[PATCH] vhost: Add polling mode
From: Razya Ladelsky ra...@il.ibm.com Date: Thu, 31 Jul 2014 09:47:20 +0300 Subject: [PATCH] vhost: Add polling mode When vhost is waiting for buffers from the guest driver (e.g., more packets to send in vhost-net's transmit queue), it normally goes to sleep and waits for the guest to kick it. This kick involves a PIO in the guest, and therefore an exit (and possibly userspace involvement in translating this PIO exit into a file descriptor event), all of which hurts performance. If the system is under-utilized (has cpu time to spare), vhost can continuously poll the virtqueues for new buffers, and avoid asking the guest to kick us. This patch adds an optional polling mode to vhost, that can be enabled via a kernel module parameter, poll_start_rate. When polling is active for a virtqueue, the guest is asked to disable notification (kicks), and the worker thread continuously checks for new buffers. When it does discover new buffers, it simulates a kick by invoking the underlying backend driver (such as vhost-net), which thinks it got a real kick from the guest, and acts accordingly. If the underlying driver asks not to be kicked, we disable polling on this virtqueue. We start polling on a virtqueue when we notice it has work to do. Polling on this virtqueue is later disabled after 3 seconds of polling turning up no new work, as in this case we are better off returning to the exit-based notification mechanism. The default timeout of 3 seconds can be changed with the poll_stop_idle kernel module parameter. This polling approach makes lot of sense for new HW with posted-interrupts for which we have exitless host-to-guest notifications. But even with support for posted interrupts, guest-to-host communication still causes exits. Polling adds the missing part. When systems are overloaded, there won't be enough cpu time for the various vhost threads to poll their guests' devices. For these scenarios, we plan to add support for vhost threads that can be shared by multiple devices, even of multiple vms. Our ultimate goal is to implement the I/O acceleration features described in: KVM Forum 2013: Efficient and Scalable Virtio (by Abel Gordon) https://www.youtube.com/watch?v=9EyweibHfEs and https://www.mail-archive.com/kvm@vger.kernel.org/msg98179.html I ran some experiments with TCP stream netperf and filebench (having 2 threads performing random reads) benchmarks on an IBM System x3650 M4. I have two machines, A and B. A hosts the vms, B runs the netserver. The vms (on A) run netperf, its destination server is running on B. All runs loaded the guests in a way that they were (cpu) saturated. For example, I ran netperf with 64B messages, which is heavily loading the vm (which is why its throughput is low). The idea was to get it 100% loaded, so we can see that the polling is getting it to produce higher throughput. The system had two cores per guest, as to allow for both the vcpu and the vhost thread to run concurrently for maximum throughput (but I didn't pin the threads to specific cores). My experiments were fair in a sense that for both cases, with or without polling, I run both threads, vcpu and vhost, on 2 cores (set their affinity that way). The only difference was whether polling was enabled/disabled. Results: Netperf, 1 vm: The polling patch improved throughput by ~33% (1516 MB/sec - 2046 MB/sec). Number of exits/sec decreased 6x. The same improvement was shown when I tested with 3 vms running netperf (4086 MB/sec - 5545 MB/sec). filebench, 1 vm: ops/sec improved by 13% with the polling patch. Number of exits was reduced by 31%. The same experiment with 3 vms running filebench showed similar numbers. Signed-off-by: Razya Ladelsky ra...@il.ibm.com --- drivers/vhost/net.c |6 +- drivers/vhost/scsi.c |6 +- drivers/vhost/vhost.c | 245 +++-- drivers/vhost/vhost.h | 38 +++- 4 files changed, 277 insertions(+), 18 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 971a760..558aecb 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -742,8 +742,10 @@ static int vhost_net_open(struct inode *inode, struct file *f) } vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX); - vhost_poll_init(n-poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev); - vhost_poll_init(n-poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev); + vhost_poll_init(n-poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, + vqs[VHOST_NET_VQ_TX]); + vhost_poll_init(n-poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, + vqs[VHOST_NET_VQ_RX]); f-private_data = n; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 4f4ffa4..665eeeb 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1528,9 +1528,9 @@ static int vhost_scsi_open(struct inode *inode, struct file *f) if (!vqs) goto err_vqs; -
RFC: [PATCH v1] KVM: Use trace_printk() for vcpu_unimpl() for performance reasons
vcpu_unimpl() is called to notify for example about unhandled wrmsr requests made by KVM guests. It used to call printk() but in certain setups printk() may cause severe performance impact thus replacing printk() with guaranteed to be buffered trace_printk() avoids this caveat. Signed-off-by: Ilari Stenroth ilari.stenr...@gmail.com --- include/linux/kvm_host.h | 8 1 file changed, 8 insertions(+) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index a4c33b3..b79ce59 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -24,6 +24,8 @@ #include linux/err.h #include linux/irqflags.h #include linux/context_tracking.h +#include linux/kernel.h +#include linux/kern_levels.h #include asm/signal.h #include linux/kvm.h @@ -408,9 +410,15 @@ struct kvm { pr_info(kvm [%i]: fmt, task_pid_nr(current), ## __VA_ARGS__) #define kvm_debug(fmt, ...) \ pr_debug(kvm [%i]: fmt, task_pid_nr(current), ## __VA_ARGS__) +#ifdef CONFIG_TRACING +#define kvm_pr_unimpl(fmt, ...) \ + trace_printk(pr_fmt(KERN_ERR kvm [%i]: fmt), \ + task_tgid_nr(current), ## __VA_ARGS__) +#else #define kvm_pr_unimpl(fmt, ...) \ pr_err_ratelimited(kvm [%i]: fmt, \ task_tgid_nr(current), ## __VA_ARGS__) +#endif /* The guest did something we don't support. */ #define vcpu_unimpl(vcpu, fmt, ...)\ -- 2.0.4 -- To unsubscribe from this list: send the line unsubscribe kvm in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: [PATCH] vhost: Add polling mode
