Update guide with instructions to run on Aarch64 based Ampere Altra
platform
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
v3:
- Fix duplicate target warning by using anonymous reference
v2:
- Update driver guide with instructions to run on aarch64 instead
---
.mailmap
Update guide with instructions to run on Aarch64 based Ampere Altra
platform
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
v2:
- Update driver guide with instructions to run on aarch64 instead
of release notes.
---
.mailmap | 2 +-
doc/guides/cryptodevs
From: Kamalakshitha Aligeri
Integrated zero-copy put API in mempool cache in i40e PMD.
On Ampere Altra server, l3fwd single core's performance improves by 5%
with the new API
Signed-off-by: Kamalakshitha Aligeri
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Reviewed-by: F
: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Acked-by: Konstantin Ananyev
Acked-by: Chengwen Feng
---
v12:
* Fix CI compilation issues on [patch 2/2] in the series
v11:
* Changed patch description and version to 23.07
v10:
* Added mempool test cases with zero-copy API's
v9:
* Also set rte_err
Update release notes with added support for QAT on Ampere Altra.
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
doc/guides/rel_notes/release_23_07.rst | 4
1 file changed, 4 insertions(+)
diff --git a/doc/guides/rel_notes/release_23_07.rst
b/doc/guides/rel_notes
Hi,
Thank you for the comments!
Based on the suggestions, I tested the patch for single core L3Fwd performance
with increased number of routes/flows (maximum 8K) to increase cache footprint.
However, I don’t see much improvement with the patch.
> On Jan 21, 2022, at 5:25 AM, Ananyev, Konstantin
Hi Konstatin,
> On Jan 13, 2022, at 4:37 AM, Ananyev, Konstantin
> wrote:
>
>
> Hi Dharmik,
>
>>>
Current mempool per core cache implementation stores pointers to mbufs
On 64b architectures, each pointer consumes 8B
This patch replaces it with index-based implementation,
cache
L3Fwd performance testing reveals minor improvements in the cache
performance (L1 and L2 misses reduced by 0.60%)
with no change in throughput
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
lib/mempool/rte_mempool.h | 150
ing
---
Dharmik Thakkar (1):
mempool: implement index-based per core cache
lib/mempool/rte_mempool.h | 150 +-
lib/mempool/rte_mempool_ops_default.c | 7 ++
2 files changed, 156 insertions(+), 1 deletion(-)
--
2.17.1
gt;>> From: Bruce Richardson [mailto:bruce.richard...@intel.com]
>>>>> Sent: Friday, 7 January 2022 12.16
>>>>>
>>>>> On Sat, Dec 25, 2021 at 01:16:03AM +0100, Morten Brørup wrote:
>>>>>>> From: Dharmik Thakkar [mailto:dha
_bulk=32 n_keep=32 :
> 1262052966.00/1007039283.00/-20.21
> cache=512 cores=2 n_get_bulk=32 n_put_bulk=32 n_keep=128 :
> 1517853081.00/1230818508.00/-18.91
> cache=512 cores=8 n_get_bulk=32 n_put_bulk=32 n_keep=32
> :5054529533.00/4028052273.00/-20.31
> cache=512
red
Dharmik Thakkar (1):
mempool: implement index-based per core cache
lib/mempool/rte_mempool.h | 114 +-
lib/mempool/rte_mempool_ops_default.c | 7 ++
2 files changed, 119 insertions(+), 2 deletions(-)
--
2.25.1
cache
L3Fwd performance testing reveals minor improvements in the cache
performance (L1 and L2 misses reduced by 0.60%)
with no change in throughput
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
lib/mempool/rte_mempool.h | 114
> On Nov 3, 2021, at 10:52 AM, Morten Brørup wrote:
>
>> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Dharmik Thakkar
>> Sent: Wednesday, 3 November 2021 16.13
>>
>> Hi,
>>
>> Thank you everyone for the comments! I am currently w
Hi,
Thank you everyone for the comments! I am currently working on making the
global pool ring’s implementation as index based.
Once done, I will send a patch for community review. I will also make it as a
compile time option.
> On Oct 31, 2021, at 3:14 AM, Morten Brørup wrote:
>
>> From: Mor
towards examples dir.
