rcuperf: Add support to vary the slab object sizes
PATCH 1/2 rcuperf: Add support to vary the slab object sizes
This patch varies the allocated size of objects to be more realistic in comparison to production workloads.
--- kernel/rcu/rcuperf.c | 48 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 41 insertions(+), 7 deletions(-)
kernel/rcu/rcuperf.c +41 -7
@@ -87,6 +87,7 @@ torture_param(bool, shutdown, RCUPERF_SHUTDOWN,torture_param (int, verbose,1 ,"Enable verbose debugging printk()s" );torture_param (int, writer_holdoff,0 ,"Holdoff (us) between GPs, zero to disable" );torture_param (int, kfree_rcu_test,0 ,"Do we run a kfree_rcu() perf test?" ); +torture_param (bool, kfree_vary_obj_size,0 ,"Vary the kfree_rcu object size" );static char *perf_type ="rcu" ;module_param (perf_type, charp,0444 );
@@ -599,17 +600,29 @@ static int kfree_nrealthreads;static atomic_t n_kfree_perf_thread_started;static atomic_t n_kfree_perf_thread_ended; -struct kfree_obj { -char kfree_obj[8 ]; -struct rcu_head rh; -}; +/* +* Define a kfree_obj with size as the @size parameter + the size of rcu_head +* (rcu_head is 16 bytes on 64-bit arch). +*/ +#define DEFINE_KFREE_OBJ (size) \ +struct kfree_obj_ ## size { \ + char kfree_obj[size]; \ + struct rcu_head rh; \ +} + +/* This should goto the right sized slabs on both 32-bit and 64-bit arch */ +DEFINE_KFREE_OBJ (16 );// goes on kmalloc-32 slab +DEFINE_KFREE_OBJ (32 );// goes on kmalloc-64 slab +DEFINE_KFREE_OBJ (64 );// goes on kmalloc-96 slab +DEFINE_KFREE_OBJ (96 );// goes on kmalloc-128 slab static int kfree_perf_thread (void *arg) {int i, loop =0 ;long me = (long )arg; -struct kfree_obj *alloc_ptr; +void *alloc_ptr; +u64 start_time, end_time;VERBOSE_PERFOUT_STRING ("kfree_perf_thread task started" );
@@ -627,11 +640,32 @@ kfree_perf_thread(void *arg) do { for (i = 0; i < kfree_alloc_num; i++) { - alloc_ptr = kmalloc(sizeof(struct kfree_obj), GFP_KERNEL); + int kfree_type = i % 4; + + // Allocate only kfree_obj_16 if rcuperf.kfree_vary_obj_size not passed. + if (!kfree_vary_obj_size) + kfree_type = 0; + + if (kfree_type == 0) + alloc_ptr = kmalloc(sizeof(struct kfree_obj_16), GFP_KERNEL); + else if (kfree_type == 1) + alloc_ptr = kmalloc(sizeof(struct kfree_obj_32), GFP_KERNEL); + else if (kfree_type == 2) + alloc_ptr = kmalloc(sizeof(struct kfree_obj_64), GFP_KERNEL); + else + alloc_ptr = kmalloc(sizeof(struct kfree_obj_96), GFP_KERNEL); + if (!alloc_ptr) return -ENOMEM; - kfree_rcu(alloc_ptr, rh); + if (kfree_type == 0) + kfree_rcu((struct kfree_obj_16 *)alloc_ptr, rh); + else if (kfree_type == 1) + kfree_rcu((struct kfree_obj_32 *)alloc_ptr, rh); + else if (kfree_type == 2) + kfree_rcu((struct kfree_obj_64 *)alloc_ptr, rh); + else + kfree_rcu((struct kfree_obj_96 *)alloc_ptr, rh); } cond_resched();
Signature · 1 line
2.25.0.rc1.283.g88dfdc4193-goog
PATCH 2/2 rcuperf: Measure memory footprint during kfree_rcu() test (v4)
During changes to kfree_rcu() code, we often check the amount of free memory. As an alternative to checking this manually, this commit adds a measurement in the test itself. It measures four times during the test for available memory, digitally filters these measurements to produce a running average with a weight of 0.5, and compares this digitally filtered value with the amount of available memory at the beginning of the test.
