incubator-doris Rollup SQL in TPCDS encounter the wrong answer.

7fhtutme  于 2022-04-22  发布在  Java
关注(0)|答案(6)|浏览(253)
select 'catalog channel' as channel
       , cs_call_center_sk as id
       , sum(cs_ext_sales_price)
from  catalog_sales
where cs_sold_date_sk = 2451780
group by rollup (channel, id)
order by channel,id
lc8prwob

lc8prwob1#

doris wrong answer

+-----------------+------+---------------------------+
| channel         | id   | sum(`cs_ext_sales_price`) |
+-----------------+------+---------------------------+
| catalog channel |    1 |                 894854.96 |
| catalog channel |    2 |                1041324.42 |
| catalog channel |    5 |                 878863.84 |
| catalog channel | NULL |                2824279.62 |
| catalog channel | NULL |                    9236.4 |
| catalog channel | NULL |                2824279.62 |
+-----------------+------+---------------------------+

gp answer

channel     | id |    sum
-----------------+----+------------
 catalog channel |  1 |  894854.96
 catalog channel |  2 | 1041324.42
 catalog channel |  5 |  878863.84
 catalog channel |    |    9236.40
 catalog channel |    | 2824279.62
                 |    | 2824279.62
bttbmeg0

bttbmeg02#

query14, query27, query77 are of wrong answer

smdnsysy

smdnsysy3#

You can reproduce the bug using TPCDS(v2.13) qualification test.

This document is for qualification test.
It's different with performance test, the data should be of 1GB size.

1. Generate query for qualification.
   The query_templates for qualification should be
   modified by Appendix B.
   I have modified it already, you can replace it.

dsqgen -DIRECTORY ../query_templates
  -INPUT ../query_templates/templates.lst
  -VERBOSE Y -QUALIFY Y
  -SCALE 1GB
  -DIALECT ansi
  -OUTPUT_DIR /home/disk1/chaoyli/tpcds

2. Generate data with 10 parallelism degree
for((i=1;i<=10;i++))
do
    ./dsdgen -SCALE 1G -PARALLEL 10 -CHILD $i -TERMINATE N
done

3. Customer table ISO/IEC 8859-1 encoding, doris not support this encoding,
   should convert it to UTF-8
   iconv -f ascii -t utf-8 "$file" -o "${file%.txt}.utf8.txt"

4. Create table using DDL in create_table.sql

5. Load data into database using load.sh

6. Qualify the results with answer_sets.
ukdjmx9f

ukdjmx9f4#

create table

create table customer_address
(
    ca_address_sk             integer               not null,
    ca_address_id             char(16)              not null,
    ca_street_number          char(10)                      ,
    ca_street_name            varchar(60)                   ,
    ca_street_type            char(15)                      ,
    ca_suite_number           char(10)                      ,
    ca_city                   varchar(60)                   ,
    ca_county                 varchar(30)                   ,
    ca_state                  char(2)                       ,
    ca_zip                    char(10)                      ,
    ca_country                varchar(20)                   ,
    ca_gmt_offset             decimal(5,2)                  ,
    ca_location_type          char(20)
)
duplicate key(ca_address_sk)
distributed by hash(ca_address_sk) buckets 1
properties(
    "replication_num"="1"
);

create table customer_demographics
(
    cd_demo_sk                integer               not null,
    cd_gender                 char(1)                       ,
    cd_marital_status         char(1)                       ,
    cd_education_status       char(20)                      ,
    cd_purchase_estimate      integer                       ,
    cd_credit_rating          char(10)                      ,
    cd_dep_count              integer                       ,
    cd_dep_employed_count     integer                       ,
    cd_dep_college_count      integer
)
duplicate key (cd_demo_sk)
distributed by hash(cd_demo_sk) buckets 1
properties(
    "replication_num"="1"
);

