Roger Pau Monne
2013-Feb-28 10:28 UTC
[PATCH RFC 10/12] xen-blkback: make the queue of free requests per backend
Remove the last dependency from blkbk by moving the list of free
requests to blkif. This change reduces the contention on the list of
available requests.
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: xen-devel@lists.xen.org
---
drivers/block/xen-blkback/blkback.c | 123 +++++++----------------------------
drivers/block/xen-blkback/common.h | 27 ++++++++
drivers/block/xen-blkback/xenbus.c | 17 +++++
3 files changed, 67 insertions(+), 100 deletions(-)
diff --git a/drivers/block/xen-blkback/blkback.c
b/drivers/block/xen-blkback/blkback.c
index c43de8a..04ad2aa 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -50,18 +50,14 @@
#include "common.h"
/*
- * These are rather arbitrary. They are fairly large because adjacent requests
- * pulled from a communication ring are quite likely to end up being part of
- * the same scatter/gather request at the disc.
- *
- * ** TRY INCREASING 'xen_blkif_reqs' IF WRITE SPEEDS SEEM TOO LOW **
- *
- * This will increase the chances of being able to write whole tracks.
- * 64 should be enough to keep us competitive with Linux.
+ * This is the number of requests that will be pre-allocated for each backend.
+ * For better performance this is set to RING_SIZE (32), so requests
+ * in the ring will never have to wait for a free pending_req.
*/
-static int xen_blkif_reqs = 64;
+
+int xen_blkif_reqs = 32;
module_param_named(reqs, xen_blkif_reqs, int, 0);
-MODULE_PARM_DESC(reqs, "Number of blkback requests to allocate");
+MODULE_PARM_DESC(reqs, "Number of blkback requests to allocate per
backend");
/*
* Maximum number of grants to map persistently in blkback. For maximum
@@ -120,50 +116,8 @@ MODULE_PARM_DESC(max_buffer_pages,
static unsigned int log_stats;
module_param(log_stats, int, 0644);
-/*
- * Each outstanding request that we've passed to the lower device layers
has a
- * 'pending_req' allocated to it. Each buffer_head that completes
decrements
- * the pendcnt towards zero. When it hits zero, the specified domain has a
- * response queued for it, with the saved 'id' passed back.
- */
-struct pending_req {
- struct xen_blkif *blkif;
- u64 id;
- int nr_pages;
- atomic_t pendcnt;
- unsigned short operation;
- int status;
- struct list_head free_list;
- struct persistent_gnt *persistent_gnts[BLKIF_MAX_SEGMENTS_PER_REQUEST];
- struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
- grant_handle_t grant_handles[BLKIF_MAX_SEGMENTS_PER_REQUEST];
-};
-
#define BLKBACK_INVALID_HANDLE (~0)
-struct xen_blkbk {
- struct pending_req *pending_reqs;
- /* List of all 'pending_req' available */
- struct list_head pending_free;
- /* And its spinlock. */
- spinlock_t pending_free_lock;
- wait_queue_head_t pending_free_wq;
-};
-
-static struct xen_blkbk *blkbk;
-
-/*
- * Little helpful macro to figure out the index and virtual address of the
- * pending_pages[..]. For each 'pending_req' we have have up to
- * BLKIF_MAX_SEGMENTS_PER_REQUEST (11) pages. The seg would be from 0 through
- * 10 and would index in the pending_pages[..].
- */
-static inline int vaddr_pagenr(struct pending_req *req, int seg)
-{
- return (req - blkbk->pending_reqs) *
- BLKIF_MAX_SEGMENTS_PER_REQUEST + seg;
-}
-
static inline int get_free_page(struct xen_blkif *blkif, struct page **page)
{
unsigned long flags;
@@ -400,18 +354,18 @@ finished:
/*
* Retrieve from the 'pending_reqs' a free pending_req structure to be
used.
*/
-static struct pending_req *alloc_req(void)
+static struct pending_req *alloc_req(struct xen_blkif *blkif)
{
struct pending_req *req = NULL;
unsigned long flags;
- spin_lock_irqsave(&blkbk->pending_free_lock, flags);
- if (!list_empty(&blkbk->pending_free)) {
- req = list_entry(blkbk->pending_free.next, struct pending_req,
+ spin_lock_irqsave(&blkif->pending_free_lock, flags);
+ if (!list_empty(&blkif->pending_free)) {
+ req = list_entry(blkif->pending_free.next, struct pending_req,
free_list);
list_del(&req->free_list);
}
- spin_unlock_irqrestore(&blkbk->pending_free_lock, flags);
+ spin_unlock_irqrestore(&blkif->pending_free_lock, flags);
return req;
}
@@ -419,17 +373,17 @@ static struct pending_req *alloc_req(void)
* Return the 'pending_req' structure back to the freepool. We also
* wake up the thread if it was waiting for a free page.
