Re: [SPDK] SPDK perf starting I/O failed

* Re: [SPDK] SPDK perf starting I/O failed
@ 2017-08-21  2:32 Oza Oza
  0 siblings, 0 replies; 10+ messages in thread
From: Oza Oza @ 2017-08-21  2:32 UTC (permalink / raw)
  To: spdk

[-- Attachment #1: Type: text/plain, Size: 3932 bytes --]

That’s great, Lance,

I possible, can you please post the patch, because I have to backport it on
older version of SPDK.

Regards,

Oza.

*From:* SPDK [mailto:spdk-bounces(a)lists.01.org] *On Behalf Of *Lance
Hartmann ORACLE
*Sent:* Saturday, August 19, 2017 8:40 PM
*To:* Storage Performance Development Kit
*Subject:* Re: [SPDK] SPDK perf starting I/O failed

Thanks Paul.  I’m trying to get on a system this morning where we have an
NVMoF configuration so that I can sanity-check that my fix operates okay in
that environment too.

--

Lance Hartmann
lance.hartmann(a)oracle.com

On Aug 19, 2017, at 10:02 AM, Luse, Paul E <paul.e.luse(a)intel.com> wrote:

Excellent! Reach out if you have any problems getting a patch going….

Thx

Paul

*From:* SPDK [mailto:spdk-bounces(a)lists.01.org <spdk-bounces(a)lists.01.org>] *On
Behalf Of *Lance Hartmann ORACLE
*Sent:* Saturday, August 19, 2017 7:50 AM
*To:* Storage Performance Development Kit <spdk(a)lists.01.org>
*Subject:* Re: [SPDK] SPDK perf starting I/O failed

I have a fix for this.  I haven’t tested it yet with NVMoF, but have it
working for NVMe.

--
Lance Hartmann
lance.hartmann(a)oracle.com

On Aug 18, 2017, at 9:12 AM, Luse, Paul E <paul.e.luse(a)intel.com> wrote:

Hi Oza,

If nobody else resolves this soon, I’ll try and repro on my end here in a
few hours.  Have some things to wrap up first

Thx

Paul

*From:* SPDK [mailto:spdk-bounces(a)lists.01.org <spdk-bounces(a)lists.01.org>] *On
Behalf Of *Oza Oza
*Sent:* Thursday, August 17, 2017 11:13 PM
*To:* Storage Performance Development Kit <spdk(a)lists.01.org>
*Subject:* [SPDK] SPDK perf starting I/O failed

Hi All,

SPDK perf test queue size more than 8187 fails.

Test procedure:
1. Increase the number of huge pages to 4096 - that means total huge page
memory reserved is 4096 * 2048KB. that means 8GB
$echo 4096 >/proc/sys/vm/nr_hugepages
2. Run the perf test with queue size as 8188 (or above) and DPDK memory
allocation to be around 6GB.
/usr/share/spdk/examples/nvme/perf -r 'trtype:PCIe traddr:0001:01:00.0' -q
8188 -s 2048 -w read -d 6144 -t 30 -c 0x1
3. Observer the test fails at "spdk_nvme_ns_cmd_read" for one request. (it
seems 8187 requests succeeds, any number above that fails
4. Observe the aplication also hangs
5. run the same test with queue size as 8187 and observe the test passes
/usr/share/spdk/examples/nvme/perf -r 'trtype:PCIe traddr:0001:01:00.0' -q
8187 -s 2048 -w read -d 6144 -t 30 -c 0x1

THE COMMAND OUTPUT IS:
root(a)bcm958742t:~# /usr/share/spdk/examples/nvme/perf -r 'trtype:PCIe
traddr:0001:01:00.0' -q 8188 -s 2048 -w read -d 6144 -t 30 -c 0x1
Starting DPDK 16.11.1 initialization...
[ DPDK EAL parameters: perf -c 1 -m 6144 --file-prefix=spdk_pid10557 ]
EAL: Detected 8 lcore(s)
EAL: Probing VFIO support...
EAL: VFIO support initialized
EAL: cannot open /proc/self/numa_maps, consider that all memory is in
socket_id 0
Initializing NVMe Controllers
EAL: PCI device 0001:01:00.0 on NUMA socket 0
EAL: probe driver: 8086:953 spdk_nvme
EAL: using IOMMU type 1 (Type 1)
[151516.159960] vfio-pci 0001:01:00.0: enabling device (0400 -> 0402)
[151516.272405] vfio_ecap_init: 0001:01:00.0 hiding ecap 0x19(a)0x2a0
Attaching to NVMe Controller at 0001:01:00.0 [8086:0953]
Attached to NVMe Controller at 0001:01:00.0 [8086:0953]
Associating INTEL SSDPEDMW400G4 (CVCQ6433008P400AGN ) with lcore 0
Initialization complete. Launching workers.
Starting thread on core 0
starting I/O failed

Regards,

Oza.

_______________________________________________
SPDK mailing list
SPDK(a)lists.01.org
https://lists.01.org/mailman/listinfo/spdk

_______________________________________________
SPDK mailing list
SPDK(a)lists.01.org
https://lists.01.org/mailman/listinfo/spdk

[-- Attachment #2: attachment.html --]
[-- Type: text/html, Size: 19499 bytes --]

^ permalink raw reply	[flat|nested] 10+ messages in thread