DAOS-17322 ddb: DTX aggregation with ddb (Part 1) by knard38 · Pull Request #16745 · daos-stack/daos

knard38 · 2025-08-18T08:04:17Z

Description

First PR to add DTX entries aggregation sub commands to DDB.

This preliminary PR introduce the following modifications:

Cleanup of the SCons file src/utils/ddb/tests/SConscript
Fix miscellaneous issues detected by clangd linter.
Add a new DDB sub command dtx_stat allowing to print statistics on DTX entries.

This PR will be followed by the PR #16746 introducing a new DDB sub command dtx_aggr allowing to aggregate DTX entries with DDB.

Steps for the author:

Commit message follows the guidelines.
Appropriate Features or Test-tag pragmas were used.
Appropriate Functional Test Stages were run.
At least two positive code reviews including at least one code owner from each category referenced in the PR.
Testing is complete. If necessary, forced-landing label added and a reason added in a comment.

After all prior steps are complete:

Gatekeeper requested (daos-gatekeeper added as a reviewer).

Cleanup of SCons file. Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

Miscellaneous fixes detected by clangd. Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

Add the following new command to ddb: - dtx_stat: Print statistics on DTX entries Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

github-actions · 2025-08-18T08:04:35Z

Ticket title is 'DTX aggregation with ddb'
Status is 'In Review'
Labels: '2.8pp'
https://daosio.atlassian.net/browse/DAOS-17322

Nasf-Fan · 2025-08-23T01:36:43Z

+		Name:      "dtx_stat",
+		Aliases:   nil,
+		Help:      "Stat on DTX entries",
+		LongHelp:  "Print statistic on the DTX entries",


Can we print the DTX statistics information like that:
if container UUID is specified in the path, then for the container; otherwise, if only pool UUID is available, then for the DTX summary of the pool or every container's DTX statistics information in the pool.

Print stat for all containers.

Print stat for all containers.

Fixed with commit 2b72e15

Nasf-Fan · 2025-08-23T01:36:56Z

+	if (strftime(buf, buf_size, "%F %T", &date) == 0)
+		return -DER_INVAL;
+
+	buf_len = strnlen(buf, buf_size);


buflen = strftime(); if (buflen == 0) return -DER_INVAL;

Remove useless strlen

Remove useless strlen

Fixed with commit 983d9d4

Nasf-Fan · 2025-08-23T01:37:52Z

+	if (!SUCCESS(rc))
+		goto done;
+
+	if (!itp_has_cont(&itp)) {


It is better to support that: if only specify pool UUID, then iterate the containers in the pool and print each container's DTX statistics information. One benefit for such ability is that we can verify whether the count of the total DTX entries for pool can match the summary of all containers' or not.

Print stat for all containers.

Fixed with commit 2b72e15

Nasf-Fan · 2025-08-23T01:38:40Z

+	if (!SUCCESS(rc))
+		goto done;
+
+	rc = vos_dtx_cmt_reindex(coh);


If we just want to obtain the committed DTX entries statistics information, it is unnecessary to reindex them. vos_dtx_cmt_reindex() is time consuming operation. Instead, we can iterate each vos_dtx_blob_df and summary the vos_dtx_blob_df::dbd_count. That is more efficient.

Replace vos_dtx_cmt_reindex() with iterate on vos_dtx_blob_df

Replace vos_dtx_cmt_reindex() with iterate on vos_dtx_blob_df

Fixed with commit 3ff2b3a

Nasf-Fan · 2025-08-23T01:43:16Z

+int
+ddb_date2epoch(const char *date, uint64_t *epoch)
+{
+	struct tm       date_tm;


struct tm date_tm = {0}; then no need memset();

Use static initialisation instead of explicit initialisation.

Use static initialisation instead of explicit initialisation.

Fixed with commit 983d9d4

Nasf-Fan · 2025-08-23T02:19:41Z

+			D_ALLOC_ARRAY(_buf, _buf_size);                                            \
+			assert_non_null(_buf);                                                     \
+			regerror(_rc, &_preg, _buf, _buf_size);                                    \
+			if (_buf)                                                                  \


You have assert assert_non_null(_buf);

Remove useless test

Fixed with commit 983d9d4

@Nasf-Fan , at the end this test is needed to manage gcc false positive warning.

