From: andros@netapp.com
To: pnfs@linux-nfs.org
Cc: linux-nfs@vger.kernel.org, Andy Adamson <andros@netapp.com>
Subject: [PATCH 03/14] SQUASHME pnfs_submit: remove multilist4 caching
Date: Thu, 8 Apr 2010 15:53:59 -0400 [thread overview]
Message-ID: <1270756450-5570-4-git-send-email-andros@netapp.com> (raw)
In-Reply-To: <1270756450-5570-3-git-send-email-andros@netapp.com>
From: Andy Adamson <andros@netapp.com>
We only support the use of the first multipath4 data server.
Remove the multipath structures from struct nfs4_file_layout_dsaddr
and regroup it's allocation to fit the new strucuture.
Refactor the associated debug print routines.
Signed-off-by: Andy Adamson <andros@netapp.com>
---
fs/nfs/nfs4filelayout.c | 44 ++++---------
fs/nfs/nfs4filelayout.h | 12 +---
fs/nfs/nfs4filelayoutdev.c | 151 +++++++++++++++++++-------------------------
3 files changed, 81 insertions(+), 126 deletions(-)
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index ffc3ef2..abdf691 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -252,7 +252,6 @@ filelayout_read_pagelist(struct pnfs_layout_type *layoutid,
struct inode *inode = PNFS_INODE(layoutid);
struct nfs4_filelayout_segment *flseg;
struct nfs4_pnfs_dserver dserver;
- struct nfs4_pnfs_ds *ds;
int status;
dprintk("--> %s ino %lu nr_pages %d pgbase %u req %Zu@%llu\n",
@@ -271,14 +270,12 @@ filelayout_read_pagelist(struct pnfs_layout_type *layoutid,
return PNFS_NOT_ATTEMPTED;
}
- ds = dserver.multipath->ds_list[0];
-
dprintk("%s USE DS:ip %x %s\n", __func__,
- htonl(ds->ds_ip_addr), ds->r_addr);
+ htonl(dserver.ds->ds_ip_addr), dserver.ds->r_addr);
/* just try the first data server for the index..*/
- data->fldata.pnfs_client = ds->ds_clp->cl_rpcclient;
- data->fldata.ds_nfs_client = ds->ds_clp;
+ data->fldata.pnfs_client = dserver.ds->ds_clp->cl_rpcclient;
+ data->fldata.ds_nfs_client = dserver.ds->ds_clp;
data->args.fh = dserver.fh;
/* Now get the file offset on the dserver
@@ -300,16 +297,6 @@ filelayout_read_pagelist(struct pnfs_layout_type *layoutid,
return PNFS_ATTEMPTED;
}
-void
-print_ds(struct nfs4_pnfs_ds *ds)
-{
- dprintk(" ds->ds_ip_addr %x\n", htonl(ds->ds_ip_addr));
- dprintk(" ds->ds_port %hu\n", ntohs(ds->ds_port));
- dprintk(" ds->ds_clp %p\n", ds->ds_clp);
- dprintk(" ds->ds_count %d\n", atomic_read(&ds->ds_count));
- dprintk(" %s\n", ds->r_addr);
-}
-
/* Perform async writes. */
static enum pnfs_try_status
filelayout_write_pagelist(struct pnfs_layout_type *layoutid,
@@ -324,7 +311,6 @@ filelayout_write_pagelist(struct pnfs_layout_type *layoutid,
struct inode *inode = PNFS_INODE(layoutid);
struct nfs4_filelayout_segment *flseg = LSEG_LD_DATA(data->pdata.lseg);
struct nfs4_pnfs_dserver dserver;
- struct nfs4_pnfs_ds *ds;
int status;
dprintk("--> %s ino %lu nr_pages %d pgbase %u req %Zu@%llu sync %d\n",
@@ -342,16 +328,13 @@ filelayout_write_pagelist(struct pnfs_layout_type *layoutid,
return PNFS_NOT_ATTEMPTED;
}
- /* use the first multipath data server */
- ds = dserver.multipath->ds_list[0];
-
dprintk("%s ino %lu %Zu@%llu DS:%x:%hu %s\n",
__func__, inode->i_ino, count, offset,
- htonl(ds->ds_ip_addr), ntohs(ds->ds_port),
- ds->r_addr);
+ htonl(dserver.ds->ds_ip_addr), ntohs(dserver.ds->ds_port),
+ dserver.ds->r_addr);
- data->fldata.pnfs_client = ds->ds_clp->cl_rpcclient;
- data->fldata.ds_nfs_client = ds->ds_clp;
+ data->fldata.pnfs_client = dserver.ds->ds_clp->cl_rpcclient;
+ data->fldata.ds_nfs_client = dserver.ds->ds_clp;
data->args.fh = dserver.fh;
/* Get the file offset on the dserver. Set the write offset to
@@ -396,8 +379,8 @@ filelayout_free_layout(void *layoutid)
* Make sure layout segment parameters are sane WRT the device.
