Re: NVMe Poll CQ on timeout

On Thu, Sep 19, 2019 at 01:47:50PM +, Bharat Kumar Gogada wrote: > Hi All, > > We are testing NVMe cards on ARM64 platform, the card uses MSI-X interrupts. > We are hitting following case in drivers/nvme/host/pci.c > /* > * Did we miss an interrupt? > */ > if

NVMe Poll CQ on timeout

Hi All, We are testing NVMe cards on ARM64 platform, the card uses MSI-X interrupts. We are hitting following case in drivers/nvme/host/pci.c /* * Did we miss an interrupt? */ if (__nvme_poll(nvmeq, req->tag)) { dev_warn(dev->ctrl.device,

RE: NVMe Poll CQ on timeout

> I recall we did observe issues like this when legacy interrupts were used, so > the driver does try to use MSI/MSIx if possible. > > The nvme_timeout() is called from the block layer when the driver didn't > provide a completion within the timeout (default is 30 seconds for IO, > 60 seconds for

RE: NVMe Poll CQ on timeout

> I recall we did observe issues like this when legacy interrupts were used, so > the driver does try to use MSI/MSIx if possible. > > The nvme_timeout() is called from the block layer when the driver didn't > provide a completion within the timeout (default is 30 seconds for IO, > 60 seconds for

Re: NVMe Poll CQ on timeout

On Mon, May 07, 2018 at 06:57:54AM +, Bharat Kumar Gogada wrote: > Hi, > > Does anyone have any inputs ? Hi, I recall we did observe issues like this when legacy interrupts were used, so the driver does try to use MSI/MSIx if possible. The nvme_timeout() is called from the block layer when

Re: NVMe Poll CQ on timeout

On Mon, May 07, 2018 at 06:57:54AM +, Bharat Kumar Gogada wrote: > Hi, > > Does anyone have any inputs ? Hi, I recall we did observe issues like this when legacy interrupts were used, so the driver does try to use MSI/MSIx if possible. The nvme_timeout() is called from the block layer when

RE: NVMe Poll CQ on timeout

Hi, Does anyone have any inputs ? Regards, Bharat > Hi, > > We are testing NVMe cards on ARM64 platform, the card uses legacy > interrupts. > Intermittently we are hitting following case in drivers/nvme/host/pci.c >/* > * Did we miss an interrupt? > */ > if

RE: NVMe Poll CQ on timeout

Hi, Does anyone have any inputs ? Regards, Bharat > Hi, > > We are testing NVMe cards on ARM64 platform, the card uses legacy > interrupts. > Intermittently we are hitting following case in drivers/nvme/host/pci.c >/* > * Did we miss an interrupt? > */ > if

NVMe Poll CQ on timeout

Hi, We are testing NVMe cards on ARM64 platform, the card uses legacy interrupts. Intermittently we are hitting following case in drivers/nvme/host/pci.c /* * Did we miss an interrupt? */ if (__nvme_poll(nvmeq, req->tag)) {

NVMe Poll CQ on timeout

Hi, We are testing NVMe cards on ARM64 platform, the card uses legacy interrupts. Intermittently we are hitting following case in drivers/nvme/host/pci.c /* * Did we miss an interrupt? */ if (__nvme_poll(nvmeq, req->tag)) {