-
Notifications
You must be signed in to change notification settings - Fork 310
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
DAOS-17006 cart: Publish Mercury counters as metrics #15870
Conversation
Ticket title is 'Expose Mercury perf counters as DAOS metrics' |
Test stage NLT on EL 8.8 completed with status UNSTABLE. https://build.hpdd.intel.com/job/daos-stack/job/daos//view/change-requests/job/PR-15870/1/testReport/ |
4a68150
to
5d5e6e1
Compare
Test stage NLT on EL 8.8 completed with status UNSTABLE. https://build.hpdd.intel.com/job/daos-stack/job/daos//view/change-requests/job/PR-15870/2/testReport/ |
Test stage Functional on EL 8.8 completed with status UNSTABLE. https://build.hpdd.intel.com/job/daos-stack/job/daos//view/change-requests/job/PR-15870/2/testReport/ |
5d5e6e1
to
44c2e8e
Compare
@soumagne: FYI... Do you see any major problems with the approach? I think the additional overhead for this should be pretty small. |
Test stage NLT on EL 8.8 completed with status UNSTABLE. https://build.hpdd.intel.com/job/daos-stack/job/daos//view/change-requests/job/PR-15870/3/testReport/ |
91c22aa
to
310ee3e
Compare
I think that looks good to me, thanks! Right there should not be any significant overhead. |
When Mercury has been built with diagnostic RPC counters enabled, CaRT will periodically republish the counters as DAOS telemetry for consumption by monitoring infrastructure. Features: telemetry Skip-nlt: true Change-Id: I3b0bcb260ad970798ac1cd838f8469c4cfbede55 Signed-off-by: Michael MacDonald <mjmac@google.com>
310ee3e
to
f6758a6
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Based on the skype discussions I was under the impression that we also require 'reset counters' call to be performed after each query -- is the plan different now on how counters will be consumed in the end?
One other comment inline.
LGTM otherwise.
We don't need to reset the counters. There was a misunderstanding about what was needed to re-export the mercury diagnostics via DAOS metrics. |
Test stage Functional on EL 8.8 completed with status UNSTABLE. https://build.hpdd.intel.com/job/daos-stack/job/daos//view/change-requests/job/PR-15870/6/testReport/ |
* convert active_rpcs metric to gauge * remove debug repub_count metrics from ftest Features: telemetry Skip-nlt: true Change-Id: I44d2528f5d3fc55069cfc66f2fb387723d3b8c81 Signed-off-by: Michael MacDonald <mjmac@google.com>
Allow-unstable-test: true Features: telemetry Change-Id: I0232d0da8007374fd1d28d395c65544c7fa57bc1 Signed-off-by: Jeff Olivier <jeffolivier@google.com>
Test stage NLT on EL 8.8 completed with status UNSTABLE. https://build.hpdd.intel.com/job/daos-stack/job/daos//view/change-requests/job/PR-15870/8/testReport/ |
When Mercury has been built with diagnostic RPC counters enabled, CaRT will periodically republish the counters as DAOS telemetry for consumption by monitoring infrastructure. NB: Requires Mercury > 2.4.0. Change-Id: I0232d0da8007374fd1d28d395c65544c7fa57bc1 Signed-off-by: Michael MacDonald <mjmac@google.com> Co-authored-by: Jeff Olivier <jeffolivier@google.com>
When Mercury has been built with diagnostic RPC counters enabled, CaRT will periodically republish the counters as DAOS telemetry for consumption by monitoring infrastructure. NB: Requires Mercury > 2.4.0. Change-Id: I0232d0da8007374fd1d28d395c65544c7fa57bc1 Signed-off-by: Michael MacDonald <mjmac@google.com> Co-authored-by: Jeff Olivier <jeffolivier@google.com>
When Mercury has been built with diagnostic RPC counters enabled, CaRT will periodically republish the counters as DAOS telemetry for consumption by monitoring infrastructure. NB: Requires Mercury > 2.4.0. Change-Id: I0232d0da8007374fd1d28d395c65544c7fa57bc1 Signed-off-by: Michael MacDonald <mjmac@google.com> Co-authored-by: Jeff Olivier <jeffolivier@google.com> Co-authored-by: Nicholas Murphy <ncmurphy@google.com>
When Mercury has been built with diagnostic RPC counters enabled, CaRT will periodically republish the counters as DAOS telemetry for consumption by monitoring infrastructure. NB: Requires Mercury > 2.4.0. Change-Id: I0232d0da8007374fd1d28d395c65544c7fa57bc1 Signed-off-by: Michael MacDonald <mjmac@google.com> Co-authored-by: Jeff Olivier <jeffolivier@google.com> Co-authored-by: Nicholas Murphy <ncmurphy@google.com>
When Mercury has been built with diagnostic RPC counters enabled, CaRT will periodically republish the counters as DAOS telemetry for consumption by monitoring infrastructure. NB: Requires Mercury > 2.4.0. Signed-off-by: Michael MacDonald <mjmac@google.com> Co-authored-by: Jeff Olivier <jeffolivier@google.com> Co-authored-by: Nicholas Murphy <ncmurphy@google.com>
When Mercury has been built with diagnostic RPC counters
enabled, CaRT will periodically republish the counters as DAOS
telemetry for consumption by monitoring infrastructure.
Change-Id: I3b0bcb260ad970798ac1cd838f8469c4cfbede55
Signed-off-by: Michael MacDonald mjmac@google.com