[2025-09-11T18:30:29.037Z] In file included from src/utils/ddb/tests/ddb_commands_tests.c:21: [2025-09-11T18:30:29.037Z] src/utils/ddb/tests/ddb_commands_tests.c: In function ‘dtx_stat_tests’: [2025-09-11T18:30:29.037Z] src/utils/ddb/tests/ddb_cmocka.h:89:25: error: ‘%s’ directive argument is null [-Werror=format-overflow=] [2025-09-11T18:30:29.038Z] 89 | print_error("ERROR: invalid regex '%s': %s\n", regex, _buf); \ [2025-09-11T18:30:29.038Z] | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [2025-09-11T18:30:29.038Z] src/utils/ddb/tests/ddb_commands_tests.c:422:9: note: in expansion of macro ‘assert_regex_match’ [2025-09-11T18:30:29.038Z] 422 | assert_regex_match( [2025-09-11T18:30:29.038Z] | ^~~~~~~~~~~~~~~~~~ [2025-09-11T18:30:29.038Z] src/utils/ddb/tests/ddb_cmocka.h:89:65: note: format string is defined here [2025-09-11T18:30:29.038Z] 89 | print_error("ERROR: invalid regex '%s': %s\n", regex, _buf); \

More details could be found in the log of the PR build #5
This test was reintroduced with the commit 7c96b6a

Nasf-Fan · 2025-08-23T02:19:44Z

+			if (_buf)                                                                  \
+				print_error("ERROR: invalid regex '%s': %s\n", regex, _buf);       \
+			D_FREE(_buf);                                                              \
+			regfree(&_preg);                                                           \


If regcomp() return failure, then _preg maybe uninitialized?

fix invalid regfree()

fix invalid regfree()

Fixed with commit 77e3c21

kjacque

Only looked at the Go side in detail. LGTM.

…/daos-17322-part1

Integrate reviewers comments: - Remove useless test - Remove useless strlen - Use static initialisation instead of explicit initialisation. Features: aggregation Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

daosbuild3 · 2025-09-10T09:02:10Z

Test stage Build RPM on EL 9 completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net//job/daos-stack/job/daos/view/change-requests/job/PR-16745/2/execution/node/350/log

daosbuild3 · 2025-09-10T09:02:48Z

Test stage Build on EL 9 completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net//job/daos-stack/job/daos/view/change-requests/job/PR-16745/2/execution/node/418/log

daosbuild3 · 2025-09-10T09:09:47Z

Test stage Build RPM on EL 8 completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net//job/daos-stack/job/daos/view/change-requests/job/PR-16745/2/execution/node/386/log

daosbuild3 · 2025-09-10T09:10:36Z

Test stage Build RPM on Leap 15.5 completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net//job/daos-stack/job/daos/view/change-requests/job/PR-16745/2/execution/node/385/log

Integrate reviewers comments: - fix invalid regfree() Features: aggregation Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

daosbuild3 · 2025-09-10T09:17:42Z

Test stage Build on EL 9 completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net//job/daos-stack/job/daos/view/change-requests/job/PR-16745/3/execution/node/404/log

daosbuild3 · 2025-09-10T09:18:38Z

Test stage Build RPM on EL 9 completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net//job/daos-stack/job/daos/view/change-requests/job/PR-16745/3/execution/node/416/log

daosbuild3 · 2025-09-10T09:24:32Z

Test stage Build RPM on EL 8 completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net//job/daos-stack/job/daos/view/change-requests/job/PR-16745/3/execution/node/347/log

daosbuild3 · 2025-09-10T09:25:48Z

Test stage Build RPM on Leap 15.5 completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net//job/daos-stack/job/daos/view/change-requests/job/PR-16745/3/execution/node/421/log

daosbuild3 · 2025-09-16T14:29:17Z

Test stage Unit Test with memcheck on EL 8.8 completed with status UNSTABLE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net/job/daos-stack/job/daos//view/change-requests/job/PR-16745/9/testReport/

daosbuild3 · 2025-09-16T16:03:18Z

Test stage Unit Test bdev with memcheck on EL 8.8 completed with status UNSTABLE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net/job/daos-stack/job/daos//view/change-requests/job/PR-16745/9/testReport/

