From mboxrd@z Thu Jan 1 00:00:00 1970 From: Josef Bacik Subject: Re: Boot speed/mount time regression with 3.4.0-rc2 Date: Wed, 11 Apr 2012 14:24:26 -0400 Message-ID: <20120411182426.GD2506@localhost.localdomain> References: <1333986823.2928.6.camel@ayu> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Cc: Calvin Walton , linux-btrfs@vger.kernel.org To: Chester Return-path: In-Reply-To: List-ID: On Wed, Apr 11, 2012 at 11:38:33AM -0500, Chester wrote: > On Mon, Apr 9, 2012 at 10:53 AM, Calvin Walton wrote: > > > > Hi, > > > > I have a system that's using a dracut-generated initramfs to mount = a > > btrfs root. After upgrading to kernel 3.4.0-rc2 to test it out, I'v= e > > noticed that the process of mounting the root filesystem takes much > > longer with 3.4.0-rc2 than it did with 3.3.1 - nearly 30 seconds sl= ower! > > > > Does anyone have any ideas? I'm going to try bisecting the issue to= see > > if I can narrow down the cause. I've included excerpts from dmesg o= f the > > bad and good kernels here, and attached the complete dmesg from the= bad > > kernel, in case it has anything interesting that I've trimmed out h= ere. > > > > slow: > > [ =A0 =A00.000000] Linux version 3.4.0-rc2 (cwalton@ayu) (gcc versi= on 4.6.3 > > (Exherbo gcc-4.6.3) ) #57 SMP PREEMPT Mon Apr 9 11:19:43 EDT 2012 > > [ =A0 =A00.000000] Command line: > > root=3DUUID=3D43969cd0-4aca-4297-bfbe-952a692f7d55 > > rootflags=3Dsubvolid=3D262,compress=3Dlzo,autodefrag,space_cache,in= ode_cache,noatime > > mtrr_chunk_size=3D512M quiet > > > > [ =A0 =A01.058257] udevd[701]: starting version 182 > > [ =A0 =A01.389606] device label Linux data devid 1 transid 611923 /= dev/sda4 > > [ =A0 =A01.498659] dracut: Checking, if btrfs device complete > > [ =A0 =A01.644808] device label Linux data devid 1 transid 611923 /= dev/sda4 > > [ =A0 =A01.647993] btrfs: disk space caching is enabled > > [ =A0 =A02.180836] device label Linux data devid 1 transid 611923 /= dev/sda4 > > [ =A0 =A02.181663] btrfs: use lzo compression > > [ =A0 =A02.181667] btrfs: enabling auto defrag > > [ =A0 =A02.181670] btrfs: enabling inode map caching > > [ =A0 =A02.181672] btrfs: disk space caching is enabled > > [ =A0 =A02.697845] dracut: Checking btrfs: > > /dev/disk/by-uuid/43969cd0-4aca-4297-bfbe-952a692f7d55 > > [ =A0 =A02.699999] dracut: trying to mount > > /dev/disk/by-uuid/43969cd0-4aca-4297-bfbe-952a692f7d55 > > [ =A0 =A02.702637] device label Linux data devid 1 transid 611923 /= dev/sda4 > > [ =A0 =A02.704376] btrfs: disk space caching is enabled > > [ =A0 =A03.081720] dracut: btrfs: > > /dev/disk/by-uuid/43969cd0-4aca-4297-bfbe-952a692f7d55 is clean > > [ =A0 29.934639] dracut: Remounting > > /dev/disk/by-uuid/43969cd0-4aca-4297-bfbe-952a692f7d55 with -o > > subvolid=3D262,compress=3Dlzo,autodefrag,space_cache,inode_cache,no= atime,ro > > [ =A0 29.936810] device label Linux data devid 1 transid 611926 /de= v/sda4 > > [ =A0 29.937720] btrfs: use lzo compression > > [ =A0 29.937726] btrfs: enabling auto defrag > > [ =A0 29.937733] btrfs: enabling inode map caching > > [ =A0 29.937735] btrfs: disk space caching is enabled > > [ =A0 30.388066] dracut: Mounted root filesystem /dev/sda4 > > [ =A0 30.461884] dracut: Switching root > > [ =A0 31.241729] udevd[1322]: starting version 182 > > [ =A0 31.422905] btrfs: use lzo compression > > [ =A0 31.422909] btrfs: enabling auto defrag > > [ =A0 31.422913] btrfs: enabling inode map caching > > [ =A0 31.422915] btrfs: disk space caching is enabled > > > > vs fast: > > [ =A0 =A00.000000] Linux version 3.3.1 (cwalton@ayu) (gcc version 4= =2E6.3 > > (Exherbo gcc-4.6.3) ) #53 SMP PREEMPT Wed Apr 4 01:20:47 EDT 2012 > > [ =A0 =A00.000000] Command line: > > root=3DUUID=3D43969cd0-4aca-4297-bfbe-952a692f7d55 > > rootflags=3Dsubvolid=3D262,compress=3Dlzo,autodefrag,space_cache,in= ode_cache,noatime >=20 > Calvin, I noticed that you have the space_cache mount option set. I > remember josef saying that it is a one-time option where it's a > permanent change after mounting for the first time, therefore each > subsequent mount will not require the option. In fact, if the option > is specified again, the space_cache is reset. >=20 > Is this still up-to-date info? >=20 No you can leave space_cache set, there's another option for resetting = the space cache, clear_cache iirc. Thanks, Josef -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" = in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html