* Re: [RFC][QEMU Patch] KVM: Enable QEMU to free the pages hinted by the guest [not found] <CAKgT0Ue=kGB4D2oV1WUmWHiYhrXa64KWBP2ZhLgHNgvWyOng5A@mail.gmail.com> @ 2019-03-07 0:35 ` Alexander Duyck 2019-03-07 12:23 ` Nitesh Narayan Lal 0 siblings, 1 reply; 3+ messages in thread From: Alexander Duyck @ 2019-03-07 0:35 UTC (permalink / raw) To: nitesh Cc: yang.zhang.wz, pagupta, kvm, riel, david, linux-kernel, lcapitulino, linux-mm, wei.w.wang, aarcange, mst, dhildenb, pbonzini, dodgen, konrad.wilk Here are some changes I made to your patch in order to address the sizing issue I called out. You may want to try testing with this patch applied to your QEMU as I am finding it is making a signficant difference. It has cut the test time for the 32G memhog test I called out earlier in half. Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> --- hw/virtio/virtio-balloon.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c index d2cf66ada3c0..3ca6b1c6d511 100644 --- a/hw/virtio/virtio-balloon.c +++ b/hw/virtio/virtio-balloon.c @@ -285,7 +285,7 @@ static void balloon_stats_set_poll_interval(Object *obj, Visitor *v, balloon_stats_change_timer(s, 0); } -static void *gpa2hva(MemoryRegion **p_mr, hwaddr addr, Error **errp) +static void *gpa2hva(MemoryRegion **p_mr, unsigned long *size, hwaddr addr, Error **errp) { MemoryRegionSection mrs = memory_region_find(get_system_memory(), addr, 1); @@ -302,6 +302,7 @@ static void *gpa2hva(MemoryRegion **p_mr, hwaddr addr, Error **errp) } *p_mr = mrs.mr; + *size = mrs.mr->size - mrs.offset_within_region; return qemu_map_ram_ptr(mrs.mr->ram_block, mrs.offset_within_region); } @@ -313,30 +314,35 @@ void page_hinting_request(uint64_t addr, uint32_t len) struct guest_pages *guest_obj; int i = 0; void *hvaddr_to_free; - unsigned long pfn, pfn_end; uint64_t gpaddr_to_free; - void * temp_addr = gpa2hva(&mr, addr, &local_err); + unsigned long madv_size, size; + void * temp_addr = gpa2hva(&mr, &madv_size, addr, &local_err); if (local_err) { error_report_err(local_err); return; } + if (madv_size < sizeof(*guest_obj)) { + printf("\nBad guest object ptr\n"); + return; + } guest_obj = temp_addr; while (i < len) { - pfn = guest_obj[i].pfn; - pfn_end = guest_obj[i].pfn + (1 << guest_obj[i].order) - 1; - trace_virtio_balloon_hinting_request(pfn,(1 << guest_obj[i].order)); - while (pfn <= pfn_end) { - gpaddr_to_free = pfn << VIRTIO_BALLOON_PFN_SHIFT; - hvaddr_to_free = gpa2hva(&mr, gpaddr_to_free, &local_err); + gpaddr_to_free = guest_obj[i].pfn << VIRTIO_BALLOON_PFN_SHIFT; + size = (1 << VIRTIO_BALLOON_PFN_SHIFT) << guest_obj[i].order; + while (size) { + hvaddr_to_free = gpa2hva(&mr, &madv_size, gpaddr_to_free, &local_err); if (local_err) { error_report_err(local_err); return; } - ret = qemu_madvise((void *)hvaddr_to_free, 4096, QEMU_MADV_DONTNEED); + if (size < madv_size) + madv_size = size; + ret = qemu_madvise((void *)hvaddr_to_free, madv_size, QEMU_MADV_DONTNEED); if (ret == -1) printf("\n%d:%s Error: Madvise failed with error:%d\n", __LINE__, __func__, ret); - pfn++; + gpaddr_to_free += madv_size; + size -= madv_size; } i++; } ^ permalink raw reply related [flat|nested] 3+ messages in thread
