Skip to content

L
linux
Switch branch/tag
  1. 28 Mar, 2017 11 commits
    • Shaohua Li's avatar
      blk-throttle: detect completed idle cgroup · aec24246
      Shaohua Li authored 
      cgroup could be assigned a limit, but doesn't dispatch enough IO, eg the
cgroup is idle. When this happens, the cgroup doesn't hit its limit, so
we can't move the state machine to higher level and all cgroups will be
throttled to their lower limit, so we waste bandwidth. Detecting idle
cgroup is hard. This patch handles a simple case, a cgroup doesn't
dispatch any IO. We ignore such cgroup's limit, so other cgroups can use
the bandwidth.

Please note this will be replaced with a more sophisticated algorithm
later, but this demonstrates the idea how we handle idle cgroups, so I
leave it here.
Signed-off-by: default avatarShaohua Li <shli@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      aec24246
    • Shaohua Li's avatar
      blk-throttle: choose a small throtl_slice for SSD · d61fcfa4
      Shaohua Li authored 
      The throtl_slice is 100ms by default. This is a long time for SSD, a lot
of IO can run. To make cgroups have smoother throughput, we choose a
small value (20ms) for SSD.
Signed-off-by: default avatarShaohua Li <shli@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      d61fcfa4
    • Shaohua Li's avatar
      blk-throttle: make throtl_slice tunable · 297e3d85
      Shaohua Li authored 
      throtl_slice is important for blk-throttling. It's called slice
internally but it really is a time window blk-throttling samples data.
blk-throttling will make decision based on the samplings. An example is
bandwidth measurement. A cgroup's bandwidth is measured in the time
interval of throtl_slice.

A small throtl_slice meanse cgroups have smoother throughput but burn
more CPUs. It has 100ms default value, which is not appropriate for all
disks. A fast SSD can dispatch a lot of IOs in 100ms. This patch makes
it tunable.

Since throtl_slice isn't a time slice, the sysfs name
'throttle_sample_time' reflects its character better.
Signed-off-by: default avatarShaohua Li <shli@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      297e3d85
    • Shaohua Li's avatar
      blk-throttle: make sure expire time isn't too big · 06cceedc
      Shaohua Li authored 
      cgroup could be throttled to a limit but when all cgroups cross high
limit, queue enters a higher state and so the group should be throttled
to a higher limit. It's possible the cgroup is sleeping because of
throttle and other cgroups don't dispatch IO any more. In this case,
nobody can trigger current downgrade/upgrade logic. To fix this issue,
we could either set up a timer to wakeup the cgroup if other cgroups are
idle or make sure this cgroup doesn't sleep too long. Setting up a timer
means we must change the timer very frequently. This patch chooses the
latter. Making cgroup sleep time not too big wouldn't change cgroup
bps/iops, but could make it wakeup more frequently, which isn't a big
issue because throtl_slice * 8 is already quite big.
Signed-off-by: default avatarShaohua Li <shli@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      06cceedc
    • Shaohua Li's avatar
      blk-throttle: add downgrade logic · 3f0abd80
      Shaohua Li authored 
      When queue state machine is in LIMIT_MAX state, but a cgroup is below
its low limit for some time, the queue should be downgraded to lower
state as one cgroup's low limit isn't met.
Signed-off-by: default avatarShaohua Li <shli@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      3f0abd80
    • Shaohua Li's avatar
      blk-throttle: add upgrade logic for LIMIT_LOW state · c79892c5
      Shaohua Li authored 
      When queue is in LIMIT_LOW state and all cgroups with low limit cross
the bps/iops limitation, we will upgrade queue's state to
LIMIT_MAX. To determine if a cgroup exceeds its limitation, we check if
the cgroup has pending request. Since cgroup is throttled according to
the limit, pending request means the cgroup reaches the limit.

If a cgroup has limit set for both read and write, we consider the
combination of them for upgrade. The reason is read IO and write IO can
interfere with each other. If we do the upgrade based in one direction
IO, the other direction IO could be severly harmed.

For a cgroup hierarchy, there are two cases. Children has lower low
limit than parent. Parent's low limit is meaningless. If children's
bps/iops cross low limit, we can upgrade queue state. The other case is
children has higher low limit than parent. Children's low limit is
meaningless. As long as parent's bps/iops (which is a sum of childrens
bps/iops) cross low limit, we can upgrade queue state.
Signed-off-by: default avatarShaohua Li <shli@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      c79892c5
    • Shaohua Li's avatar
      blk-throttle: configure bps/iops limit for cgroup in low limit · b22c417c
      Shaohua Li authored 
      each queue will have a state machine. Initially queue is in LIMIT_LOW
state, which means all cgroups will be throttled according to their low
limit. After all cgroups with low limit cross the limit, the queue state
gets upgraded to LIMIT_MAX state.
For max limit, cgroup will use the limit configured by user.
For low limit, cgroup will use the minimal value between low limit and
max limit configured by user. If the minimal value is 0, which means the
cgroup doesn't configure low limit, we will use max limit to throttle
the cgroup and the cgroup is ready to upgrade to LIMIT_MAX
Signed-off-by: default avatarShaohua Li <shli@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      b22c417c
    • Shaohua Li's avatar
      blk-throttle: add .low interface · cd5ab1b0
      Shaohua Li authored 
      Add low limit for cgroup and corresponding cgroup interface. To be
consistent with memcg, we allow users configure .low limit higher than
.max limit. But the internal logic always assumes .low limit is lower
than .max limit. So we add extra bps/iops_conf fields in throtl_grp for
userspace configuration. Old bps/iops fields in throtl_grp will be the
actual limit we use for throttling.
Signed-off-by: default avatarShaohua Li <shli@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      cd5ab1b0
    • Shaohua Li's avatar
      blk-throttle: add configure option for new .low interface · 327ffb9b
      Shaohua Li authored 
      As discussed in LSF, add configure option for the interface and mark it
as experimental, so people can try/test.
Signed-off-by: default avatarShaohua Li <shli@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      327ffb9b
    • Shaohua Li's avatar
      blk-throttle: prepare support multiple limits · 9f626e37
      Shaohua Li authored 
      We are going to support low/max limit, each cgroup will have 2 limits
after that. This patch prepares for the multiple limits change.
Signed-off-by: default avatarShaohua Li <shli@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      9f626e37
    • Shaohua Li's avatar
      blk-throttle: use U64_MAX/UINT_MAX to replace -1 · 2ab5492d
      Shaohua Li authored 
      clean up the code to avoid using -1
Signed-off-by: default avatarShaohua Li <shli@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      2ab5492d
  3. 25 Mar, 2017 1 commit
  5. 24 Mar, 2017 4 commits
  7. 23 Mar, 2017 16 commits
  9. 21 Mar, 2017 6 commits
    • Jens Axboe's avatar
      block: fix stacked driver stats init and free · a83b576c
      Jens Axboe authored 
      If a driver allocates a queue for stacked usage, then it does
not currently get stats allocated. This causes the later init
of, eg, writeback throttling to blow up. Move the init to the
queue allocation instead.

