Re: [dpdk-dev] [PATCH 2/3] app/compress-perf: add performance measurement

["Jozwiak, TomaszX" <tomaszx.jozwiak@intel.com>]

Hi Shally,

Please see my comment inline.

> -----Original Message-----
> From: Verma, Shally [mailto:Shally.Verma@cavium.com]
> Sent: Monday, November 5, 2018 9:34 AM
> To: Jozwiak, TomaszX <tomaszx.jozwiak@intel.com>; dev@dpdk.org; Trahe,
> Fiona <fiona.trahe@intel.com>; akhil.goyal@nxp.com; De Lara Guarch, Pablo
> <pablo.de.lara.guarch@intel.com>
> Cc: De@dpdk.org; Lara@dpdk.org; Guarch@dpdk.org
> Subject: RE: [dpdk-dev] [PATCH 2/3] app/compress-perf: add performance
> measurement
> 
> 
> 
> >-----Original Message-----
> >From: Jozwiak, TomaszX <tomaszx.jozwiak@intel.com>
> >Sent: 02 November 2018 15:29
> >To: dev@dpdk.org; Trahe, Fiona <fiona.trahe@intel.com>;
> >akhil.goyal@nxp.com; Verma, Shally <Shally.Verma@cavium.com>; De Lara
> >Guarch, Pablo <pablo.de.lara.guarch@intel.com>
> >Cc: De@dpdk.org; Lara@dpdk.org; Guarch@dpdk.org
> >Subject: RE: [dpdk-dev] [PATCH 2/3] app/compress-perf: add performance
> >measurement
> >
> >External Email
> >
> >Hi Shally,
> >
> >Sorry for delay - I was on sick leave.
> >We had some issues with dynamic compression test so I block this test
> >in V2. May be there's too late to add this into this release but we've decided
> to send this V2 to DPDK.
> >
> >My comment inline (not all have answer so far, still working on that)
> >
> >> -----Original Message-----
> >> From: Verma, Shally [mailto:Shally.Verma@cavium.com]
> >> Sent: Friday, October 12, 2018 12:16 PM
> >> To: Jozwiak, TomaszX <tomaszx.jozwiak@intel.com>; dev@dpdk.org;
> >> Trahe, Fiona <fiona.trahe@intel.com>; akhil.goyal@nxp.com; De Lara
> >> Guarch, Pablo <pablo.de.lara.guarch@intel.com>
> >> Cc: De@dpdk.org; Lara@dpdk.org; Guarch@dpdk.org
> >> Subject: RE: [dpdk-dev] [PATCH 2/3] app/compress-perf: add
> >> performance measurement
> >>
> >> HI TomaszX
> >>
> >> Sorry for delay in response. Comments inline.
> >>
> >> >-----Original Message-----
> >> >From: dev <dev-bounces@dpdk.org> On Behalf Of Tomasz Jozwiak
> >> >Sent: 01 October 2018 18:57
> >> >To: dev@dpdk.org; fiona.trahe@intel.com; tomaszx.jozwiak@intel.com;
> >> >akhil.goyal@nxp.com; pablo.de.lara.guarch@intel.com
> >> >Cc: De@dpdk.org; Lara@dpdk.org; Guarch@dpdk.org
> >> >Subject: [dpdk-dev] [PATCH 2/3] app/compress-perf: add performance
> >> >measurement
> >> >
> >> >External Email
> >> >
> >> >Added performance measurement part into compression perf. test.
> >> >
> >> >Signed-off-by: De Lara Guarch, Pablo
> >> ><pablo.de.lara.guarch@intel.com>
> >> >Signed-off-by: Tomasz Jozwiak <tomaszx.jozwiak@intel.com>
> >> >---
> >> > app/test-compress-perf/main.c | 844
> >> >++++++++++++++++++++++++++++++++++++++++++
> >> > 1 file changed, 844 insertions(+)
> >> >
> >> >diff --git a/app/test-compress-perf/main.c
> >> >b/app/test-compress-perf/main.c index f52b98d..093dfaf 100644
> >> >--- a/app/test-compress-perf/main.c
> >> >+++ b/app/test-compress-perf/main.c
> >> >@@ -5,13 +5,721 @@
> >> > #include <rte_malloc.h>
> >> > #include <rte_eal.h>
> >> > #include <rte_log.h>
