From: Nick Hengeveld Date: Wed, 28 Sep 2005 17:14:04 +0000 (-0700) Subject: [PATCH] HTTP partial transfer support for object, pack, and index transfers X-Git-Tag: v0.99.8~19 X-Git-Url: https://git.tokkee.org/?a=commitdiff_plain;h=49a0f240f7be05728f97903efd97ad7898ff6d08;p=git.git [PATCH] HTTP partial transfer support for object, pack, and index transfers HTTP partial transfer support for object, pack, and index transfers [jc: this should not be placed in "master" -- it does not have any fixes requested on the list.] Signed-off-by: Nick Hengeveld Signed-off-by: Junio C Hamano --- diff --git a/http-fetch.c b/http-fetch.c index 0566a9125..778d50824 100644 --- a/http-fetch.c +++ b/http-fetch.c @@ -13,8 +13,12 @@ #define curl_global_init(a) do { /* nothing */ } while(0) #endif +#define PREV_BUF_SIZE 4096 +#define RANGE_HEADER_SIZE 30 + static CURL *curl; static struct curl_slist *no_pragma_header; +static struct curl_slist *no_range_header; static char curl_errorstr[CURL_ERROR_SIZE]; static char *initial_base; @@ -87,12 +91,37 @@ void prefetch(unsigned char *sha1) { } +int relink_or_rename(char *old, char *new) { + int ret; + + ret = link(old, new); + if (ret < 0) { + /* Same Coda hack as in write_sha1_file(sha1_file.c) */ + ret = errno; + if (ret == EXDEV && !rename(old, new)) + return 0; + } + unlink(old); + if (ret) { + if (ret != EEXIST) + return ret; + } + + return 0; +} + static int got_alternates = 0; static int fetch_index(struct alt_base *repo, unsigned char *sha1) { char *filename; char *url; + char tmpfile[PATH_MAX]; + int ret; + long prev_posn = 0; + char range[RANGE_HEADER_SIZE]; + struct curl_slist *range_header = NULL; + CURLcode curl_result; FILE *indexfile; @@ -108,7 +137,8 @@ static int fetch_index(struct alt_base *repo, unsigned char *sha1) repo->base, sha1_to_hex(sha1)); filename = sha1_pack_index_name(sha1); - indexfile = fopen(filename, "w"); + snprintf(tmpfile, sizeof(tmpfile), "%s.temp", filename); + indexfile = fopen(tmpfile, "a"); if (!indexfile) return error("Unable to open local file %s for pack index", filename); @@ -119,13 +149,36 @@ static int fetch_index(struct alt_base *repo, unsigned char *sha1) curl_easy_setopt(curl, CURLOPT_HTTPHEADER, no_pragma_header); curl_easy_setopt(curl, CURLOPT_ERRORBUFFER, curl_errorstr); - if (curl_easy_perform(curl)) { + /* If there is data present from a previous transfer attempt, + resume where it left off */ + prev_posn = ftell(indexfile); + if (prev_posn>0) { + if (get_verbosely) + fprintf(stderr, + "Resuming fetch of index for pack %s at byte %ld\n", + sha1_to_hex(sha1), prev_posn); + sprintf(range, "Range: bytes=%ld-", prev_posn); + range_header = curl_slist_append(range_header, range); + curl_easy_setopt(curl, CURLOPT_HTTPHEADER, range_header); + } + + /* Clear out the Range: header after performing the request, so + other curl requests don't inherit inappropriate header data */ + curl_result = curl_easy_perform(curl); + curl_easy_setopt(curl, CURLOPT_HTTPHEADER, no_range_header); + if (curl_result != 0) { fclose(indexfile); return error("Unable to get pack index %s\n%s", url, curl_errorstr); } fclose(indexfile); + + ret = relink_or_rename(tmpfile, filename); + if (ret) + return error("unable to write index filename %s: %s", + filename, strerror(ret)); + return 0; } @@ -306,6 +359,12 @@ static int fetch_pack(struct alt_base *repo, unsigned char *sha1) struct packed_git **lst; FILE *packfile; char *filename; + char tmpfile[PATH_MAX]; + int ret; + long prev_posn = 0; + char range[RANGE_HEADER_SIZE]; + struct curl_slist *range_header = NULL; + CURLcode curl_result; if (fetch_indices(repo)) return -1; @@ -325,7 +384,8 @@ static int fetch_pack(struct alt_base *repo, unsigned char *sha1) repo->base, sha1_to_hex(target->sha1)); filename = sha1_pack_name(target->sha1); - packfile = fopen(filename, "w"); + snprintf(tmpfile, sizeof(tmpfile), "%s.temp", filename); + packfile = fopen(tmpfile, "a"); if (!packfile) return error("Unable to open local file %s for pack", filename); @@ -336,7 +396,24 @@ static int fetch_pack(struct alt_base *repo, unsigned char *sha1) curl_easy_setopt(curl, CURLOPT_HTTPHEADER, no_pragma_header); curl_easy_setopt(curl, CURLOPT_ERRORBUFFER, curl_errorstr); - if (curl_easy_perform(curl)) { + /* If there is data present from a previous transfer attempt, + resume where it left off */ + prev_posn = ftell(packfile); + if (prev_posn>0) { + if (get_verbosely) + fprintf(stderr, + "Resuming fetch of pack %s at byte %ld\n", + sha1_to_hex(target->sha1), prev_posn); + sprintf(range, "Range: bytes=%ld-", prev_posn); + range_header = curl_slist_append(range_header, range); + curl_easy_setopt(curl, CURLOPT_HTTPHEADER, range_header); + } + + /* Clear out the Range: header after performing the request, so + other curl requests don't inherit inappropriate header data */ + curl_result = curl_easy_perform(curl); + curl_easy_setopt(curl, CURLOPT_HTTPHEADER, no_range_header); + if (curl_result != 0) { fclose(packfile); return error("Unable to get pack file %s\n%s", url, curl_errorstr); @@ -344,6 +421,11 @@ static int fetch_pack(struct alt_base *repo, unsigned char *sha1) fclose(packfile); + ret = relink_or_rename(tmpfile, filename); + if (ret) + return error("unable to write pack filename %s: %s", + filename, strerror(ret)); + lst = &repo->packs; while (*lst != target) lst = &((*lst)->next); @@ -360,14 +442,29 @@ static int fetch_object(struct alt_base *repo, unsigned char *sha1) char *filename = sha1_file_name(sha1); unsigned char real_sha1[20]; char tmpfile[PATH_MAX]; + char prevfile[PATH_MAX]; int ret; char *url; char *posn; + int prevlocal; + unsigned char prev_buf[PREV_BUF_SIZE]; + ssize_t prev_read = 0; + long prev_posn = 0; + char range[RANGE_HEADER_SIZE]; + struct curl_slist *range_header = NULL; + CURLcode curl_result; + + snprintf(tmpfile, sizeof(tmpfile), "%s.temp", filename); + snprintf(prevfile, sizeof(prevfile), "%s.prev", filename); + unlink(prevfile); + rename(tmpfile, prevfile); + unlink(tmpfile); + + local = open(tmpfile, O_WRONLY | O_CREAT | O_EXCL, 0666); - snprintf(tmpfile, sizeof(tmpfile), "%s/obj_XXXXXX", - get_object_directory()); + /* Note: if another instance starts now, it will turn our new + tmpfile into its prevfile. */ - local = mkstemp(tmpfile); if (local < 0) return error("Couldn't create temporary file %s for %s: %s\n", tmpfile, filename, strerror(errno)); @@ -396,8 +493,57 @@ static int fetch_object(struct alt_base *repo, unsigned char *sha1) curl_easy_setopt(curl, CURLOPT_URL, url); - if (curl_easy_perform(curl)) { - unlink(filename); + /* If a previous temp file is present, process what was already + fetched. */ + prevlocal = open(prevfile, O_RDONLY); + if (prevlocal != -1) { + do { + prev_read = read(prevlocal, prev_buf, PREV_BUF_SIZE); + if (prev_read>0) { + if (fwrite_sha1_file(prev_buf, + 1, + prev_read, + NULL) == prev_read) { + prev_posn += prev_read; + } else { + prev_read = -1; + } + } + } while (prev_read > 0); + close(prevlocal); + } + unlink(prevfile); + + /* Reset inflate/SHA1 if there was an error reading the previous temp + file; also rewind to the beginning of the local file. */ + if (prev_read == -1) { + memset(&stream, 0, sizeof(stream)); + inflateInit(&stream); + SHA1_Init(&c); + if (prev_posn>0) { + prev_posn = 0; + lseek(local, SEEK_SET, 0); + } + } + + /* If we have successfully processed data from a previous fetch + attempt, only fetch the data we don't already have. */ + if (prev_posn>0) { + if (get_verbosely) + fprintf(stderr, + "Resuming fetch of object %s at byte %ld\n", + hex, prev_posn); + sprintf(range, "Range: bytes=%ld-", prev_posn); + range_header = curl_slist_append(range_header, range); + curl_easy_setopt(curl, CURLOPT_HTTPHEADER, range_header); + } + + /* Clear out the Range: header after performing the request, so + other curl requests don't inherit inappropriate header data */ + curl_result = curl_easy_perform(curl); + curl_easy_setopt(curl, CURLOPT_HTTPHEADER, no_range_header); + if (curl_result != 0) { + unlink(tmpfile); return error("%s", curl_errorstr); } @@ -413,20 +559,11 @@ static int fetch_object(struct alt_base *repo, unsigned char *sha1) unlink(tmpfile); return error("File %s has bad hash\n", hex); } - ret = link(tmpfile, filename); - if (ret < 0) { - /* Same Coda hack as in write_sha1_file(sha1_file.c) */ - ret = errno; - if (ret == EXDEV && !rename(tmpfile, filename)) - goto out; - } - unlink(tmpfile); - if (ret) { - if (ret != EEXIST) - return error("unable to write sha1 filename %s: %s", - filename, strerror(ret)); - } - out: + ret = relink_or_rename(tmpfile, filename); + if (ret) + return error("unable to write sha1 filename %s: %s", + filename, strerror(ret)); + pull_say("got %s\n", hex); return 0; } @@ -519,6 +656,7 @@ int main(int argc, char **argv) curl = curl_easy_init(); no_pragma_header = curl_slist_append(no_pragma_header, "Pragma:"); + no_range_header = curl_slist_append(no_range_header, "Range:"); curl_ssl_verify = getenv("GIT_SSL_NO_VERIFY") ? 0 : 1; curl_easy_setopt(curl, CURLOPT_SSL_VERIFYPEER, curl_ssl_verify);