stream data */ - FileSet *subxact_fileset; /* file set for subxact info */ -} StreamXidHash; - static MemoryContext ApplyMessageContext = NULL; MemoryContext ApplyContext = NULL; @@ -255,10 +241,11 @@ static bool in_streamed_transaction = false; static TransactionId stream_xid = InvalidTransactionId; /* - * Hash table for storing the streaming xid information along with filesets - * for streaming and subxact files. + * Fileset for storing the changes and subxact information for the streaming + * transaction. We will use only one fileset and for each xid a separate + * changes and subxact files will be created under the same fileset. */ -static HTAB *xidhash = NULL; +static FileSet *xidfileset = NULL; /* BufFile handle of the current streaming file */ static BufFile *stream_fd = NULL; @@ -1129,7 +1116,6 @@ static void apply_handle_stream_start(StringInfo s) { bool first_segment; - HASHCTL hash_ctl; if (in_streamed_transaction) ereport(ERROR, @@ -1157,17 +1143,21 @@ apply_handle_stream_start(StringInfo s) errmsg_internal("invalid transaction ID in streamed replication transaction"))); /* - * Initialize the xidhash table if we haven't yet. This will be used for - * the entire duration of the apply worker so create it in permanent - * context. + * Initialize the xidfileset if we haven't yet. This will be used for the + * entire duration of the apply worker so create it in permanent context. */ - if (xidhash == NULL) + if (xidfileset == NULL) { - hash_ctl.keysize = sizeof(TransactionId); - hash_ctl.entrysize = sizeof(StreamXidHash); - hash_ctl.hcxt = ApplyContext; - xidhash = hash_create("StreamXidHash", 1024, &hash_ctl, - HASH_ELEM | HASH_BLOBS | HASH_CONTEXT); + MemoryContext oldctx; + + /* + * We need to keep the fileset for the worker lifetime so need to + * allocate it in a persistent context. + */ + oldctx = MemoryContextSwitchTo(ApplyContext); + xidfileset = palloc(sizeof(FileSet)); + FileSetInit(xidfileset); + MemoryContextSwitchTo(oldctx); } /* open the spool file for this transaction */ @@ -1258,7 +1248,6 @@ apply_handle_stream_abort(StringInfo s) BufFile *fd; bool found = false; char path[MAXPGPATH]; - StreamXidHash *ent; subidx = -1; begin_replication_step(); @@ -1287,19 +1276,9 @@ apply_handle_stream_abort(StringInfo s) return; } - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* open the changes file */ changes_filename(path, MyLogicalRepWorker->subid, xid); - fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(xidfileset, path, O_RDWR, false); /* OK, truncate the file at the right offset */ BufFileTruncateFileSet(fd, subxact_data.subxacts[subidx].fileno, @@ -1327,7 +1306,6 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) int nchanges; char path[MAXPGPATH]; char *buffer = NULL; - StreamXidHash *ent; MemoryContext oldcxt; BufFile *fd; @@ -1345,17 +1323,7 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) changes_filename(path, MyLogicalRepWorker->subid, xid); elog(DEBUG1, "replaying changes from file \"%s\"", path); - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - - fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(xidfileset, path, O_RDONLY, false); buffer = palloc(BLCKSZ); initStringInfo(&s2); @@ -2508,31 +2476,14 @@ UpdateWorkerStats(XLogRecPtr last_lsn, TimestampTz send_time, bool reply) } } - /* - * Cleanup filesets. +/* + * Cleanup fileset if created. */ static void worker_cleanup(int code, Datum arg) { - HASH_SEQ_STATUS status; - StreamXidHash *hentry; - - /* - * Scan the xidhash table if created and from each entry delete stream - * fileset and the subxact fileset. - */ - if (xidhash) - { - hash_seq_init(&status, xidhash); - while ((hentry = (StreamXidHash *) hash_seq_search(&status)) != NULL) - { - FileSetDeleteAll(hentry->stream_fileset); - - /* Delete the subxact fileset only if it is created */ - if (hentry->subxact_fileset) - FileSetDeleteAll(hentry->subxact_fileset); - } - } + if (xidfileset != NULL) + FileSetDeleteAll(xidfileset); } /* @@ -2562,7 +2513,7 @@ LogicalRepApplyLoop(XLogRecPtr last_received) ALLOCSET_DEFAULT_SIZES); /* - * Register before-shmem-exit hook to ensure filesets are dropped while we + * Register before-shmem-exit hook to ensure fileset is dropped while we * can still report stats for underlying temporary files. */ before_shmem_exit(worker_cleanup, (Datum) 0); @@ -2990,18 +2941,11 @@ subxact_info_write(Oid subid, TransactionId xid) { char path[MAXPGPATH]; Size len; - StreamXidHash *ent; BufFile *fd; Assert(TransactionIdIsValid(xid)); - /* Find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - /* By this time we must have created the transaction entry */ - Assert(ent); + subxact_filename(path, subid, xid); /* * If there is no subtransaction then nothing to do, but if already have @@ -3009,39 +2953,18 @@ subxact_info_write(Oid subid, TransactionId xid) */ if (subxact_data.nsubxacts == 0) { - if (ent->subxact_fileset) - { - cleanup_subxact_info(); - FileSetDeleteAll(ent->subxact_fileset); - pfree(ent->subxact_fileset); - ent->subxact_fileset = NULL; - } + cleanup_subxact_info(); + BufFileDeleteFileSet(xidfileset, path, true); + return; } subxact_filename(path, subid, xid); - /* - * Create the subxact file if it not already created, otherwise open the - * existing file. - */ - if (ent->subxact_fileset == NULL) - { - MemoryContext oldctx; - - /* - * We need to maintain fileset across multiple stream start/stop calls. - * So, need to allocate it in a persistent context. - */ - oldctx = MemoryContextSwitchTo(ApplyContext); - ent->subxact_fileset = palloc(sizeof(FileSet)); - FileSetInit(ent->subxact_fileset); - MemoryContextSwitchTo(oldctx); - - fd = BufFileCreateFileSet(ent->subxact_fileset, path); - } - else - fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDWR); + /* Try to open the subxact file, if it doesn't exist then create it */ + fd = BufFileOpenFileSet(xidfileset, path, O_RDWR, true); + if (fd == NULL) + fd = BufFileCreateFileSet(xidfileset, path); len = sizeof(SubXactInfo) * subxact_data.nsubxacts; @@ -3068,34 +2991,17 @@ subxact_info_read(Oid subid, TransactionId xid) char path[MAXPGPATH]; Size len; BufFile *fd; - StreamXidHash *ent; MemoryContext oldctx; Assert(!subxact_data.subxacts); Assert(subxact_data.nsubxacts == 0); Assert(subxact_data.nsubxacts_max == 0); - /* Find the stream xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - - /* - * If subxact_fileset is not valid that mean we don't have any subxact - * info - */ - if (ent->subxact_fileset == NULL) - return; - subxact_filename(path, subid, xid); - fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(xidfileset, path, O_RDONLY, true); + if (fd == NULL) + return; /* read number of subxact items */ if (BufFileRead(fd, &subxact_data.nsubxacts, @@ -3237,36 +3143,13 @@ static void stream_cleanup_files(Oid subid, TransactionId xid) { char path[MAXPGPATH]; - StreamXidHash *ent; - - /* Find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); /* Delete the change file and release the stream fileset memory */ changes_filename(path, subid, xid); - FileSetDeleteAll(ent->stream_fileset); - pfree(ent->stream_fileset); - ent->stream_fileset = NULL; - - /* Delete the subxact file and release the memory, if it exist */ - if (ent->subxact_fileset) - { - subxact_filename(path, subid, xid); - FileSetDeleteAll(ent->subxact_fileset); - pfree(ent->subxact_fileset); - ent->subxact_fileset = NULL; - } + BufFileDeleteFileSet(xidfileset, path, false); - /* Remove the xid entry from the stream xid hash */ - hash_search(xidhash, (void *) &xid, HASH_REMOVE, NULL); + subxact_filename(path, subid, xid); + BufFileDeleteFileSet(xidfileset, path, true); } /* @@ -3276,8 +3159,8 @@ stream_cleanup_files(Oid subid, TransactionId xid) * * Open a file for streamed changes from a toplevel transaction identified * by stream_xid (global variable). If it's the first chunk of streamed - * changes for this transaction, initialize the fileset and create the buffile, - * otherwise open the previously created file. + * changes for this transaction, create the buffile, otherwise open the + * previously created file. * * This can only be called at the beginning of a "streaming" block, i.e. * between stream_start/stream_stop messages from the upstream. @@ -3286,20 +3169,13 @@ static void stream_open_file(Oid subid, TransactionId xid, bool first_segment) { char path[MAXPGPATH]; - bool found; MemoryContext oldcxt; - StreamXidHash *ent; Assert(in_streamed_transaction); Assert(OidIsValid(subid)); Assert(TransactionIdIsValid(xid)); Assert(stream_fd == NULL); - /* create or find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_ENTER, - &found); changes_filename(path, subid, xid); elog(DEBUG1, "opening file \"%s\" for streamed changes", path); @@ -3316,44 +3192,14 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) * writing, in append mode. */ if (first_segment) - { - MemoryContext savectx; - FileSet *fileset; - - if (found) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); - - /* - * We need to maintain fileset across multiple stream start/stop calls. - * So, need to allocate it in a persistent context. - */ - savectx = MemoryContextSwitchTo(ApplyContext); - fileset = palloc(sizeof(FileSet)); - - FileSetInit(fileset); - MemoryContextSwitchTo(savectx); - - stream_fd = BufFileCreateFileSet(fileset, path); - - /* Remember the fileset for the next stream of the same transaction */ - ent->xid = xid; - ent->stream_fileset = fileset; - ent->subxact_fileset = NULL; - } + stream_fd = BufFileCreateFileSet(xidfileset, path); else { - if (!found) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); - /* * Open the file and seek to the end of the file because we always * append the changes file. */ - stream_fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); + stream_fd = BufFileOpenFileSet(xidfileset, path, O_RDWR, false); BufFileSeek(stream_fd, 0, 0, SEEK_END); } diff --git a/src/backend/storage/file/buffile.c b/src/backend/storage/file/buffile.c index b9ca298..dbaa0e6 100644 --- a/src/backend/storage/file/buffile.c +++ b/src/backend/storage/file/buffile.c @@ -278,10 +278,12 @@ BufFileCreateFileSet(FileSet *fileset, const char *name) * with BufFileCreateFileSet in the same FileSet using the same name. * The backend that created the file must have called BufFileClose() or * BufFileExportFileSet() to make sure that it is ready to be opened by other - * backends and render it read-only. + * backends and render it read-only. If missing_ok is true then it will return + * NULL if file doesn't exist otherwise error. */ BufFile * -BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) +BufFileOpenFileSet(FileSet *fileset, const char *name, int mode, + bool missing_ok) { BufFile *file; char segment_name[MAXPGPATH]; @@ -318,10 +320,18 @@ BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) * name. */ if (nfiles == 0) + { + /* free the memory */ + pfree(files); + + if (missing_ok) + return NULL; + ereport(ERROR, (errcode_for_file_access(), errmsg("could not open temporary file \"%s\" from BufFile \"%s\": %m", segment_name, name))); + } file = makeBufFileCommon(nfiles); file->files = files; @@ -341,10 +351,11 @@ BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) * the FileSet to be cleaned up. * * Only one backend should attempt to delete a given name, and should know - * that it exists and has been exported or closed. + * that it exists and has been exported or closed otherwise missing_ok should + * be passed true. */ void -BufFileDeleteFileSet(FileSet *fileset, const char *name) +BufFileDeleteFileSet(FileSet *fileset, const char *name, bool missing_ok) { char segment_name[MAXPGPATH]; int segment = 0; @@ -358,7 +369,7 @@ BufFileDeleteFileSet(FileSet *fileset, const char *name) for (;;) { SegmentName(segment_name, name, segment); - if (!FileSetDelete(fileset, segment_name, true)) + if (!FileSetDelete(fileset, segment_name, !missing_ok)) break; found = true; ++segment; @@ -366,7 +377,7 @@ BufFileDeleteFileSet(FileSet *fileset, const char *name) CHECK_FOR_INTERRUPTS(); } - if (!found) + if (!found && !missing_ok) elog(ERROR, "could not delete unknown BufFile \"%s\"", name); } diff --git a/src/backend/utils/sort/logtape.c b/src/backend/utils/sort/logtape.c index f7994d7..debf12e1 100644 --- a/src/backend/utils/sort/logtape.c +++ b/src/backend/utils/sort/logtape.c @@ -564,7 +564,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, lt = &lts->tapes[i]; pg_itoa(i, filename); - file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY); + file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY, false); filesize = BufFileSize(file); /* diff --git a/src/backend/utils/sort/sharedtuplestore.c b/src/backend/utils/sort/sharedtuplestore.c index 72acd54..8c5135c 100644 --- a/src/backend/utils/sort/sharedtuplestore.c +++ b/src/backend/utils/sort/sharedtuplestore.c @@ -560,7 +560,8 @@ sts_parallel_scan_next(SharedTuplestoreAccessor *accessor, void *meta_data) sts_filename(name, accessor, accessor->read_participant); accessor->read_file = - BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY); + BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY, + false); } /* Seek and load the chunk header. */ diff --git a/src/include/storage/buffile.h b/src/include/storage/buffile.h index 032a823..5e9df44 100644 --- a/src/include/storage/buffile.h +++ b/src/include/storage/buffile.h @@ -49,8 +49,9 @@ extern long BufFileAppend(BufFile *target, BufFile *source); extern BufFile *BufFileCreateFileSet(FileSet *fileset, const char *name); extern void BufFileExportFileSet(BufFile *file); extern BufFile *BufFileOpenFileSet(FileSet *fileset, const char *name, - int mode); -extern void BufFileDeleteFileSet(FileSet *fileset, const char *name); + int mode, bool missing_ok); +extern void BufFileDeleteFileSet(FileSet *fileset, const char *name, + bool missing_ok); extern void BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset); #endif /* BUFFILE_H */ -- 1.8.3.1
^ permalink raw reply [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
@ 2021-08-24 06:56       ` Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  0 siblings, 1 reply; 26+ messages in thread

From: Amit Kapila @ 2021-08-24 06:56 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Mon, Aug 23, 2021 at 3:13 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>
> On Mon, Aug 23, 2021 at 1:43 PM Amit Kapila <amit.kapila16@gmail.com> wrote:
>
> Note: merge comments from multiple mails
>
> > > I think we should handle that in worker.c itself, by adding a
> > > before_dsm_detach function before_shmem_exit right?
> > >
> >
> > Yeah, I thought of handling it in worker.c similar to what you've in 0002 patch.
> >
>
> I have done handling in worker.c
>
> On Mon, Aug 23, 2021 at 9:11 AM houzj.fnst@fujitsu.com
> <houzj.fnst@fujitsu.com> wrote:
> >
> > On Sat, Aug 21, 2021 8:38 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
> >
> > 1)
> > +       TempTablespacePath(tempdirpath, tablespace);
> > +       snprintf(path, MAXPGPATH, "%s/%s%lu.%u.sharedfileset",
> > +                        tempdirpath, PG_TEMP_FILE_PREFIX,
> > +                        (unsigned long) fileset->creator_pid, fileset->number);
> >
> > do we need to use different filename for shared and un-shared fileset ?
>
> I was also thinking about the same, does it make sense to name it just
> ""%s/%s%lu.%u.fileset"?
>

I think it is reasonable to use .fileset as proposed by you.

Few other comments:
=================
1.
+ /*
+ * Register before-shmem-exit hook to ensure filesets are dropped while we
+ * can still report stats for underlying temporary files.
+ */
+ before_shmem_exit(worker_cleanup, (Datum) 0);
+

Do we really need to register a new callback here? Won't the existing
logical replication worker exit routine (logicalrep_worker_onexit) be
sufficient for this patch's purpose?

2.
- SharedFileSet *fileset; /* space for segment files if shared */
- const char *name; /* name of this BufFile if shared */
+ FileSet    *fileset; /* space for fileset for fileset based file */
+ const char *name; /* name of this BufFile */

The comments for the above two variables can be written as (a) space
for fileset based segment files, (b) name of fileset based BufFile.

3.
 /*
- * Create a new segment file backing a shared BufFile.
+ * Create a new segment file backing a fileset BufFile.
  */
 static File
-MakeNewSharedSegment(BufFile *buffile, int segment)
+MakeNewSegment(BufFile *buffile, int segment)

I think it is better to name this function as MakeNewFileSetSegment.
You can slightly change the comment as: "Create a new segment file
backing a fileset based BufFile."

4.
/*
  * It is possible that there are files left over from before a crash
- * restart with the same name.  In order for BufFileOpenShared() not to
+ * restart with the same name.  In order for BufFileOpen() not to
  * get confused about how many segments there are, we'll unlink the next

Typo. /BufFileOpen/BufFileOpenFileSet

5.
 static void
-SharedSegmentName(char *name, const char *buffile_name, int segment)
+SegmentName(char *name, const char *buffile_name, int segment)

Can we name this as FileSetSegmentName?

6.
  *
- * The naming scheme for shared BufFiles is left up to the calling code.  The
+ * The naming scheme for fileset BufFiles is left up to the calling code.

Isn't it better to say "... fileset based BufFiles .."?

7.
+ * FileSets provide a temporary namespace (think directory) so that files can
+ * be discovered by name

A full stop is missing at the end of the statement.

8.
+ *
+ * The callers are expected to explicitly remove such files by using
+ * SharedFileSetDelete/ SharedFileSetDeleteAll.
+ *
+ * Files will be distributed over the tablespaces configured in
+ * temp_tablespaces.
+ *
+ * Under the covers the set is one or more directories which will eventually
+ * be deleted.
+ */
+void
+FileSetInit(FileSet *fileset)

Is there a need to mention 'Shared' in API names (SharedFileSetDelete/
SharedFileSetDeleteAll) in the comments? Also, there doesn't seem to
be a need for extra space before *DeleteAll API in comments.

9.
 * Files will be distributed over the tablespaces configured in
 * temp_tablespaces.
 *
 * Under the covers the set is one or more directories which will eventually
 * be deleted.
 */
void
SharedFileSetInit(SharedFileSet *fileset, dsm_segment *seg)

I think we can remove the part of the above comment where it says
"Files will be distributed over ..." as that is already mentioned atop
FileSetInit.

-- 
With Regards,
Amit Kapila.





^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
@ 2021-08-24 10:25         ` Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 01:50           ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  0 siblings, 2 replies; 26+ messages in thread

From: Dilip Kumar @ 2021-08-24 10:25 UTC (permalink / raw)
  To: Amit Kapila <amit.kapila16@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Tue, Aug 24, 2021 at 12:26 PM Amit Kapila <amit.kapila16@gmail.com> wrote:

> > I was also thinking about the same, does it make sense to name it just
> > ""%s/%s%lu.%u.fileset"?

Done

> I think it is reasonable to use .fileset as proposed by you.
>
> Few other comments:
> =================
> 1.
> + /*
> + * Register before-shmem-exit hook to ensure filesets are dropped while we
> + * can still report stats for underlying temporary files.
> + */
> + before_shmem_exit(worker_cleanup, (Datum) 0);
> +
>
> Do we really need to register a new callback here? Won't the existing
> logical replication worker exit routine (logicalrep_worker_onexit) be
> sufficient for this patch's purpose?

Right, we don't need an extra function for this.

> 2.
> - SharedFileSet *fileset; /* space for segment files if shared */
> - const char *name; /* name of this BufFile if shared */
> + FileSet    *fileset; /* space for fileset for fileset based file */
> + const char *name; /* name of this BufFile */
>
> The comments for the above two variables can be written as (a) space
> for fileset based segment files, (b) name of fileset based BufFile.

Done

> 3.
>  /*
> - * Create a new segment file backing a shared BufFile.
> + * Create a new segment file backing a fileset BufFile.
>   */
>  static File
> -MakeNewSharedSegment(BufFile *buffile, int segment)
> +MakeNewSegment(BufFile *buffile, int segment)
>
> I think it is better to name this function as MakeNewFileSetSegment.
> You can slightly change the comment as: "Create a new segment file
> backing a fileset based BufFile."

 Make sense

> 4.
> /*
>   * It is possible that there are files left over from before a crash
> - * restart with the same name.  In order for BufFileOpenShared() not to
> + * restart with the same name.  In order for BufFileOpen() not to
>   * get confused about how many segments there are, we'll unlink the next
>
> Typo. /BufFileOpen/BufFileOpenFileSet

Fixed

> 5.
>  static void
> -SharedSegmentName(char *name, const char *buffile_name, int segment)
> +SegmentName(char *name, const char *buffile_name, int segment)
>
> Can we name this as FileSetSegmentName?

Done

> 6.
>   *
> - * The naming scheme for shared BufFiles is left up to the calling code.  The
> + * The naming scheme for fileset BufFiles is left up to the calling code.
>
> Isn't it better to say "... fileset based BufFiles .."?

Done

> 7.
> + * FileSets provide a temporary namespace (think directory) so that files can
> + * be discovered by name
>
> A full stop is missing at the end of the statement.

Fixed

> 8.
> + *
> + * The callers are expected to explicitly remove such files by using
> + * SharedFileSetDelete/ SharedFileSetDeleteAll.
> + *
> + * Files will be distributed over the tablespaces configured in
> + * temp_tablespaces.
> + *
> + * Under the covers the set is one or more directories which will eventually
> + * be deleted.
> + */
> +void
> +FileSetInit(FileSet *fileset)
>
> Is there a need to mention 'Shared' in API names (SharedFileSetDelete/
> SharedFileSetDeleteAll) in the comments? Also, there doesn't seem to
> be a need for extra space before *DeleteAll API in comments.

Fixed

> 9.
>  * Files will be distributed over the tablespaces configured in
>  * temp_tablespaces.
>  *
>  * Under the covers the set is one or more directories which will eventually
>  * be deleted.
>  */
> void
> SharedFileSetInit(SharedFileSet *fileset, dsm_segment *seg)
>
> I think we can remove the part of the above comment where it says
> "Files will be distributed over ..." as that is already mentioned atop
> FileSetInit.

Done

-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com

Attachments: download all (2 files, .tar.gz)

