From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Moyer Subject: Re: [-stable 3.8.1 performance regression] madvise POSIX_FADV_DONTNEED Date: Wed, 03 Jul 2013 10:53:08 -0400 Message-ID: References: <20130617141357.GA6034@Krystal> <20130617142459.1d563072231ba269cdac8f11@linux-foundation.org> <20130618092925.GI1875@suse.de> <20130618101147.GA7436@suse.de> <20130619192508.GA666@Krystal> <20130620122016.GA12700@Krystal> <20130625015648.GO29376@dastard> <20130702135858.GA30837@Krystal> <20130703005514.GA17149@Krystal> <20130703084715.GF1875@suse.de> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: In-Reply-To: <20130703084715.GF1875@suse.de> (Mel Gorman's message of "Wed, 3 Jul 2013 09:47:15 +0100") Sender: stable-owner@vger.kernel.org To: Mel Gorman Cc: Mathieu Desnoyers , Dave Chinner , Rob van der Heij , Andrew Morton , Yannick Brosseau , stable@vger.kernel.org, LKML , "lttng-dev@lists.lttng.org" List-Id: lttng-dev@lists.lttng.org Mel Gorman writes: >> > I just tried replacing my sync_file_range()+fadvise() calls and instead >> > pass the O_DIRECT flag to open(). Unfortunately, I must be doing >> > something very wrong, because I get only 1/3rd of the throughput, and >> > the page cache fills up. Any idea why ? >> >> Since O_DIRECT does not seem to provide acceptable throughput, it may be >> interesting to investigate other ways to lessen the latency impact of >> the fadvise DONTNEED hint. >> > > There are cases where O_DIRECT falls back to buffered IO which is why you > might have found that page cache was still filling up. There are a few > reasons why this can happen but I would guess the common cause is that > the range of pages being written was in the page cache already and could > not be invalidated for some reason. I'm guessing this is the common case > for page cache filling even with O_DIRECT but would not bet money on it > as it's not a problem I investigated before. Even when O_DIRECT falls back to buffered I/O for writes, it will invalidate the page cache range described by the buffered I/O once it completes. For reads, the range is written out synchronously before the direct I/O is issued. Either way, you shouldn't see the page cache filling up. Switching to O_DIRECT often incurs a performance hit, especially if the application does not submit more than one I/O at a time. Remember, you're not getting readahead, and you're not getting the benefit of the writeback code submitting batches of I/O. HTH, Jeff