[pacman-dev] [PATCH] Introduce alpm_dbs_update() function for parallel db updates
Anatol Pomozov
anatol.pomozov at gmail.com
Fri Mar 6 20:48:39 UTC 2020
Hi
On Fri, Mar 6, 2020 at 12:35 PM Anatol Pomozov <anatol.pomozov at gmail.com> wrote:
>
> This is an equivalent of alpm_db_update but for multiplexed (parallel)
> download. The difference is that this function accepts list of
> databases to update. And then ALPM internals download it in parallel if
> possible.
>
> Add a stub for _alpm_multi_download the function that will do parallel
> payloads downloads in the future.
>
> Introduce dload_payload->filepath field that contains url path to the
> file we download. It is like fileurl field but does not contain
> protocol/server part. The rationale for having this field is that with
> the curl multidownload the server retry logic is going to move to a curl
> callback. And the callback needs to be able to reconstruct the 'next'
> fileurl. One will be able to do it by getting the next server url from
> 'servers' list and then concat with filepath. Once the 'parallel download'
> refactoring is over 'fileurl' field will go away.
>
> Signed-off-by: Anatol Pomozov <anatol.pomozov at gmail.com>
> ---
> lib/libalpm/alpm.h | 2 +
> lib/libalpm/be_sync.c | 132 ++++++++++++++++++++++++++++++++++++++++++
> lib/libalpm/dload.c | 12 ++++
> lib/libalpm/dload.h | 5 ++
> 4 files changed, 151 insertions(+)
>
> diff --git a/lib/libalpm/alpm.h b/lib/libalpm/alpm.h
> index 93b97f44..eb0490eb 100644
> --- a/lib/libalpm/alpm.h
> +++ b/lib/libalpm/alpm.h
> @@ -1045,6 +1045,8 @@ int alpm_db_remove_server(alpm_db_t *db, const char *url);
> */
> int alpm_db_update(int force, alpm_db_t *db);
>
> +int alpm_dbs_update(alpm_handle_t *handle, alpm_list_t *dbs, int force, int failfast);
> +
> /** Get a package entry from a package database.
> * @param db pointer to the package database to get the package from
> * @param name of the package
> diff --git a/lib/libalpm/be_sync.c b/lib/libalpm/be_sync.c
> index aafed15d..cdb46bd9 100644
> --- a/lib/libalpm/be_sync.c
> +++ b/lib/libalpm/be_sync.c
> @@ -301,6 +301,138 @@ int SYMEXPORT alpm_db_update(int force, alpm_db_t *db)
> return ret;
> }
>
> +/** Update list of databases. This function may run updates in parallel.
> + *
> + * @param dbs a list of alpm_db_t to update.
> + */
> +int SYMEXPORT alpm_dbs_update(alpm_handle_t *handle, alpm_list_t *dbs, int force, UNUSED int failfast) {
One question I had initially is whether we need 'failfast' option for
parallel downloads. Failfast means once any error is detected ALPM
stops all the download streams right away and returns error back to
the client.
But now I am not sure if this option will be really useful. Currently
multi-download implementation waits for download transactions to
finish and only then returns to the client. It works just fine.
So I am thinking to remove failfast option unless someone has a strong
opinion we should keep it.
> + char *syncpath;
> + const char *dbext = handle->dbext;
> + alpm_list_t *i;
> + int ret = -1;
> + mode_t oldmask;
> + alpm_list_t *payloads = NULL;
> +
> + /* Sanity checks */
> + ASSERT(dbs != NULL, return -1);
> + handle->pm_errno = ALPM_ERR_OK;
> +
> + syncpath = get_sync_dir(handle);
> + ASSERT(syncpath != NULL, return -1);
> +
> + /* make sure we have a sane umask */
> + oldmask = umask(0022);
> +
> + for(i = dbs; i; i = i->next) {
> + alpm_db_t *db = i->data;
> + int dbforce = force;
> + struct dload_payload *payload = NULL;
> + size_t len;
> + int siglevel;
> +
> + if(!(db->usage & ALPM_DB_USAGE_SYNC)) {
> + continue;
> + }
> +
> + ASSERT(db != handle->db_local, RET_ERR(handle, ALPM_ERR_WRONG_ARGS, -1));
> + ASSERT(db->servers != NULL, RET_ERR(handle, ALPM_ERR_SERVER_NONE, -1));
> +
> + /* force update of invalid databases to fix potential mismatched database/signature */
> + if(db->status & DB_STATUS_INVALID) {
> + dbforce = 1;
> + }
> +
> + CALLOC(payload, 1, sizeof(*payload), RET_ERR(handle, ALPM_ERR_MEMORY, -1));
> +
> + /* set hard upper limit of 128MiB */
> + payload->max_size = 128 * 1024 * 1024;
> + ASSERT(db->servers != NULL, RET_ERR(handle, ALPM_ERR_SERVER_NONE, -1));
> + payload->servers = db->servers;
> +
> + /* print server + filename into a buffer */
> + len = strlen(db->treename) + strlen(dbext) + 1;
> + MALLOC(payload->filepath, len, GOTO_ERR(handle, ALPM_ERR_MEMORY, cleanup));
> + snprintf(payload->filepath, len, "%s%s", db->treename, dbext);
