[v3,2/3] vhost: move dirty logging cache out of the virtqueue
Checks
Commit Message
This patch moves the per-virtqueue's dirty logging cache
out of the virtqueue struct, by allocating it dynamically
only when live-migration is enabled.
It saves 8 cachelines in vhost_virtqueue struct.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
lib/librte_vhost/vhost.c | 13 +++++++++++++
lib/librte_vhost/vhost.h | 2 +-
lib/librte_vhost/vhost_user.c | 21 +++++++++++++++++++++
3 files changed, 35 insertions(+), 1 deletion(-)
Comments
> -----Original Message-----
> From: Maxime Coquelin <maxime.coquelin@redhat.com>
> Sent: Thursday, March 18, 2021 1:09 AM
> To: dev@dpdk.org; Xia, Chenbo <chenbo.xia@intel.com>; amorenoz@redhat.com;
> david.marchand@redhat.com; olivier.matz@6wind.com; bnemeth@redhat.com
> Cc: Maxime Coquelin <maxime.coquelin@redhat.com>
> Subject: [PATCH v3 2/3] vhost: move dirty logging cache out of the virtqueue
>
> This patch moves the per-virtqueue's dirty logging cache
> out of the virtqueue struct, by allocating it dynamically
> only when live-migration is enabled.
>
> It saves 8 cachelines in vhost_virtqueue struct.
>
> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> ---
> lib/librte_vhost/vhost.c | 13 +++++++++++++
> lib/librte_vhost/vhost.h | 2 +-
> lib/librte_vhost/vhost_user.c | 21 +++++++++++++++++++++
> 3 files changed, 35 insertions(+), 1 deletion(-)
>
> diff --git a/lib/librte_vhost/vhost.c b/lib/librte_vhost/vhost.c
> index 5a7c0c6cff..a8032e3ba1 100644
> --- a/lib/librte_vhost/vhost.c
> +++ b/lib/librte_vhost/vhost.c
> @@ -145,6 +145,10 @@ __vhost_log_cache_sync(struct virtio_net *dev, struct
> vhost_virtqueue *vq)
> if (unlikely(!dev->log_base))
> return;
>
> + /* No cache, nothing to sync */
> + if (unlikely(!vq->log_cache))
> + return;
> +
> rte_atomic_thread_fence(__ATOMIC_RELEASE);
>
> log_base = (unsigned long *)(uintptr_t)dev->log_base;
> @@ -177,6 +181,14 @@ vhost_log_cache_page(struct virtio_net *dev, struct
> vhost_virtqueue *vq,
> uint32_t offset = page / (sizeof(unsigned long) << 3);
> int i;
>
> + if (unlikely(!vq->log_cache)) {
> + /* No logging cache allocated, write dirty log map directly */
> + rte_atomic_thread_fence(__ATOMIC_RELEASE);
> + vhost_log_page((uint8_t *)(uintptr_t)dev->log_base, page);
> +
> + return;
> + }
> +
> for (i = 0; i < vq->log_cache_nb_elem; i++) {
> struct log_cache_entry *elem = vq->log_cache + i;
>
> @@ -354,6 +366,7 @@ free_vq(struct virtio_net *dev, struct vhost_virtqueue *vq)
> }
> rte_free(vq->batch_copy_elems);
> rte_mempool_free(vq->iotlb_pool);
> + rte_free(vq->log_cache);
> rte_free(vq);
> }
>
> diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
> index 717f410548..3a71dfeed9 100644
> --- a/lib/librte_vhost/vhost.h
> +++ b/lib/librte_vhost/vhost.h
> @@ -183,7 +183,7 @@ struct vhost_virtqueue {
> bool used_wrap_counter;
> bool avail_wrap_counter;
>
> - struct log_cache_entry log_cache[VHOST_LOG_CACHE_NR];
> + struct log_cache_entry *log_cache;
> uint16_t log_cache_nb_elem;
>
> rte_rwlock_t iotlb_lock;
> diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
> index a60bb945ad..4d9e76e49e 100644
> --- a/lib/librte_vhost/vhost_user.c
> +++ b/lib/librte_vhost/vhost_user.c
> @@ -2022,6 +2022,9 @@ vhost_user_get_vring_base(struct virtio_net **pdev,
> rte_free(vq->batch_copy_elems);
> vq->batch_copy_elems = NULL;
>
> + rte_free(vq->log_cache);
> + vq->log_cache = NULL;
> +
> msg->size = sizeof(msg->payload.state);
> msg->fd_num = 0;
>
> @@ -2121,6 +2124,7 @@ vhost_user_set_log_base(struct virtio_net **pdev, struct
> VhostUserMsg *msg,
> int fd = msg->fds[0];
> uint64_t size, off;
> void *addr;
> + uint32_t i;
>
> if (validate_msg_fds(msg, 1) != 0)
> return RTE_VHOST_MSG_RESULT_ERR;
> @@ -2174,6 +2178,23 @@ vhost_user_set_log_base(struct virtio_net **pdev,
> struct VhostUserMsg *msg,
> dev->log_base = dev->log_addr + off;
> dev->log_size = size;
>
> + for (i = 0; i < dev->nr_vring; i++) {
> + struct vhost_virtqueue *vq = dev->virtqueue[i];
> +
> + rte_free(vq->log_cache);
> + vq->log_cache = NULL;
> + vq->log_cache_nb_elem = 0;
> + vq->log_cache = rte_zmalloc("vq log cache",
> + sizeof(struct log_cache_entry) * VHOST_LOG_CACHE_NR,
> + 0);
> + /*
> + * If log cache alloc fail, don't fail migration, but no
> + * caching will be done, which will impact performance
> + */
> + if (!vq->log_cache)
> + VHOST_LOG_CONFIG(ERR, "Failed to allocate VQ logging
> cache\n");
> + }
> +
> /*
> * The spec is not clear about it (yet), but QEMU doesn't expect
> * any payload in the reply.
> --
> 2.30.2
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
@@ -145,6 +145,10 @@ __vhost_log_cache_sync(struct virtio_net *dev, struct vhost_virtqueue *vq)
if (unlikely(!dev->log_base))
return;
+ /* No cache, nothing to sync */
+ if (unlikely(!vq->log_cache))
+ return;
+
rte_atomic_thread_fence(__ATOMIC_RELEASE);
log_base = (unsigned long *)(uintptr_t)dev->log_base;
@@ -177,6 +181,14 @@ vhost_log_cache_page(struct virtio_net *dev, struct vhost_virtqueue *vq,
uint32_t offset = page / (sizeof(unsigned long) << 3);
int i;
+ if (unlikely(!vq->log_cache)) {
+ /* No logging cache allocated, write dirty log map directly */
+ rte_atomic_thread_fence(__ATOMIC_RELEASE);
+ vhost_log_page((uint8_t *)(uintptr_t)dev->log_base, page);
+
+ return;
+ }
+
for (i = 0; i < vq->log_cache_nb_elem; i++) {
struct log_cache_entry *elem = vq->log_cache + i;
@@ -354,6 +366,7 @@ free_vq(struct virtio_net *dev, struct vhost_virtqueue *vq)
}
rte_free(vq->batch_copy_elems);
rte_mempool_free(vq->iotlb_pool);
+ rte_free(vq->log_cache);
rte_free(vq);
}
@@ -183,7 +183,7 @@ struct vhost_virtqueue {
bool used_wrap_counter;
bool avail_wrap_counter;
- struct log_cache_entry log_cache[VHOST_LOG_CACHE_NR];
+ struct log_cache_entry *log_cache;
uint16_t log_cache_nb_elem;
rte_rwlock_t iotlb_lock;
@@ -2022,6 +2022,9 @@ vhost_user_get_vring_base(struct virtio_net **pdev,
rte_free(vq->batch_copy_elems);
vq->batch_copy_elems = NULL;
+ rte_free(vq->log_cache);
+ vq->log_cache = NULL;
+
msg->size = sizeof(msg->payload.state);
msg->fd_num = 0;
@@ -2121,6 +2124,7 @@ vhost_user_set_log_base(struct virtio_net **pdev, struct VhostUserMsg *msg,
int fd = msg->fds[0];
uint64_t size, off;
void *addr;
+ uint32_t i;
if (validate_msg_fds(msg, 1) != 0)
return RTE_VHOST_MSG_RESULT_ERR;
@@ -2174,6 +2178,23 @@ vhost_user_set_log_base(struct virtio_net **pdev, struct VhostUserMsg *msg,
dev->log_base = dev->log_addr + off;
dev->log_size = size;
+ for (i = 0; i < dev->nr_vring; i++) {
+ struct vhost_virtqueue *vq = dev->virtqueue[i];
+
+ rte_free(vq->log_cache);
+ vq->log_cache = NULL;
+ vq->log_cache_nb_elem = 0;
+ vq->log_cache = rte_zmalloc("vq log cache",
+ sizeof(struct log_cache_entry) * VHOST_LOG_CACHE_NR,
+ 0);
+ /*
+ * If log cache alloc fail, don't fail migration, but no
+ * caching will be done, which will impact performance
+ */
+ if (!vq->log_cache)
+ VHOST_LOG_CONFIG(ERR, "Failed to allocate VQ logging cache\n");
+ }
+
/*
* The spec is not clear about it (yet), but QEMU doesn't expect
* any payload in the reply.