All of lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH-Resend] NFS41: layoutget optimize and pnfsblock cleanup
@ 2012-10-07 21:59 Peng Tao
  2012-10-07 22:06 ` Myklebust, Trond
  2012-10-09 18:44 ` Boaz Harrosh
  0 siblings, 2 replies; 7+ messages in thread
From: Peng Tao @ 2012-10-07 21:59 UTC (permalink / raw)
  To: Trond Myklebust; +Cc: linuxnfs

[-- Attachment #1: Type: text/plain, Size: 915 bytes --]

Hi Trond,

Following first three patches were sent before and optimize layoutget size.
Last patch is cleanup and is also sent before.

Sorry that I have to send patches as attachments. I am having problem
with my smtp setup.

Thanks,
Tao

Peng Tao (4):
  NFS: track direct IO left bytes
  NFS41: send real write size in layoutget
  NFS41: send real read size in layoutget
  pnfsblock: cleanup nfs4_blkdev_get

 fs/nfs/blocklayout/blocklayout.c    |   38 ++++++++++++++++++++++++++++++++--
 fs/nfs/blocklayout/blocklayout.h    |    1 -
 fs/nfs/blocklayout/blocklayoutdev.c |   25 ++++------------------
 fs/nfs/direct.c                     |   12 +++++++++++
 fs/nfs/internal.h                   |    1 +
 fs/nfs/objlayout/objio_osd.c        |    9 +++++++-
 fs/nfs/pnfs.c                       |   16 ++++++++++++--
 fs/nfs/pnfs.h                       |    3 +-
 8 files changed, 76 insertions(+), 29 deletions(-)

[-- Attachment #2: 0001-NFS-track-direct-IO-left-bytes.patch --]
[-- Type: application/octet-stream, Size: 2055 bytes --]

From 8f90bbd22998b218a766e67c4f6db74d043c5adb Mon Sep 17 00:00:00 2001
From: Peng Tao <bergwolf@gmail.com>
Date: Tue, 25 Sep 2012 14:55:57 +0800
Subject: [PATCH-Resend 1/4] NFS: track direct IO left bytes

Signed-off-by: Peng Tao <tao.peng@emc.com>
---
 fs/nfs/direct.c |    5 +++++
 1 files changed, 5 insertions(+), 0 deletions(-)

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 253d397..4be8673 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -78,6 +78,7 @@ struct nfs_direct_req {
 	atomic_t		io_count;	/* i/os we're waiting for */
 	spinlock_t		lock;		/* protect completion state */
 	ssize_t			count,		/* bytes actually processed */
+				bytes_left,	/* bytes left to be sent */
 				error;		/* any reported error */
 	struct completion	completion;	/* wait for i/o completion */
 
@@ -390,6 +391,7 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de
 			user_addr += req_len;
 			pos += req_len;
 			count -= req_len;
+			dreq->bytes_left -= req_len;
 		}
 		/* The nfs_page now hold references to these pages */
 		nfs_direct_release_pages(pagevec, npages);
@@ -457,6 +459,7 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
 		goto out;
 
 	dreq->inode = inode;
+	dreq->bytes_left = iov_length(iov, nr_segs);
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
 	l_ctx = nfs_get_lock_context(dreq->ctx);
 	if (IS_ERR(l_ctx)) {
@@ -710,6 +713,7 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d
 			user_addr += req_len;
 			pos += req_len;
 			count -= req_len;
+			dreq->bytes_left -= req_len;
 		}
 		/* The nfs_page now hold references to these pages */
 		nfs_direct_release_pages(pagevec, npages);
@@ -860,6 +864,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
 		goto out;
 
 	dreq->inode = inode;
+	dreq->bytes_left = count;
 	dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp));
 	l_ctx = nfs_get_lock_context(dreq->ctx);
 	if (IS_ERR(l_ctx)) {
-- 
1.7.7.6


[-- Attachment #3: 0002-NFS41-send-real-write-size-in-layoutget.patch --]
[-- Type: application/octet-stream, Size: 6325 bytes --]

From 700a8f23d588113ececcd7261f461232c813e738 Mon Sep 17 00:00:00 2001
From: Peng Tao <bergwolf@gmail.com>
Date: Tue, 25 Sep 2012 14:55:57 +0800
Subject: [PATCH-Resend 2/4] NFS41: send real write size in layoutget

For buffer write, block layout client scan inode mapping to find
next hole and use offset-to-hole as layoutget length. Object
layout client uses offset-to-isize as layoutget length.