* Re: [RFC][QEMU Patch] KVM: Enable QEMU to free the pages hinted by the guest 2019-03-07 0:35 ` [RFC][QEMU Patch] KVM: Enable QEMU to free the pages hinted by the guest Alexander Duyck @ 2019-03-07 12:23 ` Nitesh Narayan Lal 0 siblings, 0 replies; 3+ messages in thread From: Nitesh Narayan Lal @ 2019-03-07 12:23 UTC (permalink / raw) To: Alexander Duyck Cc: yang.zhang.wz, pagupta, kvm, riel, david, linux-kernel, lcapitulino, linux-mm, wei.w.wang, aarcange, mst, dhildenb, pbonzini, dodgen, konrad.wilk [-- Attachment #1.1: Type: text/plain, Size: 3308 bytes --] On 3/6/19 7:35 PM, Alexander Duyck wrote: > Here are some changes I made to your patch in order to address the sizing > issue I called out. You may want to try testing with this patch applied to > your QEMU as I am finding it is making a signficant difference. It has cut > the test time for the 32G memhog test I called out earlier in half. Thanks, I will try this out. > > Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com> > --- > hw/virtio/virtio-balloon.c | 28 +++++++++++++++++----------- > 1 file changed, 17 insertions(+), 11 deletions(-) > > diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c > index d2cf66ada3c0..3ca6b1c6d511 100644 > --- a/hw/virtio/virtio-balloon.c > +++ b/hw/virtio/virtio-balloon.c > @@ -285,7 +285,7 @@ static void balloon_stats_set_poll_interval(Object *obj, Visitor *v, > balloon_stats_change_timer(s, 0); > } > > -static void *gpa2hva(MemoryRegion **p_mr, hwaddr addr, Error **errp) > +static void *gpa2hva(MemoryRegion **p_mr, unsigned long *size, hwaddr addr, Error **errp) > { > MemoryRegionSection mrs = memory_region_find(get_system_memory(), > addr, 1); > @@ -302,6 +302,7 @@ static void *gpa2hva(MemoryRegion **p_mr, hwaddr addr, Error **errp) > } > > *p_mr = mrs.mr; > + *size = mrs.mr->size - mrs.offset_within_region; > return qemu_map_ram_ptr(mrs.mr->ram_block, mrs.offset_within_region); > } > > @@ -313,30 +314,35 @@ void page_hinting_request(uint64_t addr, uint32_t len) > struct guest_pages *guest_obj; > int i = 0; > void *hvaddr_to_free; > - unsigned long pfn, pfn_end; > uint64_t gpaddr_to_free; > - void * temp_addr = gpa2hva(&mr, addr, &local_err); > + unsigned long madv_size, size; > + void * temp_addr = gpa2hva(&mr, &madv_size, addr, &local_err); > > if (local_err) { > error_report_err(local_err); > return; > } > + if (madv_size < sizeof(*guest_obj)) { > + printf("\nBad guest object ptr\n"); > + return; > + } > guest_obj = temp_addr; > while (i < len) { > - pfn = guest_obj[i].pfn; > - pfn_end = guest_obj[i].pfn + (1 << guest_obj[i].order) - 1; > - trace_virtio_balloon_hinting_request(pfn,(1 << guest_obj[i].order)); > - while (pfn <= pfn_end) { > - gpaddr_to_free = pfn << VIRTIO_BALLOON_PFN_SHIFT; > - hvaddr_to_free = gpa2hva(&mr, gpaddr_to_free, &local_err); > + gpaddr_to_free = guest_obj[i].pfn << VIRTIO_BALLOON_PFN_SHIFT; > + size = (1 << VIRTIO_BALLOON_PFN_SHIFT) << guest_obj[i].order; > + while (size) { > + hvaddr_to_free = gpa2hva(&mr, &madv_size, gpaddr_to_free, &local_err); > if (local_err) { > error_report_err(local_err); > return; > } > - ret = qemu_madvise((void *)hvaddr_to_free, 4096, QEMU_MADV_DONTNEED); > + if (size < madv_size) > + madv_size = size; > + ret = qemu_madvise((void *)hvaddr_to_free, madv_size, QEMU_MADV_DONTNEED); > if (ret == -1) > printf("\n%d:%s Error: Madvise failed with error:%d\n", __LINE__, __func__, ret); > - pfn++; > + gpaddr_to_free += madv_size; > + size -= madv_size; > } > i++; > } > -- Regards Nitesh [-- Attachment #2: OpenPGP digital signature --] [-- Type: application/pgp-signature, Size: 833 bytes --] ^ permalink raw reply [flat|nested] 3+ messages in thread