…/daos-17322-part1 Features: aggregation

daosbuild3 · 2025-09-16T20:25:29Z

Test stage Unit Test on EL 8.8 completed with status UNSTABLE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net/job/daos-stack/job/daos//view/change-requests/job/PR-16745/10/testReport/

daosbuild3 · 2025-09-16T20:42:55Z

Test stage NLT on EL 8.8 completed with status UNSTABLE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net/job/daos-stack/job/daos//view/change-requests/job/PR-16745/10/testReport/

daosbuild3 · 2025-09-16T21:00:14Z

Test stage Unit Test with memcheck on EL 8.8 completed with status UNSTABLE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net/job/daos-stack/job/daos//view/change-requests/job/PR-16745/10/testReport/

daosbuild3 · 2025-09-16T22:46:37Z

Test stage Unit Test bdev with memcheck on EL 8.8 completed with status UNSTABLE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net/job/daos-stack/job/daos//view/change-requests/job/PR-16745/10/testReport/

…/daos-17322-part1 Features: aggregation

knard38 · 2025-09-18T05:26:03Z

@Nasf-Fan , please could you have a look at the C code and if the latest changes and comments are OK for you.
@kjacque , please could you have a look at the GO code. Since your last review, I just made the container parameter to be optional.

Nasf-Fan · 2025-09-18T08:13:06Z

+	dbd = umem_off2ptr(umm, cont->vc_cont_df->cd_dtx_committed_head);
+	while (dbd != NULL) {
+		D_ASSERTF(dbd->dbd_magic == DTX_CMT_BLOB_MAGIC,
+			  "Corrupted committed DTX blob (2) %x\n", dbd->dbd_magic);


Different from regular vos logic, ddb is usually to handle system corruption, then it is better not assertion the on-disk data, instead, we can report some error.

Change assert into error code.

Change assert into error code.

Fixed with commit 49be495

Nasf-Fan · 2025-09-18T08:13:31Z

+	ctx  = args->ctx;
+
+	itp_set_cont(&itp, entry->ie_couuid, args->cont_seen);
+	++args->cont_seen;


Better ++(args->cont_seen); to avoid confusion.

fix C coding standard

fix C coding standard

Fixed with commit 49be495

Nasf-Fan · 2025-09-18T08:13:54Z

+	param.ip_hdl        = ctx->dc_poh;
+	param.ip_epr.epr_hi = DAOS_EPOCH_MAX;
+	do {
+		struct vos_iter_anchors anchors = {0};


Move anchors outside the while() block; otherwise, you will reset the iteration repeatedly and fall into dead loop.

Arghhhh, not yet used to manage this kind of iterator.

Fix iterator management.

Arghhhh, not yet used to manage this kind of iterator.

Fix iterator management.

Fixed with commit 49be495

Nasf-Fan · 2025-09-18T08:19:10Z

+		Dbds[i].dbd_cap   = DBD_BLOB_DF_CAP;
+		DbdsOff[i]        = umem_ptr2off(&Pool.vp_umm, &Dbds[i]);
+		Dbds[i].dbd_next =
+		    (i == DBD_COUNT - 1) ? UMOFF_NULL : umem_ptr2off(&Pool.vp_umm, &Dbds[i + 1]);


The real committed DTX table is something like that: for each vos_dtx_blob_df, the vos_dtx_cmt_ent_df array will be contiguous with its vos_dtx_blob_df header. But in your test_setup, all the headers of vos_dtx_blob_df are together, that does not match the real case.
Since the test logic does not use any committed DTX entry, then maybe you can only allocate array for vos_dtx_cmt_ent_df headers without vos_dtx_cmt_ent_df array. Otherwise, the position for &Dbds[i + 1]) may belong to some vos_dtx_cmt_ent_df.

BTW, in DAOS engine, the C logic variable name is usually lowercase. I would suggest the same for the test logic. Thanks!

On the other hand, there is not strict requirement for adding unit test for the new VOS API vos_dtx_get_cmt_cnt that is quite simple and only used for ddb.

BTW, in DAOS engine, the C logic variable name is usually lowercase. I would suggest the same for the test logic. Thanks!

I have to confess that I have used some existing test file as example and do not take attention of the case variable name issue.

