Commit Graph

248 Commits

Author SHA1 Message Date
Liu Yuan bd751f2204 sheepdog: don't update inode when create_and_write fails
For the error case such as SD_RES_NO_SPACE, we shouldn't update the inode bitmap
to avoid the scenario that the object is allocated but wasn't created at the
server side. This will result in VM's IO error on the failed object.

Cc: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Cc: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Liu Yuan <tailai.ly@taobao.com>
Reviewed-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-01-02 16:08:58 +01:00
Paolo Bonzini 1de7afc984 misc: move include files to include/qemu/
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2012-12-19 08:32:39 +01:00
Paolo Bonzini 737e150e89 block: move include files to include/block/
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2012-12-19 08:31:31 +01:00
Stefan Hajnoczi d7331bed11 aio: rename AIOPool to AIOCBInfo
Now that AIOPool no longer keeps a freelist, it isn't really a "pool"
anymore.  Rename it to AIOCBInfo and make it const since it no longer
needs to be modified.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-11-14 18:19:21 +01:00
MORITA Kazutaka 2f5368017f sheepdog: use bool for boolean variables
This improves readability.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2012-10-12 10:47:35 +02:00
Jim Meyering 3178e2755e sheepdog: avoid a few buffer overruns
* parse_vdiname: Use pstrcpy, not strncpy, when the destination
buffer must be NUL-terminated.
* sd_open: Likewise, avoid buffer overrun.
* do_sd_create: Likewise.  Leave the preceding memset, since
pstrcpy does not NUL-fill, and filename needs that.
* sd_snapshot_create: Add a comment/question.
* find_vdi_name: Remove a useless memset.
* sd_snapshot_goto: Remove a useless memset.
Use pstrcpy to NUL-terminate, because find_vdi_name requires
that its vdi arg (filename parameter) be NUL-terminated.
It seems ok not to NUL-fill the buffer.
Do the same for snapid: remove useless memset-0 (instead,
zero tag[0]).  Use pstrcpy, not strncpy.
* sd_snapshot_list: Use pstrcpy, not strncpy to write
into the ->name member.  Each must be NUL-terminated.

Acked-by: Kevin Wolf <kwolf@redhat.com>
Acked-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Jim Meyering <meyering@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2012-10-05 07:58:36 -05:00
Jeff Cody 39c9fb9565 block: do not parse BDRV_O_CACHE_WB in block drivers
Block drivers should ignore BDRV_O_CACHE_WB in .bdrv_open flags,
and in the bs->open_flags.

This patch removes the code, leaving the behaviour behind as if
BDRV_O_CACHE_WB was set.

Signed-off-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-09-24 15:15:11 +02:00
MORITA Kazutaka 1f7a48de44 sheepdog: fix savevm and loadvm
This patch sets data to be sent to Sheepdog correctly and fixes savevm
and loadvm operations on a Sheepdog image.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-09-12 15:50:09 +02:00
Jim Meyering a7e47d4bfc sheepdog: don't leak socket file descriptor upon connection failure
Signed-off-by: Jim Meyering <meyering@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2012-08-22 10:47:14 -05:00
Christoph Hellwig 19db9b9042 sheepdog: do not blindly memset all read buffers
Only buffers that map to unallocated blocks need to be zeroed.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-07-17 16:48:29 +02:00
MORITA Kazutaka cddd4ac7a2 sheepdog: always use coroutine-based network functions
This reduces some code duplication.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-07-17 16:48:29 +02:00
Anthony Liguori 23797df3d9 Merge remote-tracking branch 'mjt/mjt-iov2' into staging
* mjt/mjt-iov2:
  rewrite iov_send_recv() and move it to iov.c
  cleanup qemu_co_sendv(), qemu_co_recvv() and friends
  export iov_send_recv() and use it in iov_send() and iov_recv()
  rename qemu_sendv to iov_send, change proto and move declarations to iov.h
  change qemu_iovec_to_buf() to match other to,from_buf functions
  consolidate qemu_iovec_copy() and qemu_iovec_concat() and make them consistent
  allow qemu_iovec_from_buffer() to specify offset from which to start copying
  consolidate qemu_iovec_memset{,_skip}() into single function and use existing iov_memset()
  rewrite iov_* functions
  change iov_* function prototypes to be more appropriate
  virtio-serial-bus: use correct lengths in control_out() message