v3-0001-Sharedfileset-refactoring.patch (text/x-patch, 41.8K) download From 94a8a22726f08f07259b49ccee340ab1d4cba116 Mon Sep 17 00:00:00 2001 From: Dilip Kumar <dilipkumar@localhost.localdomain> Date: Wed, 18 Aug 2021 15:52:21 +0530 Subject: [PATCH v3 1/2] Sharedfileset refactoring Currently, sharedfileset.c is designed for a very specific purpose i.e. one backend could create the fileset and that could be shared across multiple backends so the fileset should be created in DSM. But in some use cases, we need exact behavior as sharedfileset that the files are created under this should be named files and should also survive the transaction and should be allowed to be opened and closed. In this patch we have refactored these files such that there will be two files a) fileset.c which will provide general-purpose interfaces b) sharedfileset.c, which will internally used fileset.c but this will be specific for DSM-based filesets. --- src/backend/replication/logical/launcher.c | 3 + src/backend/replication/logical/worker.c | 83 ++++++---- src/backend/storage/file/Makefile | 1 + src/backend/storage/file/buffile.c | 84 +++++----- src/backend/storage/file/fd.c | 2 +- src/backend/storage/file/fileset.c | 204 ++++++++++++++++++++++++ src/backend/storage/file/sharedfileset.c | 244 +---------------------------- src/backend/utils/sort/logtape.c | 8 +- src/backend/utils/sort/sharedtuplestore.c | 5 +- src/include/replication/worker_internal.h | 1 + src/include/storage/buffile.h | 12 +- src/include/storage/fileset.h | 40 +++++ src/include/storage/sharedfileset.h | 14 +- 13 files changed, 367 insertions(+), 334 deletions(-) create mode 100644 src/backend/storage/file/fileset.c create mode 100644 src/include/storage/fileset.h diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index e3b11da..8b1772d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -648,6 +648,9 @@ logicalrep_worker_onexit(int code, Datum arg) logicalrep_worker_detach(); + /* Cleanup filesets used for streaming transactions. */ + logicalrep_worker_cleanupfileset(); + ApplyLauncherWakeup(); } diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index ecaed15..07a2c90 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -39,13 +39,13 @@ * BufFile infrastructure supports temporary files that exceed the OS file size * limit, (b) provides a way for automatic clean up on the error and (c) provides * a way to survive these files across local transactions and allow to open and - * close at stream start and close. We decided to use SharedFileSet + * close at stream start and close. We decided to use FileSet * infrastructure as without that it deletes the files on the closure of the * file and if we decide to keep stream files open across the start/stop stream * then it will consume a lot of memory (more than 8K for each BufFile and * there could be multiple such BufFiles as the subscriber could receive * multiple start/stop streams for different transactions before getting the - * commit). Moreover, if we don't use SharedFileSet then we also need to invent + * commit). Moreover, if we don't use FileSet then we also need to invent * a new way to pass filenames to BufFile APIs so that we are allowed to open * the file we desired across multiple stream-open calls for the same * transaction. @@ -231,8 +231,8 @@ typedef struct ApplyExecutionData typedef struct StreamXidHash { TransactionId xid; /* xid is the hash key and must be first */ - SharedFileSet *stream_fileset; /* shared file set for stream data */ - SharedFileSet *subxact_fileset; /* shared file set for subxact info */ + FileSet *stream_fileset; /* file set for stream data */ + FileSet *subxact_fileset; /* file set for subxact info */ } StreamXidHash; static MemoryContext ApplyMessageContext = NULL; @@ -255,8 +255,8 @@ static bool in_streamed_transaction = false; static TransactionId stream_xid = InvalidTransactionId; /* - * Hash table for storing the streaming xid information along with shared file - * set for streaming and subxact files. + * Hash table for storing the streaming xid information along with filesets + * for streaming and subxact files. */ static HTAB *xidhash = NULL; @@ -1299,10 +1299,10 @@ apply_handle_stream_abort(StringInfo s) /* open the changes file */ changes_filename(path, MyLogicalRepWorker->subid, xid); - fd = BufFileOpenShared(ent->stream_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); /* OK, truncate the file at the right offset */ - BufFileTruncateShared(fd, subxact_data.subxacts[subidx].fileno, + BufFileTruncateFileSet(fd, subxact_data.subxacts[subidx].fileno, subxact_data.subxacts[subidx].offset); BufFileClose(fd); @@ -1355,7 +1355,7 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) errmsg_internal("transaction %u not found in stream XID hash table", xid))); - fd = BufFileOpenShared(ent->stream_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDONLY); buffer = palloc(BLCKSZ); initStringInfo(&s2); @@ -2509,6 +2509,33 @@ UpdateWorkerStats(XLogRecPtr last_lsn, TimestampTz send_time, bool reply) } /* + * Cleanup filesets. + */ +void +logicalrep_worker_cleanupfileset() +{ + HASH_SEQ_STATUS status; + StreamXidHash *hentry; + + /* + * Scan the xidhash table if created and from each entry delete stream + * fileset and the subxact fileset. + */ + if (xidhash) + { + hash_seq_init(&status, xidhash); + while ((hentry = (StreamXidHash *) hash_seq_search(&status)) != NULL) + { + FileSetDeleteAll(hentry->stream_fileset); + + /* Delete the subxact fileset only if it is created */ + if (hentry->subxact_fileset) + FileSetDeleteAll(hentry->subxact_fileset); + } + } +} + +/* * Apply main loop. */ static void @@ -2979,7 +3006,7 @@ subxact_info_write(Oid subid, TransactionId xid) if (ent->subxact_fileset) { cleanup_subxact_info(); - SharedFileSetDeleteAll(ent->subxact_fileset); + FileSetDeleteAll(ent->subxact_fileset); pfree(ent->subxact_fileset); ent->subxact_fileset = NULL; } @@ -2997,18 +3024,18 @@ subxact_info_write(Oid subid, TransactionId xid) MemoryContext oldctx; /* - * We need to maintain shared fileset across multiple stream - * start/stop calls. So, need to allocate it in a persistent context. + * We need to maintain fileset across multiple stream start/stop calls. + * So, need to allocate it in a persistent context. */ oldctx = MemoryContextSwitchTo(ApplyContext); - ent->subxact_fileset = palloc(sizeof(SharedFileSet)); - SharedFileSetInit(ent->subxact_fileset, NULL); + ent->subxact_fileset = palloc(sizeof(FileSet)); + FileSetInit(ent->subxact_fileset); MemoryContextSwitchTo(oldctx); - fd = BufFileCreateShared(ent->subxact_fileset, path); + fd = BufFileCreateFileSet(ent->subxact_fileset, path); } else - fd = BufFileOpenShared(ent->subxact_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDWR); len = sizeof(SubXactInfo) * subxact_data.nsubxacts; @@ -3062,7 +3089,7 @@ subxact_info_read(Oid subid, TransactionId xid) subxact_filename(path, subid, xid); - fd = BufFileOpenShared(ent->subxact_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDONLY); /* read number of subxact items */ if (BufFileRead(fd, &subxact_data.nsubxacts, @@ -3219,7 +3246,7 @@ stream_cleanup_files(Oid subid, TransactionId xid) /* Delete the change file and release the stream fileset memory */ changes_filename(path, subid, xid); - SharedFileSetDeleteAll(ent->stream_fileset); + FileSetDeleteAll(ent->stream_fileset); pfree(ent->stream_fileset); ent->stream_fileset = NULL; @@ -3227,7 +3254,7 @@ stream_cleanup_files(Oid subid, TransactionId xid) if (ent->subxact_fileset) { subxact_filename(path, subid, xid); - SharedFileSetDeleteAll(ent->subxact_fileset); + FileSetDeleteAll(ent->subxact_fileset); pfree(ent->subxact_fileset); ent->subxact_fileset = NULL; } @@ -3243,8 +3270,8 @@ stream_cleanup_files(Oid subid, TransactionId xid) * * Open a file for streamed changes from a toplevel transaction identified * by stream_xid (global variable). If it's the first chunk of streamed - * changes for this transaction, initialize the shared fileset and create the - * buffile, otherwise open the previously created file. + * changes for this transaction, initialize the fileset and create the buffile, + * otherwise open the previously created file. * * This can only be called at the beginning of a "streaming" block, i.e. * between stream_start/stream_stop messages from the upstream. @@ -3285,7 +3312,7 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) if (first_segment) { MemoryContext savectx; - SharedFileSet *fileset; + FileSet *fileset; if (found) ereport(ERROR, @@ -3293,16 +3320,16 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); /* - * We need to maintain shared fileset across multiple stream - * start/stop calls. So, need to allocate it in a persistent context. + * We need to maintain fileset across multiple stream start/stop calls. + * So, need to allocate it in a persistent context. */ savectx = MemoryContextSwitchTo(ApplyContext); - fileset = palloc(sizeof(SharedFileSet)); + fileset = palloc(sizeof(FileSet)); - SharedFileSetInit(fileset, NULL); + FileSetInit(fileset); MemoryContextSwitchTo(savectx); - stream_fd = BufFileCreateShared(fileset, path); + stream_fd = BufFileCreateFileSet(fileset, path); /* Remember the fileset for the next stream of the same transaction */ ent->xid = xid; @@ -3320,7 +3347,7 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) * Open the file and seek to the end of the file because we always * append the changes file. */ - stream_fd = BufFileOpenShared(ent->stream_fileset, path, O_RDWR); + stream_fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); BufFileSeek(stream_fd, 0, 0, SEEK_END); } diff --git a/src/backend/storage/file/Makefile b/src/backend/storage/file/Makefile index 5e1291b..660ac51 100644 --- a/src/backend/storage/file/Makefile +++ b/src/backend/storage/file/Makefile @@ -16,6 +16,7 @@ OBJS = \ buffile.o \ copydir.o \ fd.o \ + fileset.o \ reinit.o \ sharedfileset.o diff --git a/src/backend/storage/file/buffile.c b/src/backend/storage/file/buffile.c index a4be5fe..df3e099 100644 --- a/src/backend/storage/file/buffile.c +++ b/src/backend/storage/file/buffile.c @@ -39,7 +39,7 @@ * BufFile also supports temporary files that can be used by the single backend * when the corresponding files need to be survived across the transaction and * need to be opened and closed multiple times. Such files need to be created - * as a member of a SharedFileSet. + * as a member of a FileSet. *------------------------------------------------------------------------- */ @@ -77,8 +77,8 @@ struct BufFile bool dirty; /* does buffer need to be written? */ bool readOnly; /* has the file been set to read only? */ - SharedFileSet *fileset; /* space for segment files if shared */ - const char *name; /* name of this BufFile if shared */ + FileSet *fileset; /* space for fileset based segment files */ + const char *name; /* name of fileset based BufFile */ /* * resowner is the ResourceOwner to use for underlying temp files. (We @@ -104,7 +104,7 @@ static void extendBufFile(BufFile *file); static void BufFileLoadBuffer(BufFile *file); static void BufFileDumpBuffer(BufFile *file); static void BufFileFlush(BufFile *file); -static File MakeNewSharedSegment(BufFile *file, int segment); +static File MakeNewFileSetSegment(BufFile *file, int segment); /* * Create BufFile and perform the common initialization. @@ -160,7 +160,7 @@ extendBufFile(BufFile *file) if (file->fileset == NULL) pfile = OpenTemporaryFile(file->isInterXact); else - pfile = MakeNewSharedSegment(file, file->numFiles); + pfile = MakeNewFileSetSegment(file, file->numFiles); Assert(pfile >= 0); @@ -214,34 +214,34 @@ BufFileCreateTemp(bool interXact) * Build the name for a given segment of a given BufFile. */ static void -SharedSegmentName(char *name, const char *buffile_name, int segment) +FileSetSegmentName(char *name, const char *buffile_name, int segment) { snprintf(name, MAXPGPATH, "%s.%d", buffile_name, segment); } /* - * Create a new segment file backing a shared BufFile. + * Create a new segment file backing a fileset based BufFile. */ static File -MakeNewSharedSegment(BufFile *buffile, int segment) +MakeNewFileSetSegment(BufFile *buffile, int segment) { char name[MAXPGPATH]; File file; /* * It is possible that there are files left over from before a crash - * restart with the same name. In order for BufFileOpenShared() not to + * restart with the same name. In order for BufFileOpenFileSet() not to * get confused about how many segments there are, we'll unlink the next * segment number if it already exists. */ - SharedSegmentName(name, buffile->name, segment + 1); - SharedFileSetDelete(buffile->fileset, name, true); + FileSetSegmentName(name, buffile->name, segment + 1); + FileSetDelete(buffile->fileset, name, true); /* Create the new segment. */ - SharedSegmentName(name, buffile->name, segment); - file = SharedFileSetCreate(buffile->fileset, name); + FileSetSegmentName(name, buffile->name, segment); + file = FileSetCreate(buffile->fileset, name); - /* SharedFileSetCreate would've errored out */ + /* FileSetCreate would've errored out */ Assert(file > 0); return file; @@ -251,15 +251,15 @@ MakeNewSharedSegment(BufFile *buffile, int segment) * Create a BufFile that can be discovered and opened read-only by other * backends that are attached to the same SharedFileSet using the same name. * - * The naming scheme for shared BufFiles is left up to the calling code. The - * name will appear as part of one or more filenames on disk, and might + * The naming scheme for fileset based BufFiles is left up to the calling code. + * The name will appear as part of one or more filenames on disk, and might * provide clues to administrators about which subsystem is generating * temporary file data. Since each SharedFileSet object is backed by one or * more uniquely named temporary directory, names don't conflict with * unrelated SharedFileSet objects. */ BufFile * -BufFileCreateShared(SharedFileSet *fileset, const char *name) +BufFileCreateFileSet(FileSet *fileset, const char *name) { BufFile *file; @@ -267,7 +267,7 @@ BufFileCreateShared(SharedFileSet *fileset, const char *name) file->fileset = fileset; file->name = pstrdup(name); file->files = (File *) palloc(sizeof(File)); - file->files[0] = MakeNewSharedSegment(file, 0); + file->files[0] = MakeNewFileSetSegment(file, 0); file->readOnly = false; return file; @@ -275,13 +275,13 @@ BufFileCreateShared(SharedFileSet *fileset, const char *name) /* * Open a file that was previously created in another backend (or this one) - * with BufFileCreateShared in the same SharedFileSet using the same name. + * with BufFileCreateFileSet in the same FileSet using the same name. * The backend that created the file must have called BufFileClose() or - * BufFileExportShared() to make sure that it is ready to be opened by other + * BufFileExportFileSet() to make sure that it is ready to be opened by other * backends and render it read-only. */ BufFile * -BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) +BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) { BufFile *file; char segment_name[MAXPGPATH]; @@ -304,8 +304,8 @@ BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) files = repalloc(files, sizeof(File) * capacity); } /* Try to load a segment. */ - SharedSegmentName(segment_name, name, nfiles); - files[nfiles] = SharedFileSetOpen(fileset, segment_name, mode); + FileSetSegmentName(segment_name, name, nfiles); + files[nfiles] = FileSetOpen(fileset, segment_name, mode); if (files[nfiles] <= 0) break; ++nfiles; @@ -333,18 +333,18 @@ BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) } /* - * Delete a BufFile that was created by BufFileCreateShared in the given - * SharedFileSet using the given name. + * Delete a BufFile that was created by BufFileCreateFileSet in the given + * FileSet using the given name. * * It is not necessary to delete files explicitly with this function. It is * provided only as a way to delete files proactively, rather than waiting for - * the SharedFileSet to be cleaned up. + * the FileSet to be cleaned up. * * Only one backend should attempt to delete a given name, and should know * that it exists and has been exported or closed. */ void -BufFileDeleteShared(SharedFileSet *fileset, const char *name) +BufFileDeleteFileSet(FileSet *fileset, const char *name) { char segment_name[MAXPGPATH]; int segment = 0; @@ -357,8 +357,8 @@ BufFileDeleteShared(SharedFileSet *fileset, const char *name) */ for (;;) { - SharedSegmentName(segment_name, name, segment); - if (!SharedFileSetDelete(fileset, segment_name, true)) + FileSetSegmentName(segment_name, name, segment); + if (!FileSetDelete(fileset, segment_name, true)) break; found = true; ++segment; @@ -367,16 +367,16 @@ BufFileDeleteShared(SharedFileSet *fileset, const char *name) } if (!found) - elog(ERROR, "could not delete unknown shared BufFile \"%s\"", name); + elog(ERROR, "could not delete unknown BufFile \"%s\"", name); } /* - * BufFileExportShared --- flush and make read-only, in preparation for sharing. + * BufFileExportFileSet --- flush and make read-only, in preparation for sharing. */ void -BufFileExportShared(BufFile *file) +BufFileExportFileSet(BufFile *file) { - /* Must be a file belonging to a SharedFileSet. */ + /* Must be a file belonging to a FileSet. */ Assert(file->fileset != NULL); /* It's probably a bug if someone calls this twice. */ @@ -785,7 +785,7 @@ BufFileTellBlock(BufFile *file) #endif /* - * Return the current shared BufFile size. + * Return the current fileset based BufFile size. * * Counts any holes left behind by BufFileAppend as part of the size. * ereport()s on failure. @@ -811,8 +811,8 @@ BufFileSize(BufFile *file) } /* - * Append the contents of source file (managed within shared fileset) to - * end of target file (managed within same shared fileset). + * Append the contents of source file (managed within fileset) to + * end of target file (managed within same fileset). * * Note that operation subsumes ownership of underlying resources from * "source". Caller should never call BufFileClose against source having @@ -854,11 +854,11 @@ BufFileAppend(BufFile *target, BufFile *source) } /* - * Truncate a BufFile created by BufFileCreateShared up to the given fileno and - * the offset. + * Truncate a BufFile created by BufFileCreateFileSet up to the given fileno + * and the offset. */ void -BufFileTruncateShared(BufFile *file, int fileno, off_t offset) +BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset) { int numFiles = file->numFiles; int newFile = fileno; @@ -876,12 +876,12 @@ BufFileTruncateShared(BufFile *file, int fileno, off_t offset) { if ((i != fileno || offset == 0) && i != 0) { - SharedSegmentName(segment_name, file->name, i); + FileSetSegmentName(segment_name, file->name, i); FileClose(file->files[i]); - if (!SharedFileSetDelete(file->fileset, segment_name, true)) + if (!FileSetDelete(file->fileset, segment_name, true)) ereport(ERROR, (errcode_for_file_access(), - errmsg("could not delete shared fileset \"%s\": %m", + errmsg("could not delete fileset \"%s\": %m", segment_name))); numFiles--; newOffset = MAX_PHYSICAL_FILESIZE; diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c index b58b399..433e283 100644 --- a/src/backend/storage/file/fd.c +++ b/src/backend/storage/file/fd.c @@ -1921,7 +1921,7 @@ PathNameDeleteTemporaryFile(const char *path, bool error_on_failure) /* * Unlike FileClose's automatic file deletion code, we tolerate - * non-existence to support BufFileDeleteShared which doesn't know how + * non-existence to support BufFileDeleteFileSet which doesn't know how * many segments it has to delete until it runs out. */ if (stat_errno == ENOENT) diff --git a/src/backend/storage/file/fileset.c b/src/backend/storage/file/fileset.c new file mode 100644 index 0000000..91b06dd --- /dev/null +++ b/src/backend/storage/file/fileset.c @@ -0,0 +1,204 @@ +/*------------------------------------------------------------------------- + * + * fileset.c + * temporary file set management. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/backend/storage/file/fileset.c + * + * FileSets provide a temporary namespace (think directory) so that files can + * be discovered by name. + * + * FileSets can be used by backends when the temporary files need to be + * opened/closed multiple times and the underlying files need to survive across + * transactions. + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include <limits.h> + +#include "catalog/pg_tablespace.h" +#include "commands/tablespace.h" +#include "common/hashfn.h" +#include "miscadmin.h" +#include "storage/ipc.h" +#include "storage/fileset.h" +#include "utils/builtins.h" + +static void FileSetPath(char *path, FileSet *fileset, Oid tablespace); +static void FilePath(char *path, FileSet *fileset, const char *name); +static Oid ChooseTablespace(const FileSet *fileset, const char *name); + +/* + * Initialize a space for temporary files. This API can be used by shared + * fileset as well as if the temporary files are used only by single backend + * but the files need to be opened and closed multiple times and also the + * underlying files need to survive across transactions. + * + * The callers are expected to explicitly remove such files by using + * FileSetDelete/FileSetDeleteAll. + * + * Files will be distributed over the tablespaces configured in + * temp_tablespaces. + * + * Under the covers the set is one or more directories which will eventually + * be deleted. + */ +void +FileSetInit(FileSet *fileset) +{ + static uint32 counter = 0; + + fileset->creator_pid = MyProcPid; + fileset->number = counter; + counter = (counter + 1) % INT_MAX; + + /* Capture the tablespace OIDs so that all backends agree on them. */ + PrepareTempTablespaces(); + fileset->ntablespaces = + GetTempTablespaces(&fileset->tablespaces[0], + lengthof(fileset->tablespaces)); + if (fileset->ntablespaces == 0) + { + /* If the GUC is empty, use current database's default tablespace */ + fileset->tablespaces[0] = MyDatabaseTableSpace; + fileset->ntablespaces = 1; + } + else + { + int i; + + /* + * An entry of InvalidOid means use the default tablespace for the + * current database. Replace that now, to be sure that all users of + * the FileSet agree on what to do. + */ + for (i = 0; i < fileset->ntablespaces; i++) + { + if (fileset->tablespaces[i] == InvalidOid) + fileset->tablespaces[i] = MyDatabaseTableSpace; + } + } +} + +/* + * Create a new file in the given set. + */ +File +FileSetCreate(FileSet *fileset, const char *name) +{ + char path[MAXPGPATH]; + File file; + + FilePath(path, fileset, name); + file = PathNameCreateTemporaryFile(path, false); + + /* If we failed, see if we need to create the directory on demand. */ + if (file <= 0) + { + char tempdirpath[MAXPGPATH]; + char filesetpath[MAXPGPATH]; + Oid tablespace = ChooseTablespace(fileset, name); + + TempTablespacePath(tempdirpath, tablespace); + FileSetPath(filesetpath, fileset, tablespace); + PathNameCreateTemporaryDir(tempdirpath, filesetpath); + file = PathNameCreateTemporaryFile(path, true); + } + + return file; +} + +/* + * Open a file that was created with FileSetCreate() */ +File +FileSetOpen(FileSet *fileset, const char *name, int mode) +{ + char path[MAXPGPATH]; + File file; + + FilePath(path, fileset, name); + file = PathNameOpenTemporaryFile(path, mode); + + return file; +} + +/* + * Delete a file that was created with FileSetCreate(). + * Return true if the file existed, false if didn't. + */ +bool +FileSetDelete(FileSet *fileset, const char *name, + bool error_on_failure) +{ + char path[MAXPGPATH]; + + FilePath(path, fileset, name); + + return PathNameDeleteTemporaryFile(path, error_on_failure); +} + +/* + * Delete all files in the set. + */ +void +FileSetDeleteAll(FileSet *fileset) +{ + char dirpath[MAXPGPATH]; + int i; + + /* + * Delete the directory we created in each tablespace. Doesn't fail + * because we use this in error cleanup paths, but can generate LOG + * message on IO error. + */ + for (i = 0; i < fileset->ntablespaces; ++i) + { + FileSetPath(dirpath, fileset, fileset->tablespaces[i]); + PathNameDeleteTemporaryDir(dirpath); + } +} + +/* + * Build the path for the directory holding the files backing a FileSet in a + * given tablespace. + */ +static void +FileSetPath(char *path, FileSet *fileset, Oid tablespace) +{ + char tempdirpath[MAXPGPATH]; + + TempTablespacePath(tempdirpath, tablespace); + snprintf(path, MAXPGPATH, "%s/%s%lu.%u.fileset", + tempdirpath, PG_TEMP_FILE_PREFIX, + (unsigned long) fileset->creator_pid, fileset->number); +} + +/* + * Sorting hat to determine which tablespace a given temporary file belongs in. + */ +static Oid +ChooseTablespace(const FileSet *fileset, const char *name) +{ + uint32 hash = hash_any((const unsigned char *) name, strlen(name)); + + return fileset->tablespaces[hash % fileset->ntablespaces]; +} + +/* + * Compute the full path of a file in a FileSet. + */ +static void +FilePath(char *path, FileSet *fileset, const char *name) +{ + char dirpath[MAXPGPATH]; + + FileSetPath(dirpath, fileset, ChooseTablespace(fileset, name)); + snprintf(path, MAXPGPATH, "%s/%s", dirpath, name); +} diff --git a/src/backend/storage/file/sharedfileset.c b/src/backend/storage/file/sharedfileset.c index ed37c94..5bb3d44 100644 --- a/src/backend/storage/file/sharedfileset.c +++ b/src/backend/storage/file/sharedfileset.c @@ -13,10 +13,6 @@ * files can be discovered by name, and a shared ownership semantics so that * shared files survive until the last user detaches. * - * SharedFileSets can be used by backends when the temporary files need to be - * opened/closed multiple times and the underlying files need to survive across - * transactions. - * *------------------------------------------------------------------------- */ @@ -33,13 +29,7 @@ #include "storage/sharedfileset.h" #include "utils/builtins.h" -static List *filesetlist = NIL; - static void SharedFileSetOnDetach(dsm_segment *segment, Datum datum); -static void SharedFileSetDeleteOnProcExit(int status, Datum arg); -static void SharedFileSetPath(char *path, SharedFileSet *fileset, Oid tablespace); -static void SharedFilePath(char *path, SharedFileSet *fileset, const char *name); -static Oid ChooseTablespace(const SharedFileSet *fileset, const char *name); /* * Initialize a space for temporary files that can be opened by other backends. @@ -47,77 +37,22 @@ static Oid ChooseTablespace(const SharedFileSet *fileset, const char *name); * SharedFileSet with 'seg'. Any contained files will be deleted when the * last backend detaches. * - * We can also use this interface if the temporary files are used only by - * single backend but the files need to be opened and closed multiple times - * and also the underlying files need to survive across transactions. For - * such cases, dsm segment 'seg' should be passed as NULL. Callers are - * expected to explicitly remove such files by using SharedFileSetDelete/ - * SharedFileSetDeleteAll or we remove such files on proc exit. - * - * Files will be distributed over the tablespaces configured in - * temp_tablespaces. - * * Under the covers the set is one or more directories which will eventually * be deleted. */ void SharedFileSetInit(SharedFileSet *fileset, dsm_segment *seg) { - static uint32 counter = 0; - + /* Initialize the shared fileset specific members. */ SpinLockInit(&fileset->mutex); fileset->refcnt = 1; - fileset->creator_pid = MyProcPid; - fileset->number = counter; - counter = (counter + 1) % INT_MAX; - - /* Capture the tablespace OIDs so that all backends agree on them. */ - PrepareTempTablespaces(); - fileset->ntablespaces = - GetTempTablespaces(&fileset->tablespaces[0], - lengthof(fileset->tablespaces)); - if (fileset->ntablespaces == 0) - { - /* If the GUC is empty, use current database's default tablespace */ - fileset->tablespaces[0] = MyDatabaseTableSpace; - fileset->ntablespaces = 1; - } - else - { - int i; - /* - * An entry of InvalidOid means use the default tablespace for the - * current database. Replace that now, to be sure that all users of - * the SharedFileSet agree on what to do. - */ - for (i = 0; i < fileset->ntablespaces; i++) - { - if (fileset->tablespaces[i] == InvalidOid) - fileset->tablespaces[i] = MyDatabaseTableSpace; - } - } + /* Initialize the fileset. */ + FileSetInit(&fileset->fs); /* Register our cleanup callback. */ if (seg) on_dsm_detach(seg, SharedFileSetOnDetach, PointerGetDatum(fileset)); - else - { - static bool registered_cleanup = false; - - if (!registered_cleanup) - { - /* - * We must not have registered any fileset before registering the - * fileset clean up. - */ - Assert(filesetlist == NIL); - on_proc_exit(SharedFileSetDeleteOnProcExit, 0); - registered_cleanup = true; - } - - filesetlist = lcons((void *) fileset, filesetlist); - } } /* @@ -148,86 +83,12 @@ SharedFileSetAttach(SharedFileSet *fileset, dsm_segment *seg) } /* - * Create a new file in the given set. - */ -File -SharedFileSetCreate(SharedFileSet *fileset, const char *name) -{ - char path[MAXPGPATH]; - File file; - - SharedFilePath(path, fileset, name); - file = PathNameCreateTemporaryFile(path, false); - - /* If we failed, see if we need to create the directory on demand. */ - if (file <= 0) - { - char tempdirpath[MAXPGPATH]; - char filesetpath[MAXPGPATH]; - Oid tablespace = ChooseTablespace(fileset, name); - - TempTablespacePath(tempdirpath, tablespace); - SharedFileSetPath(filesetpath, fileset, tablespace); - PathNameCreateTemporaryDir(tempdirpath, filesetpath); - file = PathNameCreateTemporaryFile(path, true); - } - - return file; -} - -/* - * Open a file that was created with SharedFileSetCreate(), possibly in - * another backend. - */ -File -SharedFileSetOpen(SharedFileSet *fileset, const char *name, int mode) -{ - char path[MAXPGPATH]; - File file; - - SharedFilePath(path, fileset, name); - file = PathNameOpenTemporaryFile(path, mode); - - return file; -} - -/* - * Delete a file that was created with SharedFileSetCreate(). - * Return true if the file existed, false if didn't. - */ -bool -SharedFileSetDelete(SharedFileSet *fileset, const char *name, - bool error_on_failure) -{ - char path[MAXPGPATH]; - - SharedFilePath(path, fileset, name); - - return PathNameDeleteTemporaryFile(path, error_on_failure); -} - -/* * Delete all files in the set. */ void SharedFileSetDeleteAll(SharedFileSet *fileset) { - char dirpath[MAXPGPATH]; - int i; - - /* - * Delete the directory we created in each tablespace. Doesn't fail - * because we use this in error cleanup paths, but can generate LOG - * message on IO error. - */ - for (i = 0; i < fileset->ntablespaces; ++i) - { - SharedFileSetPath(dirpath, fileset, fileset->tablespaces[i]); - PathNameDeleteTemporaryDir(dirpath); - } - - /* Unregister the shared fileset */ - SharedFileSetUnregister(fileset); + return FileSetDeleteAll(&fileset->fs); } /* @@ -255,100 +116,5 @@ SharedFileSetOnDetach(dsm_segment *segment, Datum datum) * this function so we can safely access its data. */ if (unlink_all) - SharedFileSetDeleteAll(fileset); -} - -/* - * Callback function that will be invoked on the process exit. This will - * process the list of all the registered sharedfilesets and delete the - * underlying files. - */ -static void -SharedFileSetDeleteOnProcExit(int status, Datum arg) -{ - /* - * Remove all the pending shared fileset entries. We don't use foreach() - * here because SharedFileSetDeleteAll will remove the current element in - * filesetlist. Though we have used foreach_delete_current() to remove the - * element from filesetlist it could only fix up the state of one of the - * loops, see SharedFileSetUnregister. - */ - while (list_length(filesetlist) > 0) - { - SharedFileSet *fileset = (SharedFileSet *) linitial(filesetlist); - - SharedFileSetDeleteAll(fileset); - } - - filesetlist = NIL; -} - -/* - * Unregister the shared fileset entry registered for cleanup on proc exit. - */ -void -SharedFileSetUnregister(SharedFileSet *input_fileset) -{ - ListCell *l; - - /* - * If the caller is following the dsm based cleanup then we don't maintain - * the filesetlist so return. - */ - if (filesetlist == NIL) - return; - - foreach(l, filesetlist) - { - SharedFileSet *fileset = (SharedFileSet *) lfirst(l); - - /* Remove the entry from the list */ - if (input_fileset == fileset) - { - filesetlist = foreach_delete_current(filesetlist, l); - return; - } - } - - /* Should have found a match */ - Assert(false); -} - -/* - * Build the path for the directory holding the files backing a SharedFileSet - * in a given tablespace. - */ -static void -SharedFileSetPath(char *path, SharedFileSet *fileset, Oid tablespace) -{ - char tempdirpath[MAXPGPATH]; - - TempTablespacePath(tempdirpath, tablespace); - snprintf(path, MAXPGPATH, "%s/%s%lu.%u.sharedfileset", - tempdirpath, PG_TEMP_FILE_PREFIX, - (unsigned long) fileset->creator_pid, fileset->number); -} - -/* - * Sorting hat to determine which tablespace a given shared temporary file - * belongs in. - */ -static Oid -ChooseTablespace(const SharedFileSet *fileset, const char *name) -{ - uint32 hash = hash_any((const unsigned char *) name, strlen(name)); - - return fileset->tablespaces[hash % fileset->ntablespaces]; -} - -/* - * Compute the full path of a file in a SharedFileSet. - */ -static void -SharedFilePath(char *path, SharedFileSet *fileset, const char *name) -{ - char dirpath[MAXPGPATH]; - - SharedFileSetPath(dirpath, fileset, ChooseTablespace(fileset, name)); - snprintf(path, MAXPGPATH, "%s/%s", dirpath, name); + FileSetDeleteAll(&fileset->fs); } diff --git a/src/backend/utils/sort/logtape.c b/src/backend/utils/sort/logtape.c index cafc087..f7994d7 100644 --- a/src/backend/utils/sort/logtape.c +++ b/src/backend/utils/sort/logtape.c @@ -564,7 +564,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, lt = &lts->tapes[i]; pg_itoa(i, filename); - file = BufFileOpenShared(fileset, filename, O_RDONLY); + file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY); filesize = BufFileSize(file); /* @@ -610,7 +610,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, * offset). * * The only thing that currently prevents writing to the leader tape from - * working is the fact that BufFiles opened using BufFileOpenShared() are + * working is the fact that BufFiles opened using BufFileOpenFileSet() are * read-only by definition, but that could be changed if it seemed * worthwhile. For now, writing to the leader tape will raise a "Bad file * descriptor" error, so tuplesort must avoid writing to the leader tape @@ -722,7 +722,7 @@ LogicalTapeSetCreate(int ntapes, bool preallocate, TapeShare *shared, char filename[MAXPGPATH]; pg_itoa(worker, filename); - lts->pfile = BufFileCreateShared(fileset, filename); + lts->pfile = BufFileCreateFileSet(&fileset->fs, filename); } else lts->pfile = BufFileCreateTemp(false); @@ -1096,7 +1096,7 @@ LogicalTapeFreeze(LogicalTapeSet *lts, int tapenum, TapeShare *share) /* Handle extra steps when caller is to share its tapeset */ if (share) { - BufFileExportShared(lts->pfile); + BufFileExportFileSet(lts->pfile); share->firstblocknumber = lt->firstBlockNumber; } } diff --git a/src/backend/utils/sort/sharedtuplestore.c b/src/backend/utils/sort/sharedtuplestore.c index 57e35db..72acd54 100644 --- a/src/backend/utils/sort/sharedtuplestore.c +++ b/src/backend/utils/sort/sharedtuplestore.c @@ -310,7 +310,8 @@ sts_puttuple(SharedTuplestoreAccessor *accessor, void *meta_data, /* Create one. Only this backend will write into it. */ sts_filename(name, accessor, accessor->participant); - accessor->write_file = BufFileCreateShared(accessor->fileset, name); + accessor->write_file = + BufFileCreateFileSet(&accessor->fileset->fs, name); /* Set up the shared state for this backend's file. */ participant = &accessor->sts->participants[accessor->participant]; @@ -559,7 +560,7 @@ sts_parallel_scan_next(SharedTuplestoreAccessor *accessor, void *meta_data) sts_filename(name, accessor, accessor->read_participant); accessor->read_file = - BufFileOpenShared(accessor->fileset, name, O_RDONLY); + BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY); } /* Seek and load the chunk header. */ diff --git a/src/include/replication/worker_internal.h b/src/include/replication/worker_internal.h index 41c7487..a6c9d4e 100644 --- a/src/include/replication/worker_internal.h +++ b/src/include/replication/worker_internal.h @@ -79,6 +79,7 @@ extern void logicalrep_worker_launch(Oid dbid, Oid subid, const char *subname, extern void logicalrep_worker_stop(Oid subid, Oid relid); extern void logicalrep_worker_wakeup(Oid subid, Oid relid); extern void logicalrep_worker_wakeup_ptr(LogicalRepWorker *worker); +extern void logicalrep_worker_cleanupfileset(void); extern int logicalrep_sync_worker_count(Oid subid); diff --git a/src/include/storage/buffile.h b/src/include/storage/buffile.h index 566523d..032a823 100644 --- a/src/include/storage/buffile.h +++ b/src/include/storage/buffile.h @@ -26,7 +26,7 @@ #ifndef BUFFILE_H #define BUFFILE_H -#include "storage/sharedfileset.h" +#include "storage/fileset.h" /* BufFile is an opaque type whose details are not known outside buffile.c. */ @@ -46,11 +46,11 @@ extern int BufFileSeekBlock(BufFile *file, long blknum); extern int64 BufFileSize(BufFile *file); extern long BufFileAppend(BufFile *target, BufFile *source); -extern BufFile *BufFileCreateShared(SharedFileSet *fileset, const char *name); -extern void BufFileExportShared(BufFile *file); -extern BufFile *BufFileOpenShared(SharedFileSet *fileset, const char *name, +extern BufFile *BufFileCreateFileSet(FileSet *fileset, const char *name); +extern void BufFileExportFileSet(BufFile *file); +extern BufFile *BufFileOpenFileSet(FileSet *fileset, const char *name, int mode); -extern void BufFileDeleteShared(SharedFileSet *fileset, const char *name); -extern void BufFileTruncateShared(BufFile *file, int fileno, off_t offset); +extern void BufFileDeleteFileSet(FileSet *fileset, const char *name); +extern void BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset); #endif /* BUFFILE_H */ diff --git a/src/include/storage/fileset.h b/src/include/storage/fileset.h new file mode 100644 index 0000000..8795fd1 --- /dev/null +++ b/src/include/storage/fileset.h @@ -0,0 +1,40 @@ +/*------------------------------------------------------------------------- + * + * fileset.h + * temporary file management. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/storage/fileset.h + * + *------------------------------------------------------------------------- + */ + +#ifndef FILESET_H +#define FILESET_H + +#include "storage/fd.h" + +/* + * A set of temporary files. + */ +typedef struct FileSet +{ + pid_t creator_pid; /* PID of the creating process */ + uint32 number; /* per-PID identifier */ + int ntablespaces; /* number of tablespaces to use */ + Oid tablespaces[8]; /* OIDs of tablespaces to use. Assumes that + * it's rare that there more than temp + * tablespaces. */ +} FileSet; + +extern void FileSetInit(FileSet *fileset); +extern File FileSetCreate(FileSet *fileset, const char *name); +extern File FileSetOpen(FileSet *fileset, const char *name, + int mode); +extern bool FileSetDelete(FileSet *fileset, const char *name, + bool error_on_failure); +extern void FileSetDeleteAll(FileSet *fileset); + +#endif diff --git a/src/include/storage/sharedfileset.h b/src/include/storage/sharedfileset.h index 09ba121..59becfb 100644 --- a/src/include/storage/sharedfileset.h +++ b/src/include/storage/sharedfileset.h @@ -17,6 +17,7 @@ #include "storage/dsm.h" #include "storage/fd.h" +#include "storage/fileset.h" #include "storage/spin.h" /* @@ -24,24 +25,13 @@ */ typedef struct SharedFileSet { - pid_t creator_pid; /* PID of the creating process */ - uint32 number; /* per-PID identifier */ + FileSet fs; slock_t mutex; /* mutex protecting the reference count */ int refcnt; /* number of attached backends */ - int ntablespaces; /* number of tablespaces to use */ - Oid tablespaces[8]; /* OIDs of tablespaces to use. Assumes that - * it's rare that there more than temp - * tablespaces. */ } SharedFileSet; extern void SharedFileSetInit(SharedFileSet *fileset, dsm_segment *seg); extern void SharedFileSetAttach(SharedFileSet *fileset, dsm_segment *seg); -extern File SharedFileSetCreate(SharedFileSet *fileset, const char *name); -extern File SharedFileSetOpen(SharedFileSet *fileset, const char *name, - int mode); -extern bool SharedFileSetDelete(SharedFileSet *fileset, const char *name, - bool error_on_failure); extern void SharedFileSetDeleteAll(SharedFileSet *fileset); -extern void SharedFileSetUnregister(SharedFileSet *input_fileset); #endif -- 1.8.3.1
v3-0002-Better-usage-of-fileset-in-apply-worker.patch (text/x-patch, 17.8K) download From e7494c21da24d856e113a19dcba8b3c9893055fb Mon Sep 17 00:00:00 2001 From: Dilip Kumar <dilipkumar@localhost.localdomain> Date: Tue, 24 Aug 2021 14:44:59 +0530 Subject: [PATCH v3 2/2] Better usage of fileset in apply worker Instead of using a separate fileset for each xid, use just one fileset for whole lifetime of the worker. So for each xid, create buffilea under the same fileset and remove the files whenever we are done with those files. For subxact file we only need to create once we get the first subtransaction and for detecting that we have also extended the buffile open and buffile delete interfaces to allow the missing files. --- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/worker.c | 234 +++++------------------------ src/backend/storage/file/buffile.c | 23 ++- src/backend/utils/sort/logtape.c | 2 +- src/backend/utils/sort/sharedtuplestore.c | 3 +- src/include/storage/buffile.h | 5 +- 6 files changed, 64 insertions(+), 205 deletions(-) diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 8b1772d..644a9c2 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -648,7 +648,7 @@ logicalrep_worker_onexit(int code, Datum arg) logicalrep_worker_detach(); - /* Cleanup filesets used for streaming transactions. */ + /* Cleanup fileset used for streaming transactions. */ logicalrep_worker_cleanupfileset(); ApplyLauncherWakeup(); diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index 07a2c90..77aaba1 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -221,20 +221,6 @@ typedef struct ApplyExecutionData PartitionTupleRouting *proute; /* partition routing info */ } ApplyExecutionData; -/* - * Stream xid hash entry. Whenever we see a new xid we create this entry in the - * xidhash and along with it create the streaming file and store the fileset handle. - * The subxact file is created iff there is any subxact info under this xid. This - * entry is used on the subsequent streams for the xid to get the corresponding - * fileset handles, so storing them in hash makes the search faster. - */ -typedef struct StreamXidHash -{ - TransactionId xid; /* xid is the hash key and must be first */ - FileSet *stream_fileset; /* file set for stream data */ - FileSet *subxact_fileset; /* file set for subxact info */ -} StreamXidHash; - static MemoryContext ApplyMessageContext = NULL; MemoryContext ApplyContext = NULL; @@ -255,10 +241,11 @@ static bool in_streamed_transaction = false; static TransactionId stream_xid = InvalidTransactionId; /* - * Hash table for storing the streaming xid information along with filesets - * for streaming and subxact files. + * Fileset for storing the changes and subxact information for the streaming + * transaction. We will use only one fileset and for each xid a separate + * changes and subxact files will be created under the same fileset. */ -static HTAB *xidhash = NULL; +static FileSet *xidfileset = NULL; /* BufFile handle of the current streaming file */ static BufFile *stream_fd = NULL; @@ -1129,7 +1116,6 @@ static void apply_handle_stream_start(StringInfo s) { bool first_segment; - HASHCTL hash_ctl; if (in_streamed_transaction) ereport(ERROR, @@ -1157,17 +1143,21 @@ apply_handle_stream_start(StringInfo s) errmsg_internal("invalid transaction ID in streamed replication transaction"))); /* - * Initialize the xidhash table if we haven't yet. This will be used for - * the entire duration of the apply worker so create it in permanent - * context. + * Initialize the xidfileset if we haven't yet. This will be used for the + * entire duration of the apply worker so create it in permanent context. */ - if (xidhash == NULL) + if (xidfileset == NULL) { - hash_ctl.keysize = sizeof(TransactionId); - hash_ctl.entrysize = sizeof(StreamXidHash); - hash_ctl.hcxt = ApplyContext; - xidhash = hash_create("StreamXidHash", 1024, &hash_ctl, - HASH_ELEM | HASH_BLOBS | HASH_CONTEXT); + MemoryContext oldctx; + + /* + * We need to keep the fileset for the worker lifetime so need to + * allocate it in a persistent context. + */ + oldctx = MemoryContextSwitchTo(ApplyContext); + xidfileset = palloc(sizeof(FileSet)); + FileSetInit(xidfileset); + MemoryContextSwitchTo(oldctx); } /* open the spool file for this transaction */ @@ -1258,7 +1248,6 @@ apply_handle_stream_abort(StringInfo s) BufFile *fd; bool found = false; char path[MAXPGPATH]; - StreamXidHash *ent; subidx = -1; begin_replication_step(); @@ -1287,19 +1276,9 @@ apply_handle_stream_abort(StringInfo s) return; } - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* open the changes file */ changes_filename(path, MyLogicalRepWorker->subid, xid); - fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(xidfileset, path, O_RDWR, false); /* OK, truncate the file at the right offset */ BufFileTruncateFileSet(fd, subxact_data.subxacts[subidx].fileno, @@ -1327,7 +1306,6 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) int nchanges; char path[MAXPGPATH]; char *buffer = NULL; - StreamXidHash *ent; MemoryContext oldcxt; BufFile *fd; @@ -1345,17 +1323,7 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) changes_filename(path, MyLogicalRepWorker->subid, xid); elog(DEBUG1, "replaying changes from file \"%s\"", path); - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - - fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(xidfileset, path, O_RDONLY, false); buffer = palloc(BLCKSZ); initStringInfo(&s2); @@ -2509,30 +2477,13 @@ UpdateWorkerStats(XLogRecPtr last_lsn, TimestampTz send_time, bool reply) } /* - * Cleanup filesets. + * Cleanup fileset. */ void logicalrep_worker_cleanupfileset() { - HASH_SEQ_STATUS status; - StreamXidHash *hentry; - - /* - * Scan the xidhash table if created and from each entry delete stream - * fileset and the subxact fileset. - */ - if (xidhash) - { - hash_seq_init(&status, xidhash); - while ((hentry = (StreamXidHash *) hash_seq_search(&status)) != NULL) - { - FileSetDeleteAll(hentry->stream_fileset); - - /* Delete the subxact fileset only if it is created */ - if (hentry->subxact_fileset) - FileSetDeleteAll(hentry->subxact_fileset); - } - } + if (xidfileset != NULL) + FileSetDeleteAll(xidfileset); } /* @@ -2984,18 +2935,11 @@ subxact_info_write(Oid subid, TransactionId xid) { char path[MAXPGPATH]; Size len; - StreamXidHash *ent; BufFile *fd; Assert(TransactionIdIsValid(xid)); - /* Find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - /* By this time we must have created the transaction entry */ - Assert(ent); + subxact_filename(path, subid, xid); /* * If there is no subtransaction then nothing to do, but if already have @@ -3003,39 +2947,18 @@ subxact_info_write(Oid subid, TransactionId xid) */ if (subxact_data.nsubxacts == 0) { - if (ent->subxact_fileset) - { - cleanup_subxact_info(); - FileSetDeleteAll(ent->subxact_fileset); - pfree(ent->subxact_fileset); - ent->subxact_fileset = NULL; - } + cleanup_subxact_info(); + BufFileDeleteFileSet(xidfileset, path, true); + return; } subxact_filename(path, subid, xid); - /* - * Create the subxact file if it not already created, otherwise open the - * existing file. - */ - if (ent->subxact_fileset == NULL) - { - MemoryContext oldctx; - - /* - * We need to maintain fileset across multiple stream start/stop calls. - * So, need to allocate it in a persistent context. - */ - oldctx = MemoryContextSwitchTo(ApplyContext); - ent->subxact_fileset = palloc(sizeof(FileSet)); - FileSetInit(ent->subxact_fileset); - MemoryContextSwitchTo(oldctx); - - fd = BufFileCreateFileSet(ent->subxact_fileset, path); - } - else - fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDWR); + /* Try to open the subxact file, if it doesn't exist then create it */ + fd = BufFileOpenFileSet(xidfileset, path, O_RDWR, true); + if (fd == NULL) + fd = BufFileCreateFileSet(xidfileset, path); len = sizeof(SubXactInfo) * subxact_data.nsubxacts; @@ -3062,34 +2985,17 @@ subxact_info_read(Oid subid, TransactionId xid) char path[MAXPGPATH]; Size len; BufFile *fd; - StreamXidHash *ent; MemoryContext oldctx; Assert(!subxact_data.subxacts); Assert(subxact_data.nsubxacts == 0); Assert(subxact_data.nsubxacts_max == 0); - /* Find the stream xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - - /* - * If subxact_fileset is not valid that mean we don't have any subxact - * info - */ - if (ent->subxact_fileset == NULL) - return; - subxact_filename(path, subid, xid); - fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(xidfileset, path, O_RDONLY, true); + if (fd == NULL) + return; /* read number of subxact items */ if (BufFileRead(fd, &subxact_data.nsubxacts, @@ -3231,36 +3137,13 @@ static void stream_cleanup_files(Oid subid, TransactionId xid) { char path[MAXPGPATH]; - StreamXidHash *ent; - - /* Find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); /* Delete the change file and release the stream fileset memory */ changes_filename(path, subid, xid); - FileSetDeleteAll(ent->stream_fileset); - pfree(ent->stream_fileset); - ent->stream_fileset = NULL; - - /* Delete the subxact file and release the memory, if it exist */ - if (ent->subxact_fileset) - { - subxact_filename(path, subid, xid); - FileSetDeleteAll(ent->subxact_fileset); - pfree(ent->subxact_fileset); - ent->subxact_fileset = NULL; - } + BufFileDeleteFileSet(xidfileset, path, false); - /* Remove the xid entry from the stream xid hash */ - hash_search(xidhash, (void *) &xid, HASH_REMOVE, NULL); + subxact_filename(path, subid, xid); + BufFileDeleteFileSet(xidfileset, path, true); } /* @@ -3270,8 +3153,8 @@ stream_cleanup_files(Oid subid, TransactionId xid) * * Open a file for streamed changes from a toplevel transaction identified * by stream_xid (global variable). If it's the first chunk of streamed - * changes for this transaction, initialize the fileset and create the buffile, - * otherwise open the previously created file. + * changes for this transaction, create the buffile, otherwise open the + * previously created file. * * This can only be called at the beginning of a "streaming" block, i.e. * between stream_start/stream_stop messages from the upstream. @@ -3280,20 +3163,13 @@ static void stream_open_file(Oid subid, TransactionId xid, bool first_segment) { char path[MAXPGPATH]; - bool found; MemoryContext oldcxt; - StreamXidHash *ent; Assert(in_streamed_transaction); Assert(OidIsValid(subid)); Assert(TransactionIdIsValid(xid)); Assert(stream_fd == NULL); - /* create or find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_ENTER, - &found); changes_filename(path, subid, xid); elog(DEBUG1, "opening file \"%s\" for streamed changes", path); @@ -3310,44 +3186,14 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) * writing, in append mode. */ if (first_segment) - { - MemoryContext savectx; - FileSet *fileset; - - if (found) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); - - /* - * We need to maintain fileset across multiple stream start/stop calls. - * So, need to allocate it in a persistent context. - */ - savectx = MemoryContextSwitchTo(ApplyContext); - fileset = palloc(sizeof(FileSet)); - - FileSetInit(fileset); - MemoryContextSwitchTo(savectx); - - stream_fd = BufFileCreateFileSet(fileset, path); - - /* Remember the fileset for the next stream of the same transaction */ - ent->xid = xid; - ent->stream_fileset = fileset; - ent->subxact_fileset = NULL; - } + stream_fd = BufFileCreateFileSet(xidfileset, path); else { - if (!found) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); - /* * Open the file and seek to the end of the file because we always * append the changes file. */ - stream_fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); + stream_fd = BufFileOpenFileSet(xidfileset, path, O_RDWR, false); BufFileSeek(stream_fd, 0, 0, SEEK_END); } diff --git a/src/backend/storage/file/buffile.c b/src/backend/storage/file/buffile.c index df3e099..1cf9733 100644 --- a/src/backend/storage/file/buffile.c +++ b/src/backend/storage/file/buffile.c @@ -278,10 +278,12 @@ BufFileCreateFileSet(FileSet *fileset, const char *name) * with BufFileCreateFileSet in the same FileSet using the same name. * The backend that created the file must have called BufFileClose() or * BufFileExportFileSet() to make sure that it is ready to be opened by other - * backends and render it read-only. + * backends and render it read-only. If missing_ok is true then it will return + * NULL if file doesn't exist otherwise error. */ BufFile * -BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) +BufFileOpenFileSet(FileSet *fileset, const char *name, int mode, + bool missing_ok) { BufFile *file; char segment_name[MAXPGPATH]; @@ -318,10 +320,18 @@ BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) * name. */ if (nfiles == 0) + { + /* free the memory */ + pfree(files); + + if (missing_ok) + return NULL; + ereport(ERROR, (errcode_for_file_access(), errmsg("could not open temporary file \"%s\" from BufFile \"%s\": %m", segment_name, name))); + } file = makeBufFileCommon(nfiles); file->files = files; @@ -341,10 +351,11 @@ BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) * the FileSet to be cleaned up. * * Only one backend should attempt to delete a given name, and should know - * that it exists and has been exported or closed. + * that it exists and has been exported or closed otherwise missing_ok should + * be passed true. */ void -BufFileDeleteFileSet(FileSet *fileset, const char *name) +BufFileDeleteFileSet(FileSet *fileset, const char *name, bool missing_ok) { char segment_name[MAXPGPATH]; int segment = 0; @@ -358,7 +369,7 @@ BufFileDeleteFileSet(FileSet *fileset, const char *name) for (;;) { FileSetSegmentName(segment_name, name, segment); - if (!FileSetDelete(fileset, segment_name, true)) + if (!FileSetDelete(fileset, segment_name, !missing_ok)) break; found = true; ++segment; @@ -366,7 +377,7 @@ BufFileDeleteFileSet(FileSet *fileset, const char *name) CHECK_FOR_INTERRUPTS(); } - if (!found) + if (!found && !missing_ok) elog(ERROR, "could not delete unknown BufFile \"%s\"", name); } diff --git a/src/backend/utils/sort/logtape.c b/src/backend/utils/sort/logtape.c index f7994d7..debf12e1 100644 --- a/src/backend/utils/sort/logtape.c +++ b/src/backend/utils/sort/logtape.c @@ -564,7 +564,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, lt = &lts->tapes[i]; pg_itoa(i, filename); - file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY); + file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY, false); filesize = BufFileSize(file); /* diff --git a/src/backend/utils/sort/sharedtuplestore.c b/src/backend/utils/sort/sharedtuplestore.c index 72acd54..8c5135c 100644 --- a/src/backend/utils/sort/sharedtuplestore.c +++ b/src/backend/utils/sort/sharedtuplestore.c @@ -560,7 +560,8 @@ sts_parallel_scan_next(SharedTuplestoreAccessor *accessor, void *meta_data) sts_filename(name, accessor, accessor->read_participant); accessor->read_file = - BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY); + BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY, + false); } /* Seek and load the chunk header. */ diff --git a/src/include/storage/buffile.h b/src/include/storage/buffile.h index 032a823..5e9df44 100644 --- a/src/include/storage/buffile.h +++ b/src/include/storage/buffile.h @@ -49,8 +49,9 @@ extern long BufFileAppend(BufFile *target, BufFile *source); extern BufFile *BufFileCreateFileSet(FileSet *fileset, const char *name); extern void BufFileExportFileSet(BufFile *file); extern BufFile *BufFileOpenFileSet(FileSet *fileset, const char *name, - int mode); -extern void BufFileDeleteFileSet(FileSet *fileset, const char *name); + int mode, bool missing_ok); +extern void BufFileDeleteFileSet(FileSet *fileset, const char *name, + bool missing_ok); extern void BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset); #endif /* BUFFILE_H */ -- 1.8.3.1
^ permalink raw reply [nested|flat] 26+ messages in thread

* RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
@ 2021-08-25 01:50           ` houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  1 sibling, 0 replies; 26+ messages in thread

From: houzj.fnst@fujitsu.com @ 2021-08-25 01:50 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>; Amit Kapila <amit.kapila16@gmail.com>

On Tuesday, August 24, 2021 6:25 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
> On Tue, Aug 24, 2021 at 12:26 PM Amit Kapila <amit.kapila16@gmail.com> wrote:
> 
> > > I was also thinking about the same, does it make sense to name it
> > > just ""%s/%s%lu.%u.fileset"?
> 
> Done
> 
> > I think it is reasonable to use .fileset as proposed by you.
> >
> > Few other comments:
> Done

After applying the patch, I tested the impacted features
(parallel hashjoin/btree build) with different settings
(log_temp_files/maintenance_work_mem/parallel_leader_participation/workers)
, and the patch works well.

