From mboxrd@z Thu Jan 1 00:00:00 1970 From: Chris Mason Subject: Re: Btrfs: broken file system design (was Unbound(?) internal fragmentation in Btrfs) Date: Fri, 18 Jun 2010 14:10:11 -0400 Message-ID: <20100618181011.GS27466@think> References: <4C07C321.8010000@redhat.com> <4C1B7560.1000806@gmail.com> <20100618134755.GG27466@think> <4C1B8B4A.9060308@gmail.com> <20100618151017.GN27466@think> <4C1B9D4F.6010008@gmail.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Mat , LKML , linux-fsdevel@vger.kernel.org, Ric Wheeler , Andrew Morton , Linus Torvalds , The development of BTRFS To: Edward Shishkin Return-path: In-Reply-To: <4C1B9D4F.6010008@gmail.com> List-ID: On Fri, Jun 18, 2010 at 06:22:39PM +0200, Edward Shishkin wrote: > Chris Mason wrote: > >On Fri, Jun 18, 2010 at 05:05:46PM +0200, Edward Shishkin wrote: > >>Chris Mason wrote: > >>>On Fri, Jun 18, 2010 at 03:32:16PM +0200, Edward Shishkin wrote: > >>>>Mat wrote: > >>>>>On Thu, Jun 3, 2010 at 4:58 PM, Edward Shishkin wrote: > >>>>>>Hello everyone. > >>>>>> > >>>>>>I was asked to review/evaluate Btrfs for using in enterprise > >>>>>>systems and the below are my first impressions (linux-2.6.33). > >>>>>> > >>>>>>The first test I have made was filling an empty 659M (/dev/sdb2) > >>>>>>btrfs partition (mounted to /mnt) with 2K files: > >>>>>> > >>>>>># for i in $(seq 1000000); \ > >>>>>>do dd if=/dev/zero of=/mnt/file_$i bs=2048 count=1; done > >>>>>>(terminated after getting "No space left on device" reports). > >>>>>> > >>>>>># ls /mnt | wc -l > >>>>>>59480 > >>>>>> > >>>>>>So, I got the "dirty" utilization 59480*2048 / (659*1024*1024) = 0.17, > >>>>>>and the first obvious question is "hey, where are other 83% of my > >>>>>>disk space???" I looked at the btrfs storage tree (fs_tree) and was > >>>>>>shocked with the situation on the leaf level. The Appendix B shows > >>>>>>5 adjacent btrfs leafs, which have the same parent. > >>>>>> > >>>>>>For example, look at the leaf 29425664: "items 1 free space 3892" > >>>>>>(of 4096!!). Note, that this "free" space (3892) is _dead_: any > >>>>>>attempts to write to the file system will result in "No space left > >>>>>>on device". > >>>There are two easy ways to fix this problem. Turn off the inline > >>>extents (max_inline=0) or allow splitting of the inline extents. I > >>>didn't put in the splitting simply because the complexity was high while > >>>the benefits were low (in comparison with just turning off the inline > >>>extents). > >>Hello, Chris. Thanks for response! > >>I afraid that both ways won't fix the problem. Look at this leaf: > >> > >>[...] > >>leaf 29425664 items 1 free space 3892 generation 8 owner 5 > >>fs uuid 50268d9d-2a53-4f4d-b3a3-4fbff74dd956 > >>chunk uuid 963ba49a-bb2b-48a3-9b35-520d857aade6 > >> item 0 key (320 XATTR_ITEM 3817753667) itemoff 3917 itemsize 78 > >> location key (0 UNKNOWN 0) type 8 > >> namelen 16 datalen 32 name: security.selinux > >>[...] > >> > >>There is no inline extents, and what are you going to split here? > >>All leafs must be at least a half filled, otherwise we loose all > >>boundaries, which provides non-zero utilization.. > > > >Right, there is no inline extent because we require them to fit entirely > >in the leaf. So we end up with mostly empty leaves because the inline > >item is large enough to make it difficult to push around but not large > >enough to fill the leaf. > > How about left and right neighbors? They contain a lot of > free space (1572 and 1901 respectively). > I am not happy with the very fact of such shallow leafs which > contain only one small (xattr) item.. Sure, the balancing can also be made more aggressive. This should be very easy to fix. -chris