Add kunit tests to benchmark 256MiB copies to a UBUF iterator and an IOVEC
iterator. This attaches a userspace VM with a mapped file in it
temporarily to the test thread.
Signed-off-by: David Howells <[email protected]>
cc: Andrew Morton <[email protected]>
cc: Christoph Hellwig <[email protected]>
cc: Christian Brauner <[email protected]>
cc: Jens Axboe <[email protected]>
cc: Al Viro <[email protected]>
cc: Matthew Wilcox <[email protected]>
cc: David Hildenbrand <[email protected]>
cc: John Hubbard <[email protected]>
cc: Brendan Higgins <[email protected]>
cc: David Gow <[email protected]>
cc: [email protected]
cc: [email protected]
cc: [email protected]
cc: [email protected]
---
lib/kunit_iov_iter.c | 85 ++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 85 insertions(+)
diff --git a/lib/kunit_iov_iter.c b/lib/kunit_iov_iter.c
index f8d0cd6a2923..cc9c64663a73 100644
--- a/lib/kunit_iov_iter.c
+++ b/lib/kunit_iov_iter.c
@@ -1304,6 +1304,89 @@ static void *__init iov_kunit_create_source(struct kunit *test, size_t npages)
return scratch;
}
+/*
+ * Time copying 256MiB through an ITER_UBUF.
+ */
+static void __init iov_kunit_benchmark_ubuf(struct kunit *test)
+{
+ struct iov_iter iter;
+ unsigned int samples[IOV_KUNIT_NR_SAMPLES];
+ ktime_t a, b;
+ ssize_t copied;
+ size_t size = 256 * 1024 * 1024, npages = size / PAGE_SIZE;
+ void *scratch;
+ int i;
+ u8 __user *buffer;
+
+ /* Allocate a huge buffer and populate it with pages. */
+ buffer = iov_kunit_create_user_buf(test, npages, NULL);
+
+ /* Create a single large buffer to copy to/from. */
+ scratch = iov_kunit_create_source(test, npages);
+
+ /* Perform and time a bunch of copies. */
+ kunit_info(test, "Benchmarking copy_to_iter() over UBUF:\n");
+ for (i = 0; i < IOV_KUNIT_NR_SAMPLES; i++) {
+ iov_iter_ubuf(&iter, ITER_DEST, buffer, size);
+
+ a = ktime_get_real();
+ copied = copy_to_iter(scratch, size, &iter);
+ b = ktime_get_real();
+ KUNIT_EXPECT_EQ(test, copied, size);
+ samples[i] = ktime_to_us(ktime_sub(b, a));
+ }
+
+ iov_kunit_benchmark_print_stats(test, samples);
+ KUNIT_SUCCEED();
+}
+
+/*
+ * Time copying 256MiB through an ITER_IOVEC.
+ */
+static void __init iov_kunit_benchmark_iovec(struct kunit *test)
+{
+ struct iov_iter iter;
+ struct iovec iov[8];
+ unsigned int samples[IOV_KUNIT_NR_SAMPLES];
+ ktime_t a, b;
+ ssize_t copied;
+ size_t size = 256 * 1024 * 1024, npages = size / PAGE_SIZE, part;
+ void *scratch;
+ int i;
+ u8 __user *buffer;
+
+ /* Allocate a huge buffer and populate it with pages. */
+ buffer = iov_kunit_create_user_buf(test, npages, NULL);
+
+ /* Create a single large buffer to copy to/from. */
+ scratch = iov_kunit_create_source(test, npages);
+
+ /* Split the target over a number of iovecs */
+ copied = 0;
+ for (i = 0; i < ARRAY_SIZE(iov); i++) {
+ part = size / ARRAY_SIZE(iov);
+ iov[i].iov_base = buffer + copied;
+ iov[i].iov_len = part;
+ copied += part;
+ }
+ iov[i - 1].iov_len += size - part;
+
+ /* Perform and time a bunch of copies. */
+ kunit_info(test, "Benchmarking copy_to_iter() over IOVEC:\n");
+ for (i = 0; i < IOV_KUNIT_NR_SAMPLES; i++) {
+ iov_iter_init(&iter, ITER_DEST, iov, ARRAY_SIZE(iov), size);
+
+ a = ktime_get_real();
+ copied = copy_to_iter(scratch, size, &iter);
+ b = ktime_get_real();
+ KUNIT_EXPECT_EQ(test, copied, size);
+ samples[i] = ktime_to_us(ktime_sub(b, a));
+ }
+
+ iov_kunit_benchmark_print_stats(test, samples);
+ KUNIT_SUCCEED();
+}
+
/*
* Time copying 256MiB through an ITER_KVEC.
