https://ftp.ncbi.nlm.nih.gov/blast/db/FASTA/
nt.gz                   2020-02-03 16:19   64G

reczko@fix:~/Elixir/metagenomics/kma/index$ zcat nt.gz | ./my_rename_nt.py 

zcat nt.gz | awk -f rename_nt.awk | gzip -9 -c   > nt_w_taxid.fas.gz

time ~/Elixir/metagenomics/kma/genomicepidemiology-kma-c24447397d5d/kma index -i nt_w_taxid.fas.gz -o nt_w_taxid.idx


time ~/Elixir/metagenomics/kma/genomicepidemiology-kma-c24447397d5d/kma index -i ~/Elixir/metagenomics/kma/index/nt_w_taxid.fas -o nt_w_taxid.idx
# Indexing databases.
# Updating DBs
# Reading inputfile: 	/home/reczko/Elixir/metagenomics/kma/index/nt_w_taxid.fas
# Added:	9646|X17276.1 Giant Panda satellite 1 DNA
# Added:	9913|X51700.1 Bos taurus mRNA for bone Gla protein


wc nt_w_taxid.fas 
  3342983172   4026597175 271058846460 nt_w_taxid.fas

(/ 3342983172 2)
1671491586

reczko@fix:~/Elixir/metagenomics/kma/index/metagenomics/kma/index$  time /home/reczko/Elixir/metagenomics/kma/genomicepidemiology-kma-c24447397d5d/kma index -i xaa2 -o nt_w_taxid_1.idx

#on max:
time /home/reczko/Elixir/metagenomics/kma/genomicepidemiology-kma-c24447397d5d/kma index -i  /mnt/fix/a/reczko_lab/metagenomics/kma/index/xab2  -o nt_w_taxid_2.idx -t 10

# Added:	562|CP023852.1 Escherichia coli strain 4/0 plasmid p4_0.3, complete sequence
Error: 12 (Cannot allocate memory)

real	1226m10.687s
user	1040m4.639s
sys	181m24.198s
  -rw-r--r-- 1 reczko users 466948485124 Mar 18 17:24 nt_w_taxid_2.idx.index.b
  -rw-r--r-- 1 reczko users            0 Mar 17 20:58 nt_w_taxid_2.idx.length.b
  -rw-r--r-- 1 reczko users   1289780561 Mar 18 17:24 nt_w_taxid_2.idx.name
  -rw-r--r-- 1 reczko users  14637071896 Mar 18 17:24 nt_w_taxid_2.idx.seq.b