From: Mina Almasry <almasrymina@google.com>
To: mike.kravetz@oracle.com
Cc: shuah@kernel.org, almasrymina@google.com, rientjes@google.com,
shakeelb@google.com, gthelen@google.com,
akpm@linux-foundation.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, linux-kselftest@vger.kernel.org,
cgroups@vger.kernel.org
Subject: [PATCH v12 9/9] hugetlb_cgroup: Add hugetlb_cgroup reservation docs
Date: Tue, 11 Feb 2020 13:31:28 -0800 [thread overview]
Message-ID: <20200211213128.73302-9-almasrymina@google.com> (raw)
In-Reply-To: <20200211213128.73302-1-almasrymina@google.com>
Add docs for how to use hugetlb_cgroup reservations, and their behavior.
Signed-off-by: Mina Almasry <almasrymina@google.com>
---
Changes in v11:
- Changed resv.* to rsvd.*
Changes in v10:
- Clarify reparenting behavior.
- Reword benefits of reservation limits.
Changes in v6:
- Updated docs to reflect the new design based on a new counter that
tracks both reservations and faults.
---
.../admin-guide/cgroup-v1/hugetlb.rst | 103 ++++++++++++++++--
1 file changed, 92 insertions(+), 11 deletions(-)
diff --git a/Documentation/admin-guide/cgroup-v1/hugetlb.rst b/Documentation/admin-guide/cgroup-v1/hugetlb.rst
index a3902aa253a96..338f2c7d7a1cd 100644
--- a/Documentation/admin-guide/cgroup-v1/hugetlb.rst
+++ b/Documentation/admin-guide/cgroup-v1/hugetlb.rst
@@ -2,13 +2,6 @@
HugeTLB Controller
==================
-The HugeTLB controller allows to limit the HugeTLB usage per control group and
-enforces the controller limit during page fault. Since HugeTLB doesn't
-support page reclaim, enforcing the limit at page fault time implies that,
-the application will get SIGBUS signal if it tries to access HugeTLB pages
-beyond its limit. This requires the application to know beforehand how much
-HugeTLB pages it would require for its use.
-
HugeTLB controller can be created by first mounting the cgroup filesystem.
# mount -t cgroup -o hugetlb none /sys/fs/cgroup
@@ -28,10 +21,14 @@ process (bash) into it.
Brief summary of control files::
- hugetlb.<hugepagesize>.limit_in_bytes # set/show limit of "hugepagesize" hugetlb usage
- hugetlb.<hugepagesize>.max_usage_in_bytes # show max "hugepagesize" hugetlb usage recorded
- hugetlb.<hugepagesize>.usage_in_bytes # show current usage for "hugepagesize" hugetlb
- hugetlb.<hugepagesize>.failcnt # show the number of allocation failure due to HugeTLB limit
+ hugetlb.<hugepagesize>.rsvd.limit_in_bytes # set/show limit of "hugepagesize" hugetlb reservations
+ hugetlb.<hugepagesize>.rsvd.max_usage_in_bytes # show max "hugepagesize" hugetlb reservations and no-reserve faults
+ hugetlb.<hugepagesize>.rsvd.usage_in_bytes # show current reservations and no-reserve faults for "hugepagesize" hugetlb
+ hugetlb.<hugepagesize>.rsvd.failcnt # show the number of allocation failure due to HugeTLB reservation limit
+ hugetlb.<hugepagesize>.limit_in_bytes # set/show limit of "hugepagesize" hugetlb faults
+ hugetlb.<hugepagesize>.max_usage_in_bytes # show max "hugepagesize" hugetlb usage recorded
+ hugetlb.<hugepagesize>.usage_in_bytes # show current usage for "hugepagesize" hugetlb
+ hugetlb.<hugepagesize>.failcnt # show the number of allocation failure due to HugeTLB usage limit
For a system supporting three hugepage sizes (64k, 32M and 1G), the control
files include::
@@ -40,11 +37,95 @@ files include::
hugetlb.1GB.max_usage_in_bytes
hugetlb.1GB.usage_in_bytes
hugetlb.1GB.failcnt
+ hugetlb.1GB.rsvd.limit_in_bytes
+ hugetlb.1GB.rsvd.max_usage_in_bytes
+ hugetlb.1GB.rsvd.usage_in_bytes
+ hugetlb.1GB.rsvd.failcnt