For direct write, both block layout and object layout use dreq->bytes_left.

Signed-off-by: Peng Tao <tao.peng@emc.com>
---
 fs/nfs/blocklayout/blocklayout.c |   38 +++++++++++++++++++++++++++++++++++---
 fs/nfs/direct.c                  |    7 +++++++
 fs/nfs/internal.h                |    1 +
 fs/nfs/objlayout/objio_osd.c     |    9 ++++++++-
 fs/nfs/pnfs.c                    |    6 ++++--
 fs/nfs/pnfs.h                    |    3 ++-
 6 files changed, 57 insertions(+), 7 deletions(-)

diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index a34014a..f1027b0 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -37,6 +37,7 @@
 #include <linux/bio.h>		/* struct bio */
 #include <linux/buffer_head.h>	/* various write calls */
 #include <linux/prefetch.h>
+#include <linux/pagevec.h>
 
 #include "../pnfs.h"
 #include "../internal.h"
@@ -1204,14 +1205,45 @@ bl_pg_test_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 	return pnfs_generic_pg_test(pgio, prev, req);
 }
 
+/*
+ * Return the number of contiguous bytes for a given inode
+ * starting at page frame idx.
+ */
+static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx)
+{
+	struct address_space *mapping = inode->i_mapping;
+	pgoff_t end;
+
+	/* Optimize common case that writes from 0 to end of file */
+	end = DIV_ROUND_UP(i_size_read(inode), PAGE_CACHE_SIZE);
+	if (end != NFS_I(inode)->npages) {
+		rcu_read_lock();
+		end = radix_tree_next_hole(&mapping->page_tree, idx + 1, ULONG_MAX);
+		rcu_read_unlock();
+	}
+
+	if (!end)
+		return i_size_read(inode) - (idx << PAGE_CACHE_SHIFT);
+	else
+		return (end - idx) << PAGE_CACHE_SHIFT;
+}
+
 static void
 bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
 	if (pgio->pg_dreq != NULL &&
-	    !is_aligned_req(req, PAGE_CACHE_SIZE))
+	    !is_aligned_req(req, PAGE_CACHE_SIZE)) {
 		nfs_pageio_reset_write_mds(pgio);
-	else
-		pnfs_generic_pg_init_write(pgio, req);
+	} else {
+		u64 wb_size;
+		if (pgio->pg_dreq == NULL)
+			wb_size = pnfs_num_cont_bytes(pgio->pg_inode,
+						      req->wb_index);
+		else
+			wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+
+		pnfs_generic_pg_init_write(pgio, req, wb_size);
+	}
 }
 
 static bool
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 4be8673..cae26cb 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -46,6 +46,7 @@
 #include <linux/kref.h>
 #include <linux/slab.h>
 #include <linux/task_io_accounting_ops.h>
+#include <linux/module.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_page.h>
@@ -191,6 +192,12 @@ static void nfs_direct_req_release(struct nfs_direct_req *dreq)
 	kref_put(&dreq->kref, nfs_direct_req_free);
 }
 
+ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq)
+{
+	return dreq->bytes_left;
+}
+EXPORT_SYMBOL_GPL(nfs_dreq_bytes_left);
+
 /*
  * Collects and returns the final error value/byte-count.
  */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 89a795d..59b133c 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -464,6 +464,7 @@ static inline void nfs_inode_dio_wait(struct inode *inode)
 {
 	inode_dio_wait(inode);
 }
+extern ssize_t nfs_dreq_bytes_left(struct nfs_direct_req *dreq);
 
 /* nfs4proc.c */
 extern void __nfs4_read_done_cb(struct nfs_read_data *);
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index ea6d111..be731e6 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -41,6 +41,7 @@
 #include <scsi/osd_ore.h>
 
 #include "objlayout.h"
+#include "../internal.h"
 
 #define NFSDBG_FACILITY         NFSDBG_PNFS_LD
 
@@ -606,8 +607,14 @@ static bool aligned_on_raid_stripe(u64 offset, struct ore_layout *layout,
 void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
 	unsigned long stripe_end = 0;
+	u64 wb_size;
 