* [RFC][Patch v9 0/6] KVM: Guest Free Page Hinting @ 2019-03-06 15:50 Nitesh Narayan Lal 2019-03-06 15:52 ` [RFC][QEMU Patch] KVM: Enable QEMU to free the pages hinted by the guest Nitesh Narayan Lal 0 siblings, 1 reply; 3+ messages in thread From: Nitesh Narayan Lal @ 2019-03-06 15:50 UTC (permalink / raw) To: kvm, linux-kernel, linux-mm, pbonzini, lcapitulino, pagupta, wei.w.wang, yang.zhang.wz, riel, david, mst, dodgen, konrad.wilk, dhildenb, aarcange, alexander.duyck The following patch-set proposes an efficient mechanism for handing freed memory between the guest and the host. It enables the guests with no page cache to rapidly free and reclaims memory to and from the host respectively. Benefit: With this patch-series, in our test-case, executed on a single system and single NUMA node with 15GB memory, we were able to successfully launch 5 guests(each with 5 GB memory) when page hinting was enabled and 3 without it. (Detailed explanation of the test procedure is provided at the bottom under Test - 1). Changelog in v9: * Guest free page hinting hook is now invoked after a page has been merged in the buddy. * Free pages only with order FREE_PAGE_HINTING_MIN_ORDER(currently defined as MAX_ORDER - 1) are captured. * Removed kthread which was earlier used to perform the scanning, isolation & reporting of free pages. * Pages, captured in the per cpu array are sorted based on the zone numbers. This is to avoid redundancy of acquiring zone locks. * Dynamically allocated space is used to hold the isolated guest free pages. * All the pages are reported asynchronously to the host via virtio driver. * Pages are returned back to the guest buddy free list only when the host response is received. Pending items: * Make sure that the guest free page hinting's current implementation doesn't break hugepages or device assigned guests. * Follow up on VIRTIO_BALLOON_F_PAGE_POISON's device side support. (It is currently missing) * Compare reporting free pages via vring with vhost. * Decide between MADV_DONTNEED and MADV_FREE. * Analyze overall performance impact due to guest free page hinting. * Come up with proper/traceable error-message/logs. Tests: 1. Use-case - Number of guests we can launch NUMA Nodes = 1 with 15 GB memory Guest Memory = 5 GB Number of cores in guest = 1 Workload = test allocation program allocates 4GB memory, touches it via memset and exits. Procedure = The first guest is launched and once its console is up, the test allocation program is executed with 4 GB memory request (Due to this the guest occupies almost 4-5 GB of memory in the host in a system without page hinting). Once this program exits at that time another guest is launched in the host and the same process is followed. We continue launching the guests until a guest gets killed due to low memory condition in the host. Results: Without hinting = 3 With hinting = 5 2. Hackbench Guest Memory = 5 GB Number of cores = 4 Number of tasks Time with Hinting Time without Hinting 4000 19.540 17.818 ^ permalink raw reply [flat|nested] 3+ messages in thread