One thing I noticed is that when enable log_temp_files, the pathname in log
changed from "xxx.sharedfileset" to "xxx.fileset", and I also noticed some
blogs[1] reference the old path name. Although, I think it doesn't matter, just
share the information here in case someone has different opinions.


Some minor thing I noticed in the patch:

1)
it seems we can add "FileSet" to typedefs.list

2)
The commit message in 0002 used "shared fileset" which should be "fileset",
---
Instead of using a separate shared fileset for each xid, use one shared
fileset for whole lifetime of the worker...
---

[1] https://blog.dbi-services.com/about-temp_tablespaces-in-postgresql/

Best regards,
Hou zj



^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
@ 2021-08-25 12:19           ` Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 01:46             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Masahiko Sawada <sawada.mshk@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  1 sibling, 2 replies; 26+ messages in thread

From: Amit Kapila @ 2021-08-25 12:19 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Tue, Aug 24, 2021 at 3:55 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>
> On Tue, Aug 24, 2021 at 12:26 PM Amit Kapila <amit.kapila16@gmail.com> wrote:
>

The first patch looks good to me. I have made minor changes to the
attached patch. The changes include: fixing compilation warning, made
some comment changes, ran pgindent, and few other cosmetic changes. If
you are fine with the attached, then kindly rebase the second patch
atop it.

-- 
With Regards,
Amit Kapila.

Attachments:

v5-0001-Refactor-sharedfileset.c-to-separate-out-fileset-.patch (application/octet-stream, 42.1K) download From bbf58ee17aab7057b92d4d1da69a5e9503b0f85e Mon Sep 17 00:00:00 2001 From: Amit Kapila <akapila@postgresql.org> Date: Wed, 25 Aug 2021 15:00:19 +0530 Subject: [PATCH v5] Refactor sharedfileset.c to separate out fileset implementation. Move fileset related implementation out of sharedfileset.c to allow its usage by backends that don't want to share filesets among different processes. After this split, fileset infrastructure is used by both sharedfileset.c and worker.c for the named temporary files that survive across transactions. Author: Dilip Kumar, based on suggestion by Andres Freund Reviewed-by: Hou Zhijie, Masahiko Sawada, Amit Kapila Discussion: https://postgr.es/m/E1mCC6U-0004Ik-Fs@gemulon.postgresql.org --- src/backend/replication/logical/launcher.c | 3 + src/backend/replication/logical/worker.c | 82 ++++++---- src/backend/storage/file/Makefile | 1 + src/backend/storage/file/buffile.c | 84 +++++----- src/backend/storage/file/fd.c | 2 +- src/backend/storage/file/fileset.c | 205 ++++++++++++++++++++++++ src/backend/storage/file/sharedfileset.c | 244 +---------------------------- src/backend/utils/sort/logtape.c | 8 +- src/backend/utils/sort/sharedtuplestore.c | 5 +- src/include/replication/worker_internal.h | 1 + src/include/storage/buffile.h | 14 +- src/include/storage/fileset.h | 40 +++++ src/include/storage/sharedfileset.h | 14 +- src/tools/pgindent/typedefs.list | 1 + 14 files changed, 368 insertions(+), 336 deletions(-) create mode 100644 src/backend/storage/file/fileset.c create mode 100644 src/include/storage/fileset.h diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index e3b11da..8b1772d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -648,6 +648,9 @@ logicalrep_worker_onexit(int code, Datum arg) logicalrep_worker_detach(); + /* Cleanup filesets used for streaming transactions. */ + logicalrep_worker_cleanupfileset(); + ApplyLauncherWakeup(); } diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index 38b493e..6adc6ddd 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -39,13 +39,13 @@ * BufFile infrastructure supports temporary files that exceed the OS file size * limit, (b) provides a way for automatic clean up on the error and (c) provides * a way to survive these files across local transactions and allow to open and - * close at stream start and close. We decided to use SharedFileSet + * close at stream start and close. We decided to use FileSet * infrastructure as without that it deletes the files on the closure of the * file and if we decide to keep stream files open across the start/stop stream * then it will consume a lot of memory (more than 8K for each BufFile and * there could be multiple such BufFiles as the subscriber could receive * multiple start/stop streams for different transactions before getting the - * commit). Moreover, if we don't use SharedFileSet then we also need to invent + * commit). Moreover, if we don't use FileSet then we also need to invent * a new way to pass filenames to BufFile APIs so that we are allowed to open * the file we desired across multiple stream-open calls for the same * transaction. @@ -231,8 +231,8 @@ typedef struct ApplyExecutionData typedef struct StreamXidHash { TransactionId xid; /* xid is the hash key and must be first */ - SharedFileSet *stream_fileset; /* shared file set for stream data */ - SharedFileSet *subxact_fileset; /* shared file set for subxact info */ + FileSet *stream_fileset; /* file set for stream data */ + FileSet *subxact_fileset; /* file set for subxact info */ } StreamXidHash; static MemoryContext ApplyMessageContext = NULL; @@ -255,8 +255,8 @@ static bool in_streamed_transaction = false; static TransactionId stream_xid = InvalidTransactionId; /* - * Hash table for storing the streaming xid information along with shared file - * set for streaming and subxact files. + * Hash table for storing the streaming xid information along with filesets + * for streaming and subxact files. */ static HTAB *xidhash = NULL; @@ -1299,11 +1299,11 @@ apply_handle_stream_abort(StringInfo s) /* open the changes file */ changes_filename(path, MyLogicalRepWorker->subid, xid); - fd = BufFileOpenShared(ent->stream_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); /* OK, truncate the file at the right offset */ - BufFileTruncateShared(fd, subxact_data.subxacts[subidx].fileno, - subxact_data.subxacts[subidx].offset); + BufFileTruncateFileSet(fd, subxact_data.subxacts[subidx].fileno, + subxact_data.subxacts[subidx].offset); BufFileClose(fd); /* discard the subxacts added later */ @@ -1355,7 +1355,7 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) errmsg_internal("transaction %u not found in stream XID hash table", xid))); - fd = BufFileOpenShared(ent->stream_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDONLY); buffer = palloc(BLCKSZ); initStringInfo(&s2); @@ -2509,6 +2509,30 @@ UpdateWorkerStats(XLogRecPtr last_lsn, TimestampTz send_time, bool reply) } /* + * Cleanup filesets. + */ +void +logicalrep_worker_cleanupfileset(void) +{ + HASH_SEQ_STATUS status; + StreamXidHash *hentry; + + /* Remove all the pending stream and subxact filesets. */ + if (xidhash) + { + hash_seq_init(&status, xidhash); + while ((hentry = (StreamXidHash *) hash_seq_search(&status)) != NULL) + { + FileSetDeleteAll(hentry->stream_fileset); + + /* Delete the subxact fileset iff it is created. */ + if (hentry->subxact_fileset) + FileSetDeleteAll(hentry->subxact_fileset); + } + } +} + +/* * Apply main loop. */ static void @@ -2979,7 +3003,7 @@ subxact_info_write(Oid subid, TransactionId xid) if (ent->subxact_fileset) { cleanup_subxact_info(); - SharedFileSetDeleteAll(ent->subxact_fileset); + FileSetDeleteAll(ent->subxact_fileset); pfree(ent->subxact_fileset); ent->subxact_fileset = NULL; } @@ -2997,18 +3021,18 @@ subxact_info_write(Oid subid, TransactionId xid) MemoryContext oldctx; /* - * We need to maintain shared fileset across multiple stream - * start/stop calls. So, need to allocate it in a persistent context. + * We need to maintain fileset across multiple stream start/stop + * calls. So, need to allocate it in a persistent context. */ oldctx = MemoryContextSwitchTo(ApplyContext); - ent->subxact_fileset = palloc(sizeof(SharedFileSet)); - SharedFileSetInit(ent->subxact_fileset, NULL); + ent->subxact_fileset = palloc(sizeof(FileSet)); + FileSetInit(ent->subxact_fileset); MemoryContextSwitchTo(oldctx); - fd = BufFileCreateShared(ent->subxact_fileset, path); + fd = BufFileCreateFileSet(ent->subxact_fileset, path); } else - fd = BufFileOpenShared(ent->subxact_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDWR); len = sizeof(SubXactInfo) * subxact_data.nsubxacts; @@ -3062,7 +3086,7 @@ subxact_info_read(Oid subid, TransactionId xid) subxact_filename(path, subid, xid); - fd = BufFileOpenShared(ent->subxact_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDONLY); /* read number of subxact items */ if (BufFileRead(fd, &subxact_data.nsubxacts, @@ -3219,7 +3243,7 @@ stream_cleanup_files(Oid subid, TransactionId xid) /* Delete the change file and release the stream fileset memory */ changes_filename(path, subid, xid); - SharedFileSetDeleteAll(ent->stream_fileset); + FileSetDeleteAll(ent->stream_fileset); pfree(ent->stream_fileset); ent->stream_fileset = NULL; @@ -3227,7 +3251,7 @@ stream_cleanup_files(Oid subid, TransactionId xid) if (ent->subxact_fileset) { subxact_filename(path, subid, xid); - SharedFileSetDeleteAll(ent->subxact_fileset); + FileSetDeleteAll(ent->subxact_fileset); pfree(ent->subxact_fileset); ent->subxact_fileset = NULL; } @@ -3243,8 +3267,8 @@ stream_cleanup_files(Oid subid, TransactionId xid) * * Open a file for streamed changes from a toplevel transaction identified * by stream_xid (global variable). If it's the first chunk of streamed - * changes for this transaction, initialize the shared fileset and create the - * buffile, otherwise open the previously created file. + * changes for this transaction, initialize the fileset and create the buffile, + * otherwise open the previously created file. * * This can only be called at the beginning of a "streaming" block, i.e. * between stream_start/stream_stop messages from the upstream. @@ -3285,7 +3309,7 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) if (first_segment) { MemoryContext savectx; - SharedFileSet *fileset; + FileSet *fileset; if (found) ereport(ERROR, @@ -3293,16 +3317,16 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); /* - * We need to maintain shared fileset across multiple stream - * start/stop calls. So, need to allocate it in a persistent context. + * We need to maintain fileset across multiple stream start/stop + * calls. So, need to allocate it in a persistent context. */ savectx = MemoryContextSwitchTo(ApplyContext); - fileset = palloc(sizeof(SharedFileSet)); + fileset = palloc(sizeof(FileSet)); - SharedFileSetInit(fileset, NULL); + FileSetInit(fileset); MemoryContextSwitchTo(savectx); - stream_fd = BufFileCreateShared(fileset, path); + stream_fd = BufFileCreateFileSet(fileset, path); /* Remember the fileset for the next stream of the same transaction */ ent->xid = xid; @@ -3320,7 +3344,7 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) * Open the file and seek to the end of the file because we always * append the changes file. */ - stream_fd = BufFileOpenShared(ent->stream_fileset, path, O_RDWR); + stream_fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); BufFileSeek(stream_fd, 0, 0, SEEK_END); } diff --git a/src/backend/storage/file/Makefile b/src/backend/storage/file/Makefile index 5e1291b..660ac51 100644 --- a/src/backend/storage/file/Makefile +++ b/src/backend/storage/file/Makefile @@ -16,6 +16,7 @@ OBJS = \ buffile.o \ copydir.o \ fd.o \ + fileset.o \ reinit.o \ sharedfileset.o diff --git a/src/backend/storage/file/buffile.c b/src/backend/storage/file/buffile.c index a4be5fe..5e5409d 100644 --- a/src/backend/storage/file/buffile.c +++ b/src/backend/storage/file/buffile.c @@ -39,7 +39,7 @@ * BufFile also supports temporary files that can be used by the single backend * when the corresponding files need to be survived across the transaction and * need to be opened and closed multiple times. Such files need to be created - * as a member of a SharedFileSet. + * as a member of a FileSet. *------------------------------------------------------------------------- */ @@ -77,8 +77,8 @@ struct BufFile bool dirty; /* does buffer need to be written? */ bool readOnly; /* has the file been set to read only? */ - SharedFileSet *fileset; /* space for segment files if shared */ - const char *name; /* name of this BufFile if shared */ + FileSet *fileset; /* space for fileset based segment files */ + const char *name; /* name of fileset based BufFile */ /* * resowner is the ResourceOwner to use for underlying temp files. (We @@ -104,7 +104,7 @@ static void extendBufFile(BufFile *file); static void BufFileLoadBuffer(BufFile *file); static void BufFileDumpBuffer(BufFile *file); static void BufFileFlush(BufFile *file); -static File MakeNewSharedSegment(BufFile *file, int segment); +static File MakeNewFileSetSegment(BufFile *file, int segment); /* * Create BufFile and perform the common initialization. @@ -160,7 +160,7 @@ extendBufFile(BufFile *file) if (file->fileset == NULL) pfile = OpenTemporaryFile(file->isInterXact); else - pfile = MakeNewSharedSegment(file, file->numFiles); + pfile = MakeNewFileSetSegment(file, file->numFiles); Assert(pfile >= 0); @@ -214,34 +214,34 @@ BufFileCreateTemp(bool interXact) * Build the name for a given segment of a given BufFile. */ static void -SharedSegmentName(char *name, const char *buffile_name, int segment) +FileSetSegmentName(char *name, const char *buffile_name, int segment) { snprintf(name, MAXPGPATH, "%s.%d", buffile_name, segment); } /* - * Create a new segment file backing a shared BufFile. + * Create a new segment file backing a fileset based BufFile. */ static File -MakeNewSharedSegment(BufFile *buffile, int segment) +MakeNewFileSetSegment(BufFile *buffile, int segment) { char name[MAXPGPATH]; File file; /* * It is possible that there are files left over from before a crash - * restart with the same name. In order for BufFileOpenShared() not to + * restart with the same name. In order for BufFileOpenFileSet() not to * get confused about how many segments there are, we'll unlink the next * segment number if it already exists. */ - SharedSegmentName(name, buffile->name, segment + 1); - SharedFileSetDelete(buffile->fileset, name, true); + FileSetSegmentName(name, buffile->name, segment + 1); + FileSetDelete(buffile->fileset, name, true); /* Create the new segment. */ - SharedSegmentName(name, buffile->name, segment); - file = SharedFileSetCreate(buffile->fileset, name); + FileSetSegmentName(name, buffile->name, segment); + file = FileSetCreate(buffile->fileset, name); - /* SharedFileSetCreate would've errored out */ + /* FileSetCreate would've errored out */ Assert(file > 0); return file; @@ -251,15 +251,15 @@ MakeNewSharedSegment(BufFile *buffile, int segment) * Create a BufFile that can be discovered and opened read-only by other * backends that are attached to the same SharedFileSet using the same name. * - * The naming scheme for shared BufFiles is left up to the calling code. The - * name will appear as part of one or more filenames on disk, and might + * The naming scheme for fileset based BufFiles is left up to the calling code. + * The name will appear as part of one or more filenames on disk, and might * provide clues to administrators about which subsystem is generating * temporary file data. Since each SharedFileSet object is backed by one or * more uniquely named temporary directory, names don't conflict with * unrelated SharedFileSet objects. */ BufFile * -BufFileCreateShared(SharedFileSet *fileset, const char *name) +BufFileCreateFileSet(FileSet *fileset, const char *name) { BufFile *file; @@ -267,7 +267,7 @@ BufFileCreateShared(SharedFileSet *fileset, const char *name) file->fileset = fileset; file->name = pstrdup(name); file->files = (File *) palloc(sizeof(File)); - file->files[0] = MakeNewSharedSegment(file, 0); + file->files[0] = MakeNewFileSetSegment(file, 0); file->readOnly = false; return file; @@ -275,13 +275,13 @@ BufFileCreateShared(SharedFileSet *fileset, const char *name) /* * Open a file that was previously created in another backend (or this one) - * with BufFileCreateShared in the same SharedFileSet using the same name. + * with BufFileCreateFileSet in the same FileSet using the same name. * The backend that created the file must have called BufFileClose() or - * BufFileExportShared() to make sure that it is ready to be opened by other + * BufFileExportFileSet() to make sure that it is ready to be opened by other * backends and render it read-only. */ BufFile * -BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) +BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) { BufFile *file; char segment_name[MAXPGPATH]; @@ -304,8 +304,8 @@ BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) files = repalloc(files, sizeof(File) * capacity); } /* Try to load a segment. */ - SharedSegmentName(segment_name, name, nfiles); - files[nfiles] = SharedFileSetOpen(fileset, segment_name, mode); + FileSetSegmentName(segment_name, name, nfiles); + files[nfiles] = FileSetOpen(fileset, segment_name, mode); if (files[nfiles] <= 0) break; ++nfiles; @@ -333,18 +333,18 @@ BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) } /* - * Delete a BufFile that was created by BufFileCreateShared in the given - * SharedFileSet using the given name. + * Delete a BufFile that was created by BufFileCreateFileSet in the given + * FileSet using the given name. * * It is not necessary to delete files explicitly with this function. It is * provided only as a way to delete files proactively, rather than waiting for - * the SharedFileSet to be cleaned up. + * the FileSet to be cleaned up. * * Only one backend should attempt to delete a given name, and should know * that it exists and has been exported or closed. */ void -BufFileDeleteShared(SharedFileSet *fileset, const char *name) +BufFileDeleteFileSet(FileSet *fileset, const char *name) { char segment_name[MAXPGPATH]; int segment = 0; @@ -357,8 +357,8 @@ BufFileDeleteShared(SharedFileSet *fileset, const char *name) */ for (;;) { - SharedSegmentName(segment_name, name, segment); - if (!SharedFileSetDelete(fileset, segment_name, true)) + FileSetSegmentName(segment_name, name, segment); + if (!FileSetDelete(fileset, segment_name, true)) break; found = true; ++segment; @@ -367,16 +367,16 @@ BufFileDeleteShared(SharedFileSet *fileset, const char *name) } if (!found) - elog(ERROR, "could not delete unknown shared BufFile \"%s\"", name); + elog(ERROR, "could not delete unknown BufFile \"%s\"", name); } /* - * BufFileExportShared --- flush and make read-only, in preparation for sharing. + * BufFileExportFileSet --- flush and make read-only, in preparation for sharing. */ void -BufFileExportShared(BufFile *file) +BufFileExportFileSet(BufFile *file) { - /* Must be a file belonging to a SharedFileSet. */ + /* Must be a file belonging to a FileSet. */ Assert(file->fileset != NULL); /* It's probably a bug if someone calls this twice. */ @@ -785,7 +785,7 @@ BufFileTellBlock(BufFile *file) #endif /* - * Return the current shared BufFile size. + * Return the current fileset based BufFile size. * * Counts any holes left behind by BufFileAppend as part of the size. * ereport()s on failure. @@ -811,8 +811,8 @@ BufFileSize(BufFile *file) } /* - * Append the contents of source file (managed within shared fileset) to - * end of target file (managed within same shared fileset). + * Append the contents of source file (managed within fileset) to + * end of target file (managed within same fileset). * * Note that operation subsumes ownership of underlying resources from * "source". Caller should never call BufFileClose against source having @@ -854,11 +854,11 @@ BufFileAppend(BufFile *target, BufFile *source) } /* - * Truncate a BufFile created by BufFileCreateShared up to the given fileno and - * the offset. + * Truncate a BufFile created by BufFileCreateFileSet up to the given fileno + * and the offset. */ void -BufFileTruncateShared(BufFile *file, int fileno, off_t offset) +BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset) { int numFiles = file->numFiles; int newFile = fileno; @@ -876,12 +876,12 @@ BufFileTruncateShared(BufFile *file, int fileno, off_t offset) { if ((i != fileno || offset == 0) && i != 0) { - SharedSegmentName(segment_name, file->name, i); + FileSetSegmentName(segment_name, file->name, i); FileClose(file->files[i]); - if (!SharedFileSetDelete(file->fileset, segment_name, true)) + if (!FileSetDelete(file->fileset, segment_name, true)) ereport(ERROR, (errcode_for_file_access(), - errmsg("could not delete shared fileset \"%s\": %m", + errmsg("could not delete fileset \"%s\": %m", segment_name))); numFiles--; newOffset = MAX_PHYSICAL_FILESIZE; diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c index b58b399..433e283 100644 --- a/src/backend/storage/file/fd.c +++ b/src/backend/storage/file/fd.c @@ -1921,7 +1921,7 @@ PathNameDeleteTemporaryFile(const char *path, bool error_on_failure) /* * Unlike FileClose's automatic file deletion code, we tolerate - * non-existence to support BufFileDeleteShared which doesn't know how + * non-existence to support BufFileDeleteFileSet which doesn't know how * many segments it has to delete until it runs out. */ if (stat_errno == ENOENT) diff --git a/src/backend/storage/file/fileset.c b/src/backend/storage/file/fileset.c new file mode 100644 index 0000000..282ff12 --- /dev/null +++ b/src/backend/storage/file/fileset.c @@ -0,0 +1,205 @@ +/*------------------------------------------------------------------------- + * + * fileset.c + * Management of named temporary files. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/backend/storage/file/fileset.c + * + * FileSets provide a temporary namespace (think directory) so that files can + * be discovered by name. + * + * FileSets can be used by backends when the temporary files need to be + * opened/closed multiple times and the underlying files need to survive across + * transactions. + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include <limits.h> + +#include "catalog/pg_tablespace.h" +#include "commands/tablespace.h" +#include "common/hashfn.h" +#include "miscadmin.h" +#include "storage/ipc.h" +#include "storage/fileset.h" +#include "utils/builtins.h" + +static void FileSetPath(char *path, FileSet *fileset, Oid tablespace); +static void FilePath(char *path, FileSet *fileset, const char *name); +static Oid ChooseTablespace(const FileSet *fileset, const char *name); + +/* + * Initialize a space for temporary files. This API can be used by shared + * fileset as well as if the temporary files are used only by single backend + * but the files need to be opened and closed multiple times and also the + * underlying files need to survive across transactions. + * + * The callers are expected to explicitly remove such files by using + * FileSetDelete/FileSetDeleteAll. + * + * Files will be distributed over the tablespaces configured in + * temp_tablespaces. + * + * Under the covers the set is one or more directories which will eventually + * be deleted. + */ +void +FileSetInit(FileSet *fileset) +{ + static uint32 counter = 0; + + fileset->creator_pid = MyProcPid; + fileset->number = counter; + counter = (counter + 1) % INT_MAX; + + /* Capture the tablespace OIDs so that all backends agree on them. */ + PrepareTempTablespaces(); + fileset->ntablespaces = + GetTempTablespaces(&fileset->tablespaces[0], + lengthof(fileset->tablespaces)); + if (fileset->ntablespaces == 0) + { + /* If the GUC is empty, use current database's default tablespace */ + fileset->tablespaces[0] = MyDatabaseTableSpace; + fileset->ntablespaces = 1; + } + else + { + int i; + + /* + * An entry of InvalidOid means use the default tablespace for the + * current database. Replace that now, to be sure that all users of + * the FileSet agree on what to do. + */ + for (i = 0; i < fileset->ntablespaces; i++) + { + if (fileset->tablespaces[i] == InvalidOid) + fileset->tablespaces[i] = MyDatabaseTableSpace; + } + } +} + +/* + * Create a new file in the given set. + */ +File +FileSetCreate(FileSet *fileset, const char *name) +{ + char path[MAXPGPATH]; + File file; + + FilePath(path, fileset, name); + file = PathNameCreateTemporaryFile(path, false); + + /* If we failed, see if we need to create the directory on demand. */ + if (file <= 0) + { + char tempdirpath[MAXPGPATH]; + char filesetpath[MAXPGPATH]; + Oid tablespace = ChooseTablespace(fileset, name); + + TempTablespacePath(tempdirpath, tablespace); + FileSetPath(filesetpath, fileset, tablespace); + PathNameCreateTemporaryDir(tempdirpath, filesetpath); + file = PathNameCreateTemporaryFile(path, true); + } + + return file; +} + +/* + * Open a file that was created with FileSetCreate() */ +File +FileSetOpen(FileSet *fileset, const char *name, int mode) +{ + char path[MAXPGPATH]; + File file; + + FilePath(path, fileset, name); + file = PathNameOpenTemporaryFile(path, mode); + + return file; +} + +/* + * Delete a file that was created with FileSetCreate(). + * + * Return true if the file existed, false if didn't. + */ +bool +FileSetDelete(FileSet *fileset, const char *name, + bool error_on_failure) +{ + char path[MAXPGPATH]; + + FilePath(path, fileset, name); + + return PathNameDeleteTemporaryFile(path, error_on_failure); +} + +/* + * Delete all files in the set. + */ +void +FileSetDeleteAll(FileSet *fileset) +{ + char dirpath[MAXPGPATH]; + int i; + + /* + * Delete the directory we created in each tablespace. Doesn't fail + * because we use this in error cleanup paths, but can generate LOG + * message on IO error. + */ + for (i = 0; i < fileset->ntablespaces; ++i) + { + FileSetPath(dirpath, fileset, fileset->tablespaces[i]); + PathNameDeleteTemporaryDir(dirpath); + } +} + +/* + * Build the path for the directory holding the files backing a FileSet in a + * given tablespace. + */ +static void +FileSetPath(char *path, FileSet *fileset, Oid tablespace) +{ + char tempdirpath[MAXPGPATH]; + + TempTablespacePath(tempdirpath, tablespace); + snprintf(path, MAXPGPATH, "%s/%s%lu.%u.fileset", + tempdirpath, PG_TEMP_FILE_PREFIX, + (unsigned long) fileset->creator_pid, fileset->number); +} + +/* + * Sorting has to determine which tablespace a given temporary file belongs in. + */ +static Oid +ChooseTablespace(const FileSet *fileset, const char *name) +{ + uint32 hash = hash_any((const unsigned char *) name, strlen(name)); + + return fileset->tablespaces[hash % fileset->ntablespaces]; +} + +/* + * Compute the full path of a file in a FileSet. + */ +static void +FilePath(char *path, FileSet *fileset, const char *name) +{ + char dirpath[MAXPGPATH]; + + FileSetPath(dirpath, fileset, ChooseTablespace(fileset, name)); + snprintf(path, MAXPGPATH, "%s/%s", dirpath, name); +} diff --git a/src/backend/storage/file/sharedfileset.c b/src/backend/storage/file/sharedfileset.c index ed37c94..6a33fac 100644 --- a/src/backend/storage/file/sharedfileset.c +++ b/src/backend/storage/file/sharedfileset.c @@ -13,10 +13,6 @@ * files can be discovered by name, and a shared ownership semantics so that * shared files survive until the last user detaches. * - * SharedFileSets can be used by backends when the temporary files need to be - * opened/closed multiple times and the underlying files need to survive across - * transactions. - * *------------------------------------------------------------------------- */ @@ -33,13 +29,7 @@ #include "storage/sharedfileset.h" #include "utils/builtins.h" -static List *filesetlist = NIL; - static void SharedFileSetOnDetach(dsm_segment *segment, Datum datum); -static void SharedFileSetDeleteOnProcExit(int status, Datum arg); -static void SharedFileSetPath(char *path, SharedFileSet *fileset, Oid tablespace); -static void SharedFilePath(char *path, SharedFileSet *fileset, const char *name); -static Oid ChooseTablespace(const SharedFileSet *fileset, const char *name); /* * Initialize a space for temporary files that can be opened by other backends. @@ -47,77 +37,22 @@ static Oid ChooseTablespace(const SharedFileSet *fileset, const char *name); * SharedFileSet with 'seg'. Any contained files will be deleted when the * last backend detaches. * - * We can also use this interface if the temporary files are used only by - * single backend but the files need to be opened and closed multiple times - * and also the underlying files need to survive across transactions. For - * such cases, dsm segment 'seg' should be passed as NULL. Callers are - * expected to explicitly remove such files by using SharedFileSetDelete/ - * SharedFileSetDeleteAll or we remove such files on proc exit. - * - * Files will be distributed over the tablespaces configured in - * temp_tablespaces. - * * Under the covers the set is one or more directories which will eventually * be deleted. */ void SharedFileSetInit(SharedFileSet *fileset, dsm_segment *seg) { - static uint32 counter = 0; - + /* Initialize the shared fileset specific members. */ SpinLockInit(&fileset->mutex); fileset->refcnt = 1; - fileset->creator_pid = MyProcPid; - fileset->number = counter; - counter = (counter + 1) % INT_MAX; - - /* Capture the tablespace OIDs so that all backends agree on them. */ - PrepareTempTablespaces(); - fileset->ntablespaces = - GetTempTablespaces(&fileset->tablespaces[0], - lengthof(fileset->tablespaces)); - if (fileset->ntablespaces == 0) - { - /* If the GUC is empty, use current database's default tablespace */ - fileset->tablespaces[0] = MyDatabaseTableSpace; - fileset->ntablespaces = 1; - } - else - { - int i; - /* - * An entry of InvalidOid means use the default tablespace for the - * current database. Replace that now, to be sure that all users of - * the SharedFileSet agree on what to do. - */ - for (i = 0; i < fileset->ntablespaces; i++) - { - if (fileset->tablespaces[i] == InvalidOid) - fileset->tablespaces[i] = MyDatabaseTableSpace; - } - } + /* Initialize the fileset. */ + FileSetInit(&fileset->fs); /* Register our cleanup callback. */ if (seg) on_dsm_detach(seg, SharedFileSetOnDetach, PointerGetDatum(fileset)); - else - { - static bool registered_cleanup = false; - - if (!registered_cleanup) - { - /* - * We must not have registered any fileset before registering the - * fileset clean up. - */ - Assert(filesetlist == NIL); - on_proc_exit(SharedFileSetDeleteOnProcExit, 0); - registered_cleanup = true; - } - - filesetlist = lcons((void *) fileset, filesetlist); - } } /* @@ -148,86 +83,12 @@ SharedFileSetAttach(SharedFileSet *fileset, dsm_segment *seg) } /* - * Create a new file in the given set. - */ -File -SharedFileSetCreate(SharedFileSet *fileset, const char *name) -{ - char path[MAXPGPATH]; - File file; - - SharedFilePath(path, fileset, name); - file = PathNameCreateTemporaryFile(path, false); - - /* If we failed, see if we need to create the directory on demand. */ - if (file <= 0) - { - char tempdirpath[MAXPGPATH]; - char filesetpath[MAXPGPATH]; - Oid tablespace = ChooseTablespace(fileset, name); - - TempTablespacePath(tempdirpath, tablespace); - SharedFileSetPath(filesetpath, fileset, tablespace); - PathNameCreateTemporaryDir(tempdirpath, filesetpath); - file = PathNameCreateTemporaryFile(path, true); - } - - return file; -} - -/* - * Open a file that was created with SharedFileSetCreate(), possibly in - * another backend. - */ -File -SharedFileSetOpen(SharedFileSet *fileset, const char *name, int mode) -{ - char path[MAXPGPATH]; - File file; - - SharedFilePath(path, fileset, name); - file = PathNameOpenTemporaryFile(path, mode); - - return file; -} - -/* - * Delete a file that was created with SharedFileSetCreate(). - * Return true if the file existed, false if didn't. - */ -bool -SharedFileSetDelete(SharedFileSet *fileset, const char *name, - bool error_on_failure) -{ - char path[MAXPGPATH]; - - SharedFilePath(path, fileset, name); - - return PathNameDeleteTemporaryFile(path, error_on_failure); -} - -/* * Delete all files in the set. */ void SharedFileSetDeleteAll(SharedFileSet *fileset) { - char dirpath[MAXPGPATH]; - int i; - - /* - * Delete the directory we created in each tablespace. Doesn't fail - * because we use this in error cleanup paths, but can generate LOG - * message on IO error. - */ - for (i = 0; i < fileset->ntablespaces; ++i) - { - SharedFileSetPath(dirpath, fileset, fileset->tablespaces[i]); - PathNameDeleteTemporaryDir(dirpath); - } - - /* Unregister the shared fileset */ - SharedFileSetUnregister(fileset); + FileSetDeleteAll(&fileset->fs); } /* @@ -255,100 +116,5 @@ SharedFileSetOnDetach(dsm_segment *segment, Datum datum) * this function so we can safely access its data. */ if (unlink_all) - SharedFileSetDeleteAll(fileset); -} - -/* - * Callback function that will be invoked on the process exit. This will - * process the list of all the registered sharedfilesets and delete the - * underlying files. - */ -static void -SharedFileSetDeleteOnProcExit(int status, Datum arg) -{ - /* - * Remove all the pending shared fileset entries. We don't use foreach() - * here because SharedFileSetDeleteAll will remove the current element in - * filesetlist. Though we have used foreach_delete_current() to remove the - * element from filesetlist it could only fix up the state of one of the - * loops, see SharedFileSetUnregister. - */ - while (list_length(filesetlist) > 0) - { - SharedFileSet *fileset = (SharedFileSet *) linitial(filesetlist); - - SharedFileSetDeleteAll(fileset); - } - - filesetlist = NIL; -} - -/* - * Unregister the shared fileset entry registered for cleanup on proc exit. - */ -void -SharedFileSetUnregister(SharedFileSet *input_fileset) -{ - ListCell *l; - - /* - * If the caller is following the dsm based cleanup then we don't maintain - * the filesetlist so return. - */ - if (filesetlist == NIL) - return; - - foreach(l, filesetlist) - { - SharedFileSet *fileset = (SharedFileSet *) lfirst(l); - - /* Remove the entry from the list */ - if (input_fileset == fileset) - { - filesetlist = foreach_delete_current(filesetlist, l); - return; - } - } - - /* Should have found a match */ - Assert(false); -} - -/* - * Build the path for the directory holding the files backing a SharedFileSet - * in a given tablespace. - */ -static void -SharedFileSetPath(char *path, SharedFileSet *fileset, Oid tablespace) -{ - char tempdirpath[MAXPGPATH]; - - TempTablespacePath(tempdirpath, tablespace); - snprintf(path, MAXPGPATH, "%s/%s%lu.%u.sharedfileset", - tempdirpath, PG_TEMP_FILE_PREFIX, - (unsigned long) fileset->creator_pid, fileset->number); -} - -/* - * Sorting hat to determine which tablespace a given shared temporary file - * belongs in. - */ -static Oid -ChooseTablespace(const SharedFileSet *fileset, const char *name) -{ - uint32 hash = hash_any((const unsigned char *) name, strlen(name)); - - return fileset->tablespaces[hash % fileset->ntablespaces]; -} - -/* - * Compute the full path of a file in a SharedFileSet. - */ -static void -SharedFilePath(char *path, SharedFileSet *fileset, const char *name) -{ - char dirpath[MAXPGPATH]; - - SharedFileSetPath(dirpath, fileset, ChooseTablespace(fileset, name)); - snprintf(path, MAXPGPATH, "%s/%s", dirpath, name); + FileSetDeleteAll(&fileset->fs); } diff --git a/src/backend/utils/sort/logtape.c b/src/backend/utils/sort/logtape.c index cafc087..f7994d7 100644 --- a/src/backend/utils/sort/logtape.c +++ b/src/backend/utils/sort/logtape.c @@ -564,7 +564,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, lt = &lts->tapes[i]; pg_itoa(i, filename); - file = BufFileOpenShared(fileset, filename, O_RDONLY); + file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY); filesize = BufFileSize(file); /* @@ -610,7 +610,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, * offset). * * The only thing that currently prevents writing to the leader tape from - * working is the fact that BufFiles opened using BufFileOpenShared() are + * working is the fact that BufFiles opened using BufFileOpenFileSet() are * read-only by definition, but that could be changed if it seemed * worthwhile. For now, writing to the leader tape will raise a "Bad file * descriptor" error, so tuplesort must avoid writing to the leader tape @@ -722,7 +722,7 @@ LogicalTapeSetCreate(int ntapes, bool preallocate, TapeShare *shared, char filename[MAXPGPATH]; pg_itoa(worker, filename); - lts->pfile = BufFileCreateShared(fileset, filename); + lts->pfile = BufFileCreateFileSet(&fileset->fs, filename); } else lts->pfile = BufFileCreateTemp(false); @@ -1096,7 +1096,7 @@ LogicalTapeFreeze(LogicalTapeSet *lts, int tapenum, TapeShare *share) /* Handle extra steps when caller is to share its tapeset */ if (share) { - BufFileExportShared(lts->pfile); + BufFileExportFileSet(lts->pfile); share->firstblocknumber = lt->firstBlockNumber; } } diff --git a/src/backend/utils/sort/sharedtuplestore.c b/src/backend/utils/sort/sharedtuplestore.c index 57e35db..504ef1c 100644 --- a/src/backend/utils/sort/sharedtuplestore.c +++ b/src/backend/utils/sort/sharedtuplestore.c @@ -310,7 +310,8 @@ sts_puttuple(SharedTuplestoreAccessor *accessor, void *meta_data, /* Create one. Only this backend will write into it. */ sts_filename(name, accessor, accessor->participant); - accessor->write_file = BufFileCreateShared(accessor->fileset, name); + accessor->write_file = + BufFileCreateFileSet(&accessor->fileset->fs, name); /* Set up the shared state for this backend's file. */ participant = &accessor->sts->participants[accessor->participant]; @@ -559,7 +560,7 @@ sts_parallel_scan_next(SharedTuplestoreAccessor *accessor, void *meta_data) sts_filename(name, accessor, accessor->read_participant); accessor->read_file = - BufFileOpenShared(accessor->fileset, name, O_RDONLY); + BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY); } /* Seek and load the chunk header. */ diff --git a/src/include/replication/worker_internal.h b/src/include/replication/worker_internal.h index 41c7487..a6c9d4e 100644 --- a/src/include/replication/worker_internal.h +++ b/src/include/replication/worker_internal.h @@ -79,6 +79,7 @@ extern void logicalrep_worker_launch(Oid dbid, Oid subid, const char *subname, extern void logicalrep_worker_stop(Oid subid, Oid relid); extern void logicalrep_worker_wakeup(Oid subid, Oid relid); extern void logicalrep_worker_wakeup_ptr(LogicalRepWorker *worker); +extern void logicalrep_worker_cleanupfileset(void); extern int logicalrep_sync_worker_count(Oid subid); diff --git a/src/include/storage/buffile.h b/src/include/storage/buffile.h index 566523d..143eada 100644 --- a/src/include/storage/buffile.h +++ b/src/include/storage/buffile.h @@ -26,7 +26,7 @@ #ifndef BUFFILE_H #define BUFFILE_H -#include "storage/sharedfileset.h" +#include "storage/fileset.h" /* BufFile is an opaque type whose details are not known outside buffile.c. */ @@ -46,11 +46,11 @@ extern int BufFileSeekBlock(BufFile *file, long blknum); extern int64 BufFileSize(BufFile *file); extern long BufFileAppend(BufFile *target, BufFile *source); -extern BufFile *BufFileCreateShared(SharedFileSet *fileset, const char *name); -extern void BufFileExportShared(BufFile *file); -extern BufFile *BufFileOpenShared(SharedFileSet *fileset, const char *name, - int mode); -extern void BufFileDeleteShared(SharedFileSet *fileset, const char *name); -extern void BufFileTruncateShared(BufFile *file, int fileno, off_t offset); +extern BufFile *BufFileCreateFileSet(FileSet *fileset, const char *name); +extern void BufFileExportFileSet(BufFile *file); +extern BufFile *BufFileOpenFileSet(FileSet *fileset, const char *name, + int mode); +extern void BufFileDeleteFileSet(FileSet *fileset, const char *name); +extern void BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset); #endif /* BUFFILE_H */ diff --git a/src/include/storage/fileset.h b/src/include/storage/fileset.h new file mode 100644 index 0000000..be0e097 --- /dev/null +++ b/src/include/storage/fileset.h @@ -0,0 +1,40 @@ +/*------------------------------------------------------------------------- + * + * fileset.h + * Management of named temporary files. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/storage/fileset.h + * + *------------------------------------------------------------------------- + */ + +#ifndef FILESET_H +#define FILESET_H + +#include "storage/fd.h" + +/* + * A set of temporary files. + */ +typedef struct FileSet +{ + pid_t creator_pid; /* PID of the creating process */ + uint32 number; /* per-PID identifier */ + int ntablespaces; /* number of tablespaces to use */ + Oid tablespaces[8]; /* OIDs of tablespaces to use. Assumes that + * it's rare that there more than temp + * tablespaces. */ +} FileSet; + +extern void FileSetInit(FileSet *fileset); +extern File FileSetCreate(FileSet *fileset, const char *name); +extern File FileSetOpen(FileSet *fileset, const char *name, + int mode); +extern bool FileSetDelete(FileSet *fileset, const char *name, + bool error_on_failure); +extern void FileSetDeleteAll(FileSet *fileset); + +#endif diff --git a/src/include/storage/sharedfileset.h b/src/include/storage/sharedfileset.h index 09ba121..59becfb 100644 --- a/src/include/storage/sharedfileset.h +++ b/src/include/storage/sharedfileset.h @@ -17,6 +17,7 @@ #include "storage/dsm.h" #include "storage/fd.h" +#include "storage/fileset.h" #include "storage/spin.h" /* @@ -24,24 +25,13 @@ */ typedef struct SharedFileSet { - pid_t creator_pid; /* PID of the creating process */ - uint32 number; /* per-PID identifier */ + FileSet fs; slock_t mutex; /* mutex protecting the reference count */ int refcnt; /* number of attached backends */ - int ntablespaces; /* number of tablespaces to use */ - Oid tablespaces[8]; /* OIDs of tablespaces to use. Assumes that - * it's rare that there more than temp - * tablespaces. */ } SharedFileSet; extern void SharedFileSetInit(SharedFileSet *fileset, dsm_segment *seg); extern void SharedFileSetAttach(SharedFileSet *fileset, dsm_segment *seg); -extern File SharedFileSetCreate(SharedFileSet *fileset, const char *name); -extern File SharedFileSetOpen(SharedFileSet *fileset, const char *name, - int mode); -extern bool SharedFileSetDelete(SharedFileSet *fileset, const char *name, - bool error_on_failure); extern void SharedFileSetDeleteAll(SharedFileSet *fileset); -extern void SharedFileSetUnregister(SharedFileSet *input_fileset); #endif diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 37cf4b2..4770740 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -708,6 +708,7 @@ File FileFdwExecutionState FileFdwPlanState FileNameMap +FileSet FileTag FinalPathExtraData FindColsContext -- 1.8.3.1
^ permalink raw reply [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
@ 2021-08-26 01:46             ` Masahiko Sawada <sawada.mshk@gmail.com>
  1 sibling, 0 replies; 26+ messages in thread

