From 27af01d552331eacf1ed2671b2b4b6ad4c268106 Mon Sep 17 00:00:00 2001 From: Tay Ray Chuan Date: Wed, 17 Aug 2011 09:53:57 +0800 Subject: [PATCH] xdiff/xprepare: improve O(n*m) performance in xdl_cleanup_records() In xdl_cleanup_records(), we see O(n*m) performance, where n is the number of records from xdf->dstart to xdf->dend, and m is the size of a bucket in xdf->rhash (<= by mlim). Here, we improve this to O(n) by pre-computing nm (in rcrec->len(1|2)) in xdl_classify_record(). Reported-by: Marat Radchenko Signed-off-by: Tay Ray Chuan Signed-off-by: Junio C Hamano --- xdiff/xprepare.c | 86 ++++++++++++++++++++++++++++-------------------- 1 file changed, 50 insertions(+), 36 deletions(-) diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c index 168908523..05a8f01f3 100644 --- a/xdiff/xprepare.c +++ b/xdiff/xprepare.c @@ -34,6 +34,7 @@ typedef struct s_xdlclass { char const *line; long size; long idx; + long len1, len2; } xdlclass_t; typedef struct s_xdlclassifier { @@ -41,6 +42,8 @@ typedef struct s_xdlclassifier { long hsize; xdlclass_t **rchash; chastore_t ncha; + xdlclass_t **rcrecs; + long alloc; long count; long flags; } xdlclassifier_t; @@ -50,15 +53,15 @@ typedef struct s_xdlclassifier { static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags); static void xdl_free_classifier(xdlclassifier_t *cf); -static int xdl_classify_record(xdlclassifier_t *cf, xrecord_t **rhash, unsigned int hbits, - xrecord_t *rec); -static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp, +static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t **rhash, + unsigned int hbits, xrecord_t *rec); +static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp, xdlclassifier_t *cf, xdfile_t *xdf); static void xdl_free_ctx(xdfile_t *xdf); static int xdl_clean_mmatch(char const *dis, long i, long s, long e); -static int xdl_cleanup_records(xdfile_t *xdf1, xdfile_t *xdf2); +static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2); static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2); -static int xdl_optimize_ctxs(xdfile_t *xdf1, xdfile_t *xdf2); +static int xdl_optimize_ctxs(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2); @@ -83,6 +86,14 @@ static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags) { for (i = 0; i < cf->hsize; i++) cf->rchash[i] = NULL; + cf->alloc = size; + if (!(cf->rcrecs = (xdlclass_t **) xdl_malloc(cf->alloc * sizeof(xdlclass_t *)))) { + + xdl_free(cf->rchash); + xdl_cha_free(&cf->ncha); + return -1; + } + cf->count = 0; return 0; @@ -91,16 +102,18 @@ static int xdl_init_classifier(xdlclassifier_t *cf, long size, long flags) { static void xdl_free_classifier(xdlclassifier_t *cf) { + xdl_free(cf->rcrecs); xdl_free(cf->rchash); xdl_cha_free(&cf->ncha); } -static int xdl_classify_record(xdlclassifier_t *cf, xrecord_t **rhash, unsigned int hbits, - xrecord_t *rec) { +static int xdl_classify_record(unsigned int pass, xdlclassifier_t *cf, xrecord_t **rhash, + unsigned int hbits, xrecord_t *rec) { long hi; char const *line; xdlclass_t *rcrec; + xdlclass_t **rcrecs; line = rec->ptr; hi = (long) XDL_HASHLONG(rec->ha, cf->hbits); @@ -116,13 +129,25 @@ static int xdl_classify_record(xdlclassifier_t *cf, xrecord_t **rhash, unsigned return -1; } rcrec->idx = cf->count++; + if (cf->count > cf->alloc) { + cf->alloc *= 2; + if (!