Fix coding standard issue

The real committed DTX table is something like that: for each vos_dtx_blob_df, the vos_dtx_cmt_ent_df array will be contiguous with its vos_dtx_blob_df header. But in your test_setup, all the headers of vos_dtx_blob_df are together, that does not match the real case.
Since the test logic does not use any committed DTX entry, then maybe you can only allocate array for vos_dtx_cmt_ent_df headers without vos_dtx_cmt_ent_df array. Otherwise, the position for &Dbds[i + 1]) may belong to some vos_dtx_cmt_ent_df.

Fix DTX blob offset

On the other hand, there is not strict requirement for adding unit test for the new VOS API vos_dtx_get_cmt_cnt that is quite simple and only used for ddb.

I agree that this test is over kill considering the complexity of the tested function. From my side, it allowed me to better understand this part of the DAOS code.
I have no issue to remove it if you think that it could make some confusion. If yes, before removing it, could it be possible to push the fix of the invalid DTX blob offset for being sure that I properly understood the issue.

BTW, in DAOS engine, the C logic variable name is usually lowercase. I would suggest the same for the test logic. Thanks!

I have to confess that I have used some existing test file as example and do not take attention of the case variable name issue.

Fix coding standard issue

Fixed with commit 49be495

The real committed DTX table is something like that: for each vos_dtx_blob_df, the vos_dtx_cmt_ent_df array will be contiguous with its vos_dtx_blob_df header. But in your test_setup, all the headers of vos_dtx_blob_df are together, that does not match the real case.
Since the test logic does not use any committed DTX entry, then maybe you can only allocate array for vos_dtx_cmt_ent_df headers without vos_dtx_cmt_ent_df array. Otherwise, the position for &Dbds[i + 1]) may belong to some vos_dtx_cmt_ent_df.

Fix DTX blob offset

Fixed with commit 49be495

Nasf-Fan · 2025-09-18T08:27:42Z

+	if (!SUCCESS(rc))
+		goto done;
+
+	cnt_tmp = vos_dtx_get_cmt_cnt(coh);


I would suggest vos_dtx_get_cmt_cnt() can return failure if hit corruption instead of triggering assertion.

Change assert into error code.

Change assert into error code.

Fixed with commit 49be495

Nasf-Fan · 2025-09-18T08:31:03Z

@Nasf-Fan , please could you have a look at the C code and if the latest changes and comments are OK for you.

Thanks @knard38 for the changes, most of them looks fine for me, just some small issues to be resolved.

…/daos-17322-part1

Integrate reviewers comments: - Change assert into error code. - Fix C coding standard. - Fix iterator management. - Fix coding standard issue - Fix DTX blob offset Features: aggregation Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

Nasf-Fan · 2025-09-19T03:17:15Z

-		assert_true(Dbds[i].dbd_count <= DBD_BLOB_DF_CAP);
+		struct vos_dtx_blob_df *dbd;
+
+		dbd = (struct vos_dtx_blob_df *)((uint64_t)(&mock_dbds[0]) + i * CELL_SIZE);


Is it correct? (uint64_t)(&mock_dbds[0]) seems to be (void *)(&mock_dbds[0]). Honestly, we can simplify the logic to initialize each mock_dbds[i] independently, something like that:

for (i = 0; i < DBD_COUNT; i++) { D_ALLOC(mock_dbds[i], CELL_SIZE); if (mock_dbds[i] == NULL) return -DER_NOMEM; ... mock_dbds_off[i] = xxx; if (i > 0) { mock_dbds[i].dbd_prev = mock_dbds_off[i - 1]; mock_dbds[i - 1].dbd_next = mock_dbds_off[i]; } else { mock_dbds[i].dbd_prev = UMOFF_NULL; } } mock_dbds[0].dbd_next = mock_dbds_off[1];

Correspondingly, destroy them one by one in test_teardown:

for (i = 0; i < DBD_COUNT; i--) { D_FREE(mock_dbds[i]); }

Then the logic is more easy to be understood and avoid bugs during calculate next and prev.

Perfectly agree, using one allocation is over complicated for no good reason (i.e. just avoid to have two loop: one for memory allocation and one for initialisation).
Going to fix this as you suggested.

Use multiple allocation.

Perfectly agree, using one allocation is over complicated for no good reason (i.e. just avoid to have two loop: one for memory allocation and one for initialisation). Going to fix this as you suggested.

