Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755212AbZKSPTe (ORCPT ); Thu, 19 Nov 2009 10:19:34 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753538AbZKSPTd (ORCPT ); Thu, 19 Nov 2009 10:19:33 -0500 Received: from e37.co.us.ibm.com ([32.97.110.158]:37188 "EHLO e37.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751598AbZKSPTc (ORCPT ); Thu, 19 Nov 2009 10:19:32 -0500 Subject: virtio: Add memory statistics reporting to the balloon driver (V3) From: Adam Litke To: Anthony Liguori , Rusty Russell Cc: qemu-devel@nongnu.org, Avi Kivity , virtualization@lists.linux-foundation.org, linux-kernel@vger.kernel.org In-Reply-To: <1258643169.3464.3.camel@aglitke> References: <1258643169.3464.3.camel@aglitke> Content-Type: text/plain; charset="UTF-8" Organization: IBM Date: Thu, 19 Nov 2009 09:19:05 -0600 Message-ID: <1258643945.3464.5.camel@aglitke> Mime-Version: 1.0 X-Mailer: Evolution 2.28.1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7324 Lines: 213 Rusty and Anthony, If I've addressed all outstanding issues, please consider this patch for inclusion. Thanks. Changes since V2: - Increase stat field size to 64 bits - Report all sizes in kb (not pages) - Drop anon_pages stat and fix endianness conversion Changes since V1: - Use a virtqueue instead of the device config space When using ballooning to manage overcommitted memory on a host, a system for guests to communicate their memory usage to the host can provide information that will minimize the impact of ballooning on the guests. The current method employs a daemon running in each guest that communicates memory statistics to a host daemon at a specified time interval. The host daemon aggregates this information and inflates and/or deflates balloons according to the level of host memory pressure. This approach is effective but overly complex since a daemon must be installed inside each guest and coordinated to communicate with the host. A simpler approach is to collect memory statistics in the virtio balloon driver and communicate them directly to the hypervisor. This patch enables the guest-side support by adding stats collection and reporting to the virtio balloon driver. Signed-off-by: Adam Litke Cc: Rusty Russell Cc: Anthony Liguori Cc: virtualization@lists.linux-foundation.org Cc: linux-kernel@vger.kernel.org diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 200c22f..ebc9d39 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -29,7 +29,7 @@ struct virtio_balloon { struct virtio_device *vdev; - struct virtqueue *inflate_vq, *deflate_vq; + struct virtqueue *inflate_vq, *deflate_vq, *stats_vq; /* Where the ballooning thread waits for config to change. */ wait_queue_head_t config_change; @@ -50,6 +50,9 @@ struct virtio_balloon /* The array of pfns we tell the Host about. */ unsigned int num_pfns; u32 pfns[256]; + + /* Memory statistics */ + struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR]; }; static struct virtio_device_id id_table[] = { @@ -155,6 +158,57 @@ static void leak_balloon(struct virtio_balloon *vb, size_t num) } } +static inline void update_stat(struct virtio_balloon *vb, int idx, + __le16 tag, __le64 val) +{ + BUG_ON(idx >= VIRTIO_BALLOON_S_NR); + vb->stats[idx].tag = cpu_to_le16(tag); + vb->stats[idx].val = cpu_to_le64(val); +} + +#define K(x) ((x) << (PAGE_SHIFT - 10)) +static void update_balloon_stats(struct virtio_balloon *vb) +{ + unsigned long events[NR_VM_EVENT_ITEMS]; + struct sysinfo i; + int idx = 0; + + all_vm_events(events); + si_meminfo(&i); + + update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_IN, K(events[PSWPIN])); + update_stat(vb, idx++, VIRTIO_BALLOON_S_SWAP_OUT, K(events[PSWPOUT])); + update_stat(vb, idx++, VIRTIO_BALLOON_S_MAJFLT, events[PGMAJFAULT]); + update_stat(vb, idx++, VIRTIO_BALLOON_S_MINFLT, events[PGFAULT]); + update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMFREE, K(i.freeram)); + update_stat(vb, idx++, VIRTIO_BALLOON_S_MEMTOT, K(i.totalram)); +} + +/* + * While