hugetlb.64KB.limit_in_bytes
hugetlb.64KB.max_usage_in_bytes
hugetlb.64KB.usage_in_bytes
hugetlb.64KB.failcnt
+ hugetlb.64KB.rsvd.limit_in_bytes
+ hugetlb.64KB.rsvd.max_usage_in_bytes
+ hugetlb.64KB.rsvd.usage_in_bytes
+ hugetlb.64KB.rsvd.failcnt
hugetlb.32MB.limit_in_bytes
hugetlb.32MB.max_usage_in_bytes
hugetlb.32MB.usage_in_bytes
hugetlb.32MB.failcnt
+ hugetlb.32MB.rsvd.limit_in_bytes
+ hugetlb.32MB.rsvd.max_usage_in_bytes
+ hugetlb.32MB.rsvd.usage_in_bytes
+ hugetlb.32MB.rsvd.failcnt
+
+
+1. Page fault accounting
+
+hugetlb.<hugepagesize>.limit_in_bytes
+hugetlb.<hugepagesize>.max_usage_in_bytes
+hugetlb.<hugepagesize>.usage_in_bytes
+hugetlb.<hugepagesize>.failcnt
+
+The HugeTLB controller allows users to limit the HugeTLB usage (page fault) per
+control group and enforces the limit during page fault. Since HugeTLB
+doesn't support page reclaim, enforcing the limit at page fault time implies
+that, the application will get SIGBUS signal if it tries to fault in HugeTLB
+pages beyond its limit. Therefore the application needs to know exactly how many
+HugeTLB pages it uses before hand, and the sysadmin needs to make sure that
+there are enough available on the machine for all the users to avoid processes
+getting SIGBUS.
+
+
+2. Reservation accounting
+
+hugetlb.<hugepagesize>.rsvd.limit_in_bytes
+hugetlb.<hugepagesize>.rsvd.max_usage_in_bytes
+hugetlb.<hugepagesize>.rsvd.usage_in_bytes
+hugetlb.<hugepagesize>.rsvd.failcnt
+
+The HugeTLB controller allows to limit the HugeTLB reservations per control
+group and enforces the controller limit at reservation time and at the fault of
+HugeTLB memory for which no reservation exists. Since reservation limits are
+enforced at reservation time (on mmap or shget), reservation limits never causes
+the application to get SIGBUS signal if the memory was reserved before hand. For
+MAP_NORESERVE allocations, the reservation limit behaves the same as the fault
+limit, enforcing memory usage at fault time and causing the application to
+receive a SIGBUS if it's crossing its limit.
+
+Reservation limits are superior to page fault limits described above, since
+reservation limits are enforced at reservation time (on mmap or shget), and
+never causes the application to get SIGBUS signal if the memory was reserved
+before hand. This allows for easier fallback to alternatives such as
+non-HugeTLB memory for example. In the case of page fault accounting, it's very
+hard to avoid processes getting SIGBUS since the sysadmin needs precisely know
+the HugeTLB usage of all the tasks in the system and make sure there is enough
+pages to satisfy all requests. Avoiding tasks getting SIGBUS on overcommited
+systems is practically impossible with page fault accounting.
+
+
+3. Caveats with shared memory
+
+For shared HugeTLB memory, both HugeTLB reservation and page faults are charged
+to the first task that causes the memory to be reserved or faulted, and all
+subsequent uses of this reserved or faulted memory is done without charging.
+
+Shared HugeTLB memory is only uncharged when it is unreserved or deallocated.
+This is usually when the HugeTLB file is deleted, and not when the task that
+caused the reservation or fault has exited.
+
+
+4. Caveats with HugeTLB cgroup offline.
+
+When a HugeTLB cgroup goes offline with some reservations or faults still
+charged to it, the behavior is as follows:
+
+- The fault charges are charged to the parent HugeTLB cgroup (reparented),
+- the reservation charges remain on the offline HugeTLB cgroup.
