Re: [PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql

2006-04-28 Thread Mikael Carneholm
To: pgsql-performance@postgresql.org Cc: Guoping Zhang (E-mail) Subject: [PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql Hi,. We are new to Postgresql. I am appreciated if the following question can be answered. Our application has a strict speed requirem

Re: [PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql

2006-04-27 Thread Guoping Zhang
Message- From: Tom Lane [mailto:[EMAIL PROTECTED] Sent: 2006Äê4ÔÂ28ÈÕ 14:57 To: [EMAIL PROTECTED] Cc: pgsql-performance@postgresql.org; 'Guoping Zhang (E-mail)' Subject: Re: [PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql "Guoping Zhang&quo

Re: [PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql

2006-04-27 Thread Guoping Zhang
erformance@postgresql.org; Guoping Zhang (E-mail) Subject: Re: [PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql Guoping, On 4/27/06, Guoping Zhang <[EMAIL PROTECTED]> wrote: > We have to looking at setting fsync OFF option for performance reason, Did you try

Re: [PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql

2006-04-27 Thread Tom Lane
"Guoping Zhang" <[EMAIL PROTECTED]> writes: > a) The tests consists of ten thousands very small transactions, which are > not grouped, that is why so slow with compare to set fsync off. Yup. > c) wal_sync_method is set to 'open_datasync', which is fastest among the > four, right? Well, is it? Y

Re: [PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql

2006-04-27 Thread Guoping Zhang
Lane Sent: 2006Äê4ÔÂ28ÈÕ 0:53 To: [EMAIL PROTECTED] Cc: pgsql-performance@postgresql.org; Guoping Zhang (E-mail) Subject: Re: [PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql "Guoping Zhang" <[EMAIL PROTECTED]> writes: > Our application has a st

Re: [PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql

2006-04-27 Thread Tom Lane
"Guoping Zhang" <[EMAIL PROTECTED]> writes: > Our application has a strict speed requirement for DB operation. Our tests > show that it takes about 10secs for the operation when setting fsync off, > but takes about 70 seconds when setting fsync ON (with other WAL related > parametered tuned). I ca

Re: [PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql

2006-04-27 Thread Guillaume Smet
Guoping, On 4/27/06, Guoping Zhang <[EMAIL PROTECTED]> wrote: > We have to looking at setting fsync OFF option for performance reason, Did you try the other wal sync methods (fdatasync in particular)? I saw a few posts lately explaining how changing sync method can affect performances in specific

Re: [PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql

2006-04-27 Thread Mikael Carneholm
) Subject: [PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql Hi,. We are new to Postgresql. I am appreciated if the following question can be answered. Our application has a strict speed requirement for DB operation. Our tests show that it takes about 10secs for the

[PERFORM] how unsafe (or worst scenarios) when setting fsync OFF for postgresql

2006-04-27 Thread Guoping Zhang
Hi,. We are new to Postgresql. I am appreciated if the following question can be answered. Our application has a strict speed requirement for DB operation. Our tests show that it takes about 10secs for the operation when setting fsync off, but takes about 70 seconds when setting fsync ON (with ot