> + payload->handle = handle;
> + payload->force = dbforce;
> + payload->unlink_on_fail = 1;
> +
> + payloads = alpm_list_add(payloads, payload);
> +
> + siglevel = alpm_db_get_siglevel(db);
> + if(siglevel & ALPM_SIG_DATABASE) {
> + struct dload_payload *sig_payload;
> + CALLOC(sig_payload, 1, sizeof(*sig_payload), GOTO_ERR(handle, ALPM_ERR_MEMORY, cleanup));
> +
> + /* print filename into a buffer (leave space for separator and .sig) */
> + len = strlen(db->treename) + strlen(dbext) + 5;
> + MALLOC(sig_payload->filepath, len, goto cleanup);
> + snprintf(sig_payload->filepath, len, "%s%s.sig", db->treename, dbext);
> +
> + sig_payload->handle = handle;
> + sig_payload->force = dbforce;
> + sig_payload->errors_ok = (siglevel & ALPM_SIG_DATABASE_OPTIONAL);
> +
> + /* set hard upper limit of 16KiB */
> + sig_payload->max_size = 16 * 1024;
> + sig_payload->servers = db->servers;
> +
> + payloads = alpm_list_add(payloads, sig_payload);
> + }
> + }
> +
> + /* attempt to grab a lock */
> + if(_alpm_handle_lock(handle)) {
> + GOTO_ERR(handle, ALPM_ERR_HANDLE_LOCK, cleanup);
> + }
> +
> + ret = _alpm_multi_download(handle, payloads, syncpath);
> + if(ret < 0) {
> + goto cleanup;
> + }
> +
> + for(i = dbs; i; i = i->next) {
> + alpm_db_t *db = i->data;
> + if(!(db->usage & ALPM_DB_USAGE_SYNC)) {
> + continue;
> + }
> +
> + /* Cache needs to be rebuilt */
> + _alpm_db_free_pkgcache(db);
> +
> + /* clear all status flags regarding validity/existence */
> + db->status &= ~DB_STATUS_VALID;
> + db->status &= ~DB_STATUS_INVALID;
> + db->status &= ~DB_STATUS_EXISTS;
> + db->status &= ~DB_STATUS_MISSING;
> +
> + /* if the download failed skip validation to preserve the download error */
> + if(sync_db_validate(db) != 0) {
> + /* pm_errno should be set */
> + ret = -1;
> + }
> + }
> +
> +cleanup:
> + _alpm_handle_unlock(handle);
> +
> + if(ret == -1) {
> + /* pm_errno was set by the download code */
> + _alpm_log(handle, ALPM_LOG_DEBUG, "failed to sync dbs: %s\n",
> + alpm_strerror(handle->pm_errno));
> + } else {
> + handle->pm_errno = ALPM_ERR_OK;
> + }
> +
> + if(payloads) {
> + alpm_list_free_inner(payloads, (alpm_list_fn_free)_alpm_dload_payload_reset);
> + FREELIST(payloads);
> + }
> + free(syncpath);
> + umask(oldmask);
> + return ret;
> +}
> +
> /* Forward decl so I don't reorganize the whole file right now */
> static int sync_db_read(alpm_db_t *db, struct archive *archive,
> struct archive_entry *entry, alpm_pkg_t **likely_pkg);
> diff --git a/lib/libalpm/dload.c b/lib/libalpm/dload.c
> index 670da03d..7cd3e3a4 100644
> --- a/lib/libalpm/dload.c
> +++ b/lib/libalpm/dload.c
> @@ -636,6 +636,16 @@ int _alpm_download(struct dload_payload *payload, const char *localpath,
> }
> }
>
> +int _alpm_multi_download(alpm_handle_t *handle,
> + alpm_list_t *payloads /* struct dload_payload */,
> + const char *localpath)
> +{
> + (void)handle;
> + (void)payloads;
> + (void)localpath;
> + return 0;
> +}
> +
> static char *filecache_find_url(alpm_handle_t *handle, const char *url)
> {
> const char *filebase = strrchr(url, '/');
> @@ -738,6 +748,7 @@ void _alpm_dload_payload_reset(struct dload_payload *payload)
> FREE(payload->destfile_name);
> FREE(payload->content_disp_name);
> FREE(payload->fileurl);
> + FREE(payload->filepath);
> *payload = (struct dload_payload){0};
> }
>
> @@ -746,6 +757,7 @@ void _alpm_dload_payload_reset_for_retry(struct dload_payload *payload)
> ASSERT(payload, return);
>
> FREE(payload->fileurl);
> + FREE(payload->filepath);
> payload->initial_size += payload->prevprogress;
> payload->prevprogress = 0;
> payload->unlink_on_fail = 0;
> diff --git a/lib/libalpm/dload.h b/lib/libalpm/dload.h
> index 1e8f75f3..3eb7fbe1 100644
> --- a/lib/libalpm/dload.h
> +++ b/lib/libalpm/dload.h
> @@ -31,6 +31,7 @@ struct dload_payload {
> char *destfile_name;
> char *content_disp_name;
> char *fileurl;
> + char *filepath; /* download URL path */
> alpm_list_t *servers;
> long respcode;
> off_t initial_size;
> @@ -53,4 +54,8 @@ void _alpm_dload_payload_reset_for_retry(struct dload_payload *payload);
> int _alpm_download(struct dload_payload *payload, const char *localpath,
> char **final_file, const char **final_url);
>
> +int _alpm_multi_download(alpm_handle_t *handle,
> + alpm_list_t *payloads /* struct dload_payload */,
> + const char *localpath);
> +
> #endif /* ALPM_DLOAD_H */
> --
> 2.25.1
>
More information about the pacman-dev
mailing list