+
+This means that if a HugeTLB cgroup gets offlined while there is still HugeTLB
+reservations charged to it, that cgroup persists as a zombie until all HugeTLB
+reservations are uncharged. HugeTLB reservations behave in this manner to match
+the memory controller whose cgroups also persist as zombie until all charged
+memory is uncharged. Also, the tracking of HugeTLB reservations is a bit more
+complex compared to the tracking of HugeTLB faults, so it is significantly
+harder to reparent reservations at offline time.
--
2.25.0.225.g125e21ebc7-goog
next prev parent reply other threads:[~2020-02-11 21:32 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-11 21:31 [PATCH v12 1/9] hugetlb_cgroup: Add hugetlb_cgroup reservation counter Mina Almasry
2020-02-11 21:31 ` [PATCH v12 2/9] hugetlb_cgroup: add interface for charge/uncharge hugetlb reservations Mina Almasry
2020-02-15 0:50 ` Mike Kravetz
2020-02-16 1:21 ` David Rientjes
2020-02-11 21:31 ` [PATCH v12 3/9] hugetlb_cgroup: add reservation accounting for private mappings Mina Almasry
2020-02-11 21:31 ` [PATCH v12 4/9] hugetlb: disable region_add file_region coalescing Mina Almasry
2020-02-15 1:27 ` Mike Kravetz
2020-02-16 1:25 ` David Rientjes
2020-02-11 21:31 ` [PATCH v12 5/9] hugetlb_cgroup: add accounting for shared mappings Mina Almasry
2020-02-16 1:29 ` David Rientjes
2020-02-18 18:07 ` Mike Kravetz
2020-02-11 21:31 ` [PATCH v12 6/9] hugetlb_cgroup: support noreserve mappings Mina Almasry
2020-02-18 20:57 ` Mike Kravetz
2020-02-11 21:31 ` [PATCH v12 7/9] hugetlb: support file_region coalescing again Mina Almasry
2020-02-16 1:29 ` David Rientjes
2020-02-19 3:28 ` Mike Kravetz
2020-02-19 7:54 ` Mina Almasry
2020-02-19 23:36 ` [PATCH] hugetlb: Remove check_coalesce_bug debug code Mina Almasry
2020-02-20 0:07 ` Mike Kravetz
2020-02-11 21:31 ` [PATCH v12 8/9] hugetlb_cgroup: Add hugetlb_cgroup reservation tests Mina Almasry
2020-02-12 8:50 ` Sandipan Das
2020-02-20 0:05 ` Mina Almasry
2020-02-21 0:52 ` Mike Kravetz
2020-02-11 21:31 ` Mina Almasry [this message]
2020-02-20 0:03 ` [PATCH v12 9/9] hugetlb_cgroup: Add hugetlb_cgroup reservation docs Mina Almasry
2020-02-20 0:18 ` Mike Kravetz
2020-02-11 23:19 ` [PATCH v12 1/9] hugetlb_cgroup: Add hugetlb_cgroup reservation counter Andrew Morton
2020-02-18 14:21 ` Qian Cai
2020-02-18 18:35 ` Mina Almasry
2020-02-18 18:41 ` Qian Cai
2020-02-18 19:14 ` Mike Kravetz
2020-02-18 19:25 ` Mina Almasry
2020-02-18 21:36 ` Mina Almasry
2020-02-18 21:41 ` Mike Kravetz
2020-02-18 22:27 ` Mina Almasry
2020-02-19 19:05 ` Mina Almasry
2020-02-19 21:06 ` Andrew Morton
2020-02-20 19:22 ` Mina Almasry
2020-02-21 0:28 ` Andrew Morton
2020-02-21 0:41 ` Mike Kravetz
2020-02-21 1:52 ` Mina Almasry
2020-02-21 20:19 ` Mina Almasry
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=20200211213128.73302-9-almasrymina@google.com \
--to=almasrymina@google.com \
--cc=akpm@linux-foundation.org \
--cc=cgroups@vger.kernel.org \
--cc=gthelen@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mike.kravetz@oracle.com \
--cc=rientjes@google.com \
--cc=shakeelb@google.com \
--cc=shuah@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;
as well as URLs for NNTP newsgroup(s).