*/
@@ -1504,6 +1587,8 @@ static struct kunit_case __refdata iov_kunit_cases[] = {
KUNIT_CASE(iov_kunit_extract_pages_kvec),
KUNIT_CASE(iov_kunit_extract_pages_bvec),
KUNIT_CASE(iov_kunit_extract_pages_xarray),
+ KUNIT_CASE(iov_kunit_benchmark_ubuf),
+ KUNIT_CASE(iov_kunit_benchmark_iovec),
KUNIT_CASE(iov_kunit_benchmark_kvec),
KUNIT_CASE(iov_kunit_benchmark_bvec),
KUNIT_CASE(iov_kunit_benchmark_bvec_split),
From: David Howells
> Sent: 14 September 2023 23:15
>
> Add kunit tests to benchmark 256MiB copies to a UBUF iterator and an IOVEC
> iterator. This attaches a userspace VM with a mapped file in it
> temporarily to the test thread.
Isn't that going to be completely dominated by the cache fills
from memory?
I'd have thought you'd need to use something with a lot of
small fragments so that the iteration code dominates the copy.
Some measurements can be made using readv() and writev()
on /dev/zero and /dev/null.
David
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
David Laight <[email protected]> wrote:
> > Add kunit tests to benchmark 256MiB copies to a UBUF iterator and an IOVEC
> > iterator. This attaches a userspace VM with a mapped file in it
> > temporarily to the test thread.
>
> Isn't that going to be completely dominated by the cache fills
> from memory?
Yes... but it should be consistent in the amount of time that consumes since
no device drivers are involved. I can try adding the same folio to the
anon_file multiple times - it might work especially if I don't put the pages
on the LRU (if that's even possible) - but I wanted separate pages for the
extraction test.
> I'd have thought you'd need to use something with a lot of
> small fragments so that the iteration code dominates the copy.
That would actually be a separate benchmark case which I should try also.
> Some measurements can be made using readv() and writev()
> on /dev/zero and /dev/null.
Forget /dev/null; that doesn't actually engage any iteration code. The same
for writing to /dev/zero. Reading from /dev/zero does its own iteration thing
rather than using iterate_and_advance(), presumably because it checks for
signals and resched.
David
From: David Howells
> Sent: 15 September 2023 12:23
>
> David Laight <[email protected]> wrote:
>
> > > > Some measurements can be made using readv() and writev()
> > > > on /dev/zero and /dev/null.
> > >
> > > Forget /dev/null; that doesn't actually engage any iteration code. The same
> > > for writing to /dev/zero. Reading from /dev/zero does its own iteration thing
> > > rather than using iterate_and_advance(), presumably because it checks for
> > > signals and resched.
> >
> > Using /dev/null does exercise the 'copy iov from user' code.
>
> Ummm.... Not really:
I was thinking of import_iovec() - or whatever its current
name is.
That really needs a single structure that contains the iov_iter
and the cache[] (which the caller pretty much always allocates
in the same place).
Fiddling with that is ok until you find what io_uring does.
Then it all gets entirely horrid.
David
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
From: David Howells
> Sent: 15 September 2023 13:36
>
> David Laight <[email protected]> wrote:
>
> > I was thinking of import_iovec() - or whatever its current
> > name is.
>
> That doesn't actually access the buffer described by the iovec[].
>
> > That really needs a single structure that contains the iov_iter
> > and the cache[] (which the caller pretty much always allocates
> > in the same place).
>
> cache[]?
Ah it is usually called iovstack[].
That is the code that reads the iovec[] from user.
For small counts there is an on-stack cache[], for large
counts it has call kmalloc().
