Re: Fwd: Abyssmal dump cache efficiency

2007-03-09 Thread Boris Samorodov
On Fri, 23 Feb 2007 10:56:17 +0700 Eugene Grosbein wrote: On Thu, Feb 22, 2007 at 12:37:00PM -0500, Zaphod Beeblebrox wrote: Peter Jeremy wrote: I've found that you do get a worthwhile improvement in dump|restore performance by introducing a large (10's of MB) fifo between them. This

Re: Fwd: Abyssmal dump cache efficiency

2007-02-23 Thread Eugene Grosbein
On Thu, Feb 22, 2007 at 12:37:00PM -0500, Zaphod Beeblebrox wrote: Peter Jeremy wrote: I've found that you do get a worthwhile improvement in dump|restore performance by introducing a large (10's of MB) fifo between them. This helps reduce synchronisation between dump and restore (so that

Re: Fwd: Abyssmal dump cache efficiency

2007-02-22 Thread Zaphod Beeblebrox
On 2/21/07, Oliver Fromme [EMAIL PROTECTED] wrote: Peter Jeremy wrote: I've found that you do get a worthwhile improvement in dump|restore performance by introducing a large (10's of MB) fifo between them. This helps reduce synchronisation between dump and restore (so that dump can continue

Re: Fwd: Abyssmal dump cache efficiency

2007-02-21 Thread Oliver Fromme
Peter Jeremy wrote: I've found that you do get a worthwhile improvement in dump|restore performance by introducing a large (10's of MB) fifo between them. This helps reduce synchronisation between dump and restore (so that dump can continue to read whilst restore is busy writing a batch of

Fwd: Abyssmal dump cache efficiency

2007-02-20 Thread Zaphod Beeblebrox
(oops... didn't group reply) -- Forwarded message -- From: Zaphod Beeblebrox [EMAIL PROTECTED] Date: Feb 20, 2007 2:46 AM Subject: Re: Abyssmal dump cache efficiency To: Peter Jeremy [EMAIL PROTECTED] On 2/17/07, Peter Jeremy [EMAIL PROTECTED] wrote: I've tried modelling

Re: Fwd: Abyssmal dump cache efficiency

2007-02-20 Thread Peter Jeremy
On 2007-Feb-20 02:47:00 -0500, Zaphod Beeblebrox [EMAIL PROTECTED] wrote: On 2/17/07, Peter Jeremy [EMAIL PROTECTED] wrote: I've tried modelling a unified cache along the NetBSD line and there appears to be a massive improvement in cache performance. It's unclear how much of an improvement this

Abyssmal dump cache efficiency

2007-02-17 Thread Peter Jeremy
I've been looking into the efficiency of the caching in dump(8) and it's abyssmal: After instrumenting dump(8) and looking at its access patterns, it turns out that it typically reads roughly three times as much data into its cache as it should, whilst using five times as much RAM as requested.