Conflicts:
	tests/Makefile

Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2012-07-09 12:35:06 -05:00
MORITA Kazutaka 7dc1cde05b sheepdog: traverse pending_list from the first for each time
The pending list can be modified in other coroutine context
sd_co_rw_vector, so we need to traverse the list from the first again
after we send the pending request.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-07-09 15:53:02 +02:00
MORITA Kazutaka c292ee6a67 sheepdog: split outstanding list into inflight and pending
outstanding_list_head is used for both pending and inflight requests.
This patch splits it and improves readability.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-07-09 15:53:02 +02:00
MORITA Kazutaka 1d732d7d7c sheepdog: make sure we don't free aiocb before sending all requests
This patch increments the pending counter before sending requests, and
make sures that aiocb is not freed while sending them.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-07-09 15:53:01 +02:00
MORITA Kazutaka b97564f4c5 sheepdog: use coroutine based socket functions in coroutine context
This removes blocking network I/Os in coroutine context.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-07-09 15:53:01 +02:00
MORITA Kazutaka 2dfcca3b68 sheepdog: restart I/O when socket becomes ready in do_co_req()
Currently, no one reenters the yielded coroutine.  This fixes it.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-07-09 15:53:01 +02:00
MORITA Kazutaka 1b6ac9985a sheepdog: fix dprintf format strings
This fixes warnings about dprintf format in debug mode.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-07-09 15:53:01 +02:00
MORITA Kazutaka e0d93a89b9 sheepdog: add coroutine_fn markers to coroutine functions
Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Reviewed-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-06-15 14:03:42 +02:00
Michael Tokarev 2fc8ae1dd7 cleanup qemu_co_sendv(), qemu_co_recvv() and friends
The same as for non-coroutine versions in previous
patches: rename arguments to be more obvious, change
type of arguments from int to size_t where appropriate,
and use common code for send and receive paths (with
one extra argument) since these are exactly the same.
Use common iov_send_recv() directly.

qemu_co_sendv(), qemu_co_recvv(), and qemu_co_recv()
are now trivial #define's merely adding one extra arg.

qemu_co_sendv() and qemu_co_recvv() callers are
converted to different argument order and extra
`iov_cnt' argument.

Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
2012-06-11 23:12:11 +04:00
MORITA Kazutaka 6f3c714eb7 sheepdog: fix return value of do_load_save_vm_state
bdrv_save_vmstate and bdrv_load_vmstate should return the vmstate size
on success, and -errno on error.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-05-30 09:58:39 +02:00
MORITA Kazutaka b6fc8245e9 sheepdog: use heap instead of stack for BDRVSheepdogState
bdrv_create() is called in coroutine context now, so we cannot use
more stack than 1 MB in the function if we use ucontext coroutine.
This patch allocates BDRVSheepdogState, whose size is 4 MB, on the
heap in sd_create().

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-05-25 18:12:54 +02:00
MORITA Kazutaka cb595887cc sheepdog: return -errno on error
On error, BlockDriver APIs should return -errno instead of -1.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-05-25 18:12:54 +02:00
MORITA Kazutaka 622b6057be sheepdog: mark image as snapshot when tag is specified
When a snapshot tag is specified in the filename, the opened image is
a snapshot.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-05-25 18:12:54 +02:00
MORITA Kazutaka 115c2b5a68 sheepdog: switch to writethrough mode if cluster doesn't support flush
This is necessary for qemu to work with the older version of Sheepdog
which doesn't support SD_OP_FLUSH_VDI.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@gmail.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-05-07 19:33:18 +02:00
Paolo Bonzini bafbd6a1c6 aio: remove process_queue callback and qemu_aio_process_queue
Both unused after the previous patch.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-04-19 16:37:53 +02:00
Liu Yuan eb09218077 sheepdog: fix send req helpers
We should return if reading of the header fails.

