今天mentor给了一个sql语句优化的任务。（环境是sql developer）有一个语句执行很慢，查询出来的结果有17544条记录，但需970秒，速度很慢。语句是这样的：
select distinct 'amend_new',
reporttitle,
reportsubtitle,
cab_cab_transactions.branchcode,
cab_cab_transactions.prtfo_cd,
cab_cab_transactions.sstm_scrty_id,
cab_cab_transactions.sstm_trx_id,
cab_cab_transactions.trde_dttm,
cab_cab_transactions.efcte_dttm,
cab_cab_transactions.due_stlmnt_dt,
cab_cab_transactions.cncl_efcte_dttm,
cab_cab_transactions.trde_sstm_id,
cab_cab_transactions.trx_type_cd,
cab_cab_transactions.trx_type_dscrn,
cab_cab_transactions.trx_subtype_cd,
cab_cab_transactions.trde_stat_flg,
cab_cab_transactions.csh_cr_dr_indcr,
cab_cab_transactions.long_shrt_indcr,
cab_cab_transactions.lcl_crncy,
cab_cab_transactions.stlmt_crncy,
cab_cab_transactions.nomin_qty,
cab_cab_transactions.price,
cab_cab_transactions.lcl_cst,
cab_cab_transactions.prtfo_cst,
cab_cab_transactions.lcl_book_cst,
cab_cab_transactions.prtfo_book_cst,
cab_cab_transactions.lcl_sell_prcds,
cab_cab_transactions.prtfo_sell_prcds,
cab_cab_transactions.lcl_gnls,
cab_cab_transactions.prtfo_gnls,
cab_cab_transactions.lcl_acrd_intrt,
cab_cab_transactions.prtfo_acrd_intrt,
cab_cab_transactions.stlmt_crncy_stlmt_amt,
cab_cab_transactions.lcl_net_amt,
cab_cab_transactions.prtfo_net_amt,
cab_cab_transactions.fx_bght_amt,
cab_cab_transactions.fx_sold_amt,
cab_cab_transactions.prtfo_crncy_stlmt_amt,
cab_cab_transactions.prtfo_net_incme,
cab_cab_transactions.dvnd_crncy_net_incme,
cab_cab_transactions.dvnd_type_cd,
cab_cab_transactions.lcl_intrt_pd_rec,
cab_cab_transactions.prtfo_intrt_pd_rec,
cab_cab_transactions.lcl_dvdnd_pd_rec,
cab_cab_transactions.prtfo_dvdnd_pd_rec,
cab_cab_transactions.lcl_sundry_inc_pd_rec,
cab_cab_transactions.prtfo_sundry_inc_pd_rec,
cab_cab_transactions.bnk_csh_cptl_secid,
cab_cab_transactions.bnk_csh_inc_secid,
cab_cab_transactions.reportdate,
cab_cab_transactions.filename,
sysdate,
'e483448'
from cab_cfg_trx_type_mapping right join(cab_cab_tran_adjustments
inner join cab_cab_transactions on(cab_cab_transactions.branchcode = cab_cab_tran_adjustments.branchcode )
and(cab_cab_tran_adjustments.sstm_trx_id = cab_cab_transactions.sstm_trx_id)) on(cab_cfg_trx_type_mapping.cab_trx_type_cd = cab_cab_transactions.trx_type_cd)
and(nvl(cab_cfg_trx_type_mapping.cab_trx_subtype_cd,' ') = nvl(cab_cab_transactions.trx_subtype_cd,' ')
and (cab_cfg_trx_type_mapping.branchcode=cab_cab_transactions.branchcode))
where cab_cab_transactions.prtfo_cd in
(select distinct prtfo_cd
from cab_cab_valuations_working
where created_by = 'e483448'
and branchcode='isa')
and cab_cab_tran_adjustments.efcte_dttm > '2011-07-31'
