Re: [PATCH v8] NVMe: convert to blk-mq
On Tue, Jun 24, 2014 at 11:47 PM, Keith Busch wrote: > On Tue, 24 Jun 2014, Matias Bjørling wrote: >> >> On Tue, Jun 24, 2014 at 10:33 PM, Keith Busch >> wrote: >>> >>> On Tue, 24 Jun 2014, Matias Bjorling wrote: Den 16-06-2014 17:57, Keith Busch skrev: > > > This latest is otherwise stable on my dev machine. May I add an Acked-by from you? >>> >>> >>> Totally up to Willy, but my feeling is "not just yet". I see the value >>> this driver provides, but I would need to give this to a customer and >>> hear their results before adding an "ack". It maybe a couple more weeks >>> before they'll be able to try it. >> >> >> I was hoping to get an OK before that, to make sure it is picked up >> for the 3.17 release. >> >> Should I pack it up in a specific way to help it along? > > > I think what you're doing is the right way to go. I trust you removed > the test code from your next iteration, and this does pass my tests on my > machine... I was just hoping to hear what some other people with better > macro level benchmarking abilities would say. So okay, you can put my > "Acked-by" on this, but I don't have all the performance numbers yet. Thanks. Yes, agree. I'll also send the patch to a couple of people that have nvme devices for further testing. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v8] NVMe: convert to blk-mq
On Tue, 24 Jun 2014, Matias Bjørling wrote: On Tue, Jun 24, 2014 at 10:33 PM, Keith Busch wrote: On Tue, 24 Jun 2014, Matias Bjorling wrote: Den 16-06-2014 17:57, Keith Busch skrev: This latest is otherwise stable on my dev machine. May I add an Acked-by from you? Totally up to Willy, but my feeling is "not just yet". I see the value this driver provides, but I would need to give this to a customer and hear their results before adding an "ack". It maybe a couple more weeks before they'll be able to try it. I was hoping to get an OK before that, to make sure it is picked up for the 3.17 release. Should I pack it up in a specific way to help it along? I think what you're doing is the right way to go. I trust you removed the test code from your next iteration, and this does pass my tests on my machine... I was just hoping to hear what some other people with better macro level benchmarking abilities would say. So okay, you can put my "Acked-by" on this, but I don't have all the performance numbers yet.
Re: [PATCH v8] NVMe: convert to blk-mq
On Tue, Jun 24, 2014 at 10:33 PM, Keith Busch wrote: > On Tue, 24 Jun 2014, Matias Bjorling wrote: >> >> Den 16-06-2014 17:57, Keith Busch skrev: >>> >>> This latest is otherwise stable on my dev machine. >> >> >> May I add an Acked-by from you? > > > Totally up to Willy, but my feeling is "not just yet". I see the value > this driver provides, but I would need to give this to a customer and > hear their results before adding an "ack". It maybe a couple more weeks > before they'll be able to try it. I was hoping to get an OK before that, to make sure it is picked up for the 3.17 release. Should I pack it up in a specific way to help it along? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v8] NVMe: convert to blk-mq
On Tue, 24 Jun 2014, Matias Bjorling wrote: Den 16-06-2014 17:57, Keith Busch skrev: This latest is otherwise stable on my dev machine. May I add an Acked-by from you? Totally up to Willy, but my feeling is "not just yet". I see the value this driver provides, but I would need to give this to a customer and hear their results before adding an "ack". It maybe a couple more weeks before they'll be able to try it. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v8] NVMe: convert to blk-mq