create table date_dim
(
    d_date_sk                 integer               not null,
    d_date_id                 char(16)              not null,
    d_date                    date                          ,
    d_month_seq               integer                       ,
    d_week_seq                integer                       ,
    d_quarter_seq             integer                       ,
    d_year                    integer                       ,
    d_dow                     integer                       ,
    d_moy                     integer                       ,
    d_dom                     integer                       ,
    d_qoy                     integer                       ,
    d_fy_year                 integer                       ,
    d_fy_quarter_seq          integer                       ,
    d_fy_week_seq             integer                       ,
    d_day_name                char(9)                       ,
    d_quarter_name            char(6)                       ,
    d_holiday                 char(1)                       ,
    d_weekend                 char(1)                       ,
    d_following_holiday       char(1)                       ,
    d_first_dom               integer                       ,
    d_last_dom                integer                       ,
    d_same_day_ly             integer                       ,
    d_same_day_lq             integer                       ,
    d_current_day             char(1)                       ,
    d_current_week            char(1)                       ,
    d_current_month           char(1)                       ,
    d_current_quarter         char(1)                       ,
    d_current_year            char(1)
)
duplicate key (d_date_sk)
distributed by hash(d_date_sk) buckets 1
properties(
    "replication_num"="1"
);

create table warehouse
(
    w_warehouse_sk            integer               not null,
    w_warehouse_id            char(16)              not null,
    w_warehouse_name          varchar(20)                   ,
    w_warehouse_sq_ft         integer                       ,
    w_street_number           char(10)                      ,
    w_street_name             varchar(60)                   ,
    w_street_type             char(15)                      ,
    w_suite_number            char(10)                      ,
    w_city                    varchar(60)                   ,
    w_county                  varchar(30)                   ,
    w_state                   char(2)                       ,
    w_zip                     char(10)                      ,
    w_country                 varchar(20)                   ,
    w_gmt_offset              decimal(5,2)
)
duplicate key (w_warehouse_sk)
distributed by hash(w_warehouse_sk) buckets 1
properties(
    "replication_num"="1"
);

create table ship_mode
(
    sm_ship_mode_sk           integer               not null,
    sm_ship_mode_id           char(16)              not null,
    sm_type                   char(30)                      ,
    sm_code                   char(10)                      ,
    sm_carrier                char(20)                      ,
    sm_contract               char(20)
)
duplicate key (sm_ship_mode_sk)
distributed by hash(sm_ship_mode_sk) buckets 1
properties(
    "replication_num"="1"
);

create table time_dim
(
    t_time_sk                 integer               not null,
    t_time_id                 char(16)              not null,
    t_time                    integer                       ,
    t_hour                    integer                       ,
    t_minute                  integer                       ,
    t_second                  integer                       ,
    t_am_pm                   char(2)                       ,
    t_shift                   char(20)                      ,
    t_sub_shift               char(20)                      ,
    t_meal_time               char(20)
)
duplicate key (t_time_sk)
distributed by hash(t_time_sk) buckets 1
properties(
    "replication_num"="1"
);

create table reason
(
    r_reason_sk               integer               not null,
    r_reason_id               char(16)              not null,
    r_reason_desc             char(100)
)
duplicate key (r_reason_sk)
distributed by hash(r_reason_sk) buckets 1
properties(
    "replication_num"="1"
);

create table income_band
(
    ib_income_band_sk         integer               not null,
    ib_lower_bound            integer                       ,
    ib_upper_bound            integer
)
duplicate key (ib_income_band_sk)
distributed by hash(ib_income_band_sk) buckets 1
properties(
    "replication_num"="1"
);

create table item
(
    i_item_sk                 integer               not null,
    i_item_id                 char(16)              not null,
    i_rec_start_date          date                          ,
    i_rec_end_date            date                          ,
    i_item_desc               varchar(200)                  ,
    i_current_price           decimal(7,2)                  ,
    i_wholesale_cost          decimal(7,2)                  ,
    i_brand_id                integer                       ,
    i_brand                   char(50)                      ,
    i_class_id                integer                       ,
    i_class                   char(50)                      ,
    i_category_id             integer                       ,
    i_category                char(50)                      ,
    i_manufact_id             integer                       ,
    i_manufact                char(50)                      ,
    i_size                    char(20)                      ,
    i_formulation             char(20)                      ,
    i_color                   char(20)                      ,
    i_units                   char(10)                      ,
    i_container               char(10)                      ,
    i_manager_id              integer                       ,
    i_product_name            char(50)
)
duplicate key (i_item_sk)
distributed by hash(i_item_sk) buckets 1
properties(
    "replication_num"="1"
);