-	pnfs_generic_pg_init_write(pgio, req);
+	if (pgio->pg_dreq == NULL)
+		wb_size = i_size_read(pgio->pg_inode) - req_offset(req);
+	else
+		wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+
+	pnfs_generic_pg_init_write(pgio, req, wb_size);
 	if (unlikely(pgio->pg_lseg == NULL))
 		return; /* Not pNFS */
 
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index de82725..97dd47c 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1242,7 +1242,8 @@ pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *r
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_read);
 
 void
-pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
+			   struct nfs_page *req, u64 wb_size)
 {
 	BUG_ON(pgio->pg_lseg != NULL);
 
@@ -1250,10 +1251,11 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *
 		nfs_pageio_reset_write_mds(pgio);
 		return;
 	}
+
 	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   req_offset(req),
-					   req->wb_bytes,
+					   wb_size,
 					   IOMODE_RW,
 					   GFP_NOFS);
 	/* If no lseg, fall back to write through mds */
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 6cede2c..2d722db 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -186,7 +186,8 @@ void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32);
 void unset_pnfs_layoutdriver(struct nfs_server *);
 void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *);
 int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
-void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *, struct nfs_page *);
+void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
+			        struct nfs_page *req, u64 wb_size);
 int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc);
 bool pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev, struct nfs_page *req);
 void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg);
-- 
1.7.7.6


[-- Attachment #4: 0003-NFS41-send-real-read-size-in-layoutget.patch --]
[-- Type: application/octet-stream, Size: 1236 bytes --]

From 0e2ceea4cf1830297726a175e1fabafe2a31adf0 Mon Sep 17 00:00:00 2001
From: Peng Tao <bergwolf@gmail.com>
Date: Tue, 25 Sep 2012 14:55:57 +0800
Subject: [PATCH-Resend 3/4] NFS41: send real read size in layoutget

For buffer read, use offst-to-isize.

For direct read, use dreq->bytes_left.

Signed-off-by: Peng Tao <tao.peng@emc.com>
---
 fs/nfs/pnfs.c |   10 +++++++++-
 1 files changed, 9 insertions(+), 1 deletions(-)

diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 97dd47c..0c01bca 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1222,16 +1222,24 @@ out_forget_reply:
 void
 pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
+	u64 rd_size = req->wb_bytes;
+
 	BUG_ON(pgio->pg_lseg != NULL);
 
 	if (req->wb_offset != req->wb_pgbase) {
 		nfs_pageio_reset_read_mds(pgio);
 		return;
 	}
+
+	if (pgio->pg_dreq == NULL)
+		rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
+	else
+		rd_size = nfs_dreq_bytes_left(pgio->pg_dreq);
+
 	pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 					   req->wb_context,
 					   req_offset(req),
-					   req->wb_bytes,
+					   rd_size,
 					   IOMODE_READ,
 					   GFP_KERNEL);
 	/* If no lseg, fall back to read through mds */
-- 
1.7.7.6


[-- Attachment #5: 0004-pnfsblock-cleanup-nfs4_blkdev_get.patch --]
[-- Type: application/octet-stream, Size: 2308 bytes --]

From d3097f1e2a2fe3b55ec87559b70abdcfc5466346 Mon Sep 17 00:00:00 2001
From: Peng Tao <bergwolf@gmail.com>
Date: Tue, 25 Sep 2012 14:55:57 +0800
Subject: [PATCH-Resend 4/4] pnfsblock: cleanup nfs4_blkdev_get

It is not needed at all and it is messing with return values...

Reported-by: Wei Yongjun <yongjun_wei@trendmicro.com.cn>
Signed-off-by: Peng Tao <tao.peng@emc.com>
---
 fs/nfs/blocklayout/blocklayout.h    |    1 -
 fs/nfs/blocklayout/blocklayoutdev.c |   25 +++++--------------------
 2 files changed, 5 insertions(+), 21 deletions(-)

