Skip to content
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.

Sign up for GitHub

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

Jump to bottom

DAOS-15204 cart: add crt_perf utils #13825

Draft
wants to merge 7 commits into
base: master
Choose a base branch
from
Draft

DAOS-15204 cart: add crt_perf utils #13825

wants to merge 7 commits into from

Conversation

soumagne
Copy link
Collaborator

Before requesting gatekeeper:

  • Two review approvals and any prior change requests have been resolved.
  • Testing is complete and all tests passed or there is a reason documented in the PR why it should be force landed and forced-landing tag is set.
  • Features: (or Test-tag*) commit pragma was used or there is a reason documented that there are no appropriate tags for this PR.
  • Commit messages follows the guidelines outlined here.
  • Any tests skipped by the ticket being addressed have been run and passed in the PR.

Gatekeeper:

  • You are the appropriate gatekeeper to be landing the patch.
  • The PR has 2 reviews by people familiar with the code, including appropriate owners.
  • Githooks were used. If not, request that user install them and check copyright dates.
  • Checkpatch issues are resolved. Pay particular attention to ones that will show up on future PRs.
  • All builds have passed. Check non-required builds for any new compiler warnings.
  • Sufficient testing is done. Check feature pragmas and test tags and that tests skipped for the ticket are run and now pass with the changes.
  • If applicable, the PR has addressed any potential version compatibility issues.
  • Check the target branch. If it is master branch, should the PR go to a feature branch? If it is a release branch, does it have merge approval in the JIRA ticket.
  • Extra checks if forced landing is requested
    • Review comments are sufficiently resolved, particularly by prior reviewers that requested changes.
    • No new NLT or valgrind warnings. Check the classic view.
    • Quick-build or Quick-functional is not used.
  • Fix the commit message upon landing. Check the standard here. Edit it to create a single commit. If necessary, ask submitter for a new summary.

@github-actions GitHub Actions
Copy link

Bug-tracker data:
Ticket title is 'Add crt_perf utilities'
Status is 'In Progress'
https://daosio.atlassian.net/browse/DAOS-15204

@daosbuild1
Copy link
Collaborator

Test stage Build on EL 8 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/1/execution/node/376/log

@daosbuild1
Copy link
Collaborator

Test stage Build on Leap 15.5 with Intel-C and TARGET_PREFIX completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/1/execution/node/383/log

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on Leap 15.5 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/1/execution/node/305/log

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on EL 8 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/1/execution/node/361/log

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on EL 9 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/1/execution/node/349/log

@daosbuild1
Copy link
Collaborator

Test stage Build DEB on Ubuntu 20.04 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/1/execution/node/327/log

@github-actions GitHub Actions
Copy link

Bug-tracker data:
Ticket title is 'Add crt_perf utilities'
Status is 'In Progress'
https://daosio.atlassian.net/browse/DAOS-15204

@daosbuild1
Copy link
Collaborator

Test stage Build on EL 8 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/2/execution/node/295/log

@daosbuild1
Copy link
Collaborator

Test stage Build on Leap 15.5 with Intel-C and TARGET_PREFIX completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/2/execution/node/380/log

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on Leap 15.5 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/2/execution/node/278/log

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on EL 8 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/2/execution/node/370/log

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on EL 9 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/2/execution/node/383/log

@github-actions GitHub Actions
Copy link

Bug-tracker data:
Ticket title is 'Add crt_perf utilities'
Status is 'In Progress'
https://daosio.atlassian.net/browse/DAOS-15204

@daosbuild1
Copy link
Collaborator

Test stage Build DEB on Ubuntu 20.04 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/2/execution/node/324/log

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on Leap 15.5 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/3/execution/node/287/log

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on EL 9 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/3/execution/node/310/log

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on EL 8 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/3/execution/node/315/log

@daosbuild1
Copy link
Collaborator

Test stage Build DEB on Ubuntu 20.04 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/3/execution/node/344/log

