Re: database vacuum from cron hanging

"Kevin Grittner" <Kevin.Grittner@wicourts.gov> writes:
> bufmgr.s file coming in separate (off-list) email.

Yup, here is the smoking gun!  This code in PinBuffer
    LockBufHdr_NoHoldoff(buf);    buf->refcount++;    result = (buf->flags & BM_VALID) != 0;
UnlockBufHdr_NoHoldoff(buf);

is translated as
movb    $1, %alcmpb    $0,28(%ebx)    jne    1f        lock            xchgb    %al,28(%ebx)        <-- acquire
spinlock
1: testb    %al, %aljne    .L228            <-- (failure case is out-of-line)
.L221:movl    20(%ebx), %ecx        <-- fetch refcountmovw    16(%ebx), %axincl    %ecx            <-- increment
refcountmovb   $0, 28(%ebx)        <-- release spinlockshrl    %eaxmovl    %ecx, 20(%ebx)        <-- store back
refcountandl   $1, %eaxmovl    %eax, %edi
 

For comparison, gcc 4.0.1 on my Fedora machine produces
movb    $1, %alcmpb    $0,28(%ebx)    jne    1f        lock            xchgb    %al,28(%ebx)        <-- acquire
spinlock
1: testb    %al, %aljne    .L117incl    20(%ebx)        <-- increment refcountmovw    16(%ebx), %axmovb    $0, 28(%ebx)
      <-- release spinlockmovl    %eax, %edishrl    %ediandl    $1, %edimovl    PrivateRefCount, %eax
 

which is safe.

What we probably need to do is insert some "volatile" qualifiers
to force the compiler to behave better.  What happens to the code
if you change PinBuffer to be declared as

static bool
PinBuffer(volatile BufferDesc *buf)

?
        regards, tom lane