Commits · 5fadeb47dcc5c30d4b6cf481b4a78689eab59443 · Kirill Smelkov / linux

03 Feb, 2015 40 commits

nfs: count DIO good bytes correctly with mirroring · 5fadeb47

Peng Tao authored Jan 19, 2015

When resending to MDS, we might resend multiple mirroring
requests to MDS. As a result, nfs_direct_good_bytes() ends
up counting bytes multiple times, causing application to
get wrong return results in read/write syscalls.

Fix it by tracking start of a dreq and checking the range of
pgio header.

Cc: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Peng Tao <tao.peng@primarydata.com>

5fadeb47

nfs41: wait for LAYOUTRETURN before retrying LAYOUTGET · aa8a45ee

Peng Tao authored Dec 01, 2014

Also take care to stop waiting if someone clears retry bit.
Signed-off-by: Peng Tao <tao.peng@primarydata.com>

aa8a45ee

nfs: add a helper to set NFS_ODIRECT_RESCHED_WRITES to direct writes · 012fa16d
Peng Tao authored Dec 01, 2014
```
To allow pnfs LD to ask direct writes to be resend.
Signed-off-by: Peng Tao <tao.peng@primarydata.com>
```
012fa16d

nfs41: add NFS_LAYOUT_RETRY_LAYOUTGET to layout header flags · c829013d

Peng Tao authored Dec 01, 2014

Use it to indicate that LD wants to retry layoutget. LD can set
it whenever it wants the common pnfs code to return and retry
pnfs path through a new layout.

The bit gets cleared when client does a new layoutget, when client
closes the file (ROC case), or when kernel needs to evict the inode
(non-ROC case).
Signed-off-by: Peng Tao <tao.peng@primarydata.com>

c829013d

nfs/flexfiles: send layoutreturn before freeing lseg · 27b6f539

Peng Tao authored Oct 20, 2014

Otherwise we'll lose error tracking information when
encoding layoutreturn.

pnfs_put_lseg may be called from rpc callbacks. So we should not
call pnfs_send_layoutreturn directly because it can deadlock in
the rpc layer.
Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Tom Haynes <loghyr@primarydata.com>

27b6f539

nfs41: introduce NFS_LAYOUT_RETURN_BEFORE_CLOSE · 193e3aa2

Peng Tao authored Nov 17, 2014

When it is set, generic pnfs would try to send layoutreturn right
before last close/delegation_return regard less NFS_LAYOUT_ROC is
set or not. LD can then make sure layoutreturn is always sent
rather than being omitted.

The difference against NFS_LAYOUT_RETURN is that
NFS_LAYOUT_RETURN_BEFORE_CLOSE does not block usage of the layout so
LD can set it and expect generic layer to try pnfs path at the
same time.
Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Tom Haynes <loghyr@primarydata.com>

193e3aa2

nfs41: allow async version layoutreturn · 6c16605d

Peng Tao authored Nov 17, 2014

Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Tom Haynes <loghyr@primarydata.com>

6c16605d

nfs41: add range to layoutreturn args · 15eb67c1

Peng Tao authored Nov 17, 2014

So that callers can specify which range to return.
Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Tom Haynes <loghyr@primarydata.com>

15eb67c1

pnfs: allow LD to ask to resend read through pnfs · ceb11e13

Peng Tao authored Nov 10, 2014

If current IO cannot be completed due to some transient errors,
LD may want to ask generic layer to resend the request through
pnfs again.
Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Tom Haynes <loghyr@primarydata.com>

ceb11e13

nfs: add nfs_pgio_current_mirror helper · 48d635f1

Peng Tao authored Nov 10, 2014

Let it return current nfs_pgio_mirror in use depending on pg_mirror_count.
For read, we always use pg_mirrors[0], so this effectively gives us freedom
to use pg_mirror_idx to track the actual mirror to read from through out the
IO stack.
Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Tom Haynes <loghyr@primarydata.com>

48d635f1

nfs: only reset desc->pg_mirror_idx when mirroring is supported · 47af81f2

Peng Tao authored Nov 10, 2014

so that we don't reset desc->pg_mirror_idx for read unnecessarily.
Remove WARN_ON_ONCE from __nfs_pageio_add_request to allow LD to
set pg_mirror_idx for read where pg_mirror_count is always 1.
Signed-off-by: Peng Tao <tao.peng@primarydata.com>
Signed-off-by: Tom Haynes <loghyr@primarydata.com>

47af81f2

nfs41: add a debug warning if we destroy an unempty layout · 566f8737

Peng Tao authored Oct 10, 2014

So that we can detect the case if some layout segments are still
pinned which is surely a bug that we need to fix.
Signed-off-by: Peng Tao <tao.peng@primarydata.com>

566f8737

pnfs: fail comparison when bucket verifier not set · 80c76fe3

Weston Andros Adamson authored Oct 01, 2014

This skips the WARN_ON_ONCE, but doesnt change behavior (the memcmp would
fail).
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>
Signed-off-by: Tom Haynes <Thomas.Haynes@primarydata.com>

80c76fe3

nfs: mirroring support for direct io · 0a00b77b

Weston Andros Adamson authored Sep 19, 2014

The current mirroring code only notices short writes to the first
mirror. This patch keeps per-mirror byte counts and only considers
a byte to be written once all mirrors report so.
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>

0a00b77b

nfs: add mirroring support to pgio layer · a7d42ddb

Weston Andros Adamson authored Sep 19, 2014

This patch adds mirrored write support to the pgio layer. The default
is to use one mirror, but pgio callers may define callbacks to change
this to any value up to the (arbitrarily selected) limit of 16.

The basic idea is to break out members of nfs_pageio_descriptor that cannot
be shared between mirrored DSes and put them in a new structure.
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>

a7d42ddb

pnfs: pass ds_commit_idx through the commit path · b57ff130

Weston Andros Adamson authored Sep 05, 2014

Pass ds_commit_idx through the nfs commit path. It's used to select
the commit bucket when using pnfs and is ignored when not using pnfs.
Several functions had to be changed: nfs_retry_commit,
nfs_mark_request_commit, pnfs_mark_request_commit and the pnfs layout
driver .mark_request_commit functions.
Signed-off-by: Tom Haynes <loghyr@primarydata.com>

b57ff130

nfs: rename pgio header ds_idx to ds_commit_idx · 6cccbb6f

Weston Andros Adamson authored Sep 16, 2014

'ds_commit_idx' is a better name - it is used to select the right
commit bucket for pnfs.
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>

6cccbb6f

nfs: handle overlapping reqs in lock_and_join · 309a1d65

Weston Andros Adamson authored Sep 05, 2014

This is needed for mirrored DS support, where multuple requests
cover the same range.
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>

309a1d65

pnfs: release lseg in pnfs_generic_pg_cleanup · 180bb5ec

Weston Andros Adamson authored Sep 10, 2014

This is needed to support mirrored writes - the first write can't just
trash the lseg, we need to keep it around until all mirrors have
written.
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>

180bb5ec

nfs: introduce pg_cleanup op for pgio descriptors · 2176bf42

Weston Andros Adamson authored Sep 10, 2014

Add a new operation to nfs_pageio_ops that is called on nfs_pageio_complete.
Signed-off-by: Weston Andros Adamson <dros@primarydata.com>

2176bf42

nfs/filelayout: use pnfs_error_mark_layout_for_return · c220106f