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on EL 8 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/4/execution/node/383/log

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on Leap 15.5 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/4/execution/node/378/log

@daosbuild1
Copy link
Collaborator

Test stage Build DEB on Ubuntu 20.04 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/4/execution/node/322/log

@github-actions GitHub Actions
Copy link

Bug-tracker data:
Ticket title is 'Add crt_perf utilities'
Status is 'In Progress'
https://daosio.atlassian.net/browse/DAOS-15204

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on EL 9 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/4/execution/node/377/log

@github-actions GitHub Actions
Copy link

Bug-tracker data:
Ticket title is 'Add crt_perf utilities'
Status is 'In Progress'
https://daosio.atlassian.net/browse/DAOS-15204

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on EL 9 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/5/execution/node/363/log

@daosbuild1
Copy link
Collaborator

Test stage Build RPM on Leap 15.5 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/5/execution/node/278/log

@github-actions GitHub Actions
Copy link

Bug-tracker data:
Ticket title is 'Add crt_perf utilities'
Status is 'In Progress'
https://daosio.atlassian.net/browse/DAOS-15204

frostedcmos
frostedcmos reviewed Mar 20, 2024
View reviewed changes
src/utils/crt_perf/crt_bw_read.c
CRT_PERF_CHECK_D_ERROR(error, rc, "could not create request");

in_struct = crt_req_get(request->rpc);
in_struct->handle_id =
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

a comment here would help to explain what you are doing:)

src/utils/crt_perf/crt_bw_write.c
/*******************/

static int
crt_perf_run(const struct crt_perf_info *perf_info, struct crt_perf_context_info *info,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

it looks like crt_perf_run() implementations in most tests is very similar with the main difference being how input args are populated. any way to move this into crt_perf.c perhaps and pass it a function/cb to populate args instead?

src/utils/crt_perf/crt_perf.h
Comment on lines +108 to +110
#define CRT_PERF_LAT_SKIP_SMALL 100
#define CRT_PERF_LAT_SKIP_LARGE 10
#define CRT_PERF_LARGE_SIZE 8192
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

would help to explain those, i dont quite understand what they mean by just reading them

src/utils/crt_perf/crt_perf.c
sizeof(uri_name) * info->mpi_info.size);

rc = crt_perf_mpi_allgather(&info->mpi_info, uri_name, sizeof(uri_name), uri_list,
sizeof(uri_name));
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

hmm.. shoudnt the last arg here be sizeof(uri_name) * info->mpi_info.size?

src/utils/crt_perf/crt_perf.c
Comment on lines +516 to +520
char *rank_uri = uri_list + rank * sizeof(uri_name);

if (rank == info->mpi_info.rank)
continue; /* our rank is already added */

rc = crt_group_primary_rank_add(info->context_info[0].context, NULL, rank,
rank_uri);
CRT_PERF_CHECK_D_ERROR(error, rc, "could not add rank %d %s", rank,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

you can also use crt_group_primary_modify() and add all ranks and uris in a bulk if you want to avoid the loop

src/utils/crt_perf/crt_perf.c
rc = crt_init_opt(listen ? CRT_PERF_GROUP_ID : NULL, crt_init_flags, &crt_init_options);
CRT_PERF_CHECK_D_ERROR(error, rc, "could not init CART");

if (attach_info_path) {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

from past experience might be helpful to debug/info print the attach info path

src/utils/crt_perf/crt_perf.c
CRT_PERF_CHECK_ERROR(cb_info->cci_rc != 0, out, info->rc, cb_info->cci_rc,
"callback failed");

if (info->cb) {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

surprised checkpatch doesnt complain about single statement being wrapped in { } 's

@github-actions GitHub Actions
Copy link

Ticket title is 'Add crt_perf utilities'
Status is 'In Progress'
https://daosio.atlassian.net/browse/DAOS-15204