create table store
(
    s_store_sk                integer               not null,
    s_store_id                char(16)              not null,
    s_rec_start_date          date                          ,
    s_rec_end_date            date                          ,
    s_closed_date_sk          integer                       ,
    s_store_name              varchar(50)                   ,
    s_number_employees        integer                       ,
    s_floor_space             integer                       ,
    s_hours                   char(20)                      ,
    s_manager                 varchar(40)                   ,
    s_market_id               integer                       ,
    s_geography_class         varchar(100)                  ,
    s_market_desc             varchar(100)                  ,
    s_market_manager          varchar(40)                   ,
    s_division_id             integer                       ,
    s_division_name           varchar(50)                   ,
    s_company_id              integer                       ,
    s_company_name            varchar(50)                   ,
    s_street_number           varchar(10)                   ,
    s_street_name             varchar(60)                   ,
    s_street_type             char(15)                      ,
    s_suite_number            char(10)                      ,
    s_city                    varchar(60)                   ,
    s_county                  varchar(30)                   ,
    s_state                   char(2)                       ,
    s_zip                     char(10)                      ,
    s_country                 varchar(20)                   ,
    s_gmt_offset              decimal(5,2)                  ,
    s_tax_precentage          decimal(5,2)
)
duplicate key (s_store_sk)
distributed by hash(s_store_sk) buckets 1
properties(
    "replication_num"="1"
);

create table call_center
(
    cc_call_center_sk         integer               not null,
    cc_call_center_id         char(16)              not null,
    cc_rec_start_date         date                          ,
    cc_rec_end_date           date                          ,
    cc_closed_date_sk         integer                       ,
    cc_open_date_sk           integer                       ,
    cc_name                   varchar(50)                   ,
    cc_class                  varchar(50)                   ,
    cc_employees              integer                       ,
    cc_sq_ft                  integer                       ,
    cc_hours                  char(20)                      ,
    cc_manager                varchar(40)                   ,
    cc_mkt_id                 integer                       ,
    cc_mkt_class              char(50)                      ,
    cc_mkt_desc               varchar(100)                  ,
    cc_market_manager         varchar(40)                   ,
    cc_division               integer                       ,
    cc_division_name          varchar(50)                   ,
    cc_company                integer                       ,
    cc_company_name           char(50)                      ,
    cc_street_number          char(10)                      ,
    cc_street_name            varchar(60)                   ,
    cc_street_type            char(15)                      ,
    cc_suite_number           char(10)                      ,
    cc_city                   varchar(60)                   ,
    cc_county                 varchar(30)                   ,
    cc_state                  char(2)                       ,
    cc_zip                    char(10)                      ,
    cc_country                varchar(20)                   ,
    cc_gmt_offset             decimal(5,2)                  ,
    cc_tax_percentage         decimal(5,2)
)
duplicate key (cc_call_center_sk)
distributed by hash(cc_call_center_sk) buckets 1
properties(
    "replication_num"="1"
);

create table customer
(
    c_customer_sk             integer               not null,
    c_customer_id             char(16)              not null,
    c_current_cdemo_sk        integer                       ,
    c_current_hdemo_sk        integer                       ,
    c_current_addr_sk         integer                       ,
    c_first_shipto_date_sk    integer                       ,
    c_first_sales_date_sk     integer                       ,
    c_salutation              char(10)                      ,
    c_first_name              char(20)                      ,
    c_last_name               char(30)                      ,
    c_preferred_cust_flag     char(1)                       ,
    c_birth_day               integer                       ,
    c_birth_month             integer                       ,
    c_birth_year              integer                       ,
    c_birth_country           varchar(20)                   ,
    c_login                   char(13)                      ,
    c_email_address           char(50)                      ,
    c_last_review_date        char(10)
)
duplicate key (c_customer_sk)
distributed by hash(c_customer_sk) buckets 1
properties(
    "replication_num"="1"
);

