Date: Wed, 4 Dec 2013 08:45:03 -0500
From: Jeff Layton <jlayton@redhat.com>
To: Christoph Hellwig <hch@infradead.org>
Cc: bfields@fieldses.org, gartim@gmail.com, linux-nfs@vger.kernel.org
Subject: Re: [PATCH] nfsd: when reusing an existing repcache entry, unhash
 it first
Message-ID: <20131204084503.5f94ad81@tlielax.poochiereds.net>
In-Reply-To: <20131204134036.GA3953@infradead.org>
References: <1386015979-27511-1-git-send-email-jlayton@redhat.com>
	<20131203102517.GA12576@infradead.org>
	<20131203132112.1f19c014@tlielax.poochiereds.net>
	<20131204083336.GB30216@infradead.org>
	<20131204075402.7b00d09d@tlielax.poochiereds.net>
	<20131204130944.GA3464@infradead.org>
	<20131204083101.6422fb40@tlielax.poochiereds.net>
	<20131204134036.GA3953@infradead.org>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Sender: linux-nfs-owner@vger.kernel.org

On Wed, 4 Dec 2013 05:40:36 -0800
Christoph Hellwig <hch@infradead.org> wrote:

> On Wed, Dec 04, 2013 at 08:31:01AM -0500, Jeff Layton wrote:
> > > Exactly.  Btw, what about the comment that the DRC should be per-client
> > > on top of the file?  That also seems like some very low hanging fruit.
> > > 
> > 
> > Ok, I'll see about spinning up a patchset that does that. We'll also
> > probably want to just allocate entries out of the slabcache in that
> > case, so that'll make things quite a bit simpler.
> 
> FYI I'm testing a patch at the moment that just rips out the "direct
> reclaim" as an alternative to your patch, without actually redoing
> the whole LRU infrastructure.  Unfortunately with your patch 075
> still hangs for me, although it at lest doesn't crash.
> 

Yeah, I've noticed the same hang, but hadn't able to determine why it
was hanging. I suspect that that hang is what's tickles the bug that my
patch fixes. With the hang, we see the client doing retransmits and not
getting replies and that means that we exercise the DRC more...

-- 
Jeff Layton <jlayton@redhat.com>