search

intel / intel-cmt-cat

User space software for Intel(R) Resource Director Technology
http://www.intel.com/content/www/us/en/architecture-and-technology/resource-director-technology.html
Other
692 stars 182 forks source link

Error initializing PQoS library on AWS c5.metal/r5.metal instance #190

Closed SenRamakri closed 3 years ago

SenRamakri commented 3 years ago

I'm seeing the below error when trying to run "sudo pqos -s" on an AWS c5.metal instance. Is this a known issue? How can I get intel-cmt-cat working?

~$ sudo pqos -s NOTE: Mixed use of MSR and kernel interfaces to manage CAT or CMT & MBM may lead to unexpected behavior. API lock initialization error! Error initializing PQoS library!

The OS on that machine is Ubuntu 20.04.2 LTS(kernel version 5.4.0). And the CPU on that instance is Intel(R) Xeon(R) Platinum 8275CL CPU @ 3.00GHz. And I have verified that "msr" driver is loaded.

kmabbasi commented 3 years ago

Hi Ramakrishnan,

When pqos library initializes, it creates libpqos file in /var/lock directory. It looks like permission issue.

Can you check libpqos is present in /var/lock directory? if not, try below command to check permissions are ok.

sudo touch /var/lock/libpqos

Also can you confirm you are not using VM or container?

Thanks, Khawar

SenRamakri commented 3 years ago

Thanks for your response @kmabbasi Yes, the /var/lock/libpqos does exist. The permissions on that looks fine as well. And I'm not running a container or VM. I'm on a "c5.metal" bare-metal instance. I have tried this on r5.metal instance as well and see the same error.

kmabbasi commented 3 years ago

Would it be possible for you to try manually deleting that lock file and run pqos again?

Thanks, Khawar

SenRamakri commented 3 years ago

@kmabbasi - Deleting the lock file before running pqos seems to have fixed the problem. Now I see the below output when doing "sudo pqos -s". Thanks for your help with this issue.

NOTE: Mixed use of MSR and kernel interfaces to manage CAT or CMT & MBM may lead to unexpected behavior. L3CA/MBA COS definitions for Socket 0: L3CA COS0 => MASK 0x7ff L3CA COS1 => MASK 0x7ff L3CA COS2 => MASK 0x7ff L3CA COS3 => MASK 0x7ff L3CA COS4 => MASK 0x7ff L3CA COS5 => MASK 0x7ff L3CA COS6 => MASK 0x7ff L3CA COS7 => MASK 0x7ff L3CA COS8 => MASK 0x7ff L3CA COS9 => MASK 0x7ff L3CA COS10 => MASK 0x7ff L3CA COS11 => MASK 0x7ff L3CA COS12 => MASK 0x7ff L3CA COS13 => MASK 0x7ff L3CA COS14 => MASK 0x7ff L3CA COS15 => MASK 0x7ff MBA COS0 => 100% available MBA COS1 => 100% available MBA COS2 => 100% available MBA COS3 => 100% available MBA COS4 => 100% available MBA COS5 => 100% available MBA COS6 => 100% available MBA COS7 => 100% available ...

kmabbasi commented 3 years ago

I am glad, your issue has been resolved!

Thanks, Khawar