create table web_site
(
    web_site_sk               integer               not null,
    web_site_id               char(16)              not null,
    web_rec_start_date        date                          ,
    web_rec_end_date          date                          ,
    web_name                  varchar(50)                   ,
    web_open_date_sk          integer                       ,
    web_close_date_sk         integer                       ,
    web_class                 varchar(50)                   ,
    web_manager               varchar(40)                   ,
    web_mkt_id                integer                       ,
    web_mkt_class             varchar(50)                   ,
    web_mkt_desc              varchar(100)                  ,
    web_market_manager        varchar(40)                   ,
    web_company_id            integer                       ,
    web_company_name          char(50)                      ,
    web_street_number         char(10)                      ,
    web_street_name           varchar(60)                   ,
    web_street_type           char(15)                      ,
    web_suite_number          char(10)                      ,
    web_city                  varchar(60)                   ,
    web_county                varchar(30)                   ,
    web_state                 char(2)                       ,
    web_zip                   char(10)                      ,
    web_country               varchar(20)                   ,
    web_gmt_offset            decimal(5,2)                  ,
    web_tax_percentage        decimal(5,2)
)
duplicate key (web_site_sk)
distributed by hash(web_site_sk) buckets 1
properties(
    "replication_num"="1"
);

create table store_returns
(
    sr_item_sk                integer               not null,
    sr_ticket_number          integer               not null,
    sr_returned_date_sk       integer                       ,
    sr_return_time_sk         integer                       ,
    sr_customer_sk            integer                       ,
    sr_cdemo_sk               integer                       ,
    sr_hdemo_sk               integer                       ,
    sr_addr_sk                integer                       ,
    sr_store_sk               integer                       ,
    sr_reason_sk              integer                       ,
    sr_return_quantity        integer                       ,
    sr_return_amt             decimal(7,2)                  ,
    sr_return_tax             decimal(7,2)                  ,
    sr_return_amt_inc_tax     decimal(7,2)                  ,
    sr_fee                    decimal(7,2)                  ,
    sr_return_ship_cost       decimal(7,2)                  ,
    sr_refunded_cash          decimal(7,2)                  ,
    sr_reversed_charge        decimal(7,2)                  ,
    sr_store_credit           decimal(7,2)                  ,
    sr_net_loss               decimal(7,2)
)
duplicate key (sr_item_sk, sr_ticket_number)
distributed by hash(sr_item_sk, sr_ticket_number) buckets 1
properties(
    "replication_num"="1"
);

create table household_demographics
(
    hd_demo_sk                integer               not null,
    hd_income_band_sk         integer                       ,
    hd_buy_potential          char(15)                      ,
    hd_dep_count              integer                       ,
    hd_vehicle_count          integer
)
duplicate key (hd_demo_sk)
distributed by hash(hd_demo_sk) buckets 1
properties(
    "replication_num"="1"
);

create table web_page
(
    wp_web_page_sk            integer               not null,
    wp_web_page_id            char(16)              not null,
    wp_rec_start_date         date                          ,
    wp_rec_end_date           date                          ,
    wp_creation_date_sk       integer                       ,
    wp_access_date_sk         integer                       ,
    wp_autogen_flag           char(1)                       ,
    wp_customer_sk            integer                       ,
    wp_url                    varchar(100)                  ,
    wp_type                   char(50)                      ,
    wp_char_count             integer                       ,
    wp_link_count             integer                       ,
    wp_image_count            integer                       ,
    wp_max_ad_count           integer
)
duplicate key (wp_web_page_sk)
distributed by hash(wp_web_page_sk) buckets 1
properties(
    "replication_num"="1"
);

create table promotion
(
    p_promo_sk                integer               not null,
    p_promo_id                char(16)              not null,
    p_start_date_sk           integer                       ,
    p_end_date_sk             integer                       ,
    p_item_sk                 integer                       ,
    p_cost                    decimal(15,2)                 ,
    p_response_target         integer                       ,
    p_promo_name              char(50)                      ,
    p_channel_dmail           char(1)                       ,
    p_channel_email           char(1)                       ,
    p_channel_catalog         char(1)                       ,
    p_channel_tv              char(1)                       ,
    p_channel_radio           char(1)                       ,
    p_channel_press           char(1)                       ,
    p_channel_event           char(1)                       ,
    p_channel_demo            char(1)                       ,
    p_channel_details         varchar(100)                  ,
    p_purpose                 char(15)                      ,
    p_discount_active         char(1)
)
duplicate key (p_promo_sk)
distributed by hash(p_promo_sk) buckets 1
properties(
    "replication_num"="1"
);