* [RFC][QEMU Patch] KVM: Enable QEMU to free the pages hinted by the guest 2019-03-06 15:50 [RFC][Patch v9 0/6] KVM: Guest Free Page Hinting Nitesh Narayan Lal @ 2019-03-06 15:52 ` Nitesh Narayan Lal 0 siblings, 0 replies; 3+ messages in thread From: Nitesh Narayan Lal @ 2019-03-06 15:52 UTC (permalink / raw) To: kvm, linux-kernel, linux-mm, pbonzini, lcapitulino, pagupta, wei.w.wang, yang.zhang.wz, riel, david, mst, dodgen, konrad.wilk, dhildenb, aarcange, alexander.duyck Cc: Nitesh Narayan Lal This patch enables QEMU to perform MADVISE_DONTNEED on the pages reported by the guest. Signed-off-by: Nitesh Narayan Lal <nitesh@redhat.com> --- hw/virtio/trace-events | 1 + hw/virtio/virtio-balloon.c | 90 +++++++++++++++++++ include/hw/virtio/virtio-balloon.h | 2 +- .../standard-headers/linux/virtio_balloon.h | 1 + 4 files changed, 93 insertions(+), 1 deletion(-) diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index 07bcbe9e85..e3ab66f126 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -46,3 +46,4 @@ virtio_balloon_handle_output(const char *name, uint64_t gpa) "section name: %s g virtio_balloon_get_config(uint32_t num_pages, uint32_t actual) "num_pages: %d actual: %d" virtio_balloon_set_config(uint32_t actual, uint32_t oldactual) "actual: %d oldactual: %d" virtio_balloon_to_target(uint64_t target, uint32_t num_pages) "balloon target: 0x%"PRIx64" num_pages: %d" +virtio_balloon_hinting_request(unsigned long pfn, unsigned int num_pages) "Guest page hinting request: %lu num_pages: %d" diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c index a12677d4d5..7ab1471017 100644 --- a/hw/virtio/virtio-balloon.c +++ b/hw/virtio/virtio-balloon.c @@ -33,6 +33,13 @@ #define BALLOON_PAGE_SIZE (1 << VIRTIO_BALLOON_PFN_SHIFT) +struct guest_pages { + unsigned long pfn; + unsigned int order; +}; + +void page_hinting_request(uint64_t addr, uint32_t len); + static void balloon_page(void *addr, int deflate) { if (!qemu_balloon_is_inhibited()) { @@ -207,6 +214,85 @@ static void balloon_stats_set_poll_interval(Object *obj, Visitor *v, balloon_stats_change_timer(s, 0); } +static void *gpa2hva(MemoryRegion **p_mr, hwaddr addr, Error **errp) +{ + MemoryRegionSection mrs = memory_region_find(get_system_memory(), + addr, 1); + + if (!mrs.mr) { + error_setg(errp, "No memory is mapped at address 0x%" HWADDR_PRIx, addr); + return NULL; + } + + if (!memory_region_is_ram(mrs.mr) && !memory_region_is_romd(mrs.mr)) { + error_setg(errp, "Memory at address 0x%" HWADDR_PRIx "is not RAM", addr); + memory_region_unref(mrs.mr); + return NULL; + } + + *p_mr = mrs.mr; + return qemu_map_ram_ptr(mrs.mr->ram_block, mrs.offset_within_region); +} + +void page_hinting_request(uint64_t addr, uint32_t len) +{ + Error *local_err = NULL; + MemoryRegion *mr = NULL; + int ret = 0; + struct guest_pages *guest_obj; + int i = 0; + void *hvaddr_to_free; + unsigned long pfn, pfn_end; + uint64_t gpaddr_to_free; + void * temp_addr = gpa2hva(&mr, addr, &local_err); + + if (local_err) { + error_report_err(local_err); + return; + } + guest_obj = temp_addr; + while (i < len) { + pfn = guest_obj[i].pfn; + pfn_end = guest_obj[i].pfn + (1 << guest_obj[i].order) - 1; + trace_virtio_balloon_hinting_request(pfn,(1 << guest_obj[i].order)); + while (pfn <= pfn_end) { + gpaddr_to_free = pfn << VIRTIO_BALLOON_PFN_SHIFT; + hvaddr_to_free = gpa2hva(&mr, gpaddr_to_free, &local_err); + if (local_err) { + error_report_err(local_err); + return; + } + ret = qemu_madvise((void *)hvaddr_to_free, 4096, QEMU_MADV_DONTNEED); + if (ret == -1) + printf("\n%d:%s Error: Madvise failed with error:%d\n", __LINE__, __func__, ret); + pfn++; + } + i++; + } +} + +static void virtio_balloon_page_hinting(VirtIODevice *vdev, VirtQueue *vq) +{ + VirtQueueElement *elem = NULL; + uint64_t temp_addr; + uint32_t