*
* Notes:
- * 1) current code insists that # stripe index = # multipath devices which
- * is wrong.
+ * 1) current code insists that # stripe index = # data servers in ds_list
+ * which is wrong.
* 2) pattern_offset is ignored and must == 0 which is wrong;
* 3) the pattern_offset needs to be a mutliple of the stripe unit.
* 4) stripe unit is multiple of page size
@@ -443,9 +426,9 @@ filelayout_check_layout(struct pnfs_layout_type *lo,
}
/* XXX only support SPARSE packing. Don't support use MDS open fh */
- if (!(fl->num_fh == 1 || fl->num_fh == dsaddr->multipath_count)) {
- dprintk("%s num_fh %u not equal to 1 or multipath_count %u\n",
- __func__, fl->num_fh, dsaddr->multipath_count);
+ if (!(fl->num_fh == 1 || fl->num_fh == dsaddr->ds_num)) {
+ dprintk("%s num_fh %u not equal to 1 or ds_num %u\n",
+ __func__, fl->num_fh, dsaddr->ds_num);
goto out;
}
@@ -714,8 +697,7 @@ filelayout_commit(struct pnfs_layout_type *layoutid, int sync,
list_add(&dsdata->pages, &head2);
list_del_init(&head2);
- /* Just try the first multipath data server */
- ds = dserver.multipath->ds_list[0];
+ ds = dserver.ds;
dsdata->fldata.pnfs_client = ds->ds_clp->cl_rpcclient;
dsdata->fldata.ds_nfs_client = ds->ds_clp;
dsdata->args.fh = dserver.fh;
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
index 3821989..0df1eaf 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/nfs4filelayout.h
@@ -42,18 +42,13 @@ struct nfs4_pnfs_ds {
char r_addr[29];
};
-struct nfs4_multipath {
- int num_ds;
- struct nfs4_pnfs_ds *ds_list[NFS4_PNFS_MAX_MULTI_DS];
-};
-
struct nfs4_file_layout_dsaddr {
struct hlist_node hash_node; /* nfs4_pnfs_dev_hlist dev_list */
struct pnfs_deviceid dev_id;
u32 stripe_count;
u8 *stripe_indices;
- u32 multipath_count;
- struct nfs4_multipath *multipath_list;
+ u32 ds_num;
+ struct nfs4_pnfs_ds *ds_list[1];
};
struct nfs4_pnfs_dev_hlist {
@@ -69,7 +64,7 @@ struct nfs4_pnfs_dev_hlist {
struct nfs4_pnfs_dserver {
struct nfs_fh *fh;
- struct nfs4_multipath *multipath;
+ struct nfs4_pnfs_ds *ds;
};
struct nfs4_filelayout_segment {
@@ -97,6 +92,7 @@ struct filelayout_mount_type {
extern struct pnfs_client_operations *pnfs_callback_ops;
+extern void print_ds(struct nfs4_pnfs_ds *ds);
char *deviceid_fmt(const struct pnfs_deviceid *dev_id);
int nfs4_pnfs_devlist_init(struct nfs4_pnfs_dev_hlist *hlist);
void nfs4_pnfs_devlist_destroy(struct nfs4_pnfs_dev_hlist *hlist);
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index ebb9845..ea25bd2 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -53,43 +53,31 @@
#define NFSDBG_FACILITY NFSDBG_PNFS_LD
void
-print_ds_list(struct nfs4_multipath *multipath)
+print_ds(struct nfs4_pnfs_ds *ds)
{
- struct nfs4_pnfs_ds *ds;
- int i;
-
- ds = multipath->ds_list[0];
if (ds == NULL) {
dprintk("%s NULL device \n", __func__);
return;
}
- for (i = 0; i < multipath->num_ds; i++) {
- dprintk(" ip_addr %x\n", ntohl(ds->ds_ip_addr));
- dprintk(" port %hu\n", ntohs(ds->ds_port));
- dprintk(" client %p\n", ds->ds_clp);
- dprintk(" ref count %d\n", atomic_read(&ds->ds_count));
- if (ds->ds_clp)
- dprintk(" cl_exchange_flags %x\n",
+ dprintk(" ip_addr %x\n", ntohl(ds->ds_ip_addr));
+ dprintk(" port %hu\n", ntohs(ds->ds_port));
+ dprintk(" client %p\n", ds->ds_clp);