Additionally, allow a NULL callback unregistration. This avoids
having the caller check for that, fixing another oops on
removal of a block device that doesn't have poll stats allocated.

Fixes: 34dbad5d ("blk-stat: convert to callback-based statistics reporting")
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      a83b576c
    • Omar Sandoval's avatar
      blk-stat: convert to callback-based statistics reporting · 34dbad5d
      Omar Sandoval authored 
      Currently, statistics are gathered in ~0.13s windows, and users grab the
statistics whenever they need them. This is not ideal for both in-tree
users:

1. Writeback throttling wants its own dynamically sized window of
   statistics. Since the blk-stats statistics are reset after every
   window and the wbt windows don't line up with the blk-stats windows,
   wbt doesn't see every I/O.
2. Polling currently grabs the statistics on every I/O. Again, depending
   on how the window lines up, we may miss some I/Os. It's also
   unnecessary overhead to get the statistics on every I/O; the hybrid
   polling heuristic would be just as happy with the statistics from the
   previous full window.

This reworks the blk-stats infrastructure to be callback-based: users
register a callback that they want called at a given time with all of
the statistics from the window during which the callback was active.
Users can dynamically bucketize the statistics. wbt and polling both
currently use read vs. write, but polling can be extended to further
subdivide based on request size.

The callbacks are kept on an RCU list, and each callback has percpu
stats buffers. There will only be a few users, so the overhead on the
I/O completion side is low. The stats flushing is also simplified
considerably: since the timer function is responsible for clearing the
statistics, we don't have to worry about stale statistics.

wbt is a trivial conversion. After the conversion, the windowing problem
mentioned above is fixed.

For polling, we register an extra callback that caches the previous
window's statistics in the struct request_queue for the hybrid polling
heuristic to use.

Since we no longer have a single stats buffer for the request queue,
this also removes the sysfs and debugfs stats entries. To replace those,
we add a debugfs entry for the poll statistics.
Signed-off-by: default avatarOmar Sandoval <osandov@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      34dbad5d
    • Omar Sandoval's avatar
      blk-stat: move BLK_RQ_STAT_BATCH definition to blk-stat.c · 4875253f
      Omar Sandoval authored 
      This is an implementation detail that no-one outside of blk-stat.c uses.
Signed-off-by: default avatarOmar Sandoval <osandov@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      4875253f
    • Omar Sandoval's avatar
      blk-stat: use READ and WRITE instead of BLK_STAT_{READ,WRITE} · fa2e39cb
      Omar Sandoval authored 
      The stats buckets will become generic soon, so make the existing users
use the common READ and WRITE definitions instead of one internal to
blk-stat.
Signed-off-by: default avatarOmar Sandoval <osandov@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      fa2e39cb
    • Omar Sandoval's avatar
      block: remove extra calls to wbt_exit() · 0315b159
      Omar Sandoval authored 
      We always call wbt_exit() from blk_release_queue(), so these are
unnecessary.
Signed-off-by: default avatarOmar Sandoval <osandov@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      0315b159
    • Omar Sandoval's avatar
      blk-stat: fix blk_stat_sum() if all samples are batched · 7d8d0014
      Omar Sandoval authored 
      We need to flush the batch _before_ we check the number of samples,
otherwise we'll miss all of the batched samples.

Fixes: cf43e6be ("block: add scalable completion tracking of requests")
Signed-off-by: default avatarOmar Sandoval <osandov@fb.com>
Signed-off-by: default avatarJens Axboe <axboe@fb.com>
      7d8d0014
  11. 20 Mar, 2017 2 commits
    • Linus Torvalds's avatar
      Linux 4.11-rc3 · 97da3854
      Linus Torvalds authored
      97da3854
    • Linus Torvalds's avatar
      mm/swap: don't BUG_ON() due to uninitialized swap slot cache · 452b94b8
      Linus Torvalds authored 
      This BUG_ON() triggered for me once at shutdown, and I don't see a
reason for the check.  The code correctly checks whether the swap slot
cache is usable or not, so an uninitialized swap slot cache is not
actually problematic afaik.

I've temporarily just switched the BUG_ON() to a WARN_ON_ONCE(), since
I'm not sure why that seemingly pointless check was there.  I suspect
the real fix is to just remove it entirely, but for now we'll warn about
it but not bring the machine down.

Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      452b94b8
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7