So when the io completes you have to free the allocated buffer.
A canonical example is:
static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
unsigned long vlen, loff_t *pos, rwf_t flags)
{
struct iovec iovstack[UIO_FASTIOV];
struct iovec *iov = iovstack;
struct iov_iter iter;
ssize_t ret;
ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
if (ret >= 0) {
ret = do_iter_read(file, &iter, pos, flags);
kfree(iov);
}
return ret;
}
If 'iter' and 'iovstack' are put together in a structure the
calling sequence becomes much less annoying.
The kfree() can (probably) check iter.iovec != iovsatack (as an inline).
But io_uring manages to allocate the iov_iter and iovstack[] in
entirely different places - and then copies them about.
David
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
David Laight <[email protected]> wrote:
> > > Some measurements can be made using readv() and writev()
> > > on /dev/zero and /dev/null.
> >
> > Forget /dev/null; that doesn't actually engage any iteration code. The same
> > for writing to /dev/zero. Reading from /dev/zero does its own iteration thing
> > rather than using iterate_and_advance(), presumably because it checks for
> > signals and resched.
>
> Using /dev/null does exercise the 'copy iov from user' code.
Ummm.... Not really:
static ssize_t read_null(struct file *file, char __user *buf,
size_t count, loff_t *ppos)
{
return 0;
}
static ssize_t write_null(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
return count;
}
static ssize_t read_iter_null(struct kiocb *iocb, struct iov_iter *to)
{
return 0;
}
static ssize_t write_iter_null(struct kiocb *iocb, struct iov_iter *from)
{
size_t count = iov_iter_count(from);
iov_iter_advance(from, count);
return count;
}
David
From: David Howells
> Sent: 15 September 2023 11:10
>
> David Laight <[email protected]> wrote:
>
> > > Add kunit tests to benchmark 256MiB copies to a UBUF iterator and an IOVEC
> > > iterator. This attaches a userspace VM with a mapped file in it
> > > temporarily to the test thread.
> >
> > Isn't that going to be completely dominated by the cache fills
> > from memory?
>
> Yes... but it should be consistent in the amount of time that consumes since
> no device drivers are involved. I can try adding the same folio to the
> anon_file multiple times - it might work especially if I don't put the pages
> on the LRU (if that's even possible) - but I wanted separate pages for the
> extraction test.
You could also just not do the copy!
Although you need (say) asm volatile("\n",:::"memory") to
stop it all being completely optimised away.
That might show up a difference in the 'out_of_line' test
where 15% on top on the data copies is massive - it may be
that the data cache behaviour is very different for the
two cases.
...
> > Some measurements can be made using readv() and writev()
> > on /dev/zero and /dev/null.
>
> Forget /dev/null; that doesn't actually engage any iteration code. The same
> for writing to /dev/zero. Reading from /dev/zero does its own iteration thing
> rather than using iterate_and_advance(), presumably because it checks for
> signals and resched.
Using /dev/null does exercise the 'copy iov from user' code.
Last time I looked at that the 32bit compat code was faster than
the 64bit code on x86!
David
-
Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
Registration No: 1397386 (Wales)
David Laight <[email protected]> wrote:
> Isn't that going to be completely dominated by the cache fills
> from memory?
>
> I'd have thought you'd need to use something with a lot of
> small fragments so that the iteration code dominates the copy.
Okay, if I switch it to using MAP_ANON for the big 256MiB buffer, switch all
the benchmarking tests to use copy_from_iter() rather than copy_to_iter() and
make the iovec benchmark use a separate iovec for each page, there's then a
single page replicated across the mapping.