+ dprintk(" ref count %d\n", atomic_read(&ds->ds_count));
+ if (ds->ds_clp)
+ dprintk(" cl_exchange_flags %x\n",
ds->ds_clp->cl_exchange_flags);
- dprintk(" ip:port %s\n", ds->r_addr);
- ds++;
- }
+ dprintk(" ip:port %s\n", ds->r_addr);
}
void
-print_multipath_list(struct nfs4_file_layout_dsaddr *dsaddr)
+print_ds_list(struct nfs4_file_layout_dsaddr *dsaddr)
{
- struct nfs4_multipath *multipath;
int i;
- multipath = &dsaddr->multipath_list[0];
- dprintk("%s dsaddr->multipath_count %d\n", __func__,
- dsaddr->multipath_count);
- for (i = 0; i < dsaddr->multipath_count; i++) {
- dprintk(" num_ds %d\n", multipath->num_ds);
- print_ds_list(multipath);
- multipath++;
- }
+ dprintk("%s dsaddr->ds_num %d\n", __func__,
+ dsaddr->ds_num);
+ for (i = 0; i < dsaddr->ds_num; i++)
+ print_ds(dsaddr->ds_list[i]);
}
/* Debugging function assuming a 64bit major/minor split of the deviceid */
@@ -174,9 +162,9 @@ _device_add(struct nfs4_pnfs_dev_hlist *hlist,
{
unsigned long hash;
- dprintk("_device_add: dev_id=%s\nmultipath_list:\n",
+ dprintk("_device_add: dev_id=%s ds_list:\n",
deviceid_fmt(&dsaddr->dev_id));
- print_multipath_list(dsaddr);
+ print_ds_list(dsaddr);
hash = _deviceid_hash(&dsaddr->dev_id);
hlist_add_head(&dsaddr->hash_node, &hlist->dev_list[hash]);
@@ -306,34 +294,29 @@ static void
nfs4_pnfs_device_destroy(struct nfs4_file_layout_dsaddr *dsaddr,
struct nfs4_pnfs_dev_hlist *hlist)
{
- struct nfs4_multipath *multipath;
struct nfs4_pnfs_ds *ds;
HLIST_HEAD(release);
- int i, j;
+ int i;
if (!dsaddr)
return;
dprintk("%s: dev_id=%s\ndev_list:\n", __func__,
deviceid_fmt(&dsaddr->dev_id));
- print_multipath_list(dsaddr);
+ print_ds_list(dsaddr);
write_lock(&hlist->dev_lock);
hlist_del_init(&dsaddr->hash_node);
- multipath = &dsaddr->multipath_list[0];
- for (i = 0; i < dsaddr->multipath_count; i++) {
- for (j = 0; j < multipath->num_ds; j++) {
- ds = multipath->ds_list[j];
- if (ds != NULL) {
- /* if we are last user - move to release list */
- if (atomic_dec_and_test(&ds->ds_count)) {
- hlist_del_init(&ds->ds_node);
- hlist_add_head(&ds->ds_node, &release);
- }
+ for (i = 0; i < dsaddr->ds_num; i++) {
+ ds = dsaddr->ds_list[i];
+ if (ds != NULL) {
+ /* if we are last user - move to release list */
+ if (atomic_dec_and_test(&ds->ds_count)) {
+ hlist_del_init(&ds->ds_node);
+ hlist_add_head(&ds->ds_node, &release);
}
}
- multipath++;
}
write_unlock(&hlist->dev_lock);
while (!hlist_empty(&release)) {
@@ -341,8 +324,6 @@ nfs4_pnfs_device_destroy(struct nfs4_file_layout_dsaddr *dsaddr,
hlist_del(&ds->ds_node);
destroy_ds(ds);
}
- kfree(dsaddr->multipath_list);
- kfree(dsaddr->stripe_indices);
kfree(dsaddr);
}
@@ -540,47 +521,44 @@ static struct nfs4_file_layout_dsaddr*
decode_device(struct filelayout_mount_type *mt, struct pnfs_device *pdev)
{
int i, dummy;
+ u32 cnt, num;
u8 *indexp;
uint32_t *p = (u32 *)pdev->area, *indicesp;
struct nfs4_file_layout_dsaddr *dsaddr;
- struct nfs4_multipath *multipath;
-
- dsaddr = kzalloc(sizeof(*dsaddr), GFP_KERNEL);
- if (!dsaddr)
- goto out_err;
/* Get the stripe count (number of stripe index) */
- READ32(dsaddr->stripe_count);
- dprintk("%s stripe count %d\n", __func__, dsaddr->stripe_count);
- if (dsaddr->stripe_count > NFS4_PNFS_MAX_STRIPE_CNT) {