> >> >+#include <rte_cycles.h>
> >> > #include <rte_compressdev.h>
> >> >
> >> > #include "comp_perf_options.h"
> >> >
> >> >+#define NUM_MAX_XFORMS 16
> >> >+#define NUM_MAX_INFLIGHT_OPS 512
> >> >+#define EXPANSE_RATIO 1.05
> >> >+#define MIN_ISAL_SIZE 8
> >> >+
> >> >+#define DIV_CEIL(a, b)  ((a) / (b) + ((a) % (b) != 0))
> >> >+
> >> >+static int
> >> >+param_range_check(uint16_t size, const struct rte_param_log2_range
> >> >+*range) {
> >> >+       unsigned int next_size;
> >> >+
> >> >+       /* Check lower/upper bounds */
> >> >+       if (size < range->min)
> >> >+               return -1;
> >> >+
> >> >+       if (size > range->max)
> >> >+               return -1;
> >> >+
> >> >+       /* If range is actually only one value, size is correct */
> >> >+       if (range->increment == 0)
> >> >+               return 0;
> >> >+
> >> >+       /* Check if value is one of the supported sizes */
> >> >+       for (next_size = range->min; next_size <= range->max;
> >> >+                       next_size += range->increment)
> >> >+               if (size == next_size)
> >> >+                       return 0;
> >> >+
> >> >+       return -1;
> >> >+}
> >> >+
> >> >+static int
> >> >+comp_perf_check_capabilities(struct comp_test_data *test_data) {
> >> >+       const struct rte_compressdev_capabilities *cap;
> >> >+
> >> >+       cap = rte_compressdev_capability_get(test_data->cdev_id,
> >> >+                                            RTE_COMP_ALGO_DEFLATE);
> >> >+
> >> >+       if (cap == NULL) {
> >> >+               RTE_LOG(ERR, USER1,
> >> >+                       "Compress device does not support DEFLATE\n");
> >> >+               return -1;
> >> >+       }
> >> >+
> >> >+       uint64_t comp_flags = cap->comp_feature_flags;
> >> >+
> >> >+       /* Huffman enconding */
> >> >+       if (test_data->huffman_enc == RTE_COMP_HUFFMAN_FIXED &&
> >> >+                       (comp_flags & RTE_COMP_FF_HUFFMAN_FIXED) == 0) {
> >> >+               RTE_LOG(ERR, USER1,
> >> >+                       "Compress device does not supported Fixed Huffman\n");
> >> >+               return -1;
> >> >+       }
> >> >+
> >> >+       if (test_data->huffman_enc == RTE_COMP_HUFFMAN_DYNAMIC
> &&
> >> >+                       (comp_flags & RTE_COMP_FF_HUFFMAN_DYNAMIC) == 0)
> {
> >> >+               RTE_LOG(ERR, USER1,
> >> >+                       "Compress device does not supported Dynamic
> Huffman\n");
> >> >+               return -1;
> >> >+       }
> >> >+
> >> >+       /* Window size */
> >> >+       if (test_data->window_sz != -1) {
> >> >+               if (param_range_check(test_data->window_sz,
> >> >+ &cap->window_size)
> >> What if cap->window_size is 0 i.e. implementation default?
> >
> >TJ: You probably mean cap->window_size.increment = 0 (because
> >cap->window_size is a structure). In that case we check if
> >test_data->window_sz >=min and test_data->window_sz <= max only,
> because increment = 0 means (base on compression API) we have only one
> value of windows_size (no range is supported).
> But PMD can set min and max too 0 for such case.