and cab_cab_tran_adjustments.efcte_dttm <= '2011-08-31'
and eff_trde_stat_flg <> 'x'
and cab_cab_transactions.branchcode = 'isa'
and cab_cab_tran_adjustments.branchcode = 'isa'
and(cab_cfg_trx_type_mapping.cab_reportgroup = 'cabvaluation' or cab_cfg_trx_type_mapping.cab_reportgroup is null)
问题在distinct上面，它会导致对全表扫描，而且会导致排序，然后删除重复的记录，所以速度很慢，因此需要优化distinct。查了不少资料，并逐一尝试，最后发现了一个非常可观的优化结果，用group by。语句如下：
select 'amend_new',
reporttitle,
reportsubtitle,
cab_cab_transactions.branchcode,
cab_cab_transactions.prtfo_cd,
cab_cab_transactions.sstm_scrty_id,
cab_cab_transactions.sstm_trx_id,
cab_cab_transactions.trde_dttm,
cab_cab_transactions.efcte_dttm,
cab_cab_transactions.due_stlmnt_dt,
cab_cab_transactions.cncl_efcte_dttm,
cab_cab_transactions.trde_sstm_id,
cab_cab_transactions.trx_type_cd,
cab_cab_transactions.trx_type_dscrn,
cab_cab_transactions.trx_subtype_cd,
cab_cab_transactions.trde_stat_flg,
cab_cab_transactions.csh_cr_dr_indcr,
cab_cab_transactions.long_shrt_indcr,
cab_cab_transactions.lcl_crncy,
cab_cab_transactions.stlmt_crncy,
cab_cab_transactions.nomin_qty,
cab_cab_transactions.price,
cab_cab_transactions.lcl_cst,
cab_cab_transactions.prtfo_cst,
cab_cab_transactions.lcl_book_cst,
cab_cab_transactions.prtfo_book_cst,
cab_cab_transactions.lcl_sell_prcds,
cab_cab_transactions.prtfo_sell_prcds,
cab_cab_transactions.lcl_gnls,
cab_cab_transactions.prtfo_gnls,
cab_cab_transactions.lcl_acrd_intrt,
cab_cab_transactions.prtfo_acrd_intrt,
cab_cab_transactions.stlmt_crncy_stlmt_amt,
cab_cab_transactions.lcl_net_amt,
cab_cab_transactions.prtfo_net_amt,
cab_cab_transactions.fx_bght_amt,
cab_cab_transactions.fx_sold_amt,
cab_cab_transactions.prtfo_crncy_stlmt_amt,
cab_cab_transactions.prtfo_net_incme,
cab_cab_transactions.dvnd_crncy_net_incme,
cab_cab_transactions.dvnd_type_cd,
cab_cab_transactions.lcl_intrt_pd_rec,
cab_cab_transactions.prtfo_intrt_pd_rec,
cab_cab_transactions.lcl_dvdnd_pd_rec,
cab_cab_transactions.prtfo_dvdnd_pd_rec,
cab_cab_transactions.lcl_sundry_inc_pd_rec,
cab_cab_transactions.prtfo_sundry_inc_pd_rec,
cab_cab_transactions.bnk_csh_cptl_secid,
cab_cab_transactions.bnk_csh_inc_secid,
cab_cab_transactions.reportdate,
cab_cab_transactions.filename,
sysdate,
'e483448'
from cab_cfg_trx_type_mapping right join(cab_cab_tran_adjustments
inner join cab_cab_transactions on(cab_cab_transactions.branchcode = cab_cab_tran_adjustments.branchcode )
and(cab_cab_tran_adjustments.sstm_trx_id = cab_cab_transactions.sstm_trx_id)) on(cab_cfg_trx_type_mapping.cab_trx_type_cd = cab_cab_transactions.trx_type_cd)
and(nvl(cab_cfg_trx_type_mapping.cab_trx_subtype_cd,' ') = nvl(cab_cab_transactions.trx_subtype_cd,' ')