*/
-static void free_req(struct pending_req *req)
+static void free_req(struct xen_blkif *blkif, struct pending_req *req)
{
unsigned long flags;
int was_empty;
- spin_lock_irqsave(&blkbk->pending_free_lock, flags);
- was_empty = list_empty(&blkbk->pending_free);
- list_add(&req->free_list, &blkbk->pending_free);
- spin_unlock_irqrestore(&blkbk->pending_free_lock, flags);
+ spin_lock_irqsave(&blkif->pending_free_lock, flags);
+ was_empty = list_empty(&blkif->pending_free);
+ list_add(&req->free_list, &blkif->pending_free);
+ spin_unlock_irqrestore(&blkif->pending_free_lock, flags);
if (was_empty)
- wake_up(&blkbk->pending_free_wq);
+ wake_up(&blkif->pending_free_wq);
}
/*
@@ -564,8 +518,8 @@ int xen_blkif_schedule(void *arg)
if (timeout == 0)
goto purge_gnt_list;
timeout = wait_event_interruptible_timeout(
- blkbk->pending_free_wq,
- !list_empty(&blkbk->pending_free) ||
+ blkif->pending_free_wq,
+ !list_empty(&blkif->pending_free) ||
kthread_should_stop(),
timeout);
if (timeout == 0)
@@ -886,7 +840,7 @@ static void __end_block_io_op(struct pending_req
*pending_req, int error)
if (atomic_read(&pending_req->blkif->drain))
complete(&pending_req->blkif->drain_complete);
}
- free_req(pending_req);
+ free_req(pending_req->blkif, pending_req);
}
}
@@ -929,7 +883,7 @@ __do_block_io_op(struct xen_blkif *blkif)
break;
}
- pending_req = alloc_req();
+ pending_req = alloc_req(blkif);
if (NULL == pending_req) {
blkif->st_oo_req++;
more_to_do = 1;
@@ -954,7 +908,7 @@ __do_block_io_op(struct xen_blkif *blkif)
/* Apply all sanity checks to /private copy/ of request. */
barrier();
if (unlikely(req.operation == BLKIF_OP_DISCARD)) {
- free_req(pending_req);
+ free_req(blkif, pending_req);
if (dispatch_discard_io(blkif, &req))
break;
} else if (dispatch_rw_block_io(blkif, &req, pending_req))
@@ -1157,7 +1111,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
fail_response:
/* Haven't submitted any bio's yet. */
make_response(blkif, req->u.rw.id, req->operation, BLKIF_RSP_ERROR);
- free_req(pending_req);
+ free_req(blkif, pending_req);
msleep(1); /* back off a bit */
return -EIO;
@@ -1213,51 +1167,20 @@ static void make_response(struct xen_blkif *blkif, u64
id,
static int __init xen_blkif_init(void)
{
- int i;
int rc = 0;
if (!xen_domain())
return -ENODEV;
- blkbk = kzalloc(sizeof(struct xen_blkbk), GFP_KERNEL);
- if (!blkbk) {
- pr_alert(DRV_PFX "%s: out of memory!\n", __func__);
- return -ENOMEM;
- }
-
-
- blkbk->pending_reqs = kzalloc(sizeof(blkbk->pending_reqs[0]) *
- xen_blkif_reqs, GFP_KERNEL);
-
- if (!blkbk->pending_reqs) {
- rc = -ENOMEM;
- goto out_of_memory;
- }
-
rc = xen_blkif_interface_init();
if (rc)
goto failed_init;
- INIT_LIST_HEAD(&blkbk->pending_free);
- spin_lock_init(&blkbk->pending_free_lock);
- init_waitqueue_head(&blkbk->pending_free_wq);
-
- for (i = 0; i < xen_blkif_reqs; i++)
- list_add_tail(&blkbk->pending_reqs[i].free_list,
- &blkbk->pending_free);
-
rc = xen_blkif_xenbus_init();
if (rc)
goto failed_init;
- return 0;
-
- out_of_memory:
- pr_alert(DRV_PFX "%s: out of memory\n", __func__);
failed_init:
- kfree(blkbk->pending_reqs);
- kfree(blkbk);
- blkbk = NULL;
return rc;
}
diff --git a/drivers/block/xen-blkback/common.h
b/drivers/block/xen-blkback/common.h
index 604bd30..0b0ad3f 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -214,6 +214,14 @@ struct xen_blkif {
int free_pages_num;
struct list_head free_pages;
+ /* Allocation of pending_reqs */
+ struct pending_req *pending_reqs;
+ /* List of all 'pending_req' available */
+ struct list_head pending_free;
+ /* And its spinlock. */
+ spinlock_t pending_free_lock;
+ wait_queue_head_t pending_free_wq;
+
/* statistics */
unsigned long st_print;
int st_rd_req;
@@ -227,6 +235,25 @@ struct xen_blkif {
wait_queue_head_t waiting_to_free;
};
+/*
+ * Each outstanding request that we've passed to the lower device layers
has a
+ * 'pending_req' allocated to it. Each buffer_head that completes
decrements
+ * the pendcnt towards zero. When it hits zero, the specified domain has a
+ * response queued for it, with the saved 'id' passed back.
+ */
+struct pending_req {
+ struct xen_blkif *blkif;
+ u64 id;
+ int nr_pages;
+ atomic_t pendcnt;
+ unsigned short operation;
+ int status;
+ struct list_head free_list;
+ struct persistent_gnt *persistent_gnts[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ grant_handle_t grant_handles[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+};
+
#define vbd_sz(_v) ((_v)->bdev->bd_part ? \
(_v)->bdev->bd_part->nr_sects : \
diff --git a/drivers/block/xen-blkback/xenbus.c
b/drivers/block/xen-blkback/xenbus.c
index d7926ec..8f929cb 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -30,6 +30,8 @@ struct backend_info {
char *mode;
};
+extern int xen_blkif_reqs;
+
static struct kmem_cache *xen_blkif_cachep;
static void connect(struct backend_info *);
static int connect_ring(struct backend_info *);
@@ -104,6 +106,7 @@ static void xen_update_blkif_status(struct xen_blkif *blkif)
static struct xen_blkif *xen_blkif_alloc(domid_t domid)
{
struct xen_blkif *blkif;
+ int i;
blkif = kmem_cache_zalloc(xen_blkif_cachep, GFP_KERNEL);
if (!blkif)
@@ -122,6 +125,19 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid)
spin_lock_init(&blkif->free_pages_lock);
INIT_LIST_HEAD(&blkif->free_pages);
blkif->free_pages_num = 0;
+ blkif->pending_reqs = kzalloc(sizeof(blkif->pending_reqs[0]) *
+ xen_blkif_reqs, GFP_KERNEL);
+ if (!blkif->pending_reqs) {
+ kmem_cache_free(xen_blkif_cachep, blkif);
+ return ERR_PTR(-ENOMEM);
+ }
+ INIT_LIST_HEAD(&blkif->pending_free);
+ spin_lock_init(&blkif->pending_free_lock);
+ init_waitqueue_head(&blkif->pending_free_wq);
+
+ for (i = 0; i < xen_blkif_reqs; i++)
+ list_add_tail(&blkif->pending_reqs[i].free_list,
+ &blkif->pending_free);
return blkif;
}
@@ -204,6 +220,7 @@ static void xen_blkif_free(struct xen_blkif *blkif)
{
if (!atomic_dec_and_test(&blkif->refcnt))
BUG();
+ kfree(blkif->pending_reqs);
kmem_cache_free(xen_blkif_cachep, blkif);
}
--
1.7.7.5 (Apple Git-26)
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel
Jan Beulich
2013-Feb-28 11:08 UTC
Re: [PATCH RFC 10/12] xen-blkback: make the queue of free requests per backend
>>> On 28.02.13 at 11:28, Roger Pau Monne <roger.pau@citrix.com> wrote: > @@ -122,6 +125,19 @@ static struct xen_blkif *xen_blkif_alloc(domid_t domid) > spin_lock_init(&blkif->free_pages_lock); > INIT_LIST_HEAD(&blkif->free_pages); > blkif->free_pages_num = 0; > + blkif->pending_reqs = kzalloc(sizeof(blkif->pending_reqs[0]) * > + xen_blkif_reqs, GFP_KERNEL);kcalloc() is preferred in cases like this, I believe. Jan