temp_len; + size_t size, t_size = 0; + + elem = virtqueue_pop(vq, sizeof(VirtQueueElement)); + if (!elem) { + printf("\npop error\n"); + return; + } + size = iov_to_buf(elem->out_sg, elem->out_num, 0, &temp_addr, sizeof(temp_addr)); + t_size += size; + size = iov_to_buf(elem->out_sg, elem->out_num, 8, &temp_len, sizeof(temp_len)); + t_size += size; + page_hinting_request(temp_addr, temp_len); + virtqueue_push(vq, elem, t_size); + virtio_notify(vdev, vq); + g_free(elem); +} + static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq) { VirtIOBalloon *s = VIRTIO_BALLOON(vdev); @@ -376,6 +462,7 @@ static uint64_t virtio_balloon_get_features(VirtIODevice *vdev, uint64_t f, VirtIOBalloon *dev = VIRTIO_BALLOON(vdev); f |= dev->host_features; virtio_add_feature(&f, VIRTIO_BALLOON_F_STATS_VQ); + virtio_add_feature(&f, VIRTIO_BALLOON_F_HINTING); return f; } @@ -445,6 +532,7 @@ static void virtio_balloon_device_realize(DeviceState *dev, Error **errp) s->ivq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output); s->dvq = virtio_add_queue(vdev, 128, virtio_balloon_handle_output); s->svq = virtio_add_queue(vdev, 128, virtio_balloon_receive_stats); + s->hvq = virtio_add_queue(vdev, 128, virtio_balloon_page_hinting); reset_stats(s); } @@ -488,6 +576,8 @@ static void virtio_balloon_instance_init(Object *obj) object_property_add(obj, "guest-stats", "guest statistics", balloon_stats_get_all, NULL, NULL, s, NULL); + object_property_add(obj, "guest-page-hinting", "guest page hinting", + NULL, NULL, NULL, s, NULL); object_property_add(obj, "guest-stats-polling-interval", "int", balloon_stats_get_poll_interval, diff --git a/include/hw/virtio/virtio-balloon.h b/include/hw/virtio/virtio-balloon.h index e0df3528c8..774498a6ca 100644 --- a/include/hw/virtio/virtio-balloon.h +++ b/include/hw/virtio/virtio-balloon.h @@ -32,7 +32,7 @@ typedef struct virtio_balloon_stat_modern { typedef struct VirtIOBalloon { VirtIODevice parent_obj; - VirtQueue *ivq, *dvq, *svq; + VirtQueue *ivq, *dvq, *svq, *hvq; uint32_t num_pages; uint32_t actual; uint64_t stats[VIRTIO_BALLOON_S_NR]; diff --git a/include/standard-headers/linux/virtio_balloon.h b/include/standard-headers/linux/virtio_balloon.h index 4dbb7dc6c0..f50c0d95ea 100644 --- a/include/standard-headers/linux/virtio_balloon.h +++ b/include/standard-headers/linux/virtio_balloon.h @@ -34,6 +34,7 @@ #define VIRTIO_BALLOON_F_MUST_TELL_HOST 0 /* Tell before reclaiming pages */ #define VIRTIO_BALLOON_F_STATS_VQ 1 /* Memory Stats virtqueue */ #define VIRTIO_BALLOON_F_DEFLATE_ON_OOM 2 /* Deflate balloon on OOM */ +#define VIRTIO_BALLOON_F_HINTING 5 /* Page hinting virtqueue */ /* Size of a PFN in the balloon interface. */ #define VIRTIO_BALLOON_PFN_SHIFT 12 -- 2.17.2 ^ permalink raw reply related [flat|nested] 3+ messages in thread
end of thread, other threads:[~2019-03-07 12:23 UTC | newest] Thread overview: 3+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- [not found] <CAKgT0Ue=kGB4D2oV1WUmWHiYhrXa64KWBP2ZhLgHNgvWyOng5A@mail.gmail.com> 2019-03-07 0:35 ` [RFC][QEMU Patch] KVM: Enable QEMU to free the pages hinted by the guest Alexander Duyck 2019-03-07 12:23 ` Nitesh Narayan Lal 2019-03-06 15:50 [RFC][Patch v9 0/6] KVM: Guest Free Page Hinting Nitesh Narayan Lal 2019-03-06 15:52 ` [RFC][QEMU Patch] KVM: Enable QEMU to free the pages hinted by the guest Nitesh Narayan Lal
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).