+ READ32(cnt);
+ dprintk("%s stripe count %d\n", __func__, cnt);
+ if (cnt > NFS4_PNFS_MAX_STRIPE_CNT) {
printk(KERN_WARNING "%s: stripe count %d greater than "
"supported maximum %d\n", __func__,
- dsaddr->stripe_count, NFS4_PNFS_MAX_STRIPE_CNT);
- dsaddr->stripe_count = 0;
- goto out_err_free;
+ cnt, NFS4_PNFS_MAX_STRIPE_CNT);
+ goto out_err;
}
/* Check the multipath list count */
indicesp = p;
- p += XDR_QUADLEN(dsaddr->stripe_count << 2);
- READ32(dsaddr->multipath_count);
- dprintk("%s multipath_count %u\n", __func__, dsaddr->multipath_count);
- if (dsaddr->multipath_count > NFS4_PNFS_MAX_MULTI_CNT) {
+ p += XDR_QUADLEN(cnt << 2);
+ READ32(num);
+ dprintk("%s ds_num %u\n", __func__, num);
+ if (num > NFS4_PNFS_MAX_MULTI_CNT) {
printk(KERN_WARNING "%s: multipath count %d greater than "
"supported maximum %d\n", __func__,
- dsaddr->multipath_count, NFS4_PNFS_MAX_MULTI_CNT);
- dsaddr->multipath_count = 0;
- goto out_err_free;
+ num, NFS4_PNFS_MAX_MULTI_CNT);
+ goto out_err;
}
- dsaddr->stripe_indices = kzalloc(sizeof(u8) * dsaddr->stripe_count,
- GFP_KERNEL);
+ dsaddr = kzalloc(sizeof(*dsaddr) +
+ (sizeof(struct nfs4_pnfs_ds *) * (num - 1)),
+ GFP_KERNEL);
+ if (!dsaddr)
+ goto out_err;
+
+ dsaddr->stripe_indices = kzalloc(sizeof(u8) * cnt, GFP_KERNEL);
if (!dsaddr->stripe_indices)
goto out_err_free;
- dsaddr->multipath_list = kzalloc(sizeof(struct nfs4_multipath) *
- dsaddr->multipath_count, GFP_KERNEL);
- if (!dsaddr->multipath_list)
- goto out_err_free;
+ dsaddr->stripe_count = cnt;
+ dsaddr->ds_num = num;
memcpy(&dsaddr->dev_id, &pdev->dev_id, NFS4_PNFS_DEVICEID4_SIZE);
@@ -595,19 +573,22 @@ decode_device(struct filelayout_mount_type *mt, struct pnfs_device *pdev)
/* Skip already read multipath list count */
p++;
- multipath = &dsaddr->multipath_list[0];
- for (i = 0; i < dsaddr->multipath_count; i++) {
+ for (i = 0; i < dsaddr->ds_num; i++) {
int j;
- READ32(multipath->num_ds);
- if (multipath->num_ds > NFS4_PNFS_MAX_MULTI_DS) {
+ READ32(dummy); /* multipath count */
+ if (dummy > 1) {
printk(KERN_WARNING
"%s: Multipath count %d not supported, "
- "skipping all greater than %d\n", __func__,
- multipath->num_ds, NFS4_PNFS_MAX_MULTI_DS);
+ "skipping all greater than 1\n", __func__,
+ dummy);
}
- for (j = 0; j < multipath->num_ds; j++) {
- if (j >= NFS4_PNFS_MAX_MULTI_DS) {
+ for (j = 0; j < dummy; j++) {
+ if (j == 0) {
+ dsaddr->ds_list[i] = decode_and_add_ds(&p, mt);
+ if (dsaddr->ds_list[i] == NULL)
+ goto out_err_free;
+ } else {
u32 len;
/* skip extra multipath */
READ32(len);
@@ -616,11 +597,7 @@ decode_device(struct filelayout_mount_type *mt, struct pnfs_device *pdev)
p += XDR_QUADLEN(len);
continue;
}
- multipath->ds_list[j] = decode_and_add_ds(&p, mt);
- if (multipath->ds_list[j] == NULL)
- goto out_err_free;
}
- multipath++;
}
return dsaddr;
@@ -771,7 +748,7 @@ nfs4_pnfs_dserver_get(struct pnfs_layout_segment *lseg,
struct inode *inode = PNFS_INODE(lseg->layout);
struct nfs4_file_layout_dsaddr *dsaddr;
u64 tmp, tmp2;
- u32 stripe_idx, end_idx, multipath_idx;
+ u32 stripe_idx, end_idx, ds_idx;
if (!layout)
return 1;
@@ -798,10 +775,10 @@ nfs4_pnfs_dserver_get(struct pnfs_layout_segment *lseg,
BUG_ON(end_idx != stripe_idx);