create table catalog_page
(
    cp_catalog_page_sk        integer               not null,
    cp_catalog_page_id        char(16)              not null,
    cp_start_date_sk          integer                       ,
    cp_end_date_sk            integer                       ,
    cp_department             varchar(50)                   ,
    cp_catalog_number         integer                       ,
    cp_catalog_page_number    integer                       ,
    cp_description            varchar(100)                  ,
    cp_type                   varchar(100)
)
duplicate key (cp_catalog_page_sk)
distributed by hash(cp_catalog_page_sk) buckets 1
properties(
    "replication_num"="1"
);

create table inventory
(
    inv_date_sk               integer               not null,
    inv_item_sk               integer               not null,
    inv_warehouse_sk          integer               not null,
    inv_quantity_on_hand      integer
)
duplicate key (inv_date_sk, inv_item_sk, inv_warehouse_sk)
distributed by hash(inv_date_sk, inv_item_sk, inv_warehouse_sk) buckets 1
properties(
    "replication_num"="1"
);

create table catalog_returns
(
    cr_item_sk                integer               not null,
    cr_order_number           integer               not null,
    cr_returned_date_sk       integer                       ,
    cr_returned_time_sk       integer                       ,
    cr_refunded_customer_sk   integer                       ,
    cr_refunded_cdemo_sk      integer                       ,
    cr_refunded_hdemo_sk      integer                       ,
    cr_refunded_addr_sk       integer                       ,
    cr_returning_customer_sk  integer                       ,
    cr_returning_cdemo_sk     integer                       ,
    cr_returning_hdemo_sk     integer                       ,
    cr_returning_addr_sk      integer                       ,
    cr_call_center_sk         integer                       ,
    cr_catalog_page_sk        integer                       ,
    cr_ship_mode_sk           integer                       ,
    cr_warehouse_sk           integer                       ,
    cr_reason_sk              integer                       ,
    cr_return_quantity        integer                       ,
    cr_return_amount          decimal(7,2)                  ,
    cr_return_tax             decimal(7,2)                  ,
    cr_return_amt_inc_tax     decimal(7,2)                  ,
    cr_fee                    decimal(7,2)                  ,
    cr_return_ship_cost       decimal(7,2)                  ,
    cr_refunded_cash          decimal(7,2)                  ,
    cr_reversed_charge        decimal(7,2)                  ,
    cr_store_credit           decimal(7,2)                  ,
    cr_net_loss               decimal(7,2)
)
duplicate key (cr_item_sk, cr_order_number)
distributed by hash(cr_item_sk, cr_order_number) buckets 1
properties(
    "replication_num"="1"
);

create table web_returns
(
    wr_item_sk                integer               not null,
    wr_order_number           integer               not null,
    wr_returned_date_sk       integer                       ,
    wr_returned_time_sk       integer                       ,
    wr_refunded_customer_sk   integer                       ,
    wr_refunded_cdemo_sk      integer                       ,
    wr_refunded_hdemo_sk      integer                       ,
    wr_refunded_addr_sk       integer                       ,
    wr_returning_customer_sk  integer                       ,
    wr_returning_cdemo_sk     integer                       ,
    wr_returning_hdemo_sk     integer                       ,
    wr_returning_addr_sk      integer                       ,
    wr_web_page_sk            integer                       ,
    wr_reason_sk              integer                       ,
    wr_return_quantity        integer                       ,
    wr_return_amt             decimal(7,2)                  ,
    wr_return_tax             decimal(7,2)                  ,
    wr_return_amt_inc_tax     decimal(7,2)                  ,
    wr_fee                    decimal(7,2)                  ,
    wr_return_ship_cost       decimal(7,2)                  ,
    wr_refunded_cash          decimal(7,2)                  ,
    wr_reversed_charge        decimal(7,2)                  ,
    wr_account_credit         decimal(7,2)                  ,
    wr_net_loss               decimal(7,2)
)
duplicate key (wr_item_sk, wr_order_number)
distributed by hash(wr_item_sk, wr_order_number) buckets 1
properties(
    "replication_num"="1"
);

