apcxi performance counter module using sys fs reads - #11
Open
cdsudheer9 wants to merge 17 commits into
Open
Conversation
apss: correct the duplicate declaration and correct the first APSS co…
correct the variable dereference
APSS: correcting the macro names
The node name format for OLCF Crusher is different from ALCF Polaris Only one slot in a chassis was populated and the topology spread with 10 groups on Polaris, where as Crusher nodes are populated in just 2 groups. Hence, the slots in the chassis are populated on Crusher. This necessitated change in the node coordinates.
The node names on Crusher use a custom notation, hence a mapping from the custom node names to HPE specific node names is required. HPE specific code names can be used to decipher the topology details.
Rename the HPE slingshot Cassini nic performance counter module as apcxi.
…le system reads The cassini nic performance counter module reads the nic performance counter module by reading from the sys file system First, the number of available nics on the compute node are determined by reading the number of directories in /sys/class/cxi/ The topology is discovered using the xnodename node name format on the HPE EX systems Only one rank/process per compute node is used to read and report the nic performance counters Each monitoring rank reads the counters predefined and configurable list of counters in apcxi/darshan-apcxi-log-format.h file. The counters from each of the available nics are read and reported.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
A different version of APCXI network performance counter module that relies on reading the counters directly from the SYS file system.
Thus, the dependency on the PAPI can be removed for this version of the library.