Skip to contentSkip to conversation

appropriate timeout values in bdev_nvme_set_options for failover tests

SPDK lullajd at yahoo.com 1 participant 2 messages Nov 12, 2021

lore
Share & tools
lore

lullajd at yahoo.com

#0 lore raw

Hi,

This is about the case where initiator is using spdk.

For testing nvmeof/TCP failover (cold primary/backup) I am trying to use the following timeout values but they don't seem to help:

{
"subsystems": [

    { 
      "subsystem": "bdev",
      "config": [
        {
        "method": "bdev_nvme_set_options", "params": {
	    "retry_count": 254,
            "timeout_us": 255000000,
	    "keep_alive_timeout_ms": 255000, 
	    "transport_retry_count": 254,
	    "bdev_retry_count": -1,
            "nvme_adminq_poll_period_us": 100000,
            "nvme_ioq_poll_period_us": 0,

In my test, when the IO has started, after some time, I am making the primary network path to the nvme device (nvmeof + tcp) unavailable. I expect the secondary path to become active and the IO must resume.

Without spdk (ie when I use the kernel drivers on linux), the path switchover on initiator takes ~45 seconds and the IO resumes.

I suspect something wrong in the timeout values above when trying with spdk.

Could somebody please suggest more appropriate values for the above timeouts? And also please point out if something else also need to be corrected above?

thanks
Jitendra

#1 lore raw

Hi Jitendra,

When we use bdev_nvme_attach_controller with multipath="failover", I/O path is recovered but I/O is failed immediately if I/O path error occurred.

Will you try using bdev_nvme_attach_controller with multipath="multipath"? Please keep opts->bdev_retry_count to be -1 as you did.

P.S.,

multipath="multipath" is still under development, and your experiment is very appreaciated if possible.

Thanks,
Shuhei

________________________________
差出人: lullajd(a)yahoo.com <lullajd(a)yahoo.com>
送信日時: 2021年11月12日 14:06
宛先: spdk(a)lists.01.org <spdk(a)lists.01.org>
件名: [SPDK] appropriate timeout values in bdev_nvme_set_options for failover tests

Hi,

This is about the case where initiator is using spdk.

For testing nvmeof/TCP failover (cold primary/backup) I am trying to use the following timeout values but they don't seem to help:

{
"subsystems": [

    {
      "subsystem": "bdev",
      "config": [
        {
        "method": "bdev_nvme_set_options", "params": {
            "retry_count": 254,
            "timeout_us": 255000000,
            "keep_alive_timeout_ms": 255000,
            "transport_retry_count": 254,
            "bdev_retry_count": -1,
            "nvme_adminq_poll_period_us": 100000,
            "nvme_ioq_poll_period_us": 0,

In my test, when the IO has started, after some time, I am making the primary network path to the nvme device (nvmeof + tcp) unavailable. I expect the secondary path to become active and the IO must resume.

Without spdk (ie when I use the kernel drivers on linux), the path switchover on initiator takes ~45 seconds and the IO resumes.

I suspect something wrong in the timeout values above when trying with spdk.

Could somebody please suggest more appropriate values for the above timeouts? And also please point out if something else also need to be corrected above?

thanks
Jitendra
_______________________________________________
SPDK mailing list -- spdk(a)lists.01.org
To unsubscribe send an email to spdk-leave(a)lists.01.org