summaryrefslogtreecommitdiffstats
path: root/mm/hugetlb.c
diff options
context:
space:
mode:
authorLiam R. Howlett <Liam.Howlett@Oracle.com>2017-07-10 15:48:15 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-07-10 16:32:31 -0700
commitd715cf804a0318e83c75c0a7abd1a4b9ce13e8da (patch)
tree5e632e1f13e6685827ea91af1fb2ffcc4dbfd451 /mm/hugetlb.c
parente35ef6397b8273a0059a2b837c26f92b0ecf8596 (diff)
downloadlinux-d715cf804a0318e83c75c0a7abd1a4b9ce13e8da.tar.bz2
mm/hugetlb.c: warn the user when issues arise on boot due to hugepages
When the user specifies too many hugepages or an invalid default_hugepagesz the communication to the user is implicit in the allocation message. This patch adds a warning when the desired page count is not allocated and prints an error when the default_hugepagesz is invalid on boot. During boot hugepages will allocate until there is a fraction of the hugepage size left. That is, we allocate until either the request is satisfied or memory for the pages is exhausted. When memory for the pages is exhausted, it will most likely lead to the system failing with the OOM manager not finding enough (or anything) to kill (unless you're using really big hugepages in the order of 100s of MB or in the GBs). The user will most likely see the OOM messages much later in the boot sequence than the implicitly stated message. Worse yet, you may even get an OOM for each processor which causes many pages of OOMs on modern systems. Although these messages will be printed earlier than the OOM messages, at least giving the user errors and warnings will highlight the configuration as an issue. I'm trying to point the user in the right direction by providing a more robust statement of what is failing. During the sysctl or echo command, the user can check the results much easier than if the system hangs during boot and the scenario of having nothing to OOM for kernel memory is highly unlikely. Mike said: "Before sending out this patch, I asked Liam off list why he was doing it. Was it something he just thought would be useful? Or, was there some type of user situation/need. He said that he had been called in to assist on several occasions when a system OOMed during boot. In almost all of these situations, the user had grossly misconfigured huge pages. DB users want to pre-allocate just the right amount of huge pages, but sometimes they can be really off. In such situations, the huge page init code just allocates as many huge pages as it can and reports the number allocated. There is no indication that it quit allocating because it ran out of memory. Of course, a user could compare the number in the message to what they requested on the command line to determine if they got all the huge pages they requested. The thought was that it would be useful to at least flag this situation. That way, the user might be able to better relate the huge page allocation failure to the OOM. I'm not sure if the e-mail discussion made it obvious that this is something he has seen on several occasions. I see Michal's point that this will only flag the situation where someone configures huge pages very badly. And, a more extensive look at the situation of misconfiguring huge pages might be in order. But, this has happened on several occasions which led to the creation of this patch" [akpm@linux-foundation.org: reposition memfmt() to avoid forward declaration] Link: http://lkml.kernel.org/r/20170603005413.10380-1-Liam.Howlett@Oracle.com Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com> Cc: zhongjiang <zhongjiang@huawei.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r--mm/hugetlb.c36
1 files changed, 24 insertions, 12 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8254e8f6db6b..761a669d0b62 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -70,6 +70,17 @@ struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
/* Forward declaration */
static int hugetlb_acct_memory(struct hstate *h, long delta);
+static char * __init memfmt(char *buf, unsigned long n)
+{
+ if (n >= (1UL << 30))
+ sprintf(buf, "%lu GB", n >> 30);
+ else if (n >= (1UL << 20))
+ sprintf(buf, "%lu MB", n >> 20);
+ else
+ sprintf(buf, "%lu KB", n >> 10);
+ return buf;
+}
+
static inline void unlock_or_release_subpool(struct hugepage_subpool *spool)
{
bool free = (spool->count == 0) && (spool->used_hpages == 0);
@@ -2212,7 +2223,14 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
&node_states[N_MEMORY]))
break;
}
- h->max_huge_pages = i;
+ if (i < h->max_huge_pages) {
+ char buf[32];
+
+ memfmt(buf, huge_page_size(h)),
+ pr_warn("HugeTLB: allocating %lu of page size %s failed. Only allocated %lu hugepages.\n",
+ h->max_huge_pages, buf, i);
+ h->max_huge_pages = i;
+ }
}
static void __init hugetlb_init_hstates(void)
@@ -2230,17 +2248,6 @@ static void __init hugetlb_init_hstates(void)
VM_BUG_ON(minimum_order == UINT_MAX);
}
-static char * __init memfmt(char *buf, unsigned long n)
-{
- if (n >= (1UL << 30))
- sprintf(buf, "%lu GB", n >> 30);
- else if (n >= (1UL << 20))
- sprintf(buf, "%lu MB", n >> 20);
- else
- sprintf(buf, "%lu KB", n >> 10);
- return buf;
-}
-
static void __init report_hugepages(void)
{
struct hstate *h;
@@ -2808,6 +2815,11 @@ static int __init hugetlb_init(void)
return 0;
if (!size_to_hstate(default_hstate_size)) {
+ if (default_hstate_size != 0) {
+ pr_err("HugeTLB: unsupported default_hugepagesz %lu. Reverting to %lu\n",
+ default_hstate_size, HPAGE_SIZE);
+ }
+
default_hstate_size = HPAGE_SIZE;
if (!size_to_hstate(default_hstate_size))
hugetlb_add_hstate(HUGETLB_PAGE_ORDER);