diff --git a/docs/03-hermes/06-components/03-buffering-target.md b/docs/03-hermes/06-components/03-buffering-target.md index 5f4e9eee..4dce4d4a 100644 --- a/docs/03-hermes/06-components/03-buffering-target.md +++ b/docs/03-hermes/06-components/03-buffering-target.md @@ -91,48 +91,62 @@ means a local target list will consist of 3 targets, a neighborhood target list ## Kitchen Sink - - - - - - + + + + + +

From the OctopusFS paper:

-
    -
  • Tiers T1, …, Tk
    • -
  • Media mi -
      -
    • Tier[mi] - the tier of medium mi
      • -
    • Cap[mi] - the total capacity of medium mi
      • -
    • Rem[mi] - the remaining capacity of medium mi
      • -
    • NrConn[mi] - the number of active I/O connections to medium mi
      • -
    • WThru[mi] - the sustained write throughput of medium mi
      • -
    • RThru[mi] - the sustained read throughput of medium mi
      • -
    • -
  • Workers W1, …, Wn -
      -
    • Slightly different concept -
        -
      • Stores and manages file blocks on storage media
        • -
      • Serves read and write requests from clients
        • -
      • Block creation, deletion, replication (instructed by name nodes HDFS...)
        • -
      • -
    • -

From Wrike:

-
    -
  • Wi =  < node, tier>
    • -
  • Workers are a dedicated thread per tier available on the node
    • -
  • Worker characteristics: -
      -
    • Capacity
      • -
    • BW
      • -
    • Latency
      • -
    • Energy consumption
      • -
    • Concurrency (expressed as the number of lanes of the bus e.g., PCIex8 or SATA)
      • -
    • Queue pressure (outstanding requests) -
        -
      • Aggregate data size in queue
        • -
      • Number of pending requests
        • -
      • -
    • -
+

From the OctopusFS paper:

+
    +
  • Tiers T1, …, Tk
    • +
  • + Media mi +
      +
    • Tier[mi] - the tier of medium mi
      • +
    • Cap[mi] - the total capacity of medium mi
      • +
    • Rem[mi] - the remaining capacity of medium mi
      • +
    • NrConn[mi] - the number of active I/O connections to medium mi
      • +
    • WThru[mi] - the sustained write throughput of medium mi
      • +
    • RThru[mi] - the sustained read throughput of medium mi
      • +
    +
    • +
  • + Workers W1, …, Wn +
      +
    • + Slightly different concept +
        +
      • Stores and manages file blocks on storage media
        • +
      • Serves read and write requests from clients
        • +
      • Block creation, deletion, replication (instructed by name nodes HDFS...)
        • +
      +
      • +
    +
    • +
+ 		+

From Wrike:

+
    +
  • Wi =  < node, tier>
    • +
  • Workers are a dedicated thread per tier available on the node
    • +
  • + Worker characteristics: +
      +
    • Capacity
      • +
    • BW
      • +
    • Latency
      • +
    • Energy consumption
      • +
    • Concurrency (expressed as the number of lanes of the bus e.g., PCIex8 or SATA)
      • +
    • + Queue pressure (outstanding requests) +
        +
      • Aggregate data size in queue
        • +
      • Number of pending requests
        • +
      +
      • +
    +
    • +
+
diff --git a/docs/03-hermes/06-components/07-runtime.md b/docs/03-hermes/06-components/07-runtime.md index 8a0c7175..9855809c 100644 --- a/docs/03-hermes/06-components/07-runtime.md +++ b/docs/03-hermes/06-components/07-runtime.md @@ -64,7 +64,7 @@ A Task Library implements the following concepts: released as a shared object. 3. **Task Client**: A class responsible for submitting tasks to the hermes runtime. This is released as a header file, which is included by the client program. -To easily bootstrap a task lib, Hermes provides a python-based code generator called make_task. This script assumes a Linux system at this time (Windows has a different pathing system). Let's say you want to create a new task lib named "compress" for creating a factory of compression libraries. The task lib is located in the task repo ${HOME}/my_task_repo. +To easily bootstrap a task lib, Hermes provides a python-based code generator called make_task. This script assumes a Linux system at this time (Windows has a different pathing system). Let's say you want to create a new task lib named "compress" for creating a factory of compression libraries. The task lib is located in the task repo `${HOME}/my_task_repo`. ```bash codegen/make_task ${HOME}/my_task_repo/compress diff --git a/docs/03-hermes/11-faq.md b/docs/03-hermes/11-faq.md index 21078b69..930ac9ee 100644 --- a/docs/03-hermes/11-faq.md +++ b/docs/03-hermes/11-faq.md @@ -47,7 +47,7 @@ inline std::string GetFilenameFromFD(int fd) { ## Can I run Hermes on Chameleon JupyterLab Server? -Maybe. However, installation with Spack will fail due to timeout. For older (<0.8) Hermes, Google OR-Tools installation will fail. +Maybe. However, installation with Spack will fail due to timeout. For older (< 0.8) Hermes, Google OR-Tools installation will fail. ## Why do I get `mercury->fatal` error when I use `rpc_protocol = "ofi+verbs";` in configuration file? diff --git a/docs/05-jarvis/02-jarvis-cd/02-getting-started.md b/docs/05-jarvis/02-jarvis-cd/02-getting-started.md index d452bcd1..df7704d9 100644 --- a/docs/05-jarvis/02-jarvis-cd/02-getting-started.md +++ b/docs/05-jarvis/02-jarvis-cd/02-getting-started.md @@ -42,9 +42,7 @@ To begin polling the system, run: jarvis resource-graph build +walkthrough ``` -This information will be stored under ${JARVIS_ROOT}/config/resource_graph.yaml. -The command uses SSH to connect to all pkgs. It will use the -hostfile from the previous command and scan those pkgs. +This information will be stored under `${JARVIS_ROOT}/config/resource_graph.yaml`. The command uses SSH to connect to all pkgs. It will use the hostfile from the previous command and scan those pkgs. ## Create an empty pipeline diff --git a/docs/05-jarvis/02-jarvis-cd/08-packages/wrf.md b/docs/05-jarvis/02-jarvis-cd/08-packages/wrf.md index 6544ec50..31690f60 100644 --- a/docs/05-jarvis/02-jarvis-cd/08-packages/wrf.md +++ b/docs/05-jarvis/02-jarvis-cd/08-packages/wrf.md @@ -138,7 +138,7 @@ export NETCDF=$DIR ``` 4. Build NetCDF fortran library links with NETCDF-C, after successful installation, - netcdf.inc will be ${NETCDF}/include file. + netcdf.inc will be `${NETCDF}/include` file. For sometimes, it will show C compiler stop working, Please check the environment variable in LIBS="-lnetcdf -lhdf5_hl -lhdf5 -lz", make sure netcdf and hdf5 path in the environment variables. diff --git a/src/pages/contact.mdx b/src/pages/contact.mdx index ff71497e..f359f4af 100644 --- a/src/pages/contact.mdx +++ b/src/pages/contact.mdx @@ -15,5 +15,5 @@ Chicago, Illinois 60616 **Contact Info** -Email:
+Email: grc@iit.edu
Phone: [+1 312 567 6885](tel:3125676885) diff --git a/src/pages/research/projects/hermes.mdx b/src/pages/research/projects/hermes.mdx index 6fed715d..4b712171 100644 --- a/src/pages/research/projects/hermes.mdx +++ b/src/pages/research/projects/hermes.mdx @@ -360,9 +360,11 @@ A new, multi-tiered, distributed buffering platform that is:

- National Science Foundation

+ National Science Foundation +

- (NSF OCI-1835764)

+ (NSF OCI-1835764) +