public inbox for [email protected]
 help / color / mirror / Atom feed
From: kernel test robot <[email protected]>
To: Xiaobing Li <[email protected]>,
	[email protected], [email protected], [email protected],
	[email protected], [email protected],
	[email protected], [email protected], [email protected],
	[email protected], [email protected], [email protected],
	[email protected]
Cc: [email protected], [email protected],
	[email protected], [email protected],
	[email protected], [email protected],
	[email protected], [email protected],
	[email protected], [email protected],
	[email protected], Xiaobing Li <[email protected]>
Subject: Re: [PATCH 3/3] IO_URING: Statistics of the true utilization of sq threads.
Date: Fri, 29 Sep 2023 02:33:50 +0800	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

Hi Xiaobing,

kernel test robot noticed the following build errors:

[auto build test ERROR on tip/sched/core]
[also build test ERROR on linus/master v6.6-rc3 next-20230928]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Xiaobing-Li/SCHEDULER-Add-an-interface-for-counting-real-utilization/20230928-103219
base:   tip/sched/core
patch link:    https://lore.kernel.org/r/20230928022228.15770-4-xiaobing.li%40samsung.com
patch subject: [PATCH 3/3] IO_URING: Statistics of the true utilization of sq threads.
config: arm-mmp2_defconfig (https://download.01.org/0day-ci/archive/20230929/[email protected]/config)
compiler: clang version 15.0.7 (https://github.com/llvm/llvm-project.git 8dfdcc7b7bf66834a761bd8de445840ef68e4d1a)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20230929/[email protected]/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <[email protected]>
| Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/

All errors (new ones prefixed by >>):

   io_uring/sqpoll.c:254:7: error: no member named 'sq_avg' in 'struct sched_entity'
                   se->sq_avg.last_update_time;
                   ~~  ^
>> io_uring/sqpoll.c:260:3: error: call to undeclared function '__update_sq_avg_block'; ISO C99 and later do not support implicit function declarations [-Werror,-Wimplicit-function-declaration]
                   __update_sq_avg_block(now, se);
                   ^
   io_uring/sqpoll.c:272:7: error: no member named 'sq_avg' in 'struct sched_entity'
                   se->sq_avg.last_update_time;
                   ~~  ^
>> io_uring/sqpoll.c:275:4: error: call to undeclared function '__update_sq_avg'; ISO C99 and later do not support implicit function declarations [-Werror,-Wimplicit-function-declaration]
                           __update_sq_avg(now, se);
                           ^
   4 errors generated.