We apply the digital filter only once we are more than 25% into the test. At the 25% mark, we just read available memory and don't apply any filtering. This prevents the first sample from skewing the results as we would not consider memory readings that were before memory was allocated.
A sample run shows something like:
Total time taken by all kfree'ers: 6369738407 ns, loops: 10000, batches: 764, memory footprint: 216MB
---v1->v2: Minor correctionsv1->v3: Use long long to prevent 32-bit system's overflow
Handle case where some threads start later than others. Start measuring only once 25% into the test. Slightly more accurate.v3->v4: Simplified test more. Using simple average.
kernel/rcu/rcuperf.c | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-)
kernel/rcu/rcuperf.c +25 -3
@@ -12,6 +12,7 @@#include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> +#include <linux/mm.h> #include <linux/module.h> #include <linux/kthread.h> #include <linux/err.h>
@@ -616,14 +617,17 @@ DEFINE_KFREE_OBJ(32); // goes on kmalloc-64 slabDEFINE_KFREE_OBJ (64 );// goes on kmalloc-96 slab DEFINE_KFREE_OBJ (96 );// goes on kmalloc-128 slab +long long mem_begin; +static int kfree_perf_thread (void *arg) {int i, loop =0 ;long me = (long )arg;void *alloc_ptr; -u64 start_time, end_time; +long mem_samples =0 ; +long long mem_during =0 ;VERBOSE_PERFOUT_STRING ("kfree_perf_thread task started" );set_cpus_allowed_ptr (current,cpumask_of (me % nr_cpu_ids));
@@ -638,7 +642,17 @@ kfree_perf_thread(void *arg) b_rcu_gp_test_started = cur_ops->get_gp_seq (); } +// Prevent "% 0" error below. +if (kfree_loops <4 ) + kfree_loops =4 ; + do { + // Start measuring only from when we are at least 25% into the test. + if ((loop != 0) && (loop % (kfree_loops / 4) == 0)) { + mem_during = mem_during + si_mem_available(); + mem_samples++; + } + for (i = 0; i < kfree_alloc_num; i++) { int kfree_type = i % 4;
@@ -671,6 +685,8 @@ kfree_perf_thread(void *arg)cond_resched (); }while (!torture_must_stop () && ++loop < kfree_loops); + mem_during = (mem_during / mem_samples); +if (atomic_inc_return (&n_kfree_perf_thread_ended) >= kfree_nrealthreads) { end_time =ktime_get_mono_fast_ns ();
@@ -679,9 +695,13 @@ kfree_perf_thread(void *arg)else b_rcu_gp_test_finished = cur_ops->get_gp_seq (); -pr_alert ("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld\n" , +// The "memory footprint" field represents how much in-flight +// memory is allocated during the test and waiting to be freed. +pr_alert ("Total time taken by all kfree'ers: %llu ns, loops: %d, batches: %ld, memory footprint: %lldMB\n" , (unsigned long long )(end_time - start_time), kfree_loops, -rcuperf_seq_diff (b_rcu_gp_test_finished, b_rcu_gp_test_started)); +rcuperf_seq_diff (b_rcu_gp_test_finished, b_rcu_gp_test_started), + (mem_begin - mem_during) >> (20 -PAGE_SHIFT )); +if (shutdown) {smp_mb ();/* Assign before wake. */ wake_up (&shutdown_wq);
@@ -753,6 +773,8 @@ kfree_perf_init(void) goto unwind; } + mem_begin =si_mem_available (); +for (i =0 ; i < kfree_nrealthreads; i++) { firsterr =torture_create_kthread (kfree_perf_thread, (void *)i, kfree_reader_tasks[i]);
Signature · 1 line
2.25.0.rc1.283.g88dfdc4193-goog
kbuild test robot
build botRe: [PATCH 2/2] rcuperf: Measure memory footprint during kfree_rcu() test (v4)
Thank you for the patch! Yet something to improve:
Hi "Joel,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on next-20200116]
[cannot apply to rcu/dev linux/master linus/master v5.5-rc6 v5.5-rc5 v5.5-rc4 v5.5-rc6] [if your patch is applied to the wrong git tree, please drop us a note to help improve the system. BTW, we also suggest to use '--base' option to specify the base tree in git format-patch, please see https://stackoverflow.com/a/37406982]
url: https://github.com/0day-ci/linux/commits/Joel-Fernandes-Google/rcuperf-Add-support-to-vary-the-slab-object-sizes/20200117-101205 base: 2747d5fdab78f43210256cd52fb2718e0b3cce74 config: m68k-allmodconfig (attached as .config) compiler: m68k-linux-gcc (GCC) 7.5.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
GCC_VERSION=7.5.0 make.cross ARCH=m68k
If you fix the issue, kindly add following tag
All errors (new ones prefixed by >>):
>> ERROR: "__divdi3" [kernel/rcu/rcuperf.ko] undefined!