Another recently upstreamed patch series [1] also reported a similar CI failure.
Thus, this looks like a common CI issue.
[1]
https://lab.dpdk.org/results/dashboard/patchsets/19456/
> On Oct 13, 2021, at 1:54 PM, Dharmik Thakkar wrote:
>
> From: Joyce Kong
>
From: Joyce Kong
In stack module, remove the header file rte_atomic.h
as it is not being used.
Signed-off-by: Joyce Kong
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
v2:
Change commit message (Olivier)
---
app/test/test_stack.c | 1 -
lib/stack/rte_stack.c | 1 -
lib
From: Joyce Kong
Remove the unnecessary header file rte_atomic.h
included in example module.
Signed-off-by: Joyce Kong
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
examples/bond/main.c | 1 -
examples/ip_fragmentation/main.c
From: Joyce Kong
Convert rte_atomic32_test_and_set to compiler CAS atomic
operation for display_stats sync.
Signed-off-by: Joyce Kong
Reviewed-by: Ruifeng Wang
---
examples/server_node_efd/server/main.c | 7 ---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/examples/server
From: Joyce Kong
Convert rte_atomic32_cmpset to compiler atomic CAS
operation for channel status sync.
Signed-off-by: Joyce Kong
Reviewed-by: Ruifeng Wang
---
examples/vm_power_manager/channel_monitor.c | 11 ++-
1 file changed, 6 insertions(+), 5 deletions(-)
diff --git a/examples/v
From: Joyce Kong
Convert rte_atomic usages to compiler atomic built-ins
for stats_read_pending sync in l2fwd_jobstats module.
Signed-off-by: Joyce Kong
Reviewed-by: Ruifeng Wang
---
examples/l2fwd-jobstats/main.c | 11 +--
1 file changed, 5 insertions(+), 6 deletions(-)
diff --git a/
From: Joyce Kong
Convert rte_atomic usages to compiler atomic built-ins
for thread sync.
Signed-off-by: Joyce Kong
Reviewed-by: Ruifeng Wang
---
examples/performance-thread/common/lthread.c | 10 +++---
.../performance-thread/common/lthread_diag.h | 10 +++---
.../performance-thread/common/
From: Joyce Kong
Convert rte_atomic usages to compiler atomic builit-ins
for kni_stop and kni_pause sync.
Signed-off-by: Joyce Kong
Reviewed-by: Ruifeng Wang
---
examples/kni/main.c | 27 +--
1 file changed, 13 insertions(+), 14 deletions(-)
diff --git a/examples/kni/
From: Joyce Kong
Convert rte_atomic32_test_and_set usage to compiler atomic
CAS operation for display_stats sync.
Signed-off-by: Joyce Kong
Reviewed-by: Ruifeng Wang
---
examples/multi_process/client_server_mp/mp_server/main.c | 7 ---
1 file changed, 4 insertions(+), 3 deletions(-)
diff
From: Joyce Kong
Convert rte_atomic usages to compiler atomic built-ins
for global_exit_flag sync.
Signed-off-by: Joyce Kong
Reviewed-by: Ruifeng Wang
---
examples/bbdev_app/main.c | 13 ++---
1 file changed, 6 insertions(+), 7 deletions(-)
diff --git a/examples/bbdev_app/main.c b/ex
Since atomic operations have been adopted in DPDK now[1],
change rte_atomicNN_xxx APIs to compiler's atomic built-ins
in examples module[2].
[1] https://www.dpdk.org/blog/2021/03/26/dpdk-adopts-the-c11-memory-model/
[2] https://doc.dpdk.org/guides/rel_notes/deprecation.html
v3:
Keep rte_atomic.
d-off-by: Dharmik Thakkar
---
drivers/mempool/ring/rte_mempool_ring.c | 2 +-
lib/mempool/rte_mempool.c | 8 +++
lib/mempool/rte_mempool.h | 74 ++---
3 files changed, 74 insertions(+), 10 deletions(-)
diff --git a/drivers/mempool
Convert rte_atomic usages to compiler atomic built-ins
for stats sync
Signed-off-by: Dharmik Thakkar
Reviewed-by: Joyce Kong
Reviewed-by: Ruifeng Wang
---
app/test/test_hash_multiwriter.c | 19
app/test/test_hash_readwrite.c | 80 +++-
2 files changed
Hi,
Apologies for the delayed response!