Use multiple allocation.

Fixed with commit 9d81546

Nasf-Fan · 2025-09-19T03:18:26Z


-	return cnt;
+	*cnt = tmp;
+	rc   = -DER_SUCCESS;


[suggestion] I am wondering why return -DER_SUCCESS instead of 0? That seems confused although we usually define DER_SUCCESS as 0. You have already described \return 0 on success, error otherwise in the header. So please just return 0 and adjust related test cases. Thanks!

Replace -DER_SUCCESS with 0

Replace -DER_SUCCESS with 0

Fixed with commit 9d81546

…/daos-17322-part1

Integrate reviewers comments: - Replace -DER_SUCCESS with 0 - Use multiple allocation Features: aggregation Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

Fix clang format issue Features: aggregation Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

Nasf-Fan · 2025-09-19T07:44:09Z

 	for (i = 0; i < DBD_COUNT; i++) {
-		struct vos_dtx_blob_df *dbd;
+		D_ALLOC(mock_dbds[i], CELL_SIZE);
+		assert_non_null(mock_dbds[i]);


mock_dbds_off[i] = umem_ptr2off(&mock_pool.vp_umm, mock_dbds[i]);

Add above line in this for section. Then in subsequent for section, we can directly use them, for example:

if (i == DBD_COUNT - 1) mock_dbds[i]->dbd_next = UMOFF_NULL; else mock_dbds[i]->dbd_next = mock_dbds_off[i + 1]; if (i == 0) mock_dbds[i]->dbd_prev = UMOFF_NULL; else mock_dbds[i]->dbd_prev = mock_dbds_off[i - 1];

Anyway, just some code optimization, not fatal. If you have other chance to refresh the patch, you can consider.

If I have no mandatory change requested, I will integrate your remarks in the following up PR introducing the ddb aggregation command.

Simplify linked list management

Simplify linked list management

Fixed with commit 182b4ac of PR #16746

daosbuild3 · 2025-09-19T08:22:50Z

Test stage NLT on EL 8.8 completed with status UNSTABLE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net/job/daos-stack/job/daos//view/change-requests/job/PR-16745/14/testReport/

kjacque

Go changes LGTM. Didn't look closely at the rest.

…/daos-17322-part1 Features: aggregation

daosbuild3 · 2025-09-21T20:43:42Z

Test stage NLT on EL 8.8 completed with status UNSTABLE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net/job/daos-stack/job/daos//view/change-requests/job/PR-16745/15/testReport/

daosbuild3 · 2025-09-22T10:54:56Z

Test stage Functional Hardware Large MD on SSD completed with status FAILURE. https://jenkins-3.daos.hpc.amslabs.hpecorp.net//job/daos-stack/job/daos/view/change-requests/job/PR-16745/15/execution/node/1300/log

…/daos-17322-part1 Features: aggregation

knard38 · 2025-09-25T04:17:49Z

@daos-stack/daos-gatekeeper please could you lend this PR.

kanard38 added 3 commits August 18, 2025 09:43

DAOS-17322 ddb: DTX aggregation with ddb

00fc38b

Cleanup of SCons file. Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

DAOS-17322 ddb: DTX aggregation with ddb

3ee405a

Miscellaneous fixes detected by clangd. Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

DAOS-17322 ddb: DTX aggregation with ddb

0be6e7e

Add the following new command to ddb: - dtx_stat: Print statistics on DTX entries Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

knard38 self-assigned this Aug 19, 2025

knard38 added the CR Catastrophic Recovery Feature label Aug 19, 2025

knard38 requested review from Nasf-Fan and janekmi August 19, 2025 05:49

knard38 marked this pull request as ready for review August 19, 2025 05:50

knard38 requested review from a team as code owners August 19, 2025 05:50

Nasf-Fan reviewed Aug 23, 2025

View reviewed changes

Nasf-Fan self-requested a review August 23, 2025 02:01

Nasf-Fan reviewed Aug 23, 2025

View reviewed changes

Nasf-Fan self-requested a review August 23, 2025 02:21

kjacque previously approved these changes Sep 9, 2025

View reviewed changes

kanard38 added 2 commits September 10, 2025 08:52

Merge remote-tracking branch 'origin/master' into ckochhof/dev/master…

f6b3aa3

…/daos-17322-part1

DAOS-17322 ddb: DTX aggregation with ddb

983d9d4

Integrate reviewers comments: - Remove useless test - Remove useless strlen - Use static initialisation instead of explicit initialisation. Features: aggregation Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

knard38 dismissed kjacque’s stale review via 983d9d4 September 10, 2025 08:54

DAOS-17322 ddb: DTX aggregation with ddb

77e3c21

Integrate reviewers comments: - fix invalid regfree() Features: aggregation Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