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org Intel Corporation
kbuild test robot
build botRe: [PATCH 2/2] rcuperf: Measure memory footprint during kfree_rcu() test (v4)
In reply to Joel Fernandes (Google)Thank you for the patch! Yet something to improve:
Hi "Joel,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on next-20200116]
[cannot apply to rcu/dev linux/master linus/master v5.5-rc6 v5.5-rc5 v5.5-rc4 v5.5-rc6] [if your patch is applied to the wrong git tree, please drop us a note to help improve the system. BTW, we also suggest to use '--base' option to specify the base tree in git format-patch, please see https://stackoverflow.com/a/37406982]
url: https://github.com/0day-ci/linux/commits/Joel-Fernandes-Google/rcuperf-Add-support-to-vary-the-slab-object-sizes/20200117-101205 base: 2747d5fdab78f43210256cd52fb2718e0b3cce74 config: arm-allyesconfig (attached as .config) compiler: arm-linux-gnueabi-gcc (GCC) 7.5.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
GCC_VERSION=7.5.0 make.cross ARCH=arm
If you fix the issue, kindly add following tag
All errors (new ones prefixed by >>):
kernel/rcu/rcuperf.o: In function `kfree_perf_thread':
>> rcuperf.c:(.text+0xb5c): undefined reference to `__aeabi_ldivmod'
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org Intel Corporation
kbuild test robot
build botRe: [PATCH 2/2] rcuperf: Measure memory footprint during kfree_rcu() test (v4)
In reply to Joel Fernandes (Google)Thank you for the patch! Perhaps something to improve:
Hi "Joel,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on next-20200116]
[cannot apply to rcu/dev linux/master linus/master v5.5-rc6 v5.5-rc5 v5.5-rc4 v5.5] [if your patch is applied to the wrong git tree, please drop us a note to help improve the system. BTW, we also suggest to use '--base' option to specify the base tree in git format-patch, please see https://stackoverflow.com/a/37406982]
url: https://github.com/0day-ci/linux/commits/Joel-Fernandes-Google/rcuperf-Add-support-to-vary-the-slab-object-sizes/20200117-101205 base: 2747d5fdab78f43210256cd52fb2718e0b3cce74 reproduce: # apt-get install sparse # sparse version: v0.6.1-153-g47b6dfef-dirty make ARCH=x86_64 allmodconfig make C=1 CF='-fdiagnostic-prefix -D__CHECK_ENDIAN__'
If you fix the issue, kindly add following tag
sparse warnings: (new ones prefixed by >>)
>> kernel/rcu/rcuperf.c:620:11: sparse: sparse: symbol 'mem_begin' was not declared. Should it be static?
Please review and possibly fold the followup patch.
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/hyperkitty/list/kbuild-all(a)lists.01.org Intel Corporation
kbuild test robot
build bot[RFC PATCH] rcuperf: mem_begin can be static
In reply to Joel Fernandes (Google)Fixes: e4b6bfefb245 ("rcuperf: Measure memory footprint during kfree_rcu() test (v4)")
--- rcuperf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/rcu/rcuperf.c +1 -1
@@ -617,7 +617,7 @@ DEFINE_KFREE_OBJ(32); // goes on kmalloc-64 slabDEFINE_KFREE_OBJ (64 );// goes on kmalloc-96 slab DEFINE_KFREE_OBJ (96 );// goes on kmalloc-128 slab -long long mem_begin; +static long long mem_begin;static int kfree_perf_thread (void *arg)
Hello, Joel.