> On Mar 10, 2021, at 9:10 AM, Stephen Hemminger
> wrote:
>
> On Wed, 10 Mar 2021 12:10:01 +0100
> Thomas Monjalon wrote:
>
>> 10/03/2021 12:04, Dharmik Thakkar:
>>> Enable volatile considered harmful warning sin
Hi,
Kathleen has submitted an RFC patch [1] in this regard. We’d appreciate your
comments.
[1]
https://patches.dpdk.org/project/dpdk/patch/20210430213747.41530-2-kathleen.cape...@arm.com/
Thank you!
> On Apr 30, 2021, at 4:28 AM, Ananyev, Konstantin
> wrote:
>
>>
>>
>> On Thu, Apr 29, 2021
From: Joyce Kong
If cache is enabled, objects will be retrieved/put from/to cache,
subsequently from/to the common pool. Now the debug stats calculate
the objects retrieved/put from/to cache and pool together, it is
better to distinguish them.
Signed-off-by: Joyce Kong
Signed-off-by: Dharmik
Make __MEMPOOL_STAT_ADD macro more generic and delete
__MEMPOOL_CONTIG_BLOCKS_STAT_ADD macro
Suggested-by: Olivier Matz
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa Nagarahalli
Acked-by: Olivier Matz
---
lib/mempool/rte_mempool.h | 34
ro generic
- Remove other stat add/subtract macros
- Rename counters for better understanding
- Add put/get cache bulk counters
v2:
- Fix typo in the commit message
---
Dharmik Thakkar (1):
mempool: make stats macro generic
Joyce Kong (1):
mempool: distinguish debug counters from cache and
+Honnappa
> On Apr 22, 2021, at 8:29 PM, Dharmik Thakkar wrote:
>
> From: Joyce Kong
>
> If cache is enabled, objects will be retrieved/put from/to cache,
> subsequently from/to the common pool. Now the debug stats calculate
> the objects retrieved/put from/to cache and
Make __MEMPOOL_STAT_ADD macro more generic and delete
__MEMPOOL_CONTIG_BLOCKS_STAT_ADD macro
Suggested-by: Olivier Matz
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa Nagarahalli
Acked-by: Olivier Matz
---
lib/mempool/rte_mempool.h | 34
From: Joyce Kong
If cache is enabled, objects will be retrieved/put from/to cache,
subsequently from/to the common pool. Now the debug stats calculate
the objects retrieved/put from/to cache and pool together, it is
better to distinguish them.
Signed-off-by: Joyce Kong
Signed-off-by: Dharmik
bulk counters
v2:
- Fix typo in the commit message
---
Dharmik Thakkar (1):
lib/mempool: make stats macro generic
Joyce Kong (1):
lib/mempool: distinguish debug counters from cache and pool
lib/mempool/rte_mempool.c | 16 ++
lib/mempool/rte_mempool.h | 67
Hi Olivier,
Thank you for your comments!
> On Apr 21, 2021, at 11:29 AM, Olivier Matz wrote:
>
> Hi Dharmik,
>
> Please see some comments below.
>
> On Mon, Apr 19, 2021 at 07:08:00PM -0500, Dharmik Thakkar wrote:
>> From: Joyce Kong
>>
>> If cache is
Hi Olivier,
Apologies for the delayed response!
I’m stepping in since Joyce is on vacation.
I have updated the patch with the required changes.
Thank you!
> On Apr 7, 2021, at 9:28 AM, Olivier Matz wrote:
From: Joyce Kong
If cache is enabled, objects will be retrieved/put from/to cache,
subsequently from/to the common pool. Now the debug stats calculate
the objects retrieved/put from/to cache and pool together, it is
better to distinguish them.
Signed-off-by: Joyce Kong
Signed-off-by: Dharmik
Make __MEMPOOL_STAT_ADD macro more generic and delete
__MEMPOOL_CONTIG_BLOCKS_STAT_ADD macro
Suggested-by: Olivier Matz
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa Nagarahalli
---
lib/librte_mempool/rte_mempool.h | 34 +++-
1
v2:
- Fix typo in the commit message
---
Dharmik Thakkar (1):
lib/mempool: make stats macro generic
Joyce Kong (1):
lib/mempool: distinguish debug counters from cache and pool
lib/librte_mempool/rte_mempool.c | 24 +++
lib/librte_mempool/rte_mempool.h | 71
Enable volatile considered harmful warning since use of volatile
is suspect.
Suggested-by: Stephen Hemminger
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
devtools/checkpatches.sh | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/devtools/checkpatches.sh b
rite the values for any (native, SoC or cross) build
>
Tested ok on N1SDP and ThunderX2. No regression seen with testpmd and l3fwd.
Tested using native build, default build and using arm_soc option.
Series Tested-by: Dharmik Thakkar
armv8.html
Suggested-by: Thomas Monjalon
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
drivers/crypto/armv8/meson.build | 19 ---
meson_options.txt| 2 --
2 files changed, 4 insertions(+), 17 deletions(-)
diff --git a/drivers/crypto/armv8/meson.build
Remove build steps about using meson option armv8_crypto_dir.
Add build steps about using pkg-config.
Suggested-by: Thomas Monjalon
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
doc/guides/cryptodevs/armv8.rst | 10 --
1 file changed, 8 insertions(+), 2 deletions
Remove redundant error checking for reader threads
since they never return error.
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa N
Return error if Add/Delete fail in multiwriter perf test
Return error if single or multi writer test fails
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
R
ance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa Nagarahalli
---
app/test/test_lpm_perf.c | 45 ++--
1 file changed, 16 insertions(+), 29 deletions(-)
diff --git a/
Avoid code duplication by combining single and multi threaded tests
Also, enable support for more than 2 writers
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa Nagarahalli
---
app/test/test_lpm_perf.c | 356 +--
1 file
re details about the fix to the commit message
- Replace hard coded values with an enum
- Remove lock acquire/release for single writer
Dharmik Thakkar (4):
test/lpm: fix cycle calculation in rcu qsbr perf
test/lpm: return error on failure in rcu qsbr perf
test/lpm: remove error checking in rcu
> On Nov 4, 2020, at 9:46 AM, Medvedkin, Vladimir
> wrote:
>
> Hi Thakkar,
>
> On 03/11/2020 22:23, Dharmik Thakkar wrote:
>> Avoid code duplication by combining single and multi threaded tests
>> Also, enable support for more than 2 writers
>> Signed-off
ance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa Nagarahalli
---
app/test/test_lpm_perf.c | 45 ++--
1 file changed, 16 insertions(+), 29 deletions(-)
diff --git a/
Avoid code duplication by combining single and multi threaded tests
Also, enable support for more than 2 writers
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_perf.c | 359 +--
1 file changed, 84 insertions(+), 275 deletions
Return error if Add/Delete fail in multiwriter perf test
Return error if single or multi writer test fails
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
R
Remove redundant error checking for reader threads
since they never return error.
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa N
gle writer
Dharmik Thakkar (4):
test/lpm: fix cycle calculation in rcu qsbr perf
test/lpm: return error on failure in rcu qsbr perf
test/lpm: remove error checking in rcu qsbr perf
test/lpm: avoid code duplication in rcu qsbr perf
app/test/test_lpm_perf.c | 383 ++--
> On Nov 2, 2020, at 11:32 PM, Honnappa Nagarahalli
> wrote:
>
>
>
>>>>
>>>> Avoid code duplication by combining single and multi threaded tests
>>>>
>>>> Signed-off-by: Dharmik Thakkar
>>>&
Remove redundant error checking for reader threads
since they never return error.