Cc: Kevin Wolf <kwolf@redhat.com>
Cc: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Liu Yuan <tailai.ly@taobao.com>
Acked-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-04-05 14:54:41 +02:00
Liu Yuan 47622c44d0 sheepdog: implement SD_OP_FLUSH_VDI operation
Flush operation is supposed to flush the write-back cache of
sheepdog cluster.

By issuing flush operation, we can assure the Guest of data
reaching the sheepdog cluster storage.

Cc: Kevin Wolf <kwolf@redhat.com>
Cc: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Liu Yuan <tailai.ly@taobao.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-04-05 14:54:41 +02:00
MORITA Kazutaka 6d1acda8f1 sheepdog: fix co_recv coroutine context
The co_recv coroutine has two things that will try to enter it:

  1. The select(2) read callback on the sheepdog socket.
  2. The aio_add_request() blocking operations, including a coroutine
     mutex.

This patch fixes it by setting NULL to co_recv before sending data.

In future, we should make the sheepdog driver fully coroutine-based
and simplify request handling.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2012-02-09 16:17:51 +01:00
Paolo Bonzini 6b620ca3b0 prepare for future GPLv2+ relicensing
All files under GPLv2 will get GPLv2+ changes starting tomorrow.
event_notifier.c and exec-obsolete.h were only ever touched by Red Hat
employees and can be relicensed now.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2012-01-13 10:55:56 -06:00
Paolo Bonzini 128aa58947 move corking functions to osdep.c
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2011-12-22 11:53:58 +01:00
Paolo Bonzini 8c5135f90e sheepdog: move coroutine send/recv function to generic code
Outside coroutines, avoid busy waiting on EAGAIN by temporarily
making the socket blocking.

The API of qemu_recvv/qemu_sendv is slightly different from
do_readv/do_writev because they do not handle coroutines.  It
returns the number of bytes written before encountering an
EAGAIN.  The specificity of yielding on EAGAIN is entirely in
qemu-coroutine.c.

Reviewed-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2011-12-22 11:53:53 +01:00
Dong Xu Wang a968168c58 block: Add coroutine_fn marker to coroutine functions
Looks better when reviewing these source files.

Signed-off-by: Dong Xu Wang <wdongxu@linux.vnet.ibm.com>
Reviewed-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2011-12-05 14:51:35 +01:00
Dong Xu Wang c3fecea50d sheepdog: Avoid deadlock in error path
s->lock should be unlocked before leaving add_aio_request.

Signed-off-by: Dong Xu Wang <wdongxu@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2011-11-22 10:33:43 +01:00
Paolo Bonzini d8716b41b9 sheepdog: add coroutine_fn markers
This makes the following patch easier to review.

Cc: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2011-10-21 17:34:12 +02:00
Dong Xu Wang 7acae208ca sheepdog: correct spelling
Reviewed-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: Dong Xu Wang <wdongxu@linux.vnet.ibm.com>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-10-14 14:46:59 +01:00
MORITA Kazutaka 2df4624662 sheepdog: use coroutines
This makes the sheepdog block driver support bdrv_co_readv/writev
instead of bdrv_aio_readv/writev.

With this patch, Sheepdog network I/O becomes fully asynchronous.  The
block driver yields back when send/recv returns EAGAIN, and is resumed
when the sheepdog network connection is ready for the operation.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2011-08-24 14:53:51 +02:00
Anthony Liguori 7267c0947d Use glib memory allocation and free functions
qemu_malloc/qemu_free no longer exist after this commit.

Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
2011-08-20 23:01:08 -05:00
Blue Swirl 00aa0040e8 Wrap recv to avoid warnings
Avoid warnings like these by wrapping recv():
  CC    slirp/ip_icmp.o
/src/qemu/slirp/ip_icmp.c: In function 'icmp_receive':
/src/qemu/slirp/ip_icmp.c:418:5: error: passing argument 2 of 'recv' from incompatible pointer type [-Werror]
/usr/local/lib/gcc/i686-mingw32msvc/4.6.0/../../../../i686-mingw32msvc/include/winsock2.h:547:32: note: expected 'char *' but argument is of type 'struct icmp *'

Remove also casts used to avoid warnings.

Reviewed-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
2011-07-25 14:38:56 +00:00
MORITA Kazutaka a8e0fdd715 sheepdog: add full data preallocation support
This introduces qemu-img create option for sheepdog which allows the
data to be fully preallocated (note that sheepdog always preallocates
metadata).

The option is disabled by default and you need to enable it like the
following:

qemu-img create sheepdog:test -o preallocation=full 1G

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2011-07-18 16:06:26 +02:00
Markus Armbruster 6daf194dde Strip trailing '\n' from error_report()'s first argument
error_report() prepends location, and appends a newline.  The message
constructed from the arguments should not contain a newline.  Fix the
obvious offenders.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-06-24 09:13:36 +01:00
Markus Armbruster db78ef5b0a sheepdog: qemu_bh_new() can't return null pointer, drop check
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-06-24 09:13:36 +01:00
Stefan Weil ebabb67a17 Fix typo in code and comments
Replace writeable -> writable

Signed-off-by: Stefan Weil <weil@mail.berlios.de>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-05-06 08:19:25 +01:00
Michael Tokarev 8cffde7329 get rid of private bitmap functions in block/sheepdog.c, use generic ones
qemu now has generic bitmap functions,
so don't redefine them in sheepdog.c,
use common header instead.  A small cleanup.

Here's only one function which is actually
used in sheepdog and gets replaced with
a generic one (simplified):

- static inline int test_bit(int nr, const volatile unsigned long *addr)
+ static inline int test_bit(int nr, const unsigned long *addr)
 {
-  return ((1UL << (nr % BITS_PER_LONG))
            & ((unsigned long*)addr)[nr / BITS_PER_LONG])) != 0;
+  return 1UL & (addr[nr / BITS_PER_LONG] >> (nr & (BITS_PER_LONG-1)));
 }

The body is equivalent, but the argument is not: there's
"volatile" in there.  Why it is used for - I'm not sure.

Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
Acked-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
2011-04-01 22:23:06 +02:00
MORITA Kazutaka b444736346 sheepdog: support creating images on remote hosts
This patch parses the input filename in sd_create(), and enables us
specifying a target server to create sheepdog images.

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2011-01-31 10:03:00 +01:00
Izumi Tsutsui 010cb2b314 sheepdog: remove unnecessary includes
"qemu_socket.h" includes all necessary files and
including <netinet/tcp.h> without <netinet/in.h>
could cause errors on some systems.

Signed-off-by: Izumi Tsutsui <tsutsui@ceres.dti.ne.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-08-30 18:29:22 +02:00
MORITA Kazutaka 6defcc3784 sheepdog: fix compile error on systems without TCP_CORK
WIN32 is not only the system which doesn't have TCP_CORK (e.g. OS X).

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
2010-07-07 20:54:56 +03:00
MORITA Kazutaka 33b1db1c88 block: add sheepdog driver for distributed storage support
Sheepdog is a distributed storage system for QEMU. It provides highly
available block level storage volumes to VMs like Amazon EBS.  This
patch adds a qemu block driver for Sheepdog.

Sheepdog features are:
- No node in the cluster is special (no metadata node, no control
  node, etc)
- Linear scalability in performance and capacity
- No single point of failure
- Autonomous management (zero configuration)
- Useful volume management support such as snapshot and cloning
- Thin provisioning
- Autonomous load balancing

The more details are available at the project site:
    http://www.osrg.net/sheepdog/

Signed-off-by: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2010-07-06 17:05:50 +02:00