Re: [HACKERS] LWLock Queue Jumping

2009-08-31 Thread Stefan Kaltenbrunner
Jeff Janes wrote: On Sun, Aug 30, 2009 at 11:01 AM, Stefan Kaltenbrunner wrote: Jeff Janes wrote: -- Forwarded message -- From: Stefan Kaltenbrunner To: Heikki Linnakangas mailto:heikki.linnakan...@enterprisedb.com>

Re: [HACKERS] LWLock Queue Jumping

2009-08-30 Thread Jeff Janes
On Sun, Aug 30, 2009 at 11:01 AM, Stefan Kaltenbrunner wrote: > Jeff Janes wrote: > >>-- Forwarded message -- >>From: Stefan Kaltenbrunner >>To: Heikki Linnakangas >> >>Date: Sun, 30 Aug 2009 11:48:47 +0200 >>Sub

Re: [HACKERS] LWLock Queue Jumping

2009-08-30 Thread Stefan Kaltenbrunner
Jeff Janes wrote: -- Forwarded message -- From: Stefan Kaltenbrunner To: Heikki Linnakangas mailto:heikki.linnakan...@enterprisedb.com>> Date: Sun, 30 Aug 2009 11:48:47 +0200 Subject: Re: LWLock Queue Jumping Heikki Linnakangas wrote: Greg Stark w

Re: [HACKERS] LWLock Queue Jumping

2009-08-30 Thread Jeff Janes
> > -- Forwarded message -- > From: Stefan Kaltenbrunner > To: Heikki Linnakangas > Date: Sun, 30 Aug 2009 11:48:47 +0200 > Subject: Re: LWLock Queue Jumping > Heikki Linnakangas wrote: > >> Greg Stark wrote: >> >>> On Fri, Aug 28, 2009 at 8:07 PM, Simon Riggs >>> wrote: >>>

Re: [HACKERS] LWLock Queue Jumping

2009-08-30 Thread Simon Riggs
On Sun, 2009-08-30 at 09:03 +0300, Heikki Linnakangas wrote: > The Hot Standby thing has been discussed, but no-one has actually posted > a patch which does the locking correctly, where the ProcArrayLock is > held while the SnapshotData WAL record is inserted. So there is no > evidence that it's

Re: [HACKERS] LWLock Queue Jumping

2009-08-30 Thread Stefan Kaltenbrunner
Heikki Linnakangas wrote: Greg Stark wrote: On Fri, Aug 28, 2009 at 8:07 PM, Simon Riggs wrote: WALInsertLock is heavily contended and likely always will be even if we apply some of the planned fixes. I've lost any earlier messages, could you resend the raw data on which this is based? I don

Re: [HACKERS] LWLock Queue Jumping

2009-08-29 Thread Heikki Linnakangas
Greg Stark wrote: > On Fri, Aug 28, 2009 at 8:07 PM, Simon Riggs wrote: >> WALInsertLock is heavily contended and likely always will be even if we >> apply some of the planned fixes. > > I've lost any earlier messages, could you resend the raw data on which > this is based? I don't have any point

Re: [HACKERS] LWLock Queue Jumping

2009-08-29 Thread Greg Stark
On Fri, Aug 28, 2009 at 8:07 PM, Simon Riggs wrote: > WALInsertLock is heavily contended and likely always will be even if we > apply some of the planned fixes. I've lost any earlier messages, could you resend the raw data on which this is based? > Some callers of WALInsertLock are more important

Re: [HACKERS] LWLock Queue Jumping

2009-08-29 Thread Jeff Janes
On Sat, Aug 29, 2009 at 4:02 AM, Simon Riggs wrote: > > On Fri, 2009-08-28 at 14:44 -0700, Jeff Janes wrote: > > > I'd previously implemented this just by copying and pasting and making > > some changes, perhaps not the most desirable way but I thought adding > > another parameter to all existing

Re: [HACKERS] LWLock Queue Jumping

2009-08-29 Thread Simon Riggs
On Fri, 2009-08-28 at 14:44 -0700, Jeff Janes wrote: > I'd previously implemented this just by copying and pasting and making > some changes, perhaps not the most desirable way but I thought adding > another parameter to all existing invocations would be a bit > excessive. That's the way I would

[HACKERS] LWLock Queue Jumping

2009-08-28 Thread Jeff Janes
> > -- Forwarded message -- > From: Simon Riggs > To: pgsql-hackers > Date: Fri, 28 Aug 2009 20:07:32 +0100 > Subject: LWLock Queue Jumping > > WALInsertLock is heavily contended and likely always will be even if we > apply some of the planned fixes. > > Some callers of WALInsertL

[HACKERS] LWLock Queue Jumping

2009-08-28 Thread Simon Riggs
WALInsertLock is heavily contended and likely always will be even if we apply some of the planned fixes. Some callers of WALInsertLock are more important than others * Writing new Clog or Multixact pages (serialized by ClogControlLock) * For Hot Standby, writing SnapshotData (serialized by ProcA