From: Masahiko Sawada @ 2021-08-26 01:46 UTC (permalink / raw)
  To: Amit Kapila <amit.kapila16@gmail.com>; +Cc: Dilip Kumar <dilipbalaut@gmail.com>; houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Tom Lane <tgl@sss.pgh.pa.us>

On Wed, Aug 25, 2021 at 9:19 PM Amit Kapila <amit.kapila16@gmail.com> wrote:
>
> On Tue, Aug 24, 2021 at 3:55 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
> >
> > On Tue, Aug 24, 2021 at 12:26 PM Amit Kapila <amit.kapila16@gmail.com> wrote:
> >
>
> The first patch looks good to me. I have made minor changes to the
> attached patch. The changes include: fixing compilation warning, made
> some comment changes, ran pgindent, and few other cosmetic changes. If
> you are fine with the attached, then kindly rebase the second patch
> atop it.

The patch looks good to me.

Regards,

-- 
Masahiko Sawada
EDB:  https://www.enterprisedb.com/





^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
@ 2021-08-26 06:17             ` Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-26 08:40               ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-27 05:26               ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  1 sibling, 2 replies; 26+ messages in thread

From: Dilip Kumar @ 2021-08-26 06:17 UTC (permalink / raw)
  To: Amit Kapila <amit.kapila16@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Wed, Aug 25, 2021 at 5:49 PM Amit Kapila <amit.kapila16@gmail.com> wrote:

> On Tue, Aug 24, 2021 at 3:55 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
> >
> > On Tue, Aug 24, 2021 at 12:26 PM Amit Kapila <amit.kapila16@gmail.com>
> wrote:
> >
>
> The first patch looks good to me. I have made minor changes to the
> attached patch. The changes include: fixing compilation warning, made
> some comment changes, ran pgindent, and few other cosmetic changes. If
> you are fine with the attached, then kindly rebase the second patch
> atop it.
>
>
The patch looks good to me, I have rebased 0002 atop this patch and also
done some cosmetic fixes in 0002.


-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com

Attachments: download all (2 files, .tar.gz)

v5-0001-Refactor-sharedfileset.c-to-separate-out-fileset-.patch (text/x-patch, 42.1K) download From 3558cdc8a4f77e3c9092bbaeded451eaaa1feca4 Mon Sep 17 00:00:00 2001 From: Amit Kapila <akapila@postgresql.org> Date: Wed, 25 Aug 2021 15:00:19 +0530 Subject: [PATCH v5 1/2] Refactor sharedfileset.c to separate out fileset implementation. Move fileset related implementation out of sharedfileset.c to allow its usage by backends that don't want to share filesets among different processes. After this split, fileset infrastructure is used by both sharedfileset.c and worker.c for the named temporary files that survive across transactions. Author: Dilip Kumar, based on suggestion by Andres Freund Reviewed-by: Hou Zhijie, Masahiko Sawada, Amit Kapila Discussion: https://postgr.es/m/E1mCC6U-0004Ik-Fs@gemulon.postgresql.org --- src/backend/replication/logical/launcher.c | 3 + src/backend/replication/logical/worker.c | 82 ++++++---- src/backend/storage/file/Makefile | 1 + src/backend/storage/file/buffile.c | 84 +++++----- src/backend/storage/file/fd.c | 2 +- src/backend/storage/file/fileset.c | 205 ++++++++++++++++++++++++ src/backend/storage/file/sharedfileset.c | 244 +---------------------------- src/backend/utils/sort/logtape.c | 8 +- src/backend/utils/sort/sharedtuplestore.c | 5 +- src/include/replication/worker_internal.h | 1 + src/include/storage/buffile.h | 14 +- src/include/storage/fileset.h | 40 +++++ src/include/storage/sharedfileset.h | 14 +- src/tools/pgindent/typedefs.list | 1 + 14 files changed, 368 insertions(+), 336 deletions(-) create mode 100644 src/backend/storage/file/fileset.c create mode 100644 src/include/storage/fileset.h diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index e3b11da..8b1772d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -648,6 +648,9 @@ logicalrep_worker_onexit(int code, Datum arg) logicalrep_worker_detach(); + /* Cleanup filesets used for streaming transactions. */ + logicalrep_worker_cleanupfileset(); + ApplyLauncherWakeup(); } diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index 38b493e..6adc6ddd 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -39,13 +39,13 @@ * BufFile infrastructure supports temporary files that exceed the OS file size * limit, (b) provides a way for automatic clean up on the error and (c) provides * a way to survive these files across local transactions and allow to open and - * close at stream start and close. We decided to use SharedFileSet + * close at stream start and close. We decided to use FileSet * infrastructure as without that it deletes the files on the closure of the * file and if we decide to keep stream files open across the start/stop stream * then it will consume a lot of memory (more than 8K for each BufFile and * there could be multiple such BufFiles as the subscriber could receive * multiple start/stop streams for different transactions before getting the - * commit). Moreover, if we don't use SharedFileSet then we also need to invent + * commit). Moreover, if we don't use FileSet then we also need to invent * a new way to pass filenames to BufFile APIs so that we are allowed to open * the file we desired across multiple stream-open calls for the same * transaction. @@ -231,8 +231,8 @@ typedef struct ApplyExecutionData typedef struct StreamXidHash { TransactionId xid; /* xid is the hash key and must be first */ - SharedFileSet *stream_fileset; /* shared file set for stream data */ - SharedFileSet *subxact_fileset; /* shared file set for subxact info */ + FileSet *stream_fileset; /* file set for stream data */ + FileSet *subxact_fileset; /* file set for subxact info */ } StreamXidHash; static MemoryContext ApplyMessageContext = NULL; @@ -255,8 +255,8 @@ static bool in_streamed_transaction = false; static TransactionId stream_xid = InvalidTransactionId; /* - * Hash table for storing the streaming xid information along with shared file - * set for streaming and subxact files. + * Hash table for storing the streaming xid information along with filesets + * for streaming and subxact files. */ static HTAB *xidhash = NULL; @@ -1299,11 +1299,11 @@ apply_handle_stream_abort(StringInfo s) /* open the changes file */ changes_filename(path, MyLogicalRepWorker->subid, xid); - fd = BufFileOpenShared(ent->stream_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); /* OK, truncate the file at the right offset */ - BufFileTruncateShared(fd, subxact_data.subxacts[subidx].fileno, - subxact_data.subxacts[subidx].offset); + BufFileTruncateFileSet(fd, subxact_data.subxacts[subidx].fileno, + subxact_data.subxacts[subidx].offset); BufFileClose(fd); /* discard the subxacts added later */ @@ -1355,7 +1355,7 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) errmsg_internal("transaction %u not found in stream XID hash table", xid))); - fd = BufFileOpenShared(ent->stream_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDONLY); buffer = palloc(BLCKSZ); initStringInfo(&s2); @@ -2509,6 +2509,30 @@ UpdateWorkerStats(XLogRecPtr last_lsn, TimestampTz send_time, bool reply) } /* + * Cleanup filesets. + */ +void +logicalrep_worker_cleanupfileset(void) +{ + HASH_SEQ_STATUS status; + StreamXidHash *hentry; + + /* Remove all the pending stream and subxact filesets. */ + if (xidhash) + { + hash_seq_init(&status, xidhash); + while ((hentry = (StreamXidHash *) hash_seq_search(&status)) != NULL) + { + FileSetDeleteAll(hentry->stream_fileset); + + /* Delete the subxact fileset iff it is created. */ + if (hentry->subxact_fileset) + FileSetDeleteAll(hentry->subxact_fileset); + } + } +} + +/* * Apply main loop. */ static void @@ -2979,7 +3003,7 @@ subxact_info_write(Oid subid, TransactionId xid) if (ent->subxact_fileset) { cleanup_subxact_info(); - SharedFileSetDeleteAll(ent->subxact_fileset); + FileSetDeleteAll(ent->subxact_fileset); pfree(ent->subxact_fileset); ent->subxact_fileset = NULL; } @@ -2997,18 +3021,18 @@ subxact_info_write(Oid subid, TransactionId xid) MemoryContext oldctx; /* - * We need to maintain shared fileset across multiple stream - * start/stop calls. So, need to allocate it in a persistent context. + * We need to maintain fileset across multiple stream start/stop + * calls. So, need to allocate it in a persistent context. */ oldctx = MemoryContextSwitchTo(ApplyContext); - ent->subxact_fileset = palloc(sizeof(SharedFileSet)); - SharedFileSetInit(ent->subxact_fileset, NULL); + ent->subxact_fileset = palloc(sizeof(FileSet)); + FileSetInit(ent->subxact_fileset); MemoryContextSwitchTo(oldctx); - fd = BufFileCreateShared(ent->subxact_fileset, path); + fd = BufFileCreateFileSet(ent->subxact_fileset, path); } else - fd = BufFileOpenShared(ent->subxact_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDWR); len = sizeof(SubXactInfo) * subxact_data.nsubxacts; @@ -3062,7 +3086,7 @@ subxact_info_read(Oid subid, TransactionId xid) subxact_filename(path, subid, xid); - fd = BufFileOpenShared(ent->subxact_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDONLY); /* read number of subxact items */ if (BufFileRead(fd, &subxact_data.nsubxacts, @@ -3219,7 +3243,7 @@ stream_cleanup_files(Oid subid, TransactionId xid) /* Delete the change file and release the stream fileset memory */ changes_filename(path, subid, xid); - SharedFileSetDeleteAll(ent->stream_fileset); + FileSetDeleteAll(ent->stream_fileset); pfree(ent->stream_fileset); ent->stream_fileset = NULL; @@ -3227,7 +3251,7 @@ stream_cleanup_files(Oid subid, TransactionId xid) if (ent->subxact_fileset) { subxact_filename(path, subid, xid); - SharedFileSetDeleteAll(ent->subxact_fileset); + FileSetDeleteAll(ent->subxact_fileset); pfree(ent->subxact_fileset); ent->subxact_fileset = NULL; } @@ -3243,8 +3267,8 @@ stream_cleanup_files(Oid subid, TransactionId xid) * * Open a file for streamed changes from a toplevel transaction identified * by stream_xid (global variable). If it's the first chunk of streamed - * changes for this transaction, initialize the shared fileset and create the - * buffile, otherwise open the previously created file. + * changes for this transaction, initialize the fileset and create the buffile, + * otherwise open the previously created file. * * This can only be called at the beginning of a "streaming" block, i.e. * between stream_start/stream_stop messages from the upstream. @@ -3285,7 +3309,7 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) if (first_segment) { MemoryContext savectx; - SharedFileSet *fileset; + FileSet *fileset; if (found) ereport(ERROR, @@ -3293,16 +3317,16 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); /* - * We need to maintain shared fileset across multiple stream - * start/stop calls. So, need to allocate it in a persistent context. + * We need to maintain fileset across multiple stream start/stop + * calls. So, need to allocate it in a persistent context. */ savectx = MemoryContextSwitchTo(ApplyContext); - fileset = palloc(sizeof(SharedFileSet)); + fileset = palloc(sizeof(FileSet)); - SharedFileSetInit(fileset, NULL); + FileSetInit(fileset); MemoryContextSwitchTo(savectx); - stream_fd = BufFileCreateShared(fileset, path); + stream_fd = BufFileCreateFileSet(fileset, path); /* Remember the fileset for the next stream of the same transaction */ ent->xid = xid; @@ -3320,7 +3344,7 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) * Open the file and seek to the end of the file because we always * append the changes file. */ - stream_fd = BufFileOpenShared(ent->stream_fileset, path, O_RDWR); + stream_fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); BufFileSeek(stream_fd, 0, 0, SEEK_END); } diff --git a/src/backend/storage/file/Makefile b/src/backend/storage/file/Makefile index 5e1291b..660ac51 100644 --- a/src/backend/storage/file/Makefile +++ b/src/backend/storage/file/Makefile @@ -16,6 +16,7 @@ OBJS = \ buffile.o \ copydir.o \ fd.o \ + fileset.o \ reinit.o \ sharedfileset.o diff --git a/src/backend/storage/file/buffile.c b/src/backend/storage/file/buffile.c index a4be5fe..5e5409d 100644 --- a/src/backend/storage/file/buffile.c +++ b/src/backend/storage/file/buffile.c @@ -39,7 +39,7 @@ * BufFile also supports temporary files that can be used by the single backend * when the corresponding files need to be survived across the transaction and * need to be opened and closed multiple times. Such files need to be created - * as a member of a SharedFileSet. + * as a member of a FileSet. *------------------------------------------------------------------------- */ @@ -77,8 +77,8 @@ struct BufFile bool dirty; /* does buffer need to be written? */ bool readOnly; /* has the file been set to read only? */ - SharedFileSet *fileset; /* space for segment files if shared */ - const char *name; /* name of this BufFile if shared */ + FileSet *fileset; /* space for fileset based segment files */ + const char *name; /* name of fileset based BufFile */ /* * resowner is the ResourceOwner to use for underlying temp files. (We @@ -104,7 +104,7 @@ static void extendBufFile(BufFile *file); static void BufFileLoadBuffer(BufFile *file); static void BufFileDumpBuffer(BufFile *file); static void BufFileFlush(BufFile *file); -static File MakeNewSharedSegment(BufFile *file, int segment); +static File MakeNewFileSetSegment(BufFile *file, int segment); /* * Create BufFile and perform the common initialization. @@ -160,7 +160,7 @@ extendBufFile(BufFile *file) if (file->fileset == NULL) pfile = OpenTemporaryFile(file->isInterXact); else - pfile = MakeNewSharedSegment(file, file->numFiles); + pfile = MakeNewFileSetSegment(file, file->numFiles); Assert(pfile >= 0); @@ -214,34 +214,34 @@ BufFileCreateTemp(bool interXact) * Build the name for a given segment of a given BufFile. */ static void -SharedSegmentName(char *name, const char *buffile_name, int segment) +FileSetSegmentName(char *name, const char *buffile_name, int segment) { snprintf(name, MAXPGPATH, "%s.%d", buffile_name, segment); } /* - * Create a new segment file backing a shared BufFile. + * Create a new segment file backing a fileset based BufFile. */ static File -MakeNewSharedSegment(BufFile *buffile, int segment) +MakeNewFileSetSegment(BufFile *buffile, int segment) { char name[MAXPGPATH]; File file; /* * It is possible that there are files left over from before a crash - * restart with the same name. In order for BufFileOpenShared() not to + * restart with the same name. In order for BufFileOpenFileSet() not to * get confused about how many segments there are, we'll unlink the next * segment number if it already exists. */ - SharedSegmentName(name, buffile->name, segment + 1); - SharedFileSetDelete(buffile->fileset, name, true); + FileSetSegmentName(name, buffile->name, segment + 1); + FileSetDelete(buffile->fileset, name, true); /* Create the new segment. */ - SharedSegmentName(name, buffile->name, segment); - file = SharedFileSetCreate(buffile->fileset, name); + FileSetSegmentName(name, buffile->name, segment); + file = FileSetCreate(buffile->fileset, name); - /* SharedFileSetCreate would've errored out */ + /* FileSetCreate would've errored out */ Assert(file > 0); return file; @@ -251,15 +251,15 @@ MakeNewSharedSegment(BufFile *buffile, int segment) * Create a BufFile that can be discovered and opened read-only by other * backends that are attached to the same SharedFileSet using the same name. * - * The naming scheme for shared BufFiles is left up to the calling code. The - * name will appear as part of one or more filenames on disk, and might + * The naming scheme for fileset based BufFiles is left up to the calling code. + * The name will appear as part of one or more filenames on disk, and might * provide clues to administrators about which subsystem is generating * temporary file data. Since each SharedFileSet object is backed by one or * more uniquely named temporary directory, names don't conflict with * unrelated SharedFileSet objects. */ BufFile * -BufFileCreateShared(SharedFileSet *fileset, const char *name) +BufFileCreateFileSet(FileSet *fileset, const char *name) { BufFile *file; @@ -267,7 +267,7 @@ BufFileCreateShared(SharedFileSet *fileset, const char *name) file->fileset = fileset; file->name = pstrdup(name); file->files = (File *) palloc(sizeof(File)); - file->files[0] = MakeNewSharedSegment(file, 0); + file->files[0] = MakeNewFileSetSegment(file, 0); file->readOnly = false; return file; @@ -275,13 +275,13 @@ BufFileCreateShared(SharedFileSet *fileset, const char *name) /* * Open a file that was previously created in another backend (or this one) - * with BufFileCreateShared in the same SharedFileSet using the same name. + * with BufFileCreateFileSet in the same FileSet using the same name. * The backend that created the file must have called BufFileClose() or - * BufFileExportShared() to make sure that it is ready to be opened by other + * BufFileExportFileSet() to make sure that it is ready to be opened by other * backends and render it read-only. */ BufFile * -BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) +BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) { BufFile *file; char segment_name[MAXPGPATH]; @@ -304,8 +304,8 @@ BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) files = repalloc(files, sizeof(File) * capacity); } /* Try to load a segment. */ - SharedSegmentName(segment_name, name, nfiles); - files[nfiles] = SharedFileSetOpen(fileset, segment_name, mode); + FileSetSegmentName(segment_name, name, nfiles); + files[nfiles] = FileSetOpen(fileset, segment_name, mode); if (files[nfiles] <= 0) break; ++nfiles; @@ -333,18 +333,18 @@ BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) } /* - * Delete a BufFile that was created by BufFileCreateShared in the given - * SharedFileSet using the given name. + * Delete a BufFile that was created by BufFileCreateFileSet in the given + * FileSet using the given name. * * It is not necessary to delete files explicitly with this function. It is * provided only as a way to delete files proactively, rather than waiting for - * the SharedFileSet to be cleaned up. + * the FileSet to be cleaned up. * * Only one backend should attempt to delete a given name, and should know * that it exists and has been exported or closed. */ void -BufFileDeleteShared(SharedFileSet *fileset, const char *name) +BufFileDeleteFileSet(FileSet *fileset, const char *name) { char segment_name[MAXPGPATH]; int segment = 0; @@ -357,8 +357,8 @@ BufFileDeleteShared(SharedFileSet *fileset, const char *name) */ for (;;) { - SharedSegmentName(segment_name, name, segment); - if (!SharedFileSetDelete(fileset, segment_name, true)) + FileSetSegmentName(segment_name, name, segment); + if (!FileSetDelete(fileset, segment_name, true)) break; found = true; ++segment; @@ -367,16 +367,16 @@ BufFileDeleteShared(SharedFileSet *fileset, const char *name) } if (!found) - elog(ERROR, "could not delete unknown shared BufFile \"%s\"", name); + elog(ERROR, "could not delete unknown BufFile \"%s\"", name); } /* - * BufFileExportShared --- flush and make read-only, in preparation for sharing. + * BufFileExportFileSet --- flush and make read-only, in preparation for sharing. */ void -BufFileExportShared(BufFile *file) +BufFileExportFileSet(BufFile *file) { - /* Must be a file belonging to a SharedFileSet. */ + /* Must be a file belonging to a FileSet. */ Assert(file->fileset != NULL); /* It's probably a bug if someone calls this twice. */ @@ -785,7 +785,7 @@ BufFileTellBlock(BufFile *file) #endif /* - * Return the current shared BufFile size. + * Return the current fileset based BufFile size. * * Counts any holes left behind by BufFileAppend as part of the size. * ereport()s on failure. @@ -811,8 +811,8 @@ BufFileSize(BufFile *file) } /* - * Append the contents of source file (managed within shared fileset) to - * end of target file (managed within same shared fileset). + * Append the contents of source file (managed within fileset) to + * end of target file (managed within same fileset). * * Note that operation subsumes ownership of underlying resources from * "source". Caller should never call BufFileClose against source having @@ -854,11 +854,11 @@ BufFileAppend(BufFile *target, BufFile *source) } /* - * Truncate a BufFile created by BufFileCreateShared up to the given fileno and - * the offset. + * Truncate a BufFile created by BufFileCreateFileSet up to the given fileno + * and the offset. */ void -BufFileTruncateShared(BufFile *file, int fileno, off_t offset) +BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset) { int numFiles = file->numFiles; int newFile = fileno; @@ -876,12 +876,12 @@ BufFileTruncateShared(BufFile *file, int fileno, off_t offset) { if ((i != fileno || offset == 0) && i != 0) { - SharedSegmentName(segment_name, file->name, i); + FileSetSegmentName(segment_name, file->name, i); FileClose(file->files[i]); - if (!SharedFileSetDelete(file->fileset, segment_name, true)) + if (!FileSetDelete(file->fileset, segment_name, true)) ereport(ERROR, (errcode_for_file_access(), - errmsg("could not delete shared fileset \"%s\": %m", + errmsg("could not delete fileset \"%s\": %m", segment_name))); numFiles--; newOffset = MAX_PHYSICAL_FILESIZE; diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c index b58b399..433e283 100644 --- a/src/backend/storage/file/fd.c +++ b/src/backend/storage/file/fd.c @@ -1921,7 +1921,7 @@ PathNameDeleteTemporaryFile(const char *path, bool error_on_failure) /* * Unlike FileClose's automatic file deletion code, we tolerate - * non-existence to support BufFileDeleteShared which doesn't know how + * non-existence to support BufFileDeleteFileSet which doesn't know how * many segments it has to delete until it runs out. */ if (stat_errno == ENOENT) diff --git a/src/backend/storage/file/fileset.c b/src/backend/storage/file/fileset.c new file mode 100644 index 0000000..282ff12 --- /dev/null +++ b/src/backend/storage/file/fileset.c @@ -0,0 +1,205 @@ +/*------------------------------------------------------------------------- + * + * fileset.c + * Management of named temporary files. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/backend/storage/file/fileset.c + * + * FileSets provide a temporary namespace (think directory) so that files can + * be discovered by name. + * + * FileSets can be used by backends when the temporary files need to be + * opened/closed multiple times and the underlying files need to survive across + * transactions. + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include <limits.h> + +#include "catalog/pg_tablespace.h" +#include "commands/tablespace.h" +#include "common/hashfn.h" +#include "miscadmin.h" +#include "storage/ipc.h" +#include "storage/fileset.h" +#include "utils/builtins.h" + +static void FileSetPath(char *path, FileSet *fileset, Oid tablespace); +static void FilePath(char *path, FileSet *fileset, const char *name); +static Oid ChooseTablespace(const FileSet *fileset, const char *name); + +/* + * Initialize a space for temporary files. This API can be used by shared + * fileset as well as if the temporary files are used only by single backend + * but the files need to be opened and closed multiple times and also the + * underlying files need to survive across transactions. + * + * The callers are expected to explicitly remove such files by using + * FileSetDelete/FileSetDeleteAll. + * + * Files will be distributed over the tablespaces configured in + * temp_tablespaces. + * + * Under the covers the set is one or more directories which will eventually + * be deleted. + */ +void +FileSetInit(FileSet *fileset) +{ + static uint32 counter = 0; + + fileset->creator_pid = MyProcPid; + fileset->number = counter; + counter = (counter + 1) % INT_MAX; + + /* Capture the tablespace OIDs so that all backends agree on them. */ + PrepareTempTablespaces(); + fileset->ntablespaces = + GetTempTablespaces(&fileset->tablespaces[0], + lengthof(fileset->tablespaces)); + if (fileset->ntablespaces == 0) + { + /* If the GUC is empty, use current database's default tablespace */ + fileset->tablespaces[0] = MyDatabaseTableSpace; + fileset->ntablespaces = 1; + } + else + { + int i; + + /* + * An entry of InvalidOid means use the default tablespace for the + * current database. Replace that now, to be sure that all users of + * the FileSet agree on what to do. + */ + for (i = 0; i < fileset->ntablespaces; i++) + { + if (fileset->tablespaces[i] == InvalidOid) + fileset->tablespaces[i] = MyDatabaseTableSpace; + } + } +} + +/* + * Create a new file in the given set. + */ +File +FileSetCreate(FileSet *fileset, const char *name) +{ + char path[MAXPGPATH]; + File file; + + FilePath(path, fileset, name); + file = PathNameCreateTemporaryFile(path, false); + + /* If we failed, see if we need to create the directory on demand. */ + if (file <= 0) + { + char tempdirpath[MAXPGPATH]; + char filesetpath[MAXPGPATH]; + Oid tablespace = ChooseTablespace(fileset, name); + + TempTablespacePath(tempdirpath, tablespace); + FileSetPath(filesetpath, fileset, tablespace); + PathNameCreateTemporaryDir(tempdirpath, filesetpath); + file = PathNameCreateTemporaryFile(path, true); + } + + return file; +} + +/* + * Open a file that was created with FileSetCreate() */ +File +FileSetOpen(FileSet *fileset, const char *name, int mode) +{ + char path[MAXPGPATH]; + File file; + + FilePath(path, fileset, name); + file = PathNameOpenTemporaryFile(path, mode); + + return file; +} + +/* + * Delete a file that was created with FileSetCreate(). + * + * Return true if the file existed, false if didn't. + */ +bool +FileSetDelete(FileSet *fileset, const char *name, + bool error_on_failure) +{ + char path[MAXPGPATH]; + + FilePath(path, fileset, name); + + return PathNameDeleteTemporaryFile(path, error_on_failure); +} + +/* + * Delete all files in the set. + */ +void +FileSetDeleteAll(FileSet *fileset) +{ + char dirpath[MAXPGPATH]; + int i; + + /* + * Delete the directory we created in each tablespace. Doesn't fail + * because we use this in error cleanup paths, but can generate LOG + * message on IO error. + */ + for (i = 0; i < fileset->ntablespaces; ++i) + { + FileSetPath(dirpath, fileset, fileset->tablespaces[i]); + PathNameDeleteTemporaryDir(dirpath); + } +} + +/* + * Build the path for the directory holding the files backing a FileSet in a + * given tablespace. + */ +static void +FileSetPath(char *path, FileSet *fileset, Oid tablespace) +{ + char tempdirpath[MAXPGPATH]; + + TempTablespacePath(tempdirpath, tablespace); + snprintf(path, MAXPGPATH, "%s/%s%lu.%u.fileset", + tempdirpath, PG_TEMP_FILE_PREFIX, + (unsigned long) fileset->creator_pid, fileset->number); +} + +/* + * Sorting has to determine which tablespace a given temporary file belongs in. + */ +static Oid +ChooseTablespace(const FileSet *fileset, const char *name) +{ + uint32 hash = hash_any((const unsigned char *) name, strlen(name)); + + return fileset->tablespaces[hash % fileset->ntablespaces]; +} + +/* + * Compute the full path of a file in a FileSet. + */ +static void +FilePath(char *path, FileSet *fileset, const char *name) +{ + char dirpath[MAXPGPATH]; + + FileSetPath(dirpath, fileset, ChooseTablespace(fileset, name)); + snprintf(path, MAXPGPATH, "%s/%s", dirpath, name); +} diff --git a/src/backend/storage/file/sharedfileset.c b/src/backend/storage/file/sharedfileset.c index ed37c94..6a33fac 100644 --- a/src/backend/storage/file/sharedfileset.c +++ b/src/backend/storage/file/sharedfileset.c @@ -13,10 +13,6 @@ * files can be discovered by name, and a shared ownership semantics so that * shared files survive until the last user detaches. * - * SharedFileSets can be used by backends when the temporary files need to be - * opened/closed multiple times and the underlying files need to survive across - * transactions. - * *------------------------------------------------------------------------- */ @@ -33,13 +29,7 @@ #include "storage/sharedfileset.h" #include "utils/builtins.h" -static List *filesetlist = NIL; - static void SharedFileSetOnDetach(dsm_segment *segment, Datum datum); -static void SharedFileSetDeleteOnProcExit(int status, Datum arg); -static void SharedFileSetPath(char *path, SharedFileSet *fileset, Oid tablespace); -static void SharedFilePath(char *path, SharedFileSet *fileset, const char *name); -static Oid ChooseTablespace(const SharedFileSet *fileset, const char *name); /* * Initialize a space for temporary files that can be opened by other backends. @@ -47,77 +37,22 @@ static Oid ChooseTablespace(const SharedFileSet *fileset, const char *name); * SharedFileSet with 'seg'. Any contained files will be deleted when the * last backend detaches. * - * We can also use this interface if the temporary files are used only by - * single backend but the files need to be opened and closed multiple times - * and also the underlying files need to survive across transactions. For - * such cases, dsm segment 'seg' should be passed as NULL. Callers are - * expected to explicitly remove such files by using SharedFileSetDelete/ - * SharedFileSetDeleteAll or we remove such files on proc exit. - * - * Files will be distributed over the tablespaces configured in - * temp_tablespaces. - * * Under the covers the set is one or more directories which will eventually * be deleted. */ void SharedFileSetInit(SharedFileSet *fileset, dsm_segment *seg) { - static uint32 counter = 0; - + /* Initialize the shared fileset specific members. */ SpinLockInit(&fileset->mutex); fileset->refcnt = 1; - fileset->creator_pid = MyProcPid; - fileset->number = counter; - counter = (counter + 1) % INT_MAX; - - /* Capture the tablespace OIDs so that all backends agree on them. */ - PrepareTempTablespaces(); - fileset->ntablespaces = - GetTempTablespaces(&fileset->tablespaces[0], - lengthof(fileset->tablespaces)); - if (fileset->ntablespaces == 0) - { - /* If the GUC is empty, use current database's default tablespace */ - fileset->tablespaces[0] = MyDatabaseTableSpace; - fileset->ntablespaces = 1; - } - else - { - int i; - /* - * An entry of InvalidOid means use the default tablespace for the - * current database. Replace that now, to be sure that all users of - * the SharedFileSet agree on what to do. - */ - for (i = 0; i < fileset->ntablespaces; i++) - { - if (fileset->tablespaces[i] == InvalidOid) - fileset->tablespaces[i] = MyDatabaseTableSpace; - } - } + /* Initialize the fileset. */ + FileSetInit(&fileset->fs); /* Register our cleanup callback. */ if (seg) on_dsm_detach(seg, SharedFileSetOnDetach, PointerGetDatum(fileset)); - else - { - static bool registered_cleanup = false; - - if (!registered_cleanup) - { - /* - * We must not have registered any fileset before registering the - * fileset clean up. - */ - Assert(filesetlist == NIL); - on_proc_exit(SharedFileSetDeleteOnProcExit, 0); - registered_cleanup = true; - } - - filesetlist = lcons((void *) fileset, filesetlist); - } } /* @@ -148,86 +83,12 @@ SharedFileSetAttach(SharedFileSet *fileset, dsm_segment *seg) } /* - * Create a new file in the given set. - */ -File -SharedFileSetCreate(SharedFileSet *fileset, const char *name) -{ - char path[MAXPGPATH]; - File file; - - SharedFilePath(path, fileset, name); - file = PathNameCreateTemporaryFile(path, false); - - /* If we failed, see if we need to create the directory on demand. */ - if (file <= 0) - { - char tempdirpath[MAXPGPATH]; - char filesetpath[MAXPGPATH]; - Oid tablespace = ChooseTablespace(fileset, name); - - TempTablespacePath(tempdirpath, tablespace); - SharedFileSetPath(filesetpath, fileset, tablespace); - PathNameCreateTemporaryDir(tempdirpath, filesetpath); - file = PathNameCreateTemporaryFile(path, true); - } - - return file; -} - -/* - * Open a file that was created with SharedFileSetCreate(), possibly in - * another backend. - */ -File -SharedFileSetOpen(SharedFileSet *fileset, const char *name, int mode) -{ - char path[MAXPGPATH]; - File file; - - SharedFilePath(path, fileset, name); - file = PathNameOpenTemporaryFile(path, mode); - - return file; -} - -/* - * Delete a file that was created with SharedFileSetCreate(). - * Return true if the file existed, false if didn't. - */ -bool -SharedFileSetDelete(SharedFileSet *fileset, const char *name, - bool error_on_failure) -{ - char path[MAXPGPATH]; - - SharedFilePath(path, fileset, name); - - return PathNameDeleteTemporaryFile(path, error_on_failure); -} - -/* * Delete all files in the set. */ void SharedFileSetDeleteAll(SharedFileSet *fileset) { - char dirpath[MAXPGPATH]; - int i; - - /* - * Delete the directory we created in each tablespace. Doesn't fail - * because we use this in error cleanup paths, but can generate LOG - * message on IO error. - */ - for (i = 0; i < fileset->ntablespaces; ++i) - { - SharedFileSetPath(dirpath, fileset, fileset->tablespaces[i]); - PathNameDeleteTemporaryDir(dirpath); - } - - /* Unregister the shared fileset */ - SharedFileSetUnregister(fileset); + FileSetDeleteAll(&fileset->fs); } /* @@ -255,100 +116,5 @@ SharedFileSetOnDetach(dsm_segment *segment, Datum datum) * this function so we can safely access its data. */ if (unlink_all) - SharedFileSetDeleteAll(fileset); -} - -/* - * Callback function that will be invoked on the process exit. This will - * process the list of all the registered sharedfilesets and delete the - * underlying files. - */ -static void -SharedFileSetDeleteOnProcExit(int status, Datum arg) -{ - /* - * Remove all the pending shared fileset entries. We don't use foreach() - * here because SharedFileSetDeleteAll will remove the current element in - * filesetlist. Though we have used foreach_delete_current() to remove the - * element from filesetlist it could only fix up the state of one of the - * loops, see SharedFileSetUnregister. - */ - while (list_length(filesetlist) > 0) - { - SharedFileSet *fileset = (SharedFileSet *) linitial(filesetlist); - - SharedFileSetDeleteAll(fileset); - } - - filesetlist = NIL; -} - -/* - * Unregister the shared fileset entry registered for cleanup on proc exit. - */ -void -SharedFileSetUnregister(SharedFileSet *input_fileset) -{ - ListCell *l; - - /* - * If the caller is following the dsm based cleanup then we don't maintain - * the filesetlist so return. - */ - if (filesetlist == NIL) - return; - - foreach(l, filesetlist) - { - SharedFileSet *fileset = (SharedFileSet *) lfirst(l); - - /* Remove the entry from the list */ - if (input_fileset == fileset) - { - filesetlist = foreach_delete_current(filesetlist, l); - return; - } - } - - /* Should have found a match */ - Assert(false); -} - -/* - * Build the path for the directory holding the files backing a SharedFileSet - * in a given tablespace. - */ -static void -SharedFileSetPath(char *path, SharedFileSet *fileset, Oid tablespace) -{ - char tempdirpath[MAXPGPATH]; - - TempTablespacePath(tempdirpath, tablespace); - snprintf(path, MAXPGPATH, "%s/%s%lu.%u.sharedfileset", - tempdirpath, PG_TEMP_FILE_PREFIX, - (unsigned long) fileset->creator_pid, fileset->number); -} - -/* - * Sorting hat to determine which tablespace a given shared temporary file - * belongs in. - */ -static Oid -ChooseTablespace(const SharedFileSet *fileset, const char *name) -{ - uint32 hash = hash_any((const unsigned char *) name, strlen(name)); - - return fileset->tablespaces[hash % fileset->ntablespaces]; -} - -/* - * Compute the full path of a file in a SharedFileSet. - */ -static void -SharedFilePath(char *path, SharedFileSet *fileset, const char *name) -{ - char dirpath[MAXPGPATH]; - - SharedFileSetPath(dirpath, fileset, ChooseTablespace(fileset, name)); - snprintf(path, MAXPGPATH, "%s/%s", dirpath, name); + FileSetDeleteAll(&fileset->fs); } diff --git a/src/backend/utils/sort/logtape.c b/src/backend/utils/sort/logtape.c index cafc087..f7994d7 100644 --- a/src/backend/utils/sort/logtape.c +++ b/src/backend/utils/sort/logtape.c @@ -564,7 +564,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, lt = &lts->tapes[i]; pg_itoa(i, filename); - file = BufFileOpenShared(fileset, filename, O_RDONLY); + file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY); filesize = BufFileSize(file); /* @@ -610,7 +610,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, * offset). * * The only thing that currently prevents writing to the leader tape from - * working is the fact that BufFiles opened using BufFileOpenShared() are + * working is the fact that BufFiles opened using BufFileOpenFileSet() are * read-only by definition, but that could be changed if it seemed * worthwhile. For now, writing to the leader tape will raise a "Bad file * descriptor" error, so tuplesort must avoid writing to the leader tape @@ -722,7 +722,7 @@ LogicalTapeSetCreate(int ntapes, bool preallocate, TapeShare *shared, char filename[MAXPGPATH]; pg_itoa(worker, filename); - lts->pfile = BufFileCreateShared(fileset, filename); + lts->pfile = BufFileCreateFileSet(&fileset->fs, filename); } else lts->pfile = BufFileCreateTemp(false); @@ -1096,7 +1096,7 @@ LogicalTapeFreeze(LogicalTapeSet *lts, int tapenum, TapeShare *share) /* Handle extra steps when caller is to share its tapeset */ if (share) { - BufFileExportShared(lts->pfile); + BufFileExportFileSet(lts->pfile); share->firstblocknumber = lt->firstBlockNumber; } } diff --git a/src/backend/utils/sort/sharedtuplestore.c b/src/backend/utils/sort/sharedtuplestore.c index 57e35db..504ef1c 100644 --- a/src/backend/utils/sort/sharedtuplestore.c +++ b/src/backend/utils/sort/sharedtuplestore.c @@ -310,7 +310,8 @@ sts_puttuple(SharedTuplestoreAccessor *accessor, void *meta_data, /* Create one. Only this backend will write into it. */ sts_filename(name, accessor, accessor->participant); - accessor->write_file = BufFileCreateShared(accessor->fileset, name); + accessor->write_file = + BufFileCreateFileSet(&accessor->fileset->fs, name); /* Set up the shared state for this backend's file. */ participant = &accessor->sts->participants[accessor->participant]; @@ -559,7 +560,7 @@ sts_parallel_scan_next(SharedTuplestoreAccessor *accessor, void *meta_data) sts_filename(name, accessor, accessor->read_participant); accessor->read_file = - BufFileOpenShared(accessor->fileset, name, O_RDONLY); + BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY); } /* Seek and load the chunk header. */ diff --git a/src/include/replication/worker_internal.h b/src/include/replication/worker_internal.h index 41c7487..a6c9d4e 100644 --- a/src/include/replication/worker_internal.h +++ b/src/include/replication/worker_internal.h @@ -79,6 +79,7 @@ extern void logicalrep_worker_launch(Oid dbid, Oid subid, const char *subname, extern void logicalrep_worker_stop(Oid subid, Oid relid); extern void logicalrep_worker_wakeup(Oid subid, Oid relid); extern void logicalrep_worker_wakeup_ptr(LogicalRepWorker *worker); +extern void logicalrep_worker_cleanupfileset(void); extern int logicalrep_sync_worker_count(Oid subid); diff --git a/src/include/storage/buffile.h b/src/include/storage/buffile.h index 566523d..143eada 100644 --- a/src/include/storage/buffile.h +++ b/src/include/storage/buffile.h @@ -26,7 +26,7 @@ #ifndef BUFFILE_H #define BUFFILE_H -#include "storage/sharedfileset.h" +#include "storage/fileset.h" /* BufFile is an opaque type whose details are not known outside buffile.c. */ @@ -46,11 +46,11 @@ extern int BufFileSeekBlock(BufFile *file, long blknum); extern int64 BufFileSize(BufFile *file); extern long BufFileAppend(BufFile *target, BufFile *source); -extern BufFile *BufFileCreateShared(SharedFileSet *fileset, const char *name); -extern void BufFileExportShared(BufFile *file); -extern BufFile *BufFileOpenShared(SharedFileSet *fileset, const char *name, - int mode); -extern void BufFileDeleteShared(SharedFileSet *fileset, const char *name); -extern void BufFileTruncateShared(BufFile *file, int fileno, off_t offset); +extern BufFile *BufFileCreateFileSet(FileSet *fileset, const char *name); +extern void BufFileExportFileSet(BufFile *file); +extern BufFile *BufFileOpenFileSet(FileSet *fileset, const char *name, + int mode); +extern void BufFileDeleteFileSet(FileSet *fileset, const char *name); +extern void BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset); #endif /* BUFFILE_H */ diff --git a/src/include/storage/fileset.h b/src/include/storage/fileset.h new file mode 100644 index 0000000..be0e097 --- /dev/null +++ b/src/include/storage/fileset.h @@ -0,0 +1,40 @@ +/*------------------------------------------------------------------------- + * + * fileset.h + * Management of named temporary files. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/storage/fileset.h + * + *------------------------------------------------------------------------- + */ + +#ifndef FILESET_H +#define FILESET_H + +#include "storage/fd.h" + +/* + * A set of temporary files. + */ +typedef struct FileSet +{ + pid_t creator_pid; /* PID of the creating process */ + uint32 number; /* per-PID identifier */ + int ntablespaces; /* number of tablespaces to use */ + Oid tablespaces[8]; /* OIDs of tablespaces to use. Assumes that + * it's rare that there more than temp + * tablespaces. */ +} FileSet; + +extern void FileSetInit(FileSet *fileset); +extern File FileSetCreate(FileSet *fileset, const char *name); +extern File FileSetOpen(FileSet *fileset, const char *name, + int mode); +extern bool FileSetDelete(FileSet *fileset, const char *name, + bool error_on_failure); +extern void FileSetDeleteAll(FileSet *fileset); + +#endif diff --git a/src/include/storage/sharedfileset.h b/src/include/storage/sharedfileset.h index 09ba121..59becfb 100644 --- a/src/include/storage/sharedfileset.h +++ b/src/include/storage/sharedfileset.h @@ -17,6 +17,7 @@ #include "storage/dsm.h" #include "storage/fd.h" +#include "storage/fileset.h" #include "storage/spin.h" /* @@ -24,24 +25,13 @@ */ typedef struct SharedFileSet { - pid_t creator_pid; /* PID of the creating process */ - uint32 number; /* per-PID identifier */ + FileSet fs; slock_t mutex; /* mutex protecting the reference count */ int refcnt; /* number of attached backends */ - int ntablespaces; /* number of tablespaces to use */ - Oid tablespaces[8]; /* OIDs of tablespaces to use. Assumes that - * it's rare that there more than temp - * tablespaces. */ } SharedFileSet; extern void SharedFileSetInit(SharedFileSet *fileset, dsm_segment *seg); extern void SharedFileSetAttach(SharedFileSet *fileset, dsm_segment *seg); -extern File SharedFileSetCreate(SharedFileSet *fileset, const char *name); -extern File SharedFileSetOpen(SharedFileSet *fileset, const char *name, - int mode); -extern bool SharedFileSetDelete(SharedFileSet *fileset, const char *name, - bool error_on_failure); extern void SharedFileSetDeleteAll(SharedFileSet *fileset); -extern void SharedFileSetUnregister(SharedFileSet *input_fileset); #endif diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 37cf4b2..4770740 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -708,6 +708,7 @@ File FileFdwExecutionState FileFdwPlanState FileNameMap +FileSet FileTag FinalPathExtraData FindColsContext -- 1.8.3.1
v5-0002-Using-fileset-more-effectively-in-the-apply-worke.patch (text/x-patch, 18.8K) download From d879f4046f5d98d1409fa686e46863ce25c37dd2 Mon Sep 17 00:00:00 2001 From: Dilip Kumar <dilipkumar@localhost.localdomain> Date: Thu, 26 Aug 2021 09:42:36 +0530 Subject: [PATCH v5 2/2] Using fileset more effectively in the apply worker MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Do not use separate file sets for each xid, instead use one fileset for the worker's entire lifetime.  Now, the changes/subxacts files for every streaming transaction will be created under the same fileset and the files will be deleted after the transaction is completed. The fileset will be there until the worker exit. --- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/worker.c | 249 ++++++----------------------- src/backend/storage/file/buffile.c | 23 ++- src/backend/utils/sort/logtape.c | 2 +- src/backend/utils/sort/sharedtuplestore.c | 3 +- src/include/storage/buffile.h | 5 +- 6 files changed, 75 insertions(+), 209 deletions(-) diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 8b1772d..644a9c2 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -648,7 +648,7 @@ logicalrep_worker_onexit(int code, Datum arg) logicalrep_worker_detach(); - /* Cleanup filesets used for streaming transactions. */ + /* Cleanup fileset used for streaming transactions. */ logicalrep_worker_cleanupfileset(); ApplyLauncherWakeup(); diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index 6adc6ddd..eda71b6 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -221,20 +221,6 @@ typedef struct ApplyExecutionData PartitionTupleRouting *proute; /* partition routing info */ } ApplyExecutionData; -/* - * Stream xid hash entry. Whenever we see a new xid we create this entry in the - * xidhash and along with it create the streaming file and store the fileset handle. - * The subxact file is created iff there is any subxact info under this xid. This - * entry is used on the subsequent streams for the xid to get the corresponding - * fileset handles, so storing them in hash makes the search faster. - */ -typedef struct StreamXidHash -{ - TransactionId xid; /* xid is the hash key and must be first */ - FileSet *stream_fileset; /* file set for stream data */ - FileSet *subxact_fileset; /* file set for subxact info */ -} StreamXidHash; - static MemoryContext ApplyMessageContext = NULL; MemoryContext ApplyContext = NULL; @@ -255,10 +241,13 @@ static bool in_streamed_transaction = false; static TransactionId stream_xid = InvalidTransactionId; /* - * Hash table for storing the streaming xid information along with filesets - * for streaming and subxact files. + * The fileset is used by the worker to create the changes and subxact files + * for the streaming transaction. Upon the arrival of the first streaming + * transaction, the fileset will be initialized, and it will be deleted when + * the worker exits. Under this, separate buffiles would be created for each + * transaction and would be deleted after the transaction is completed. */ -static HTAB *xidhash = NULL; +static FileSet *stream_fileset = NULL; /* BufFile handle of the current streaming file */ static BufFile *stream_fd = NULL; @@ -1129,7 +1118,6 @@ static void apply_handle_stream_start(StringInfo s) { bool first_segment; - HASHCTL hash_ctl; if (in_streamed_transaction) ereport(ERROR, @@ -1157,17 +1145,20 @@ apply_handle_stream_start(StringInfo s) errmsg_internal("invalid transaction ID in streamed replication transaction"))); /* - * Initialize the xidhash table if we haven't yet. This will be used for + * Initialize the stream_fileset if we haven't yet. This will be used for * the entire duration of the apply worker so create it in permanent * context. */ - if (xidhash == NULL) + if (stream_fileset == NULL) { - hash_ctl.keysize = sizeof(TransactionId); - hash_ctl.entrysize = sizeof(StreamXidHash); - hash_ctl.hcxt = ApplyContext; - xidhash = hash_create("StreamXidHash", 1024, &hash_ctl, - HASH_ELEM | HASH_BLOBS | HASH_CONTEXT); + MemoryContext oldctx; + + oldctx = MemoryContextSwitchTo(ApplyContext); + + stream_fileset = palloc(sizeof(FileSet)); + FileSetInit(stream_fileset); + + MemoryContextSwitchTo(oldctx); } /* open the spool file for this transaction */ @@ -1258,7 +1249,6 @@ apply_handle_stream_abort(StringInfo s) BufFile *fd; bool found = false; char path[MAXPGPATH]; - StreamXidHash *ent; subidx = -1; begin_replication_step(); @@ -1287,19 +1277,9 @@ apply_handle_stream_abort(StringInfo s) return; } - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* open the changes file */ changes_filename(path, MyLogicalRepWorker->subid, xid); - fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(stream_fileset, path, O_RDWR, false); /* OK, truncate the file at the right offset */ BufFileTruncateFileSet(fd, subxact_data.subxacts[subidx].fileno, @@ -1327,7 +1307,6 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) int nchanges; char path[MAXPGPATH]; char *buffer = NULL; - StreamXidHash *ent; MemoryContext oldcxt; BufFile *fd; @@ -1345,17 +1324,7 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) changes_filename(path, MyLogicalRepWorker->subid, xid); elog(DEBUG1, "replaying changes from file \"%s\"", path); - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - - fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(stream_fileset, path, O_RDONLY, false); buffer = palloc(BLCKSZ); initStringInfo(&s2); @@ -2509,27 +2478,14 @@ UpdateWorkerStats(XLogRecPtr last_lsn, TimestampTz send_time, bool reply) } /* - * Cleanup filesets. + * Cleanup fileset. */ void -logicalrep_worker_cleanupfileset(void) +logicalrep_worker_cleanupfileset() { - HASH_SEQ_STATUS status; - StreamXidHash *hentry; - - /* Remove all the pending stream and subxact filesets. */ - if (xidhash) - { - hash_seq_init(&status, xidhash); - while ((hentry = (StreamXidHash *) hash_seq_search(&status)) != NULL) - { - FileSetDeleteAll(hentry->stream_fileset); - - /* Delete the subxact fileset iff it is created. */ - if (hentry->subxact_fileset) - FileSetDeleteAll(hentry->subxact_fileset); - } - } + /* If the fileset is created, clean the underlying files. */ + if (stream_fileset != NULL) + FileSetDeleteAll(stream_fileset); } /* @@ -2981,58 +2937,29 @@ subxact_info_write(Oid subid, TransactionId xid) { char path[MAXPGPATH]; Size len; - StreamXidHash *ent; BufFile *fd; Assert(TransactionIdIsValid(xid)); - /* Find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - /* By this time we must have created the transaction entry */ - Assert(ent); + /* Get the subxact filename. */ + subxact_filename(path, subid, xid); /* - * If there is no subtransaction then nothing to do, but if already have - * subxact file then delete that. + * If there are no subtransactions, there is nothing to be done, but if + * subxacts already exist, delete it. */ if (subxact_data.nsubxacts == 0) { - if (ent->subxact_fileset) - { - cleanup_subxact_info(); - FileSetDeleteAll(ent->subxact_fileset); - pfree(ent->subxact_fileset); - ent->subxact_fileset = NULL; - } + cleanup_subxact_info(); + BufFileDeleteFileSet(stream_fileset, path, true); + return; } - subxact_filename(path, subid, xid); - - /* - * Create the subxact file if it not already created, otherwise open the - * existing file. - */ - if (ent->subxact_fileset == NULL) - { - MemoryContext oldctx; - - /* - * We need to maintain fileset across multiple stream start/stop - * calls. So, need to allocate it in a persistent context. - */ - oldctx = MemoryContextSwitchTo(ApplyContext); - ent->subxact_fileset = palloc(sizeof(FileSet)); - FileSetInit(ent->subxact_fileset); - MemoryContextSwitchTo(oldctx); - - fd = BufFileCreateFileSet(ent->subxact_fileset, path); - } - else - fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDWR); + /* Open the subxact file, if it does not exist, create it. */ + fd = BufFileOpenFileSet(stream_fileset, path, O_RDWR, true); + if (fd == NULL) + fd = BufFileCreateFileSet(stream_fileset, path); len = sizeof(SubXactInfo) * subxact_data.nsubxacts; @@ -3059,34 +2986,20 @@ subxact_info_read(Oid subid, TransactionId xid) char path[MAXPGPATH]; Size len; BufFile *fd; - StreamXidHash *ent; MemoryContext oldctx; Assert(!subxact_data.subxacts); Assert(subxact_data.nsubxacts == 0); Assert(subxact_data.nsubxacts_max == 0); - /* Find the stream xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* - * If subxact_fileset is not valid that mean we don't have any subxact - * info + * Open the subxact file for the input streaming xid, just return if the + * file does not exist. */ - if (ent->subxact_fileset == NULL) - return; - subxact_filename(path, subid, xid); - - fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(stream_fileset, path, O_RDONLY, true); + if (fd == NULL) + return; /* read number of subxact items */ if (BufFileRead(fd, &subxact_data.nsubxacts, @@ -3222,42 +3135,20 @@ changes_filename(char *path, Oid subid, TransactionId xid) * Cleanup files for a subscription / toplevel transaction. * * Remove files with serialized changes and subxact info for a particular - * toplevel transaction. Each subscription has a separate set of files. + * toplevel transaction. Each subscription has a separate files. */ static void stream_cleanup_files(Oid subid, TransactionId xid) { char path[MAXPGPATH]; - StreamXidHash *ent; - - /* Find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* Delete the change file and release the stream fileset memory */ + /* Delete the changes file. */ changes_filename(path, subid, xid); - FileSetDeleteAll(ent->stream_fileset); - pfree(ent->stream_fileset); - ent->stream_fileset = NULL; + BufFileDeleteFileSet(stream_fileset, path, false); - /* Delete the subxact file and release the memory, if it exist */ - if (ent->subxact_fileset) - { - subxact_filename(path, subid, xid); - FileSetDeleteAll(ent->subxact_fileset); - pfree(ent->subxact_fileset); - ent->subxact_fileset = NULL; - } - - /* Remove the xid entry from the stream xid hash */ - hash_search(xidhash, (void *) &xid, HASH_REMOVE, NULL); + /* Delete the subxact file, if it exist. */ + subxact_filename(path, subid, xid); + BufFileDeleteFileSet(stream_fileset, path, true); } /* @@ -3267,8 +3158,8 @@ stream_cleanup_files(Oid subid, TransactionId xid) * * Open a file for streamed changes from a toplevel transaction identified * by stream_xid (global variable). If it's the first chunk of streamed - * changes for this transaction, initialize the fileset and create the buffile, - * otherwise open the previously created file. + * changes for this transaction, create the buffile, otherwise open the + * previously created file. * * This can only be called at the beginning of a "streaming" block, i.e. * between stream_start/stream_stop messages from the upstream. @@ -3277,20 +3168,13 @@ static void stream_open_file(Oid subid, TransactionId xid, bool first_segment) { char path[MAXPGPATH]; - bool found; MemoryContext oldcxt; - StreamXidHash *ent; Assert(in_streamed_transaction); Assert(OidIsValid(subid)); Assert(TransactionIdIsValid(xid)); Assert(stream_fd == NULL); - /* create or find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_ENTER, - &found); changes_filename(path, subid, xid); elog(DEBUG1, "opening file \"%s\" for streamed changes", path); @@ -3302,49 +3186,18 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) oldcxt = MemoryContextSwitchTo(LogicalStreamingContext); /* - * If this is the first streamed segment, the file must not exist, so make - * sure we're the ones creating it. Otherwise just open the file for - * writing, in append mode. + * If this is the first streamed segment, create the changes file. + * Otherwise, just open it file for writing, in append mode. */ if (first_segment) - { - MemoryContext savectx; - FileSet *fileset; - - if (found) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); - - /* - * We need to maintain fileset across multiple stream start/stop - * calls. So, need to allocate it in a persistent context. - */ - savectx = MemoryContextSwitchTo(ApplyContext); - fileset = palloc(sizeof(FileSet)); - - FileSetInit(fileset); - MemoryContextSwitchTo(savectx); - - stream_fd = BufFileCreateFileSet(fileset, path); - - /* Remember the fileset for the next stream of the same transaction */ - ent->xid = xid; - ent->stream_fileset = fileset; - ent->subxact_fileset = NULL; - } + stream_fd = BufFileCreateFileSet(stream_fileset, path); else { - if (!found) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); - /* * Open the file and seek to the end of the file because we always * append the changes file. */ - stream_fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); + stream_fd = BufFileOpenFileSet(stream_fileset, path, O_RDWR, false); BufFileSeek(stream_fd, 0, 0, SEEK_END); } diff --git a/src/backend/storage/file/buffile.c b/src/backend/storage/file/buffile.c index 5e5409d..d96b25d 100644 --- a/src/backend/storage/file/buffile.c +++ b/src/backend/storage/file/buffile.c @@ -278,10 +278,12 @@ BufFileCreateFileSet(FileSet *fileset, const char *name) * with BufFileCreateFileSet in the same FileSet using the same name. * The backend that created the file must have called BufFileClose() or * BufFileExportFileSet() to make sure that it is ready to be opened by other - * backends and render it read-only. + * backends and render it read-only. If missing_ok is true, it will return + * NULL if the file does not exist otherwise, it will throw an error. */ BufFile * -BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) +BufFileOpenFileSet(FileSet *fileset, const char *name, int mode, + bool missing_ok) { BufFile *file; char segment_name[MAXPGPATH]; @@ -318,10 +320,18 @@ BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) * name. */ if (nfiles == 0) + { + /* free the memory */ + pfree(files); + + if (missing_ok) + return NULL; + ereport(ERROR, (errcode_for_file_access(), errmsg("could not open temporary file \"%s\" from BufFile \"%s\": %m", segment_name, name))); + } file = makeBufFileCommon(nfiles); file->files = files; @@ -341,10 +351,11 @@ BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) * the FileSet to be cleaned up. * * Only one backend should attempt to delete a given name, and should know - * that it exists and has been exported or closed. + * that it exists and has been exported or closed otherwise missing_ok should + * be passed true. */ void -BufFileDeleteFileSet(FileSet *fileset, const char *name) +BufFileDeleteFileSet(FileSet *fileset, const char *name, bool missing_ok) { char segment_name[MAXPGPATH]; int segment = 0; @@ -358,7 +369,7 @@ BufFileDeleteFileSet(FileSet *fileset, const char *name) for (;;) { FileSetSegmentName(segment_name, name, segment); - if (!FileSetDelete(fileset, segment_name, true)) + if (!FileSetDelete(fileset, segment_name, !missing_ok)) break; found = true; ++segment; @@ -366,7 +377,7 @@ BufFileDeleteFileSet(FileSet *fileset, const char *name) CHECK_FOR_INTERRUPTS(); } - if (!found) + if (!found && !missing_ok) elog(ERROR, "could not delete unknown BufFile \"%s\"", name); } diff --git a/src/backend/utils/sort/logtape.c b/src/backend/utils/sort/logtape.c index f7994d7..debf12e1 100644 --- a/src/backend/utils/sort/logtape.c +++ b/src/backend/utils/sort/logtape.c @@ -564,7 +564,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, lt = &lts->tapes[i]; pg_itoa(i, filename); - file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY); + file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY, false); filesize = BufFileSize(file); /* diff --git a/src/backend/utils/sort/sharedtuplestore.c b/src/backend/utils/sort/sharedtuplestore.c index 504ef1c..033088f 100644 --- a/src/backend/utils/sort/sharedtuplestore.c +++ b/src/backend/utils/sort/sharedtuplestore.c @@ -560,7 +560,8 @@ sts_parallel_scan_next(SharedTuplestoreAccessor *accessor, void *meta_data) sts_filename(name, accessor, accessor->read_participant); accessor->read_file = - BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY); + BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY, + false); } /* Seek and load the chunk header. */ diff --git a/src/include/storage/buffile.h b/src/include/storage/buffile.h index 143eada..7ae5ea2 100644 --- a/src/include/storage/buffile.h +++ b/src/include/storage/buffile.h @@ -49,8 +49,9 @@ extern long BufFileAppend(BufFile *target, BufFile *source); extern BufFile *BufFileCreateFileSet(FileSet *fileset, const char *name); extern void BufFileExportFileSet(BufFile *file); extern BufFile *BufFileOpenFileSet(FileSet *fileset, const char *name, - int mode); -extern void BufFileDeleteFileSet(FileSet *fileset, const char *name); + int mode, bool missing_ok); +extern void BufFileDeleteFileSet(FileSet *fileset, const char *name, + bool missing_ok); extern void BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset); #endif /* BUFFILE_H */ -- 1.8.3.1
^ permalink raw reply [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
@ 2021-08-26 08:40               ` Amit Kapila <amit.kapila16@gmail.com>
  2021-08-27 05:24                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  1 sibling, 1 reply; 26+ messages in thread

