A good understanding of the MARS efficiency issues is essential especially for downloading large amounts of data.

The aim of this page is to help users to improve their MARS requests performance focusing in CMA reforecast data using the ECMWF WEB API.

It is every important for a user to understand how the S2S data is organised in MARS.

In general it is organised in MARS as a huge tree, with the indentation below, showing different levels down that tree:

• centre (ECMWF, NCEP, JMA, ...)
  • realtime or reforecast
    •  type of data (control forecast or perturbed forecast)
      • type of level (single level or pressure level or potential  temperature)
        • dates (2015-01-01 or 2015-01-05 or 2015-01-08, ...)
          •  time-steps
            • members (for perturbed forecast)
              • levels (for pl or pt)
                • parameters

The idea is to be in the same tape file, all time-steps, all members, all parameters for a type of level, a type, a date

Following the previous paragraph the natural way to group requests would be:
all parameters, all levels, all members, all time-steps for 1 date.

Note the following:

1. 'all' means 'all' that the user wants. It doesn't have to be all parameters.
2. If a user is interested only on z500,  he may request more dates in one go, since the overall request will not be so big.

Taking under consideration what has been explained above,  if you need to loop in a MARS request, follow the hierarchy below

• date
  
  • hindcast date
    • number (EPS only)
      • level
        • parameter (inner loop)

• for date in dates-list
  
  • for hindcast date in hincasts-list
          request

for each year from 2010 to 2014

    for months April, June
        for each hindcast date
            request
        

1.  4 categories of requests:
   
   1. control plevels
   2. control sfc
   3. ensemble plevels
   4. ensemble sfc
2. For each category above:
   1. For each year from 1994 to 2014
      1. For each month from January to December
         
         1. retrieve hindcast dates 1-15 using requests according to data availability*
            
            1. API request 1
            2. API request 2
            3. API request 3
         2. retrieve hindcast dates 15-end of month using requests according to data availability
            1. API request 1
            2. API request 2
            3. API request 3

• for instance
  
  • for plevels different parameters are available on different levels so Ben has created 3 pl requests
• • for sfc different parameters are available for different  steps so he has created 3 sfc requests

cf and pf are stored separately. 

For pf is not efficient to do:
        HDATE = 20040101/20040106/20040111/20040116/20040121/20040126/20040201/20040206/20040211/20040216/20040221/20040226/20040301/20040306/20040311/20040316/20040321/20040326/20040401/20040406/20040411/20040416/20040421/20040426/20040501/20040506/20040511/20040516/20040521/20040526/20040601/20040606/20040611/20040616/20040621/20040626/20040701/20040706/20040711/20040716/20040721/20040726/20040801/20040806/20040811/20040816/20040821/20040826/20040901/20040906/20040911/20040916/20040921/20040926/20041001/20041006/20041011/20041016/20041021/20041026/20041101/20041106/20041111/20041116/20041121/20041126/20041201/20041206/20041211/20041216/20041221/20041226,
        NUMBER = 1,

but it is more efficient to group all members in one go for fewer dates:
        HDATE = 20040101/20040106/20040111/20040116/20040121/20040126,
        NUMBER = 1/to/50
This implies less positioning and more contiguous reads.

We could look at increasing the 10GB limit. We have more hardware and are in a better position to handle bigger chunks.


For the 3 allowed streams, I would extract different type/levtype in different streams. For instance:
a) 1 stream: pf/sfc
b) 1 stream: pf/pl
c) 1 stream: cf/sfc and when it finishes,cf/pl
and I would put 2 requests for each stream above. Once a request finishes and starts the downloading, the next request will kick in, and it will find in many cases that the tape volume is still in the tape drive, which will save in avg 2 minutes for a tape mount.