Age | Commit message (Collapse) | Author | Files | Lines |
|
Avoiding any predictable memory access patterns
is more important than similarity between 2p and 6p profiles.
+ Seed values now match parts of IP source address.
Change-Id: Ib1830cf9d3e7b329e54de19a92ecea77c8baeeb5
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|
|
This reverts commit b8f31fc3da4b0a6ab5805eea61af0fe7e869a453.
Change-Id: I65f79bb323f48d9e7b3ed7a1990db1b1486da26e
Signed-off-by: Peter Mikus <peter.mikus@protonmail.ch>
|
|
This reverts commit 4e2635deff33db4bea476003ac222ffd9ab504b1.
Change-Id: Idb9145fbf13e7943392a72f77ef9a1b479187732
Signed-off-by: Peter Mikus <peter.mikus@protonmail.ch>
|
|
+ Add trailing commas to prevent black from collapsing argument lists.
Change-Id: I8a2f2aca0df7a9271a073f87603f9abfa4870b11
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|
|
On one hand, using seed==1 for all W-E streams
and seed=2 for all E-W streams would make 6p tests
even more comparable with 2p tests.
But current rnd profiles were mixing the two seed values.
On the other hand, using unique seed values for each stream
would ensure VPP is less likely to deviate from average preformance.
As the second approach also results in smaller profile files,
this patch applies that approach.
Change-Id: If0f57282a2899a1a4fb154dd6ed810064cb5c212
Signed-off-by: Vratko Polak <vrpolak@cisco.com>
|
|
Signed-off-by: pmikus <peter.mikus@protonmail.ch>
Change-Id: I1d6d32cf95fc518e5095c475c050fe626df8041a
|
|
Signed-off-by: Peter Mikus <peter.mikus@protonmail.ch>
Change-Id: I69ee305b25b9e05d2305cb82aba71ef6418780ab
|