Issue about memory order on ARM - Mailing list pgsql-hackers

From 盏一
Subject Issue about memory order on ARM
Date
Msg-id tencent_0A67458526FCC13F055424A0@qq.com
Whole thread Raw
Responses Re: Issue about memory order on ARM  (Tom Lane <tgl@sss.pgh.pa.us>)
Re:Issue about memory order on ARM  ("盏一" <w@hidva.com>)
List pgsql-hackers
The code in GetSnapshotData() that read the `xid` field of  PGXACT struct has a dependency on code in GetNewTransactionId() that write `MyPgXact->xid`. It means that the store of xid should happen before the load of it. In C11, we can use [Release-Acquire ordering](https://en.cppreference.com/w/c/atomic/memory_order#Release-Acquire_ordering) to achieve it. But now, there is no special operation to do it(, and the [volatile](https://en.cppreference.com/w/c/language/volatile) keyword should not play any role in this situation).

So it means that when a backend A returns from GetNewTransactionId(), the newval of `MyPgXact->xid` maybe just in CPU store buffer, or CPU cache line, so the newval is not yet visible to backend B that calling GetSnapshotData(). So the assumption that 'all top-level XIDs <= latestCompletedXid are either present in the ProcArray, or not running anymore' may not be safe. 

pgsql-hackers by date:

Previous
From: Amit Kapila
Date:
Subject: Re: [HACKERS] Block level parallel vacuum
Next
From: Sergei Kornilov
Date:
Subject: Re: [HACKERS] Block level parallel vacuum