Re: [PERFORM] WAL in RAM

2011-11-29 Thread Marcus Engene
On 10/29/11 10:11 , Scott Marlowe wrote: In over 10 years of using hardware RAID controllers with battery backup on many many machines, I have had exactly zero data loss due to a failed battery backup. Of course proper monitoring is important, to make sure the batteries aren't old and dead, but

Re: [PERFORM] WAL in RAM

2011-10-29 Thread Scott Marlowe
On Sat, Oct 29, 2011 at 11:54 AM, Marcus Engene wrote: > The problem I have with battery backed raid controllers is the battery part. > They're simply not reliable and requires testing etc which I as a rather > insignificant customer at a generic datacenter cannot have done properly. I > have how

Re: [PERFORM] WAL in RAM

2011-10-29 Thread Marcus Engene
On 10/28/11 5:45 , Kevin Grittner wrote: Marcus Engene wrote: Every now and then I have write peaks which causes annoying delay on my website Does anyone here have any recommendations here? For our largest machines we put WAL on a RAID1 drive pair dedicated to that tas

Re: [PERFORM] WAL in RAM

2011-10-28 Thread David Boreham
On 10/28/2011 12:26 PM, Tomas Vondra wrote: For example the Intel 710 SSD has a sequential write speed of 210MB/s, while a simple SATA 7.2k drive can write about 50-100 MB/s for less than 1/10 of the 710 price. Bulk data transfer rates mean almost nothing in the context of a database (unless you

Re: [PERFORM] WAL in RAM

2011-10-28 Thread Claudio Freire
On Fri, Oct 28, 2011 at 12:28 PM, Marcus Engene wrote: > Hi list, > > Every now and then I have write peaks which causes annoying delay on my > website. No particular reason it seems, just that laws of probability > dictates that there will be peaks every now and then. > > Anyway, thinking of ways

Re: [PERFORM] WAL in RAM

2011-10-28 Thread Tomas Vondra
On 28 Říjen 2011, 20:40, Merlin Moncure wrote: > sure, but then you have to have a more complicated setup with a > drive(s) designated for WAL, another for storage, etc. Also, your > argument falls away if the WAL is shared with another drive. The era > of the SSD is here. All new systems I plan w

Re: [PERFORM] WAL in RAM

2011-10-28 Thread Tomas Vondra
Hi, On 28 Říjen 2011, 17:28, Marcus Engene wrote: > Hi list, > > Every now and then I have write peaks which causes annoying delay on my > website. No particular reason it seems, just that laws of probability > dictates that there will be peaks every now and then. > > Anyway, thinking of ways to m

Re: [PERFORM] WAL in RAM

2011-10-28 Thread Merlin Moncure
On Fri, Oct 28, 2011 at 1:26 PM, Tomas Vondra wrote: > On 28 Říjen 2011, 18:11, Merlin Moncure wrote: >> On Fri, Oct 28, 2011 at 10:28 AM, Marcus Engene wrote: >>> Hi list, >>> >>> Every now and then I have write peaks which causes annoying delay on my >>> website. No particular reason it seems,

Re: [PERFORM] WAL in RAM

2011-10-28 Thread Tomas Vondra
On 28 Říjen 2011, 18:11, Merlin Moncure wrote: > On Fri, Oct 28, 2011 at 10:28 AM, Marcus Engene wrote: >> Hi list, >> >> Every now and then I have write peaks which causes annoying delay on my >> website. No particular reason it seems, just that laws of probability >> dictates that there will be

Re: [PERFORM] WAL in RAM

2011-10-28 Thread Merlin Moncure
On Fri, Oct 28, 2011 at 10:28 AM, Marcus Engene wrote: > Hi list, > > Every now and then I have write peaks which causes annoying delay on my > website. No particular reason it seems, just that laws of probability > dictates that there will be peaks every now and then. > > Anyway, thinking of ways

Re: [PERFORM] WAL in RAM

2011-10-28 Thread Kevin Grittner
Marcus Engene wrote: > Every now and then I have write peaks which causes annoying delay > on my website > Does anyone here have any recommendations here? For our largest machines we put WAL on a RAID1 drive pair dedicated to that task, on its own controller with battery-backed cache configu

[PERFORM] WAL in RAM

2011-10-28 Thread Marcus Engene
Hi list, Every now and then I have write peaks which causes annoying delay on my website. No particular reason it seems, just that laws of probability dictates that there will be peaks every now and then. Anyway, thinking of ways to make the peaks more bareable, I saw the new 9.1 feature to