aboutsummaryrefslogtreecommitdiffstats
path: root/GPL/tools/trex/trex_astf_profile.py
AgeCommit message (Collapse)AuthorFilesLines
2022-05-18fix(trex): use reset instead of clear_profileVratko Polak1-3/+2
Now sure why clear_profile gets stuck with v2.97 (unless block=False), but calling reset() works, and will be less risky next time we bump TRex version. - Only ASTF for now. Change-Id: Ib6906fb8ce269e888bf0e0438d3309931d5e9981 Signed-off-by: Vratko Polak <vrpolak@cisco.com>
2022-05-16Core: T-rex 2.97pmikus1-1/+1
Signed-off-by: pmikus <pmikus@cisco.com> Change-Id: Id4d84aa7268080843b099fd7ab9851234612968b
2022-05-03feat(astf): Support framesizes for ASTFVratko Polak1-2/+14
- No support for IMIX. + Fix a bad bug in padding (most ASTF profiles had wrong frame sizes). + Fix a big typo in TCP PPS profiles (s->c was not data, just RST). + Control transaction size via ASTF_N_DATA_FRAMES env variable. - Default value 5 leads to transactions smaller than before. + It ensures transaction is one burst (per direction) even for jumbo. + Edit autogen to set supported frame sizes based on suite id. + Both TCP and UDP use the same values: + 64B for CPS (exact for UDP, nominal for TCP). + 100B, 1518B and 9000B for TPUT and PPS. - TCP TPUT achievable minimum is 70B. + Used 100B to leave room for possible IPv6 ASTF tests. + Separate function for code reused by vpp and trex tests. - I do not really like the new "copy and edit" approach added here. + But it is a quick edit, better autogen refactor is low priority. + Consider both established and transitory sessions as valid. - Mostly for compatibility with 2202 behavior and to avoid ramp-ups. - Assuming both session states have similar enough VPP CPU overhead. + Added a TODO to investigate and maybe reconsider later. + Update the state timeout value to 240s. + That is the default for TCP (for transitory state). - UDP could keep using 300s. + But I prefer UDP and TCP to behave as similarly as possible. + Use TRex tunables to get the exact frame size (for data packets). - It is not clear why the recipe for MSS has to be this complicated. + Move code away from profile init, as frame size is not known there. + Change internal profile API, so values related to MSS are passed. + Lower ramp-up rate for TCP TPUT tests. + Because without lower rate, jumbo fails on packet loss in ramp-up. + UDP TPUT ramp-up rate also lowered (just to keep suites more similar). + Distinguish one-direction and aggregated average frame size. + Update keyword documentation where the distiction matters. + One-direction is needed for turning bandwidth limit to TPS limit. + Aggregated is needed for correct NDRPDR bandwidth result value. - TCP TPUT will always be few percent below bidirectional maximum. + That is unavoidable, as one direction sends more control packets. + Add runtime consistency checks so future refactors are safer. + Fail if padding requested would be negative. + Fail if suite claims unexpected values for packets per transaction. + Edit the 4 types of ASTF profiles to keep them similar to each other. + Move UDP TPUT limit value from a field back to direct argument. + Stop pretending first UDP packet is not data. + Apply small improvements where convenient. + Replace "aggregate" with "aggregated" where possible. + To lower probability of any future typos in variable names. + Avoid calling Set Numeric Frame Sizes twice. + Code formatting, keyword documentation, code comments, ... + Add TODOs for less important code quality improvements. - Postpone updating of methodology pages to a subsequent change. Change-Id: I4b381e5210e69669f972326202fdcc5a2c9c923b Signed-off-by: Vratko Polak <vrpolak@cisco.com>
2021-06-10FIX: Pylint reducepmikus1-1/+1
Signed-off-by: pmikus <pmikus@cisco.com> Change-Id: I909942dbb920df7f0fe15c0c92cda92c3cd8d8ad
2021-03-26STL traffic: Use the sleep+stop logicVratko Polak1-14/+16
+ PPS limit for AWS set to 1.2 Mpps. + The logic is very similar to that one in ASTF driver. + This helps for testbeds with high duration stretching (e.g. AWS). + Difference: No transaction scale, and we deal with floats. + Update loss counting to count unsent packets as lost. + Also count "unsent" transactions for other transaction types. + If nonzero, log the number of unsent packets/transactions. + Make STL and ASTF time overhead constant (called delay) configurable. + Subtract delay from approximated_duration, also for ASTF. Change-Id: I6ee6aa6fba4f110ba1636e1b0ff76cac64383e33 Signed-off-by: Vratko Polak <vrpolak@cisco.com>
2021-03-16Perf: Bump T-Rex to 2.88pmikus1-1/+1
+ Mellanox 4.6 is not for Ubuntu 20.04 + Mellanox for ubuntu 20.04 is 4.9+ + T-Rex 2.86 is not for Mellanox 4.6+ + T-Rex for Mellanox 5.2 is 2.88+ ================================== = Bump Signed-off-by: pmikus <pmikus@cisco.com> Change-Id: I902dfc2a43e6718b385e89f31a34260e09d61bd3
2021-01-12License: Wrap GPL block to 80 charactersVratko Polak1-2/+3