TJ: I can't see any issue in that case too. Maybe I don't understand what you mean but the logic is as follow:
1)  if you pass '--window-sz  ...' param. into command line your intention is to force that value of window size during test. We check is this value is allow (by param_range_check() function).
2) if you plan to use default value - just don't pass '--window-sz' param. in command line at all. In that case we get windows size from window_size.max field, so if window_size.min= window_size.max=0 
test_data->window_sz will be zero, as well. 
If you mean that behavior is not good - I will be grateful for other suggestions.

> 
> >
> >
> >
> ....
> 
> >> >+
> >> >+               if (fread(data, data_to_read, 1, f) != 1) {
> >> >+                       RTE_LOG(ERR, USER1, "Input file could not be read\n");
> >> >+                       goto err;
> >> >+               }
> >> >+               if (fseek(f, 0, SEEK_SET) != 0) {
> >> >+                       RTE_LOG(ERR, USER1,
> >> >+                               "Size of input could not be calculated\n");
> >> >+                       goto err;
> >> >+               }
> >> >+               remaining_data -= data_to_read;
> >> >+               data += data_to_read;
> >> It looks like it will run 2nd time only if input file size < input
> >> data size in which case it will just keep filling input buffer with repeated
> data.
> >> Is that the intention here?
> >
> >TJ: Yes exactly. If test_data->input_data_sz is bigger than
> >actual_file_sz then we fill the buffer with repeated data from file to fill
> whole buffer.
> I mentioned in one of the earlier reply, wont that then influence the
> compression behaviour and o/p? my suggestion was to work on actual user
> provided input to take perf to get actual perf for given content.

TJ: You right, but this solution is flexible. You can pass ' --extended-input-sz" or not, so you can use original input data or extend it if you want.

> 
> >
> >>
> ...
> 
> >> >+                       if (data_addr == NULL) {
> >> >+                               RTE_LOG(ERR, USER1, "Could not
> >> >+ append data\n");
> >> Since a new buffer per segment is allocated, so is it possible for
> >> append to fail? think, this check is redundant here.
> >
> >TJ: Yes, you're right, it should never fail. But I think it's good coding practice
> to add the check just in case.
> >
> Unless it is called in data path which might cost perf a bit.

TJ:  prepare_bufs() is out of perf measurement, so shouldn't impact to measurements. The performance measurement is inside main_loop() only.