From: Amit Kapila @ 2021-08-26 08:40 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Thu, Aug 26, 2021 at 11:47 AM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>
> On Wed, Aug 25, 2021 at 5:49 PM Amit Kapila <amit.kapila16@gmail.com> wrote:
>>
>> On Tue, Aug 24, 2021 at 3:55 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>> >
>> > On Tue, Aug 24, 2021 at 12:26 PM Amit Kapila <amit.kapila16@gmail.com> wrote:
>> >
>>
>> The first patch looks good to me. I have made minor changes to the
>> attached patch. The changes include: fixing compilation warning, made
>> some comment changes, ran pgindent, and few other cosmetic changes. If
>> you are fine with the attached, then kindly rebase the second patch
>> atop it.
>>
>
> The patch looks good to me,
>

Thanks, Sawada-San and Dilip for confirmation. I would like to commit
this and the second patch (the second one still needs some more
testing and review) for PG-15 as there is no bug per-se related to
this work in PG-14 but I see an argument to commit this for PG-14 to
keep the code (APIs) consistent. What do you think? Does anybody else
have any opinion on this?

Below is a summary of each of the patches for those who are not
following this closely:
Patch-1: The purpose of this patch is to refactor sharedfileset.c to
separate out fileset implementation. Basically, this moves the fileset
related implementation out of sharedfileset.c to allow its usage by
backends that don't want to share filesets among different processes.
After this split, fileset infrastructure is used by both
sharedfileset.c and worker.c for the named temporary files that
survive across transactions. This is suggested by Andres to have a
cleaner API and its usage.

Patch-2: Allow to use single fileset in worker.c (for the lifetime of
worker) instead of using a separate fileset for each remote
transaction. After this, the files to record changes for each remote
transaction will be created under the same fileset and the files will
be deleted after the transaction is completed. This is suggested by
Thomas to allow better resource usage.

-- 
With Regards,
Amit Kapila.





^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-26 08:40               ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
@ 2021-08-27 05:24                 ` Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-27 05:28                   ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  2021-08-30 01:12                   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Masahiko Sawada <sawada.mshk@gmail.com>
  0 siblings, 2 replies; 26+ messages in thread

From: Dilip Kumar @ 2021-08-27 05:24 UTC (permalink / raw)
  To: Amit Kapila <amit.kapila16@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Thu, Aug 26, 2021 at 2:10 PM Amit Kapila <amit.kapila16@gmail.com> wrote:

>
> Thanks, Sawada-San and Dilip for confirmation. I would like to commit
> this and the second patch (the second one still needs some more
> testing and review) for PG-15 as there is no bug per-se related to
> this work in PG-14 but I see an argument to commit this for PG-14 to
> keep the code (APIs) consistent. What do you think? Does anybody else
> have any opinion on this?
>
>
IMHO, this is a fair amount of refactoring and this is actually an
improvement patch so we should push it to v15.

-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com

^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-26 08:40               ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-27 05:24                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
@ 2021-08-27 05:28                   ` houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  1 sibling, 0 replies; 26+ messages in thread

From: houzj.fnst@fujitsu.com @ 2021-08-27 05:28 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>; Amit Kapila <amit.kapila16@gmail.com>

On Fri, Aug 27, 2021 1:25 PM Dilip Kumar <dilipbalaut@gmail.com>  wrote:
> On Thu, Aug 26, 2021 at 2:10 PM Amit Kapila <mailto:amit.kapila16@gmail.com> wrote:
> 
>> Thanks, Sawada-San and Dilip for confirmation. I would like to commit
>> this and the second patch (the second one still needs some more
>> testing and review) for PG-15 as there is no bug per-se related to
>> this work in PG-14 but I see an argument to commit this for PG-14 to
>> keep the code (APIs) consistent. What do you think? Does anybody else
>> have any opinion on this?

> IMHO, this is a fair amount of refactoring and this is actually an
> improvement patch so we should push it to v15.

+1

Best regards,
Hou zj


^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-26 08:40               ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-27 05:24                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
@ 2021-08-30 01:12                   ` Masahiko Sawada <sawada.mshk@gmail.com>
  2021-08-30 06:44                     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  1 sibling, 1 reply; 26+ messages in thread

From: Masahiko Sawada @ 2021-08-30 01:12 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: Amit Kapila <amit.kapila16@gmail.com>; houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Tom Lane <tgl@sss.pgh.pa.us>

On Fri, Aug 27, 2021 at 2:25 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>
> On Thu, Aug 26, 2021 at 2:10 PM Amit Kapila <amit.kapila16@gmail.com> wrote:
>>
>>
>> Thanks, Sawada-San and Dilip for confirmation. I would like to commit
>> this and the second patch (the second one still needs some more
>> testing and review) for PG-15 as there is no bug per-se related to
>> this work in PG-14 but I see an argument to commit this for PG-14 to
>> keep the code (APIs) consistent. What do you think? Does anybody else
>> have any opinion on this?
>>
>
> IMHO, this is a fair amount of refactoring and this is actually an improvement patch so we should push it to v15.

I think so too.

Regards,

--
Masahiko Sawada
EDB:  https://www.enterprisedb.com/





^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-26 08:40               ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-27 05:24                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-30 01:12                   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Masahiko Sawada <sawada.mshk@gmail.com>
@ 2021-08-30 06:44                     ` Amit Kapila <amit.kapila16@gmail.com>
  0 siblings, 0 replies; 26+ messages in thread

From: Amit Kapila @ 2021-08-30 06:44 UTC (permalink / raw)
  To: Masahiko Sawada <sawada.mshk@gmail.com>; +Cc: Dilip Kumar <dilipbalaut@gmail.com>; houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Tom Lane <tgl@sss.pgh.pa.us>

On Mon, Aug 30, 2021 at 6:42 AM Masahiko Sawada <sawada.mshk@gmail.com> wrote:
>
> On Fri, Aug 27, 2021 at 2:25 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
> >
> > On Thu, Aug 26, 2021 at 2:10 PM Amit Kapila <amit.kapila16@gmail.com> wrote:
> >>
> >>
> >> Thanks, Sawada-San and Dilip for confirmation. I would like to commit
> >> this and the second patch (the second one still needs some more
> >> testing and review) for PG-15 as there is no bug per-se related to
> >> this work in PG-14 but I see an argument to commit this for PG-14 to
> >> keep the code (APIs) consistent. What do you think? Does anybody else
> >> have any opinion on this?
> >>
> >
> > IMHO, this is a fair amount of refactoring and this is actually an improvement patch so we should push it to v15.
>
> I think so too.
>

I have pushed the first patch in this series.

-- 
With Regards,
Amit Kapila.





^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
@ 2021-08-27 05:26               ` houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  2021-08-27 06:34                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  1 sibling, 1 reply; 26+ messages in thread

From: houzj.fnst@fujitsu.com @ 2021-08-27 05:26 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>; Amit Kapila <amit.kapila16@gmail.com>

On Thu, Aug 26, 2021 2:18 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:

> The patch looks good to me, I have rebased 0002 atop
> this patch and also done some cosmetic fixes in 0002. 

Here are some comments for the 0002 patch.

1)

- * toplevel transaction. Each subscription has a separate set of files.
+ * toplevel transaction. Each subscription has a separate files.

a separate files => a separate file

2)
+	 * Otherwise, just open it file for writing, in append mode.
 	 */

open it file => open the file


3)
 	if (subxact_data.nsubxacts == 0)
 	{
-		if (ent->subxact_fileset)
-		{
-			cleanup_subxact_info();
-			FileSetDeleteAll(ent->subxact_fileset);
-			pfree(ent->subxact_fileset);
-			ent->subxact_fileset = NULL;
-		}
+		cleanup_subxact_info();
+		BufFileDeleteFileSet(stream_fileset, path, true);
+


Before applying the patch, the code only invoke cleanup_subxact_info() when the
file exists. After applying the patch, it will invoke cleanup_subxact_info()
either the file exists or not. Is it correct ?


4)
 	/*
-	 * If this is the first streamed segment, the file must not exist, so make
-	 * sure we're the ones creating it. Otherwise just open the file for
-	 * writing, in append mode.
+	 * If this is the first streamed segment, create the changes file.
+	 * Otherwise, just open it file for writing, in append mode.
 	 */
 	if (first_segment)
-	{
	...
-		if (found)
-			ereport(ERROR,
-					(errcode(ERRCODE_PROTOCOL_VIOLATION),
-					 errmsg_internal("incorrect first-segment flag for streamed replication transaction")));
	...
-	}
+		stream_fd = BufFileCreateFileSet(stream_fileset, path);


Since the function BufFileCreateFileSet() doesn't check the file's existence,
the change here seems remove the file existence check which the old code did.


Best regards,
Hou zj


^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-27 05:26               ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
@ 2021-08-27 06:34                 ` Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-30 06:15                   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Masahiko Sawada <sawada.mshk@gmail.com>
  2021-08-31 09:50                   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  0 siblings, 2 replies; 26+ messages in thread

From: Dilip Kumar @ 2021-08-27 06:34 UTC (permalink / raw)
  To: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; +Cc: Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>; Amit Kapila <amit.kapila16@gmail.com>

On Fri, Aug 27, 2021 at 10:56 AM houzj.fnst@fujitsu.com
<houzj.fnst@fujitsu.com> wrote:
>
> On Thu, Aug 26, 2021 2:18 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>
> > The patch looks good to me, I have rebased 0002 atop
> > this patch and also done some cosmetic fixes in 0002.
>
> Here are some comments for the 0002 patch.
>
> 1)
>
> - * toplevel transaction. Each subscription has a separate set of files.
> + * toplevel transaction. Each subscription has a separate files.
>
> a separate files => a separate file

Done

> 2)
> +        * Otherwise, just open it file for writing, in append mode.
>          */
>
> open it file => open the file

Done

>
> 3)
>         if (subxact_data.nsubxacts == 0)
>         {
> -               if (ent->subxact_fileset)
> -               {
> -                       cleanup_subxact_info();
> -                       FileSetDeleteAll(ent->subxact_fileset);
> -                       pfree(ent->subxact_fileset);
> -                       ent->subxact_fileset = NULL;
> -               }
> +               cleanup_subxact_info();
> +               BufFileDeleteFileSet(stream_fileset, path, true);
> +
>
> Before applying the patch, the code only invoke cleanup_subxact_info() when the
> file exists. After applying the patch, it will invoke cleanup_subxact_info()
> either the file exists or not. Is it correct ?

I think this is just structure resetting at the end of the stream.
Earlier the hash was telling us whether we have ever dirtied that
structure or not but now we are not maintaining that hash so we just
reset it at the end of the stream.  I don't think its any bad, in fact
I think this is much cheaper compared to maining the hash.