The original license block was adapted from https://wiki.fd.io/view/TSC/Proposed_Header_Python_Test_Scripts resulting in a line longer than 80 chars, but those are reported (although not blocked) by tox verify job. As the text from wiki was not used in verbatim (it uses c-style comment block), minor formatting change like this should not be a big deal. + Bump copyright year. Change-Id: I55e3a0232639b448b1a6d7b1f3af84d903a8d0a5 Signed-off-by: Vratko Polak <vrpolak@cisco.com>
2020-11-18T-Rex: 2.86pmikus1-1/+1
Signed-off-by: pmikus <pmikus@cisco.com> Change-Id: Id56b87ab868f2897a6563914b0beca2acc25e706
2020-11-12Switch licenses in GPL directoryVratko Polak1-3/+12
To be merged after this completes: https://wiki.fd.io/view/TSC/Relicensing_Procedure Change-Id: I003e53a620a5f82ba2bcc65b12f9c84ae92264ef Signed-off-by: Vratko Polak <vrpolak@cisco.com>
2020-10-29Support existing test types with ASTFVratko Polak1-126/+121
+ Add UDP_CPS, TCP_CPS, UDP_PPS and TCP_PPS suites. + Update existing cps traffic profiles. + Add missing traffic profiles. + UDP: + Single burst of 32 packets was confirmed as safe enough for TRex. + Maybe 64 could work, but not enough testing for that. + Multiple bursts have lead to reduced TRex performance, as overlaping bursts (from different client instances) tend to fill up the buffers. + TCP: + Data size set to 11111 bytes, completely arbitrarily. + Results look reasonable, so I have kept that. - MSS not set at all - No tested support for frame size other than 64B. - Frame size does not even factor into TCP profiles. + So other frame sizes are skipped in autogen. + Update tags in related suites. - HOSTS_{n} and SRC_USER_{n} should be unified. - Questionable clarification on difference between IP4BASE and SCALE. + Add NAT state resetters to tests that need them. + Resetter is called (if set) before each measurement. + If ramp-up is detected, resetter is not set. + Rename "mult" argument to "multiplier". + Abstracted from packets to transactions. + Transaction corresponds to profile. + TRex multiplier argument sets target rate in transactions per second. + The familiar STL traffic: + Bidirectional is considered to be 2 packets per transaction. + Unidirectional is considered to be 1 packet per transaction. + The newer ASTF traffic: + 4 subtypes, each has different number of packets per transaction. + For max rate computation: + Packets in the more numerous direction are considered. + Rely on TRex reported traffic duration for ASTF: + Use the server side value. - Client side value is higher by an overhead. - TRex is not sending traffic during that time. + Remove delays from traffic profiles. - Those delays would increase the reprted traffic time. + Support for scale lmited trials. + Only for ASTF profiles, each ASTF profile has limited scale. + Scale defined in suite variables. + For TRex to send all transactions provided duration value is ignored. + The appropriate value is computed in TrafficGenerator. + An ad-hoc time constant is added to match the TRex client side time overhead. + The profile driver receives the computed duration. + Measurement for PLRsearch add a sleep if the computed duration is smaller. + Alternative argument for search algos if scale is limited. + Both need higher timeout to accomodate big scales. + MLRsearch can afford fewer phases. + Added a parameter to optionally shorten the duration. + Use short duration for runtime stats trial and failure stats trial. + Use very large keepalive values in udp profiles to avoid ka packets. + No polling in ASTF profile driver. - Polling could eliminate the time overhead value. + But polling proved to introduce some loss, affecting the results. + Handle duration stretching in ASTF by stopping traffic. + The stop has several steps so that: + The traffic is really stopped entirely. + Late packets do not count (maybe as errors). + Stats are preserved to read for results (and cleared afterwards). + Several quantities added to ReceiveRateMeasurement: + Original target duration is preserved (algos need that). + Input estimate (tps) for early search iterations. + Output estimate (maybe pps) for MRR output. + Strict result (unsent counts as loss) for NDR. + Use L2 counters (opackets, ipackets) where possible. - TRex has trouble processing packets for the L7 ones at high loads. + Remove warmup from profile drivers and keywords. + Suites should call "Send ramp-up traffic" explicitly if needed. + Added parsing for few more counters. + Both to use in formulas or just for debug purposes. - Only 64B cases in autogen, framesize support to be added later. + Latency streams during search can be enabled via PERF_USE_LATENCY env var. + MLRsearch improvments: + Rename argument names to min_rate and max_rate. + Use relative receive rate in initial phase. + PLRsearch improvements: + Careful computation when output (pps) does not match input (tps). + Use geometric distribution (instead of Poisson). + Helps