vim +/__update_sq_avg_block +260 io_uring/sqpoll.c

   221	
   222	static int io_sq_thread(void *data)
   223	{
   224		struct io_sq_data *sqd = data;
   225		struct io_ring_ctx *ctx;
   226		unsigned long timeout = 0;
   227		char buf[TASK_COMM_LEN];
   228		DEFINE_WAIT(wait);
   229	
   230		snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid);
   231		set_task_comm(current, buf);
   232	
   233		if (sqd->sq_cpu != -1)
   234			set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu));
   235		else
   236			set_cpus_allowed_ptr(current, cpu_online_mask);
   237	
   238		mutex_lock(&sqd->lock);
   239		bool first = true;
   240		struct timespec64 ts_start, ts_end;
   241		struct timespec64 ts_delta;
   242		struct sched_entity *se = &sqd->thread->se;
   243		while (1) {
   244			bool cap_entries, sqt_spin = false;
   245	
   246			if (io_sqd_events_pending(sqd) || signal_pending(current)) {
   247				if (io_sqd_handle_event(sqd))
   248					break;
   249				timeout = jiffies + sqd->sq_thread_idle;
   250			}
   251			ktime_get_boottime_ts64(&ts_start);
   252			ts_delta = timespec64_sub(ts_start, ts_end);
   253			unsigned long long now = ts_delta.tv_sec * NSEC_PER_SEC + ts_delta.tv_nsec +
   254			se->sq_avg.last_update_time;
   255	
   256			if (first) {
   257				now = 0;
   258				first = false;
   259			}
 > 260			__update_sq_avg_block(now, se);
   261			cap_entries = !list_is_singular(&sqd->ctx_list);
   262			list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
   263				int ret = __io_sq_thread(ctx, cap_entries);
   264	
   265				if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list)))
   266					sqt_spin = true;
   267			}
   268	
   269			ktime_get_boottime_ts64(&ts_end);
   270			ts_delta = timespec64_sub(ts_end, ts_start);
   271			now = ts_delta.tv_sec * NSEC_PER_SEC + ts_delta.tv_nsec +
   272			se->sq_avg.last_update_time;
   273	
   274			if (sqt_spin)
 > 275				__update_sq_avg(now, se);
   276			else
   277				__update_sq_avg_block(now, se);
   278			if (io_run_task_work())
   279				sqt_spin = true;
   280	
   281			if (sqt_spin || !time_after(jiffies, timeout)) {
   282				if (sqt_spin)
   283					timeout = jiffies + sqd->sq_thread_idle;
   284				if (unlikely(need_resched())) {
   285					mutex_unlock(&sqd->lock);
   286					cond_resched();
   287					mutex_lock(&sqd->lock);
   288				}
   289				continue;
   290			}
   291	
   292			prepare_to_wait(&sqd->wait, &wait, TASK_INTERRUPTIBLE);
   293			if (!io_sqd_events_pending(sqd) && !task_work_pending(current)) {
   294				bool needs_sched = true;
   295	
   296				list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
   297					atomic_or(IORING_SQ_NEED_WAKEUP,
   298							&ctx->rings->sq_flags);
   299					if ((ctx->flags & IORING_SETUP_IOPOLL) &&
   300					    !wq_list_empty(&ctx->iopoll_list)) {
   301						needs_sched = false;
   302						break;
   303					}
   304	
   305					/*
   306					 * Ensure the store of the wakeup flag is not
   307					 * reordered with the load of the SQ tail
   308					 */
   309					smp_mb__after_atomic();
   310	
   311					if (io_sqring_entries(ctx)) {
   312						needs_sched = false;
   313						break;
   314					}
   315				}
   316	
   317				if (needs_sched) {
   318					mutex_unlock(&sqd->lock);
   319					schedule();
   320					mutex_lock(&sqd->lock);
   321				}
   322				list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
   323					atomic_andnot(IORING_SQ_NEED_WAKEUP,
   324							&ctx->rings->sq_flags);
   325			}
   326	
   327			finish_wait(&sqd->wait, &wait);
   328			timeout = jiffies + sqd->sq_thread_idle;
   329		}
   330	
   331		io_uring_cancel_generic(true, sqd);
   332		sqd->thread = NULL;
   333		list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
   334			atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags);
   335		io_run_task_work();
   336		mutex_unlock(&sqd->lock);
   337	
   338		complete(&sqd->exited);
   339		do_exit(0);
   340	}
   341	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki

      parent reply	other threads:[~2023-09-28 18:41 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <CGME20230928023004epcas5p4a6dac4cda9c867f3673690521a8c18b6@epcas5p4.samsung.com>
2023-09-28  2:22 ` [PATCH 0/3] Sq thread real utilization statistics Xiaobing Li
     [not found]   ` <CGME20230928023007epcas5p276b6e029a67001a6ed8ab28c05b2be9c@epcas5p2.samsung.com>
2023-09-28  2:22     ` [PATCH 1/3] SCHEDULER: Add an interface for counting real utilization Xiaobing Li
2023-09-28  7:52       ` kernel test robot
2023-09-28  8:02       ` Peter Zijlstra
2023-09-29  0:31       ` Thomas Gleixner
     [not found]   ` <CGME20230928023011epcas5p32668b193b447f1cd6bf78035f4894c42@epcas5p3.samsung.com>
2023-09-28  2:22     ` [PATCH 2/3] PROC FILESYSTEM: Add real utilization data of sq thread Xiaobing Li
     [not found]   ` <CGME20230928023015epcas5p273b3eaebf3759790c278b03c7f0341c8@epcas5p2.samsung.com>
2023-09-28  2:22     ` [PATCH 3/3] IO_URING: Statistics of the true utilization of sq threads Xiaobing Li
2023-09-28  8:01       ` Peter Zijlstra
2023-09-28  8:23         ` Jens Axboe
2023-09-28  8:37         ` Matthew Wilcox
2023-09-28  8:41           ` Jens Axboe
2023-09-28 18:33       ` kernel test robot [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox