From: kbuild test robot <lkp@intel.com>
To: Dennis Zhou <dennisszhou@gmail.com>
Cc: kbuild-all@01.org, Tejun Heo <tj@kernel.org>,
Jens Axboe <axboe@kernel.dk>, Josef Bacik <jbacik@fb.com>,
kernel-team@fb.com, linux-block@vger.kernel.org,
linux-kernel@vger.kernel.org,
Johannes Weiner <hannes@cmpxchg.org>,
"Dennis Zhou (Facebook)" <dennisszhou@gmail.com>
Subject: Re: [PATCH v2] block: make iolatency avg_lat exponentially decay
Date: Wed, 1 Aug 2018 12:46:12 +0800 [thread overview]
Message-ID: <201808011245.cVEYgmq3%fengguang.wu@intel.com> (raw)
In-Reply-To: <20180801002559.36261-1-dennisszhou@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 3800 bytes --]
Hi Dennis,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on block/for-next]
[also build test ERROR on next-20180731]
[cannot apply to v4.18-rc7]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Dennis-Zhou/block-make-iolatency-avg_lat-exponentially-decay/20180801-100533
base: https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git for-next
config: i386-randconfig-i1-201830 (attached as .config)
compiler: gcc-7 (Debian 7.3.0-16) 7.3.0
reproduce:
# save the attached .config to linux build tree
make ARCH=i386
All errors (new ones prefixed by >>):
block/blk-iolatency.o: In function `iolatency_check_latencies':
>> block/blk-iolatency.c:511: undefined reference to `__udivdi3'
vim +511 block/blk-iolatency.c
478
479 static void iolatency_check_latencies(struct iolatency_grp *iolat, u64 now)
480 {
481 struct blkcg_gq *blkg = lat_to_blkg(iolat);
482 struct iolatency_grp *parent;
483 struct child_latency_info *lat_info;
484 struct blk_rq_stat stat;
485 unsigned long flags;
486 int cpu, exp_idx;
487
488 blk_rq_stat_init(&stat);
489 preempt_disable();
490 for_each_online_cpu(cpu) {
491 struct blk_rq_stat *s;
492 s = per_cpu_ptr(iolat->stats, cpu);
493 blk_rq_stat_sum(&stat, s);
494 blk_rq_stat_init(s);
495 }
496 preempt_enable();
497
498 parent = blkg_to_lat(blkg->parent);
499 if (!parent)
500 return;
501
502 lat_info = &parent->child_lat;
503
504 /*
505 * CALC_LOAD takes in a number stored in fixed point representation.
506 * Because we are using this for IO time in ns, the values stored
507 * are significantly larger than the FIXED_1 denominator (2048).
508 * Therefore, rounding errors in the calculation are negligible and
509 * can be ignored.
510 */
> 511 exp_idx = min_t(int, BLKIOLATENCY_NR_EXP_FACTORS - 1,
512 iolat->cur_win_nsec / BLKIOLATENCY_EXP_BUCKET_SIZE);
513 CALC_LOAD(iolat->total_lat_avg, iolatency_exp_factors[exp_idx],
514 stat.mean);
515
516 /* Everything is ok and we don't need to adjust the scale. */
517 if (stat.mean <= iolat->min_lat_nsec &&
518 atomic_read(&lat_info->scale_cookie) == DEFAULT_SCALE_COOKIE)
519 return;
520
521 /* Somebody beat us to the punch, just bail. */
522 spin_lock_irqsave(&lat_info->lock, flags);
523 lat_info->nr_samples -= iolat->nr_samples;
524 lat_info->nr_samples += stat.nr_samples;
525 iolat->nr_samples = stat.nr_samples;
526
527 if ((lat_info->last_scale_event >= now ||
528 now - lat_info->last_scale_event < BLKIOLATENCY_MIN_ADJUST_TIME) &&
529 lat_info->scale_lat <= iolat->min_lat_nsec)
530 goto out;
531
532 if (stat.mean <= iolat->min_lat_nsec &&
533 stat.nr_samples >= BLKIOLATENCY_MIN_GOOD_SAMPLES) {
534 if (lat_info->scale_grp == iolat) {
535 lat_info->last_scale_event = now;
536 scale_cookie_change(iolat->blkiolat, lat_info, true);
537 }
538 } else if (stat.mean > iolat->min_lat_nsec) {
539 lat_info->last_scale_event = now;
540 if (!lat_info->scale_grp ||
541 lat_info->scale_lat > iolat->min_lat_nsec) {
542 WRITE_ONCE(lat_info->scale_lat, iolat->min_lat_nsec);
543 lat_info->scale_grp = iolat;
544 }
545 scale_cookie_change(iolat->blkiolat, lat_info, false);
546 }
547 out:
548 spin_unlock_irqrestore(&lat_info->lock, flags);
549 }
550
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 28309 bytes --]
next prev parent reply other threads:[~2018-08-01 4:47 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-08-01 0:25 Dennis Zhou
2018-08-01 4:46 ` kbuild test robot [this message]
2018-08-01 15:49 ` Tejun Heo
2018-08-01 16:10 ` Tejun Heo
2018-08-02 6:11 ` Dennis Zhou
2018-08-01 16:02 ` Johannes Weiner
2018-08-01 16:26 ` Josef Bacik
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 \
--in-reply-to=201808011245.cVEYgmq3%fengguang.wu@intel.com \
--to=lkp@intel.com \
--cc=axboe@kernel.dk \
--cc=dennisszhou@gmail.com \
--cc=hannes@cmpxchg.org \
--cc=jbacik@fb.com \
--cc=kbuild-all@01.org \
--cc=kernel-team@fb.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=tj@kernel.org \
/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
all inboxes | Powered by JetHome®