Quoted 95 lines
This patch varies the allocated size of objects to be more realistic in comparison to production workloads.
Signed-off-by Joel Fernandes (Google) <[email protected]>--- kernel/rcu/rcuperf.c | 48 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 41 insertions(+), 7 deletions(-)kernel/rcu/rcuperf.c +41
-7@@ -87,6 +87,7 @@ torture_param(bool, shutdown, RCUPERF_SHUTDOWN,torture_param (int, verbose,1 ,"Enable verbose debugging printk()s" );torture_param (int, writer_holdoff,0 ,"Holdoff (us) between GPs, zero to disable" );torture_param (int, kfree_rcu_test,0 ,"Do we run a kfree_rcu() perf test?" ); +torture_param (bool, kfree_vary_obj_size,0 ,"Vary the kfree_rcu object size" );static char *perf_type ="rcu" ;module_param (perf_type, charp,0444 );@@ -599,17 +600,29 @@ static int kfree_nrealthreads;static atomic_t n_kfree_perf_thread_started;static atomic_t n_kfree_perf_thread_ended; -struct kfree_obj { -char kfree_obj[8 ]; -struct rcu_head rh; -}; +/* +* Define a kfree_obj with size as the @size parameter + the size of rcu_head +* (rcu_head is 16 bytes on 64-bit arch). +*/ +#define DEFINE_KFREE_OBJ (size) \ +struct kfree_obj_ ## size { \ + char kfree_obj[size]; \ + struct rcu_head rh; \ +} + +/* This should goto the right sized slabs on both 32-bit and 64-bit arch */ +DEFINE_KFREE_OBJ (16 );// goes on kmalloc-32 slab +DEFINE_KFREE_OBJ (32 );// goes on kmalloc-64 slab +DEFINE_KFREE_OBJ (64 );// goes on kmalloc-96 slab +DEFINE_KFREE_OBJ (96 );// goes on kmalloc-128 slab static int kfree_perf_thread (void *arg) {int i, loop =0 ;long me = (long )arg; -struct kfree_obj *alloc_ptr; +void *alloc_ptr; +u64 start_time, end_time;VERBOSE_PERFOUT_STRING ("kfree_perf_thread task started" );@@ -627,11 +640,32 @@ kfree_perf_thread(void *arg) do { for (i = 0; i < kfree_alloc_num; i++) { - alloc_ptr = kmalloc(sizeof(struct kfree_obj), GFP_KERNEL); + int kfree_type = i % 4; + + // Allocate only kfree_obj_16 if rcuperf.kfree_vary_obj_size not passed. + if (!kfree_vary_obj_size) + kfree_type = 0; + + if (kfree_type == 0) + alloc_ptr = kmalloc(sizeof(struct kfree_obj_16), GFP_KERNEL); + else if (kfree_type == 1) + alloc_ptr = kmalloc(sizeof(struct kfree_obj_32), GFP_KERNEL); + else if (kfree_type == 2) + alloc_ptr = kmalloc(sizeof(struct kfree_obj_64), GFP_KERNEL); + else + alloc_ptr = kmalloc(sizeof(struct kfree_obj_96), GFP_KERNEL); + if (!alloc_ptr) return -ENOMEM; - kfree_rcu(alloc_ptr, rh); + if (kfree_type == 0) + kfree_rcu((struct kfree_obj_16 *)alloc_ptr, rh); + else if (kfree_type == 1) + kfree_rcu((struct kfree_obj_32 *)alloc_ptr, rh); + else if (kfree_type == 2) + kfree_rcu((struct kfree_obj_64 *)alloc_ptr, rh); + else + kfree_rcu((struct kfree_obj_96 *)alloc_ptr, rh); } cond_resched();Signature · 1 line
2.25.0.rc1.283.g88dfdc4193-goog
Good point and patch!
--
Vlad Rezki