and (cab_cfg_trx_type_mapping.branchcode=cab_cab_transactions.branchcode))
where cab_cab_transactions.prtfo_cd in
(select distinct prtfo_cd
from cab_cab_valuations_working
where created_by = 'e483448'
and branchcode='isa')
and cab_cab_tran_adjustments.efcte_dttm > '2011-07-31'
and cab_cab_tran_adjustments.efcte_dttm <= '2011-08-31'
and eff_trde_stat_flg <> 'x'
and cab_cab_transactions.branchcode = 'isa'
and cab_cab_tran_adjustments.branchcode = 'isa'
and(cab_cfg_trx_type_mapping.cab_reportgroup = 'cabvaluation' or cab_cfg_trx_type_mapping.cab_reportgroup is null)
group by reporttitle,
reportsubtitle,
cab_cab_transactions.branchcode,
cab_cab_transactions.prtfo_cd,
cab_cab_transactions.sstm_scrty_id,
cab_cab_transactions.sstm_trx_id,
cab_cab_transactions.trde_dttm,
cab_cab_transactions.efcte_dttm,
cab_cab_transactions.due_stlmnt_dt,
cab_cab_transactions.cncl_efcte_dttm,
cab_cab_transactions.trde_sstm_id,
cab_cab_transactions.trx_type_cd,
cab_cab_transactions.trx_type_dscrn,
cab_cab_transactions.trx_subtype_cd,
cab_cab_transactions.trde_stat_flg,
cab_cab_transactions.csh_cr_dr_indcr,
cab_cab_transactions.long_shrt_indcr,
cab_cab_transactions.lcl_crncy,
cab_cab_transactions.stlmt_crncy,
cab_cab_transactions.nomin_qty,
cab_cab_transactions.price,
cab_cab_transactions.lcl_cst,
cab_cab_transactions.prtfo_cst,
cab_cab_transactions.lcl_book_cst,
cab_cab_transactions.prtfo_book_cst,
cab_cab_transactions.lcl_sell_prcds,
cab_cab_transactions.prtfo_sell_prcds,
cab_cab_transactions.lcl_gnls,
cab_cab_transactions.prtfo_gnls,
cab_cab_transactions.lcl_acrd_intrt,
cab_cab_transactions.prtfo_acrd_intrt,
cab_cab_transactions.stlmt_crncy_stlmt_amt,
cab_cab_transactions.lcl_net_amt,
cab_cab_transactions.prtfo_net_amt,
cab_cab_transactions.fx_bght_amt,
cab_cab_transactions.fx_sold_amt,
cab_cab_transactions.prtfo_crncy_stlmt_amt,
cab_cab_transactions.prtfo_net_incme,
cab_cab_transactions.dvnd_crncy_net_incme,
cab_cab_transactions.dvnd_type_cd,
cab_cab_transactions.lcl_intrt_pd_rec,
cab_cab_transactions.prtfo_intrt_pd_rec,
cab_cab_transactions.lcl_dvdnd_pd_rec,
cab_cab_transactions.prtfo_dvdnd_pd_rec,
cab_cab_transactions.lcl_sundry_inc_pd_rec,
cab_cab_transactions.prtfo_sundry_inc_pd_rec,
cab_cab_transactions.bnk_csh_cptl_secid,
cab_cab_transactions.bnk_csh_inc_secid,
cab_cab_transactions.reportdate,
cab_cab_transactions.filename
最后执行时间只有15.1秒，快了60多倍，不得不说这优化效果还是很可观的。不过查了很多资料，仍然没有发现合理地解释：为什么distinct 和group by的效率会有这么大差别。查的很多资料，讲的基本都是两者相差不大，实现也差不多。有待解决。
distinct和group by这两者本质上应该没有可比性，distinct 取出唯一列，group by 是分组，但有时候在优化的时候，在没有聚合函数的时候，他们查出来的结果也一样。