>> INFO: task systemd-journal:20876 blocked for more than 120 seconds. >> [ 5037.962603] Tainted: G C O 4.14.9-1-ARCH #1 >> [ 5037.962609] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. >> [ 5037.962616] systemd-journal D 0 20876 20860 0x00000100 >> [ 5037.962622] Call Trace: >> [ 5037.962635] ? __schedule+0x290/0x890 >> [ 5037.962640] ? __slab_free+0x14e/0x300 >> [ 5037.962645] ? _copy_to_iter+0x8f/0x3d0 >> [ 5037.962651] schedule+0x2f/0x90 >> [ 5037.962704] btrfs_tree_read_lock+0xb6/0x100 [btrfs] > > Still some tree write is blocking all incoming read. > > BTW, did your tests include any send and relocation operations? > > IIRC there is a bug that makes send and relocation (I'm not sure though) > will cause similar problem. No. I’m doing nothing btrfs-specific at all, it’s just whatever systemd-nspawn —ephemeral does. Cheers, Johannes.-- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
