On Thu, 2011-02-24 at 02:58 -0700, Wido den Hollander wrote: > Hi, > > On Thu, 2011-02-24 at 15:13 +0800, Henry Chang wrote: > > Hi, > > > > I want to confirm if the following problem is related to Bug #630. > > > > Step 1. On client A, create a file of 10G by dd. > > "ceph -w" shows the total data size increased by 10G. > > > > Step 2. On client B, touch the file. > > > > Step 3. On client A, remove the file. > > "ceph -w" shows the total data size is NOT decreased. > > > > Step 4. Umount ceph on client B. > > "ceph -w" shows the total data size decreased by 10G. FWIW, I think it might be. On client B, try echo 2 > /proc/sys/vm/drop_caches rather than umount, and see if the data size decreases. --Jim > > I tried your test, I'm seeing the same behaviour. I write a 1GB.bin and > 4MB.bin and cloned the linux-2.6 tree, after removing them: > > pg v7776: 12336 pgs: 12336 active+clean; 767 MB data, 2925 MB used, 544 > GB / 558 GB avail > > But there is nothing left on the filesystem. > > Looking closer I saw that the pool "data" still contained 16937 objects > with a total size of 662876021 bytes. > > The "metadata" pool still contains 957 objects, total size is 132289047 > bytes. > > 132289047 + 662876021 = 758MB > > That is almost the same as "ceph -s" is reporting. > > I removed those files about 2 hours ago, after that there have been no > I/O's on the filesystem. > > My replication is on 3 btw. > > Wido > > > > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" in > the body of a message to majordomo@xxxxxxxxxxxxxxx > More majordomo info at http://vger.kernel.org/majordomo-info.html > -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