agains math errors. + This should improve estimate stability. - But in practice big losses still lead to significant jumps. + Traffic generator improvements: + send_traffic_on_tg now calls the full set_rate_provider_defaults. + _send_traffic_on_tg_internal for the logic without provider defaults. + As the internal function is re-used by measure() without affecting defaults. + Move _parse_traffic_results just before get_measurement_result. + As the latter uses fields set bu the former, it is now easier to read. + Multiple sources for approximate duration. + Tried from more precise to more available. + Includes logic for _pps tests (added in later change). + Move explicit type conversions to earlier occurences. + Profile driver output field uses semicolons to simplify parsing. + Performance Robot lib file split to several smaller ones. + performance_actions.robot: + Hosts Additional Statistics Action For * keywords. + performance_display.robot: + Hosts keyword for displaying and verifying results. + Change test message to use the correct unit (pps or cps). + performance_limits.robot renamed to performance_vars.robot + Added many keywords, mostly for accessing test variables. + Moved variables for Policer into a new keyword there. + Some keywords need sophisticated logic. - Other are basically Get Variable Value. + But in future more logic can be added, without editing callers. + Documentation for the new keywords acts as a documentation for test variables. + performance_utils.robot has the rest. + Eliminated arguments if the value is in test variable. + Small improvements to documentation. - Still not enough cleanup with respect to arguments and test variables. + Keywords are sorted alphabetically now in each one. + Suites: + Unified variables table: + No colons in comments. + ${n_hosts}, ${n_ports} and use them instead hardcoded numbers. + Add -cps to existing cps suite names. + Remove "trial data overwrite". + Compute max rate as in STL suites. + Each NAT suite has ip4base suite to compare results to. - Those act as indirect TRex calibration. - VPP does not lose packets in those. + Latency in ASTF suites is disabled hard. - As we do not support latency in ASTF profiles yet. + Unidirectional tests governed by suite variable, not an argument. + Write long argument lists vertically. + Prefer to use argument names. + In Python, also the last argument is followed by comma. + It makes renaming and reordering easier. + Similarly applies to prints with long lists of values. + A TODO to update api crc file comments. Change-Id: I84729355edbec051298a9de1162107f88ff5737d Signed-off-by: Vratko Polak <vrpolak@cisco.com>
2020-08-24T-Rex: 2.82, core pin, 8 workerspmikus1-1/+1
+ Bump T-Rex version. We need new features for ASTF test. + Apply core pining. Results in a more stable performance. + Tweak the number of T-Rex workers. + We need an even value to achieve ymmetric performance with pinning. + Value 8 was selected as a best compromise. This is a combination of 3 commits. This is the 1st commit message: T-Rex: 2.82 This is the commit message #2: Change Trex to CORE_MASK_PIN mode to improve performance https://trex-tgn.cisco.com/trex/doc/trex_stateless.html#_core_masking_per_interface Above link have below explaination, "When the profile is symmetric, performance can be improved by pinning half of the cores to port 0, and half of the cores to port 1, thus avoiding cache trashing and bouncing." The reason to change this is that to run CSIT with 100G NIC often failed with "TRex stateless runtime error timeout", it caused by Trex can not send enough traffic within the fixed duration. by change to CORE_MASK_PIN mode fix the issue. Not editing ASTF, as that supports different options. This is the commit message #3: Experiment: Vary number of TRex workers With CORE_MASK_PIN, we can get more predictable time distribution. Decided to use 8 workers, that gives good results both for high end (RDMA-core l2patch) and low end (vhost) tests. Change-Id: I5c61127799e0624464e960fcb980ad1c4058e744 Signed-off-by: pmikus <pmikus@cisco.com> Signed-off-by: Yulong Pei <yulong.pei@intel.com> Signed-off-by: Vratko Polak <vrpolak@cisco.com>
2020-08-07Perf: NAT44 endpoint-dependent mode - udp, part IJan Gelety1-8/+79
- continuation of https://gerrit.fd.io/r/c/csit/+/26898 as there was reached limit of changes (1000) Jira: CSIT-1711 - udp synthetic profiles w/o data packets - udp cps perf tests, phase I (no special "search cps" KW) Part I means that we are using MRR tests to collect traffic data until there is ready new CPS test type with corresponding algorithm. Change-Id: I0d30feb9ecf1d0bff937152656f8eb422f831378 Signed-off-by: Jan Gelety <jgelety@cisco.com>
2020-07-23T-Rex: Add advanced stateful modeJan Gelety1-0/+391
- provide base routines to run T-Rex in advanced stateful mode Change-Id: Ib0dc5f2919c370753335f6446860683dc4b12d93 Signed-off-by: Jan Gelety <jgelety@cisco.com>