BUG_ON(stripe_idx >= dsaddr->stripe_count);
- multipath_idx = dsaddr->stripe_indices[stripe_idx];
- dserver->multipath = &dsaddr->multipath_list[multipath_idx];
+ ds_idx = dsaddr->stripe_indices[stripe_idx];
+ dserver->ds = dsaddr->ds_list[ds_idx];
- if (dserver->multipath == NULL) {
+ if (dserver->ds == NULL) {
printk(KERN_ERR "%s: No data server for device id (%s)!! \n",
__func__, deviceid_fmt(&layout->dev_id));
return 1;
@@ -809,13 +786,13 @@ nfs4_pnfs_dserver_get(struct pnfs_layout_segment *lseg,
if (layout->num_fh == 1)
dserver->fh = &layout->fh_array[0];
else
- dserver->fh = &layout->fh_array[multipath_idx];
+ dserver->fh = &layout->fh_array[ds_idx];
- dprintk("%s: dev_id=%s, ip:port=%s, multipath_idx=%u stripe_idx=%u, "
+ dprintk("%s: dev_id=%s, ip:port=%s, ds_idx=%u stripe_idx=%u, "
"offset=%llu, count=%Zu\n",
__func__, deviceid_fmt(&layout->dev_id),
- dserver->multipath->ds_list[0]->r_addr,
- multipath_idx, stripe_idx, offset, count);
+ dserver->ds->r_addr,
+ ds_idx, stripe_idx, offset, count);
return 0;
}
--
1.6.6
next prev parent reply other threads:[~2010-04-08 19:54 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-04-08 19:53 [PATCH 0/14] pnfs_submit file layout client device management andros
2010-04-08 19:53 ` [PATCH 01/14] SQUASHME: pnfs_submit: remove unused getdevicelist functions andros
2010-04-08 19:53 ` [PATCH 02/14] SQUASHME pnfs-submit: call get_device_info from filelayout_check andros
2010-04-08 19:53 ` andros [this message]
2010-04-08 19:54 ` [PATCH 04/14] SQUASHME pnfs_submit: wait for I/O for data server connect andros
2010-04-08 19:54 ` [PATCH 05/14] SQUASHME pnfs_submit: remove xdr macros andros
2010-04-08 19:54 ` [PATCH 06/14] SQUASHME pnfs_submit: remove unused nfs4_pnfs_device_put andros
2010-04-08 19:54 ` [PATCH 07/14] SQUASHME pnfs_submit: change get_device_info parameter andros
2010-04-08 19:54 ` [PATCH 08/14] SQUASHME pnfs_submit: change decode_and_add_device parameter andros
2010-04-08 19:54 ` [PATCH 09/14] SQUASHME pnfs_submit: change decode_device parameter andros
2010-04-08 19:54 ` [PATCH 10/14] SQUASHME pnfs_submit: change decode_and_add_ds parameter andros
2010-04-08 19:54 ` [PATCH 11/14] SQUASHME pnfs_submit: change nfs4_pnfs_ds_add parameter andros
2010-04-08 19:54 ` [PATCH 12/14] SQUASHME pnfs_submit: remove filelayout CB_NOTIFY_DEVICE support andros
2010-04-08 19:54 ` [PATCH 13/14] SQUASHME pnfs_submit: stand alone data server cache andros
2010-04-08 19:54 ` [PATCH 14/14] SQUASHME pnfs_submit: remove kfree from under spinlock andros
2010-04-12 13:24 ` [pnfs] [PATCH 12/14] SQUASHME pnfs_submit: remove filelayout CB_NOTIFY_DEVICE support Benny Halevy
2010-04-12 13:17 ` [pnfs] [PATCH 07/14] SQUASHME pnfs_submit: change get_device_info parameter Benny Halevy
2010-04-12 13:13 ` [pnfs] [PATCH 02/14] SQUASHME pnfs-submit: call get_device_info from filelayout_check Benny Halevy
2010-04-12 12:12 ` [pnfs] [PATCH 0/14] pnfs_submit file layout client device management J. Bruce Fields
2010-04-12 19:03 ` Benny Halevy
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1270756450-5570-4-git-send-email-andros@netapp.com \
--to=andros@netapp.com \
--cc=linux-nfs@vger.kernel.org \
--cc=pnfs@linux-nfs.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox