Peter-Jan Gootzen
2023-Jul-03 19:14 UTC
[PATCH V4] virtio-fs: Improved request latencies when Virtio queue is full
When the Virtio queue is full, a work item is scheduled
to execute in 1ms that retries adding the request to the queue.
This is a large amount of time on the scale on which a
virtio-fs device can operate. When using a DPU this is around
40us baseline without going to a remote server (4k, QD=1).
This patch queues requests when the Virtio queue is full,
and when a completed request is taken off, immediately fills
it back up with queued requests.
This reduces the 99.9th percentile latencies in our tests by
60x and slightly increases the overall throughput, when using a
queue depth 2x the size of the Virtio queue size, with a
DPU-powered virtio-fs device.
Signed-off-by: Peter-Jan Gootzen <peter-jan at gootzen.net>
---
V4: Removed return value on error changes to simplify patch,
that should be changed in another patch.
V3: Fixed requests falling into the void when -ENOMEM and no new
incoming requests. Virtio-fs now always lets -ENOMEM bubble up to
userspace. Also made queue full condition more explicit with
-ENOSPC in `send_forget_request`.
V2: Not scheduling dispatch work anymore when not needed
and changed delayed_work structs to work_struct structs
fs/fuse/virtio_fs.c | 32 +++++++++++++++++---------------
1 file changed, 17 insertions(+), 15 deletions(-)
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 4d8d4f16c727..a676297db09b 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -45,7 +45,7 @@ struct virtio_fs_vq {
struct work_struct done_work;
struct list_head queued_reqs;
struct list_head end_reqs; /* End these requests */
- struct delayed_work dispatch_work;
+ struct work_struct dispatch_work;
struct fuse_dev *fud;
bool connected;
long in_flight;
@@ -202,7 +202,7 @@ static void virtio_fs_drain_queue(struct virtio_fs_vq *fsvq)
}
flush_work(&fsvq->done_work);
- flush_delayed_work(&fsvq->dispatch_work);
+ flush_work(&fsvq->dispatch_work);
}
static void virtio_fs_drain_all_queues_locked(struct virtio_fs *fs)
@@ -346,6 +346,9 @@ static void virtio_fs_hiprio_done_work(struct work_struct
*work)
dec_in_flight_req(fsvq);
}
} while (!virtqueue_enable_cb(vq) &&
likely(!virtqueue_is_broken(vq)));
+
+ if (!list_empty(&fsvq->queued_reqs))
+ schedule_work(&fsvq->dispatch_work);
spin_unlock(&fsvq->lock);
}
@@ -353,7 +356,7 @@ static void virtio_fs_request_dispatch_work(struct
work_struct *work)
{
struct fuse_req *req;
struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq,
- dispatch_work.work);
+ dispatch_work);
int ret;
pr_debug("virtio-fs: worker %s called.\n", __func__);
@@ -388,8 +391,6 @@ static void virtio_fs_request_dispatch_work(struct
work_struct *work)
if (ret == -ENOMEM || ret == -ENOSPC) {
spin_lock(&fsvq->lock);
list_add_tail(&req->list, &fsvq->queued_reqs);
- schedule_delayed_work(&fsvq->dispatch_work,
- msecs_to_jiffies(1));
spin_unlock(&fsvq->lock);
return;
}
@@ -436,8 +437,6 @@ static int send_forget_request(struct virtio_fs_vq *fsvq,
pr_debug("virtio-fs: Could not queue FORGET: err=%d. Will try
later\n",
ret);
list_add_tail(&forget->list, &fsvq->queued_reqs);
- schedule_delayed_work(&fsvq->dispatch_work,
- msecs_to_jiffies(1));
if (!in_flight)
inc_in_flight_req(fsvq);
/* Queue is full */
@@ -469,7 +468,7 @@ static void virtio_fs_hiprio_dispatch_work(struct
work_struct *work)
{
struct virtio_fs_forget *forget;
struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq,
- dispatch_work.work);
+ dispatch_work);
pr_debug("virtio-fs: worker %s called.\n", __func__);
while (1) {
spin_lock(&fsvq->lock);
@@ -647,6 +646,11 @@ static void virtio_fs_requests_done_work(struct work_struct
*work)
virtio_fs_request_complete(req, fsvq);
}
}
+
+ spin_lock(&fsvq->lock);
+ if (!list_empty(&fsvq->queued_reqs))
+ schedule_work(&fsvq->dispatch_work);
+ spin_unlock(&fsvq->lock);
}
/* Virtqueue interrupt handler */
@@ -670,12 +674,12 @@ static void virtio_fs_init_vq(struct virtio_fs_vq *fsvq,
char *name,
if (vq_type == VQ_REQUEST) {
INIT_WORK(&fsvq->done_work, virtio_fs_requests_done_work);
- INIT_DELAYED_WORK(&fsvq->dispatch_work,
- virtio_fs_request_dispatch_work);
+ INIT_WORK(&fsvq->dispatch_work,
+ virtio_fs_request_dispatch_work);
} else {
INIT_WORK(&fsvq->done_work, virtio_fs_hiprio_done_work);
- INIT_DELAYED_WORK(&fsvq->dispatch_work,
- virtio_fs_hiprio_dispatch_work);
+ INIT_WORK(&fsvq->dispatch_work,
+ virtio_fs_hiprio_dispatch_work);
}
}
@@ -1254,8 +1258,6 @@ __releases(fiq->lock)
spin_lock(&fsvq->lock);
list_add_tail(&req->list, &fsvq->queued_reqs);
inc_in_flight_req(fsvq);
- schedule_delayed_work(&fsvq->dispatch_work,
- msecs_to_jiffies(1));
spin_unlock(&fsvq->lock);
return;
}
@@ -1265,7 +1267,7 @@ __releases(fiq->lock)
/* Can't end request in submission context. Use a worker */
spin_lock(&fsvq->lock);
list_add_tail(&req->list, &fsvq->end_reqs);
- schedule_delayed_work(&fsvq->dispatch_work, 0);
+ schedule_work(&fsvq->dispatch_work);
spin_unlock(&fsvq->lock);
return;
}
--
2.34.1
Stefan Hajnoczi
2023-Aug-16 12:30 UTC
[PATCH V4] virtio-fs: Improved request latencies when Virtio queue is full
On Mon, Jul 03, 2023 at 09:14:59PM +0200, Peter-Jan Gootzen wrote:> When the Virtio queue is full, a work item is scheduled > to execute in 1ms that retries adding the request to the queue. > This is a large amount of time on the scale on which a > virtio-fs device can operate. When using a DPU this is around > 40us baseline without going to a remote server (4k, QD=1). > This patch queues requests when the Virtio queue is full, > and when a completed request is taken off, immediately fills > it back up with queued requests. > > This reduces the 99.9th percentile latencies in our tests by > 60x and slightly increases the overall throughput, when using a > queue depth 2x the size of the Virtio queue size, with a > DPU-powered virtio-fs device. > > Signed-off-by: Peter-Jan Gootzen <peter-jan at gootzen.net> > --- > V4: Removed return value on error changes to simplify patch, > that should be changed in another patch. > V3: Fixed requests falling into the void when -ENOMEM and no new > incoming requests. Virtio-fs now always lets -ENOMEM bubble up to > userspace. Also made queue full condition more explicit with > -ENOSPC in `send_forget_request`. > V2: Not scheduling dispatch work anymore when not needed > and changed delayed_work structs to work_struct structs > > fs/fuse/virtio_fs.c | 32 +++++++++++++++++--------------- > 1 file changed, 17 insertions(+), 15 deletions(-)Reviewed-by: Stefan Hajnoczi <stefanha at redhat.com> -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 488 bytes Desc: not available URL: <http://lists.linuxfoundation.org/pipermail/virtualization/attachments/20230816/41dd2b56/attachment.sig>
Vivek Goyal
2023-Aug-16 21:10 UTC
[PATCH V4] virtio-fs: Improved request latencies when Virtio queue is full
On Mon, Jul 03, 2023 at 09:14:59PM +0200, Peter-Jan Gootzen wrote:> When the Virtio queue is full, a work item is scheduled > to execute in 1ms that retries adding the request to the queue. > This is a large amount of time on the scale on which a > virtio-fs device can operate. When using a DPU this is around > 40us baseline without going to a remote server (4k, QD=1). > This patch queues requests when the Virtio queue is full, > and when a completed request is taken off, immediately fills > it back up with queued requests. > > This reduces the 99.9th percentile latencies in our tests by > 60x and slightly increases the overall throughput, when using a > queue depth 2x the size of the Virtio queue size, with a > DPU-powered virtio-fs device. > > Signed-off-by: Peter-Jan Gootzen <peter-jan at gootzen.net> > --- > V4: Removed return value on error changes to simplify patch, > that should be changed in another patch. > V3: Fixed requests falling into the void when -ENOMEM and no new > incoming requests. Virtio-fs now always lets -ENOMEM bubble up to > userspace. Also made queue full condition more explicit with > -ENOSPC in `send_forget_request`. > V2: Not scheduling dispatch work anymore when not needed > and changed delayed_work structs to work_struct structs > > fs/fuse/virtio_fs.c | 32 +++++++++++++++++--------------- > 1 file changed, 17 insertions(+), 15 deletions(-) > > diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c > index 4d8d4f16c727..a676297db09b 100644 > --- a/fs/fuse/virtio_fs.c > +++ b/fs/fuse/virtio_fs.c > @@ -45,7 +45,7 @@ struct virtio_fs_vq { > struct work_struct done_work; > struct list_head queued_reqs; > struct list_head end_reqs; /* End these requests */ > - struct delayed_work dispatch_work; > + struct work_struct dispatch_work; > struct fuse_dev *fud; > bool connected; > long in_flight; > @@ -202,7 +202,7 @@ static void virtio_fs_drain_queue(struct virtio_fs_vq *fsvq) > } > > flush_work(&fsvq->done_work); > - flush_delayed_work(&fsvq->dispatch_work); > + flush_work(&fsvq->dispatch_work); > } > > static void virtio_fs_drain_all_queues_locked(struct virtio_fs *fs) > @@ -346,6 +346,9 @@ static void virtio_fs_hiprio_done_work(struct work_struct *work) > dec_in_flight_req(fsvq); > } > } while (!virtqueue_enable_cb(vq) && likely(!virtqueue_is_broken(vq))); > + > + if (!list_empty(&fsvq->queued_reqs)) > + schedule_work(&fsvq->dispatch_work); > spin_unlock(&fsvq->lock); > } > > @@ -353,7 +356,7 @@ static void virtio_fs_request_dispatch_work(struct work_struct *work) > { > struct fuse_req *req; > struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, > - dispatch_work.work); > + dispatch_work); > int ret; > > pr_debug("virtio-fs: worker %s called.\n", __func__); > @@ -388,8 +391,6 @@ static void virtio_fs_request_dispatch_work(struct work_struct *work) > if (ret == -ENOMEM || ret == -ENOSPC) { > spin_lock(&fsvq->lock); > list_add_tail(&req->list, &fsvq->queued_reqs); > - schedule_delayed_work(&fsvq->dispatch_work, > - msecs_to_jiffies(1)); > spin_unlock(&fsvq->lock);If we are running low on memroy and very first request gets queued, then we had deadlock as there is no completion happening after that. I think I pointed this out in V2 as well. I think first you need to write a patch to return -ENOMEM to user space and then second patch queues the request only on -ENOSPC. Thanks Vivek> return; > } > @@ -436,8 +437,6 @@ static int send_forget_request(struct virtio_fs_vq *fsvq, > pr_debug("virtio-fs: Could not queue FORGET: err=%d. Will try later\n", > ret); > list_add_tail(&forget->list, &fsvq->queued_reqs); > - schedule_delayed_work(&fsvq->dispatch_work, > - msecs_to_jiffies(1)); > if (!in_flight) > inc_in_flight_req(fsvq); > /* Queue is full */ > @@ -469,7 +468,7 @@ static void virtio_fs_hiprio_dispatch_work(struct work_struct *work) > { > struct virtio_fs_forget *forget; > struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, > - dispatch_work.work); > + dispatch_work); > pr_debug("virtio-fs: worker %s called.\n", __func__); > while (1) { > spin_lock(&fsvq->lock); > @@ -647,6 +646,11 @@ static void virtio_fs_requests_done_work(struct work_struct *work) > virtio_fs_request_complete(req, fsvq); > } > } > + > + spin_lock(&fsvq->lock); > + if (!list_empty(&fsvq->queued_reqs)) > + schedule_work(&fsvq->dispatch_work); > + spin_unlock(&fsvq->lock); > } > > /* Virtqueue interrupt handler */ > @@ -670,12 +674,12 @@ static void virtio_fs_init_vq(struct virtio_fs_vq *fsvq, char *name, > > if (vq_type == VQ_REQUEST) { > INIT_WORK(&fsvq->done_work, virtio_fs_requests_done_work); > - INIT_DELAYED_WORK(&fsvq->dispatch_work, > - virtio_fs_request_dispatch_work); > + INIT_WORK(&fsvq->dispatch_work, > + virtio_fs_request_dispatch_work); > } else { > INIT_WORK(&fsvq->done_work, virtio_fs_hiprio_done_work); > - INIT_DELAYED_WORK(&fsvq->dispatch_work, > - virtio_fs_hiprio_dispatch_work); > + INIT_WORK(&fsvq->dispatch_work, > + virtio_fs_hiprio_dispatch_work); > } > } > > @@ -1254,8 +1258,6 @@ __releases(fiq->lock) > spin_lock(&fsvq->lock); > list_add_tail(&req->list, &fsvq->queued_reqs); > inc_in_flight_req(fsvq); > - schedule_delayed_work(&fsvq->dispatch_work, > - msecs_to_jiffies(1)); > spin_unlock(&fsvq->lock); > return; > } > @@ -1265,7 +1267,7 @@ __releases(fiq->lock) > /* Can't end request in submission context. Use a worker */ > spin_lock(&fsvq->lock); > list_add_tail(&req->list, &fsvq->end_reqs); > - schedule_delayed_work(&fsvq->dispatch_work, 0); > + schedule_work(&fsvq->dispatch_work); > spin_unlock(&fsvq->lock); > return; > } > -- > 2.34.1 >