diff --git a/fs/nfs/blocklayout/blocklayout.h b/fs/nfs/blocklayout/blocklayout.h
index 39bb51a..f4891bd 100644
--- a/fs/nfs/blocklayout/blocklayout.h
+++ b/fs/nfs/blocklayout/blocklayout.h
@@ -173,7 +173,6 @@ struct bl_msg_hdr {
 /* blocklayoutdev.c */
 ssize_t bl_pipe_downcall(struct file *, const char __user *, size_t);
 void bl_pipe_destroy_msg(struct rpc_pipe_msg *);
-struct block_device *nfs4_blkdev_get(dev_t dev);
 int nfs4_blkdev_put(struct block_device *bdev);
 struct pnfs_block_dev *nfs4_blk_decode_device(struct nfs_server *server,
 						struct pnfs_device *dev);
diff --git a/fs/nfs/blocklayout/blocklayoutdev.c b/fs/nfs/blocklayout/blocklayoutdev.c
index c965542..a86c5bd 100644
--- a/fs/nfs/blocklayout/blocklayoutdev.c
+++ b/fs/nfs/blocklayout/blocklayoutdev.c
@@ -53,22 +53,6 @@ static int decode_sector_number(__be32 **rp, sector_t *sp)
 	return 0;
 }
 
-/* Open a block_device by device number. */
-struct block_device *nfs4_blkdev_get(dev_t dev)
-{
-	struct block_device *bd;
-
-	dprintk("%s enter\n", __func__);
-	bd = blkdev_get_by_dev(dev, FMODE_READ, NULL);
-	if (IS_ERR(bd))
-		goto fail;
-	return bd;
-fail:
-	dprintk("%s failed to open device : %ld\n",
-			__func__, PTR_ERR(bd));
-	return NULL;
-}
-
 /*
  * Release the block device
  */
@@ -172,11 +156,12 @@ nfs4_blk_decode_device(struct nfs_server *server,
 		goto out;
 	}
 
-	bd = nfs4_blkdev_get(MKDEV(reply->major, reply->minor));
+	bd = blkdev_get_by_dev(MKDEV(reply->major, reply->minor),
+			       FMODE_READ, NULL);
 	if (IS_ERR(bd)) {
-		rc = PTR_ERR(bd);
-		dprintk("%s failed to open device : %d\n", __func__, rc);
-		rv = ERR_PTR(rc);
+		dprintk("%s failed to open device : %ld\n", __func__,
+			PTR_ERR(bd));
+		rv = ERR_CAST(bd);
 		goto out;
 	}
 
-- 
1.7.7.6


^ permalink raw reply related	[flat|nested] 7+ messages in thread

* Re: [PATCH-Resend] NFS41: layoutget optimize and pnfsblock cleanup
  2012-10-07 21:59 [PATCH-Resend] NFS41: layoutget optimize and pnfsblock cleanup Peng Tao
@ 2012-10-07 22:06 ` Myklebust, Trond
  2012-10-09  7:17   ` Peng Tao
  2012-10-09 18:44 ` Boaz Harrosh
  1 sibling, 1 reply; 7+ messages in thread
From: Myklebust, Trond @ 2012-10-07 22:06 UTC (permalink / raw)
  To: Peng Tao; +Cc: linuxnfs

Aren't these already in the nfs-for-next branch?

Peng Tao <bergwolf@gmail.com> wrote:


Hi Trond,

Following first three patches were sent before and optimize layoutget size.
Last patch is cleanup and is also sent before.

Sorry that I have to send patches as attachments. I am having problem
with my smtp setup.

Thanks,
Tao

Peng Tao (4):
  NFS: track direct IO left bytes
  NFS41: send real write size in layoutget
  NFS41: send real read size in layoutget
  pnfsblock: cleanup nfs4_blkdev_get

 fs/nfs/blocklayout/blocklayout.c    |   38 ++++++++++++++++++++++++++++++++--
 fs/nfs/blocklayout/blocklayout.h    |    1 -
 fs/nfs/blocklayout/blocklayoutdev.c |   25 ++++------------------
 fs/nfs/direct.c                     |   12 +++++++++++
 fs/nfs/internal.h                   |    1 +
 fs/nfs/objlayout/objio_osd.c        |    9 +++++++-
 fs/nfs/pnfs.c                       |   16 ++++++++++++--
 fs/nfs/pnfs.h                       |    3 +-
 8 files changed, 76 insertions(+), 29 deletions(-)

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH-Resend] NFS41: layoutget optimize and pnfsblock cleanup
  2012-10-07 22:06 ` Myklebust, Trond
@ 2012-10-09  7:17   ` Peng Tao
  0 siblings, 0 replies; 7+ messages in thread
From: Peng Tao @ 2012-10-09  7:17 UTC (permalink / raw)
  To: Myklebust, Trond; +Cc: linuxnfs

On 10/8/12, Myklebust, Trond <Trond.Myklebust@netapp.com> wrote:
> Aren't these already in the nfs-for-next branch?
>
No. You only merged the IO alignment and bugfix patches.
These are layoutget size optimization that you and Boaz reviewed sometime ago.