Given that, without my macro-to-inline-func patches applied, I see:
iov_kunit_benchmark_bvec: avg 3184 uS, stddev 16 uS
iov_kunit_benchmark_bvec: avg 3189 uS, stddev 17 uS
iov_kunit_benchmark_bvec: avg 3190 uS, stddev 16 uS
iov_kunit_benchmark_bvec_outofline: avg 3731 uS, stddev 10 uS
iov_kunit_benchmark_bvec_outofline: avg 3735 uS, stddev 10 uS
iov_kunit_benchmark_bvec_outofline: avg 3738 uS, stddev 11 uS
iov_kunit_benchmark_bvec_split: avg 3403 uS, stddev 10 uS
iov_kunit_benchmark_bvec_split: avg 3405 uS, stddev 18 uS
iov_kunit_benchmark_bvec_split: avg 3407 uS, stddev 29 uS
iov_kunit_benchmark_iovec: avg 6616 uS, stddev 20 uS
iov_kunit_benchmark_iovec: avg 6619 uS, stddev 22 uS
iov_kunit_benchmark_iovec: avg 6621 uS, stddev 46 uS
iov_kunit_benchmark_kvec: avg 2671 uS, stddev 12 uS
iov_kunit_benchmark_kvec: avg 2671 uS, stddev 13 uS
iov_kunit_benchmark_kvec: avg 2675 uS, stddev 12 uS
iov_kunit_benchmark_ubuf: avg 6191 uS, stddev 1946 uS
iov_kunit_benchmark_ubuf: avg 6418 uS, stddev 3263 uS
iov_kunit_benchmark_ubuf: avg 6443 uS, stddev 3275 uS
iov_kunit_benchmark_xarray: avg 3689 uS, stddev 5 uS
iov_kunit_benchmark_xarray: avg 3689 uS, stddev 6 uS
iov_kunit_benchmark_xarray: avg 3698 uS, stddev 22 uS
iov_kunit_benchmark_xarray_outofline: avg 4202 uS, stddev 3 uS
iov_kunit_benchmark_xarray_outofline: avg 4204 uS, stddev 9 uS
iov_kunit_benchmark_xarray_outofline: avg 4210 uS, stddev 9 uS
and with, I get:
iov_kunit_benchmark_bvec: avg 3241 uS, stddev 13 uS
iov_kunit_benchmark_bvec: avg 3245 uS, stddev 16 uS
iov_kunit_benchmark_bvec: avg 3248 uS, stddev 15 uS
iov_kunit_benchmark_bvec_outofline: avg 3705 uS, stddev 12 uS
iov_kunit_benchmark_bvec_outofline: avg 3706 uS, stddev 10 uS
iov_kunit_benchmark_bvec_outofline: avg 3709 uS, stddev 9 uS
iov_kunit_benchmark_bvec_split: avg 3446 uS, stddev 10 uS
iov_kunit_benchmark_bvec_split: avg 3447 uS, stddev 12 uS
iov_kunit_benchmark_bvec_split: avg 3448 uS, stddev 12 uS
iov_kunit_benchmark_iovec: avg 6587 uS, stddev 22 uS
iov_kunit_benchmark_iovec: avg 6587 uS, stddev 22 uS
iov_kunit_benchmark_iovec: avg 6590 uS, stddev 27 uS
iov_kunit_benchmark_kvec: avg 2671 uS, stddev 12 uS
iov_kunit_benchmark_kvec: avg 2672 uS, stddev 12 uS
iov_kunit_benchmark_kvec: avg 2676 uS, stddev 19 uS
iov_kunit_benchmark_ubuf: avg 6241 uS, stddev 2199 uS
iov_kunit_benchmark_ubuf: avg 6266 uS, stddev 2245 uS
iov_kunit_benchmark_ubuf: avg 6513 uS, stddev 3899 uS
iov_kunit_benchmark_xarray: avg 3695 uS, stddev 6 uS
iov_kunit_benchmark_xarray: avg 3695 uS, stddev 7 uS
iov_kunit_benchmark_xarray: avg 3703 uS, stddev 11 uS
iov_kunit_benchmark_xarray_outofline: avg 4215 uS, stddev 16 uS
iov_kunit_benchmark_xarray_outofline: avg 4217 uS, stddev 20 uS
iov_kunit_benchmark_xarray_outofline: avg 4224 uS, stddev 10 uS
Interestingly, most of them are quite tight, but UBUF is all over the place.
That's with the test covering the entire 256M span with a single UBUF
iterator, so it would seem unlikely that the difference is due to the
iteration framework.
David
David Laight <[email protected]> wrote:
> I was thinking of import_iovec() - or whatever its current
> name is.