most virtqueues communicate guest-initiated requests to the hypervisor, + * the stats queue operates in reverse. The driver initializes the virtqueue + * with a single buffer. From that point forward, all conversations consist of + * a hypervisor request (a call to this function) which directs us to refill + * the virtqueue with a fresh stats buffer. + */ +static void stats_ack(struct virtqueue *vq) +{ + struct virtio_balloon *vb; + unsigned int len; + struct scatterlist sg; + + vb = vq->vq_ops->get_buf(vq, &len); + if (!vb) + return; + + update_balloon_stats(vb); + + sg_init_one(&sg, vb->stats, sizeof(vb->stats)); + if (vq->vq_ops->add_buf(vq, &sg, 1, 0, vb) < 0) + BUG(); + vq->vq_ops->kick(vq); +} + static void virtballoon_changed(struct virtio_device *vdev) { struct virtio_balloon *vb = vdev->priv; @@ -205,10 +259,10 @@ static int balloon(void *_vballoon) static int virtballoon_probe(struct virtio_device *vdev) { struct virtio_balloon *vb; - struct virtqueue *vqs[2]; - vq_callback_t *callbacks[] = { balloon_ack, balloon_ack }; - const char *names[] = { "inflate", "deflate" }; - int err; + struct virtqueue *vqs[3]; + vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_ack }; + const char *names[] = { "inflate", "deflate", "stats" }; + int err, nvqs; vdev->priv = vb = kmalloc(sizeof(*vb), GFP_KERNEL); if (!vb) { @@ -221,13 +275,28 @@ static int virtballoon_probe(struct virtio_device *vdev) init_waitqueue_head(&vb->config_change); vb->vdev = vdev; - /* We expect two virtqueues. */ - err = vdev->config->find_vqs(vdev, 2, vqs, callbacks, names); + /* We expect two virtqueues: inflate and deflate, + * and optionally stat. */ + nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2; + err = vdev->config->find_vqs(vdev, nvqs, vqs, callbacks, names); if (err) goto out_free_vb; vb->inflate_vq = vqs[0]; vb->deflate_vq = vqs[1]; + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) { + struct scatterlist sg; + vb->stats_vq = vqs[2]; + + /* + * Prime this virtqueue with one buffer so the hypervisor can + * use it to signal us later. + */ + sg_init_one(&sg, vb->stats, sizeof(vb->stats)); + if (vb->stats_vq->vq_ops->add_buf(vb->stats_vq, &sg, 1, 0, vb) < 0) + BUG(); + vb->stats_vq->vq_ops->kick(vb->stats_vq); + } vb->thread = kthread_run(balloon, vb, "vballoon"); if (IS_ERR(vb->thread)) { @@ -265,7 +334,9 @@ static void virtballoon_remove(struct virtio_device *vdev) kfree(vb); } -static unsigned int features[] = { VIRTIO_BALLOON_F_MUST_TELL_HOST }; +static unsigned int features[] = { + VIRTIO_BALLOON_F_MUST_TELL_HOST, VIRTIO_BALLOON_F_STATS_VQ, +}; static struct virtio_driver virtio_balloon = { .feature_table = features, diff --git a/include/linux/virtio_balloon.h b/include/linux/virtio_balloon.h index 09d7300..a5c09e6 100644 --- a/include/linux/virtio_balloon.h +++ b/include/linux/virtio_balloon.h @@ -6,6 +6,7 @@ /* The feature bitmap for virtio balloon */ #define VIRTIO_BALLOON_F_MUST_TELL_HOST 0 /* Tell before reclaiming pages */ +#define VIRTIO_BALLOON_F_STATS_VQ 1 /* Memory Stats virtqueue */ /* Size of a PFN in the balloon interface. */ #define VIRTIO_BALLOON_PFN_SHIFT 12 @@ -17,4 +18,19 @@ struct virtio_balloon_config /* Number of pages we've actually got in balloon. */ __le32 actual; }; + +#define VIRTIO_BALLOON_S_SWAP_IN 0 /* Amount of memory swapped in */ +#define VIRTIO_BALLOON_S_SWAP_OUT 1 /* Amount of memory swapped out */ +#define VIRTIO_BALLOON_S_MAJFLT 2 /* Number of major faults */ +#define VIRTIO_BALLOON_S_MINFLT 3 /* Number of minor faults */ +#define VIRTIO_BALLOON_S_MEMFREE 4 /* Total amount of free memory */ +#define VIRTIO_BALLOON_S_MEMTOT 5 /* Total amount of memory */ +#define VIRTIO_BALLOON_S_NR 6 + +struct virtio_balloon_stat +{ + __le16 tag; + __le64 val; +}; + #endif /* _LINUX_VIRTIO_BALLOON_H */ -- Thanks, Adam -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/