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_p
ance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Reviewed-by: Honnappa Nagarahalli
---
app/test/test_lpm_perf.c | 45 ++--
1 file changed, 16 insertions(+), 29 deletions(-)
diff --git a/
tement
v2:
- Add more details about the fix to the commit message
- Replace hard coded values with an enum
- Remove lock acquire/release for single writer
Dharmik Thakkar (4):
test/lpm: fix cycle calculation in rcu qsbr perf
test/lpm: return error on failure in rcu qsbr perf
test/lpm: re
Return error if Add/Delete fail in multiwriter perf test
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_perf.c | 6 ++
1 file
Avoid code duplication by combining single and multi threaded tests
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_perf.c | 359 ++-
1 file changed, 89 insertions(+), 270 deletions(-)
diff --git a/app/test/test_lpm_perf.c b
;> Cc: honnappa.nagaraha...@arm.com
>> Cc: sta...@dpdk.org
>>
>> Signed-off-by: Dharmik Thakkar
>> Reviewed-by: Ruifeng Wang
>> ---
>> app/test/test_lpm_perf.c | 21 -
>> 1 file changed, 8 insertions(+), 13 deletions(-)
>>
>> d
> On Nov 2, 2020, at 7:28 PM, Honnappa Nagarahalli
> wrote:
>
>
>
>>
>> Return error if Add/Delete fail in multiwriter perf test
>>
>> Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
>> Cc: honnappa.nagaraha...@arm.c
> On Nov 2, 2020, at 10:21 PM, Honnappa Nagarahalli
> wrote:
>
>
>>
>> Avoid code duplication by combining single and multi threaded tests
>>
>> Signed-off-by: Dharmik Thakkar
>> Reviewed-by: Ruifeng Wang
ance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_perf.c | 45 ++--
1 file changed, 16 insertions(+), 29 deletions(-)
diff --git a/app/test/test_lpm_perf.c b/app/
Remove redundant error checking for reader threads
since they never return error.
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_p
Return error if Add/Delete fail in multiwriter perf test
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_perf.c | 4
1 file
- Replace hard coded values with an enum
- Remove lock acquire/release for single writer
Dharmik Thakkar (4):
test/lpm: fix cycle calculation in rcu qsbr perf
test/lpm: return error on failure in rcu qsbr perf
test/lpm: remove error checking in rcu qsbr perf
test/lpm: avoid code duplication in
Avoid code duplication by combining single and multi threaded tests
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_perf.c | 362 ++-
1 file changed, 91 insertions(+), 271 deletions(-)
diff --git a/app/test/test_lpm_perf.c b
> On Nov 2, 2020, at 11:17 AM, Medvedkin, Vladimir
> wrote:
>
> Hi Dharmik,
>
> Thanks for the patches, see comments inlined
>
>
> On 29/10/2020 15:36, Dharmik Thakkar wrote:
>> Avoid code duplication by combining single and multi threaded tests
> On Nov 2, 2020, at 9:11 AM, Bruce Richardson
> wrote:
>
> On Thu, Oct 29, 2020 at 10:36:31AM -0500, Dharmik Thakkar wrote:
>> Fix incorrect calculations for LPM adds, LPM deletes,
>> and average cycles in RCU QSBR perf tests
>>
>
> To help review thi
nfo**:
> ``rx_err_drop_offload_capa:RTE_DEV_RX_ERR_PKT_DROP_OFFLOAD_L4_CSUM``.
> +
> +
> +.. _nic_features_all_rx_error_packet_drop:
> +
> +All/any Error Packet drop on Rx
> +---
> +
> +Supports dropping of packets having any of the errors like L1 FSC, L3/L4
> Checksum on Rx.
s/FSC/FCS
> +
> +* **[uses] user config**: ``dev_conf.err_pkt_drop_conf.all``.
> +* **[provides] rte_eth_dev_info**:
> ``rx_err_drop_offload_capa:RTE_DEV_RX_ERR_PKT_DROP_OFFLOAD_ALL``.
> +
> +
> .. _nic_features_packet_type_parsing:
>
> Packet type parsing
> diff --git a/doc/guides/testpmd_app_ug/run_app.rst
> b/doc/guides/testpmd_app_ug/run_app.rst
> index e2539f693..20f2f8083 100644
> --- a/doc/guides/testpmd_app_ug/run_app.rst
> +++ b/doc/guides/testpmd_app_ug/run_app.rst
> @@ -213,6 +213,10 @@ The command line options are:
>
> Enable hardware QINQ strip.