>
> 4)
>         /*
> -        * If this is the first streamed segment, the file must not exist, so make
> -        * sure we're the ones creating it. Otherwise just open the file for
> -        * writing, in append mode.
> +        * If this is the first streamed segment, create the changes file.
> +        * Otherwise, just open it file for writing, in append mode.
>          */
>         if (first_segment)
> -       {
>         ...
> -               if (found)
> -                       ereport(ERROR,
> -                                       (errcode(ERRCODE_PROTOCOL_VIOLATION),
> -                                        errmsg_internal("incorrect first-segment flag for streamed replication transaction")));
>         ...
> -       }
> +               stream_fd = BufFileCreateFileSet(stream_fileset, path);
>
>
> Since the function BufFileCreateFileSet() doesn't check the file's existence,
> the change here seems remove the file existence check which the old code did.

Not really, we were just doing a sanity check of the in memory hash
entry, now we don't maintain that so we don't need to do that.

-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com

Attachments: download all (2 files, .tar.gz)

v6-0001-Refactor-sharedfileset.c-to-separate-out-fileset-.patch (text/x-patch, 42.1K) download From dfae7d9e3ae875c8db2de792e9a95ef86fef2b00 Mon Sep 17 00:00:00 2001 From: Amit Kapila <akapila@postgresql.org> Date: Wed, 25 Aug 2021 15:00:19 +0530 Subject: [PATCH v6 1/2] Refactor sharedfileset.c to separate out fileset implementation. Move fileset related implementation out of sharedfileset.c to allow its usage by backends that don't want to share filesets among different processes. After this split, fileset infrastructure is used by both sharedfileset.c and worker.c for the named temporary files that survive across transactions. Author: Dilip Kumar, based on suggestion by Andres Freund Reviewed-by: Hou Zhijie, Masahiko Sawada, Amit Kapila Discussion: https://postgr.es/m/E1mCC6U-0004Ik-Fs@gemulon.postgresql.org --- src/backend/replication/logical/launcher.c | 3 + src/backend/replication/logical/worker.c | 82 ++++++---- src/backend/storage/file/Makefile | 1 + src/backend/storage/file/buffile.c | 84 +++++----- src/backend/storage/file/fd.c | 2 +- src/backend/storage/file/fileset.c | 205 ++++++++++++++++++++++++ src/backend/storage/file/sharedfileset.c | 244 +---------------------------- src/backend/utils/sort/logtape.c | 8 +- src/backend/utils/sort/sharedtuplestore.c | 5 +- src/include/replication/worker_internal.h | 1 + src/include/storage/buffile.h | 14 +- src/include/storage/fileset.h | 40 +++++ src/include/storage/sharedfileset.h | 14 +- src/tools/pgindent/typedefs.list | 1 + 14 files changed, 368 insertions(+), 336 deletions(-) create mode 100644 src/backend/storage/file/fileset.c create mode 100644 src/include/storage/fileset.h diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index e3b11da..8b1772d 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -648,6 +648,9 @@ logicalrep_worker_onexit(int code, Datum arg) logicalrep_worker_detach(); + /* Cleanup filesets used for streaming transactions. */ + logicalrep_worker_cleanupfileset(); + ApplyLauncherWakeup(); } diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index 295b1e0..bfb7d1a 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -39,13 +39,13 @@ * BufFile infrastructure supports temporary files that exceed the OS file size * limit, (b) provides a way for automatic clean up on the error and (c) provides * a way to survive these files across local transactions and allow to open and - * close at stream start and close. We decided to use SharedFileSet + * close at stream start and close. We decided to use FileSet * infrastructure as without that it deletes the files on the closure of the * file and if we decide to keep stream files open across the start/stop stream * then it will consume a lot of memory (more than 8K for each BufFile and * there could be multiple such BufFiles as the subscriber could receive * multiple start/stop streams for different transactions before getting the - * commit). Moreover, if we don't use SharedFileSet then we also need to invent + * commit). Moreover, if we don't use FileSet then we also need to invent * a new way to pass filenames to BufFile APIs so that we are allowed to open * the file we desired across multiple stream-open calls for the same * transaction. @@ -246,8 +246,8 @@ static ApplyErrorCallbackArg apply_error_callback_arg = typedef struct StreamXidHash { TransactionId xid; /* xid is the hash key and must be first */ - SharedFileSet *stream_fileset; /* shared file set for stream data */ - SharedFileSet *subxact_fileset; /* shared file set for subxact info */ + FileSet *stream_fileset; /* file set for stream data */ + FileSet *subxact_fileset; /* file set for subxact info */ } StreamXidHash; static MemoryContext ApplyMessageContext = NULL; @@ -270,8 +270,8 @@ static bool in_streamed_transaction = false; static TransactionId stream_xid = InvalidTransactionId; /* - * Hash table for storing the streaming xid information along with shared file - * set for streaming and subxact files. + * Hash table for storing the streaming xid information along with filesets + * for streaming and subxact files. */ static HTAB *xidhash = NULL; @@ -1297,11 +1297,11 @@ apply_handle_stream_abort(StringInfo s) /* open the changes file */ changes_filename(path, MyLogicalRepWorker->subid, xid); - fd = BufFileOpenShared(ent->stream_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); /* OK, truncate the file at the right offset */ - BufFileTruncateShared(fd, subxact_data.subxacts[subidx].fileno, - subxact_data.subxacts[subidx].offset); + BufFileTruncateFileSet(fd, subxact_data.subxacts[subidx].fileno, + subxact_data.subxacts[subidx].offset); BufFileClose(fd); /* discard the subxacts added later */ @@ -1355,7 +1355,7 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) errmsg_internal("transaction %u not found in stream XID hash table", xid))); - fd = BufFileOpenShared(ent->stream_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDONLY); buffer = palloc(BLCKSZ); initStringInfo(&s2); @@ -2542,6 +2542,30 @@ UpdateWorkerStats(XLogRecPtr last_lsn, TimestampTz send_time, bool reply) } /* + * Cleanup filesets. + */ +void +logicalrep_worker_cleanupfileset(void) +{ + HASH_SEQ_STATUS status; + StreamXidHash *hentry; + + /* Remove all the pending stream and subxact filesets. */ + if (xidhash) + { + hash_seq_init(&status, xidhash); + while ((hentry = (StreamXidHash *) hash_seq_search(&status)) != NULL) + { + FileSetDeleteAll(hentry->stream_fileset); + + /* Delete the subxact fileset iff it is created. */ + if (hentry->subxact_fileset) + FileSetDeleteAll(hentry->subxact_fileset); + } + } +} + +/* * Apply main loop. */ static void @@ -3024,7 +3048,7 @@ subxact_info_write(Oid subid, TransactionId xid) if (ent->subxact_fileset) { cleanup_subxact_info(); - SharedFileSetDeleteAll(ent->subxact_fileset); + FileSetDeleteAll(ent->subxact_fileset); pfree(ent->subxact_fileset); ent->subxact_fileset = NULL; } @@ -3042,18 +3066,18 @@ subxact_info_write(Oid subid, TransactionId xid) MemoryContext oldctx; /* - * We need to maintain shared fileset across multiple stream - * start/stop calls. So, need to allocate it in a persistent context. + * We need to maintain fileset across multiple stream start/stop + * calls. So, need to allocate it in a persistent context. */ oldctx = MemoryContextSwitchTo(ApplyContext); - ent->subxact_fileset = palloc(sizeof(SharedFileSet)); - SharedFileSetInit(ent->subxact_fileset, NULL); + ent->subxact_fileset = palloc(sizeof(FileSet)); + FileSetInit(ent->subxact_fileset); MemoryContextSwitchTo(oldctx); - fd = BufFileCreateShared(ent->subxact_fileset, path); + fd = BufFileCreateFileSet(ent->subxact_fileset, path); } else - fd = BufFileOpenShared(ent->subxact_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDWR); len = sizeof(SubXactInfo) * subxact_data.nsubxacts; @@ -3107,7 +3131,7 @@ subxact_info_read(Oid subid, TransactionId xid) subxact_filename(path, subid, xid); - fd = BufFileOpenShared(ent->subxact_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDONLY); /* read number of subxact items */ if (BufFileRead(fd, &subxact_data.nsubxacts, @@ -3264,7 +3288,7 @@ stream_cleanup_files(Oid subid, TransactionId xid) /* Delete the change file and release the stream fileset memory */ changes_filename(path, subid, xid); - SharedFileSetDeleteAll(ent->stream_fileset); + FileSetDeleteAll(ent->stream_fileset); pfree(ent->stream_fileset); ent->stream_fileset = NULL; @@ -3272,7 +3296,7 @@ stream_cleanup_files(Oid subid, TransactionId xid) if (ent->subxact_fileset) { subxact_filename(path, subid, xid); - SharedFileSetDeleteAll(ent->subxact_fileset); + FileSetDeleteAll(ent->subxact_fileset); pfree(ent->subxact_fileset); ent->subxact_fileset = NULL; } @@ -3288,8 +3312,8 @@ stream_cleanup_files(Oid subid, TransactionId xid) * * Open a file for streamed changes from a toplevel transaction identified * by stream_xid (global variable). If it's the first chunk of streamed - * changes for this transaction, initialize the shared fileset and create the - * buffile, otherwise open the previously created file. + * changes for this transaction, initialize the fileset and create the buffile, + * otherwise open the previously created file. * * This can only be called at the beginning of a "streaming" block, i.e. * between stream_start/stream_stop messages from the upstream. @@ -3330,7 +3354,7 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) if (first_segment) { MemoryContext savectx; - SharedFileSet *fileset; + FileSet *fileset; if (found) ereport(ERROR, @@ -3338,16 +3362,16 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); /* - * We need to maintain shared fileset across multiple stream - * start/stop calls. So, need to allocate it in a persistent context. + * We need to maintain fileset across multiple stream start/stop + * calls. So, need to allocate it in a persistent context. */ savectx = MemoryContextSwitchTo(ApplyContext); - fileset = palloc(sizeof(SharedFileSet)); + fileset = palloc(sizeof(FileSet)); - SharedFileSetInit(fileset, NULL); + FileSetInit(fileset); MemoryContextSwitchTo(savectx); - stream_fd = BufFileCreateShared(fileset, path); + stream_fd = BufFileCreateFileSet(fileset, path); /* Remember the fileset for the next stream of the same transaction */ ent->xid = xid; @@ -3365,7 +3389,7 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) * Open the file and seek to the end of the file because we always * append the changes file. */ - stream_fd = BufFileOpenShared(ent->stream_fileset, path, O_RDWR); + stream_fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); BufFileSeek(stream_fd, 0, 0, SEEK_END); } diff --git a/src/backend/storage/file/Makefile b/src/backend/storage/file/Makefile index 5e1291b..660ac51 100644 --- a/src/backend/storage/file/Makefile +++ b/src/backend/storage/file/Makefile @@ -16,6 +16,7 @@ OBJS = \ buffile.o \ copydir.o \ fd.o \ + fileset.o \ reinit.o \ sharedfileset.o diff --git a/src/backend/storage/file/buffile.c b/src/backend/storage/file/buffile.c index a4be5fe..5e5409d 100644 --- a/src/backend/storage/file/buffile.c +++ b/src/backend/storage/file/buffile.c @@ -39,7 +39,7 @@ * BufFile also supports temporary files that can be used by the single backend * when the corresponding files need to be survived across the transaction and * need to be opened and closed multiple times. Such files need to be created - * as a member of a SharedFileSet. + * as a member of a FileSet. *------------------------------------------------------------------------- */ @@ -77,8 +77,8 @@ struct BufFile bool dirty; /* does buffer need to be written? */ bool readOnly; /* has the file been set to read only? */ - SharedFileSet *fileset; /* space for segment files if shared */ - const char *name; /* name of this BufFile if shared */ + FileSet *fileset; /* space for fileset based segment files */ + const char *name; /* name of fileset based BufFile */ /* * resowner is the ResourceOwner to use for underlying temp files. (We @@ -104,7 +104,7 @@ static void extendBufFile(BufFile *file); static void BufFileLoadBuffer(BufFile *file); static void BufFileDumpBuffer(BufFile *file); static void BufFileFlush(BufFile *file); -static File MakeNewSharedSegment(BufFile *file, int segment); +static File MakeNewFileSetSegment(BufFile *file, int segment); /* * Create BufFile and perform the common initialization. @@ -160,7 +160,7 @@ extendBufFile(BufFile *file) if (file->fileset == NULL) pfile = OpenTemporaryFile(file->isInterXact); else - pfile = MakeNewSharedSegment(file, file->numFiles); + pfile = MakeNewFileSetSegment(file, file->numFiles); Assert(pfile >= 0); @@ -214,34 +214,34 @@ BufFileCreateTemp(bool interXact) * Build the name for a given segment of a given BufFile. */ static void -SharedSegmentName(char *name, const char *buffile_name, int segment) +FileSetSegmentName(char *name, const char *buffile_name, int segment) { snprintf(name, MAXPGPATH, "%s.%d", buffile_name, segment); } /* - * Create a new segment file backing a shared BufFile. + * Create a new segment file backing a fileset based BufFile. */ static File -MakeNewSharedSegment(BufFile *buffile, int segment) +MakeNewFileSetSegment(BufFile *buffile, int segment) { char name[MAXPGPATH]; File file; /* * It is possible that there are files left over from before a crash - * restart with the same name. In order for BufFileOpenShared() not to + * restart with the same name. In order for BufFileOpenFileSet() not to * get confused about how many segments there are, we'll unlink the next * segment number if it already exists. */ - SharedSegmentName(name, buffile->name, segment + 1); - SharedFileSetDelete(buffile->fileset, name, true); + FileSetSegmentName(name, buffile->name, segment + 1); + FileSetDelete(buffile->fileset, name, true); /* Create the new segment. */ - SharedSegmentName(name, buffile->name, segment); - file = SharedFileSetCreate(buffile->fileset, name); + FileSetSegmentName(name, buffile->name, segment); + file = FileSetCreate(buffile->fileset, name); - /* SharedFileSetCreate would've errored out */ + /* FileSetCreate would've errored out */ Assert(file > 0); return file; @@ -251,15 +251,15 @@ MakeNewSharedSegment(BufFile *buffile, int segment) * Create a BufFile that can be discovered and opened read-only by other * backends that are attached to the same SharedFileSet using the same name. * - * The naming scheme for shared BufFiles is left up to the calling code. The - * name will appear as part of one or more filenames on disk, and might + * The naming scheme for fileset based BufFiles is left up to the calling code. + * The name will appear as part of one or more filenames on disk, and might * provide clues to administrators about which subsystem is generating * temporary file data. Since each SharedFileSet object is backed by one or * more uniquely named temporary directory, names don't conflict with * unrelated SharedFileSet objects. */ BufFile * -BufFileCreateShared(SharedFileSet *fileset, const char *name) +BufFileCreateFileSet(FileSet *fileset, const char *name) { BufFile *file; @@ -267,7 +267,7 @@ BufFileCreateShared(SharedFileSet *fileset, const char *name) file->fileset = fileset; file->name = pstrdup(name); file->files = (File *) palloc(sizeof(File)); - file->files[0] = MakeNewSharedSegment(file, 0); + file->files[0] = MakeNewFileSetSegment(file, 0); file->readOnly = false; return file; @@ -275,13 +275,13 @@ BufFileCreateShared(SharedFileSet *fileset, const char *name) /* * Open a file that was previously created in another backend (or this one) - * with BufFileCreateShared in the same SharedFileSet using the same name. + * with BufFileCreateFileSet in the same FileSet using the same name. * The backend that created the file must have called BufFileClose() or - * BufFileExportShared() to make sure that it is ready to be opened by other + * BufFileExportFileSet() to make sure that it is ready to be opened by other * backends and render it read-only. */ BufFile * -BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) +BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) { BufFile *file; char segment_name[MAXPGPATH]; @@ -304,8 +304,8 @@ BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) files = repalloc(files, sizeof(File) * capacity); } /* Try to load a segment. */ - SharedSegmentName(segment_name, name, nfiles); - files[nfiles] = SharedFileSetOpen(fileset, segment_name, mode); + FileSetSegmentName(segment_name, name, nfiles); + files[nfiles] = FileSetOpen(fileset, segment_name, mode); if (files[nfiles] <= 0) break; ++nfiles; @@ -333,18 +333,18 @@ BufFileOpenShared(SharedFileSet *fileset, const char *name, int mode) } /* - * Delete a BufFile that was created by BufFileCreateShared in the given - * SharedFileSet using the given name. + * Delete a BufFile that was created by BufFileCreateFileSet in the given + * FileSet using the given name. * * It is not necessary to delete files explicitly with this function. It is * provided only as a way to delete files proactively, rather than waiting for - * the SharedFileSet to be cleaned up. + * the FileSet to be cleaned up. * * Only one backend should attempt to delete a given name, and should know * that it exists and has been exported or closed. */ void -BufFileDeleteShared(SharedFileSet *fileset, const char *name) +BufFileDeleteFileSet(FileSet *fileset, const char *name) { char segment_name[MAXPGPATH]; int segment = 0; @@ -357,8 +357,8 @@ BufFileDeleteShared(SharedFileSet *fileset, const char *name) */ for (;;) { - SharedSegmentName(segment_name, name, segment); - if (!SharedFileSetDelete(fileset, segment_name, true)) + FileSetSegmentName(segment_name, name, segment); + if (!FileSetDelete(fileset, segment_name, true)) break; found = true; ++segment; @@ -367,16 +367,16 @@ BufFileDeleteShared(SharedFileSet *fileset, const char *name) } if (!found) - elog(ERROR, "could not delete unknown shared BufFile \"%s\"", name); + elog(ERROR, "could not delete unknown BufFile \"%s\"", name); } /* - * BufFileExportShared --- flush and make read-only, in preparation for sharing. + * BufFileExportFileSet --- flush and make read-only, in preparation for sharing. */ void -BufFileExportShared(BufFile *file) +BufFileExportFileSet(BufFile *file) { - /* Must be a file belonging to a SharedFileSet. */ + /* Must be a file belonging to a FileSet. */ Assert(file->fileset != NULL); /* It's probably a bug if someone calls this twice. */ @@ -785,7 +785,7 @@ BufFileTellBlock(BufFile *file) #endif /* - * Return the current shared BufFile size. + * Return the current fileset based BufFile size. * * Counts any holes left behind by BufFileAppend as part of the size. * ereport()s on failure. @@ -811,8 +811,8 @@ BufFileSize(BufFile *file) } /* - * Append the contents of source file (managed within shared fileset) to - * end of target file (managed within same shared fileset). + * Append the contents of source file (managed within fileset) to + * end of target file (managed within same fileset). * * Note that operation subsumes ownership of underlying resources from * "source". Caller should never call BufFileClose against source having @@ -854,11 +854,11 @@ BufFileAppend(BufFile *target, BufFile *source) } /* - * Truncate a BufFile created by BufFileCreateShared up to the given fileno and - * the offset. + * Truncate a BufFile created by BufFileCreateFileSet up to the given fileno + * and the offset. */ void -BufFileTruncateShared(BufFile *file, int fileno, off_t offset) +BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset) { int numFiles = file->numFiles; int newFile = fileno; @@ -876,12 +876,12 @@ BufFileTruncateShared(BufFile *file, int fileno, off_t offset) { if ((i != fileno || offset == 0) && i != 0) { - SharedSegmentName(segment_name, file->name, i); + FileSetSegmentName(segment_name, file->name, i); FileClose(file->files[i]); - if (!SharedFileSetDelete(file->fileset, segment_name, true)) + if (!FileSetDelete(file->fileset, segment_name, true)) ereport(ERROR, (errcode_for_file_access(), - errmsg("could not delete shared fileset \"%s\": %m", + errmsg("could not delete fileset \"%s\": %m", segment_name))); numFiles--; newOffset = MAX_PHYSICAL_FILESIZE; diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c index b58b399..433e283 100644 --- a/src/backend/storage/file/fd.c +++ b/src/backend/storage/file/fd.c @@ -1921,7 +1921,7 @@ PathNameDeleteTemporaryFile(const char *path, bool error_on_failure) /* * Unlike FileClose's automatic file deletion code, we tolerate - * non-existence to support BufFileDeleteShared which doesn't know how + * non-existence to support BufFileDeleteFileSet which doesn't know how * many segments it has to delete until it runs out. */ if (stat_errno == ENOENT) diff --git a/src/backend/storage/file/fileset.c b/src/backend/storage/file/fileset.c new file mode 100644 index 0000000..282ff12 --- /dev/null +++ b/src/backend/storage/file/fileset.c @@ -0,0 +1,205 @@ +/*------------------------------------------------------------------------- + * + * fileset.c + * Management of named temporary files. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * IDENTIFICATION + * src/backend/storage/file/fileset.c + * + * FileSets provide a temporary namespace (think directory) so that files can + * be discovered by name. + * + * FileSets can be used by backends when the temporary files need to be + * opened/closed multiple times and the underlying files need to survive across + * transactions. + * + *------------------------------------------------------------------------- + */ + +#include "postgres.h" + +#include <limits.h> + +#include "catalog/pg_tablespace.h" +#include "commands/tablespace.h" +#include "common/hashfn.h" +#include "miscadmin.h" +#include "storage/ipc.h" +#include "storage/fileset.h" +#include "utils/builtins.h" + +static void FileSetPath(char *path, FileSet *fileset, Oid tablespace); +static void FilePath(char *path, FileSet *fileset, const char *name); +static Oid ChooseTablespace(const FileSet *fileset, const char *name); + +/* + * Initialize a space for temporary files. This API can be used by shared + * fileset as well as if the temporary files are used only by single backend + * but the files need to be opened and closed multiple times and also the + * underlying files need to survive across transactions. + * + * The callers are expected to explicitly remove such files by using + * FileSetDelete/FileSetDeleteAll. + * + * Files will be distributed over the tablespaces configured in + * temp_tablespaces. + * + * Under the covers the set is one or more directories which will eventually + * be deleted. + */ +void +FileSetInit(FileSet *fileset) +{ + static uint32 counter = 0; + + fileset->creator_pid = MyProcPid; + fileset->number = counter; + counter = (counter + 1) % INT_MAX; + + /* Capture the tablespace OIDs so that all backends agree on them. */ + PrepareTempTablespaces(); + fileset->ntablespaces = + GetTempTablespaces(&fileset->tablespaces[0], + lengthof(fileset->tablespaces)); + if (fileset->ntablespaces == 0) + { + /* If the GUC is empty, use current database's default tablespace */ + fileset->tablespaces[0] = MyDatabaseTableSpace; + fileset->ntablespaces = 1; + } + else + { + int i; + + /* + * An entry of InvalidOid means use the default tablespace for the + * current database. Replace that now, to be sure that all users of + * the FileSet agree on what to do. + */ + for (i = 0; i < fileset->ntablespaces; i++) + { + if (fileset->tablespaces[i] == InvalidOid) + fileset->tablespaces[i] = MyDatabaseTableSpace; + } + } +} + +/* + * Create a new file in the given set. + */ +File +FileSetCreate(FileSet *fileset, const char *name) +{ + char path[MAXPGPATH]; + File file; + + FilePath(path, fileset, name); + file = PathNameCreateTemporaryFile(path, false); + + /* If we failed, see if we need to create the directory on demand. */ + if (file <= 0) + { + char tempdirpath[MAXPGPATH]; + char filesetpath[MAXPGPATH]; + Oid tablespace = ChooseTablespace(fileset, name); + + TempTablespacePath(tempdirpath, tablespace); + FileSetPath(filesetpath, fileset, tablespace); + PathNameCreateTemporaryDir(tempdirpath, filesetpath); + file = PathNameCreateTemporaryFile(path, true); + } + + return file; +} + +/* + * Open a file that was created with FileSetCreate() */ +File +FileSetOpen(FileSet *fileset, const char *name, int mode) +{ + char path[MAXPGPATH]; + File file; + + FilePath(path, fileset, name); + file = PathNameOpenTemporaryFile(path, mode); + + return file; +} + +/* + * Delete a file that was created with FileSetCreate(). + * + * Return true if the file existed, false if didn't. + */ +bool +FileSetDelete(FileSet *fileset, const char *name, + bool error_on_failure) +{ + char path[MAXPGPATH]; + + FilePath(path, fileset, name); + + return PathNameDeleteTemporaryFile(path, error_on_failure); +} + +/* + * Delete all files in the set. + */ +void +FileSetDeleteAll(FileSet *fileset) +{ + char dirpath[MAXPGPATH]; + int i; + + /* + * Delete the directory we created in each tablespace. Doesn't fail + * because we use this in error cleanup paths, but can generate LOG + * message on IO error. + */ + for (i = 0; i < fileset->ntablespaces; ++i) + { + FileSetPath(dirpath, fileset, fileset->tablespaces[i]); + PathNameDeleteTemporaryDir(dirpath); + } +} + +/* + * Build the path for the directory holding the files backing a FileSet in a + * given tablespace. + */ +static void +FileSetPath(char *path, FileSet *fileset, Oid tablespace) +{ + char tempdirpath[MAXPGPATH]; + + TempTablespacePath(tempdirpath, tablespace); + snprintf(path, MAXPGPATH, "%s/%s%lu.%u.fileset", + tempdirpath, PG_TEMP_FILE_PREFIX, + (unsigned long) fileset->creator_pid, fileset->number); +} + +/* + * Sorting has to determine which tablespace a given temporary file belongs in. + */ +static Oid +ChooseTablespace(const FileSet *fileset, const char *name) +{ + uint32 hash = hash_any((const unsigned char *) name, strlen(name)); + + return fileset->tablespaces[hash % fileset->ntablespaces]; +} + +/* + * Compute the full path of a file in a FileSet. + */ +static void +FilePath(char *path, FileSet *fileset, const char *name) +{ + char dirpath[MAXPGPATH]; + + FileSetPath(dirpath, fileset, ChooseTablespace(fileset, name)); + snprintf(path, MAXPGPATH, "%s/%s", dirpath, name); +} diff --git a/src/backend/storage/file/sharedfileset.c b/src/backend/storage/file/sharedfileset.c index ed37c94..6a33fac 100644 --- a/src/backend/storage/file/sharedfileset.c +++ b/src/backend/storage/file/sharedfileset.c @@ -13,10 +13,6 @@ * files can be discovered by name, and a shared ownership semantics so that * shared files survive until the last user detaches. * - * SharedFileSets can be used by backends when the temporary files need to be - * opened/closed multiple times and the underlying files need to survive across - * transactions. - * *------------------------------------------------------------------------- */ @@ -33,13 +29,7 @@ #include "storage/sharedfileset.h" #include "utils/builtins.h" -static List *filesetlist = NIL; - static void SharedFileSetOnDetach(dsm_segment *segment, Datum datum); -static void SharedFileSetDeleteOnProcExit(int status, Datum arg); -static void SharedFileSetPath(char *path, SharedFileSet *fileset, Oid tablespace); -static void SharedFilePath(char *path, SharedFileSet *fileset, const char *name); -static Oid ChooseTablespace(const SharedFileSet *fileset, const char *name); /* * Initialize a space for temporary files that can be opened by other backends. @@ -47,77 +37,22 @@ static Oid ChooseTablespace(const SharedFileSet *fileset, const char *name); * SharedFileSet with 'seg'. Any contained files will be deleted when the * last backend detaches. * - * We can also use this interface if the temporary files are used only by - * single backend but the files need to be opened and closed multiple times - * and also the underlying files need to survive across transactions. For - * such cases, dsm segment 'seg' should be passed as NULL. Callers are - * expected to explicitly remove such files by using SharedFileSetDelete/ - * SharedFileSetDeleteAll or we remove such files on proc exit. - * - * Files will be distributed over the tablespaces configured in - * temp_tablespaces. - * * Under the covers the set is one or more directories which will eventually * be deleted. */ void SharedFileSetInit(SharedFileSet *fileset, dsm_segment *seg) { - static uint32 counter = 0; - + /* Initialize the shared fileset specific members. */ SpinLockInit(&fileset->mutex); fileset->refcnt = 1; - fileset->creator_pid = MyProcPid; - fileset->number = counter; - counter = (counter + 1) % INT_MAX; - - /* Capture the tablespace OIDs so that all backends agree on them. */ - PrepareTempTablespaces(); - fileset->ntablespaces = - GetTempTablespaces(&fileset->tablespaces[0], - lengthof(fileset->tablespaces)); - if (fileset->ntablespaces == 0) - { - /* If the GUC is empty, use current database's default tablespace */ - fileset->tablespaces[0] = MyDatabaseTableSpace; - fileset->ntablespaces = 1; - } - else - { - int i; - /* - * An entry of InvalidOid means use the default tablespace for the - * current database. Replace that now, to be sure that all users of - * the SharedFileSet agree on what to do. - */ - for (i = 0; i < fileset->ntablespaces; i++) - { - if (fileset->tablespaces[i] == InvalidOid) - fileset->tablespaces[i] = MyDatabaseTableSpace; - } - } + /* Initialize the fileset. */ + FileSetInit(&fileset->fs); /* Register our cleanup callback. */ if (seg) on_dsm_detach(seg, SharedFileSetOnDetach, PointerGetDatum(fileset)); - else - { - static bool registered_cleanup = false; - - if (!registered_cleanup) - { - /* - * We must not have registered any fileset before registering the - * fileset clean up. - */ - Assert(filesetlist == NIL); - on_proc_exit(SharedFileSetDeleteOnProcExit, 0); - registered_cleanup = true; - } - - filesetlist = lcons((void *) fileset, filesetlist); - } } /* @@ -148,86 +83,12 @@ SharedFileSetAttach(SharedFileSet *fileset, dsm_segment *seg) } /* - * Create a new file in the given set. - */ -File -SharedFileSetCreate(SharedFileSet *fileset, const char *name) -{ - char path[MAXPGPATH]; - File file; - - SharedFilePath(path, fileset, name); - file = PathNameCreateTemporaryFile(path, false); - - /* If we failed, see if we need to create the directory on demand. */ - if (file <= 0) - { - char tempdirpath[MAXPGPATH]; - char filesetpath[MAXPGPATH]; - Oid tablespace = ChooseTablespace(fileset, name); - - TempTablespacePath(tempdirpath, tablespace); - SharedFileSetPath(filesetpath, fileset, tablespace); - PathNameCreateTemporaryDir(tempdirpath, filesetpath); - file = PathNameCreateTemporaryFile(path, true); - } - - return file; -} - -/* - * Open a file that was created with SharedFileSetCreate(), possibly in - * another backend. - */ -File -SharedFileSetOpen(SharedFileSet *fileset, const char *name, int mode) -{ - char path[MAXPGPATH]; - File file; - - SharedFilePath(path, fileset, name); - file = PathNameOpenTemporaryFile(path, mode); - - return file; -} - -/* - * Delete a file that was created with SharedFileSetCreate(). - * Return true if the file existed, false if didn't. - */ -bool -SharedFileSetDelete(SharedFileSet *fileset, const char *name, - bool error_on_failure) -{ - char path[MAXPGPATH]; - - SharedFilePath(path, fileset, name); - - return PathNameDeleteTemporaryFile(path, error_on_failure); -} - -/* * Delete all files in the set. */ void SharedFileSetDeleteAll(SharedFileSet *fileset) { - char dirpath[MAXPGPATH]; - int i; - - /* - * Delete the directory we created in each tablespace. Doesn't fail - * because we use this in error cleanup paths, but can generate LOG - * message on IO error. - */ - for (i = 0; i < fileset->ntablespaces; ++i) - { - SharedFileSetPath(dirpath, fileset, fileset->tablespaces[i]); - PathNameDeleteTemporaryDir(dirpath); - } - - /* Unregister the shared fileset */ - SharedFileSetUnregister(fileset); + FileSetDeleteAll(&fileset->fs); } /* @@ -255,100 +116,5 @@ SharedFileSetOnDetach(dsm_segment *segment, Datum datum) * this function so we can safely access its data. */ if (unlink_all) - SharedFileSetDeleteAll(fileset); -} - -/* - * Callback function that will be invoked on the process exit. This will - * process the list of all the registered sharedfilesets and delete the - * underlying files. - */ -static void -SharedFileSetDeleteOnProcExit(int status, Datum arg) -{ - /* - * Remove all the pending shared fileset entries. We don't use foreach() - * here because SharedFileSetDeleteAll will remove the current element in - * filesetlist. Though we have used foreach_delete_current() to remove the - * element from filesetlist it could only fix up the state of one of the - * loops, see SharedFileSetUnregister. - */ - while (list_length(filesetlist) > 0) - { - SharedFileSet *fileset = (SharedFileSet *) linitial(filesetlist); - - SharedFileSetDeleteAll(fileset); - } - - filesetlist = NIL; -} - -/* - * Unregister the shared fileset entry registered for cleanup on proc exit. - */ -void -SharedFileSetUnregister(SharedFileSet *input_fileset) -{ - ListCell *l; - - /* - * If the caller is following the dsm based cleanup then we don't maintain - * the filesetlist so return. - */ - if (filesetlist == NIL) - return; - - foreach(l, filesetlist) - { - SharedFileSet *fileset = (SharedFileSet *) lfirst(l); - - /* Remove the entry from the list */ - if (input_fileset == fileset) - { - filesetlist = foreach_delete_current(filesetlist, l); - return; - } - } - - /* Should have found a match */ - Assert(false); -} - -/* - * Build the path for the directory holding the files backing a SharedFileSet - * in a given tablespace. - */ -static void -SharedFileSetPath(char *path, SharedFileSet *fileset, Oid tablespace) -{ - char tempdirpath[MAXPGPATH]; - - TempTablespacePath(tempdirpath, tablespace); - snprintf(path, MAXPGPATH, "%s/%s%lu.%u.sharedfileset", - tempdirpath, PG_TEMP_FILE_PREFIX, - (unsigned long) fileset->creator_pid, fileset->number); -} - -/* - * Sorting hat to determine which tablespace a given shared temporary file - * belongs in. - */ -static Oid -ChooseTablespace(const SharedFileSet *fileset, const char *name) -{ - uint32 hash = hash_any((const unsigned char *) name, strlen(name)); - - return fileset->tablespaces[hash % fileset->ntablespaces]; -} - -/* - * Compute the full path of a file in a SharedFileSet. - */ -static void -SharedFilePath(char *path, SharedFileSet *fileset, const char *name) -{ - char dirpath[MAXPGPATH]; - - SharedFileSetPath(dirpath, fileset, ChooseTablespace(fileset, name)); - snprintf(path, MAXPGPATH, "%s/%s", dirpath, name); + FileSetDeleteAll(&fileset->fs); } diff --git a/src/backend/utils/sort/logtape.c b/src/backend/utils/sort/logtape.c index cafc087..f7994d7 100644 --- a/src/backend/utils/sort/logtape.c +++ b/src/backend/utils/sort/logtape.c @@ -564,7 +564,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, lt = &lts->tapes[i]; pg_itoa(i, filename); - file = BufFileOpenShared(fileset, filename, O_RDONLY); + file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY); filesize = BufFileSize(file); /* @@ -610,7 +610,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, * offset). * * The only thing that currently prevents writing to the leader tape from - * working is the fact that BufFiles opened using BufFileOpenShared() are + * working is the fact that BufFiles opened using BufFileOpenFileSet() are * read-only by definition, but that could be changed if it seemed * worthwhile. For now, writing to the leader tape will raise a "Bad file * descriptor" error, so tuplesort must avoid writing to the leader tape @@ -722,7 +722,7 @@ LogicalTapeSetCreate(int ntapes, bool preallocate, TapeShare *shared, char filename[MAXPGPATH]; pg_itoa(worker, filename); - lts->pfile = BufFileCreateShared(fileset, filename); + lts->pfile = BufFileCreateFileSet(&fileset->fs, filename); } else lts->pfile = BufFileCreateTemp(false); @@ -1096,7 +1096,7 @@ LogicalTapeFreeze(LogicalTapeSet *lts, int tapenum, TapeShare *share) /* Handle extra steps when caller is to share its tapeset */ if (share) { - BufFileExportShared(lts->pfile); + BufFileExportFileSet(lts->pfile); share->firstblocknumber = lt->firstBlockNumber; } } diff --git a/src/backend/utils/sort/sharedtuplestore.c b/src/backend/utils/sort/sharedtuplestore.c index 57e35db..504ef1c 100644 --- a/src/backend/utils/sort/sharedtuplestore.c +++ b/src/backend/utils/sort/sharedtuplestore.c @@ -310,7 +310,8 @@ sts_puttuple(SharedTuplestoreAccessor *accessor, void *meta_data, /* Create one. Only this backend will write into it. */ sts_filename(name, accessor, accessor->participant); - accessor->write_file = BufFileCreateShared(accessor->fileset, name); + accessor->write_file = + BufFileCreateFileSet(&accessor->fileset->fs, name); /* Set up the shared state for this backend's file. */ participant = &accessor->sts->participants[accessor->participant]; @@ -559,7 +560,7 @@ sts_parallel_scan_next(SharedTuplestoreAccessor *accessor, void *meta_data) sts_filename(name, accessor, accessor->read_participant); accessor->read_file = - BufFileOpenShared(accessor->fileset, name, O_RDONLY); + BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY); } /* Seek and load the chunk header. */ diff --git a/src/include/replication/worker_internal.h b/src/include/replication/worker_internal.h index 41c7487..a6c9d4e 100644 --- a/src/include/replication/worker_internal.h +++ b/src/include/replication/worker_internal.h @@ -79,6 +79,7 @@ extern void logicalrep_worker_launch(Oid dbid, Oid subid, const char *subname, extern void logicalrep_worker_stop(Oid subid, Oid relid); extern void logicalrep_worker_wakeup(Oid subid, Oid relid); extern void logicalrep_worker_wakeup_ptr(LogicalRepWorker *worker); +extern void logicalrep_worker_cleanupfileset(void); extern int logicalrep_sync_worker_count(Oid subid); diff --git a/src/include/storage/buffile.h b/src/include/storage/buffile.h index 566523d..143eada 100644 --- a/src/include/storage/buffile.h +++ b/src/include/storage/buffile.h @@ -26,7 +26,7 @@ #ifndef BUFFILE_H #define BUFFILE_H -#include "storage/sharedfileset.h" +#include "storage/fileset.h" /* BufFile is an opaque type whose details are not known outside buffile.c. */ @@ -46,11 +46,11 @@ extern int BufFileSeekBlock(BufFile *file, long blknum); extern int64 BufFileSize(BufFile *file); extern long BufFileAppend(BufFile *target, BufFile *source); -extern BufFile *BufFileCreateShared(SharedFileSet *fileset, const char *name); -extern void BufFileExportShared(BufFile *file); -extern BufFile *BufFileOpenShared(SharedFileSet *fileset, const char *name, - int mode); -extern void BufFileDeleteShared(SharedFileSet *fileset, const char *name); -extern void BufFileTruncateShared(BufFile *file, int fileno, off_t offset); +extern BufFile *BufFileCreateFileSet(FileSet *fileset, const char *name); +extern void BufFileExportFileSet(BufFile *file); +extern BufFile *BufFileOpenFileSet(FileSet *fileset, const char *name, + int mode); +extern void BufFileDeleteFileSet(FileSet *fileset, const char *name); +extern void BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset); #endif /* BUFFILE_H */ diff --git a/src/include/storage/fileset.h b/src/include/storage/fileset.h new file mode 100644 index 0000000..be0e097 --- /dev/null +++ b/src/include/storage/fileset.h @@ -0,0 +1,40 @@ +/*------------------------------------------------------------------------- + * + * fileset.h + * Management of named temporary files. + * + * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group + * Portions Copyright (c) 1994, Regents of the University of California + * + * src/include/storage/fileset.h + * + *------------------------------------------------------------------------- + */ + +#ifndef FILESET_H +#define FILESET_H + +#include "storage/fd.h" + +/* + * A set of temporary files. + */ +typedef struct FileSet +{ + pid_t creator_pid; /* PID of the creating process */ + uint32 number; /* per-PID identifier */ + int ntablespaces; /* number of tablespaces to use */ + Oid tablespaces[8]; /* OIDs of tablespaces to use. Assumes that + * it's rare that there more than temp + * tablespaces. */ +} FileSet; + +extern void FileSetInit(FileSet *fileset); +extern File FileSetCreate(FileSet *fileset, const char *name); +extern File FileSetOpen(FileSet *fileset, const char *name, + int mode); +extern bool FileSetDelete(FileSet *fileset, const char *name, + bool error_on_failure); +extern void FileSetDeleteAll(FileSet *fileset); + +#endif diff --git a/src/include/storage/sharedfileset.h b/src/include/storage/sharedfileset.h index 09ba121..59becfb 100644 --- a/src/include/storage/sharedfileset.h +++ b/src/include/storage/sharedfileset.h @@ -17,6 +17,7 @@ #include "storage/dsm.h" #include "storage/fd.h" +#include "storage/fileset.h" #include "storage/spin.h" /* @@ -24,24 +25,13 @@ */ typedef struct SharedFileSet { - pid_t creator_pid; /* PID of the creating process */ - uint32 number; /* per-PID identifier */ + FileSet fs; slock_t mutex; /* mutex protecting the reference count */ int refcnt; /* number of attached backends */ - int ntablespaces; /* number of tablespaces to use */ - Oid tablespaces[8]; /* OIDs of tablespaces to use. Assumes that - * it's rare that there more than temp - * tablespaces. */ } SharedFileSet; extern void SharedFileSetInit(SharedFileSet *fileset, dsm_segment *seg); extern void SharedFileSetAttach(SharedFileSet *fileset, dsm_segment *seg); -extern File SharedFileSetCreate(SharedFileSet *fileset, const char *name); -extern File SharedFileSetOpen(SharedFileSet *fileset, const char *name, - int mode); -extern bool SharedFileSetDelete(SharedFileSet *fileset, const char *name, - bool error_on_failure); extern void SharedFileSetDeleteAll(SharedFileSet *fileset); -extern void SharedFileSetUnregister(SharedFileSet *input_fileset); #endif diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list index 621d0cb..f31a1e4 100644 --- a/src/tools/pgindent/typedefs.list +++ b/src/tools/pgindent/typedefs.list @@ -709,6 +709,7 @@ File FileFdwExecutionState FileFdwPlanState FileNameMap +FileSet FileTag FinalPathExtraData FindColsContext -- 1.8.3.1
v6-0002-Using-fileset-more-effectively-in-the-apply-worke.patch (text/x-patch, 18.6K) download From 99a71be71a9db8b118890b71aab3797d0904285a Mon Sep 17 00:00:00 2001 From: Dilip Kumar <dilipkumar@localhost.localdomain> Date: Fri, 27 Aug 2021 11:49:12 +0530 Subject: [PATCH v6 2/2] Using fileset more effectively in the apply worker Do not use separate file sets for each xid, instead use one fileset for the worker's entire lifetime. Now, the changes/subxacts files for every streaming transaction will be created under the same fileset and the files will be deleted after the transaction is completed. The fileset will be there until the worker exit. --- src/backend/replication/logical/launcher.c | 2 +- src/backend/replication/logical/worker.c | 249 ++++++----------------------- src/backend/storage/file/buffile.c | 23 ++- src/backend/utils/sort/logtape.c | 2 +- src/backend/utils/sort/sharedtuplestore.c | 3 +- src/include/storage/buffile.h | 5 +- 6 files changed, 75 insertions(+), 209 deletions(-) diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 8b1772d..644a9c2 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -648,7 +648,7 @@ logicalrep_worker_onexit(int code, Datum arg) logicalrep_worker_detach(); - /* Cleanup filesets used for streaming transactions. */ + /* Cleanup fileset used for streaming transactions. */ logicalrep_worker_cleanupfileset(); ApplyLauncherWakeup(); diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index bfb7d1a..c3e4114 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -236,20 +236,6 @@ static ApplyErrorCallbackArg apply_error_callback_arg = .ts = 0, }; -/* - * Stream xid hash entry. Whenever we see a new xid we create this entry in the - * xidhash and along with it create the streaming file and store the fileset handle. - * The subxact file is created iff there is any subxact info under this xid. This - * entry is used on the subsequent streams for the xid to get the corresponding - * fileset handles, so storing them in hash makes the search faster. - */ -typedef struct StreamXidHash -{ - TransactionId xid; /* xid is the hash key and must be first */ - FileSet *stream_fileset; /* file set for stream data */ - FileSet *subxact_fileset; /* file set for subxact info */ -} StreamXidHash; - static MemoryContext ApplyMessageContext = NULL; MemoryContext ApplyContext = NULL; @@ -270,10 +256,13 @@ static bool in_streamed_transaction = false; static TransactionId stream_xid = InvalidTransactionId; /* - * Hash table for storing the streaming xid information along with filesets - * for streaming and subxact files. + * The fileset is used by the worker to create the changes and subxact files + * for the streaming transaction. Upon the arrival of the first streaming + * transaction, the fileset will be initialized, and it will be deleted when + * the worker exits. Under this, separate buffiles would be created for each + * transaction and would be deleted after the transaction is completed. */ -static HTAB *xidhash = NULL; +static FileSet *stream_fileset = NULL; /* BufFile handle of the current streaming file */ static BufFile *stream_fd = NULL; @@ -1118,7 +1107,6 @@ static void apply_handle_stream_start(StringInfo s) { bool first_segment; - HASHCTL hash_ctl; if (in_streamed_transaction) ereport(ERROR, @@ -1148,17 +1136,20 @@ apply_handle_stream_start(StringInfo s) set_apply_error_context_xact(stream_xid, 0); /* - * Initialize the xidhash table if we haven't yet. This will be used for + * Initialize the stream_fileset if we haven't yet. This will be used for * the entire duration of the apply worker so create it in permanent * context. */ - if (xidhash == NULL) + if (stream_fileset == NULL) { - hash_ctl.keysize = sizeof(TransactionId); - hash_ctl.entrysize = sizeof(StreamXidHash); - hash_ctl.hcxt = ApplyContext; - xidhash = hash_create("StreamXidHash", 1024, &hash_ctl, - HASH_ELEM | HASH_BLOBS | HASH_CONTEXT); + MemoryContext oldctx; + + oldctx = MemoryContextSwitchTo(ApplyContext); + + stream_fileset = palloc(sizeof(FileSet)); + FileSetInit(stream_fileset); + + MemoryContextSwitchTo(oldctx); } /* open the spool file for this transaction */ @@ -1253,7 +1244,6 @@ apply_handle_stream_abort(StringInfo s) BufFile *fd; bool found = false; char path[MAXPGPATH]; - StreamXidHash *ent; set_apply_error_context_xact(subxid, 0); @@ -1285,19 +1275,9 @@ apply_handle_stream_abort(StringInfo s) return; } - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* open the changes file */ changes_filename(path, MyLogicalRepWorker->subid, xid); - fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(stream_fileset, path, O_RDWR, false); /* OK, truncate the file at the right offset */ BufFileTruncateFileSet(fd, subxact_data.subxacts[subidx].fileno, @@ -1327,7 +1307,6 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) int nchanges; char path[MAXPGPATH]; char *buffer = NULL; - StreamXidHash *ent; MemoryContext oldcxt; BufFile *fd; @@ -1345,17 +1324,7 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) changes_filename(path, MyLogicalRepWorker->subid, xid); elog(DEBUG1, "replaying changes from file \"%s\"", path); - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - - fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(stream_fileset, path, O_RDONLY, false); buffer = palloc(BLCKSZ); initStringInfo(&s2); @@ -2542,27 +2511,14 @@ UpdateWorkerStats(XLogRecPtr last_lsn, TimestampTz send_time, bool reply) } /* - * Cleanup filesets. + * Cleanup fileset. */ void -logicalrep_worker_cleanupfileset(void) +logicalrep_worker_cleanupfileset() { - HASH_SEQ_STATUS status; - StreamXidHash *hentry; - - /* Remove all the pending stream and subxact filesets. */ - if (xidhash) - { - hash_seq_init(&status, xidhash); - while ((hentry = (StreamXidHash *) hash_seq_search(&status)) != NULL) - { - FileSetDeleteAll(hentry->stream_fileset); - - /* Delete the subxact fileset iff it is created. */ - if (hentry->subxact_fileset) - FileSetDeleteAll(hentry->subxact_fileset); - } - } + /* If the fileset is created, clean the underlying files. */ + if (stream_fileset != NULL) + FileSetDeleteAll(stream_fileset); } /* @@ -3026,58 +2982,29 @@ subxact_info_write(Oid subid, TransactionId xid) { char path[MAXPGPATH]; Size len; - StreamXidHash *ent; BufFile *fd; Assert(TransactionIdIsValid(xid)); - /* Find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - /* By this time we must have created the transaction entry */ - Assert(ent); + /* Get the subxact filename. */ + subxact_filename(path, subid, xid); /* - * If there is no subtransaction then nothing to do, but if already have - * subxact file then delete that. + * If there are no subtransactions, there is nothing to be done, but if + * subxacts already exist, delete it. */ if (subxact_data.nsubxacts == 0) { - if (ent->subxact_fileset) - { - cleanup_subxact_info(); - FileSetDeleteAll(ent->subxact_fileset); - pfree(ent->subxact_fileset); - ent->subxact_fileset = NULL; - } + cleanup_subxact_info(); + BufFileDeleteFileSet(stream_fileset, path, true); + return; } - subxact_filename(path, subid, xid); - - /* - * Create the subxact file if it not already created, otherwise open the - * existing file. - */ - if (ent->subxact_fileset == NULL) - { - MemoryContext oldctx; - - /* - * We need to maintain fileset across multiple stream start/stop - * calls. So, need to allocate it in a persistent context. - */ - oldctx = MemoryContextSwitchTo(ApplyContext); - ent->subxact_fileset = palloc(sizeof(FileSet)); - FileSetInit(ent->subxact_fileset); - MemoryContextSwitchTo(oldctx); - - fd = BufFileCreateFileSet(ent->subxact_fileset, path); - } - else - fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDWR); + /* Open the subxact file, if it does not exist, create it. */ + fd = BufFileOpenFileSet(stream_fileset, path, O_RDWR, true); + if (fd == NULL) + fd = BufFileCreateFileSet(stream_fileset, path); len = sizeof(SubXactInfo) * subxact_data.nsubxacts; @@ -3104,34 +3031,20 @@ subxact_info_read(Oid subid, TransactionId xid) char path[MAXPGPATH]; Size len; BufFile *fd; - StreamXidHash *ent; MemoryContext oldctx; Assert(!subxact_data.subxacts); Assert(subxact_data.nsubxacts == 0); Assert(subxact_data.nsubxacts_max == 0); - /* Find the stream xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* - * If subxact_fileset is not valid that mean we don't have any subxact - * info + * Open the subxact file for the input streaming xid, just return if the + * file does not exist. */ - if (ent->subxact_fileset == NULL) - return; - subxact_filename(path, subid, xid); - - fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(stream_fileset, path, O_RDONLY, true); + if (fd == NULL) + return; /* read number of subxact items */ if (BufFileRead(fd, &subxact_data.nsubxacts, @@ -3267,42 +3180,20 @@ changes_filename(char *path, Oid subid, TransactionId xid) * Cleanup files for a subscription / toplevel transaction. * * Remove files with serialized changes and subxact info for a particular - * toplevel transaction. Each subscription has a separate set of files. + * toplevel transaction. Each subscription has a separate file. */ static void stream_cleanup_files(Oid subid, TransactionId xid) { char path[MAXPGPATH]; - StreamXidHash *ent; - - /* Find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* Delete the change file and release the stream fileset memory */ + /* Delete the changes file. */ changes_filename(path, subid, xid); - FileSetDeleteAll(ent->stream_fileset); - pfree(ent->stream_fileset); - ent->stream_fileset = NULL; - - /* Delete the subxact file and release the memory, if it exist */ - if (ent->subxact_fileset) - { - subxact_filename(path, subid, xid); - FileSetDeleteAll(ent->subxact_fileset); - pfree(ent->subxact_fileset); - ent->subxact_fileset = NULL; - } + BufFileDeleteFileSet(stream_fileset, path, false); - /* Remove the xid entry from the stream xid hash */ - hash_search(xidhash, (void *) &xid, HASH_REMOVE, NULL); + /* Delete the subxact file, if it exist. */ + subxact_filename(path, subid, xid); + BufFileDeleteFileSet(stream_fileset, path, true); } /* @@ -3312,8 +3203,8 @@ stream_cleanup_files(Oid subid, TransactionId xid) * * Open a file for streamed changes from a toplevel transaction identified * by stream_xid (global variable). If it's the first chunk of streamed - * changes for this transaction, initialize the fileset and create the buffile, - * otherwise open the previously created file. + * changes for this transaction, create the buffile, otherwise open the + * previously created file. * * This can only be called at the beginning of a "streaming" block, i.e. * between stream_start/stream_stop messages from the upstream. @@ -3322,20 +3213,13 @@ static void stream_open_file(Oid subid, TransactionId xid, bool first_segment) { char path[MAXPGPATH]; - bool found; MemoryContext oldcxt; - StreamXidHash *ent; Assert(in_streamed_transaction); Assert(OidIsValid(subid)); Assert(TransactionIdIsValid(xid)); Assert(stream_fd == NULL); - /* create or find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_ENTER, - &found); changes_filename(path, subid, xid); elog(DEBUG1, "opening file \"%s\" for streamed changes", path); @@ -3347,49 +3231,18 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) oldcxt = MemoryContextSwitchTo(LogicalStreamingContext); /* - * If this is the first streamed segment, the file must not exist, so make - * sure we're the ones creating it. Otherwise just open the file for - * writing, in append mode. + * If this is the first streamed segment, create the changes file. + * Otherwise, just open the file for writing, in append mode. */ if (first_segment) - { - MemoryContext savectx; - FileSet *fileset; - - if (found) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); - - /* - * We need to maintain fileset across multiple stream start/stop - * calls. So, need to allocate it in a persistent context. - */ - savectx = MemoryContextSwitchTo(ApplyContext); - fileset = palloc(sizeof(FileSet)); - - FileSetInit(fileset); - MemoryContextSwitchTo(savectx); - - stream_fd = BufFileCreateFileSet(fileset, path); - - /* Remember the fileset for the next stream of the same transaction */ - ent->xid = xid; - ent->stream_fileset = fileset; - ent->subxact_fileset = NULL; - } + stream_fd = BufFileCreateFileSet(stream_fileset, path); else { - if (!found) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); - /* * Open the file and seek to the end of the file because we always * append the changes file. */ - stream_fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); + stream_fd = BufFileOpenFileSet(stream_fileset, path, O_RDWR, false); BufFileSeek(stream_fd, 0, 0, SEEK_END); } diff --git a/src/backend/storage/file/buffile.c b/src/backend/storage/file/buffile.c index 5e5409d..d96b25d 100644 --- a/src/backend/storage/file/buffile.c +++ b/src/backend/storage/file/buffile.c @@ -278,10 +278,12 @@ BufFileCreateFileSet(FileSet *fileset, const char *name) * with BufFileCreateFileSet in the same FileSet using the same name. * The backend that created the file must have called BufFileClose() or * BufFileExportFileSet() to make sure that it is ready to be opened by other - * backends and render it read-only. + * backends and render it read-only. If missing_ok is true, it will return + * NULL if the file does not exist otherwise, it will throw an error. */ BufFile * -BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) +BufFileOpenFileSet(FileSet *fileset, const char *name, int mode, + bool missing_ok) { BufFile *file; char segment_name[MAXPGPATH]; @@ -318,10 +320,18 @@ BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) * name. */ if (nfiles == 0) + { + /* free the memory */ + pfree(files); + + if (missing_ok) + return NULL; + ereport(ERROR, (errcode_for_file_access(), errmsg("could not open temporary file \"%s\" from BufFile \"%s\": %m", segment_name, name))); + } file = makeBufFileCommon(nfiles); file->files = files; @@ -341,10 +351,11 @@ BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) * the FileSet to be cleaned up. * * Only one backend should attempt to delete a given name, and should know - * that it exists and has been exported or closed. + * that it exists and has been exported or closed otherwise missing_ok should + * be passed true. */ void -BufFileDeleteFileSet(FileSet *fileset, const char *name) +BufFileDeleteFileSet(FileSet *fileset, const char *name, bool missing_ok) { char segment_name[MAXPGPATH]; int segment = 0; @@ -358,7 +369,7 @@ BufFileDeleteFileSet(FileSet *fileset, const char *name) for (;;) { FileSetSegmentName(segment_name, name, segment); - if (!FileSetDelete(fileset, segment_name, true)) + if (!FileSetDelete(fileset, segment_name, !missing_ok)) break; found = true; ++segment; @@ -366,7 +377,7 @@ BufFileDeleteFileSet(FileSet *fileset, const char *name) CHECK_FOR_INTERRUPTS(); } - if (!found) + if (!found && !missing_ok) elog(ERROR, "could not delete unknown BufFile \"%s\"", name); } diff --git a/src/backend/utils/sort/logtape.c b/src/backend/utils/sort/logtape.c index f7994d7..debf12e1 100644 --- a/src/backend/utils/sort/logtape.c +++ b/src/backend/utils/sort/logtape.c @@ -564,7 +564,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, lt = &lts->tapes[i]; pg_itoa(i, filename); - file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY); + file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY, false); filesize = BufFileSize(file); /* diff --git a/src/backend/utils/sort/sharedtuplestore.c b/src/backend/utils/sort/sharedtuplestore.c index 504ef1c..033088f 100644 --- a/src/backend/utils/sort/sharedtuplestore.c +++ b/src/backend/utils/sort/sharedtuplestore.c @@ -560,7 +560,8 @@ sts_parallel_scan_next(SharedTuplestoreAccessor *accessor, void *meta_data) sts_filename(name, accessor, accessor->read_participant); accessor->read_file = - BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY); + BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY, + false); } /* Seek and load the chunk header. */ diff --git a/src/include/storage/buffile.h b/src/include/storage/buffile.h index 143eada..7ae5ea2 100644 --- a/src/include/storage/buffile.h +++ b/src/include/storage/buffile.h @@ -49,8 +49,9 @@ extern long BufFileAppend(BufFile *target, BufFile *source); extern BufFile *BufFileCreateFileSet(FileSet *fileset, const char *name); extern void BufFileExportFileSet(BufFile *file); extern BufFile *BufFileOpenFileSet(FileSet *fileset, const char *name, - int mode); -extern void BufFileDeleteFileSet(FileSet *fileset, const char *name); + int mode, bool missing_ok); +extern void BufFileDeleteFileSet(FileSet *fileset, const char *name, + bool missing_ok); extern void BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset); #endif /* BUFFILE_H */ -- 1.8.3.1
^ permalink raw reply [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-27 05:26               ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  2021-08-27 06:34                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
@ 2021-08-30 06:15                   ` Masahiko Sawada <sawada.mshk@gmail.com>
  2021-08-31 02:08                     ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  1 sibling, 1 reply; 26+ messages in thread