create table web_sales
(
    ws_item_sk                integer               not null,
    ws_order_number           integer               not null,
    ws_sold_date_sk           integer                       ,
    ws_sold_time_sk           integer                       ,
    ws_ship_date_sk           integer                       ,
    ws_bill_customer_sk       integer                       ,
    ws_bill_cdemo_sk          integer                       ,
    ws_bill_hdemo_sk          integer                       ,
    ws_bill_addr_sk           integer                       ,
    ws_ship_customer_sk       integer                       ,
    ws_ship_cdemo_sk          integer                       ,
    ws_ship_hdemo_sk          integer                       ,
    ws_ship_addr_sk           integer                       ,
    ws_web_page_sk            integer                       ,
    ws_web_site_sk            integer                       ,
    ws_ship_mode_sk           integer                       ,
    ws_warehouse_sk           integer                       ,
    ws_promo_sk               integer                       ,
    ws_quantity               integer                       ,
    ws_wholesale_cost         decimal(7,2)                  ,
    ws_list_price             decimal(7,2)                  ,
    ws_sales_price            decimal(7,2)                  ,
    ws_ext_discount_amt       decimal(7,2)                  ,
    ws_ext_sales_price        decimal(7,2)                  ,
    ws_ext_wholesale_cost     decimal(7,2)                  ,
    ws_ext_list_price         decimal(7,2)                  ,
    ws_ext_tax                decimal(7,2)                  ,
    ws_coupon_amt             decimal(7,2)                  ,
    ws_ext_ship_cost          decimal(7,2)                  ,
    ws_net_paid               decimal(7,2)                  ,
    ws_net_paid_inc_tax       decimal(7,2)                  ,
    ws_net_paid_inc_ship      decimal(7,2)                  ,
    ws_net_paid_inc_ship_tax  decimal(7,2)                  ,
    ws_net_profit             decimal(7,2)
)
duplicate key (ws_item_sk, ws_order_number)
distributed by hash(ws_item_sk, ws_order_number) buckets 1
properties(
    "replication_num"="1"
);

create table catalog_sales
(
    cs_item_sk                integer               not null,
    cs_order_number           integer               not null,
    cs_sold_date_sk           integer                       ,
    cs_sold_time_sk           integer                       ,
    cs_ship_date_sk           integer                       ,
    cs_bill_customer_sk       integer                       ,
    cs_bill_cdemo_sk          integer                       ,
    cs_bill_hdemo_sk          integer                       ,
    cs_bill_addr_sk           integer                       ,
    cs_ship_customer_sk       integer                       ,
    cs_ship_cdemo_sk          integer                       ,
    cs_ship_hdemo_sk          integer                       ,
    cs_ship_addr_sk           integer                       ,
    cs_call_center_sk         integer                       ,
    cs_catalog_page_sk        integer                       ,
    cs_ship_mode_sk           integer                       ,
    cs_warehouse_sk           integer                       ,
    cs_promo_sk               integer                       ,
    cs_quantity               integer                       ,
    cs_wholesale_cost         decimal(7,2)                  ,
    cs_list_price             decimal(7,2)                  ,
    cs_sales_price            decimal(7,2)                  ,
    cs_ext_discount_amt       decimal(7,2)                  ,
    cs_ext_sales_price        decimal(7,2)                  ,
    cs_ext_wholesale_cost     decimal(7,2)                  ,
    cs_ext_list_price         decimal(7,2)                  ,
    cs_ext_tax                decimal(7,2)                  ,
    cs_coupon_amt             decimal(7,2)                  ,
    cs_ext_ship_cost          decimal(7,2)                  ,
    cs_net_paid               decimal(7,2)                  ,
    cs_net_paid_inc_tax       decimal(7,2)                  ,
    cs_net_paid_inc_ship      decimal(7,2)                  ,
    cs_net_paid_inc_ship_tax  decimal(7,2)                  ,
    cs_net_profit             decimal(7,2)
)
duplicate key (cs_item_sk, cs_order_number)
distributed by hash(cs_item_sk, cs_order_number) buckets 1
properties(
    "replication_num"="1"
);