Merge remote-tracking branch 'origin/master' into ckochhof/dev/master…

a2796f0

…/daos-17322-part1 Features: aggregation

Merge remote-tracking branch 'origin/master' into ckochhof/dev/master…

6ccb846

…/daos-17322-part1 Features: aggregation

Nasf-Fan requested changes Sep 18, 2025

View reviewed changes

kanard38 added 2 commits September 18, 2025 09:55

Merge remote-tracking branch 'origin/master' into ckochhof/dev/master…

d30d360

…/daos-17322-part1

Nasf-Fan reviewed Sep 19, 2025

View reviewed changes

kanard38 added 3 commits September 19, 2025 06:25

Merge remote-tracking branch 'origin/master' into ckochhof/dev/master…

7f056de

…/daos-17322-part1

DAOS-17322 ddb: DTX aggregation with ddb

9d81546

Integrate reviewers comments: - Replace -DER_SUCCESS with 0 - Use multiple allocation Features: aggregation Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

DAOS-17322 ddb: DTX aggregation with ddb

29583d0

Fix clang format issue Features: aggregation Signed-off-by: Cedric Koch-Hofer <cedric.koch-hofer@hpe.com>

Nasf-Fan approved these changes Sep 19, 2025

View reviewed changes

kjacque approved these changes Sep 19, 2025

View reviewed changes

Merge remote-tracking branch 'origin/master' into ckochhof/dev/master…

d0947f9

…/daos-17322-part1 Features: aggregation

Merge remote-tracking branch 'origin/master' into ckochhof/dev/master…

2129d3f

…/daos-17322-part1 Features: aggregation

knard38 requested a review from a team September 25, 2025 04:17

gnailzenh approved these changes Sep 26, 2025

View reviewed changes

gnailzenh merged commit 9860712 into master Sep 26, 2025
49 checks passed

gnailzenh deleted the ckochhof/dev/master/daos-17322-part1 branch September 26, 2025 02:29

knard38 changed the title ~~DAOS-17322 ddb: DTX aggregation with ddb~~ DAOS-17322 ddb: DTX aggregation with ddb (Part 1) Oct 8, 2025

Conversation

knard38 commented Aug 18, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Steps for the author:

After all prior steps are complete:

Uh oh!

github-actions Bot commented Aug 18, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Choose a reason for hiding this comment

Uh oh!

knard38 Sep 5, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

knard38 Sep 5, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

knard38 Sep 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

knard38 Sep 5, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

knard38 Sep 5, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

knard38 Sep 5, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

knard38 Sep 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

knard38 Sep 5, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

knard38 Sep 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

knard38 Sep 5, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

kjacque left a comment

Choose a reason for hiding this comment

Uh oh!

daosbuild3 commented Sep 10, 2025

Uh oh!

daosbuild3 commented Sep 10, 2025

knard38 commented Aug 18, 2025 •

edited

Loading

github-actions Bot commented Aug 18, 2025 •

edited

Loading

knard38 Sep 5, 2025 •

edited

Loading

knard38 Sep 5, 2025 •

edited

Loading

knard38 Sep 10, 2025 •

edited

Loading

knard38 Sep 5, 2025 •

edited

Loading

knard38 Sep 5, 2025 •

edited

Loading

knard38 Sep 5, 2025 •

edited

Loading

knard38 Sep 10, 2025 •

edited

Loading

knard38 Sep 5, 2025 •

edited

Loading

knard38 Sep 10, 2025 •

edited

Loading

knard38 Sep 5, 2025 •

edited

Loading

knard38 Sep 18, 2025 •

edited

Loading

knard38 Sep 18, 2025 •

edited

Loading

knard38 Sep 18, 2025 •

edited

Loading