From: Masahiko Sawada @ 2021-08-30 06:15 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Tom Lane <tgl@sss.pgh.pa.us>; Amit Kapila <amit.kapila16@gmail.com>

On Fri, Aug 27, 2021 at 3:34 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>
> On Fri, Aug 27, 2021 at 10:56 AM houzj.fnst@fujitsu.com
> <houzj.fnst@fujitsu.com> wrote:
> >
> > On Thu, Aug 26, 2021 2:18 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
> >
> > > The patch looks good to me, I have rebased 0002 atop
> > > this patch and also done some cosmetic fixes in 0002.
> >
> > Here are some comments for the 0002 patch.
> >
> > 1)
> >
> > - * toplevel transaction. Each subscription has a separate set of files.
> > + * toplevel transaction. Each subscription has a separate files.
> >
> > a separate files => a separate file
>
> Done
>
> > 2)
> > +        * Otherwise, just open it file for writing, in append mode.
> >          */
> >
> > open it file => open the file
>
> Done
>
> >
> > 3)
> >         if (subxact_data.nsubxacts == 0)
> >         {
> > -               if (ent->subxact_fileset)
> > -               {
> > -                       cleanup_subxact_info();
> > -                       FileSetDeleteAll(ent->subxact_fileset);
> > -                       pfree(ent->subxact_fileset);
> > -                       ent->subxact_fileset = NULL;
> > -               }
> > +               cleanup_subxact_info();
> > +               BufFileDeleteFileSet(stream_fileset, path, true);
> > +
> >
> > Before applying the patch, the code only invoke cleanup_subxact_info() when the
> > file exists. After applying the patch, it will invoke cleanup_subxact_info()
> > either the file exists or not. Is it correct ?
>
> I think this is just structure resetting at the end of the stream.
> Earlier the hash was telling us whether we have ever dirtied that
> structure or not but now we are not maintaining that hash so we just
> reset it at the end of the stream.  I don't think its any bad, in fact
> I think this is much cheaper compared to maining the hash.
>
> >
> > 4)
> >         /*
> > -        * If this is the first streamed segment, the file must not exist, so make
> > -        * sure we're the ones creating it. Otherwise just open the file for
> > -        * writing, in append mode.
> > +        * If this is the first streamed segment, create the changes file.
> > +        * Otherwise, just open it file for writing, in append mode.
> >          */
> >         if (first_segment)
> > -       {
> >         ...
> > -               if (found)
> > -                       ereport(ERROR,
> > -                                       (errcode(ERRCODE_PROTOCOL_VIOLATION),
> > -                                        errmsg_internal("incorrect first-segment flag for streamed replication transaction")));
> >         ...
> > -       }
> > +               stream_fd = BufFileCreateFileSet(stream_fileset, path);
> >
> >
> > Since the function BufFileCreateFileSet() doesn't check the file's existence,
> > the change here seems remove the file existence check which the old code did.
>
> Not really, we were just doing a sanity check of the in memory hash
> entry, now we don't maintain that so we don't need to do that.

Thank you for updating the patch!

The patch looks good to me except for the below comment:

+        /* Delete the subxact file, if it exist. */
+        subxact_filename(path, subid, xid);
+        BufFileDeleteFileSet(stream_fileset, path, true);

s/it exist/it exists/

Regards,

-- 
Masahiko Sawada
EDB:  https://www.enterprisedb.com/





^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-27 05:26               ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  2021-08-27 06:34                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-30 06:15                   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Masahiko Sawada <sawada.mshk@gmail.com>
@ 2021-08-31 02:08                     ` houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  2021-08-31 05:53                       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  0 siblings, 1 reply; 26+ messages in thread

From: houzj.fnst@fujitsu.com @ 2021-08-31 02:08 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Tom Lane <tgl@sss.pgh.pa.us>; Amit Kapila <amit.kapila16@gmail.com>; Masahiko Sawada <sawada.mshk@gmail.com>

From Mon, Aug 30, 2021 2:15 PM Masahiko Sawada <sawada.mshk@gmail.com> wrote:
> On Fri, Aug 27, 2021 at 3:34 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
> >
> > On Fri, Aug 27, 2021 at 10:56 AM houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com> wrote:
> > >
> > > On Thu, Aug 26, 2021 2:18 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
> > >
> > > > The patch looks good to me, I have rebased 0002 atop this patch
> > > > and also done some cosmetic fixes in 0002.
> 
> Thank you for updating the patch!
> 
> The patch looks good to me except for the below comment:
> 
> +        /* Delete the subxact file, if it exist. */
> +        subxact_filename(path, subid, xid);
> +        BufFileDeleteFileSet(stream_fileset, path, true);
> 
> s/it exist/it exists/

Except for Sawada-san's comment, the v6-0002 patch looks good to me.

Best regards,
Hou zj


^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-27 05:26               ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  2021-08-27 06:34                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-30 06:15                   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Masahiko Sawada <sawada.mshk@gmail.com>
  2021-08-31 02:08                     ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
@ 2021-08-31 05:53                       ` Dilip Kumar <dilipbalaut@gmail.com>
  0 siblings, 0 replies; 26+ messages in thread

From: Dilip Kumar @ 2021-08-31 05:53 UTC (permalink / raw)
  To: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; +Cc: Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Tom Lane <tgl@sss.pgh.pa.us>; Amit Kapila <amit.kapila16@gmail.com>; Masahiko Sawada <sawada.mshk@gmail.com>

On Tue, Aug 31, 2021 at 7:39 AM houzj.fnst@fujitsu.com <
houzj.fnst@fujitsu.com> wrote:

> From Mon, Aug 30, 2021 2:15 PM Masahiko Sawada <sawada.mshk@gmail.com>
> wrote:
> > On Fri, Aug 27, 2021 at 3:34 PM Dilip Kumar <dilipbalaut@gmail.com>
> wrote:
> > >
> > > On Fri, Aug 27, 2021 at 10:56 AM houzj.fnst@fujitsu.com <
> houzj.fnst@fujitsu.com> wrote:
> > > >
> > > > On Thu, Aug 26, 2021 2:18 PM Dilip Kumar <dilipbalaut@gmail.com>
> wrote:
> > > >
> > > > > The patch looks good to me, I have rebased 0002 atop this patch
> > > > > and also done some cosmetic fixes in 0002.
> >
> > Thank you for updating the patch!
> >
> > The patch looks good to me except for the below comment:
> >
> > +        /* Delete the subxact file, if it exist. */
> > +        subxact_filename(path, subid, xid);
> > +        BufFileDeleteFileSet(stream_fileset, path, true);
> >
> > s/it exist/it exists/
>
> Except for Sawada-san's comment, the v6-0002 patch looks good to me.
>

Thanks, I will wait for a day to see if there are any other comments on
this, after that I will fix this one issue and post the updated patch.

-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com

^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-27 05:26               ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  2021-08-27 06:34                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
@ 2021-08-31 09:50                   ` Amit Kapila <amit.kapila16@gmail.com>
  2021-09-01 08:23                     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  1 sibling, 1 reply; 26+ messages in thread

From: Amit Kapila @ 2021-08-31 09:50 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Fri, Aug 27, 2021 at 12:04 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>

Few comments on v6-0002*
=========================
1.
-BufFileDeleteFileSet(FileSet *fileset, const char *name)
+BufFileDeleteFileSet(FileSet *fileset, const char *name, bool missing_ok)
 {
  char segment_name[MAXPGPATH];
  int segment = 0;
@@ -358,7 +369,7 @@ BufFileDeleteFileSet(FileSet *fileset, const char *name)
  for (;;)
  {
  FileSetSegmentName(segment_name, name, segment);
- if (!FileSetDelete(fileset, segment_name, true))
+ if (!FileSetDelete(fileset, segment_name, !missing_ok))

I don't think the usage of missing_ok is correct here. If you see
FileSetDelete->PathNameDeleteTemporaryFile, it already tolerates that
the file doesn't exist but gives an error only when it is unable to
link. So, with this missing_ok users (say like worker.c) won't even
get errors when they are not able to remove files whereas I think the
need for the patch is to not get an error when the file doesn't exist.
I think you don't need to change anything in the way we invoke
FileSetDelete.

2.
-static HTAB *xidhash = NULL;
+static FileSet *stream_fileset = NULL;

Can we keep this in LogicalRepWorker and initialize it accordingly?

3.
+ /* Open the subxact file, if it does not exist, create it. */
+ fd = BufFileOpenFileSet(stream_fileset, path, O_RDWR, true);
+ if (fd == NULL)
+ fd = BufFileCreateFileSet(stream_fileset, path);

I think retaining the existing comment: "Create the subxact file if it
not already created, otherwise open the existing file." seems better
here.

4.
  /*
- * If there is no subtransaction then nothing to do, but if already have
- * subxact file then delete that.
+ * If there are no subtransactions, there is nothing to be done, but if
+ * subxacts already exist, delete it.
  */

How about changing the above comment to something like: "Delete the
subxacts file, if exists"?

5. Can we slightly change the commit message as:
Optimize fileset usage in apply worker.

Use one fileset for the entire worker lifetime instead of using
separate filesets for each streaming transaction. Now, the
changes/subxacts files for every streaming transaction will be created
under the same fileset and the files will be deleted after the
transaction is completed.

This patch extends the BufFileOpenFileSet and BufFileDeleteFileSet
APIs to allow users to specify whether to give an error on missing
files.

-- 
With Regards,
Amit Kapila.





^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-27 05:26               ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  2021-08-27 06:34                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-31 09:50                   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
@ 2021-09-01 08:23                     ` Dilip Kumar <dilipbalaut@gmail.com>
  2021-09-01 11:53                       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  0 siblings, 1 reply; 26+ messages in thread

From: Dilip Kumar @ 2021-09-01 08:23 UTC (permalink / raw)
  To: Amit Kapila <amit.kapila16@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Tue, Aug 31, 2021 at 3:20 PM Amit Kapila <amit.kapila16@gmail.com> wrote:
>
> On Fri, Aug 27, 2021 at 12:04 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
> >
>
> Few comments on v6-0002*
> =========================
> 1.
> -BufFileDeleteFileSet(FileSet *fileset, const char *name)
> +BufFileDeleteFileSet(FileSet *fileset, const char *name, bool missing_ok)
>  {
>   char segment_name[MAXPGPATH];
>   int segment = 0;
> @@ -358,7 +369,7 @@ BufFileDeleteFileSet(FileSet *fileset, const char *name)
>   for (;;)
>   {
>   FileSetSegmentName(segment_name, name, segment);
> - if (!FileSetDelete(fileset, segment_name, true))
> + if (!FileSetDelete(fileset, segment_name, !missing_ok))
>
> I don't think the usage of missing_ok is correct here. If you see
> FileSetDelete->PathNameDeleteTemporaryFile, it already tolerates that
> the file doesn't exist but gives an error only when it is unable to
> link. So, with this missing_ok users (say like worker.c) won't even
> get errors when they are not able to remove files whereas I think the
> need for the patch is to not get an error when the file doesn't exist.
> I think you don't need to change anything in the way we invoke
> FileSetDelete.

Right, fixed.

> 2.
> -static HTAB *xidhash = NULL;
> +static FileSet *stream_fileset = NULL;
>
> Can we keep this in LogicalRepWorker and initialize it accordingly?

Done

> 3.
> + /* Open the subxact file, if it does not exist, create it. */
> + fd = BufFileOpenFileSet(stream_fileset, path, O_RDWR, true);
> + if (fd == NULL)
> + fd = BufFileCreateFileSet(stream_fileset, path);
>
> I think retaining the existing comment: "Create the subxact file if it
> not already created, otherwise open the existing file." seems better
> here.

Done

> 4.
>   /*
> - * If there is no subtransaction then nothing to do, but if already have
> - * subxact file then delete that.
> + * If there are no subtransactions, there is nothing to be done, but if
> + * subxacts already exist, delete it.
>   */
>
> How about changing the above comment to something like: "Delete the
> subxacts file, if exists"?

Done

> 5. Can we slightly change the commit message as:
> Optimize fileset usage in apply worker.
>
> Use one fileset for the entire worker lifetime instead of using
> separate filesets for each streaming transaction. Now, the
> changes/subxacts files for every streaming transaction will be created
> under the same fileset and the files will be deleted after the
> transaction is completed.
>
> This patch extends the BufFileOpenFileSet and BufFileDeleteFileSet
> APIs to allow users to specify whether to give an error on missing
> files.

