Re: [HACKERS] pg_test_fsync crashes on systems with POSIX signal handling

2013-03-17 Thread Tom Lane
Bruce Momjian writes: > On Fri, Mar 15, 2013 at 03:05:54PM -0400, Tom Lane wrote: >> The quick-and-dirty fix for this is to just copy pqsignal() into >> pg_test_fsync, and use that instead of calling signal() directly. >> I wonder though if we shouldn't move that function into libpgport. >> Though

Re: [HACKERS] pg_test_fsync crashes on systems with POSIX signal handling

2013-03-15 Thread Bruce Momjian
On Fri, Mar 15, 2013 at 03:05:54PM -0400, Tom Lane wrote: > On my old HPUX box: > > $ ./pg_test_fsync > 2 seconds per test > Direct I/O is not supported on this platform. > > Compare file sync methods using one 8kB write: > (in wal_sync_method preference order, except fdatasync > is Linux's defau

[HACKERS] pg_test_fsync crashes on systems with POSIX signal handling

2013-03-15 Thread Tom Lane
On my old HPUX box: $ ./pg_test_fsync 2 seconds per test Direct I/O is not supported on this platform. Compare file sync methods using one 8kB write: (in wal_sync_method preference order, except fdatasync is Linux's default) open_datasync 165.122 ops/sec ( 6056 micros