That doesn't actually access the buffer described by the iovec[].
> That really needs a single structure that contains the iov_iter
> and the cache[] (which the caller pretty much always allocates
> in the same place).
cache[]?
> Fiddling with that is ok until you find what io_uring does.
> Then it all gets entirely horrid.
That statement sounds like back-of-the-OLS-T-shirt material ;-)
David
David Laight <[email protected]> wrote:
> You could also just not do the copy!
> Although you need (say) asm volatile("\n",:::"memory") to
> stop it all being completely optimised away.
> That might show up a difference in the 'out_of_line' test
> where 15% on top on the data copies is massive - it may be
> that the data cache behaviour is very different for the
> two cases.
I tried using the following as the load:
volatile unsigned long foo;
static __always_inline
size_t idle_user_iter(void __user *iter_from, size_t progress,
size_t len, void *to, void *priv2)
{
nop();
nop();
foo += (unsigned long)iter_from;
foo += (unsigned long)len;
foo += (unsigned long)to + progress;
nop();
nop();
return 0;
}
static __always_inline
size_t idle_kernel_iter(void *iter_from, size_t progress,
size_t len, void *to, void *priv2)
{
nop();
nop();
foo += (unsigned long)iter_from;
foo += (unsigned long)len;
foo += (unsigned long)to + progress;
nop();
nop();
return 0;
}
size_t iov_iter_idle(struct iov_iter *iter, size_t len, void *priv)
{
return iterate_and_advance(iter, len, priv,
idle_user_iter, idle_kernel_iter);
}
EXPORT_SYMBOL(iov_iter_idle);
adding various things into a volatile variable to prevent the optimiser from
discarding the calculations.
I get:
iov_kunit_benchmark_bvec: avg 395 uS, stddev 46 uS
iov_kunit_benchmark_bvec: avg 397 uS, stddev 38 uS
iov_kunit_benchmark_bvec: avg 411 uS, stddev 57 uS
iov_kunit_benchmark_bvec_outofline: avg 781 uS, stddev 5 uS
iov_kunit_benchmark_bvec_outofline: avg 781 uS, stddev 6 uS
iov_kunit_benchmark_bvec_outofline: avg 781 uS, stddev 7 uS
iov_kunit_benchmark_bvec_split: avg 3599 uS, stddev 737 uS
iov_kunit_benchmark_bvec_split: avg 3664 uS, stddev 838 uS
iov_kunit_benchmark_bvec_split: avg 3669 uS, stddev 875 uS
iov_kunit_benchmark_iovec: avg 472 uS, stddev 17 uS
iov_kunit_benchmark_iovec: avg 506 uS, stddev 59 uS
iov_kunit_benchmark_iovec: avg 525 uS, stddev 14 uS
iov_kunit_benchmark_kvec: avg 421 uS, stddev 73 uS
iov_kunit_benchmark_kvec: avg 428 uS, stddev 68 uS
iov_kunit_benchmark_kvec: avg 469 uS, stddev 75 uS
iov_kunit_benchmark_ubuf: avg 1052 uS, stddev 6 uS
iov_kunit_benchmark_ubuf: avg 1168 uS, stddev 8 uS
iov_kunit_benchmark_ubuf: avg 1168 uS, stddev 9 uS
iov_kunit_benchmark_xarray: avg 680 uS, stddev 11 uS
iov_kunit_benchmark_xarray: avg 682 uS, stddev 20 uS
iov_kunit_benchmark_xarray: avg 686 uS, stddev 46 uS
iov_kunit_benchmark_xarray_outofline: avg 1340 uS, stddev 34 uS
iov_kunit_benchmark_xarray_outofline: avg 1358 uS, stddev 12 uS
iov_kunit_benchmark_xarray_outofline: avg 1358 uS, stddev 15 uS
where I made the iovec and kvec tests split their buffers into PAGE_SIZE
segments and the ubuf test issue an iteration per PAGE_SIZE'd chunk.
Splitting kvec into just 8 results in the iteration taking <1uS.
The bvec_split test is doing a kmalloc() per 256 pages inside of the loop,
which is why that takes quite a long time.
David