Done


-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com

Attachments:

v7-0001-Optimize-fileset-usage-in-apply-worker.patch (text/x-patch, 19.7K) download From fade8ae2779e8aeda0d1fee3902a93eaedb0187f Mon Sep 17 00:00:00 2001 From: Dilip Kumar <dilipkumar@localhost.localdomain> Date: Fri, 27 Aug 2021 11:49:12 +0530 Subject: [PATCH v7] Optimize fileset usage in apply worker Use one fileset for the entire worker lifetime instead of using separate filesets for each streaming transaction. Now, the changes/subxacts files for every streaming transaction will be created under the same fileset and the files will be deleted after the transaction is completed. This patch extends the BufFileOpenFileSet and BufFileDeleteFileSet APIs to allow users to specify whether to give an error on missing files. --- src/backend/replication/logical/launcher.c | 6 +- src/backend/replication/logical/worker.c | 249 +++++------------------------ src/backend/storage/file/buffile.c | 21 ++- src/backend/utils/sort/logtape.c | 2 +- src/backend/utils/sort/sharedtuplestore.c | 3 +- src/include/replication/worker_internal.h | 11 +- src/include/storage/buffile.h | 5 +- 7 files changed, 80 insertions(+), 217 deletions(-) diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 8b1772d..3fb4caa 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -379,6 +379,7 @@ retry: worker->relid = relid; worker->relstate = SUBREL_STATE_UNKNOWN; worker->relstate_lsn = InvalidXLogRecPtr; + worker->stream_fileset = NULL; worker->last_lsn = InvalidXLogRecPtr; TIMESTAMP_NOBEGIN(worker->last_send_time); TIMESTAMP_NOBEGIN(worker->last_recv_time); @@ -648,8 +649,9 @@ logicalrep_worker_onexit(int code, Datum arg) logicalrep_worker_detach(); - /* Cleanup filesets used for streaming transactions. */ - logicalrep_worker_cleanupfileset(); + /* Cleanup fileset used for streaming transactions. */ + if (MyLogicalRepWorker->stream_fileset != NULL) + FileSetDeleteAll(MyLogicalRepWorker->stream_fileset); ApplyLauncherWakeup(); } diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index bfb7d1a..a222cb3 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -236,20 +236,6 @@ static ApplyErrorCallbackArg apply_error_callback_arg = .ts = 0, }; -/* - * Stream xid hash entry. Whenever we see a new xid we create this entry in the - * xidhash and along with it create the streaming file and store the fileset handle. - * The subxact file is created iff there is any subxact info under this xid. This - * entry is used on the subsequent streams for the xid to get the corresponding - * fileset handles, so storing them in hash makes the search faster. - */ -typedef struct StreamXidHash -{ - TransactionId xid; /* xid is the hash key and must be first */ - FileSet *stream_fileset; /* file set for stream data */ - FileSet *subxact_fileset; /* file set for subxact info */ -} StreamXidHash; - static MemoryContext ApplyMessageContext = NULL; MemoryContext ApplyContext = NULL; @@ -269,12 +255,6 @@ static bool in_streamed_transaction = false; static TransactionId stream_xid = InvalidTransactionId; -/* - * Hash table for storing the streaming xid information along with filesets - * for streaming and subxact files. - */ -static HTAB *xidhash = NULL; - /* BufFile handle of the current streaming file */ static BufFile *stream_fd = NULL; @@ -1118,7 +1098,6 @@ static void apply_handle_stream_start(StringInfo s) { bool first_segment; - HASHCTL hash_ctl; if (in_streamed_transaction) ereport(ERROR, @@ -1148,17 +1127,20 @@ apply_handle_stream_start(StringInfo s) set_apply_error_context_xact(stream_xid, 0); /* - * Initialize the xidhash table if we haven't yet. This will be used for + * Initialize the stream_fileset if we haven't yet. This will be used for * the entire duration of the apply worker so create it in permanent * context. */ - if (xidhash == NULL) + if (MyLogicalRepWorker->stream_fileset == NULL) { - hash_ctl.keysize = sizeof(TransactionId); - hash_ctl.entrysize = sizeof(StreamXidHash); - hash_ctl.hcxt = ApplyContext; - xidhash = hash_create("StreamXidHash", 1024, &hash_ctl, - HASH_ELEM | HASH_BLOBS | HASH_CONTEXT); + MemoryContext oldctx; + + oldctx = MemoryContextSwitchTo(ApplyContext); + + MyLogicalRepWorker->stream_fileset = palloc(sizeof(FileSet)); + FileSetInit(MyLogicalRepWorker->stream_fileset); + + MemoryContextSwitchTo(oldctx); } /* open the spool file for this transaction */ @@ -1253,7 +1235,6 @@ apply_handle_stream_abort(StringInfo s) BufFile *fd; bool found = false; char path[MAXPGPATH]; - StreamXidHash *ent; set_apply_error_context_xact(subxid, 0); @@ -1285,19 +1266,10 @@ apply_handle_stream_abort(StringInfo s) return; } - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* open the changes file */ changes_filename(path, MyLogicalRepWorker->subid, xid); - fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(MyLogicalRepWorker->stream_fileset, path, + O_RDWR, false); /* OK, truncate the file at the right offset */ BufFileTruncateFileSet(fd, subxact_data.subxacts[subidx].fileno, @@ -1327,7 +1299,6 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) int nchanges; char path[MAXPGPATH]; char *buffer = NULL; - StreamXidHash *ent; MemoryContext oldcxt; BufFile *fd; @@ -1345,17 +1316,8 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) changes_filename(path, MyLogicalRepWorker->subid, xid); elog(DEBUG1, "replaying changes from file \"%s\"", path); - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - - fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(MyLogicalRepWorker->stream_fileset, path, O_RDONLY, + false); buffer = palloc(BLCKSZ); initStringInfo(&s2); @@ -2542,30 +2504,6 @@ UpdateWorkerStats(XLogRecPtr last_lsn, TimestampTz send_time, bool reply) } /* - * Cleanup filesets. - */ -void -logicalrep_worker_cleanupfileset(void) -{ - HASH_SEQ_STATUS status; - StreamXidHash *hentry; - - /* Remove all the pending stream and subxact filesets. */ - if (xidhash) - { - hash_seq_init(&status, xidhash); - while ((hentry = (StreamXidHash *) hash_seq_search(&status)) != NULL) - { - FileSetDeleteAll(hentry->stream_fileset); - - /* Delete the subxact fileset iff it is created. */ - if (hentry->subxact_fileset) - FileSetDeleteAll(hentry->subxact_fileset); - } - } -} - -/* * Apply main loop. */ static void @@ -3026,58 +2964,30 @@ subxact_info_write(Oid subid, TransactionId xid) { char path[MAXPGPATH]; Size len; - StreamXidHash *ent; BufFile *fd; Assert(TransactionIdIsValid(xid)); - /* Find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - /* By this time we must have created the transaction entry */ - Assert(ent); + /* Get the subxact filename. */ + subxact_filename(path, subid, xid); - /* - * If there is no subtransaction then nothing to do, but if already have - * subxact file then delete that. - */ + /* Delete the subxacts file, if exists. */ if (subxact_data.nsubxacts == 0) { - if (ent->subxact_fileset) - { - cleanup_subxact_info(); - FileSetDeleteAll(ent->subxact_fileset); - pfree(ent->subxact_fileset); - ent->subxact_fileset = NULL; - } + cleanup_subxact_info(); + BufFileDeleteFileSet(MyLogicalRepWorker->stream_fileset, path, true); + return; } - subxact_filename(path, subid, xid); - /* * Create the subxact file if it not already created, otherwise open the * existing file. */ - if (ent->subxact_fileset == NULL) - { - MemoryContext oldctx; - - /* - * We need to maintain fileset across multiple stream start/stop - * calls. So, need to allocate it in a persistent context. - */ - oldctx = MemoryContextSwitchTo(ApplyContext); - ent->subxact_fileset = palloc(sizeof(FileSet)); - FileSetInit(ent->subxact_fileset); - MemoryContextSwitchTo(oldctx); - - fd = BufFileCreateFileSet(ent->subxact_fileset, path); - } - else - fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(MyLogicalRepWorker->stream_fileset, path, O_RDWR, + true); + if (fd == NULL) + fd = BufFileCreateFileSet(MyLogicalRepWorker->stream_fileset, path); len = sizeof(SubXactInfo) * subxact_data.nsubxacts; @@ -3104,34 +3014,21 @@ subxact_info_read(Oid subid, TransactionId xid) char path[MAXPGPATH]; Size len; BufFile *fd; - StreamXidHash *ent; MemoryContext oldctx; Assert(!subxact_data.subxacts); Assert(subxact_data.nsubxacts == 0); Assert(subxact_data.nsubxacts_max == 0); - /* Find the stream xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* - * If subxact_fileset is not valid that mean we don't have any subxact - * info + * Open the subxact file for the input streaming xid, just return if the + * file does not exist. */ - if (ent->subxact_fileset == NULL) - return; - subxact_filename(path, subid, xid); - - fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(MyLogicalRepWorker->stream_fileset, path, O_RDONLY, + true); + if (fd == NULL) + return; /* read number of subxact items */ if (BufFileRead(fd, &subxact_data.nsubxacts, @@ -3267,42 +3164,20 @@ changes_filename(char *path, Oid subid, TransactionId xid) * Cleanup files for a subscription / toplevel transaction. * * Remove files with serialized changes and subxact info for a particular - * toplevel transaction. Each subscription has a separate set of files. + * toplevel transaction. Each subscription has a separate file. */ static void stream_cleanup_files(Oid subid, TransactionId xid) { char path[MAXPGPATH]; - StreamXidHash *ent; - - /* Find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* Delete the change file and release the stream fileset memory */ + /* Delete the changes file. */ changes_filename(path, subid, xid); - FileSetDeleteAll(ent->stream_fileset); - pfree(ent->stream_fileset); - ent->stream_fileset = NULL; + BufFileDeleteFileSet(MyLogicalRepWorker->stream_fileset, path, false); - /* Delete the subxact file and release the memory, if it exist */ - if (ent->subxact_fileset) - { - subxact_filename(path, subid, xid); - FileSetDeleteAll(ent->subxact_fileset); - pfree(ent->subxact_fileset); - ent->subxact_fileset = NULL; - } - - /* Remove the xid entry from the stream xid hash */ - hash_search(xidhash, (void *) &xid, HASH_REMOVE, NULL); + /* Delete the subxact file, if it exists. */ + subxact_filename(path, subid, xid); + BufFileDeleteFileSet(MyLogicalRepWorker->stream_fileset, path, true); } /* @@ -3312,8 +3187,8 @@ stream_cleanup_files(Oid subid, TransactionId xid) * * Open a file for streamed changes from a toplevel transaction identified * by stream_xid (global variable). If it's the first chunk of streamed - * changes for this transaction, initialize the fileset and create the buffile, - * otherwise open the previously created file. + * changes for this transaction, create the buffile, otherwise open the + * previously created file. * * This can only be called at the beginning of a "streaming" block, i.e. * between stream_start/stream_stop messages from the upstream. @@ -3322,20 +3197,13 @@ static void stream_open_file(Oid subid, TransactionId xid, bool first_segment) { char path[MAXPGPATH]; - bool found; MemoryContext oldcxt; - StreamXidHash *ent; Assert(in_streamed_transaction); Assert(OidIsValid(subid)); Assert(TransactionIdIsValid(xid)); Assert(stream_fd == NULL); - /* create or find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_ENTER, - &found); changes_filename(path, subid, xid); elog(DEBUG1, "opening file \"%s\" for streamed changes", path); @@ -3347,49 +3215,20 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) oldcxt = MemoryContextSwitchTo(LogicalStreamingContext); /* - * If this is the first streamed segment, the file must not exist, so make - * sure we're the ones creating it. Otherwise just open the file for - * writing, in append mode. + * If this is the first streamed segment, create the changes file. + * Otherwise, just open the file for writing, in append mode. */ if (first_segment) - { - MemoryContext savectx; - FileSet *fileset; - - if (found) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); - - /* - * We need to maintain fileset across multiple stream start/stop - * calls. So, need to allocate it in a persistent context. - */ - savectx = MemoryContextSwitchTo(ApplyContext); - fileset = palloc(sizeof(FileSet)); - - FileSetInit(fileset); - MemoryContextSwitchTo(savectx); - - stream_fd = BufFileCreateFileSet(fileset, path); - - /* Remember the fileset for the next stream of the same transaction */ - ent->xid = xid; - ent->stream_fileset = fileset; - ent->subxact_fileset = NULL; - } + stream_fd = BufFileCreateFileSet(MyLogicalRepWorker->stream_fileset, + path); else { - if (!found) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); - /* * Open the file and seek to the end of the file because we always * append the changes file. */ - stream_fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); + stream_fd = BufFileOpenFileSet(MyLogicalRepWorker->stream_fileset, + path, O_RDWR, false); BufFileSeek(stream_fd, 0, 0, SEEK_END); } diff --git a/src/backend/storage/file/buffile.c b/src/backend/storage/file/buffile.c index 5e5409d..5b5a6e1 100644 --- a/src/backend/storage/file/buffile.c +++ b/src/backend/storage/file/buffile.c @@ -278,10 +278,12 @@ BufFileCreateFileSet(FileSet *fileset, const char *name) * with BufFileCreateFileSet in the same FileSet using the same name. * The backend that created the file must have called BufFileClose() or * BufFileExportFileSet() to make sure that it is ready to be opened by other - * backends and render it read-only. + * backends and render it read-only. If missing_ok is true, it will return + * NULL if the file does not exist otherwise, it will throw an error. */ BufFile * -BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) +BufFileOpenFileSet(FileSet *fileset, const char *name, int mode, + bool missing_ok) { BufFile *file; char segment_name[MAXPGPATH]; @@ -318,10 +320,18 @@ BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) * name. */ if (nfiles == 0) + { + /* free the memory */ + pfree(files); + + if (missing_ok) + return NULL; + ereport(ERROR, (errcode_for_file_access(), errmsg("could not open temporary file \"%s\" from BufFile \"%s\": %m", segment_name, name))); + } file = makeBufFileCommon(nfiles); file->files = files; @@ -341,10 +351,11 @@ BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) * the FileSet to be cleaned up. * * Only one backend should attempt to delete a given name, and should know - * that it exists and has been exported or closed. + * that it exists and has been exported or closed otherwise missing_ok should + * be passed true. */ void -BufFileDeleteFileSet(FileSet *fileset, const char *name) +BufFileDeleteFileSet(FileSet *fileset, const char *name, bool missing_ok) { char segment_name[MAXPGPATH]; int segment = 0; @@ -366,7 +377,7 @@ BufFileDeleteFileSet(FileSet *fileset, const char *name) CHECK_FOR_INTERRUPTS(); } - if (!found) + if (!found && !missing_ok) elog(ERROR, "could not delete unknown BufFile \"%s\"", name); } diff --git a/src/backend/utils/sort/logtape.c b/src/backend/utils/sort/logtape.c index f7994d7..debf12e1 100644 --- a/src/backend/utils/sort/logtape.c +++ b/src/backend/utils/sort/logtape.c @@ -564,7 +564,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, lt = &lts->tapes[i]; pg_itoa(i, filename); - file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY); + file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY, false); filesize = BufFileSize(file); /* diff --git a/src/backend/utils/sort/sharedtuplestore.c b/src/backend/utils/sort/sharedtuplestore.c index 504ef1c..033088f 100644 --- a/src/backend/utils/sort/sharedtuplestore.c +++ b/src/backend/utils/sort/sharedtuplestore.c @@ -560,7 +560,8 @@ sts_parallel_scan_next(SharedTuplestoreAccessor *accessor, void *meta_data) sts_filename(name, accessor, accessor->read_participant); accessor->read_file = - BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY); + BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY, + false); } /* Seek and load the chunk header. */ diff --git a/src/include/replication/worker_internal.h b/src/include/replication/worker_internal.h index a6c9d4e..1a2437a 100644 --- a/src/include/replication/worker_internal.h +++ b/src/include/replication/worker_internal.h @@ -50,6 +50,16 @@ typedef struct LogicalRepWorker XLogRecPtr relstate_lsn; slock_t relmutex; + /* + * The fileset is used by the worker to create the changes and subxact + * files for the streaming transaction. Upon the arrival of the first + * streaming transaction, the fileset will be initialized, and it will be + * deleted when the worker exits. Under this, separate buffiles would be + * created for each transaction and would be deleted after the transaction + * is completed. + */ + FileSet *stream_fileset; + /* Stats. */ XLogRecPtr last_lsn; TimestampTz last_send_time; @@ -79,7 +89,6 @@ extern void logicalrep_worker_launch(Oid dbid, Oid subid, const char *subname, extern void logicalrep_worker_stop(Oid subid, Oid relid); extern void logicalrep_worker_wakeup(Oid subid, Oid relid); extern void logicalrep_worker_wakeup_ptr(LogicalRepWorker *worker); -extern void logicalrep_worker_cleanupfileset(void); extern int logicalrep_sync_worker_count(Oid subid); diff --git a/src/include/storage/buffile.h b/src/include/storage/buffile.h index 143eada..7ae5ea2 100644 --- a/src/include/storage/buffile.h +++ b/src/include/storage/buffile.h @@ -49,8 +49,9 @@ extern long BufFileAppend(BufFile *target, BufFile *source); extern BufFile *BufFileCreateFileSet(FileSet *fileset, const char *name); extern void BufFileExportFileSet(BufFile *file); extern BufFile *BufFileOpenFileSet(FileSet *fileset, const char *name, - int mode); -extern void BufFileDeleteFileSet(FileSet *fileset, const char *name); + int mode, bool missing_ok); +extern void BufFileDeleteFileSet(FileSet *fileset, const char *name, + bool missing_ok); extern void BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset); #endif /* BUFFILE_H */ -- 1.8.3.1
^ permalink raw reply [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-27 05:26               ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  2021-08-27 06:34                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-31 09:50                   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-09-01 08:23                     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
@ 2021-09-01 11:53                       ` Amit Kapila <amit.kapila16@gmail.com>
  2021-09-01 12:02                         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-11-29 18:10                         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Andres Freund <andres@anarazel.de>
  0 siblings, 2 replies; 26+ messages in thread

From: Amit Kapila @ 2021-09-01 11:53 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Wed, Sep 1, 2021 at 1:53 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>

The latest patch looks good to me. I have made some changes in the
comments, see attached. I am planning to push this tomorrow unless you
or others have any comments on it.

-- 
With Regards,
Amit Kapila.

Attachments:

v8-0001-Optimize-fileset-usage-in-apply-worker.patch (application/octet-stream, 20.3K) download From 5c9712f210e966940448792e667c3496f78a642f Mon Sep 17 00:00:00 2001 From: Dilip Kumar <dilipkumar@localhost.localdomain> Date: Fri, 27 Aug 2021 11:49:12 +0530 Subject: [PATCH v8] Optimize fileset usage in apply worker. Use one fileset for the entire worker lifetime instead of using separate filesets for each streaming transaction. Now, the changes/subxacts files for every streaming transaction will be created under the same fileset and the files will be deleted after the transaction is completed. This patch extends the BufFileOpenFileSet and BufFileDeleteFileSet APIs to allow users to specify whether to give an error on missing files. Author: Dilip Kumar, based on suggestion by Thomas Munro Reviewed-by: Hou Zhijie, Masahiko Sawada, Amit Kapila Discussion: https://postgr.es/m/E1mCC6U-0004Ik-Fs@gemulon.postgresql.org --- src/backend/replication/logical/launcher.c | 6 +- src/backend/replication/logical/worker.c | 257 ++++++----------------------- src/backend/storage/file/buffile.c | 22 ++- src/backend/utils/sort/logtape.c | 2 +- src/backend/utils/sort/sharedtuplestore.c | 3 +- src/include/replication/worker_internal.h | 10 +- src/include/storage/buffile.h | 5 +- 7 files changed, 86 insertions(+), 219 deletions(-) diff --git a/src/backend/replication/logical/launcher.c b/src/backend/replication/logical/launcher.c index 8b1772d..3fb4caa 100644 --- a/src/backend/replication/logical/launcher.c +++ b/src/backend/replication/logical/launcher.c @@ -379,6 +379,7 @@ retry: worker->relid = relid; worker->relstate = SUBREL_STATE_UNKNOWN; worker->relstate_lsn = InvalidXLogRecPtr; + worker->stream_fileset = NULL; worker->last_lsn = InvalidXLogRecPtr; TIMESTAMP_NOBEGIN(worker->last_send_time); TIMESTAMP_NOBEGIN(worker->last_recv_time); @@ -648,8 +649,9 @@ logicalrep_worker_onexit(int code, Datum arg) logicalrep_worker_detach(); - /* Cleanup filesets used for streaming transactions. */ - logicalrep_worker_cleanupfileset(); + /* Cleanup fileset used for streaming transactions. */ + if (MyLogicalRepWorker->stream_fileset != NULL) + FileSetDeleteAll(MyLogicalRepWorker->stream_fileset); ApplyLauncherWakeup(); } diff --git a/src/backend/replication/logical/worker.c b/src/backend/replication/logical/worker.c index bfb7d1a..8d96c92 100644 --- a/src/backend/replication/logical/worker.c +++ b/src/backend/replication/logical/worker.c @@ -236,20 +236,6 @@ static ApplyErrorCallbackArg apply_error_callback_arg = .ts = 0, }; -/* - * Stream xid hash entry. Whenever we see a new xid we create this entry in the - * xidhash and along with it create the streaming file and store the fileset handle. - * The subxact file is created iff there is any subxact info under this xid. This - * entry is used on the subsequent streams for the xid to get the corresponding - * fileset handles, so storing them in hash makes the search faster. - */ -typedef struct StreamXidHash -{ - TransactionId xid; /* xid is the hash key and must be first */ - FileSet *stream_fileset; /* file set for stream data */ - FileSet *subxact_fileset; /* file set for subxact info */ -} StreamXidHash; - static MemoryContext ApplyMessageContext = NULL; MemoryContext ApplyContext = NULL; @@ -269,12 +255,6 @@ static bool in_streamed_transaction = false; static TransactionId stream_xid = InvalidTransactionId; -/* - * Hash table for storing the streaming xid information along with filesets - * for streaming and subxact files. - */ -static HTAB *xidhash = NULL; - /* BufFile handle of the current streaming file */ static BufFile *stream_fd = NULL; @@ -1118,7 +1098,6 @@ static void apply_handle_stream_start(StringInfo s) { bool first_segment; - HASHCTL hash_ctl; if (in_streamed_transaction) ereport(ERROR, @@ -1148,17 +1127,23 @@ apply_handle_stream_start(StringInfo s) set_apply_error_context_xact(stream_xid, 0); /* - * Initialize the xidhash table if we haven't yet. This will be used for - * the entire duration of the apply worker so create it in permanent - * context. + * Initialize the worker's stream_fileset if we haven't yet. This will be + * used for the entire duration of the worker so create it in a permanent + * context. We create this on the very first streaming message from any + * transaction and then use it for this and other streaming transactions. + * Now, we could create a fileset at the start of the worker as well but + * then we won't be sure that it will ever be used. */ - if (xidhash == NULL) + if (MyLogicalRepWorker->stream_fileset == NULL) { - hash_ctl.keysize = sizeof(TransactionId); - hash_ctl.entrysize = sizeof(StreamXidHash); - hash_ctl.hcxt = ApplyContext; - xidhash = hash_create("StreamXidHash", 1024, &hash_ctl, - HASH_ELEM | HASH_BLOBS | HASH_CONTEXT); + MemoryContext oldctx; + + oldctx = MemoryContextSwitchTo(ApplyContext); + + MyLogicalRepWorker->stream_fileset = palloc(sizeof(FileSet)); + FileSetInit(MyLogicalRepWorker->stream_fileset); + + MemoryContextSwitchTo(oldctx); } /* open the spool file for this transaction */ @@ -1253,7 +1238,6 @@ apply_handle_stream_abort(StringInfo s) BufFile *fd; bool found = false; char path[MAXPGPATH]; - StreamXidHash *ent; set_apply_error_context_xact(subxid, 0); @@ -1285,19 +1269,10 @@ apply_handle_stream_abort(StringInfo s) return; } - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* open the changes file */ changes_filename(path, MyLogicalRepWorker->subid, xid); - fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(MyLogicalRepWorker->stream_fileset, path, + O_RDWR, false); /* OK, truncate the file at the right offset */ BufFileTruncateFileSet(fd, subxact_data.subxacts[subidx].fileno, @@ -1327,7 +1302,6 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) int nchanges; char path[MAXPGPATH]; char *buffer = NULL; - StreamXidHash *ent; MemoryContext oldcxt; BufFile *fd; @@ -1345,17 +1319,8 @@ apply_spooled_messages(TransactionId xid, XLogRecPtr lsn) changes_filename(path, MyLogicalRepWorker->subid, xid); elog(DEBUG1, "replaying changes from file \"%s\"", path); - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - - fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(MyLogicalRepWorker->stream_fileset, path, O_RDONLY, + false); buffer = palloc(BLCKSZ); initStringInfo(&s2); @@ -2542,30 +2507,6 @@ UpdateWorkerStats(XLogRecPtr last_lsn, TimestampTz send_time, bool reply) } /* - * Cleanup filesets. - */ -void -logicalrep_worker_cleanupfileset(void) -{ - HASH_SEQ_STATUS status; - StreamXidHash *hentry; - - /* Remove all the pending stream and subxact filesets. */ - if (xidhash) - { - hash_seq_init(&status, xidhash); - while ((hentry = (StreamXidHash *) hash_seq_search(&status)) != NULL) - { - FileSetDeleteAll(hentry->stream_fileset); - - /* Delete the subxact fileset iff it is created. */ - if (hentry->subxact_fileset) - FileSetDeleteAll(hentry->subxact_fileset); - } - } -} - -/* * Apply main loop. */ static void @@ -3026,58 +2967,30 @@ subxact_info_write(Oid subid, TransactionId xid) { char path[MAXPGPATH]; Size len; - StreamXidHash *ent; BufFile *fd; Assert(TransactionIdIsValid(xid)); - /* Find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - /* By this time we must have created the transaction entry */ - Assert(ent); + /* construct the subxact filename */ + subxact_filename(path, subid, xid); - /* - * If there is no subtransaction then nothing to do, but if already have - * subxact file then delete that. - */ + /* Delete the subxacts file, if exists. */ if (subxact_data.nsubxacts == 0) { - if (ent->subxact_fileset) - { - cleanup_subxact_info(); - FileSetDeleteAll(ent->subxact_fileset); - pfree(ent->subxact_fileset); - ent->subxact_fileset = NULL; - } + cleanup_subxact_info(); + BufFileDeleteFileSet(MyLogicalRepWorker->stream_fileset, path, true); + return; } - subxact_filename(path, subid, xid); - /* * Create the subxact file if it not already created, otherwise open the * existing file. */ - if (ent->subxact_fileset == NULL) - { - MemoryContext oldctx; - - /* - * We need to maintain fileset across multiple stream start/stop - * calls. So, need to allocate it in a persistent context. - */ - oldctx = MemoryContextSwitchTo(ApplyContext); - ent->subxact_fileset = palloc(sizeof(FileSet)); - FileSetInit(ent->subxact_fileset); - MemoryContextSwitchTo(oldctx); - - fd = BufFileCreateFileSet(ent->subxact_fileset, path); - } - else - fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDWR); + fd = BufFileOpenFileSet(MyLogicalRepWorker->stream_fileset, path, O_RDWR, + true); + if (fd == NULL) + fd = BufFileCreateFileSet(MyLogicalRepWorker->stream_fileset, path); len = sizeof(SubXactInfo) * subxact_data.nsubxacts; @@ -3104,34 +3017,21 @@ subxact_info_read(Oid subid, TransactionId xid) char path[MAXPGPATH]; Size len; BufFile *fd; - StreamXidHash *ent; MemoryContext oldctx; Assert(!subxact_data.subxacts); Assert(subxact_data.nsubxacts == 0); Assert(subxact_data.nsubxacts_max == 0); - /* Find the stream xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* - * If subxact_fileset is not valid that mean we don't have any subxact - * info + * If the subxact file doesn't exist that means we don't have any subxact + * info. */ - if (ent->subxact_fileset == NULL) - return; - subxact_filename(path, subid, xid); - - fd = BufFileOpenFileSet(ent->subxact_fileset, path, O_RDONLY); + fd = BufFileOpenFileSet(MyLogicalRepWorker->stream_fileset, path, O_RDONLY, + true); + if (fd == NULL) + return; /* read number of subxact items */ if (BufFileRead(fd, &subxact_data.nsubxacts, @@ -3267,42 +3167,21 @@ changes_filename(char *path, Oid subid, TransactionId xid) * Cleanup files for a subscription / toplevel transaction. * * Remove files with serialized changes and subxact info for a particular - * toplevel transaction. Each subscription has a separate set of files. + * toplevel transaction. Each subscription has a separate set of files + * for any toplevel transaction. */ static void stream_cleanup_files(Oid subid, TransactionId xid) { char path[MAXPGPATH]; - StreamXidHash *ent; - - /* Find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_FIND, - NULL); - if (!ent) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("transaction %u not found in stream XID hash table", - xid))); - /* Delete the change file and release the stream fileset memory */ + /* Delete the changes file. */ changes_filename(path, subid, xid); - FileSetDeleteAll(ent->stream_fileset); - pfree(ent->stream_fileset); - ent->stream_fileset = NULL; + BufFileDeleteFileSet(MyLogicalRepWorker->stream_fileset, path, false); - /* Delete the subxact file and release the memory, if it exist */ - if (ent->subxact_fileset) - { - subxact_filename(path, subid, xid); - FileSetDeleteAll(ent->subxact_fileset); - pfree(ent->subxact_fileset); - ent->subxact_fileset = NULL; - } - - /* Remove the xid entry from the stream xid hash */ - hash_search(xidhash, (void *) &xid, HASH_REMOVE, NULL); + /* Delete the subxact file, if it exists. */ + subxact_filename(path, subid, xid); + BufFileDeleteFileSet(MyLogicalRepWorker->stream_fileset, path, true); } /* @@ -3312,8 +3191,8 @@ stream_cleanup_files(Oid subid, TransactionId xid) * * Open a file for streamed changes from a toplevel transaction identified * by stream_xid (global variable). If it's the first chunk of streamed - * changes for this transaction, initialize the fileset and create the buffile, - * otherwise open the previously created file. + * changes for this transaction, create the buffile, otherwise open the + * previously created file. * * This can only be called at the beginning of a "streaming" block, i.e. * between stream_start/stream_stop messages from the upstream. @@ -3322,20 +3201,13 @@ static void stream_open_file(Oid subid, TransactionId xid, bool first_segment) { char path[MAXPGPATH]; - bool found; MemoryContext oldcxt; - StreamXidHash *ent; Assert(in_streamed_transaction); Assert(OidIsValid(subid)); Assert(TransactionIdIsValid(xid)); Assert(stream_fd == NULL); - /* create or find the xid entry in the xidhash */ - ent = (StreamXidHash *) hash_search(xidhash, - (void *) &xid, - HASH_ENTER, - &found); changes_filename(path, subid, xid); elog(DEBUG1, "opening file \"%s\" for streamed changes", path); @@ -3347,49 +3219,20 @@ stream_open_file(Oid subid, TransactionId xid, bool first_segment) oldcxt = MemoryContextSwitchTo(LogicalStreamingContext); /* - * If this is the first streamed segment, the file must not exist, so make - * sure we're the ones creating it. Otherwise just open the file for - * writing, in append mode. + * If this is the first streamed segment, create the changes file. + * Otherwise, just open the file for writing, in append mode. */ if (first_segment) - { - MemoryContext savectx; - FileSet *fileset; - - if (found) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); - - /* - * We need to maintain fileset across multiple stream start/stop - * calls. So, need to allocate it in a persistent context. - */ - savectx = MemoryContextSwitchTo(ApplyContext); - fileset = palloc(sizeof(FileSet)); - - FileSetInit(fileset); - MemoryContextSwitchTo(savectx); - - stream_fd = BufFileCreateFileSet(fileset, path); - - /* Remember the fileset for the next stream of the same transaction */ - ent->xid = xid; - ent->stream_fileset = fileset; - ent->subxact_fileset = NULL; - } + stream_fd = BufFileCreateFileSet(MyLogicalRepWorker->stream_fileset, + path); else { - if (!found) - ereport(ERROR, - (errcode(ERRCODE_PROTOCOL_VIOLATION), - errmsg_internal("incorrect first-segment flag for streamed replication transaction"))); - /* * Open the file and seek to the end of the file because we always * append the changes file. */ - stream_fd = BufFileOpenFileSet(ent->stream_fileset, path, O_RDWR); + stream_fd = BufFileOpenFileSet(MyLogicalRepWorker->stream_fileset, + path, O_RDWR, false); BufFileSeek(stream_fd, 0, 0, SEEK_END); } diff --git a/src/backend/storage/file/buffile.c b/src/backend/storage/file/buffile.c index 5e5409d..ff3aa67 100644 --- a/src/backend/storage/file/buffile.c +++ b/src/backend/storage/file/buffile.c @@ -278,10 +278,13 @@ BufFileCreateFileSet(FileSet *fileset, const char *name) * with BufFileCreateFileSet in the same FileSet using the same name. * The backend that created the file must have called BufFileClose() or * BufFileExportFileSet() to make sure that it is ready to be opened by other - * backends and render it read-only. + * backends and render it read-only. If missing_ok is true, which indicates + * that missing files can be safely ignored, then return NULL if the BufFile + * with the given name is not found, otherwise, throw an error. */ BufFile * -BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) +BufFileOpenFileSet(FileSet *fileset, const char *name, int mode, + bool missing_ok) { BufFile *file; char segment_name[MAXPGPATH]; @@ -318,10 +321,18 @@ BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) * name. */ if (nfiles == 0) + { + /* free the memory */ + pfree(files); + + if (missing_ok) + return NULL; + ereport(ERROR, (errcode_for_file_access(), errmsg("could not open temporary file \"%s\" from BufFile \"%s\": %m", segment_name, name))); + } file = makeBufFileCommon(nfiles); file->files = files; @@ -341,10 +352,11 @@ BufFileOpenFileSet(FileSet *fileset, const char *name, int mode) * the FileSet to be cleaned up. * * Only one backend should attempt to delete a given name, and should know - * that it exists and has been exported or closed. + * that it exists and has been exported or closed otherwise missing_ok should + * be passed true. */ void -BufFileDeleteFileSet(FileSet *fileset, const char *name) +BufFileDeleteFileSet(FileSet *fileset, const char *name, bool missing_ok) { char segment_name[MAXPGPATH]; int segment = 0; @@ -366,7 +378,7 @@ BufFileDeleteFileSet(FileSet *fileset, const char *name) CHECK_FOR_INTERRUPTS(); } - if (!found) + if (!found && !missing_ok) elog(ERROR, "could not delete unknown BufFile \"%s\"", name); } diff --git a/src/backend/utils/sort/logtape.c b/src/backend/utils/sort/logtape.c index f7994d7..debf12e1 100644 --- a/src/backend/utils/sort/logtape.c +++ b/src/backend/utils/sort/logtape.c @@ -564,7 +564,7 @@ ltsConcatWorkerTapes(LogicalTapeSet *lts, TapeShare *shared, lt = &lts->tapes[i]; pg_itoa(i, filename); - file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY); + file = BufFileOpenFileSet(&fileset->fs, filename, O_RDONLY, false); filesize = BufFileSize(file); /* diff --git a/src/backend/utils/sort/sharedtuplestore.c b/src/backend/utils/sort/sharedtuplestore.c index 504ef1c..033088f 100644 --- a/src/backend/utils/sort/sharedtuplestore.c +++ b/src/backend/utils/sort/sharedtuplestore.c @@ -560,7 +560,8 @@ sts_parallel_scan_next(SharedTuplestoreAccessor *accessor, void *meta_data) sts_filename(name, accessor, accessor->read_participant); accessor->read_file = - BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY); + BufFileOpenFileSet(&accessor->fileset->fs, name, O_RDONLY, + false); } /* Seek and load the chunk header. */ diff --git a/src/include/replication/worker_internal.h b/src/include/replication/worker_internal.h index a6c9d4e..c00be2a 100644 --- a/src/include/replication/worker_internal.h +++ b/src/include/replication/worker_internal.h @@ -50,6 +50,15 @@ typedef struct LogicalRepWorker XLogRecPtr relstate_lsn; slock_t relmutex; + /* + * Used to create the changes and subxact files for the streaming + * transactions. Upon the arrival of the first streaming transaction, the + * fileset will be initialized, and it will be deleted when the worker + * exits. Under this, separate buffiles would be created for each + * transaction which will be deleted after the transaction is finished. + */ + FileSet *stream_fileset; + /* Stats. */ XLogRecPtr last_lsn; TimestampTz last_send_time; @@ -79,7 +88,6 @@ extern void logicalrep_worker_launch(Oid dbid, Oid subid, const char *subname, extern void logicalrep_worker_stop(Oid subid, Oid relid); extern void logicalrep_worker_wakeup(Oid subid, Oid relid); extern void logicalrep_worker_wakeup_ptr(LogicalRepWorker *worker); -extern void logicalrep_worker_cleanupfileset(void); extern int logicalrep_sync_worker_count(Oid subid); diff --git a/src/include/storage/buffile.h b/src/include/storage/buffile.h index 143eada..7ae5ea2 100644 --- a/src/include/storage/buffile.h +++ b/src/include/storage/buffile.h @@ -49,8 +49,9 @@ extern long BufFileAppend(BufFile *target, BufFile *source); extern BufFile *BufFileCreateFileSet(FileSet *fileset, const char *name); extern void BufFileExportFileSet(BufFile *file); extern BufFile *BufFileOpenFileSet(FileSet *fileset, const char *name, - int mode); -extern void BufFileDeleteFileSet(FileSet *fileset, const char *name); + int mode, bool missing_ok); +extern void BufFileDeleteFileSet(FileSet *fileset, const char *name, + bool missing_ok); extern void BufFileTruncateFileSet(BufFile *file, int fileno, off_t offset); #endif /* BUFFILE_H */ -- 1.8.3.1
^ permalink raw reply [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-27 05:26               ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  2021-08-27 06:34                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-31 09:50                   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-09-01 08:23                     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-09-01 11:53                       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
@ 2021-09-01 12:02                         ` Dilip Kumar <dilipbalaut@gmail.com>
  2021-09-02 05:36                           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  1 sibling, 1 reply; 26+ messages in thread

From: Dilip Kumar @ 2021-09-01 12:02 UTC (permalink / raw)
  To: Amit Kapila <amit.kapila16@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Wed, Sep 1, 2021 at 5:23 PM Amit Kapila <amit.kapila16@gmail.com> wrote:

> On Wed, Sep 1, 2021 at 1:53 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
> >
>
> The latest patch looks good to me. I have made some changes in the
> comments, see attached. I am planning to push this tomorrow unless you
> or others have any comments on it.
>

These comments changes look good to me.

-- 
Regards,
Dilip Kumar
EnterpriseDB: http://www.enterprisedb.com

^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-27 05:26               ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  2021-08-27 06:34                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-31 09:50                   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-09-01 08:23                     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-09-01 11:53                       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-09-01 12:02                         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
@ 2021-09-02 05:36                           ` Amit Kapila <amit.kapila16@gmail.com>
  0 siblings, 0 replies; 26+ messages in thread

From: Amit Kapila @ 2021-09-02 05:36 UTC (permalink / raw)
  To: Dilip Kumar <dilipbalaut@gmail.com>; +Cc: houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Andres Freund <andres@anarazel.de>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

On Wed, Sep 1, 2021 at 5:33 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>
> On Wed, Sep 1, 2021 at 5:23 PM Amit Kapila <amit.kapila16@gmail.com> wrote:
>>
>> On Wed, Sep 1, 2021 at 1:53 PM Dilip Kumar <dilipbalaut@gmail.com> wrote:
>> >
>>
>> The latest patch looks good to me. I have made some changes in the
>> comments, see attached. I am planning to push this tomorrow unless you
>> or others have any comments on it.
>
>
> These comments changes look good to me.
>

Pushed.

-- 
With Regards,
Amit Kapila.





^ permalink  raw  reply  [nested|flat] 26+ messages in thread

* Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o)
  2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 07:22 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-23 08:13   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-23 09:43     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-24 06:56       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-24 10:25         ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-25 12:19           ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-08-26 06:17             ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-27 05:26               ` RE: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
  2021-08-27 06:34                 ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-08-31 09:50                   ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
  2021-09-01 08:23                     ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Dilip Kumar <dilipbalaut@gmail.com>
  2021-09-01 11:53                       ` Re: Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
@ 2021-11-29 18:10                         ` Andres Freund <andres@anarazel.de>
  1 sibling, 0 replies; 26+ messages in thread

From: Andres Freund @ 2021-11-29 18:10 UTC (permalink / raw)
  To: Amit Kapila <amit.kapila16@gmail.com>; +Cc: Dilip Kumar <dilipbalaut@gmail.com>; houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>; Thomas Munro <thomas.munro@gmail.com>; pgsql-hackers <pgsql-hackers@postgresql.org>; Masahiko Sawada <sawada.mshk@gmail.com>; Tom Lane <tgl@sss.pgh.pa.us>

Hi,

Thank for all the work on this topic - I'd somehow accidentally marked this
thread as read when coming back from vacation...

Greetings,

Andres Freund





^ permalink  raw  reply  [nested|flat] 26+ messages in thread


end of thread, other threads:[~2021-11-29 18:10 UTC | newest]

Thread overview: 26+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2021-08-23 06:13 Separate out FileSet from SharedFileSet (was Re: pgsql: pgstat: Bring up pgstat in BaseInit() to fix uninitialized use o) Amit Kapila <amit.kapila16@gmail.com>
2021-08-23 07:22 ` Dilip Kumar <dilipbalaut@gmail.com>
2021-08-23 08:13   ` Amit Kapila <amit.kapila16@gmail.com>
2021-08-23 09:43     ` Dilip Kumar <dilipbalaut@gmail.com>
2021-08-24 06:56       ` Amit Kapila <amit.kapila16@gmail.com>
2021-08-24 10:25         ` Dilip Kumar <dilipbalaut@gmail.com>
2021-08-25 01:50           ` houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
2021-08-25 12:19           ` Amit Kapila <amit.kapila16@gmail.com>
2021-08-26 01:46             ` Masahiko Sawada <sawada.mshk@gmail.com>
2021-08-26 06:17             ` Dilip Kumar <dilipbalaut@gmail.com>
2021-08-26 08:40               ` Amit Kapila <amit.kapila16@gmail.com>
2021-08-27 05:24                 ` Dilip Kumar <dilipbalaut@gmail.com>
2021-08-27 05:28                   ` houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
2021-08-30 01:12                   ` Masahiko Sawada <sawada.mshk@gmail.com>
2021-08-30 06:44                     ` Amit Kapila <amit.kapila16@gmail.com>
2021-08-27 05:26               ` houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
2021-08-27 06:34                 ` Dilip Kumar <dilipbalaut@gmail.com>
2021-08-30 06:15                   ` Masahiko Sawada <sawada.mshk@gmail.com>
2021-08-31 02:08                     ` houzj.fnst@fujitsu.com <houzj.fnst@fujitsu.com>
2021-08-31 05:53                       ` Dilip Kumar <dilipbalaut@gmail.com>
2021-08-31 09:50                   ` Amit Kapila <amit.kapila16@gmail.com>
2021-09-01 08:23                     ` Dilip Kumar <dilipbalaut@gmail.com>
2021-09-01 11:53                       ` Amit Kapila <amit.kapila16@gmail.com>
2021-09-01 12:02                         ` Dilip Kumar <dilipbalaut@gmail.com>
2021-09-02 05:36                           ` Amit Kapila <amit.kapila16@gmail.com>
2021-11-29 18:10                         ` Andres Freund <andres@anarazel.de>

This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox