public inbox for [email protected]  
help / color / mirror / Atom feed
From: Andres Freund <[email protected]>
Subject: [PATCH v5 04/15] Add smgrzeroextend(), FileZero(), FileFallocate()
Date: Mon, 27 Feb 2023 17:36:37 -0800

diff --git a/src/backend/storage/file/fd.c b/src/backend/storage/file/fd.c
index 9fd8444ed4..c34ed41d52 100644
--- a/src/backend/storage/file/fd.c
+++ b/src/backend/storage/file/fd.c
@@ -2206,6 +2206,92 @@ FileSync(File file, uint32 wait_event_info)
     return returnCode;
 }

+/*
+ * Zero a region of the file.
+ *
+ * Returns 0 on success, -1 otherwise. In the latter case errno is set to the
+ * appropriate error.
+ */
+int
+FileZero(File file, off_t offset, off_t amount, uint32 wait_event_info)
+{
+    int            returnCode;
+    ssize_t        written;
+
+    Assert(FileIsValid(file));
+    returnCode = FileAccess(file);
+    if (returnCode < 0)
+        return returnCode;
+
+    pgstat_report_wait_start(wait_event_info);
+    written = pg_pwrite_zeros(VfdCache[file].fd, amount, offset);
+    pgstat_report_wait_end();
+
+    if (written < 0)
+        return -1;
+    else if (written != amount)

this doesn't need to be an else if

+    {
+        /* if errno is unset, assume problem is no disk space */
+        if (errno == 0)
+            errno = ENOSPC;
+        return -1;
+    }

+int
+FileFallocate(File file, off_t offset, off_t amount, uint32 wait_event_info)
+{
+#ifdef HAVE_POSIX_FALLOCATE
+    int            returnCode;
+
+    Assert(FileIsValid(file));
+    returnCode = FileAccess(file);
+    if (returnCode < 0)
+        return returnCode;
+
+    pgstat_report_wait_start(wait_event_info);
+    returnCode = posix_fallocate(VfdCache[file].fd, offset, amount);
+    pgstat_report_wait_end();
+
+    if (returnCode == 0)
+        return 0;
+
+    /* for compatibility with %m printing etc */
+    errno = returnCode;
+
+    /*
+    * Return in cases of a "real" failure, if fallocate is not supported,
+    * fall through to the FileZero() backed implementation.
+    */
+    if (returnCode != EINVAL && returnCode != EOPNOTSUPP)
+        return returnCode;

I'm pretty sure you can just delete the below if statement

+    if (returnCode == 0 ||
+        (returnCode != EINVAL && returnCode != EINVAL))
+        return returnCode;

diff --git a/src/backend/storage/smgr/md.c b/src/backend/storage/smgr/md.c
index 352958e1fe..59a65a8305 100644
--- a/src/backend/storage/smgr/md.c
+++ b/src/backend/storage/smgr/md.c
@@ -28,6 +28,7 @@
 #include "access/xlog.h"
 #include "access/xlogutils.h"
 #include "commands/tablespace.h"
+#include "common/file_utils.h"
 #include "miscadmin.h"
 #include "pg_trace.h"
 #include "pgstat.h"
@@ -500,6 +501,116 @@ mdextend(SMgrRelation reln, ForkNumber forknum,
BlockNumber blocknum,
     Assert(_mdnblocks(reln, forknum, v) <= ((BlockNumber) RELSEG_SIZE));
 }

+/*
+ *    mdzeroextend() -- Add ew zeroed out blocks to the specified relation.

not sure what ew is

+ *
+ *        Similar to mdrextend(), except the relation can be extended by

mdrextend->mdextend

+ *        multiple blocks at once, and that the added blocks will be
filled with

I would lose the comma and just say "and the added blocks will be filled..."

+void
+mdzeroextend(SMgrRelation reln, ForkNumber forknum,
+            BlockNumber blocknum, int nblocks, bool skipFsync)

So, I think there are  a few too many local variables in here, and it
actually makes it more confusing.
Assuming you would like to keep the input parameters blocknum and
nblocks unmodified for debugging/other reasons, here is a suggested
refactor of this function
Also, I think you can combine the two error cases (I don't know if the
user cares what you were trying to extend the file with). I've done this
below also.

void
mdzeroextend(SMgrRelation reln, ForkNumber forknum,
            BlockNumber blocknum, int nblocks, bool skipFsync)
{
    MdfdVec    *v;
    BlockNumber curblocknum = blocknum;
    int            remblocks = nblocks;

    Assert(nblocks > 0);

    /* This assert is too expensive to have on normally ... */
#ifdef CHECK_WRITE_VS_EXTEND
    Assert(blocknum >= mdnblocks(reln, forknum));
#endif

    /*
    * If a relation manages to grow to 2^32-1 blocks, refuse to extend it any
    * more --- we mustn't create a block whose number actually is
    * InvalidBlockNumber or larger.
    */
    if ((uint64) blocknum + nblocks >= (uint64) InvalidBlockNumber)
        ereport(ERROR,
                (errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
                errmsg("cannot extend file \"%s\" beyond %u blocks",
                        relpath(reln->smgr_rlocator, forknum),
                        InvalidBlockNumber)));

    while (remblocks > 0)
    {
        int            segstartblock = curblocknum % ((BlockNumber)
RELSEG_SIZE);
        int            numblocks = remblocks;
        off_t        seekpos = (off_t) BLCKSZ * segstartblock;
        int            ret;

        if (segstartblock + remblocks > RELSEG_SIZE)
            numblocks = RELSEG_SIZE - segstartblock;

        v = _mdfd_getseg(reln, forknum, curblocknum, skipFsync,
EXTENSION_CREATE);

        /*
        * If available and useful, use posix_fallocate() (via FileAllocate())
        * to extend the relation. That's often more efficient than using
        * write(), as it commonly won't cause the kernel to allocate page
        * cache space for the extended pages.
        *
        * However, we don't use FileAllocate() for small extensions, as it
        * defeats delayed allocation on some filesystems. Not clear where
        * that decision should be made though? For now just use a cutoff of
        * 8, anything between 4 and 8 worked OK in some local testing.
        */
        if (numblocks > 8)
            ret = FileFallocate(v->mdfd_vfd,
                                seekpos, (off_t) BLCKSZ * numblocks,
                                WAIT_EVENT_DATA_FILE_EXTEND);
        else
            /*
            * Even if we don't want to use fallocate, we can still extend a
            * bit more efficiently than writing each 8kB block individually.
            * pg_pwrite_zeroes() (via FileZero()) uses
            * pg_pwritev_with_retry() to avoid multiple writes or needing a
            * zeroed buffer for the whole length of the extension.
            */
            ret = FileZero(v->mdfd_vfd,
                          seekpos, (off_t) BLCKSZ * numblocks,
                          WAIT_EVENT_DATA_FILE_EXTEND);

        if (ret != 0)
            ereport(ERROR,
                    errcode_for_file_access(),
                    errmsg("could not extend file \"%s\": %m",
                            FilePathName(v->mdfd_vfd)),
                    errhint("Check free disk space."));

        if (!skipFsync && !SmgrIsTemp(reln))
            register_dirty_segment(reln, forknum, v);

        Assert(_mdnblocks(reln, forknum, v) <= ((BlockNumber) RELSEG_SIZE));

        remblocks -= numblocks;
        curblocknum += numblocks;
    }
}

diff --git a/src/backend/storage/smgr/smgr.c b/src/backend/storage/smgr/smgr.c
index dc466e5414..5224ca5259 100644
--- a/src/backend/storage/smgr/smgr.c
+++ b/src/backend/storage/smgr/smgr.c
@@ -50,6 +50,8 @@ typedef struct f_smgr
+/*
+ *    smgrzeroextend() -- Add new zeroed out blocks to a file.
+ *
+ *        Similar to smgrextend(), except the relation can be extended by
+ *        multiple blocks at once, and that the added blocks will be
filled with
+ *        zeroes.
+ */

Similar grammatical feedback as mdzeroextend.




view thread (23+ messages)  latest in thread

reply

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Reply to all the recipients using the --to and --cc options:
  reply via email

  To: [email protected]
  Cc: [email protected]
  Subject: Re: [PATCH v5 04/15] Add smgrzeroextend(), FileZero(), FileFallocate()
  In-Reply-To: <no-message-id-1858011@localhost>

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

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