(rcrecs = (xdlclass_t **) xdl_realloc(cf->rcrecs, cf->alloc * sizeof(xdlclass_t *)))) { + + return -1; + } + cf->rcrecs = rcrecs; + } + cf->rcrecs[rcrec->idx] = rcrec; rcrec->line = line; rcrec->size = rec->size; rcrec->ha = rec->ha; + rcrec->len1 = rcrec->len2 = 0; rcrec->next = cf->rchash[hi]; cf->rchash[hi] = rcrec; } + (pass == 1) ? rcrec->len1++ : rcrec->len2++; + rec->ha = (unsigned long) rcrec->idx; hi = (long) XDL_HASHLONG(rec->ha, hbits); @@ -133,7 +158,7 @@ static int xdl_classify_record(xdlclassifier_t *cf, xrecord_t **rhash, unsigned } -static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp, +static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_t const *xpp, xdlclassifier_t *cf, xdfile_t *xdf) { unsigned int hbits; long i, nrec, hsize, bsize; @@ -200,7 +225,7 @@ static int xdl_prepare_ctx(mmfile_t *mf, long narec, xpparam_t const *xpp, crec->ha = hav; recs[nrec++] = crec; - if (xdl_classify_record(cf, rhash, hbits, crec) < 0) { + if (xdl_classify_record(pass, cf, rhash, hbits, crec) < 0) { xdl_free(rhash); xdl_free(recs); @@ -276,28 +301,28 @@ int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, return -1; } - if (xdl_prepare_ctx(mf1, enl1, xpp, &cf, &xe->xdf1) < 0) { + if (xdl_prepare_ctx(1, mf1, enl1, xpp, &cf, &xe->xdf1) < 0) { xdl_free_classifier(&cf); return -1; } - if (xdl_prepare_ctx(mf2, enl2, xpp, &cf, &xe->xdf2) < 0) { + if (xdl_prepare_ctx(2, mf2, enl2, xpp, &cf, &xe->xdf2) < 0) { xdl_free_ctx(&xe->xdf1); xdl_free_classifier(&cf); return -1; } - xdl_free_classifier(&cf); - if (!(xpp->flags & XDF_PATIENCE_DIFF) && - xdl_optimize_ctxs(&xe->xdf1, &xe->xdf2) < 0) { + xdl_optimize_ctxs(&cf, &xe->xdf1, &xe->xdf2) < 0) { xdl_free_ctx(&xe->xdf2); xdl_free_ctx(&xe->xdf1); return -1; } + xdl_free_classifier(&cf); + return 0; } @@ -372,11 +397,10 @@ static int xdl_clean_mmatch(char const *dis, long i, long s, long e) { * matches on the other file. Also, lines that have multiple matches * might be potentially discarded if they happear in a run of discardable. */ -static int xdl_cleanup_records(xdfile_t *xdf1, xdfile_t *xdf2) { - long i, nm, rhi, nreff, mlim; - unsigned long hav; +static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) { + long i, nm, nreff; xrecord_t **recs; - xrecord_t *rec; + xdlclass_t *rcrec; char *dis, *dis1, *dis2; if (!(dis = (char *) xdl_malloc(xdf1->nrec + xdf2->nrec + 2))) { @@ -387,26 +411,16 @@ static int xdl_cleanup_records(xdfile_t *xdf1, xdfile_t *xdf2) { dis1 = dis; dis2 = dis1 + xdf1->nrec + 1; - if ((mlim = xdl_bogosqrt(xdf1->nrec)) > XDL_MAX_EQLIMIT) - mlim = XDL_MAX_EQLIMIT; for (i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; i <= xdf1->dend; i++, recs++) { - hav = (*recs)->ha; - rhi = (long) XDL_HASHLONG(hav, xdf2->hbits); - for (nm = 0, rec = xdf2->rhash[rhi]; rec; rec = rec->next) - if (rec->ha == hav && ++nm == mlim) - break; - dis1[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1; + rcrec = cf->rcrecs[(*recs)->ha]; + nm = rcrec ? rcrec->len2 : 0; + dis1[i] = (nm == 0) ? 0: 1; } - if ((mlim = xdl_bogosqrt(xdf2->nrec)) > XDL_MAX_EQLIMIT) - mlim = XDL_MAX_EQLIMIT; for (i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; i <= xdf2->dend; i++, recs++) { - hav = (*recs)->ha; - rhi = (long) XDL_HASHLONG(hav, xdf1->hbits); - for (nm = 0, rec = xdf1->rhash[rhi]; rec; rec = rec->next) - if (rec->ha == hav && ++nm == mlim) - break; - dis2[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1; + rcrec = cf->rcrecs[(*recs)->ha]; + nm = rcrec ? rcrec->len1 : 0; + dis2[i] = (nm == 0) ? 0: 1; } for (nreff = 0, i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; @@ -468,10 +482,10 @@ static int xdl_trim_ends(xdfile_t *xdf1, xdfile_t *xdf2) { } -static int xdl_optimize_ctxs(xdfile_t *xdf1, xdfile_t *xdf2) { +static int xdl_optimize_ctxs(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) { if (xdl_trim_ends(xdf1, xdf2) < 0 || - xdl_cleanup_records(xdf1, xdf2) < 0) { + xdl_cleanup_records(cf, xdf1, xdf2) < 0) { return -1; } -- 2.30.2