[sheepdog] [PATCH v6 0/8] different redundancy level for different VDIs
Liu Yuan
namei.unix at gmail.com
Thu Aug 23 09:11:07 CEST 2012
On 08/23/2012 11:48 AM, levin li wrote:
> From: levin li <xingke.lwp at taobao.com>
>
> v5 ---> v6
> 1. rename add_vdi_copies to add_vdi_copy_number
> 2. remove the state of recovery waiting for copy list
> 3. fix a bug that loses inode data in recovery
> -----------------------------------------
> With this patch set, we don't need to specify copies number when formating
> the cluster, there's no global redundancy level any more, instead, we need
> to specify copies number for every VDI when creating a new one, like this:
>
> # collie vdi create test 10G -c 3
>
> If the -c is not specified, then use the default copies number 3
>
> levin li (8):
> sheep: use struct vdi_iocb to simplify the vdi_create api
> collie: add -c for 'collie vdi create' to specify redundancy level
> for per-vdi
> sheep: rename ctime to create_time in vdi.c
> sheep: add vdi_copy tree to store copies number for every VDI
> sheep: fetch vdi copy list after sheep joins the cluster
> sheep: use the specified copies number for IO requests
> sheep: remove some unused copies related functions
> collie: show copy number in the output of 'collie vdi list'
>
> collie/common.c | 15 ++-
> collie/vdi.c | 41 +++++---
> include/sheepdog_proto.h | 7 +-
> sheep/farm/farm.c | 31 +++++-
> sheep/farm/trunk.c | 4 +-
> sheep/gateway.c | 4 +-
> sheep/group.c | 117 ++++++++++++--------
> sheep/ops.c | 28 +++--
> sheep/recovery.c | 11 ++-
> sheep/request.c | 2 +-
> sheep/sheep.c | 2 +
> sheep/sheep_priv.h | 29 ++++-
> sheep/store.c | 9 +-
> sheep/vdi.c | 286 ++++++++++++++++++++++++++++++++++++----------
> tests/016.out | 2 +-
> 15 files changed, 436 insertions(+), 152 deletions(-)
>
Applied after changing is_vdis_list_ready to static and read_vdi_copies
-> read_vdi_copy_number, and fix some warnings from checkpatch.pl
Thanks,
Yuan
More information about the sheepdog
mailing list