Thanks,
Tao

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH-Resend] NFS41: layoutget optimize and pnfsblock cleanup
  2012-10-07 21:59 [PATCH-Resend] NFS41: layoutget optimize and pnfsblock cleanup Peng Tao
  2012-10-07 22:06 ` Myklebust, Trond
@ 2012-10-09 18:44 ` Boaz Harrosh
  2012-10-09 19:03   ` Boaz Harrosh
  1 sibling, 1 reply; 7+ messages in thread
From: Boaz Harrosh @ 2012-10-09 18:44 UTC (permalink / raw)
  To: Peng Tao; +Cc: Trond Myklebust, linuxnfs

On 10/07/2012 02:59 PM, Peng Tao wrote:
> Hi Trond,
> 
> Following first three patches were sent before and optimize layoutget size.
> Last patch is cleanup and is also sent before.
> 
> Sorry that I have to send patches as attachments. I am having problem
> with my smtp setup.
> 
> Thanks,
> Tao
> 

Tao hi.

What are these patches based on? they do not apply to Linus tree as of today
(v3.6-9228-g547b1e8) and they do not apply to v3.6 nor v3.5 tags.

I get a conflict on the first patch:
	NFS: track direct IO left bytes

(Do you have a public git tree with these on? Why don't you ask for a git tree
 on git.linux-nfs.org. Trond who should we ask for an hosting on git.linux-nfs.org)

Thanks
Boaz

> Peng Tao (4):
>   NFS: track direct IO left bytes
>   NFS41: send real write size in layoutget
>   NFS41: send real read size in layoutget
>   pnfsblock: cleanup nfs4_blkdev_get
> 
>  fs/nfs/blocklayout/blocklayout.c    |   38 ++++++++++++++++++++++++++++++++--
>  fs/nfs/blocklayout/blocklayout.h    |    1 -
>  fs/nfs/blocklayout/blocklayoutdev.c |   25 ++++------------------
>  fs/nfs/direct.c                     |   12 +++++++++++
>  fs/nfs/internal.h                   |    1 +
>  fs/nfs/objlayout/objio_osd.c        |    9 +++++++-
>  fs/nfs/pnfs.c                       |   16 ++++++++++++--
>  fs/nfs/pnfs.h                       |    3 +-
>  8 files changed, 76 insertions(+), 29 deletions(-)
> 



^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH-Resend] NFS41: layoutget optimize and pnfsblock cleanup
  2012-10-09 18:44 ` Boaz Harrosh
@ 2012-10-09 19:03   ` Boaz Harrosh
  2012-10-10 10:13     ` Peng Tao
  0 siblings, 1 reply; 7+ messages in thread
From: Boaz Harrosh @ 2012-10-09 19:03 UTC (permalink / raw)
  To: Peng Tao; +Cc: Trond Myklebust, linuxnfs

On 10/09/2012 11:44 AM, Boaz Harrosh wrote:
> On 10/07/2012 02:59 PM, Peng Tao wrote:
>> Hi Trond,
>>
>> Following first three patches were sent before and optimize layoutget size.
>> Last patch is cleanup and is also sent before.
>>
>> Sorry that I have to send patches as attachments. I am having problem
>> with my smtp setup.
>>
>> Thanks,
>> Tao
>>
> 
> Tao hi.
> 
> What are these patches based on? they do not apply to Linus tree as of today
> (v3.6-9228-g547b1e8) and they do not apply to v3.6 nor v3.5 tags.
> 
> I get a conflict on the first patch:
> 	NFS: track direct IO left bytes
> 

Actually the second patch does not apply either. minor on pnfs.c but
a real fallout on blocklayout.c (3 and 4 are fine)

