|
1 | | -The `setenv-sh` script sets the following environment options |
2 | | -* `NTIMEFRAMES`: Number of time frames to process. |
3 | | -* `TFDELAY`: Delay in seconds between publishing time frames (1 / rate). |
4 | | -* `NGPUS`: Number of GPUs to use, data distributed round-robin. |
5 | | -* `GPUTYPE`: GPU Tracking backend to use, can be CPU / CUDA / HIP / OCL / OCL2. |
6 | | -* `SHMSIZE`: Size of the global shared memory segment. |
7 | | -* `DDSHMSIZE`: Size of shared memory unmanaged region for DataDistribution Input. |
8 | | -* `GPUMEMSIZE`: Size of allocated GPU memory (if GPUTYPE != CPU) |
9 | | -* `HOSTMEMSIZE`: Size of allocated host memory for GPU reconstruction (0 = default). |
10 | | - * For `GPUTYPE = CPU`: TPC Tracking scratch memory size. (Default 0 -> dynamic allocation.) |
11 | | - * Otherwise : Size of page-locked host memory for GPU processing. (Defauls 0 -> 1 GB.) |
12 | | -* `CREATECTFDICT`: Create CTF dictionary. |
13 | | -* `SAVECTF`: Save the CTF to a root file. |
14 | | - * 0: Read `ctf_dictionary.root` as input. |
15 | | - * 1: Create `ctf_dictionary.root`. Note that this was already done automatically if the raw data was simulated with `full_system_test.sh`. |
16 | | -* `SYNCMODE`: Run only reconstruction steps of the synchronous reconstruction. |
17 | | - * Note that there is no `ASYNCMODE` but instead the `CTFINPUT` option already enforces asynchronous processing. |
18 | | -* `NUMAGPUIDS`: NUMAID-aware GPU id selection. Needed for the full EPN configuration with 8 GPUs, 2 NUMA domains, 4 GPUs per domain. |
19 | | - In this configuration, 2 instances of `dpl-workflow.sh` must run in parallel. |
20 | | - To be used in combination with `NUMAID` to select the id per workflow. |
21 | | - `start_tmux.sh` will set up these variables automatically. |
22 | | -* `NUMAID`: SHM segment id to use for shipping data as well as set of GPUs to use (use `0` / `1` for 2 NUMA domains, 0 = GPUS `0` to `NGPUS - 1`, 1 = GPUS `NGPUS` to `2 * NGPUS - 1`) |
23 | | -* 0: Runs all reconstruction steps, of sync and of async reconstruction, using raw data input. |
24 | | -* 1: Runs only the steps of synchronous reconstruction, using raw data input. |
25 | | -* `EXTINPUT`: Receive input from raw FMQ channel instead of running o2-raw-file-reader. |
26 | | - * 0: `dpl-workflow.sh` can run as standalone benchmark, and will read the input itself. |
27 | | - * 1: To be used in combination with either `datadistribution.sh` or `raw-reader.sh` or with another DataDistribution instance. |
28 | | -* `CTFINPUT`: Read input from CTF ROOT file. This option is incompatible to EXTINPUT=1. The CTF ROOT file can be stored via SAVECTF=1. |
29 | | -* `NHBPERTF`: Time frame length (in HBF) |
30 | | -* `GLOBALDPLOPT`: Global DPL workflow options appended to o2-dpl-run. |
31 | | -* `EPNPIPELINES`: Set default EPN pipeline multiplicities. |
32 | | - Normally the workflow will start 1 dpl device per processor. |
33 | | - For some of the CPU parts, this is insufficient to keep step with the GPU processing rate, e.g. one ITS-TPC matcher on the CPU is slower than the TPC tracking on multiple GPUs. |
34 | | - This option adds some multiplicies for CPU processes using DPL's pipeline feature. |
35 | | - The settings were tuned for EPN processing with 4 GPUs (i.e. the default multiplicities are per NUMA domain). |
36 | | - The multiplicities are scaled with the `NGPUS` setting, i.e. with 1 GPU only 1/4th are applied. |
37 | | - You can pass an option different to 1, and than it will be applied as factor on top of the multiplicities. |
38 | | - It is auto-selected by `start-tmux.sh`. |
39 | | -* `SEVERITY`: Log verbosity (e.g. info or error, default: info) |
40 | | -* `INFOLOGGER_SEVERITY`: Min severity for messages sent to Infologger. (default: `$SEVERITY`) |
41 | | -* `SHMTHROW`: Throw exception when running out of SHM memory. |
42 | | - It is suggested to leave this enabled (default) on tests on the laptop to get an actual error when it runs out of memory. |
43 | | - This is disabled in `start_tmux.sh`, to avoid breaking the processing while there is a chance that another process might free memory and we can continue. |
44 | | -* `NORATELOG`: Disable FairMQ Rate Logging. |
45 | | -* `INRAWCHANNAME`: FairMQ channel name used by the raw proxy, must match the name used by DataDistribution. |
46 | | -* `WORKFLOWMODE`: run (run the workflow (default)), print (print the command to stdout), dds (create partial DDS topology) |
47 | | -* `FILEWORKDIR`: directory for all input / output files. E.g. grp / geometry / dictionaries etc. are read from here, and dictionaries / ctf / etc. are written to there. |
48 | | - Some files have more fine grained control via other environment variables (e.g. to store the CTF to somewhere else). Such variables are initialized to `$FILEWORKDIR` by default but can be overridden. |
49 | | -* `EPNSYNCMODE`: Specify that this is a workflow running on the EPN for synchronous processing, e.g. logging goes to InfoLogger, DPL metrics to to the AliECS monitoring, etc. |
50 | | -* `BEAMTYPE`: Beam type, must be PbPb, pp, pPb, cosmic, technical. |
51 | | -* `IS_SIMULATED_DATA` : 1 for MC data, 0 for RAW data. |
| 1 | +For a reference to available env-variables, please check https://github.com/AliceO2Group/AliceO2/blob/dev/prodtests/full-system-test/documentation/env-variables.md |
0 commit comments