On Sun, Aug 10, 2014 at 11:30:35AM +0300, Razya Ladelsky wrote: From: Razya Ladelsky ra...@il.ibm.com Date: Thu, 31 Jul 2014 09:47:20 +0300 Subject: [PATCH] vhost: Add polling mode When vhost is waiting for buffers from the guest driver (e.g., more packets to send in vhost-net's transmit queue), it normally goes to sleep and waits for the guest to kick it. This kick involves a PIO in the guest, and therefore an exit (and possibly userspace involvement in translating this PIO exit into a file descriptor event), all of which hurts performance. If the system is under-utilized (has cpu time to spare), vhost can continuously poll the virtqueues for new buffers, and avoid asking the guest to kick us. This patch adds an optional polling mode to vhost, that can be enabled via a kernel module parameter, poll_start_rate. When polling is active for a virtqueue, the guest is asked to disable notification (kicks), and the worker thread continuously checks for new buffers. When it does discover new buffers, it simulates a kick by invoking the underlying backend driver (such as vhost-net), which thinks it got a real kick from the guest, and acts accordingly. If the underlying driver asks not to be kicked, we disable polling on this virtqueue. We start polling on a virtqueue when we notice it has work to do. Polling on this virtqueue is later disabled after 3 seconds of polling turning up no new work, as in this case we are better off returning to the exit-based notification mechanism. The default timeout of 3 seconds can be changed with the poll_stop_idle kernel module parameter. This polling approach makes lot of sense for new HW with posted-interrupts for which we have exitless host-to-guest notifications. But even with support for posted interrupts, guest-to-host communication still causes exits. Polling adds the missing part. When systems are overloaded, there won't be enough cpu time for the various vhost threads to poll their guests' devices. For these scenarios, we plan to add support for vhost threads that can be shared by multiple devices, even of multiple vms. Our ultimate goal is to implement the I/O acceleration features described in: KVM Forum 2013: Efficient and Scalable Virtio (by Abel Gordon) https://www.youtube.com/watch?v=9EyweibHfEs and https://www.mail-archive.com/kvm@vger.kernel.org/msg98179.html I ran some experiments with TCP stream netperf and filebench (having 2 threads performing random reads) benchmarks on an IBM System x3650 M4. I have two machines, A and B. A hosts the vms, B runs the netserver. The vms (on A) run netperf, its destination server is running on B. All runs loaded the guests in a way that they were (cpu) saturated. For example, I ran netperf with 64B messages, which is heavily loading the vm (which is why its throughput is low). The idea was to get it 100% loaded, so we can see that the polling is getting it to produce higher throughput. And, did your tests actually produce 100% load on both host CPUs? The system had two cores per guest, as to allow for both the vcpu and the vhost thread to run concurrently for maximum throughput (but I didn't pin the threads to specific cores). My experiments were fair in a sense that for both cases, with or without polling, I run both threads, vcpu and vhost, on 2 cores (set their affinity that way). The only difference was whether polling was enabled/disabled. Results: Netperf, 1 vm: The polling patch improved throughput by ~33% (1516 MB/sec - 2046 MB/sec). Number of exits/sec decreased 6x. The same improvement was shown when I tested with 3 vms running netperf (4086 MB/sec - 5545 MB/sec). filebench, 1 vm: ops/sec improved by 13% with the polling patch. Number of exits was reduced by 31%. The same experiment with 3 vms running filebench showed similar numbers. Signed-off-by: Razya Ladelsky ra...@il.ibm.com --- drivers/vhost/net.c |6 +- drivers/vhost/scsi.c |6 +- drivers/vhost/vhost.c | 245 +++-- drivers/vhost/vhost.h | 38 +++- 4 files changed, 277 insertions(+), 18 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 971a760..558aecb 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -742,8 +742,10 @@ static int vhost_net_open(struct inode *inode, struct file *f) } vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX); - vhost_poll_init(n-poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev); - vhost_poll_init(n-poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev); + vhost_poll_init(n-poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, + vqs[VHOST_NET_VQ_TX]); + vhost_poll_init(n-poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, + vqs[VHOST_NET_VQ_RX]); f-private_data = n; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index
Re: [PATCH v3] powerpc/kvm: support to handle sw breakpoint
On Sunday 03 August 2014 09:21 PM, Segher Boessenkool wrote: +/* + * KVMPPC_INST_BOOK3S_DEBUG is debug Instruction for supporting Software Breakpoint. + * Based on PowerISA v2.07, Instruction with opcode 0s will be treated as illegal + * instruction. + */ primary opcode 0 instead? ok sure. +#define OP_ZERO 0x0 Using 0x0 where you mean 0, making a #define for 0 in the first place... This all looks rather silly doesn't it. I wanted to avoid zero mentioned in the case statement, but can add a comment explaining it. +case OP_ZERO: +if((inst 0x0000) == KVMPPC_INST_BOOK3S_DEBUG) { You either shouldn't mask at all here, or the mask is wrong (the primary op is the top six bits, not the top eight). Yes. I guess I dont need to check here. Will resend the patch. Thanks for review Regards Maddy Segher -- To unsubscribe from this list: send the line unsubscribe kvm in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html