From mboxrd@z Thu Jan 1 00:00:00 1970 From: Cyril Hrubis Date: Mon, 10 Oct 2016 17:03:52 +0200 Subject: [LTP] [PATCH] readahead02: estimate max readahead size In-Reply-To: <141170940.52106.1476110506518.JavaMail.zimbra@redhat.com> References: <04ff8b784a23cb62c1413b0b6575238bd5474ca4.1476098569.git.jstancek@redhat.com> <20161010141651.GB1684@rei> <141170940.52106.1476110506518.JavaMail.zimbra@redhat.com> Message-ID: <20161010150352.GC1684@rei> List-Id: MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: ltp@lists.linux.it Hi! > > I've tried this on the /tmp on Btrfs and got max_ra_estimage nearly ten times > > greater than the sysfs value. But apart from that the measured times are > > pretty > > much comparable with the previous version, which suggests that maximal > > readahead size on Btrfs is set to ~4M and the limit per device is not > > applicable. > > > > Did you get the estimate close to the value of the sysfs file in your > > environment? > > I do (on 4.8 x86 KVM guest): > # cat /sys/devices/virtual/bdi/253:1/read_ahead_kb > 4096 > readahead02 0 TINFO : max ra estimate: 4145152 > > Are you using upstream kernel or a patched one? That is Btrfs on SLES12-SP2 RC with kernel 4.4.21, but it seems to be pretty much Btrfs specific. If I point TMPDIR to ext3 fs I got estimated ra 507904 while the read_ahead_kb for the device is set to 512. -- Cyril Hrubis chrubis@suse.cz