>
> +* ``--enable-hw-drop-err-all``
> +
> +Enable hardware packet drop for any error packets
> +
> * ``--enable-drop-en``
>
> Enable per-queue packet drop for packets with no descriptors.
> —
> 2.17.1
>
Reviewed-by: Dharmik Thakkar
Avoid code duplication by combining single and multi threaded tests
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_perf.c | 338 +--
1 file changed, 73 insertions(+), 265 deletions(-)
diff --git a/app/test/test_lpm_perf.c b
Return error if Add/Delete fail in multiwriter perf test
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_perf.c | 4
1 file
Remove redundant error checking for reader threads
since they never return error.
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_lpm_p
Fix incorrect calculations for LPM adds, LPM deletes,
and average cycles in RCU QSBR perf tests
Fixes: eff30b59cc2e ("test/lpm: add RCU performance tests")
Cc: honnappa.nagaraha...@arm.com
Cc: sta...@dpdk.org
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
Hi Zhou,
Although, I see that a few of the configuration options are checking for
’test_done’, I am wondering if it is truly required.
Since, as per the documentation guidelines:
'Configuration changes only become active when forwarding is started/restarted.’
> On Oct 27, 2020, at 1:42 AM, Zhou
Apologies for the disclaimer!
> On Oct 27, 2020, at 9:59 AM, Dharmik Thakkar wrote:
>
> Hi Yunjian,
>
> Thank you for fixing the issue!
>
>> On Oct 27, 2020, at 7:51 AM, wangyunjian wrote:
>>
>> From: Yunjian Wang
>>
>> Coverity flags that
ries + 1;
>
> if (h == NULL || cfg == NULL || cfg->v == NULL) {
> rte_errno = EINVAL;
> return 1;
> }
>
> +const uint32_t total_entries = h->use_local_cache ?
> +h->entries + (RTE_MAX_LCORE - 1) * (LCORE_CACHE_SIZE - 1) + 1
> +: h->entries + 1;
> +
> if
> On Oct 22, 2020, at 4:25 PM, Honnappa Nagarahalli
> wrote:
>
> + Dharmik
>
>> -Original Message-
>> From: Thomas Monjalon
>> Sent: Thursday, October 22, 2020 4:18 PM
>> To: Ruifeng Wang
>> Cc: dev@dpdk.org; akhil.go...@nxp.com; Honnappa Nagarahalli
>> ; nd
>> Subject: Re: [dpdk-
> On Oct 24, 2020, at 4:09 AM, David Marchand wrote:
>
> On Thu, Oct 22, 2020 at 12:51 AM Dharmik Thakkar
> wrote:
>>
>> Integrate RCU QSBR to make it easier for the applications to use lock
>> free algorithm.
>>
>> Resource reclamation implementa
Hi Yipeng,
I have addressed the comments. Can you please take a look?
Thank you!
> On Oct 21, 2020, at 5:50 PM, Dharmik Thakkar wrote:
>
> Currently, users have to use external RCU mechanisms to free resources
> when using lock free hash algorithm.
>
> Integrate RCU QSBR
Add functional and performance tests for the integrated RCU QSBR.
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_hash.c | 390 -
app/test/test_hash_readwrite_lf_perf.c | 170 ++-
2
ed functions and use resource reclamation
APIs from the RCU QSBR library instead
- Remove patch (net/ixgbe: avoid multpile definitions of 'bool')
from the series as it is already accepted
Dharmik Thakkar (4):
rcu: build on Windows
lib/hash: integrate RCU QSBR
test/hash: repl
libraries.
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Acked-by: Ray Kinsella
---
doc/guides/prog_guide/hash_lib.rst | 12 +-
lib/librte_hash/meson.build| 1 +
lib/librte_hash/rte_cuckoo_hash.c | 303 ++---
lib
Replace rte_atomic APIs with C11 atomic APIs in
test_hash_readwrite_lf_perf.c
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Acked-by: Yipeng Wang
---
app/test/test_hash_readwrite_lf_perf.c | 89 +++---
1 file changed, 36 insertions(+), 53 deletions(-)
diff
Build the lib for Windows.