Den 16-06-2014 17:57, Keith Busch skrev: On Fri, 13 Jun 2014, Matias Bjørling wrote: This converts the current NVMe driver to utilize the blk-mq layer. static void nvme_reset_notify(struct pci_dev *pdev, bool prepare) { - struct nvme_dev *dev = pci_get_drvdata(pdev); +struct nvme_dev *dev = pci_get_drvdata(pdev); - if (prepare) - nvme_dev_shutdown(dev); - else - nvme_dev_resume(dev); +spin_lock(_list_lock); +if (prepare) +list_del_init(>node); +else +list_add(>node, _list); +spin_unlock(_list_lock); } +if (nvme_create_queue(dev->queues[i], i)) break; } The above change was just error injection test code so you can cause a device to become unresponsive and trigger the timeout handling. This latest is otherwise stable on my dev machine. May I add an Acked-by from you? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v8] NVMe: convert to blk-mq
Den 16-06-2014 17:57, Keith Busch skrev: On Fri, 13 Jun 2014, Matias Bjørling wrote: This converts the current NVMe driver to utilize the blk-mq layer. static void nvme_reset_notify(struct pci_dev *pdev, bool prepare) { - struct nvme_dev *dev = pci_get_drvdata(pdev); +struct nvme_dev *dev = pci_get_drvdata(pdev); - if (prepare) - nvme_dev_shutdown(dev); - else - nvme_dev_resume(dev); +spin_lock(dev_list_lock); +if (prepare) +list_del_init(dev-node); +else +list_add(dev-node, dev_list); +spin_unlock(dev_list_lock); } +if (nvme_create_queue(dev-queues[i], i)) break; } The above change was just error injection test code so you can cause a device to become unresponsive and trigger the timeout handling. This latest is otherwise stable on my dev machine. May I add an Acked-by from you? -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v8] NVMe: convert to blk-mq
On Tue, 24 Jun 2014, Matias Bjorling wrote: Den 16-06-2014 17:57, Keith Busch skrev: This latest is otherwise stable on my dev machine. May I add an Acked-by from you? Totally up to Willy, but my feeling is not just yet. I see the value this driver provides, but I would need to give this to a customer and hear their results before adding an ack. It maybe a couple more weeks before they'll be able to try it. -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v8] NVMe: convert to blk-mq
On Tue, Jun 24, 2014 at 10:33 PM, Keith Busch keith.bu...@intel.com wrote: On Tue, 24 Jun 2014, Matias Bjorling wrote: Den 16-06-2014 17:57, Keith Busch skrev: This latest is otherwise stable on my dev machine. May I add an Acked-by from you? Totally up to Willy, but my feeling is not just yet. I see the value this driver provides, but I would need to give this to a customer and hear their results before adding an ack. It maybe a couple more weeks before they'll be able to try it. I was hoping to get an OK before that, to make sure it is picked up for the 3.17 release. Should I pack it up in a specific way to help it along? -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v8] NVMe: convert to blk-mq
On Tue, 24 Jun 2014, Matias Bjørling wrote: On Tue, Jun 24, 2014 at 10:33 PM, Keith Busch keith.bu...@intel.com wrote: On Tue, 24 Jun 2014, Matias Bjorling wrote: Den 16-06-2014 17:57, Keith Busch skrev: This latest is otherwise stable on my dev machine. May I add an Acked-by from you? Totally up to Willy, but my feeling is not just yet. I see the value this driver provides, but I would need to give this to a customer and hear their results before adding an ack. It maybe a couple more weeks before they'll be able to try it. I was hoping to get an OK before that, to make sure it is picked up for the 3.17 release. Should I pack it up in a specific way to help it along? I think what you're doing is the right way to go. I trust you removed the test code from your next iteration, and this does pass my tests on my machine... I was just hoping to hear what some other people with better macro level benchmarking abilities would say. So okay, you can put my Acked-by on this, but I don't have all the performance numbers yet.
