From: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us> |
---|---|
To: | "Mikheev, Vadim" <vmikheev(at)SECTORBASE(dot)COM> |
Cc: | pgsql-hackers(at)postgresql(dot)org |
Subject: | Re: Stuck spins in current |
Date: | 2001-03-20 01:08:38 |
Message-ID: | 8592.985050518@sss.pgh.pa.us |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-hackers |
"Mikheev, Vadim" <vmikheev(at)SECTORBASE(dot)COM> writes:
>> "Vadim Mikheev" <vmikheev(at)sectorbase(dot)com> writes:
> Anyway, deadlock in my tests are very correlated with new log file
> creation - something probably is still wrong...
>>
>> Well, if you can reproduce it easily, seems like you could
>> get in there and verify or disprove my theory about where
>> the deadlock is.
> You were right - deadlock disappeared.
Okay, good. I'll bet the correlation to new-log-file was just because
the WAL insert_lck gets held for a longer time than usual if XLogInsert
is forced to call XLogWrite and that in turn is forced to make a new
log file. Were you running with wal_files = 0? The problem would
likely not have shown up at all if logfiles were created in advance...
> BTW, I've got ~320tps with 50 clients inserting (int4, text[1-256])
> records into 50 tables (-B 16384, wal_buffers = 256) on Ultra10
> with 512Mb RAM, IDE (clients run on the same host as server).
Not bad. What were you getting before these recent changes?
regards, tom lane
From | Date | Subject | |
---|---|---|---|
Next Message | Larry Rosenman | 2001-03-20 01:25:48 | Re: elog with automatic file, line, and function |
Previous Message | Mikheev, Vadim | 2001-03-20 00:59:57 | RE: Stuck spins in current |