Note: This bug is displayed in read-only format because
the product is no longer active in Red Hat Bugzilla.
RHEL Engineering is moving the tracking of its product development work on RHEL 6 through RHEL 9 to Red Hat Jira (issues.redhat.com). If you're a Red Hat customer, please continue to file support cases via the Red Hat customer portal. If you're not, please head to the "RHEL project" in Red Hat Jira and file new tickets here. Individual Bugzilla bugs in the statuses "NEW", "ASSIGNED", and "POST" are being migrated throughout September 2023. Bugs of Red Hat partners with an assigned Engineering Partner Manager (EPM) are migrated in late September as per pre-agreed dates. Bugs against components "kernel", "kernel-rt", and "kpatch" are only migrated if still in "NEW" or "ASSIGNED". If you cannot log in to RH Jira, please consult article #7032570. That failing, please send an e-mail to the RH Jira admins at rh-issues@redhat.com to troubleshoot your issue as a user management inquiry. The email creates a ServiceNow ticket with Red Hat. Individual Bugzilla bugs that are migrated will be moved to status "CLOSED", resolution "MIGRATED", and set with "MigratedToJIRA" in "Keywords". The link to the successor Jira issue will be found under "Links", have a little "two-footprint" icon next to it, and direct you to the "RHEL project" in Red Hat Jira (issue links are of type "https://issues.redhat.com/browse/RHEL-XXXX", where "X" is a digit). This same link will be available in a blue banner at the top of the page informing you that that bug has been migrated.
Currently, if you use the -t option without an argument cyclictest presumes that it should put a measurement thread on every online cpu. This is the original logic, which is to test the entire system.
The alternative is to use -t<n> and -a<cpulist> to create <n> measurement threads and affine them to <cpulist>. One complaint I have about this is that no matter where you place the measurement threads, they're labeled 0-(n-1) in the output, so it makes it hard to map a test thread back to the cpu where it ran. Wondering if we can update the output to show the core to which a test thread is bound.
I'm also wondering if we can add a third option to say "just use the cores in your current cpu affinity mask". That way you can rejigger the tuning parameters for a system and then just kick off cyclictest without having to figure out how your -a/-t options should change to match.
I'm thinking where we've diddled the isolcpus= boot parameter and want to try cyclictest over there like this:
# presumes isolcpus=0,12
taskset --cpus=0,12 cyclictest -p95 -mn --affinity-mask
So that we'd get two measurment threads, affine to cpus 0 and 12. I realize that we could do this with '-t2 -a0,12' but I was hoping to simplify things.
Currently, if you use the -t option without an argument cyclictest presumes that it should put a measurement thread on every online cpu. This is the original logic, which is to test the entire system. The alternative is to use -t<n> and -a<cpulist> to create <n> measurement threads and affine them to <cpulist>. One complaint I have about this is that no matter where you place the measurement threads, they're labeled 0-(n-1) in the output, so it makes it hard to map a test thread back to the cpu where it ran. Wondering if we can update the output to show the core to which a test thread is bound. I'm also wondering if we can add a third option to say "just use the cores in your current cpu affinity mask". That way you can rejigger the tuning parameters for a system and then just kick off cyclictest without having to figure out how your -a/-t options should change to match. I'm thinking where we've diddled the isolcpus= boot parameter and want to try cyclictest over there like this: # presumes isolcpus=0,12 taskset --cpus=0,12 cyclictest -p95 -mn --affinity-mask So that we'd get two measurment threads, affine to cpus 0 and 12. I realize that we could do this with '-t2 -a0,12' but I was hoping to simplify things.