Boaz

> (Do you have a public git tree with these on? Why don't you ask for a git tree
>  on git.linux-nfs.org. Trond who should we ask for an hosting on git.linux-nfs.org)
> 
> Thanks
> Boaz
> 
>> Peng Tao (4):
>>   NFS: track direct IO left bytes
>>   NFS41: send real write size in layoutget
>>   NFS41: send real read size in layoutget
>>   pnfsblock: cleanup nfs4_blkdev_get
>>
>>  fs/nfs/blocklayout/blocklayout.c    |   38 ++++++++++++++++++++++++++++++++--
>>  fs/nfs/blocklayout/blocklayout.h    |    1 -
>>  fs/nfs/blocklayout/blocklayoutdev.c |   25 ++++------------------
>>  fs/nfs/direct.c                     |   12 +++++++++++
>>  fs/nfs/internal.h                   |    1 +
>>  fs/nfs/objlayout/objio_osd.c        |    9 +++++++-
>>  fs/nfs/pnfs.c                       |   16 ++++++++++++--
>>  fs/nfs/pnfs.h                       |    3 +-
>>  8 files changed, 76 insertions(+), 29 deletions(-)
>>
> 
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 



^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH-Resend] NFS41: layoutget optimize and pnfsblock cleanup
  2012-10-09 19:03   ` Boaz Harrosh
@ 2012-10-10 10:13     ` Peng Tao
  2012-10-10 18:47       ` Boaz Harrosh
  0 siblings, 1 reply; 7+ messages in thread
From: Peng Tao @ 2012-10-10 10:13 UTC (permalink / raw)
  To: Boaz Harrosh; +Cc: Trond Myklebust, linuxnfs

On Wed, Oct 10, 2012 at 3:03 AM, Boaz Harrosh <bharrosh@panasas.com> wrote:
> On 10/09/2012 11:44 AM, Boaz Harrosh wrote:
>> On 10/07/2012 02:59 PM, Peng Tao wrote:
>>> Hi Trond,
>>>
>>> Following first three patches were sent before and optimize layoutget size.
>>> Last patch is cleanup and is also sent before.
>>>
>>> Sorry that I have to send patches as attachments. I am having problem
>>> with my smtp setup.
>>>
>>> Thanks,
>>> Tao
>>>
>>
>> Tao hi.
>>
>> What are these patches based on? they do not apply to Linus tree as of today
>> (v3.6-9228-g547b1e8) and they do not apply to v3.6 nor v3.5 tags.
>>
>> I get a conflict on the first patch:
>>       NFS: track direct IO left bytes
>>
>
> Actually the second patch does not apply either. minor on pnfs.c but
> a real fallout on blocklayout.c (3 and 4 are fine)
>
Sorry I forgot to mention... They apply to Trond's nfs-for-next
branch, commit (5f65753033d8c5a53e65810bff3832e8282c68d1).

Thanks,
Tao

^ permalink raw reply	[flat|nested] 7+ messages in thread

* Re: [PATCH-Resend] NFS41: layoutget optimize and pnfsblock cleanup
  2012-10-10 10:13     ` Peng Tao
@ 2012-10-10 18:47       ` Boaz Harrosh
  0 siblings, 0 replies; 7+ messages in thread
From: Boaz Harrosh @ 2012-10-10 18:47 UTC (permalink / raw)
  To: Peng Tao; +Cc: Trond Myklebust, linuxnfs

On 10/10/2012 03:13 AM, Peng Tao wrote:
> Sorry I forgot to mention... They apply to Trond's nfs-for-next
> branch, commit (5f65753033d8c5a53e65810bff3832e8282c68d1).
> 

NP thanks, I just saw Trond's pull request patches are part of that
pull, I will test with 3.7-rc1 and will report if I have any problems.

Thanks Tao
Boaz

> Thanks,
> Tao
> 

^ permalink raw reply	[flat|nested] 7+ messages in thread

end of thread, other threads:[~2012-10-10 18:47 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2012-10-07 21:59 [PATCH-Resend] NFS41: layoutget optimize and pnfsblock cleanup Peng Tao
2012-10-07 22:06 ` Myklebust, Trond
2012-10-09  7:17   ` Peng Tao
2012-10-09 18:44 ` Boaz Harrosh
2012-10-09 19:03   ` Boaz Harrosh
2012-10-10 10:13     ` Peng Tao
2012-10-10 18:47       ` Boaz Harrosh

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.