@daosbuild1
Copy link
Collaborator

Test stage Unit Test on EL 8.8 completed with status UNSTABLE. https://build.hpdd.intel.com/job/daos-stack/job/daos//view/change-requests/job/PR-13825/7/testReport/

@daosbuild1
Copy link
Collaborator

Test stage Unit Test with memcheck on EL 8.8 completed with status UNSTABLE. https://build.hpdd.intel.com/job/daos-stack/job/daos//view/change-requests/job/PR-13825/7/testReport/

@soumagne soumagne force-pushed the soumagne/crt_perf branch 3 times, most recently from 434c1ca to 9bbc837 Compare September 24, 2024 21:35
@daosbuild1
Copy link
Collaborator

Test stage NLT on EL 8.8 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/11/execution/node/816/log

frostedcmos
frostedcmos reviewed Oct 17, 2024
View reviewed changes
src/cart/SConscript
Comment on lines +78 to +90
# compiler = env.get('COMPILER').lower()
# if compiler != 'covc':
# pp_env = denv.Clone()
# pp_files = []
# for src in SRC:
# # Some day, the preprocess builder should be fixed so it can do multiple commands
# # in parallel but until then, just submit them one at a time
# pp_files.extend(pp_env.Preprocess(src))
# parsed_files = parse_pp(pp_env, pp_files)
# header = consolidate_pp(pp_env, parsed_files)

# Depends(cart_targets, header)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

while its annoying, some people use post-processed headers in their IDE. i think ideally this should be done via a flag/env/scons option

src/cart/crt_internal_types.h
@@ -150,6 +150,8 @@ struct crt_gdata {
unsigned int cg_provider_is_primary : 1;
/** use legacy progress method */
bool cg_progress_legacy;
/** use single thread to access context */
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

might want to add new field to be dumped in crt_gdata_dump(void). even though we dump envs automatically, someone might set new field via init_opt, and would be good to see that in logs.

@soumagne
DAOS-15204 cart: fix thread-safety in threaded test
aec4c65 
Required-githooks: true

Signed-off-by: Jerome Soumagne <[email protected]>
@soumagne
DAOS-15204 cart: disable intermediate preprocessor build
424abb2 
Required-githooks: true

Signed-off-by: Jerome Soumagne <[email protected]>
@soumagne
DAOS-15204 cart: switch to new event-based progress methods
17b18ff 
add crt_hg_event_progress() and query wait fd from context

add D_PROGRESS_LEGACY to revert to old progress

Required-githooks: true

Signed-off-by: Jerome Soumagne <[email protected]>
@soumagne
DAOS-15204 cart: switch RPC timeout to use timespec deadlines
184a3ae 
Avoid reacquiring time and use coarse clock

Required-githooks: true

Signed-off-by: Jerome Soumagne <[email protected]>
@soumagne
DAOS-11516 cart: relax progress thread safety using thread mode
7e828e0 
Required-githooks: true

Signed-off-by: Jerome Soumagne <[email protected]>
@soumagne
DAOS-15204 cart: add crt_perf utils
c8469ba 
Add crt_rate / crt_perf_server executables. CRT perf utils can be run
with and without MPI support. MPI support is automatically detected.

Add crt_bw_read/write benchmarks.

Required-githooks: true

Signed-off-by: Jerome Soumagne <[email protected]>
@soumagne
DAOS-15204 build: add crt_perf to packaging
10fbe20 
Required-githooks: true

Signed-off-by: Jerome Soumagne <[email protected]>
@daosbuild1
Copy link
Collaborator

Test stage NLT on EL 8.8 completed with status FAILURE. https://build.hpdd.intel.com//job/daos-stack/job/daos/view/change-requests/job/PR-13825/12/execution/node/804/log

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@frostedcmos frostedcmos frostedcmos left review comments

At least 2 approving reviews are required to merge this pull request.

Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@soumagne @daosbuild1 @frostedcmos