Signed-off-by: Dharmik Thakkar
Tested-by: Dmitry Kozlyuk
---
lib/meson.build | 1 +
1 file changed, 1 insertion(+)
diff --git a/lib/meson.build b/lib/meson.build
index dd55b5cb53e4..1bb019720c6a 100644
--- a/lib/meson.build
+++ b/lib/meson.build
@@ -41,6 +41,7 @@ if
> On Oct 20, 2020, at 10:54 PM, Wang, Yipeng1 wrote:
>
>> -Original Message-----
>> From: Dharmik Thakkar
>> Sent: Tuesday, October 20, 2020 9:13 AM
>> To: Wang, Yipeng1 ; Gobriel, Sameh
>> ; Richardson, Bruce
>> Cc: dev@dpdk.org; n...@arm.com;
> On Oct 20, 2020, at 9:42 PM, Wang, Yipeng1 wrote:
>
>> -Original Message-----
>> From: Dharmik Thakkar
>> Sent: Tuesday, October 20, 2020 9:13 AM
>> To: Wang, Yipeng1 ; Gobriel, Sameh
>> ; Richardson, Bruce
>> ; Ray Kinsella ; Neil Horman
>
> On Oct 20, 2020, at 10:52 AM, Dmitry Kozlyuk wrote:
>
> On Tue, 20 Oct 2020 12:51:14 +, Dharmik Thakkar wrote:
>> I tried cross-compilation on Linux (Ubuntu 18.04) with MinGW-w64 toolchain,
>> but I am seeing some compilation error:
>>
>> ../lib/librt
the RCU QSBR library instead
- Remove patch (net/ixgbe: avoid multpile definitions of 'bool')
from the series as it is already accepted
Dharmik Thakkar (4):
rcu: build on Windows
lib/hash: integrate RCU QSBR
test/hash: replace rte atomic with C11 atomic APIs
test/hash: add tests
Add functional and performance tests for the integrated RCU QSBR.
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_hash.c | 390 -
app/test/test_hash_readwrite_lf_perf.c | 170 ++-
2
Replace rte_atomic APIs with C11 atomic APIs in
test_hash_readwrite_lf_perf.c
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
---
app/test/test_hash_readwrite_lf_perf.c | 89 +++---
1 file changed, 36 insertions(+), 53 deletions(-)
diff --git a/app/test
libraries.
Suggested-by: Honnappa Nagarahalli
Signed-off-by: Dharmik Thakkar
Reviewed-by: Ruifeng Wang
Acked-by: Ray Kinsella
---
doc/guides/prog_guide/hash_lib.rst | 11 +-
lib/librte_hash/meson.build| 1 +
lib/librte_hash/rte_cuckoo_hash.c | 302 ++---
lib
Build the lib for Windows.
Signed-off-by: Dharmik Thakkar
Tested-by: Dmitry Kozlyuk
---
lib/meson.build | 1 +
1 file changed, 1 insertion(+)
diff --git a/lib/meson.build b/lib/meson.build
index dd55b5cb53e4..1bb019720c6a 100644
--- a/lib/meson.build
+++ b/lib/meson.build
@@ -41,6 +41,7 @@ if
> On Oct 20, 2020, at 3:34 AM, Dmitry Kozlyuk wrote:
>
> On Tue, 20 Oct 2020 10:13:11 +0200, David Marchand wrote:
>> On Tue, Oct 20, 2020 at 1:34 AM Dharmik Thakkar
>> wrote:
>>>
>>> Build the lib for Windows.
>>>
>>> Change-Id: Ib
> On Oct 20, 2020, at 3:13 AM, David Marchand wrote:
>
> On Tue, Oct 20, 2020 at 1:34 AM Dharmik Thakkar
> wrote:
>>
>> Build the lib for Windows.
>>
>> Change-Id: Ib83431a9ee56a7b38445f0474cb9a12b17cf18f9
>> Signed-off-by: Dharmik Thakkar
> On Oct 19, 2020, at 4:05 PM, David Marchand wrote:
>
> On Mon, Oct 19, 2020 at 6:37 PM Dharmik Thakkar
> wrote:
>>
>> Integrate RCU QSBR to make it easier for the applications to use lock
>> free algorithm.
>>
>> Resource reclamation implementa
1 - 100 of 263 matches
Mail list logo
