linux.git/drivers/block/rbd.c, branch v2.6.39 Linux kernel source tree rbd: fix split bio handling 2011-05-13T20:52:57+00:00 Yehuda Sadeh yehuda@hq.newdream.net 2011-05-13T20:52:56+00:00 1fec70932d867416ffe620dd17005f168cc84eb5 The rbd driver currently splits bios when they span an object boundary. However, the blk_end_request expects the completions to roll up the results in block device order, and the split rbd/ceph ops can complete in any order. This patch adds a struct rbd_req_coll to track completion of split requests and ensures that the results are passed back up to the block layer in order. This fixes errors where the file system gets completion of a read operation that spans an object boundary before the data has actually arrived. The bug is easily reproduced with iozone with a working set larger than available RAM. Reported-by: Fyodor Ustinov <ufm@ufm.su> Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> Signed-off-by: Sage Weil <sage@newdream.net> 
The rbd driver currently splits bios when they span an object boundary.
However, the blk_end_request expects the completions to roll up the results
in block device order, and the split rbd/ceph ops can complete in any
order.  This patch adds a struct rbd_req_coll to track completion of split
requests and ensures that the results are passed back up to the block layer
in order.

This fixes errors where the file system gets completion of a read operation
that spans an object boundary before the data has actually arrived.  The
bug is easily reproduced with iozone with a working set larger than
available RAM.

Reported-by: Fyodor Ustinov <ufm@ufm.su>
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
rbd: fix leak of ops struct 2011-05-13T03:59:14+00:00 Sage Weil sage@newdream.net 2011-05-12T23:13:54+00:00 11f770027b5c0de16544f3ec82b5c6f9f8d5a644 The ops vector must be freed by the rbd_do_request caller. Signed-off-by: Sage Weil <sage@newdream.net> 
The ops vector must be freed by the rbd_do_request caller.

Signed-off-by: Sage Weil <sage@newdream.net>
libceph: fix ceph_osdc_alloc_request error checks 2011-05-03T16:28:13+00:00 Sage Weil sage@newdream.net 2011-05-03T16:23:36+00:00 4ad12621e442b7a072e81270808f617cb65c5672 ceph_osdc_alloc_request returns NULL on failure. Signed-off-by: Sage Weil <sage@newdream.net> 
ceph_osdc_alloc_request returns NULL on failure.

Signed-off-by: Sage Weil <sage@newdream.net>
rbd: use watch/notify for changes in rbd header 2011-03-22T18:33:56+00:00 Yehuda Sadeh yehuda@hq.newdream.net 2011-03-21T22:10:11+00:00 59c2be1e4d42c0d4949cecdeef3f37070a1fbc13 Send notifications when we change the rbd header (e.g. create a snapshot) and wait for such notifications. This allows synchronizing the snapshot creation between different rbd clients/rools. Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> Signed-off-by: Sage Weil <sage@newdream.net> 
Send notifications when we change the rbd header (e.g. create a snapshot)
and wait for such notifications.  This allows synchronizing the snapshot
creation between different rbd clients/rools.

Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
rbd: fix cleanup when trying to mount inexistent image 2011-01-12T23:15:18+00:00 Yehuda Sadeh yehuda@hq.newdream.net 2011-01-07T22:58:42+00:00 766fc43973b16f9becb6b7402b3e052dbb84adee Previously we didn't clean up the sysfs entry that was just created. Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> Signed-off-by: Sage Weil <sage@newdream.net> 
Previously we didn't clean up the sysfs entry that was just
created.

Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
rbd: replace the rbd sysfs interface 2010-12-01T23:53:22+00:00 Yehuda Sadeh yehuda@hq.newdream.net 2010-11-19T22:51:04+00:00 dfc5606dc51381186de765243bab340c8e021868 The new interface creates directories per mapped image and under each it creates a subdir per available snapshot. This allows keeping a cleaner interface within the sysfs guidelines. The ABI documentation was updated too. Acked-by: Greg Kroah-Hartman <gregkh@suse.de> Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> Signed-off-by: Sage Weil <sage@newdream.net> 
The new interface creates directories per mapped image
and under each it creates a subdir per available snapshot.
This allows keeping a cleaner interface within the sysfs
guidelines. The ABI documentation was updated too.

Acked-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
Signed-off-by: Sage Weil <sage@newdream.net>
rbd: passing wrong variable to bvec_kunmap_irq() 2010-10-20T22:38:25+00:00 Dan Carpenter error27@gmail.com 2010-10-11T19:15:11+00:00 85b5aaa624aac568b8a3a88dbe4de6628c7cc527 We should be passing "buf" here insead of "bv". This is tricky because it's not the same as kmap() and kunmap(). GCC does warn about it if you compile on i386 with CONFIG_HIGHMEM. Signed-off-by: Dan Carpenter <error27@gmail.com> Signed-off-by: Sage Weil <sage@newdream.net> 
We should be passing "buf" here insead of "bv".  This is tricky because
it's not the same as kmap() and kunmap().  GCC does warn about it if you
compile on i386 with CONFIG_HIGHMEM.

Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Sage Weil <sage@newdream.net>
rbd: null vs ERR_PTR 2010-10-20T22:38:24+00:00 Dan Carpenter error27@gmail.com 2010-10-11T19:14:23+00:00 b8d0638a98aa4a42ff322234b882487cd74e5c52 ceph_alloc_page_vector() returns ERR_PTR(-ENOMEM) on errors. Signed-off-by: Dan Carpenter <error27@gmail.com> Signed-off-by: Sage Weil <sage@newdream.net> 
ceph_alloc_page_vector() returns ERR_PTR(-ENOMEM) on errors.

Signed-off-by: Dan Carpenter <error27@gmail.com>
Signed-off-by: Sage Weil <sage@newdream.net>
block: rbd: removing unnecessary test 2010-10-20T22:38:20+00:00 Yehuda Sadeh yehuda@hq.newdream.net 2010-09-27T17:51:53+00:00 f4cf3deef4c474381e8fee2e6099d49edd9105cb rbd_get_segment() can't return a negative value, we don't need to check the return output. Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> 
rbd_get_segment() can't return a negative value, we don't need to check
the return output.

Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>
block: rbd: fixed may leaks 2010-10-20T22:38:19+00:00 Vasiliy Kulikov segooon@gmail.com 2010-09-26T08:59:37+00:00 28f259b7cd78eb29d38b7ae6b475d656e08fd348 rbd_client_create() doesn't free rbdc, this leads to many leaks. seg_len in rbd_do_op() is unsigned, so (seg_len < 0) makes no sense. Also if fixed check fails then seg_name is leaked. Signed-off-by: Vasiliy Kulikov <segooon@gmail.com> Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net> 
rbd_client_create() doesn't free rbdc, this leads to many leaks.

seg_len in rbd_do_op() is unsigned, so (seg_len < 0) makes no sense.
Also if fixed check fails then seg_name is leaked.

Signed-off-by: Vasiliy Kulikov <segooon@gmail.com>
Signed-off-by: Yehuda Sadeh <yehuda@hq.newdream.net>