Br, Tomek

> 
> Thanks
> Shally
> 
> >> >+                               return -1;
> >> >+                       }
> >> >+
> >> >+                       rte_memcpy(data_addr, input_data_ptr, data_sz);
> >> >+                       input_data_ptr += data_sz;
> >> >+                       remaining_data -= data_sz;
> >> >+
> >> >+                       if (rte_pktmbuf_chain(test_data->decomp_bufs[i],
> >> >+                                       next_seg) < 0) {
> >> >+                               RTE_LOG(ERR, USER1, "Could not chain mbufs\n");
> >> >+                               return -1;
> >> >+                       }
> >> >+                       segs_per_mbuf++;
> >> >+               }
> >> >+
> >> >+               /* Allocate data in output mbuf */
> >> >+               test_data->comp_bufs[i] =
> >> >+                       rte_pktmbuf_alloc(test_data->comp_buf_pool);
> >> >+               if (test_data->comp_bufs[i] == NULL) {
> >> >+                       RTE_LOG(ERR, USER1, "Could not allocate mbuf\n");
> >> >+                       return -1;
> >> >+               }
> >> >+               data_addr = (uint8_t *) rte_pktmbuf_append(
> >> >+                                       test_data->comp_bufs[i],
> >> >+                                       test_data->seg_sz);
> >> >+               if (data_addr == NULL) {
> >> >+                       RTE_LOG(ERR, USER1, "Could not append data\n");
> >> >+                       return -1;
> >> >+               }
> >> >+
> >> >+               /* Chain mbufs if needed for output mbufs */
> >> >+               for (j = 1; j < segs_per_mbuf; j++) {
> >> >+                       struct rte_mbuf *next_seg =
> >> >+
> >> >+ rte_pktmbuf_alloc(test_data->comp_buf_pool);
> >> >+
> >> >+                       if (next_seg == NULL) {
> >> >+                               RTE_LOG(ERR, USER1,
> >> >+                                       "Could not allocate mbuf\n");
> >> >+                               return -1;
> >> >+                       }
> >> >+
> >> >+                       data_addr = (uint8_t *)rte_pktmbuf_append(next_seg,
> >> >+                               test_data->seg_sz);
> >> >+
> >> >+                       if (data_addr == NULL) {
> >> >+                               RTE_LOG(ERR, USER1, "Could not append data\n");
> >> >+                               return -1;
> >> >+                       }
> >> >+
> >> >+                       if (rte_pktmbuf_chain(test_data->comp_bufs[i],
> >> >+                                       next_seg) < 0) {
> >> >+                               RTE_LOG(ERR, USER1, "Could not chain mbufs\n");
> >> >+                               return -1;
> >> >+                       }
> >> >+               }
> >> >+       }
> >> >+
> >> >+       return 0;
> >> >+}
> >> >+
> >> >+static void
> >> >+free_bufs(struct comp_test_data *test_data) {
> >> >+       uint32_t i;
> >> >+
> >> >+       for (i = 0; i < test_data->total_bufs; i++) {
> >> >+               rte_pktmbuf_free(test_data->comp_bufs[i]);
> >> >+               rte_pktmbuf_free(test_data->decomp_bufs[i]);
> >> >+       }
> >> >+       rte_free(test_data->comp_bufs);
> >> >+       rte_free(test_data->decomp_bufs); }
> >> >+
> >> >+static int
> >> >+main_loop(struct comp_test_data *test_data, uint8_t level,
> >> >+                       enum rte_comp_xform_type type,
> >> >+                       uint8_t *output_data_ptr,
> >> >+                       size_t *output_data_sz,
> >> >+                       unsigned int benchmarking) {
> >> >+       uint8_t dev_id = test_data->cdev_id;
> >> >+       uint32_t i, iter, num_iter;
> >> >+       struct rte_comp_op **ops, **deq_ops;
> >> >+       void *priv_xform = NULL;
> >> >+       struct rte_comp_xform xform;
> >> >+       size_t output_size = 0;
> >> >+       struct rte_mbuf **input_bufs, **output_bufs;
> >> >+       int res = 0;
> >> >+       int allocated = 0;
> >> >+
> >> >+       if (test_data == NULL || !test_data->burst_sz) {
> >> >+               RTE_LOG(ERR, USER1,
> >> >+                       "Unknow burst size\n");
> >> >+               return -1;
> >> >+       }
> >> >+
> >> >+       ops = rte_zmalloc_socket(NULL,
> >> >+               2 * test_data->total_bufs * sizeof(struct rte_comp_op *),
> >> >+               0, rte_socket_id());
> >> >+
> >> >+       if (ops == NULL) {
> >> >+               RTE_LOG(ERR, USER1,
> >> >+                       "Can't allocate memory for ops strucures\n");
> >> >+               return -1;
> >> >+       }
> >> >+
> >> >+       deq_ops = &ops[test_data->total_bufs];
> >> >+
> >> >+       if (type == RTE_COMP_COMPRESS) {
> >> >+               xform = (struct rte_comp_xform) {
> >> >+                       .type = RTE_COMP_COMPRESS,
> >> >+                       .compress = {
> >> >+                               .algo = RTE_COMP_ALGO_DEFLATE,
> >> >+                               .deflate.huffman = test_data->huffman_enc,
> >> >+                               .level = level,
> >> >+                               .window_size = test_data->window_sz,
> >> >+                               .chksum = RTE_COMP_CHECKSUM_NONE,
> >> >+                               .hash_algo = RTE_COMP_HASH_ALGO_NONE
> >> >+                       }
> >> >+               };
> >> >+               input_bufs = test_data->decomp_bufs;
> >> >+               output_bufs = test_data->comp_bufs;
> >> >+       } else {
> >> >+               xform = (struct rte_comp_xform) {
> >> >+                       .type = RTE_COMP_DECOMPRESS,
> >> >+                       .decompress = {
> >> >+                               .algo = RTE_COMP_ALGO_DEFLATE,
> >> >+                               .chksum = RTE_COMP_CHECKSUM_NONE,
> >> >+                               .window_size = test_data->window_sz,
> >> >+                               .hash_algo = RTE_COMP_HASH_ALGO_NONE
> >> >+                       }
> >> >+               };
> >> >+               input_bufs = test_data->comp_bufs;
> >> >+               output_bufs = test_data->decomp_bufs;
> >> >+       }
> >> >+
> >> >+       /* Create private xform */
> >> >+       if (rte_compressdev_private_xform_create(dev_id, &xform,
> >> >+                       &priv_xform) < 0) {
> >> >+               RTE_LOG(ERR, USER1, "Private xform could not be created\n");
> >> >+               res = -1;
> >> >+               goto end;
> >> >+       }
> >> >+
> >> >+       uint64_t tsc_start, tsc_end, tsc_duration;
> >> >+
> >> >+       tsc_start = tsc_end = tsc_duration = 0;
> >> >+       if (benchmarking) {
> >> >+               tsc_start = rte_rdtsc();
> >> >+               num_iter = test_data->num_iter;
> >> >+       } else
> >> >+               num_iter = 1;
> >> Looks like in same code we're doing benchmarking and functional
> validation.
> >> It can be reorganised to keep validation test separately like done in
> >> crypto_perf.
> >
> >TJ: Ok, makes sense. However in the interests of getting this into the
> >18.11 release I'd like to defer this refactoring and the remainder of your
> comments below to the next release.
> >
> >
> >Next comments - WIP
> >
> >
> >Br, Tomek