Re: [PATCH v8] NVMe: convert to blk-mq
On Tue, Jun 24, 2014 at 11:47 PM, Keith Busch keith.bu...@intel.com wrote: On Tue, 24 Jun 2014, Matias Bjørling wrote: On Tue, Jun 24, 2014 at 10:33 PM, Keith Busch keith.bu...@intel.com wrote: On Tue, 24 Jun 2014, Matias Bjorling wrote: Den 16-06-2014 17:57, Keith Busch skrev: This latest is otherwise stable on my dev machine. May I add an Acked-by from you? Totally up to Willy, but my feeling is not just yet. I see the value this driver provides, but I would need to give this to a customer and hear their results before adding an ack. It maybe a couple more weeks before they'll be able to try it. I was hoping to get an OK before that, to make sure it is picked up for the 3.17 release. Should I pack it up in a specific way to help it along? I think what you're doing is the right way to go. I trust you removed the test code from your next iteration, and this does pass my tests on my machine... I was just hoping to hear what some other people with better macro level benchmarking abilities would say. So okay, you can put my Acked-by on this, but I don't have all the performance numbers yet. Thanks. Yes, agree. I'll also send the patch to a couple of people that have nvme devices for further testing. -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v8] NVMe: convert to blk-mq
Den 16-06-2014 17:57, Keith Busch skrev: On Fri, 13 Jun 2014, Matias Bjørling wrote: This converts the current NVMe driver to utilize the blk-mq layer. static void nvme_reset_notify(struct pci_dev *pdev, bool prepare) { - struct nvme_dev *dev = pci_get_drvdata(pdev); +struct nvme_dev *dev = pci_get_drvdata(pdev); - if (prepare) - nvme_dev_shutdown(dev); - else - nvme_dev_resume(dev); +spin_lock(_list_lock); +if (prepare) +list_del_init(>node); +else +list_add(>node, _list); +spin_unlock(_list_lock); } +if (nvme_create_queue(dev->queues[i], i)) break; } The above change was just error injection test code so you can cause a device to become unresponsive and trigger the timeout handling. Thanks, I'll take it off This latest is otherwise stable on my dev machine. I'm very happy to hear! -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Re: [PATCH v8] NVMe: convert to blk-mq
On Fri, 13 Jun 2014, Matias Bjørling wrote: This converts the current NVMe driver to utilize the blk-mq layer. static void nvme_reset_notify(struct pci_dev *pdev, bool prepare) { - struct nvme_dev *dev = pci_get_drvdata(pdev); + struct nvme_dev *dev = pci_get_drvdata(pdev); - if (prepare) - nvme_dev_shutdown(dev); - else - nvme_dev_resume(dev); + spin_lock(_list_lock); + if (prepare) + list_del_init(>node); + else + list_add(>node, _list); + spin_unlock(_list_lock); } + if (nvme_create_queue(dev->queues[i], i)) break; } The above change was just error injection test code so you can cause a device to become unresponsive and trigger the timeout handling. This latest is otherwise stable on my dev machine.
Re: [PATCH v8] NVMe: convert to blk-mq
On Fri, 13 Jun 2014, Matias Bjørling wrote: This converts the current NVMe driver to utilize the blk-mq layer. static void nvme_reset_notify(struct pci_dev *pdev, bool prepare) { - struct nvme_dev *dev = pci_get_drvdata(pdev); + struct nvme_dev *dev = pci_get_drvdata(pdev); - if (prepare) - nvme_dev_shutdown(dev); - else - nvme_dev_resume(dev); + spin_lock(dev_list_lock); + if (prepare) + list_del_init(dev-node); + else + list_add(dev-node, dev_list); + spin_unlock(dev_list_lock); } + if (nvme_create_queue(dev-queues[i], i)) break; } The above change was just error injection test code so you can cause a device to become unresponsive and trigger the timeout handling. This latest is otherwise stable on my dev machine.
Re: [PATCH v8] NVMe: convert to blk-mq
Den 16-06-2014 17:57, Keith Busch skrev: On Fri, 13 Jun 2014, Matias Bjørling wrote: This converts the current NVMe driver to utilize the blk-mq layer. static void nvme_reset_notify(struct pci_dev *pdev, bool prepare) { - struct nvme_dev *dev = pci_get_drvdata(pdev); +struct nvme_dev *dev = pci_get_drvdata(pdev); - if (prepare) - nvme_dev_shutdown(dev); - else - nvme_dev_resume(dev); +spin_lock(dev_list_lock); +if (prepare) +list_del_init(dev-node); +else +list_add(dev-node, dev_list); +spin_unlock(dev_list_lock); } +if (nvme_create_queue(dev-queues[i], i)) break; } The above change was just error injection test code so you can cause a device to become unresponsive and trigger the timeout handling. Thanks, I'll take it off This latest is otherwise stable on my dev machine. I'm very happy to hear! -- To unsubscribe from this list: send the line unsubscribe linux-kernel in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/