create table store_sales
(
    ss_item_sk                integer               not null,
    ss_ticket_number          integer               not null,
    ss_sold_date_sk           integer                       ,
    ss_sold_time_sk           integer                       ,
    ss_customer_sk            integer                       ,
    ss_cdemo_sk               integer                       ,
    ss_hdemo_sk               integer                       ,
    ss_addr_sk                integer                       ,
    ss_store_sk               integer                       ,
    ss_promo_sk               integer                       ,
    ss_quantity               integer                       ,
    ss_wholesale_cost         decimal(7,2)                  ,
    ss_list_price             decimal(7,2)                  ,
    ss_sales_price            decimal(7,2)                  ,
    ss_ext_discount_amt       decimal(7,2)                  ,
    ss_ext_sales_price        decimal(7,2)                  ,
    ss_ext_wholesale_cost     decimal(7,2)                  ,
    ss_ext_list_price         decimal(7,2)                  ,
    ss_ext_tax                decimal(7,2)                  ,
    ss_coupon_amt             decimal(7,2)                  ,
    ss_net_paid               decimal(7,2)                  ,
    ss_net_paid_inc_tax       decimal(7,2)                  ,
    ss_net_profit             decimal(7,2)
)
duplicate key (ss_item_sk, ss_ticket_number)
distributed by hash(ss_item_sk, ss_ticket_number) buckets 1
properties(
    "replication_num"="1"
);
e5njpo68

e5njpo685#

load data

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T customer_address_"$i"_10.dat http://host:8030/api/tpcds/customer_address/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T customer_demographics_"$i"_10.dat http://host:8030/api/tpcds/customer_demographics/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T date_dim_"$i"_10.dat http://host:8030/api/tpcds/date_dim/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T warehouse_"$i"_10.dat http://host:8030/api/tpcds/warehouse/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T ship_mode_"$i"_10.dat http://host:8030/api/tpcds/ship_mode/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T time_dim_"$i"_10.dat http://host:8030/api/tpcds/time_dim/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T reason_"$i"_10.dat http://host:8030/api/tpcds/reason/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T income_band_"$i"_10.dat http://host:8030/api/tpcds/income_band/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -H "columns:cr_returned_date_sk,cr_returned_time_sk,cr_item_sk,cr_refunded_customer_sk,cr_refunded_cdemo_sk,cr_refunded_hdemo_sk,cr_refunded_addr_sk,cr_returning_customer_sk,cr_returning_cdemo_sk,cr_returning_hdemo_sk,cr_returning_addr_sk,cr_call_center_sk,cr_catalog_page_sk,cr_ship_mode_sk,cr_warehouse_sk,cr_reason_sk,cr_order_number,cr_return_quantity,cr_return_amount,cr_return_tax,cr_return_amt_inc_tax,cr_fee,cr_return_ship_cost,cr_refunded_cash,cr_reversed_charge,cr_store_credit,cr_net_loss" -T catalog_returns_"$i"_10.dat http://host:8030/api/tpcds/catalog_returns/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -H "columns:cs_sold_date_sk,cs_sold_time_sk,cs_ship_date_sk,cs_bill_customer_sk,cs_bill_cdemo_sk,cs_bill_hdemo_sk,cs_bill_addr_sk,cs_ship_customer_sk,cs_ship_cdemo_sk,cs_ship_hdemo_sk,cs_ship_addr_sk,cs_call_center_sk,cs_catalog_page_sk,cs_ship_mode_sk,cs_warehouse_sk,cs_item_sk,cs_promo_sk,cs_order_number,cs_quantity,cs_wholesale_cost,cs_list_price,cs_sales_price,cs_ext_discount_amt,cs_ext_sales_price,cs_ext_wholesale_cost,cs_ext_list_price,cs_ext_tax,cs_coupon_amt,cs_ext_ship_cost,cs_net_paid,cs_net_paid_inc_tax,cs_net_paid_inc_ship,cs_net_paid_inc_ship_tax,cs_net_profit" -T catalog_sales_"$i"_10.dat http://host:8030/api/tpcds/catalog_sales/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T item_"$i"_10.dat http://host:8030/api/tpcds/item/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T store_"$i"_10.dat http://host:8030/api/tpcds/store/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T call_center_"$i"_10.dat http://host:8030/api/tpcds/call_center/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -H "strict_mode: false" -T customer_"$i"_10.dat http://host:8030/api/tpcds/customer/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T web_site_"$i"_10.dat http://host:8030/api/tpcds/web_site/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -H "columns:sr_returned_date_sk,sr_return_time_sk,sr_item_sk,sr_customer_sk,sr_cdemo_sk,sr_hdemo_sk,sr_addr_sk,sr_store_sk,sr_reason_sk,sr_ticket_number,sr_return_quantity,sr_return_amt,sr_return_tax,sr_return_amt_inc_tax,sr_fee,sr_return_ship_cost,sr_refunded_cash,sr_reversed_charge,sr_store_credit,sr_net_loss" -T store_returns_"$i"_10.dat http://host:8030/api/tpcds/store_returns/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T household_demographics_"$i"_10.dat http://host:8030/api/tpcds/household_demographics/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T web_page_"$i"_10.dat http://host:8030/api/tpcds/web_page/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -H "columns:ss_sold_date_sk,ss_sold_time_sk,ss_item_sk,ss_customer_sk,ss_cdemo_sk,ss_hdemo_sk,ss_addr_sk,ss_store_sk,ss_promo_sk,ss_ticket_number,ss_quantity,ss_wholesale_cost,ss_list_price,ss_sales_price,ss_ext_discount_amt,ss_ext_sales_price,ss_ext_wholesale_cost,ss_ext_list_price,ss_ext_tax,ss_coupon_amt,ss_net_paid,ss_net_paid_inc_tax,ss_net_profit" -T store_sales_"$i"_10.dat http://host:8030/api/tpcds/store_sales/_stream_load
done
for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T promotion_"$i"_10.dat http://host:8030/api/tpcds/promotion/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T catalog_page_"$i"_10.dat http://host:8030/api/tpcds/catalog_page/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -T inventory_"$i"_10.dat http://host:8030/api/tpcds/inventory/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -H "columns:wr_returned_date_sk,wr_returned_time_sk,wr_item_sk,wr_refunded_customer_sk,wr_refunded_cdemo_sk,wr_refunded_hdemo_sk,wr_refunded_addr_sk,wr_returning_customer_sk,wr_returning_cdemo_sk,wr_returning_hdemo_sk,wr_returning_addr_sk,wr_web_page_sk,wr_reason_sk,wr_order_number,wr_return_quantity,wr_return_amt,wr_return_tax,wr_return_amt_inc_tax,wr_fee,wr_return_ship_cost,wr_refunded_cash,wr_reversed_charge,wr_account_credit,wr_net_loss" -T web_returns_"$i"_10.dat http://host:8030/api/tpcds/web_returns/_stream_load
done

for((i=1;i<=10;i++))
do
    curl --location-trusted -u root: -H "max_filter_ratio:0.2" -H "column_separator:|" -H "columns:ws_sold_date_sk,ws_sold_time_sk,ws_ship_date_sk,ws_item_sk,ws_bill_customer_sk,ws_bill_cdemo_sk,ws_bill_hdemo_sk,ws_bill_addr_sk,ws_ship_customer_sk,ws_ship_cdemo_sk,ws_ship_hdemo_sk,ws_ship_addr_sk,ws_web_page_sk,ws_web_site_sk,ws_ship_mode_sk,ws_warehouse_sk,ws_promo_sk,ws_order_number,ws_quantity,ws_wholesale_cost,ws_list_price,ws_sales_price,ws_ext_discount_amt,ws_ext_sales_price,ws_ext_wholesale_cost,ws_ext_list_price,ws_ext_tax,ws_coupon_amt,ws_ext_ship_cost,ws_net_paid,ws_net_paid_inc_tax,ws_net_paid_inc_ship,ws_net_paid_inc_ship_tax,ws_net_profit" -T web_sales_"$i"_10.dat http://host:8030/api/tpcds/web_sales/_stream_load
done
lzfw57am

lzfw57am6#

This is because the completion of the constant column in our implementation is in aggNode. The calculation of rollup repetition is done between scanNode and agg, so the constant cannot be repeated correctly. This problem is difficult to solve under our current framework. I think refactor the implementation of grouping set is needed to solve this problem

相关问题